To see the other types of publications on this topic, follow the link: Remainiing useful Life.
Dissertations / Theses on the topic 'Remainiing useful Life'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Remainiing useful Life.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Agatensi, Luca. "Studio e Sperimentazione su Manutenzione Predittiva in ambito Manifatturiero." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20352/.
Full textAbstract:
La Manutenzione Predittiva - PdM è una pratica che viene utilizzata per ottimizzare i piani di manutenzione delle risorse, attraverso la previsione di guasti alle stesse, con tecniche che sfruttano la predizione di comportamenti sulla base di dati passati.
L'applicazione di PdM può portare numerosi vantaggi alle aziende, tra cui, la riduzione dei tempi di inattività e l'aumento della qualità del prodotto. Le aziende più interessate alla PdM sono quelle che si occupano di produzione manifatturiera, che è l'area di interesse in questa tesi, ma anche tutte quelle che fanno della efficienza degli impianti una loro prerogativa.
Questa tesi nasce con l'obiettivo di applicare la PdM su un caso reale, proposto da una azienda del territorio che lavora in ambito manifatturiero, sfruttando le moderne tecnologie di Machine Learning e Analitica Previsionale.
Nella tesi viene descritto approfonditamente il caso di studio in questione e la tecnologia che è stata utilizzata per portare a termine il progetto.
2
Wang, Tianyi. "Trajectory Similarity Based Prediction for Remaining Useful Life Estimation." University of Cincinnati / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1282574910.
Full text
3
Mishra, Madhav. "Model-based Prognostics for Prediction of Remaining Useful Life." Licentiate thesis, Luleå tekniska universitet, Drift, underhåll och akustik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-17263.
Full textAbstract:
Prognostics and healthmanagement (PHM) is an engineering discipline that aims to maintain the systembehaviour and function, and assure the mission success, safety andeffectiveness. Health management using a proper condition-based maintenance (CBM)deployment is a worldwide accepted technique and has grown very popular in manyindustries over the past decades. These techniques are relevant in environmentswhere the prediction of a failure and the prevention and mitigation of itsconsequences increase the profit and safety of the facilities concerned.Prognosis is the most critical part of this process and is nowadays recognizedas a key feature in maintenance strategies, since estimation of the remaininguseful life (RUL) is essential.PHM can provide a stateassessment of the future health of systems or components, e.g. when a degradedstate has been found. Using this technology, one can estimate how long it willtake before the equipment will reach a failure threshold, in future operatingconditions and future environmental conditions. This thesis focuses especiallyon physics-based prognostic approaches, which depend on a fundamentalunderstanding of the physical system in order to develop condition monitoringtechniques and to predict the RUL.The overall research objective of thework performed for this thesis has been to improve the accuracy and precisionof RUL predictions. The research hypothesis is that fusing the output of morethan one method will improve the accuracy and precision of the RUL estimation,by developing a new approach to prognostics that combines different remaininglife estimators and physics-based and data-driven methods. There are two waysof acquiring data for data-driven models, namely measurements of real systemsand syntactic data generation from simulations. The thesis deals with two casestudies, the first of which concerns the generation of synthetic data andindirect measurement of dynamic bearing loads and was performed atBillerudKorsäs paper mill at Karlsborg in Sweden. In this study the behaviourof a roller in a paper machine was analysed using the finite element method(FEM). The FEM model is a step towards the possibility of generating syntheticdata on different failure modes, and the possibility of estimating crucialparameters like dynamic bearing forces by combining real vibration measurementswith the FEM model. The second case study deals with the development ofprognostic methods for battery discharge estimation for Mars-based rovers. Herephysical models and measurement data were used in the prognostic development insuch a way that the degradation behaviour of the battery could be modelled andsimulated in order to predict the life-length. A particle filter turned out tobe the method of choice in performing the state assessment and predicting thefuture degradation. The method was then applied to a case study of batteriesthat provide power to the rover.Godkänd; 2015; 20151116 (madmis); Nedanstående person kommer att hålla licentiatseminarium för avläggande av teknologie licentiatexamen. Namn: Madhav Mishra Ämne: Drift och underhållsteknik/Operation and Maintenance Engineering Uppsats: Model-based Prognostics for Prediction of Remaining Useful Life Examinator: Professor Uday Kumar Institutionen för samhällsbyggnad och naturresurser Avdelning Drift, underhåll och akustik Luleå tekniska universitet Diskutant: Accos. Professor Jyoti Kumar Sinha University of Manchester, Aerospace and Civil Engineering, Manchester Tid: Torsdag 17 december 2015 kl 10.00 Plats: F1031, Luleå tekniska universitet
4
Liu, Gang. "A Study on Remaining Useful Life Prediction for Prognostic Applications." ScholarWorks@UNO, 2011. http://scholarworks.uno.edu/td/456.
Full textAbstract:
We consider the prediction algorithm and performance evaluation for prognostics and health management (PHM) problems, especially the prediction of remaining useful life (RUL) for the milling machine cutter and lithium ‐
ion battery. We modeled battery as a voltage source and internal resisters. By analyzing voltage change trend during discharge, we made the prediction of battery remain discharge time in one discharge cycle. By analyzing internal resistance change trend during multiple cycles, we were able to predict the battery remaining useful time during its life time. We showed that the battery rest profile is correlated with the RUL. Numerical results using the realistic battery aging data from NASA prognostics data repository yielded satisfactory performance for battery prognosis as measured by certain performance metrics. We built a battery test platform and simulated more usage pattern and verified the prediction algorithm. Prognostic performance metrics were used to compare different algorithms.
5
Bektas, Oguz. "An adaptive data filtering model for remaining useful life estimation." Thesis, University of Warwick, 2018. http://wrap.warwick.ac.uk/106052/.
Full textAbstract:
The field of Prognostics and Health Management is becoming ever more important in the modern maintenance era, with advanced techniques of automation and mechanisation becoming increasingly prevalent. Prognostic technology has promising abilities to forecast remaining useful life and likely future circumstances of complex systems. However, the evolution of data processing and its critical impact on remaining useful life predictions continually demand increasing development so as to meet higher performance levels. There is often a gap between the adequacy of prognostic pre-processing and the prediction methods. One way to reduce this gap would be to design an adaptive data processing method that can filter multidimensional condition monitoring data by incorporating useful information from multiple data sources. Due to the incomplete understanding on the multi-dimensional failure mechanisms and the collaboration between data sources, current prognostic methods lack the ability to deal effectively with complicated interdependency, multidimensional condition monitoring information and noisy data. Further conventional methods are unable to deal with these efficiently. The methodology proposed in this research handles these deficiencies by introducing a prognostic framework that allows the effective use of monitoring data from different resources to predict the lifetime of systems. The methodology presents a feed-forward neural network filtering approach for trajectory similarity based remaining useful life predictions. The extraction of health indicators is applied as a type of dynamic filtering, in which the time series having full operational conditions are used to train a neural network mapping between raw training inputs and a health indicator output. This trained network function is evaluated by repeating condition monitoring information from multiple data subsets. After the network filtering, the training trajectories are used as baselines to predict the future behaviours of test trajectories. The similarity between these data subsets compares the relationship between the historical performance deterioration of a system's prior operating period with a similar system's degradation behaviour. The proposed prognostic technique, together with dynamic data filtering and remaining useful estimation, holds the promise of increased prediction performance levels. The presented methodology was tested using the PHM08 data challenge provided by the Prognostics Centre of Excellence at NASA Ames Research Centre, and it achieved the overall leading score in the published literature.
6
Mosallam, Ahmed. "Remaining useful life estimation of critical components based on Bayesian Approaches." Thesis, Besançon, 2014. http://www.theses.fr/2014BESA2069/document.
Full textAbstract:
La construction de modèles de pronostic nécessite la compréhension du processus de dégradation des composants critiques surveillés afin d’estimer correctement leurs durées de fonctionnement avant défaillance. Un processus de d´dégradation peut être modélisé en utilisant des modèles de Connaissance issus des lois de la physique. Cependant, cette approche n´nécessite des compétences Pluridisciplinaires et des moyens expérimentaux importants pour la validation des modèles générés, ce qui n’est pas toujours facile à mettre en place en pratique. Une des alternatives consiste à apprendre le modèle de dégradation à partir de données issues de capteurs installés sur le système. On parle alors d’approche guidée par des données. Dans cette thèse, nous proposons une approche de pronostic guidée par des données. Elle vise à estimer à tout instant l’état de santé du composant physique et prédire sa durée de fonctionnement avant défaillance. Cette approche repose sur deux phases, une phase hors ligne et une phase en ligne. Dans la phase hors ligne, on cherche à sélectionner, parmi l’ensemble des signaux fournis par les capteurs, ceux qui contiennent le plus d’information sur la dégradation. Cela est réalisé en utilisant un algorithme de sélection non supervisé développé dans la thèse. Ensuite, les signaux sélectionnés sont utilisés pour construire différents indicateurs de santé représentant les différents historiques de données (un historique par composant). Dans la phase en ligne, l’approche développée permet d’estimer l’état de santé du composant test en faisant appel au filtre Bayésien discret. Elle permet également de calculer la durée de fonctionnement avant défaillance du composant en utilisant le classifieur k-plus proches voisins (k-NN) et le processus de Gauss pour la régression. La durée de fonctionnement avant défaillance est alors obtenue en comparant l’indicateur de santé courant aux indicateurs de santé appris hors ligne. L’approche développée à été vérifiée sur des données expérimentales issues de la plateforme PRO-NOSTIA sur les roulements ainsi que sur des données fournies par le Prognostic Center of Excellence de la NASA sur les batteries et les turboréacteursConstructing prognostics models rely upon understanding the degradation process of the monitoredcritical components to correctly estimate the remaining useful life (RUL). Traditionally, a degradationprocess is represented in the form of physical or experts models. Such models require extensiveexperimentation and verification that are not always feasible in practice. Another approach that buildsup knowledge about the system degradation over time from component sensor data is known as datadriven. Data driven models require that sufficient historical data have been collected.In this work, a two phases data driven method for RUL prediction is presented. In the offline phase, theproposed method builds on finding variables that contain information about the degradation behaviorusing unsupervised variable selection method. Different health indicators (HI) are constructed fromthe selected variables, which represent the degradation as a function of time, and saved in the offlinedatabase as reference models. In the online phase, the method estimates the degradation state usingdiscrete Bayesian filter. The method finally finds the most similar offline health indicator, to the onlineone, using k-nearest neighbors (k-NN) classifier and Gaussian process regression (GPR) to use it asa RUL estimator. The method is verified using PRONOSTIA bearing as well as battery and turbofanengine degradation data acquired from NASA data repository. The results show the effectiveness ofthe method in predicting the RUL
7
Siegel, David. "Evaluation of Health Assessment Techniques for Rotating Machinery." University of Cincinnati / OhioLINK, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1250282528.
Full text
8
Wengbrand, Frida, and Sofia Eriksson. "Remaining useful life of customer relationships : Valuation in accordance with IFRS 3." Thesis, Jönköping University, Jönköping International Business School, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-500.
Full textAbstract:
In the year of 2000 the European Commission adopted a communication
called EU Financial Reporting Strategy: the Way Forward. The communication intended to make all listed companies within the EU arrange their financial statements in accordance with
International Accounting Standards by 2005 at the latest. When the amendments of IFRS 3 was introduced in March 2004 it meant that companies from that moment on, when acquiring another company, have to allocate the part of the purchase price assignable to customer contracts and the related customer relationships as an intangible asset. IFRS 3 does not give any guidance whatsoever on how to
accomplish the above described allocation and estimate a true and fair value of customer contracts and relationships. Let alone any direction regarding the establishment of the remaining useful life of the customer relationships and contracts, which constitutes the
foundation of the fair valuation but also a true and fair view regarding amortizations. The purpose of this thesis is to examine how the establishments regarding remaining useful life of customer relationships and contracts have been done. Furthermore, the purpose of this thesis is to explain the decision process and motives that results in why management choose to apply the specific remaining useful life of customer relationships and contracts they do. This study has been carried out with a qualitative approach involving two listed group companies within three different industries, hence, six companies are involved in this thesis. Semi-structured telephone interviews have been made with the companies and the annual reports have been examined. In order to explain the actions behind the valuation and establishment process, the positive accounting theory has been used. None of the six companies taking part in this study have applied an outspoken method for the establishment of the remaining useful life of the customer relationships and contracts and only half of the companies have identified different customer groups. A relation can be identified between using an external consultant
and applying different remaining lives for different customer groups. All companies amortize the customer relationships and contracts on a straight-line basis. This can be explained by the positive accounting theory to some extent. All companies applied straight-line amortization even though some of them actually admit that a declining
balance would provide a fairer view. Furthermore, long amortization plans are used in some companies in order to decrease the amortization costs and hence increase the net income. Positive accounting has been applied in order to shift reported earnings.
Under år 2000 beslutade den Europeiska kommissionen om att anta ett
förslag som hette EU Financial Reporting Strategy: the Way Forward. Antagandet av förslaget innebar att alla noterade bolag inom EU skulle presentera sin redovisning och sina årsredovisningar i linje med bestämmelserna i IAS – International Accounting Standards senast år 2005. När lagändringarna i IFRS 3 introducerades i mars 2004 innebar det att noterade bolag vid företagsförvärv fortsättningsvis skulle allokera den del av köpeskillingen som är hänförlig till kundkontrakt och relaterade kundrelationer som immateriell tillgång i
balansräkningen. IFRS 3 ger ingen vägledning överhuvudtaget med avseende på hur bolagen ska genomföra den ovan beskrivna allokeringen och uppskatta ett rättvist värde på kundkontrakt och kundrelationer. Inte heller finns det någon anvisning angående fastställandet av livslängd på kundkontrakt och kundrelationer som i sin tur ligger till grund för en rättvis värdering och en rättvis avskrivningsplan.
Syftet med den här uppsatsen är att undersöka hur fastställandet av livslängden på kundrelationer och kundkontrakt har utförts. Syftet är även att förklara beslutsprocessen och de bakomliggande motiven till varför företagsledningen väljer att använda den livslängd på kundrelationer och kundkontrakt de faktiskt gör. Studien har genomförts med en kvalitativ ansats som har involverat två noterade
koncernbolag inom tre olika branscher, totalt har alltså sex bolag medverkat i uppsatsen. Semistrukturerade telefonintervjuer har gjorts med de involverade bolagen och även deras årsredovisningar har undersökts. För att kunna förklara handlandet angående värderingsprocessen och livslängdsprocessen har den positiva redovisningsteorin använts. Inget av de sex bolagen som medverkat i studien har använt sig av någon etablerad metod för att fastställa den återstående livslängden av kundrelationerna och kundkontrakten, och endast hälften av företagen har identifierat olika grupper av kunder. Ett samband har identifierats mellan att använda sig av en extern konsult vid fastställandet och att använda sig av olika återstående livslängder för olika kundgrupper. Alla sex företagen använder sig av linjär avskrivning på kundkontrakten och kundrelationerna. Detta kan till en viss gräns förklaras med positiv redovisningsteori. Alla företagen har använt sig av linjär avskrivning även om vissa av företagen till och med medger att
degressiv avskrivning skulle ge en mer rättvis bild. Dessutom har långa avskrivningstider använts i en del av företagen för att sänka avskrivningskostnaderna som i sin tur ökar resultatet. Positiv redovisningsteori har alltså använts för att flytta vinster till innevarande år.
9
Liang, Jie Jun Yi. "Novel framework for wind turbine fault diagnosis and remaining useful life prediction." Thesis, University of Macau, 2015. http://umaclib3.umac.mo/record=b3335776.
Full text
10
Oyharcabal, Astorga Nicolás. "Convolutional recurrent neural networks for remaining useful life prediction in mechanical systems." Tesis, Universidad de Chile, 2018. http://repositorio.uchile.cl/handle/2250/168514.
Full textAbstract:
Memoria para optar al título de Ingeniero Civil MecánicoLa determinación de la vida útil remanente (RUL del inglés "Remaining Useful Life") de una máquina, equipo, dispositivo o elemento mecánico, es algo en lo que se ha estado trabajando en los últimos años y que es crucial para el futuro de cualquier industria que así lo requiera. El continuo monitoreo de máquinas junto a una buena predicción de la RUL permite la minimización de costos de mantención y menor exposición a fallas. Sin embargo, los datos obtenidos del monitoreo son variados, tienen ruido, poseen un carácter secuencial y no siempre guardan estricta relación con la RUL, por lo que su estimación es un problema difícil. Es por ello que en la actualidad se utilizan distintas clases de Redes Neuronales y en particular, cuando se quiere modelar problemas de carácter secuencial, se utilizan las Redes Neuronales Recurrentes o RNN (del inglés "Recurrent Neural Network") como LSTM (del inglés "Long Short Term Memory") o JANET (del inglés "Just Another NETwork"), por su capacidad para identificar de forma autónoma patrones en secuencias temporales, pero también junto a estas últimas redes, también se utilizan alternativas que incorporan la Convolución como operación para cada célula de las RNN y que se conocen como ConvRNN (del inglés "Convolutional Recurrent Neural Network"). Estas últimas redes son mejores que sus pares convolucional y recurrentes en ciertos casos que requieren procesar secuencias de imágenes, y en el caso particular de este trabajo, series de tiempo de datos de monitoreo que son suavizados por la Convolución y procesados por la Recurrencia. El objetivo general de este trabajo es determinar la mejor opción de ConvRNN para la determinación de la RUL de un turbofan a partir de series de tiempo de la base de datos C-MAPSS. También se estudia cómo editar la base de datos para mejorar la precisión de una ConvRNN y la aplicación de la Convolución como una operación primaria en una serie de tiempo cuyos parámetros muestran el comportamiento de un turbofan. Para ello se programa una LSTM Convolucional, LSTM Convolucional Codificador-Decodificador, JANET Convolucional y JANET Convolucional Codificador-Decodificador. A partir de esto se encuentra que el modelo JANET Convolucional Codificador-Decodificador da los mejores resultados en cuanto a exactitud promedio y cantidad de parámetros necesarios (entre menos mejor pues se necesita menos memoria) para la red, siendo además capaz de asimilar la totalidad de las bases de datos C-MAPSS. Por otro lado, también se encuentra que la RUL de la base de datos puede ser modificada para datos antes de la falla. Para la programación y puesta en marcha de las diferentes redes, se utilizan los computadores del laboratorio de Integración de Confiabilidad y Mantenimiento Inteligente (ICMI) del Departamento de Ingeniería Mecánica de la Universidad de Chile.
11
Mohammadisohrabi, Ali. "Design and implementation of a Recurrent Neural Network for Remaining Useful Life prediction." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Find full textAbstract:
A key idea underlying many Predictive Maintenance solutions is Remaining Useful Life (RUL) of machine parts, and it simply involves a prediction on the time remaining before a machine part is likely to require repair or replacement. Nowadays, with respect to fact that the systems are getting more complex, the innovative Machine Learning and Deep Learning algorithms can be deployed to study the more sophisticated correlations in complex systems. The exponential increase in both data accumulation and processing power make the Deep Learning algorithms more desirable that before. In this paper a Long Short-Term Memory (LSTM) which is a Recurrent Neural Network is designed to predict the Remaining Useful Life (RUL) of Turbofan Engines. The dataset is taken from NASA data repository. Finally, the performance obtained by RNN is compared to the best Machine Learning algorithm for the dataset.
12
Tamssaouet, Ferhat. "Towards system-level prognostics : modeling, uncertainty propagation and system remaining useful life prediction." Thesis, Toulouse, INPT, 2020. http://www.theses.fr/2020INPT0079.
Full textAbstract:
Le pronostic est le processus de prédiction de la durée de vie résiduelle utile (RUL) des composants, sous-systèmes ou systèmes. Cependant, jusqu'à présent, le pronostic a souvent été abordé au niveau composant sans tenir compte des interactions entre les composants et l'impact de l'environnement, ce qui peut conduire à une mauvaise prédiction du temps de défaillance dans des systèmes complexes. Dans ce travail, une approche de pronostic au niveau du système est proposée. Cette approche est basée sur un nouveau cadre de modélisation : le modèle d'inopérabilité entrée-sortie (IIM), qui permet de prendre en compte les interactions entre les composants et les effets du profil de mission et peut être appliqué pour des systèmes hétérogènes. Ensuite, une nouvelle méthodologie en ligne pour l'estimation des paramètres (basée sur l'algorithme de la descente du gradient) et la prédiction du RUL au niveau système (SRUL) en utilisant les filtres particulaires (PF), a été proposée. En détail, l'état de santé des composants du système est estimé et prédit d'une manière probabiliste en utilisant les PF. En cas de divergence consécutive entre les estimations a priori et a posteriori de l'état de santé du système, la méthode d'estimation proposée est utilisée pour corriger et adapter les paramètres de l'IIM. Finalement, la méthodologie développée, a été appliquée sur un système industriel réaliste : le Tennessee Eastman Process, et a permis une prédiction du SRUL dans un temps de calcul raisonnablePrognostics is the process of predicting the remaining useful life (RUL) of components, subsystems, or systems. However, until now, the prognostics has often been approached from a component view without considering interactions between components and effects of the environment, leading to a misprediction of the complex systems failure time. In this work, a prognostics approach to system-level is proposed. This approach is based on a new modeling framework: the inoperability input-output model (IIM), which allows tackling the issue related to the interactions between components and the mission profile effects and can be applied for heterogeneous systems. Then, a new methodology for online joint system RUL (SRUL) prediction and model parameter estimation is developed based on particle filtering (PF) and gradient descent (GD). In detail, the state of health of system components is estimated and predicted in a probabilistic manner using PF. In the case of consecutive discrepancy between the prior and posterior estimates of the system health state, the proposed estimation method is used to correct and to adapt the IIM parameters. Finally, the developed methodology is verified on a realistic industrial system: The Tennessee Eastman Process. The obtained results highlighted its effectiveness in predicting the SRUL in reasonable computing time
13
SOUTO, MAIOR Caio Bezerra. "Remainig useful life prediction via empirical mode decomposition, wavelets and support vector machine." Universidade Federal de Pernambuco, 2017. https://repositorio.ufpe.br/handle/123456789/24930.
Full textAbstract:
Submitted by Pedro Barros (pedro.silvabarros@ufpe.br) on 2018-06-26T22:26:10Z
No. of bitstreams: 2
license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5)
DISSERTAÇÃO Caio Bezerra Souto Maior.pdf: 3924685 bytes, checksum: 6968386bf75059f45ee80306322d2a56 (MD5)Made available in DSpace on 2018-06-26T22:26:10Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) DISSERTAÇÃO Caio Bezerra Souto Maior.pdf: 3924685 bytes, checksum: 6968386bf75059f45ee80306322d2a56 (MD5) Previous issue date: 2017-02-21
CAPES
The useful life time of equipment is an important variable related to reliability and maintenance. The knowledge about the useful remaining life of operation system by means of a prognostic and health monitoring could lead to competitive advantage to the corporations. There are numbers of models trying to predict the reliability’s variable behavior, such as the remaining useful life, from different types of signal (e.g. vibration signal), however several could not be realistic due to the imposed simplifications. An alternative to those models are the learning methods, used when exist many observations about the variable. A well-known method is Support Vector Machine (SVM), with the advantage that is not necessary previous knowledge about neither the function’s behavior nor the relation between input and output. In order to achieve the best SVM’s parameters, a Particle Swarm Optimization (PSO) algorithm is coupled to enhance the solution. Empirical Mode Decomposition (EMD) and Wavelets rise as two preprocessing methods seeking to improve the input data analysis. In this paper, EMD and wavelets are used coupled with PSO+SVM to predict the rolling bearing Remaining Useful Life (RUL) from a vibration signal and compare with the prediction without any preprocessing technique. As conclusion, EMD models presented accurate predictions and outperformed the other models tested.
O tempo de vida útil de um equipamento é uma importante variável relacionada à confiabilidade e à manutenção, e o conhecimento sobre o tempo útil remanescente de um sistema em operação, por meio de um monitoramento do prognóstico de saúde, pode gerar vantagens competitivas para as corporações. Existem diversos modelos utilizados na tentativa de prever o comportamento de variáveis de confiabilidade, tal como a vida útil remanescente, a partir de diferentes tipos de sinais (e.g. sinal de vibração), porém alguns podem não ser realistas, devido às simplificações impostas. Uma alternativa a esses modelos são os métodos de aprendizado, utilizados quando se dispõe de diversas observações da variável. Um conhecido método de aprendizado supervisionado é o Support Vector Machine (SVM), que gera um mapeamento de funções de entrada-saída a partir de um conjunto de treinamento. Para encontrar os melhores parâmetros do SVM, o algoritmo de Particle Swarm Optimization (PSO) é acoplado para melhorar a solução. Empirical Mode Decomposition (EMD) e Wavelets são usados como métodos pré-processamento que buscam melhorar a qualidade dos dados de entrada para PSO+SVM. Neste trabalho, EMD e Wavelets foram usadas juntamente com PSO+SVM para estimar o tempo de vida útil remanescente de rolamentos a partir de sinais de vibração. Os resultados obtidos com e sem as técnicas de pré-processamento foram comparados. Ao final, é mostrado que modelos baseados em EMD apresentaram boa acurácia e superaram o desempenho dos outros modelos testados.
14
Tan, Hwei-Yang. "Statistical methods for the analysis of corrosion data for integrity assessments." Thesis, Brunel University, 2017. http://bura.brunel.ac.uk/handle/2438/15275.
Full textAbstract:
In the oil and gas industry, statistical methods have been used for corrosion analysis for various asset systems such as pipelines, storage tanks, and so on. However, few industrial standards and guidelines provide comprehensive stepwise procedures for the usage of statistical approaches for corrosion analysis. For example, the UK HSE (2002) report "Guidelines for the use of statistics for analysis of sample inspection of corrosion" demonstrates how statistical methods can be used to evaluate corrosion samples, but the methods explained in the document are very basic and do not consider risk factors such as pressure, temperature, design, external factors and other factors for the analyses. Furthermore, often the industrial practice that uses linear approximation on localised corrosion such as pitting is considered inappropriate as pitting growth is not uniform. The aim of this research is to develop an approach that models the stochastic behaviour of localised corrosion and demonstrate how the influencing factors can be linked to the corrosion analyses, for predicting the remaining useful life of components in oil and gas plants. This research addresses a challenge in industry practice. Non-destructive testing (NDT) and inspection techniques have improved in recent years making more and more data available to asset operators. However, this means that these data need to be processed to extract meaningful information. Increasing computer power has enabled the use of statistics for such data processing. Statistical software such as R and OpenBUGS is available to users to explore new and pragmatic statistical methods (e.g. regression models and stochastic models) and fully use the available data in the field. In this thesis, we carry out extreme value analysis to determine maximum defect depth of an offshore conductor pipe and simulate the defect depth using geometric Brownian motion in Chapter 2. In Chapter 3, we introduce a Weibull density regression that is based on a gamma transformation proportional hazards model to analyse the corrosion data of piping deadlegs. The density regression model takes multiple influencing factors into account; this model can be used to extrapolate the corrosion density of inaccessible deadlegs with data available from other piping systems. In Chapter 4, we demonstrate how the corrosion prediction models in Chapters 2 and 3 could be used to predict the remaining useful life of these components. Chapter 1 sets the background to the techniques used, and Chapter 5 presents concluding remarks based on the application of the techniques.
15
Mat, Jihin Rosmawati [Verfasser], and Dirk [Akademischer Betreuer] Söffker. "Structural Health Assessment and Remaining Useful Life Estimation for Industrial System / Rosmawati Mat Jihin ; Betreuer: Dirk Söffker." Duisburg, 2019. http://d-nb.info/119811150X/34.
Full text
16
Javed, kamran. "A robust and reliable data-driven prognostics approach based on Extreme Learning Machine and Fuzzy Clustering." Thesis, Besançon, 2014. http://www.theses.fr/2014BESA2021/document.
Full textAbstract:
Le pronostic industriel vise à étendre le cycle de vie d’un dispositif physique, tout en réduisant les couts d’exploitation et de maintenance. Pour cette raison, le pronostic est considéré comme un processus clé avec des capacités de prédiction. En effet, des estimations précises de la durée de vie avant défaillance d’un équipement, Remaining Useful Life (RUL), permettent de mieux définir un plan d’action visant à accroitre la sécurité, réduire les temps d’arrêt, assurer l’achèvement de la mission et l’efficacité de la production.Des études récentes montrent que les approches guidées par les données sont de plus en plus appliquées pour le pronostic de défaillance. Elles peuvent être considérées comme des modèles de type boite noire pour l’ étude du comportement du système directement `a partir des données de surveillance d’ état, pour définir l’ état actuel du système et prédire la progression future de défauts. Cependant, l’approximation du comportement des machines critiques est une tâche difficile qui peut entraîner des mauvais pronostic. Pour la compréhension de la modélisation du pronostic guidé par les données, on considère les points suivants. 1) Comment traiter les données brutes de surveillance pour obtenir des caractéristiques appropriées reflétant l’ évolution de la dégradation? 2) Comment distinguer les états de dégradation et définir des critères de défaillance (qui peuvent varier d’un cas `a un autre)? 3) Comment être sûr que les modèles définis seront assez robustes pour montrer une performance stable avec des entrées incertaines s’ écartant des expériences acquises, et seront suffisamment fiables pour intégrer des données inconnues (c’est `a dire les conditions de fonctionnement, les variations de l’ingénierie, etc.)? 4) Comment réaliser facilement une intégration sous des contraintes et des exigence industrielles? Ces questions sont des problèmes abordés dans cette thèse. Elles ont conduit à développer une nouvelle approche allant au-delà des limites des méthodes classiques de pronostic guidé par les donnéesPrognostics and Health Management (PHM) aims at extending the life cycle of engineerin gassets, while reducing exploitation and maintenance costs. For this reason,prognostics is considered as a key process with future capabilities. Indeed, accurateestimates of the Remaining Useful Life (RUL) of an equipment enable defining furtherplan of actions to increase safety, minimize downtime, ensure mission completion andefficient production.Recent advances show that data-driven approaches (mainly based on machine learningmethods) are increasingly applied for fault prognostics. They can be seen as black-boxmodels that learn system behavior directly from Condition Monitoring (CM) data, usethat knowledge to infer its current state and predict future progression of failure. However,approximating the behavior of critical machinery is a challenging task that canresult in poor prognostics. As for understanding, some issues of data-driven prognosticsmodeling are highlighted as follows. 1) How to effectively process raw monitoringdata to obtain suitable features that clearly reflect evolution of degradation? 2) Howto discriminate degradation states and define failure criteria (that can vary from caseto case)? 3) How to be sure that learned-models will be robust enough to show steadyperformance over uncertain inputs that deviate from learned experiences, and to bereliable enough to encounter unknown data (i.e., operating conditions, engineering variations,etc.)? 4) How to achieve ease of application under industrial constraints andrequirements? Such issues constitute the problems addressed in this thesis and have ledto develop a novel approach beyond conventional methods of data-driven prognostics
17
Espinoza, Villegas Pablo Andrés. "A simulation engine for ion-lithium battery packs in electric vehicles based on energetic autonomy and remaining useful life criteria." Tesis, Universidad de Chile, 2016. http://repositorio.uchile.cl/handle/2250/144139.
Full textAbstract:
Magíster en Ciencias de la Ingeniería, Mención EléctricaLos últimos desarrollos en baterías de ión-litio han permitido una verdadera revolución en la industria automotriz. Los vehículos eléctricos representan una porción del mercado que aumenta año a año. Estos vehículos operan bajo condiciones variables, requiriendo de bancos de baterías para hacer frente a las respectivas demandas de torque y potencia. En este trabajo construimos un simulador que, dado el tamaño del banco, determina cuando una recarga (autonomía) o reemplazo del banco (vida útil remanente) son necesarios. Con este fin estudiamos los indicadores de Estado-de-Carga (SOC), y Estado-de-Salud (SOH), usando modelos en espacio de estados discreto. Las predicciones se basan en una caracterización probabilística de los perfiles de uso en un vehículo eléctrico, que a su vez son una función de entradas genéricas, e.g. el mapa de la misión, las características mecánicas del vehículo, perfiles de conducción y configuración del banco de baterías. En nuestro enfoque estocástico, el pronóstico para el SOC y SOH son generados en un esquema basado en filtro de partículas, con medidas de riesgo e intervalos de confianza obtenidos tanto para el fin-de- la-descarga (en cada ciclo) como para el fin-de-vida-útil (reemplazo). Estos esquemas se benefician de la incorporación de metamodelos para la resistencia óh- mica interna y la eficiencia de Coulomb del banco. El primero depende de la demanda de corriente y el SOC, mientras el segundo se basa en la magnitud de la corriente y la profundi- dad de cada descarga. Ambos metamodelos son incluidos dentro del esquema del SOC/SOH, i) efectivamente introduciendo nueva fenomenología en ellos, y ii) proveyendo de una conex- ión entre el SOC/SOH y el cómo cada descarga afecta el estado de salud del banco de baterías como un todo. También presentamos una metodología para experimentos de laboratorio que son capaces de determinar estas cantidades empíricamente en baterías de ión-litio. Consideramos efectos ignorados hasta ahora en este tipo de modelos empíricos, i.e. cómo las condiciones de operación en una descarga conciernen al pronóstico de la vida útil rema- nente, y cómo las dependencias de la impedancia interna afectan la autonomía del vehículo. Un sub-producto de este trabajo es el mejoramiento del rango de opciones, modularidad y velocidad de ejecución de algoritmos. Finalmente, establecemos aquí las bases para trabajo futuro en diseño óptimo de bancos de baterías en función de perfiles de uso particulares.
18
Yang, Lei. "Methodology of Prognostics Evaluation for Multiprocess Manufacturing Systems." University of Cincinnati / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1298043095.
Full text
19
Rodriguez, obando Diego Jair. "From Deterioration Modeling to Remaining Useful Life Control : a comprehensive framework for post-prognosis decision-making applied to friction drive systems." Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAT086/document.
Full textAbstract:
La durée de vie utile résiduelle (RUL) peut être simplement définie comme une prédiction du temps restant pendant lequel un système est capable d'exécuter sa fonction prévue ; elle est mesurée à partir de l'instant présent jusqu'à la défaillance finale. Cette durée prévue dépend principalement de l'état de détérioration des composants du système et de leurs conditions de fonctionnement futures prévues. Ainsi, la prédiction de la RUL est un processus incertain et son contrôle n'est pas une tâche triviale. En général, le but de la prévision de la RUL est d'influencer la prise de décision pour le système. Dans cette thèse, on a présenté un cadre compréhensible pour le contrôle de la RUL. Les incertitudes du modèle ainsi que les perturbations du système ont été prises en compte dans le cadre proposé. Des questions telles que le traitement de l'incertitude et l'inclusion d'objectifs RUL dans la stratégie de contrôle sont étudiées, depuis la modélisation jusqu'à une architecture de contrôle globale finale. On a montré que l'on peut prédire la RUL à partir d'une estimation appropriée de la détérioration et d'hypothèses sur les conditions de fonctionnement futures. Les systèmes d'entraînement par friction sont utilisés pour illustrer l'utilité de l'architecture globale susmentionnée. Pour ce type de système, le frottement est à la fois source du mouvement et source de la détérioration. Ce double caractéristique de frottement est une motivation pour contrôler automatiquement la détérioration du système en maintenant un compromis entre les exigences de mouvement et les valeurs RUL souhaitées. Dans cette thèse, un nouveau modèle orienté contrôle pour les systèmes d'entraînement par friction, qui inclut un modèle dynamique de la détérioration, est proposé. Le degré de détérioration est considéré en fonction de l'énergie dissipée, à la surface de contact, pendant la transmission mécanique de puissance. Une approche est proposée pour estimer l'état actuel de la détérioration d'un système d'entraînement par friction. L'approche est basée sur un Filtre de Kalman Etendu (EKF en anglais) qui utilise un modèle augmenté incluant le système mécanique dynamique et la dynamique de détérioration. L'EKF fournit également des intervalles qui incluent sûrement la valeur de détérioration réelle avec une valeur de probabilité. Une nouvelle architecture de commande de la RUL est proposée, elle comprend : un système de surveillance de l'état de détérioration (par exemple l'EKF proposé), un estimateur de l'état de fonctionnement du système, un système de commande de la RUL et un principe actionneur de la RUL. L'estimateur des conditions de fonctionnement est basé sur l'hypothèse qu'il est possible de quantifier certaines caractéristiques des exigences de mouvement, par exemple le rapport cyclique des couples moteur. Le contrôleur RUL utilise une fonction de coût qui pondère les exigences de mouvement et les valeurs RUL souhaitées pour modifier un filtre à paramètres variables, utilisé ici comme principe actionneur RUL. Le principe actionneur RUL est basé sur une modification des couples exigés, provenant d'un éventuel système de contrôle de mouvement. Les résultats préliminaires montrent qu'il est possible de contrôler la RUL, selon le cadre théorique proposéRemaining Useful Lifetime (RUL) can be simply defined as a prediction of the remaining time that a system is able to perform its intended function, from the current time to the final failure. This predicted time mostly depends on the state of deterioration of the system components and their expected future operating conditions. Thus, the RUL prediction is an uncertain process and its control is not trivial task.In general, the purpose for predicting the RUL is to influence decision-making for the system. In this dissertation a comprehensive framework for controlling the RUL is presented. Model uncertainties as well as system disturbances have been considered into the proposed framework. Issues as uncertainty treatment and inclusion of RUL objectives in the control strategy are studied from the modeling until a final global control architecture. It is shown that the RUL can be predicted from a suitable estimation of the deterioration, and from hypothesis on the future operation conditions. Friction drive systems are used for illustrating the usefulness of the aforementioned global architecture. For this kind of system, the friction is the source of motion and at the same time the source of deterioration. This double characteristic of friction is a motivation for controlling automatically the deterioration of the system by keeping a trade-off, between motion requirements and desired RUL values. In this thesis, a new control-oriented model for friction drive systems, which includes a dynamical model of the deterioration is proposed. The amount of deterioration has been considered as a function of the dissipated energy, at the contact surface, during the mechanical power transmission. An approach to estimate the current deterioration condition of a friction drive system is proposed. The approach is based on an Extended Kalman Filter (EKF) which uses an augmented model including the mechanical dynamical system and the deterioration dynamics. At every time instant, the EKF also provides intervals which surely includes the actual deterioration value which a given probability. A new architecture for controlling the RUL is proposed, which includes: a deterioration condition monitoring system (for instance the proposed EKF), a system operation condition estimator, a RUL controller system, and a RUL actuation principle. The operation condition estimator is based on the assumption that it is possible quantify certain characteristics of the motion requirements, for instance the duty cycle of motor torques. The RUL controller uses a cost function that weights the motion requirements and the desired RUL values to modify a varying-parameter filter, used here as the RUL-actuating-principle. The RUL-actuating-principle is based on a modification of the demanded torques, coming from a possible motion controller system. Preliminary results show that it is possible to control de RUL according to the proposed theoretical framework
20
Santini, Thomas. "Contribution à l'étude de la fiabilité des MOSFETs en carbure de silicium." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSEI021/document.
Full textAbstract:
Ces dernières années ont vu apparaître sur le marché les premiers transistors de puissance de type MOSFET en carbure de silicium. Ce type de composant est particulièrement adapté à la réalisation d’équipement électrique à haut rendement et capable de fonctionner à haute température. Néanmoins, la question de la fiabilité doit être posée avant de pouvoir envisager la mise en œuvre de ces composants dans des applications aéronautiques ou spatiales. Les mécanismes de défaillance liés à l’oxyde de grille ont pendant longtemps retardé la mise sur le marché des transistors à grille isolée en carbure de silicium. Cette étude s’attache donc à estimer la durée de vie des MOSFET SiC de 1ére génération. Dans un premier temps, le mécanisme connu sous le nom de Time Dependent Dielectric Breakdown(TDDB) a été étudié au travers de résultats expérimentaux issus de la bibliographie. Notre analyse nous a permis de justifier de l’emploi d’une loi de Weibull pour modéliser la distribution des temps à défaillance issue de ces tests. Les résultats nous ont également permis de confirmer l’amélioration significative de la fiabilité de ces structures vis-à-vis de ce mécanisme. Dans un second temps, l’impact du mécanisme d’instabilité de la tension de seuil sur la fiabilité a été quantifié au travers de tests de vieillissement de type HTGB. Les données de dégradation ainsi collectées ont été modélisées à l’aide d’un processus gamma non-homogène, qui nous a permis de prendre en compte la variabilité entre les composants testés dans des conditions identiques et de proposer des facteurs d’accélération en tension et en température pour ce mécanisme. Enfin, ces travaux ont permis d’ouvrir la voie à la mise en œuvre d’outils de pronostic de la durée de vie résiduelle pour les équipements électriquesRecent years have seen SiC MOSFET reach the industrial market. This type of device is particularly adapted to the design of power electronics equipment with high efficiency and high reliability capable to operate in high ambient temperature. Nevertheless the question of the SiC MOSFET reliability has to be addressed prior to considering the implementation of such devices in an aeronautic application. The failure mechanisms linked to the gate oxide of the SiC MOSFET have for a long time prevented the introduction of the device. In this manuscript we propose to study the reliability of the first generation of SiC MOSFET. First, the mechanism known as the Time–Dependent Dielectric Breakdown is studied through experimental results extracted from literature. Our study shows the successful application of a Weibull law to model the time-to-failure distribution extracted from the accelerated tests. The results show also a significant improvement of the SiC MOSFET structure with respect to this phenomenon. In a second step, the impact of the threshold voltage instability is quantified through accelerated tests known as High Temperature Gate Bias. The collected degradation data are modeled using a non-homogeneous Gamma process. This approach allows taking into account the variability between devices tested under the same conditions. Acceleration factors have been proposed with respect to temperature and gate voltage. Eventually the study delivers a primary estimation of the remaining useful lifetime of the SiC MOSFET in a typical aeronautic application
21
Maré, Charl Francois. "An investigation of CFD simulation for estimation of turbine RUL." Diss., University of Pretoria, 2018. http://hdl.handle.net/2263/69152.
Full textAbstract:
Turbines encounter blade failures due to fatigue and creep. It has been shown in the literature that the primary cause of steam turbine blade failures worldwide can be ascribed to fatigue in low pressure (LP) turbine blades. The failure and damage to these blades can lead to catastrophic consequences. Some utilities use empirical methods to determine the forces experienced by turbine blades but desire more accurate methods. The inaccurate
prediction of high-cycle fatigue (HCF), thermal durability and stage performance
is introduced when one does not consider blade row interaction. Blade row interactions can, however, be accounted for by means of computational fluid dynamics (CFD). Furthermore, modern high- fidelity CFD tools would be able to contribute greatly in predicting the forces experienced by turbine blades.
Numerical tools such as CFD and nite element analysis (FEA) can greatly contribute to the estimation of the remaining useful life (RUL) of turbine blades. However, in this estimation process, there are various uncertainties and aspects that affect the estimated RUL. Understanding the sensitivity of the estimated RUL to these various uncertainties and aspects is of great importance if RUL is to be estimated as accurately as possible.
In this dissertation, a sensitivity analysis is performed with the purpose of establishing the sensitivity of the estimated RUL of the last stage rotor of an LP steam turbine, to the number of harmonics used in a nonlinear harmonic (NLH) CFD simulation. The sensitivity of the estimated RUL is evaluated in the HCF regime, where the cyclic stresses occur below the yield strength of the turbine blade. A CFD model, FE model, and fatigue model were therefore developed in such a manner that would suffice, regarding the purpose of the sensitivity analysis. The CFD model is validated by comparing the predicted CFD power to that of actual generated power of a dual 100MW LP steam turbine. The sensitivity analysis is performed for 3 operation conditions, and for each operational condition the aerodynamic forces were computed using 1, 2, and 3 harmonics in an NLH simulation.
The estimation process considers a weak coupling between the CFD model and FE model. NLH simulations are firstly performed to calculate the unsteady static surface pressure distributions on the last stage rotor. This is followed by the mapping thereof to the FE model, for which a transient structural analysis is performed. Finally, the RUL is estimated by performing a fatigue analysis on the stress history obtained from the transient structural analysis.
Based on the results of the sensitivity analysis, the following recommendations were made, from a conservative point of view. Firstly, in general, if the RUL is to be estimated with reasonable accuracy, just using 1 harmonic in an NLH simulation will not be sufficient and 2 harmonics should be used. Secondly, if the RUL has to be estimated with high accuracy, 3 harmonics should be used.Dissertation (MEng)--University of Pretoria, 2018.
National Research Foundation (NRF)
Mechanical and Aeronautical Engineering
MEng
Unrestricted
22
Spataru, Mihai. "Battery aging diagnosis and prognosis for Hybrid Electrical Vehicles Applications." The Ohio State University, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=osu1366364019.
Full text
23
Tian, Wenmeng. "Monitoring and Prognostics for Broaching Processes by Integrating Process Knowledge." Diss., Virginia Tech, 2017. http://hdl.handle.net/10919/78680.
Full textAbstract:
With the advancement of sensor technology and data processing capacities, various types of high volume data are available for process monitoring and prognostics in manufacturing systems. In a broaching process, a multi-toothed broaching tool removes material from the workpiece by sequential engagement and disengagement of multiple cutting edges. The quality of the final part, including the geometric integrity and surface finish, is highly dependent upon the broaching tool condition. Though there has been a considerable amount of research on tool condition monitoring and prognostics for various machining processes, the broaching process is unique in the following aspects: 1) a broaching process involves multiple cutting edges, which jointly contribute to the final part quality; 2) the resharpening and any other process adjustments to the tool can only be performed with the whole broaching tool or at least a whole segment of the tool replaced.
The overarching goal of this research is to explore how engineering knowledge can be used to improve process monitoring and prognostics for a complex manufacturing process like broaching. This dissertation addresses the needs for developing new monitoring and prognostics approaches based on various types of data. Specifically, the research effort focuses on 1) the use of in-situ force profile data for real-time process monitoring and fault diagnosis, 2) degradation characterization for broaching processes on an individual component level based on image processing; and 3) system-level degradation modeling and remaining useful life prediction for broaching processes based on multiple images.Ph. D.
24
Diallo, Ousmane Nasr. "A data analytics approach to gas turbine prognostics and health management." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/42845.
Full textAbstract:
As a consequence of the recent deregulation in the electrical power production industry, there has been a shift in the traditional ownership of power plants and the way they are operated. To hedge their business risks, the many new private entrepreneurs enter into long-term service agreement (LTSA) with third parties for their operation and maintenance activities. As the major LTSA providers, original equipment manufacturers have invested huge amounts of money to develop preventive maintenance strategies to minimize the occurrence of costly unplanned outages resulting from failures of the equipments covered under LTSA contracts. As a matter of fact, a recent study by the Electric Power Research Institute estimates the cost benefit of preventing a failure of a General Electric 7FA or 9FA technology compressor at $10 to $20 million.
Therefore, in this dissertation, a two-phase data analytics approach is proposed to use the existing monitoring gas path and vibration sensors data to first develop a proactive strategy that systematically detects and validates catastrophic failure precursors so as to avoid the failure; and secondly to estimate the residual time to failure of the unhealthy items. For the first part of this work, the time-frequency technique of the wavelet packet transforms is used to de-noise the noisy sensor data. Next, the time-series signal of each sensor is decomposed to perform a multi-resolution analysis to extract its features. After that, the probabilistic principal component analysis is applied as a data fusion technique to reduce the number of the potentially correlated multi-sensors measurement into a few uncorrelated principal components. The last step of the failure precursor detection methodology, the anomaly detection decision, is in itself a multi-stage process. The obtained principal components from the data fusion step are first combined into a one-dimensional reconstructed signal representing the overall health assessment of the monitored systems. Then, two damage indicators of the reconstructed signal are defined and monitored for defect using a statistical process control approach. Finally, the Bayesian evaluation method for hypothesis testing is applied to a computed threshold to test for deviations from the healthy band.
To model the residual time to failure, the anomaly severity index and the anomaly duration index are defined as defects characteristics. Two modeling techniques are investigated for the prognostication of the survival time after an anomaly is detected: the deterministic regression approach, and parametric approximation of the non-parametric Kaplan-Meier plot estimator. It is established that the deterministic regression provides poor prediction estimation. The non parametric survival data analysis technique of the Kaplan-Meier estimator provides the empirical survivor function of the data set comprised of both non-censored and right censored data. Though powerful because no a-priori predefined lifetime distribution is made, the Kaplan-Meier result lacks the flexibility to be transplanted to other units of a given fleet. The parametric analysis of survival data is performed with two popular failure analysis distributions: the exponential distribution and the Weibull distribution. The conclusion from the parametric analysis of the Kaplan-Meier plot is that the larger the data set, the more accurate is the prognostication ability of the residual time to failure model.
25
Le, Thanh Trung. "Contribution to deterioration modeling and residual life estimation based on condition monitoring data." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAT099/document.
Full textAbstract:
La maintenance prédictive joue un rôle important dans le maintien des systèmes de production continue car elle peut aider à réduire les interventions inutiles ainsi qu'à éviter des pannes imprévues. En effet, par rapport à la maintenance conditionnelle, la maintenance prédictive met en œuvre une étape supplémentaire, appelée le pronostic. Les opérations de maintenance sont planifiées sur la base de la prédiction des états de détérioration futurs et sur l'estimation de la vie résiduelle du système. Dans le cadre du projet européen FP7 SUPREME (Sustainable PREdictive Maintenance for manufacturing Equipment en Anglais), cette thèse se concentre sur le développement des modèles de détérioration stochastiques et sur des méthodes d'estimation de la vie résiduelle (Remaining Useful Life – RUL en anglais) associées pour les adapter aux cas d'application du projet. Plus précisément, les travaux présentés dans ce manuscrit sont divisés en deux parties principales. La première donne une étude détaillée des modèles de détérioration et des méthodes d'estimation de la RUL existant dans la littérature. En analysant leurs avantages et leurs inconvénients, une adaptation d’une approche de l'état de l'art est mise en œuvre sur des cas d'études issus du projet SUPREME et avec les données acquises à partir d’un banc d'essai développé pour le projet. Certains aspects pratiques de l’implémentation, à savoir la question de l'échange d'informations entre les partenaires du projet, sont également détaillées dans cette première partie. La deuxième partie est consacrée au développement de nouveaux modèles de détérioration et les méthodes d'estimation de la RUL qui permettent d'apporter des éléments de solutions aux problèmes de modélisation de détérioration et de prédiction de RUL soulevés dans le projet SUPREME. Plus précisément, pour surmonter le problème de la coexistence de plusieurs modes de détérioration, le concept des modèles « multi-branche » est proposé. Dans le cadre de cette thèse, deux catégories des modèles de type multi-branche sont présentées correspondant aux deux grands types de modélisation de l'état de santé des système, discret ou continu. Dans le cas discret, en se basant sur des modèles markoviens, deux modèles nommés Mb-HMM and Mb-HsMM (Multi-branch Hidden (semi-)Markov Model en anglais) sont présentés. Alors que dans le cas des états continus, les systèmes linéaires à sauts markoviens (JMLS) sont mis en œuvre. Pour chaque modèle, un cadre à deux phases est implémenté pour accomplir à la fois les tâches de diagnostic et de pronostic. A travers des simulations numériques, nous montrons que les modèles de type multi-branche peuvent donner des meilleures performances pour l'estimation de la RUL par rapport à celles obtenues par des modèles standards mais « mono-branche »Predictive maintenance plays a crucial role in maintaining continuous production systems since it can help to reduce unnecessary intervention actions and avoid unplanned breakdowns. Indeed, compared to the widely used condition-based maintenance (CBM), the predictive maintenance implements an additional prognostics stage. The maintenance actions are then planned based on the prediction of future deterioration states and residual life of the system. In the framework of the European FP7 project SUPREME (Sustainable PREdictive Maintenance for manufacturing Equipment), this thesis concentrates on the development of stochastic deterioration models and the associated remaining useful life (RUL) estimation methods in order to be adapted in the project application cases. Specifically, the thesis research work is divided in two main parts. The first one gives a comprehensive review of the deterioration models and RUL estimation methods existing in the literature. By analyzing their advantages and disadvantages, an adaption of the state of the art approaches is then implemented for the problem considered in the SUPREME project and for the data acquired from a project's test bench. Some practical implementation aspects, such as the issue of delivering the proper RUL information to the maintenance decision module are also detailed in this part. The second part is dedicated to the development of innovative contributions beyond the state-of-the-are in order to develop enhanced deterioration models and RUL estimation methods to solve original prognostics issues raised in the SUPREME project. Specifically, to overcome the co-existence problem of several deterioration modes, the concept of the "multi-branch" models is introduced. It refers to the deterioration models consisting of different branches in which each one represent a deterioration mode. In the framework of this thesis, two multi-branch model types are presented corresponding to the discrete and continuous cases of the systems' health state. In the discrete case, the so-called Multi-branch Hidden Markov Model (Mb-HMM) and the Multi-branch Hidden semi-Markov model (Mb-HsMM) are constructed based on the Markov and semi-Markov models. Concerning the continuous health state case, the Jump Markov Linear System (JMLS) is implemented. For each model, a two-phase framework is carried out for both the diagnostics and prognostics purposes. Through numerical simulations and a case study, we show that the multi-branch models can help to take into account the co-existence problem of multiple deterioration modes, and hence give better performances in RUL estimation compared to the ones obtained by standard "single branch" models
26
Nyman, Jacob. "Machinery Health Indicator Construction using Multi-objective Genetic Algorithm Optimization of a Feed-forward Neural Network based on Distance." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-298084.
Full textAbstract:
Assessment of machine health and prediction of future failures are critical for maintenance decisions. Many of the existing methods use unsupervised techniques to construct health indicators by measuring the disparity between the current state and either the healthy or the faulty states of the system. This approach can work well, but if the resulting health indicators are insufficient there is no easy way to steer the algorithm towards better ones. In this thesis a new method for health indicator construction is investigated that aims to solve this issue. It is based on measuring distance after transforming the sensor data into a new space using a feed-forward neural network. The feed-forward neural network is trained using a multi-objective optimization algorithm, NSGA-II, to optimize criteria that are desired in a health indicator. Thereafter the constructed health indicator is passed into a gated recurrent unit for remaining useful life prediction. The approach is compared to benchmarks on the NASA Turbofan Engine Degradation Simulation dataset and in regard to the size of the neural networks, the model performs relatively well, but does not outperform the results reported by a few of the more recent methods. The method is also investigated on a simulated dataset based on elevator weights with two independent failures. The method is able to construct a single health indicator with a desirable shape for both failures, although the latter estimates of time until failure are overestimated for the more rare failure type. On both datasets the health indicator construction method is compared with a baseline without transformation function and does in both cases outperform it in terms of the resulting remaining useful life prediction error using the gated recurrent unit. Overall, the method is shown to be flexible in generating health indicators with different characteristics and because of its properties it is adaptive to different remaining useful life prediction methods.Estimering av maskinhälsa och prognos av framtida fel är kritiska steg för underhållsbeslut. Många av de befintliga metoderna använder icke-väglett (unsupervised) lärande för att konstruera hälsoindikatorer som beskriver maskinens tillstånd över tid. Detta sker genom att mäta olikheter mellan det nuvarande tillståndet och antingen de friska eller fallerande tillstånden i systemet. Det här tillvägagångssättet kan fungera väl, men om de resulterande hälsoindikatorerna är otillräckliga så finns det inget enkelt sätt att styra algoritmen mot bättre. I det här examensarbetet undersöks en ny metod för konstruktion av hälsoindikatorer som försöker lösa det här problemet. Den är baserad på avståndsmätning efter att ha transformerat indatat till ett nytt vektorrum genom ett feed-forward neuralt nätverk. Nätverket är tränat genom en multi-objektiv optimeringsalgoritm, NSGA-II, för att optimera kriterier som är önskvärda hos en hälsoindikator. Därefter används den konstruerade hälsoindikatorn som indata till en gated recurrent unit (ett neuralt nätverk som hanterar sekventiell data) för att förutspå återstående livslängd hos systemet i fråga. Metoden jämförs med andra metoder på ett dataset från NASA som simulerar degradering hos turbofan-motorer. Med avseende på storleken på de använda neurala nätverken så är resultatet relativt bra, men överträffar inte resultaten rapporterade från några av de senaste metoderna. Metoden testas även på ett simulerat dataset baserat på elevatorer som fraktar säd med två oberoende fel. Metoden lyckas skapa en hälsoindikator som har en önskvärd form för båda felen. Dock så överskattar den senare modellen, som använde hälsoindikatorn, återstående livslängd vid estimering av det mer ovanliga felet. På båda dataseten jämförs metoden för hälsoindikatorkonstruktion med en basmetod utan transformering, d.v.s. avståndet mäts direkt från grund-datat. I båda fallen överträffar den föreslagna metoden basmetoden i termer av förutsägelsefel av återstående livslängd genom gated recurrent unit- nätverket. På det stora hela så visar sig metoden vara flexibel i skapandet av hälsoindikatorer med olika attribut och p.g.a. metodens egenskaper är den adaptiv för olika typer av metoder som förutspår återstående livslängd.
27
Alghassi, Alireza. "Prognostics and health management of power electronics." Thesis, Cranfield University, 2016. http://dspace.lib.cranfield.ac.uk/handle/1826/10968.
Full textAbstract:
Prognostics and health management (PHM) is a major tool enabling systems to evaluate their reliability in real-time operation. Despite ground-breaking advances in most engineering and scientific disciplines during the past decades, reliability engineering has not seen significant breakthroughs or noticeable advances. Therefore, self-awareness of the embedded system is also often required in the sense that the system should be able to assess its own health state and failure records, and those of its main components, and take action appropriately. This thesis presents a radically new prognostics approach to reliable system design that will revolutionise complex power electronic systems with robust prognostics capability enhanced Insulated Gate Bipolar Transistors (IGBT) in applications where reliability is significantly challenging and critical. The IGBT is considered as one of the components that is mainly damaged in converters and experiences a number of failure mechanisms, such as bond wire lift off, die attached solder crack, loose gate control voltage, etc. The resulting effects mentioned are complex. For instance, solder crack growth results in increasing the IGBT’s thermal junction which becomes a source of heat turns to wire bond lift off. As a result, the indication of this failure can be seen often in increasing on-state resistance relating to the voltage drop between on-state collector-emitter. On the other hand, hot carrier injection is increased due to electrical stress. Additionally, IGBTs are components that mainly work under high stress, temperature and power consumptions due to the higher range of load that these devices need to switch. This accelerates the degradation mechanism in the power switches in discrete fashion till reaches failure state which fail after several hundred cycles. To this end, exploiting failure mechanism knowledge of IGBTs and identifying failure parameter indication are background information of developing failure model and prognostics algorithm to calculate remaining useful life (RUL) along with ±10% confidence bounds. A number of various prognostics models have been developed for forecasting time to failure of IGBTs and the performance of the presented estimation models has been evaluated based on two different evaluation metrics. The results show significant improvement in health monitoring capability for power switches. Furthermore, the reliability of the power switch was calculated and conducted to fully describe health state of the converter and reconfigure the control parameter using adaptive algorithm under degradation and load mission limitation. As a result, the life expectancy of devices has been increased. These all allow condition-monitoring facilities to minimise stress levels and predict future failure which greatly reduces the likelihood of power switch failures in the first place.
28
Sajeva, Lisa. "Predizione del tempo rimanente di vita di un impianto mediante Hidden Markow Model." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/13846/.
Full textAbstract:
In this thesis we investigate the main methods used in the literature for the automation of conditio-base maintenance and then see a pratical application concerning bearing system. In the specifics we first analyze the row signal of vibration decomposing whit a wavelet packet transform then, we select the best level and index in term of characteristics. For create a model of failure we use the method of Hidden Markov Model. At least we compare the model generated with other level and index of decomposition to demonstrate that our choice was the best.
29
Voronin, Artyom. "Možnosti prediktivní údržby pneumatických pístů." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2021. http://www.nusl.cz/ntk/nusl-444967.
Full textAbstract:
Tato práce se zabývá vytvořením simulačního modelu dvojčinného pneumatického pístu s mechanickou sestavou, včetně modelů snímačů, s následujícím odhadem parametrů a aproximací chování demonstračního zařízení. Dalším cílem je prezentace různých přístupů prediktivní údržby na datové sadě měřené na demonstračním zařízení. Na měřený datový soubor se aplikovaly signal-based techniky bez použití simulačního modelu a model-based metody, které vyžadují použití simulačního modelu. Výsledkem této práce je ověření možnosti monitorování stavu zařízení pomocí nainstalovaných senzorů a vyhodnocení efektivity senzorů z hlediska přesnosti a finančních nákladů.
30
Aggab, Toufik. "Pronostic des systèmes complexes par l’utilisation conjointe de modèle de Markov caché et d’observateur." Thesis, Orléans, 2016. http://www.theses.fr/2016ORLE2051/document.
Full textAbstract:
Cette thèse porte sur le diagnostic et le pronostic pour l’aide à la maintenance de systèmes complexes. Elle présente deux approches de diagnostic/pronostic qui permettent de générer les indicateurs utiles pour l’optimisation de la stratégie de maintenance. Plus précisément, ces approches permettent d’évaluer l’état de santé et de prédire la durée de vie résiduelle du système. Les approches présentées visent en particulier à pallier le problème d’absence d’indicateurs de dégradation. Les développements sont fondés sur l’utilisation d’observateurs, de formalisme de Modèle de Markov Caché, des méthodes d’inférences statistiques et des méthodes de prédiction de séries temporelles à base d’apprentissage afin de caractériser et prédire les modes de fonctionnement du système. Les deux approches sont illustrées sur des exemples de dégradation d’un système de régulation de niveau d’eau, d’une machine asynchrone et d’une batterie Li-IonThe research presented in this thesis deals of diagnosis and prognosis of complex systems. It presents two approaches that generate useful indicators for optimizing maintenance strategies. Specifically, these approaches are used to assess the level of degradation and estimate the Remaining Useful Life of the system. The aim of these approaches is to overcome for the lack of degradation indicators. The developments are based on observers, Hidden Markov Model formalism, statistical inference methods and learning-based methods in order to characterize and predict the system operating modes. To illustrate the proposed failure diagnosis/prognosis approaches, a simulated tank level control system, an induction motor and a Li-Ion battery were used
31
Ammour, Rabah. "Contribution au diagnostic et pronostic des systèmes à évènements discrets temporisés par réseaux de Petri stochastiques." Thesis, Normandie, 2017. http://www.theses.fr/2017NORMLH21/document.
Full textAbstract:
La complexification des systèmes et la réduction du nombre de capteurs nécessitent l’élaboration de méthodes de surveillance de plus en plus efficaces. Le travail de cette thèse s’inscrit dans ce contexte et porte sur le diagnostic et le pronostic des Systèmes à Événements Discrets (SED) temporisés. Les réseaux de Petri stochastiques partiellement mesurés sont utilisés pour modéliser le système. Le modèle représente à la fois le comportement nominal et le comportement dysfonctionnel du système. Il permet aussi de représenter ses capteurs à travers une mesure partielle des transitions et des places. Notre contribution porte sur l’exploitation de l’information temporelle pour le diagnostic et le pronostic des SED. À partir d’une suite de mesures datées, les comportements du système qui expliqueraient ces mesures sont d’abord déterminés. La probabilité de ces comportements est ensuite évaluée pour fournir un diagnostic du système en termes de probabilité d’occurrence d’un défaut. Dans le cas où une faute est diagnostiquée, une approche permettant d’estimer la distribution de sa date d’occurrence est proposée. L’objectif est de donner plus de détails sur cette faute afin de mieux la caractériser. Par ailleurs, la probabilité des comportements compatibles est exploitée pour estimer l’état actuel du système. Il s’agit de déterminer les marquages compatibles avec les mesures ainsi que leurs probabilités associées. À partir de cette estimation d’état, la prise en considération des évolutions possibles du système permet d’envisager la prédiction de la faute avant son occurrence. Une estimation de la probabilité d’occurrence de la faute sur un horizon de temps futur est ainsi obtenue. Celle-ci est ensuite étendue à l’évaluation de la durée de vie résiduelle du système. Enfin, une application des différentes approches développées sur un cas d’un système de tri est proposéeDue to the increasing complexity of systems and to the limitation of sensors number, developing monitoring methods is a main issue. This PhD thesis deals with the fault diagnosis and prognosis of timed Discrete Event Systems (DES). For that purpose, partially observed stochastic Petri nets are used to model the system. The model represents both the nominal and faulty behaviors of the system and characterizes the uncertainty on the occurrence of events as random variables with exponential distributions. It also considers partial measurements of both markings and events to represent the sensors of the system. Our main contribution is to exploit the timed information, namely the dates of the measurements for the fault diagnosis and prognosis of DES. From the proposed model and collected measurements, the behaviors of the system that are consistent with those measurements are obtained. Based on the event dates, our approach consists in evaluating the probabilities of the consistent behaviors. The probability of faults occurrences is obtained as a consequence. When a fault is detected, a method to estimate its occurrence date is proposed. From the probability of the consistent trajectories, a state estimation is deduced. The future possible behaviors of the system, from the current state, are considered in order to achieve fault prediction. This prognosis result is extended to estimate the remaining useful life as a time interval. Finally, a case study representing a sorting system is proposed to show the applicability of the developed methods
32
Delmas, Adrien. "Contribution à l'estimation de la durée de vie résiduelle des systèmes en présence d'incertitudes." Thesis, Compiègne, 2019. http://www.theses.fr/2019COMP2476/document.
Full textAbstract:
La mise en place d’une politique de maintenance prévisionnelle est un défi majeur dans l’industrie qui tente de réduire le plus possible les frais relatifs à la maintenance. En effet, les systèmes sont de plus en plus complexes et demandent un suivi de plus en plus poussé afin de rester opérationnels et sécurisés. Une maintenance prévisionnelle nécessite d’une part d’évaluer l’état de dégradation des composants du système, et d’autre part de pronostiquer l’apparition future d’une panne. Plus précisément, il s’agit d’estimer le temps restant avant l’arrivée d’une défaillance, aussi appelé Remaining Useful Life ou RUL en anglais. L’estimation d’une RUL constitue un réel enjeu car la pertinence et l’efficacité des actions de maintenance dépendent de la justesse et de la précision des résultats obtenus. Il existe de nombreuses méthodes permettant de réaliser un pronostic de durée de vie résiduelle, chacune avec ses spécificités, ses avantages et ses inconvénients. Les travaux présentés dans ce manuscrit s’intéressent à une méthodologie générale pour estimer la RUL d’un composant. L’objectif est de proposer une méthode applicable à un grand nombre de cas et de situations différentes sans nécessiter de modification majeure. De plus, nous cherchons aussi à traiter plusieurs types d’incertitudes afin d’améliorer la justesse des résultats de pronostic. Au final, la méthodologie développée constitue une aide à la décision pour la planification des opérations de maintenance. La RUL estimée permet de décider de l’instant optimal des interventions nécessaires, et le traitement des incertitudes apporte un niveau de confiance supplémentaire dans les valeurs obtenuesPredictive maintenance strategies can help reduce the ever-growing maintenance costs, but their implementation represents a major challenge. Indeed, it requires to evaluate the health state of the component of the system and to prognosticate the occurrence of a future failure. This second step consists in estimating the remaining useful life (RUL) of the components, in Other words, the time they will continue functioning properly. This RUL estimation holds a high stake because the precision and accuracy of the results will influence the relevance and effectiveness of the maintenance operations. Many methods have been developed to prognosticate the remaining useful life of a component. Each one has its own particularities, advantages and drawbacks. The present work proposes a general methodology for component RUL estimation. The objective i to develop a method that can be applied to many different cases and situations and does not require big modifications. Moreover, several types of uncertainties are being dealt With in order to improve the accuracy of the prognostic. The proposed methodology can help in the maintenance decision making process. Indeed, it is possible to select the optimal moment for a required intervention thanks to the estimated RUL. Furthermore, dealing With the uncertainties provides additional confidence into the prognostic results
33
Gerdes, Mike. "Health Monitoring for Aircraft Systems using Decision Trees and Genetic Evolution." Diss., Aircraft Design and Systems Group (AERO), Department of Automotive and Aeronautical Engineering, Hamburg University of Applied Sciences, 2019. http://d-nb.info/1202830382.
Full textAbstract:
Reducing unscheduled maintenance is important for aircraft operators. There are significant costs if flights must be delayed or cancelled, for example, if spares are not available and have to be shipped across the world. This thesis describes three methods of aircraft health condition monitoring and prediction; one for system monitoring, one for forecasting and one combining the two other methods for a complete monitoring and prediction process. Together, the three methods allow organizations to forecast possible failures. The first two use decision trees for decision-making and genetic optimization to improve the performance of the decision trees and to reduce the need for human interaction. Decision trees have several advantages: the generated code is quickly and easily processed, it can be altered by human experts without much work, it is readable by humans, and it requires few resources for learning and evaluation. The readability and the ability to modify the results are especially important; special knowledge can be gained and errors produced by the automated code generation can be removed. A large number of data sets is needed for meaningful predictions. This thesis uses two data sources: first, data from existing aircraft sensors, and second, sound and vibration data from additionally installed sensors. It draws on methods from the field of big data and machine learning to analyse and prepare the data sets for the prediction process.
34
Hassan, Muhammad. "Production 4.0 of Ring Mill 4 Ovako AB." Thesis, Högskolan i Gävle, Elektronik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-33405.
Full textAbstract:
Cyber-Physical System (CPS) or Digital-Twin approach are becoming popular in industry 4.0 revolution. CPS not only allow to view the online status of equipment, but also allow to predict the health of tool. Based on the real time sensor data, it aims to detect anomalies in the industrial operation and prefigure future failure, which lead it towards smart maintenance. CPS can contribute to sustainable environment as well as sustainable production, due to its real-time analysis on production. In this thesis, we analyzed the behavior of a tool of Ringvalsverk 4, at Ovako with its twin model (known as Digital-Twin) over a series of data. Initially, the data contained unwanted signals which is then cleaned in the data processing phase, and only before production signal is used to identify the tool’s model. Matlab’s system identification toolbox is used for identifying the system model, the identified model is also validated and analyzed in term of stability, which is then used in CPS. The Digital-Twin model is then used and its output being analyzed together with tool’s output to detect when its start deviate from normal behavior.
35
Pradella, Lorenzo. "A data-driven prognostic approach based on AR identification and hidden Markov models." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Find full textAbstract:
In this work a data-driven prognostic approach based on AutoRegressive (AR) estimation and hidden Markov models (HMMs) is addressed. In particular, the approach is capable of achieving Prognostic and Health Management (PHM) tasks such as real time detection and Remaining Useful Life (RUL) estimation. The approach can be seen as composed of a training part (offline)
and an exploitation part (online). The offline part relies upon the use of a scalar health indicator coming from the system identification field: the Itakura Saito (IS) spectral distance. In particular, raw acceleration data, gathered in an unsupervised framework from the machine, are modeled by AR processes and then transformed into IS. Then, HMMs are used to map such IS signals into a finite number of parameters. Moreover, in the training procedure of HMMs, a left-to-right clustering of unsupervised data, based on Mixture of Gaussians (MOG) distribution is proposed.
During the online exploitation a simulation of a running signal is tested against trained ones in order to carry out PHM tasks in real time.
Simulations have been performed using a public benchmark available in ”NASA prognostic data repository”. It contains run-to-failure tests on bearings, on which acceleration signals
are gathered. In particular the gathering experiment simulates an industry application, under constant operating conditions.
Results of simulations, performed on real time data, validate the proposed prognostic approach and make the combined use of IS an HMMs a reliable way in achieving PHM goals.
36
Kubisz, Jan. "Využití umělé inteligence k monitorování stavu obráběcího stroje." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2020. http://www.nusl.cz/ntk/nusl-417752.
Full textAbstract:
Diploma thesis focus on creation of neural network’s internal structure with goal of creation Artificial Neural Network capable of machine state monitoring and predicting its remaining usefull life. Main goal is creation of algorithm’s and library for design and learning of Artificial Neural Network, and deeper understanding of the problematics in the process, then by utilising existing libraries. Selected method was forward-propagation network with multi-layered perceptron architecture, and backpropagation learning. Achieved results was, that the network was able to determine parts state from vibration measurement and on its basis predict remaining usefull life.
37
Huang, Fei. "Contributions à l'élaboration des modèles à partir de données pour l'estimation de la durée de vie résiduelle des roulements." Electronic Thesis or Diss., Université de Lorraine, 2020. http://www.theses.fr/2020LORR0019.
Full textAbstract:
Cette thèse de doctorat porte sur l’estimation de la durée de vie résiduelle d’un roulement sur la base des signatures obtenues à partir des signaux de vibration collectés pour un nombre restreint de roulements identiques durant un cycle complet de fonctionnement. Nous avons élaboré de nouvelles signatures qui ont une évolution monotone croissante avec l’état de dégradation des roulements et nous avons proposé un modèle d’estimation de la durée de vie résiduelle des roulements, basé sur un système d’inférence floue. Les paramètres du modèle sont identifiés par apprentissage à partir d’une petite quantité de données, en utilisant la méthode d’analyse du maximum de vraisemblance d’un mélange de distributions. Un ensemble de données d’apprentissage de petite taille ne permettant pas d’estimer les paramètres du modèle avec une grande précision. Nous avons donc élaboré une méthode de mise à jour des paramètres du modèle par un processus adaptatif de capitalisation de connaissancesRemaining useful life (RUL) estimation for bearings degradation monitoring is an important metric for decision making in condition based maintenance of rotating mechanics. RUL estimation involves generally two steps: degradation indicator extraction and model identification. Common vibration signal based features for bearings degradation monitoring are sensible on the last stage of the degradation process. In this thesis, we propose new bearing degradation monitoring indicators that are monotonic and incorporate historical degradation information. To overcome the drawback of a small size training datasets for model identification, we elaborated a mixture distribution analysis based fuzzy model identification method for RUL estimation. Furthermore, we proposed a method to tune the parameters of the fuzzy models for bearings RUL estimation when new knowledge becomes available. The aim is to improve the accuracy of the RUL estimation through a knowledge accumulation process
38
Krupa, Miroslav. "Metody technické prognostiky aplikovatelné v embedded systémech." Doctoral thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-233568.
Full textAbstract:
Hlavní cílem dizertace je poskytnutí uceleného pohledu na problematiku technické prognostiky, která nachází uplatnění v tzv. prediktivní údržbě založené na trvalém monitorování zařízení a odhadu úrovně degradace systému či jeho zbývající životnosti a to zejména v oblasti komplexních zařízení a strojů. V současnosti je technická diagnostika poměrně dobře zmapovaná a reálně nasazená na rozdíl od technické prognostiky, která je stále rozvíjejícím se oborem, který ovšem postrádá větší množství reálných aplikaci a navíc ne všechny metody jsou dostatečně přesné a aplikovatelné pro embedded systémy. Dizertační práce přináší přehled základních metod použitelných pro účely predikce zbývající užitné životnosti, jsou zde popsány metriky pomocí, kterých je možné jednotlivé přístupy porovnávat ať už z pohledu přesnosti, ale také i z pohledu výpočetní náročnosti. Jedno z dizertačních jader tvoří doporučení a postup pro výběr vhodné prognostické metody s ohledem na prognostická kritéria. Dalším dizertačním jádrem je představení tzv. částicového filtrovaní (particle filtering) vhodné pro model-based prognostiku s ověřením jejich implementace a porovnáním. Hlavní dizertační jádro reprezentuje případovou studii pro velmi aktuální téma prognostiky Li-Ion baterii s ohledem na trvalé monitorování. Případová studie demonstruje proces prognostiky založené na modelu a srovnává možné přístupy jednak pro odhad doby před vybitím baterie, ale také sleduje možné vlivy na degradaci baterie. Součástí práce je základní ověření modelu Li-Ion baterie a návrh prognostického procesu.
39
Jha, Mayank Shekhar. "Diagnostic et Pronostic de Systèmes Dynamiques Incertains dans un contexte Bond Graph." Thesis, Ecole centrale de Lille, 2015. http://www.theses.fr/2015ECLI0027/document.
Full textAbstract:
Cette thèse développe des approches pour le diagnostic et le pronostic de systèmes dynamiques incertains en utilisant la technique de modélisation Bond Graph (BG). Tout d'abord, une représentation par intervalles des incertitudes paramétriques et de mesures est intégrée à un modèle BG-LFT (Linear Fractional Transformation). Une méthode de détection robuste de défaut est développée en utilisant les règles de l'arithmétique d'intervalle pour la génération de seuils robustes et adaptatifs sur les résidus nominaux. La méthode est validée en temps réel sur un système de générateur de vapeur.Deuxièmement, une nouvelle méthodologie de pronostic hybride est développée en utilisant les Relations de Redondance Analytique déduites d'un modèle BG et les Filtres Particulaires. Une estimation de l'état courant du paramètre candidat pour le pronostic est obtenue en termes probabilistes. La prédiction de la durée de vie résiduelle est atteinte en termes probabilistes. Les incertitudes associées aux mesures bruitées, les conditions environnementales, etc. sont gérées efficacement. La méthode est validée en temps réel sur un système mécatronique incertain.Enfin, la méthodologie de pronostic développée est mise en œuvre et validée pour le suivi efficace de la santé d'un sous-système électrochimique d’une pile à combustible à membrane échangeuse de protons (PEMFC) industrielle à l’aide de données de dégradation réellesThis thesis develops the approaches for diagnostics and prognostics of uncertain dynamic systems in Bond Graph (BG) modeling framework. Firstly, properties of Interval Arithmetic (IA) and BG in Linear Fractional Transformation, are integrated for representation of parametric and measurement uncertainties on an uncertain BG model. Robust fault detection methodology is developed by utilizing the rules of IA for the generation of adaptive interval valued thresholds over the nominal residuals. The method is validated in real time on an uncertain and highly complex steam generator system.Secondly, a novel hybrid prognostic methodology is developed using BG derived Analytical Redundancy Relationships and Particle Filtering algorithms. Estimations of the current state of health of a system parameter and the associated hidden parameters are achieved in probabilistic terms. Prediction of the Remaining Useful Life (RUL) of the system parameter is also achieved in probabilistic terms. The associated uncertainties arising out of noisy measurements, environmental conditions etc. are effectively managed to produce a reliable prediction of RUL with suitable confidence bounds. The method is validated in real time on an uncertain mechatronic system.Thirdly, the prognostic methodology is validated and implemented on the electrical electro-chemical subsystem of an industrial Proton Exchange Membrane Fuel Cell. A BG of the latter is utilized which is suited for diagnostics and prognostics. The hybrid prognostic methodology is validated, involving real degradation data sets
40
Ginzarly, Riham. "Contribution à la modélisation et au pronostic des défaillances d'une machine synchrone à aimants permanents." Thesis, Normandie, 2019. http://www.theses.fr/2019NORMR038/document.
Full textAbstract:
L’objectif de ce travail est d’élaborer un modèle performant/précis de la machine électrique permettant de proposer une technique de pronostic. Dans cette thèse, nous commençons par un état de l’art sur les véhicules électriques hybrides (VHE), les différents types de machines électriques utilisées dans les VHE ainsi que les différents types de défauts pouvant survenir dans ces machines électriques. Nous identifions également les indicateurs de défauts appropriés aux différents défauts considérés. Ensuite, une synthèse de techniques de pronostic pouvant être appliquées est proposée. Le modèle à éléments finis électromagnétiques, thermiques et vibratoires (FEM) de la machine à aimants permanents est présenté. Le modèle est élaboré en fonctionnement normal et défaillant. Les types de défauts considérés sont : démagnétisation, court-circuit et excentricité. Une comparaison entre les deux approches analytique et FEM (méthode numérique) pour la modélisation de machines électromagnétiques est effectuée. Les indicateurs de défauts analysés pour l’extraction les plus pertinents utilisent les différents signaux mesurées suivants : le couple, la température ainsi que les signaux vibratoires en états sains et défectueux. L’approche de pronostic adoptée qui est le modèle de Markov caché (HMM) est développée. L'aspect technique de la méthode est présenté et le module du pronostic est formulé. La méthode de HMM est utilisée pour détecter et localiser les défauts à petites amplitudes. Une stratégie systématique a été développée. Le vieillissement de l’équipement de la machine, en particulier des éléments sensibles comme la bobine de stator et l’aimant permanent, est une question très importante pour le calcul du RUL (Remaining Useful Life). Une stratégie d’estimation pour le calcul RUL est présentée et discutée. La configuration en boucle fermée est très importante. Elle est adoptée par tous les systèmes de véhicules disponibles. Par conséquent, les mêmes étapes mentionnées précédemment s'appliquent également à une configuration en boucle fermée. Un modèle global où l’entrée du FEM de la machine provient de l’onduleur modélisé est élaboréThe core of the work is to build an accurate model of the electrical machine where the prognostic technique is applied. In this thesis we started by a literature review on hybrid electric vehicles (HEV), the different types of electrical machine used in HEV’s and the different types of faults that may occur in those electrical machine. We also identify the useful monitoring parameters that are beneficial for those different types of faults. Then, a survey is presented where all the prognostic techniques that can be applied on this application are enumerated. The electromagnetic, thermal and vibration finite element model (FEM) of the permanent magnet machine is presented. The model is built at healthy operation and when a fault is integrated. The considered types of faults are:demagnetization, turn to turn short circuit and eccentricity. A confrontation between analytical and FEM (numerical method) for electromagnetic machine modeling is illustrated. Fault indicators where useful measured parameters forfault identification are recognized and useful features from the measured parameters are extracted; torque, temperature and vibration signal are elaborated for healthy and faulty states. The strategy of the adopted prognostic approach which is Hidden Markov Model (HMM) is explained. The technical aspect of the method is presented and the prognostic model is formulated. HMM is applied to detect and localize small scale fault small scale faults were where a systematic strategy is developed. The aging of the machine’s equipment,specially the sensitive ones that are the stator coil’s and the permanent magnet, is a very important matter for RUL calculation. An estimation strategy for RUL calculation is presented and discussed for those mentioned machine’s components. Closed loop configuration is very important; it is adopted by all available vehicle systems. Hence, the same previously mentioned steps are applied for a closed loop configuration too. A global model where the input of the machine’s FEM comes from the modeled inverter is built
41
Khelif, Racha. "Estimation du RUL par des approches basées sur l'expérience : de la donnée vers la connaissance." Thesis, Besançon, 2015. http://www.theses.fr/2015BESA2019/document.
Full textAbstract:
Nos travaux de thèses s’intéressent au pronostic de défaillance de composant critique et à l’estimation de la durée de vie résiduelle avant défaillance (RUL). Nous avons développé des méthodes basées sur l’expérience. Cette orientation nous permet de nous affranchir de la définition d’un seuil de défaillance, point problématique lors de l’estimation du RUL. Nous avons pris appui sur le paradigme de Raisonnement à Partir de Cas (R à PC) pour assurer le suivi d’un nouveau composant critique et prédire son RUL. Une approche basée sur les instances (IBL) a été développée en proposant plusieurs formalisations de l’expérience : une supervisée tenant compte de l’ état du composant sous forme d’indicateur de santé et une non-supervisée agrégeant les données capteurs en une série temporelle mono-dimensionnelle formant une trajectoire de dégradation. Nous avons ensuite fait évoluer cette approche en intégrant de la connaissance à ces instances. La connaissance est extraite à partir de données capteurs et est de deux types : temporelle qui complète la modélisation des instances et fréquentielle qui, associée à la mesure de similarité permet d’affiner la phase de remémoration. Cette dernière prend appui sur deux types de mesures : une pondérée entre fenêtres parallèles et fixes et une pondérée avec projection temporelle. Les fenêtres sont glissantes ce qui permet d’identifier et de localiser l’état actuel de la dégradation de nouveaux composants. Une autre approche orientée donnée a été test ée. Celle-ci est se base sur des caractéristiques extraites des expériences, qui sont mono-dimensionnelles dans le premier cas et multi-dimensionnelles autrement. Ces caractéristiques seront modélisées par un algorithme de régression à vecteurs de support (SVR). Ces approches ont été évaluées sur deux types de composants : les turboréacteurs et les batteries «Li-ion». Les résultats obtenus sont intéressants mais dépendent du type de données traitéesOur thesis work is concerned with the development of experience based approachesfor criticalcomponent prognostics and Remaining Useful Life (RUL) estimation. This choice allows us to avoidthe problematic issue of setting a failure threshold.Our work was based on Case Based Reasoning (CBR) to track the health status of a new componentand predict its RUL. An Instance Based Learning (IBL) approach was first developed offering twoexperience formalizations. The first is a supervised method that takes into account the status of thecomponent and produces health indicators. The second is an unsupervised method that fuses thesensory data into degradation trajectories.The approach was then evolved by integrating knowledge. Knowledge is extracted from the sensorydata and is of two types: temporal that completes the modeling of instances and frequential that,along with the similarity measure refine the retrieval phase. The latter is based on two similaritymeasures: a weighted one between fixed parallel windows and a weighted similarity with temporalprojection through sliding windows which allow actual health status identification.Another data-driven technique was tested. This one is developed from features extracted from theexperiences that can be either mono or multi-dimensional. These features are modeled by a SupportVector Regression (SVR) algorithm. The developed approaches were assessed on two types ofcritical components: turbofans and ”Li-ion” batteries. The obtained results are interesting but theydepend on the type of the treated data
42
Liu, Tianyi. "An integrated bearing prognostics method for remaining useful life prediction." Thesis, 2013. http://spectrum.library.concordia.ca/977273/1/Liu_MASc_F2013.pdf.
Full textAbstract:
Abstract
An integrated bearing prognostics method for remaining useful life prediction
Nowadays, in order to improve the productivity and quality, more and more resources are invested in maintenance. In order to improve the reliability of an engineering system, accurate predictions of the remaining useful lifetime of the equipment and its key parts are required. Bearing plays an important role in the rotating machines. The purpose of using a bearing is to reduce rotational friction and support the load imposed on it in radial and axial directions.
The common types of bearing defects include damage in rolling elements, inner and outer races, etc. In this thesis, we focus on the spall propagation caused by rolling contact fatigue. The existing bearing prognosis methods are either model-based or data driven. In this thesis, we develop an integrated bearing prognostics method, which utilizes both physical models and condition monitoring data. In the physical model part, a Hertz contact model is used to analyze the stress developed from the contact point between two curved surfaces which are pressed together, the ball and the deep groove. Based on Paris’ law, a damage propagation model is used to describe the spall propagation process. It is difficult to measure a defect size when the machines are running. Therefore, online data is obtained and processed to transform raw signals into useful information. In this thesis, the uncertainty factors are considered, including material uncertainty, model uncertainty and measurement error. A Bayesian method is used to update the distribution of this uncertainty factor by fusing the condition monitoring data, to achieve updated predictions of remaining useful life.
Finally, two sets of data are used to verify and validate the proposed integrated bearing prognostics method. The first set of data includes a group of simulated bearing degradation histories. The second set of data were collected from lab experiments conducted using the Bearing Prognostics Simulator. These examples demonstrated the effectiveness of the proposed method.
The key contribution of this thesis is the development of an integrated bearing prognostics method, where the uncertain model parameters are updated using the collected condition monitoring data, while the existing bearing prognostics methods are either model-based or data driven. Both the development of the method and the experimental validation are significant contributions to the field of bearing prognostics.
43
Li, Chung-Chang, and 李俊昌. "Ensemble learning for remaining useful life prediction of equipment components." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/b5fxd5.
Full textAbstract:
碩士國立交通大學
統計學研究所
105
The machine equipment that is used to produce several products is important facility in factory. Therefore, how to predict the remaining useful life (RUL) of equipment components to avoid damage to the machine is an important issue. The censoring data from the machine are usually too huge and complicate to get accurate RUL prediction by one single model. Thus, in this thesis, we adopt a parametric degradation model with linear mixed effects as the base learner and combine three popular ensemble learning approaches: bagging, boosting and stacking to improve the prediction accuracy of the base learner. This thesis analyzes a set of censoring data from the MOCVD machine equipment that produces LED chips, and uses them to demonstrate the usefulness of the proposed ensemble learning approaches. Because the analyzed censoring data contain repeated measurements, instead of using the traditional bootstrap sampling method, we use the moving block bootstrap sampling in the ensemble learning procedures.
44
Chang-Kuei, Kuo, and 郭昶逵. "Enhancing Convolutional Neural Network Deep Learning for Remaining Useful Life Estimation." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/10174877759044519879.
Full textAbstract:
碩士國立中央大學
資訊工程學系
105
The smart factory becomes a hot research topic recently. Prognostic health management (PHM) plays a critical role in smart factory applications to produce different level of prognostics, such as failure prediction and remaining useful life (RUL) estimation, for machines or components. This thesis enhances the convolutional neural network (CNN) deep learning for RUL estimation in smart factory applications. A CNN is a special type of deep neural networks (DNNs) used in deep learning for analyzing image data for the applications of image recognition and video recognition. It has convolution layers, pooling layers, and fully connected layers. A convolution layer contains many filters to abstract features from input data, and a pooling layer can reduce data dimensionality without losing features. The CNN deep learning has been applied in an earlier study for RUL estimation. This thesis enhances the learning by applying more sophisticated data pre-processing, a better optimizer, namely the adaptive moment estimation (Adam) method, and a proper activation function, namely the softplus function. The enhanced CNN deep learning is applied to NASA C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) data set to estimate the RUL of aero-propulsion engines. Its performance is evaluated by a scoring function that can measure the RUL estimation accuracy. The evaluation results are compared with those of other methods using the multi-layer perceptron (MLP), support vector regression (SVR), relevance vector regression (RVR) and traditional CNN. We find that the enhanced CNN deep learning method is superior to other methods.
45
Huang, Sheng-Wen, and 黃聖文. "Prediction of the remaining useful life using simple Gaussian process particle filter." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/2q37m3.
Full textAbstract:
碩士國立交通大學
統計學研究所
105
In response to the worldwide energy crisis and environmental issues, proton exchange membrane fuel cell is regarded as a very important alternative energy sources. However, the current fuel cell applications are also limited by the lack of life issues. Therefore, the remaining useful life of the battery management is significant. The particle filter is considered to be successful in the prediction of the remaining life of the fuel cell. In this study, we propose a Simple Gaussian Process Particle Filter to predict the remaining life of the battery, and it is more flexible than traditional particle filter. We use this method to achieve a more accurate life prediction.
46
Lin, Yu-Hsin, and 林育新. "Techniques Developments for Faulty Ball Bearing Identification and Remaining Useful Life Estimation." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/62yknd.
Full textAbstract:
碩士國立中正大學
機械工程系研究所
105
The purpose of this study is to develop an intelligent diagnosis system for rolling bearings. The diagnosis for rolling bearings is aiming to identify its overall healthy state instead of detail examination for the faulty component inside the bearing. The reason is that in practice the whole bearing in the mechanical equipment is required to be replaced even though the faulty is caused by some of its components, e.g. the inner ring, outer ring, the roller etc. The thesis consists of three parts. In the first part, a novel bearing diagnosis technique called Spectral Kurtosis Entropy (SKE) which combines Entropy and Spectral Kurtosis to assess the bearing healthy state is proposed. The performance of this proposed SKE is assessed using Fisher Score (FS). In the second part, Self-organizing map (SOM) is utilized identify the faulty bearing from the healthy one with SKE, Sample Entropy (SE) and Root mean square (RMS) from bearing vibration signal as features respectively. A method of estimation for bearing Remaining Useful Life (RUL) is introduced in the third part. The estimation for bearing RUL is based on the Mahalanobis distance according to the Minimum quantization error (MQE) from the SOM neuron model. The proposed intelligent diagnosis technique is validated using the data sets from NASA, PHM and experiments. Results show that the bearing healthy state can be assessed by the proposed SKE with a performance better than SK.. It is worth of noting that the prior knowledge of the bearing type is not required whenconducting the rolling bearing healthy assessment using SOM neuron model with SKE as the feature.
47
Yen, Han Chiang, and 江衍涵. "Technique Developments of Estimations of Cutting Forces and Tool Remaining Useful Life." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/8syafw.
Full textAbstract:
碩士國立中正大學
機械工程系研究所
106
Two techniques regarding of machining based on the vibration signal are proposed. The first one is an indirect cutting force estimation and the second is an estimation of cutting tool remaining life . For cutting force estimation, a frequency transfer function between the force acting on the cutting tool tip and the acceleration on the spindle is determined firstly using experimental modal analysis (EMA). With this transfer function, the cutting force is then obtained during the machining by measuring the spindle acceleration. Experimental results show that the cutting force determined using the proposed indirection measurement agrees well with those measured using the dynamometer at low spindle speeds; however, the discrepancy increases at high spindle speed, e.g. above 6000 RPM. For the tool remaining life estimation, an indirect detection of tool wear using features extracted from vibration signal is proposed. The effectiveness and the contribution in tool wear estimation from various features extracted from the vibration and cutting force are compared using the method of Reverse Principal Components (RPCA). Then the self-organizing maps (SOM) is adopted for estimating the tool wear, and furthermore the tool useful remaining life (RUL). Experimental results show that the discrepancy in the tool wear estimation using the proposed method is less than 10% as compared with that measured directly by photos.
48
Huang, Kuang-Chieh, and 黃冠傑. "Predicting Remaining Useful Life of Equipment based on Deep Learning-based Model." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/2bd366.
Full textAbstract:
碩士元智大學
資訊管理學系
106
With the development of smart manufacturing, in order to instantly detect abnormal conditions of the equipment, a large number of sensors were built to record the variables associated with the collection of production equipment. This research focuses on the remaining useful life(RUL)prediction. Remaining useful life is a part of the predictive maintenance(PDM), it is condition based, according to the development trend of the machine in the past to detect the machine is going to malfunction, our purpose is to detect early that the machine needs to be replaced or repaired to ensure the sustainability of the system. Existing literature methods are often difficult to extract meaningful features from sensing data. This research proposes a deep learning method, constructing an autoencoder gated recurrent unit (AE-GRU) neural network model, autoencoder extracts the important features from the raw data and gated recurrent unit picks up the information of the sequences to forecasting remaining useful life precisely. In the experiment of this research, we use for the prognostics challenge competition at the IEEE International Conference on Prognostics and Health Management (PHM08) and evaluated by 5 folds cross-validation. In the verification of root mean square error(RMSE) in our experiments, our method is better than other methods, such as deep neural network(DNN)、recurrent neural network(RNN)、long short-term memory neural network(LSTM)、gated recurrent unit neural network(GRU).
49
Δημήτριος, Ρούλιας. "Methodologies for remaining useful life estimation with multiple sensors in rotating machinery." Thesis, 2014. http://hdl.handle.net/10889/8258.
Full textAbstract:
The focus of this thesis was the development of failure prognosis methods (prognostics) in rotating machinery with use of multiple sensors digital signal processing and machine learning techniques. The motivation stems from the void in literature concerning prognostics in meshing gearboxes. Moreover, there are several but inconclusive works regarding bearing prognosis.
Few research groups have studied multi-hour fatigue gear experiments and this was one of the contributions of this thesis. Moreover, the study expanded beyond the sheer application of vibration monitoring with the addition of an Oil Debris Monitoring probe (ODM) as well as Acoustic emission (AE).
The method of AE monitoring is, once again, proposed as a robust technique for failure prognosis being better correlated with gear pitting level compared to the classic vibration monitoring technique. Moreover, judging from ODM recordings the gear pitting comprises of two phases i) a linear phase, with an almost constant pitting rate and ii) a very short non linear phase where the pitting rate increases exponentially, an explicit indication of a critical failure.
Multi-hour gear experiments that are close to real scale applications are very demanding in time as well as in invested capital. To bypass this shortfall a gear failure like simulation is proposed. The simulation framework is based on real life experiments and is applied to assess a number of data-driven Remaining Useful Life (RUL) estimation techniques namely i) Proportional Hazards Μodel (PHM), ii) ε- Support Vector Regression ε-SVR and iii) Exponential extrapolation based on bootstrap sampling.
In the current thesis a feature extraction scheme for prognosis is proposed and assessed based on time domain, frequency domain statistical features and Wavelet Packet (WP) energy derived from AE and vibration recordings. ICA is proposed as a preferable fusion technique for gear failure prognostics. Application of ICA for feature fusion provided a clear improvement regarding the earlier presented bootstrap extrapolation technique.
Bearings are also taken into account since they are closely connected to gearboxes. In the current thesis a wavelet denoising method is proposed for bearing vibration recordings aiming to the improvement of the diagnostic and prognostic potential of vibration. Finally the importance of data fusion is highlighted in the case of bearings. It is observed that a feature extraction scheme can generalize the application of prognostics, even in cases where RMS may yield no important degradation trend.Η παρούσα εργασία εστιάζεται στην ανάπτυξη μεθοδολογιών πρόβλεψης τελικής αστοχίας σε περιστρεφόμενα συστήματα με χρήση πολλαπλών αισθητήρων και μεθόδων μηχανικής μάθησης και επεξεργασίας σήματος. Το κίνητρο προήλθε από το κενό που υπάρχει στη βιβλιογραφία όσον αφορά την προγνωστική σε κιβώτια ταχυτήτων. Η προγνωστική σε έδρανα έχει μεν μελετηθεί αλλά σε μικρό βαθμό και η παρούσα εργασία έρχεται να συμβάλλει και σε αυτό τον τομέα. Στα πλαίσια αυτής της εργασίας εκπονήθηκε ένας αριθμός πειραμάτων κόπωσης κιβωτίων ταχυτήτων. Η μελέτη επεκτάθηκε πέραν της παρακολούθησης κατάστασης με τη μέθοδο των κραδασμών και συγκεκριμένα μελετήθηκαν καταγραφές σωματιδίων σιδήρου στο λιπαντικό (ODM) καθώς και Ακουστική Εκπομπής (AE). Η μέθοδος ΑΕ ευρέθη πιο στενά συσχετισμένη με τη σταδιακή υποβάθμιση της ακεραιότητας του κιβωτίου ταχυτήτων σε σχέση με τις καταγραφές κραδασμών. Επίσης με βάση τις καταγραφές του αισθητήρα σωματιδίων σιδήρου διακρίθηκαν δύο στάδια υποβάθμισης i) μια γραμμική περιοχή με σχεδόν σταθερό ρυθμό απελευθέρωσης υλικού από την επιφάνεια των δοντιών και ii) μια σύντομη αλλά έντονα μη γραμμική αύξηση στο ρυθμό αυτό πολύ κοντά στο τέλος της λειτουργίας του κιβωτίου. Tα πολύωρα πειράματα κόπωσης σε γρανάζια είναι πολύ απαιτητικά. Για να παρακαμφθεί αυτή η δυσκολία αναπτύχθηκε ένα φαινομενολογικό μοντέλο για αναπαραγωγή χρονοσειρών που ομοιάζουν σε καταγραφές γραναζιών σε κόπωση. Το μοντέλο αυτό στηρίχθηκε σε πραγματικά πειράματα κόπωσης. Έτσι έγινε δυνατό να εξεταστούν και να συγκριθούν ένας αριθμός μεθοδολογιών εκτίμησης εναπομένουσας ζωής και συγκεκριμένα i) Proportional Hazards Model (PHM), ii) ε- Support Vector Regression ε-SVR και iii) Exponential extrapolation βασισμένο σε μια διαδικασία bootstrap sampling. Στην παρούσα μελέτη προτείνεται ένα σύνολο παραμέτρων προερχόμενο από το πεδίο της συχνότητας, του χρόνου και κυματοπακέτων. Αυτό, συνδυαζόμενο με μια διαδικασία σύμπτυξης δεδομένων (ανάλυση σε πρωταρχικές και ανεξάρτητες συνιστώσες) αξιοποιείται για πρόγνωση σε γρανάζια σε κόπωση. Η τεχνική ανεξάρτητων συνιστωσών προτείνεται σαν προτιμότερη από τη σκοπιά της προγνωστικής καθώς βελτιώνει την εκτίμηση της εναπομένουσας ζωής. Η εργασία επεκτάθηκε και σε έδρανα κύλισης. Προτάθηκε μια διαδικασία wavelet denoising η οποία ενισχύει τόσο τη διαγνωστική όσο και την προγνωστική δυνατότητα του αισθητήρα κραδασμών. Τέλος, η σημασία της εξαγωγής παραμέτρων υπογραμμίζεται και στην περίπτωση της προγνωστικής σε έδρανα. Συνδυάζοντας πολλαπλές παραμέτρους και αισθητήρες κραδασμών μαζί με ένα μοντέλο ε-SVR παρέχεται ένα ολοκληρωμένο μοντέλο πιθανοτικής εκτίμησης εναπομένουσας ζωής σε έδρανα κύλισης ακόμα και σε περιπτώσεις που η τιμή RMS των κραδασμών δεν παρέχει πληροφορία.
50
SU, SHAO-RONG, and 蘇紹榕. "The developing of technique to predict remaining useful life of cutting tool." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/4pa3wr.
Full textAbstract:
碩士國立中正大學
機械工程系研究所
107
This research focuses on developing an online technique to predict the remaining useful life (RUL) of cutting tool during the machining process. The vibration, cutting force and cutting moment signals are acquired by two three-axis accelerometers and a dynamometer mounted respectively on the spindle and feed drive system during the machining process. The tool wear is measured using photo image taken from a CCD camera. The tool wear model used for later RUL prediction is built using machine learning algorithm Isolation Forest. Results show that the tool RUL predicted using features extracted from vibration signals are close to that predicted using cutting force and moment from the dynamometer. Besides the Isolation Forest, the self-organizing map (SOM) is also utilized to analyze the same experimental data for comparisons. It shows that the cutting tool of the same type but from different batch numbers has different tool life, which significantly influences the accuracy of prediction of RUL for a specific tool. Results also that the prediction of RUL from IF and SOM reaches an accuracy close to each other. However, the SOM outperforms Isolation Forest in terms of less training data numbers required for training the model.