To see the other types of publications on this topic, follow the link: System of genetic algorithm.
Dissertations / Theses on the topic 'System of genetic algorithm'
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 'System of genetic algorithm.'
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
Ma, Jiya. "A Genetic Algorithm for Solar Boat." Thesis, Högskolan Dalarna, Datateknik, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:du-3488.
Full textAbstract:
Genetic algorithm has been widely used in different areas of optimization problems. Ithas been combined with renewable energy domain, photovoltaic system, in this thesis.To participate and win the solar boat race, a control program is needed and C++ hasbeen chosen for programming. To implement the program, the mathematic model hasbeen built. Besides, the approaches to calculate the boundaries related to conditionhave been explained. Afterward, the processing of the prediction and real time controlfunction are offered. The program has been simulated and the results proved thatgenetic algorithm is helpful to get the good results but it does not improve the resultstoo much since the particularity of the solar driven boat project such as the limitationof energy production
2
Rivas-Davalos, Francisco. "A genetic algorithm for power distribution system planning." Thesis, Brunel University, 2004. http://bura.brunel.ac.uk/handle/2438/7891.
Full textAbstract:
The planning of distribution systems consists in determining the optimum site and size of new substations and feeders in order to satisfy the future power demand with minimum investment and operational costs and an acceptable level of reliability. This problem is a combinatorial, non-linear and constrained optimization problem. Several solution methods based on genetic algorithms have been reported in the literature; however, some of these methods have been reported with applications to small systems while others have long solution time. In addition, the vast majority of the developed methods handle planning problems simplifying them as single-objective problems but, there are some planning aspects that can not be combined into a single scalar objective; therefore, they require to be treated separately. The cause of these shortcomings is the poor representation of the potential solutions and their genetic operators This thesis presents the design of a genetic algorithm using a direct representation technique and specialized genetic operators for power distribution system expansion planning problems. These operators effectively preserve and exploit critical configurations that contribute to the optimization of the objective function. The constraints of the problems are efficiently handle with new strategies. The genetic algorithm was tested on several theoretical and real large-scale power distribution systems. Problems of network reconfiguration for loss reduction were also included in order to show the potential of the algorithm to resolve operational problems. Both single-objective and multi-objective formulations were considered in the tests. The results were compared with results from other heuristic methods such as ant colony system algorithms, evolutionary programming, differential evolution and other genetic algorithms reported in the literature. From these comparisons it was concluded that the proposed genetic algorithm is suitable to resolve problems of largescale power distribution system planning. Moreover, the algorithm proved to be effective, efficient and robust with better performance than other previous methods.
3
Muforo, Remigius I. "Automatedgeneration of fuzzy control system using genetic algorithm." DigitalCommons@Robert W. Woodruff Library, Atlanta University Center, 1995. http://digitalcommons.auctr.edu/dissertations/3694.
Full textAbstract:
Fuzzy logic based controllers have emerged to be an inexpensive and simple solution for complex control problems. The main components of the fuzzy logic control are the rule base, the membership functions, and the inference engine. Membership functions are used to combine the antecedents and consequent (of the rules) to determine the output of the rules. Fuzzy controllers, however, suffer from significant drawbacks such as the formulation of the membership functions and tuning the rule base. In this thesis, a genetic algorithm is used to generate the fuzzy logic controller's rule base and to tune the membership functions. Temperature and pressure control in a boiler plant is used as a test bed application.
4
Guc, Gercek. "Optimization Of Water Distribution Networks Using Genetic Algorithm." Master's thesis, METU, 2006. http://etd.lib.metu.edu.tr/upload/12607192/index.pdf.
Full textAbstract:
This study gives a description about the development of a computer model, RealPipe, which relates genetic algorithm (GA) to the well known problem of least-cost design of water distribution network.
GA methodology is an evolutionary process, basically imitating evolution process of nature. GA is essentially an efficient search method basically for nonlinear optimization cases. The genetic operations take place within the population of chromosomes. By means of various operators, the genetic knowledge in chromosomes change continuously and the success of the population progressively increases as a result of these operations. GA optimization is also well suited for optimization of water distribution systems, especially large and complex systems. The primary objective of this study is optimization of a water distribution network by GA. GA operations are realized on a special program developed by the author called RealPipe. RealPipe optimizes given water network distribution systems by considering capital cost of pipes only.
Five operators are involved in the program algorithm. These operators are generation, selection, elitism, crossover and mutation. Optimum population size is found to be between 30-70 depending on the size of the network (i.e. pipe number) and number of commercially available pipe size. Elitism rate should be around 10 percent. Mutation rate should be selected around 1-5 percent depending again on the size of the network. Multipoint crossover and higher rates are advisable. Also pressure penalty parameters are found to be much important than velocity parameters. Below pressure penalty parameter is the most important one and should be roughly 100 times higher than the other.
Two known networks of the literature are examined using RealPipe and expected results are achieved. N8.3 network which is located in the northern side of Ankara is the case study. Total cost achieved by RealPipe is 16.74 percent lower than the cost of the existing networkit should be noted that the solution provided by RealPipe is hydraulically improved.
5
Tsang, Yiu-ming. "Intelligent polishing using fuzzy logic and genetic algorithm." View the Table of Contents & Abstract, 2006. http://sunzi.lib.hku.hk/hkuto/record/B37206400.
Full text
6
Tsang, Yiu-ming, and 曾耀明. "Intelligent polishing using fuzzy logic and genetic algorithm." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2006. http://hub.hku.hk/bib/B38589291.
Full text
7
Anderson, Roger J. "Characterization of Performance, Robustness, and Behavior Relationships in a Directly Connected Material Handling System." Diss., Virginia Tech, 2006. http://hdl.handle.net/10919/26967.
Full textAbstract:
In the design of material handling systems with complex and unpredictable dynamics, conventional search and optimization approaches that are based only on performance measures offer little guarantee of robustness. Using evidence from research into complex systems, the use of behavior-based optimization is proposed, which takes advantage of observed relationships between complexity and optimality with respect to both performance and robustness. Based on theoretical complexity measures, particularly algorithmic complexity, several simple complexity measures are created. The relationships between these measures and both performance and robustness are examined, using a model of a directly connected material handling system as a backdrop. The fundamental causes of the relationships and their applicability in the proposed behavior-based optimization approach are discussed.Ph. D.
8
Nguyen, Quoc Tuan. "Using the genetic algorithm to optimize Web search: Lessons from biology." Thesis, University of Ottawa (Canada), 2006. http://hdl.handle.net/10393/27160.
Full textAbstract:
Searching for information on the Web is a relatively inefficient process. My goal is to develop a method that optimizes web search queries without user intervention. Developing intelligent ways to automate this process includes the development of algorithms that automatically manipulate the use of keywords to produce the desired output. Genetic algorithms (GA) provide a potentially useful approach in this area. However, these approaches have not fully exploited the biological concepts associated with genetic reproduction and evolution. I hypothesize that an approach that uses GA but modifies it to include the biological concepts of structural and regulatory gene types and the use of a combination of deletion operator and silent genes will improve GA performance in optimizing Web search. In this paper, I describe this approach and its implementation in simulations of Web search tasks using three popular Web search engines (Google, Yahoo and Netscape). The results of this implementation are presented and are compared to the performance of a similar, but unmodified GA in the same tasks. (Abstract shortened by UMI.)
9
Singh, Ravindra. "A Novel Approach for Tuning of Power System Stabilizer Using Genetic Algorithm." Thesis, Indian Institute of Science, 2004. http://hdl.handle.net/2005/65.
Full textAbstract:
The problem of dynamic stability of power system has challenged power system engineers since over three decades now. In a generator, the electromechanical coupling between the rotor and the rest of the system causes it to behave in a manner similar to a spring mass damper system, which exhibits an oscillatory behaviour around the equilibrium state, following any disturbance, such as sudden change in loads, change in transmission line parameters, fluctuations in the output of turbine and faults etc. The use of fast acting high gain AVRs and evolution of large interconnected power systems with transfer of bulk power across weak transmission links have further aggravated the problem of low frequency oscillations. The oscillations, which are typically in the frequency range of 0.2 to 3.0 Hz, might be excited by the disturbances in the system or, in some cases, might even build up spontaneously. These oscillations limit the power transmission capability of a network and, sometimes, even cause a loss of synchronism and an eventual breakdown of the entire system.
The application of Power System Stabilizer (PSS) can help in damping out these oscillations and improve the system stability. The traditional and till date the most popular solution to this problem is application of conventional power system stabilizer (CPSS). However, continual changes in the operating condition and network parameters result in corresponding change in system dynamics. This constantly changing nature of power system makes the design of CPSS a difficult task.
Adaptive control methods have been applied to overcome this problem with some degree of success. However, the complications involved in implementing such controllers have restricted their practical usage.
In recent years there has been a growing interest in robust stabilization and disturbance attenuation problem. H∞ control theory provides a powerful tool to deal with robust stabilization and disturbance attenuation problem. However the standard H∞ control theory does not guarantee robust performance under the presence of all the uncertainties in the power plants.
This thesis provides a method for designing fixed parameter controller for system to ensure robustness under model uncertainties. Minimum performance required of PSS is decided a priori and achieved over the entire range of operating conditions.
A new method has been proposed for tuning the parameters of a fixed gain power system stabilizer. The stabilizer places the troublesome system modes in an acceptable region in the complex plane and guarantees a robust performance over a wide range of operating conditions. Robust D-stability is taken as primary specification for design. Conventional lead/lag PSS structure is retained but its parameters are re-tuned using genetic algorithm (GA) to obtain enhanced performance. The advantage of GA technique for tuning the PSS parameters is that it is independent of the complexity of the performance index considered. It suffices to specify an appropriate objective function and to place finite bounds on the optimized parameters. The efficacy of the proposed method has been tested on single machine as well as multimachine systems. The proposed method of tuning the PSS is an attractive alternative to conventional fixed gain stabilizer design as it retains the simplicity of the conventional PSS and still guarantees a robust acceptable performance over a wide range of operating and system condition.
The method suggested in this thesis can be used for designing robust power system stabilizers for guaranteeing the required closed loop performance over a prespecified range of operating and system conditions. The simplicity in design and implementation of the proposed stabilizers makes them better suited for practical applications in real plants.
10
Nassif, Nabil. "Optimization of HVAC control system strategy using two-objective genetic algorithm." Mémoire, Montréal : École de technologie supérieure, 2005. http://wwwlib.umi.com/cr/etsmtl/fullcit?pNR03069.
Full textAbstract:
Thèse (Ph.D.)-- École de technologie supérieure, Montréal, 2005."Thesis presented to the École de technologie supérieure in partial fulfiliment [i.e. fulfillment] of the thesis requirement for the degree of philosophiae doctor in engineering". Bibliogr.: f. [178]-184. Également disponible en version électronique.
11
Lee, Hee C. "Optimization of Paging Cost in Mobile Switching System by Genetic Algorithm." NSUWorks, 1997. http://nsuworks.nova.edu/gscis_etd/662.
Full textAbstract:
The maximum bandwidth capacity of radio frequency channels such as the forward control channel (FOCC) used in the mobile switching systems is fixed. The FOCC has been experiencing severe congestion because of the inefficiency of conventional mobile paging methods. A bottleneck is caused in the FOCC due to constraints of both the bandwidth and the limited number of radio frequency channels in the mobile telecommunication systems. In this dissertation, an approach that minimizes the paging cost of FOCC in order to locate a mobile station in the mobile switching system is presented. In order to minimize the paging cost and to maximize the bandwidth utilization of the FOCC, a new paging schema with the optimal partition of paging zones is developed. By using the refined mobile's probability pattern stored in the statistical profile, the approach employs the genetic algorithm and the derived fitness function to generate the optimal partition of paging zones, such that the paging cost to locate a mobile station as well as the bandwidth consumption in FOCC is minimized.
12
Hincal, Onur. "Optimization Of Multireservoir Systems By Genetic Algorithm." Phd thesis, METU, 2008. http://etd.lib.metu.edu.tr/upload/12609261/index.pdf.
Full textAbstract:
Application of optimization techniques for determining the optimal operating policy for reservoirs is a major title in water resources planning and management. Genetic algorithms, ruled by evolution techniques, have become popular for solving
optimization problems in diversified fields of science. The main aim of this research was to explore the efficiency and effectiveness of the applicability of genetic algorithm in optimization of multi-reservoirs. A computer code has been constructed for this purpose and verified by means of a reference problem with a known global optimum. Three reservoirs in the Colorado River Storage Project were optimized for maximization of energy production. Besides, a real-time approach utilizing a blend of online and a posteriori data was proposed. The results achieved were compared to
the real operational data and genetic algorithms were found to be effective, competitive and can be utilized as an alternative technique to other traditional optimization techniques.
13
Manongga, D. H. F. "Using genetic algorithm-based methods for financial analysis." Thesis, University of East Anglia, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.320950.
Full text
14
Wright, Ted. "A genetic algorithm approach to scheduling resources for a space power system." Case Western Reserve University School of Graduate Studies / OhioLINK, 1994. http://rave.ohiolink.edu/etdc/view?acc_num=case1057600490.
Full text
15
Kulankara, Krishnakumar. "Machining fixture synthesis using the genetic algorithm." Thesis, Georgia Institute of Technology, 1999. http://hdl.handle.net/1853/16491.
Full text
16
Vick, Andrew W. "Genetic Fuzzy Controller for a Gas Turbine Fuel System." University of Cincinnati / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1291053513.
Full text
17
Gilkinson, John C. "An expert scheduling system utilizing a genetic algorithm in solving a multi-parameter job shop problem." Ohio : Ohio University, 1999. http://www.ohiolink.edu/etd/view.cgi?ohiou1175881721.
Full text
18
Zhang, Xiaoyu. "Effective Search in Online Knowledge Communities: A Genetic Algorithm Approach." Thesis, Virginia Tech, 2009. http://hdl.handle.net/10919/35059.
Full textAbstract:
Online Knowledge Communities, also known as online forum, are popular web-based tools that allow members to seek and share knowledge. Documents to answer varieties of questions are associated with the process of knowledge exchange. The social network of members in an Online Knowledge Community is an important factor to improve search precision. However, prior ranking functions donâ t handle this kind of document with using this information. In this study, we try to resolve the problem of finding authoritative documents for a user query within an Online Knowledge Community. Unlike prior ranking functions which consider either content based feature, hyperlink based feature, or document structure based feature, we explored the Online Knowledge Community social network structure and members social interaction activities to design features that can gauge the two major factors affecting user knowledge adoption decision: argument quality and source credibility. We then design a customized Genetic Algorithm to adjust the weights for new features we proposed. We compared the performance of our ranking strategy with several others baselines on a real world data www.vbcity.com/forums/. The evaluation results demonstrated that our method could improve the user search satisfaction with an obviously percentage. At the end, we concluded that our approach based on knowledge adoption model and Genetic Algorithm is a better ranking strategy in the Online Knowledge Community.Master of Science
19
Ghosh, Payel. "Medical Image Segmentation Using a Genetic Algorithm." PDXScholar, 2010. https://pdxscholar.library.pdx.edu/open_access_etds/25.
Full textAbstract:
Advances in medical imaging technology have led to the acquisition of large number of images in different modalities. On some of these images the boundaries of key organs need to be accurately identified for treatment planning and diagnosis. This is typically performed manually by a physician who uses prior knowledge of organ shapes and locations to demarcate the boundaries of organs. Such manual segmentation is subjective, time consuming and prone to inconsistency. Automating this task has been found to be very challenging due to poor tissue contrast and ill-defined organ/tissue boundaries. This dissertation presents a genetic algorithm for combining representations of learned information such as known shapes, regional properties and relative location of objects into a single framework in order to perform automated segmentation. The algorithm has been tested on two different datasets: for segmenting hands on thermographic images and for prostate segmentation on pelvic computed tomography (CT) and magnetic resonance (MR) images. In this dissertation we report the results of segmentation in two dimensions (2D) for thermographic images; and two as well as three dimensions (3D) for pelvic images. We show that combining multiple features for segmentation improves segmentation accuracy as compared with segmentation using single features such as texture or shape alone.
20
Chae, Han Gil. "A Possibilistic Approach to Rotorcraft Design through a Multi-Objective Evolutionary Algorithm." Diss., Georgia Institute of Technology, 2006. http://hdl.handle.net/1853/14118.
Full textAbstract:
A method to find solutions to multi-objective design problems that involve poor information available was proposed. The method quantified the designers intuition in a systematic manner, and utilized it to approximate inaccurate and/or vague numbers. In the context of possibility theory, uncertain values were expressed through possibility distributions, i.e. fuzzy membership functions. Based on the membership functions of the value, levels of confidence of the solutions to multi-objective problems were defined through the notions of possibility and necessity. An evolutionary algorithm was modified to find sets of solutions that allow certain levels of confidence instead of the crisp sets of the solutions. The method was applied to a design problem of the gyrodyne configuration and sets of the solutions of the specified possibility and necessity were found. The results of the design problem and the suggestions for future research were discussed.
21
Kochaki, Sima Mehri. "Optimizing Bioengineered Vascular Systems: A Genetic Algorithm Approach." DigitalCommons@USU, 2017. https://digitalcommons.usu.edu/etd/6693.
Full textAbstract:
Efficiency of current cell cultures producing biological products is limited due to accumulation of the product and waste on the cells. A previous work aims at assisting bioengineers in solving this problem by introducing a new set of cells which possess the ability to connect to one another and thus form a network. Once created, the network of cells can help the initial cellules by removing their waste and product as well as nourishing them. Our project explores a technique to be able to create the best network of such cells; hence maximizing the amount of metabolic product in the cell culture.
22
Madkour, A. A. M., M. Alamgir Hossain, Keshav P. Dahal, and H. Yu. "Real-time system identification using intelligent algorithms." IEEE, 2004. http://hdl.handle.net/10454/2471.
Full textAbstract:
This research presents an investigation into
the development of real time system identification using
intelligent algorithms. A simulation platform of a flexible
beam vibration using finite difference (FD) method is
used to demonstrate the real time capabilities of the
identification algorithms. A number of approaches and
algorithms for on line system identifications are explored
and evaluated to demonstrate the merits of the algorithms
for real time implementation. These approaches include
identification using (a) traditional recursive least square
(RLS) filter, (b) Genetic Algorithms (GAs) and (c)
adaptive Neuro_Fuzzy (ANFIS) model. The above
algorithms are used to estimate a linear discrete second
order model for the flexible beam vibration. The model is
implemented, tested and validated to evaluate and
demonstrate the merits of the algorithms for real time
system identification. Finally, a comparative performance
of error convergence and real time computational
complexity of the algorithms is presented and discussed
through a set of experiments.
23
Červíček, Karel. "Algoritmické obchodování na burze s využitím strojového učení." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2018. http://www.nusl.cz/ntk/nusl-413302.
Full textAbstract:
Automatization is higly used in stock traiding. The thesis try to exploid optimalization principles and machine learning. Developed and tested stock traiding system proces financial time series and generate optimal strategy
24
Scott, Wesley Dane. "A flexible control system for flexible manufacturing systems." Diss., Texas A&M University, 2003. http://hdl.handle.net/1969.1/158.
Full textAbstract:
A flexible workcell controller has been developed using a three level control hierarchy (workcell, workstation, equipment). The cell controller is automatically generated from a model input by the user. The model consists of three sets of graphs. One set of graphs describes the process plans of the parts produced by the manufacturing system, one set describes movements into, out of and within workstations, and the third set describes movements of parts/transporters between workstations. The controller uses an event driven Petri net to maintain state information and to communicate with lower level controllers. The control logic is contained in an artificial neural network. The Petri net state information is used as the input to the neural net and messages that are Petri net events are output from the neural net. A genetic algorithm was used to search over alternative operation choices to find a "good" solution. The system was fully implemented and several test cases are described.
25
Ajlouni, Naim. "Genetic algorithms for control system design." Thesis, University of Salford, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.308088.
Full text
26
Bob, Chen, and 陳柏成. "Genetic Algorithm for Control of Structure System." Thesis, 1998. http://ndltd.ncl.edu.tw/handle/23687047038030745887.
Full textAbstract:
碩士中原大學
土木工程研究所
86
The purpose of this research is to develop how to apply the genetic algorithm in the sliding mode control system.It is desired that the structure under control can be sustained in safety and stability when subjected to external disturbances. When the classical control method is used for structure system with ATMD, occasionally the improper controls occur and consequently they induce the failure of the structure due to the resonance.The proper control rule can''t be directly derived from the variable structure control system (VSS) theory in the ATMD control system because it isn''t a canonical control form.Besides, the optimum isn''t used in the sliding mode control (SMC) easily.This thesis takes advantage of transfer matrices to obtain the SMC rule and try to combine with the genetic algorithm theory to obtain the GASMC method.This control method is treated sufficiently in the ATMD of building structure systems. This simulation results show that the ATMD control effectively reduces the response of the buildings under external disturbances.In three-degree of freedom system,locating the sensor at the top floor is more effective than at the middle or bottom floor.Because the fitness function is not defined in the FSMC method and finds the optimum solution of the control force, the GASMC method is more economical and more practical.Both the ATMD and the tendon controlller can reduce the dynamic respose in the structures.However the ATMD control uses a frugal energy.Under random external force, the ATMD control also can improve the control effect and prevent the resonance in the system without structure control.
27
Chang, Cheng-Da, and 詹政達. "Genetic Algorithm Based 3D Concreted Program System." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/83359813246985716656.
Full textAbstract:
碩士國立高雄第一科技大學
系統與控制工程研究所
94
Abstract To handle complex programs efficiently, the relations among programs such as association, relationship and coupling strength should be obvious for handler. This paper provides a visual system to reveal the relations of object-oriented (OO) programs with the concretes in a three-dimension space. The relations are measured by the OO metrics, and concretely mapped into objects whose special position are generated using a genetic algorithm (GA). For visual effects, an allocation rules standing for the features of user’s viewpoint: allocated space, total distances, number of intersection and number of projection intersections are proposed. With the chromosomes representing the special position of objects, the GA provides a fitness function to integrate the special allocation rules and find the near-optimal positions to allocate the objects. Finally, JOGL (Java Binding for OpenGL) is adapted to realize the special allocation of concreted objects in the program system for shifting, zooming, rotating and projecting in the three-dimension space.
28
Galvão, Bernardo Gil Câmara. "A multi-population hybrid Genetic Programming System." Master's thesis, 2017. http://hdl.handle.net/10362/25160.
Full textAbstract:
Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced AnalyticsIn the last few years, geometric semantic genetic programming has incremented its popularity, obtaining interesting results on several real life applications. Nevertheless, the large size of the solutions generated by geometric semantic genetic programming is still an issue, in particular for those applications in which reading and interpreting the final solution is desirable. In this thesis, a new parallel and distributed genetic programming system is introduced with the objective of mitigating this drawback. The proposed system (called MPHGP, which stands for Multi-Population Hybrid Genetic Programming) is composed by two types of subpopulations, one of which runs geometric semantic genetic programming, while the other runs a standard multi-objective genetic programming algorithm that optimizes, at the same time, fitness and size of solutions. The two subpopulations evolve independently and in parallel, exchanging individuals at prefixed synchronization instants. The presented experimental results, obtained on five real-life symbolic regression applications, suggest that MPHGP is able to find solutions that are comparable, or even better, than the ones found by geometric semantic genetic programming, both on training and on unseen testing data. At the same time, MPHGP is also able to find solutions that are significantly smaller than the ones found by geometric semantic genetic programming.
29
Weng, Chao-Jung, and 翁昭榮. "Implementation of Genetic Algorithm into Dynamic Reliability System." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/23871337804380842465.
Full textAbstract:
碩士元智大學
工業工程與管理學系
91
In this thesis, a periodic preventive maintenance (PM) of a system with deteriorated components is modeled by genetic algorithm. Simple preventive maintenance and preventive replacement are considered simultaneously for a periodic preventive maintenance schedule of mechanical systems. The life deterioration of components is modeled with dynamic reliability equation, and the effect of PM activities with reliability and failure rate of components under an age reduction model is studied. Reliability, availability and cost are considered simultaneously as the multiple performance evaluation indices in scheduling the optimal maintenance scheme at each PM stage by the genetic algorithm. From this research, the proposed preventive maintenance operation from multiple evaluation aspects is more diversification and eclectic. We present the three performance evaluation indices of the optimal maintenance scheme on every periodic preventive maintenance stage by Contour map. The more reliability of the system is, the more availability it is. As far as a lower reliability system, the Logistics Support cost would increase because of risk cost and corrective maintenance cost increased, especially when the risk cost is more expensive than component preventive maintenance cost. Eventually, the PM. activities chosen on each stage is affected with the improvement factor of components. The main PM. activity of the higher improvement factor of components is 1P; and on the other hand, the worse improvement factor of components, more the opportunity is 2P. implemented, especially to the system required higher reliability.
30
Chen, Pei-Ju, and 陳珮如. "Variable Structure Power System Stabilizer Via Genetic Algorithm." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/72304258294597802585.
Full textAbstract:
碩士國立臺北教育大學
資訊科學系碩士班
101
This thesis proposes a new approach for using genetic algorithm to design variable structure power system stabilizers (PSS). The design of a PSS can be formulated as an optimal linear regulator control problem. However, implementing this technique requires the design of estimators. This increases the implementation and reduces the reliability of control systems. These reasons, therefore, favor a control scheme that uses only some desires state variables, such as torque angle and speed. To deal with this problem, this thesis uses the optimal reduced models to reduce the power system model into two state variables system by each generator. This thesis uses the genetic algorithm to find the switching surface vector and switching control signals, propose an approach “fuzzifier fitness function” to improve the search effect of genetic algorithms, and use variable structure control to find control signal of the generator. Finally, the advantages of the proposed method are illustrated by numerical simulation of the one and two machines-infinite-bus power systems.
31
Lin, Yu-fu, and 林昱甫. "Application of Genetic Algorithm on Control System Synthesis." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/96078735967726046073.
Full textAbstract:
碩士國立成功大學
航空太空工程學系
88
We have combined the genetic algorithm and the neural network (NN) architecture to solve the inverse control problems of linear and nonlinear systems. We have compared the linear inverse filter with the neural network inverse filter, and have discussed the signal lock phenomenon of the filters due to over parameterization. We have applied the inverse control technique on systems with various dynamic characteristics: minimum phase linear systems, minimum phase nonlinear systems, and non-minimum phase nonlinear systems. Computer simulation results from these works have also been compared and discussed. Finally, we conclude this thesis with some suggestion for improving the calculation efficiency of genetic algorithm.
32
Amba, Tushar. "Genetic Algorithm Based Damage Control For Shipboard Power Systems." 2009. http://hdl.handle.net/1969.1/ETD-TAMU-2009-05-282.
Full textAbstract:
The work presented in this thesis was concerned with the implementation of a
damage control method for U.S. Navy shipboard power systems (SPS). In recent years,
the Navy has been seeking an automated damage control and power system management
approach for future reconfigurable shipboard power systems. The methodology should
be capable of representing the dynamic performance (differential algebraic description),
the steady state performance (algebraic description), and the system reconfiguration
routines (discrete events) in one comprehensive tool. The damage control approach
should also be able to improve survivability, reliability, and security, as well as reduce
manning through the automation of the reconfiguration of the SPS network.
To this end, this work implemented a damage control method for a notional Next
Generation Integrated Power System. This thesis presents a static implementation of a
dynamic formulation of a new damage control method at the DC zonal Integrated Flight
Through Power system level. The proposed method used a constrained binary genetic
algorithm to find an optimal network configuration. An optimal network configuration is
a configuration which restores all of the de-energized loads that are possible to be restored based on the priority of the load without violating the system operating
constraints. System operating limits act as constraints in the static damage control
implementation. Off-line studies were conducted using an example power system
modeled in PSCAD, an electromagnetic time domain transient simulation environment
and study tool, to evaluate the effectiveness of the damage control method in restoring
the power system. The simulation results for case studies showed that, in approximately
93% of the cases, the proposed damage algorithm was able to find the optimal network
configuration that restores the power system network without violating the power system
operating constraints.
33
Lin, You-Sheng, and 林佑昇. "An Algorithm Combining Genetic Algorithm and Ant System to Solve Vehicle Routing Problem." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/02186406761765519328.
Full textAbstract:
碩士立德管理學院
應用資訊研究所
94
The Vehicle Routing Problem VRP has already had an extensive discussion and also apply on the actual situation, for example the package delivery services, the post office business deliver, security patrols services, the problem of school bus connect … The proprietor of the store in the process of delivering goods, if the proprietor of stores to deliver goods, the transport cost has very high prices. According to the consumer’s consciousness type inflates quickly and increasing gradually for the service quality, the enterprise requests for the customer’s serves, Therefore, saving the deliver cost become the proprietor of stores most concerned thing. In this research, the situations such as the quantity of delivering and capacity of each demand point are set to be known. We use nearest neighbor algorithm to GA's chromosomes, and then use the genetic algorithm to reproduce, cross over and mutate. The routes are clustered by ant algorithm. Less than 3% inaccuracy of fruiting at several fifty database. And this study proposes suggestions to logistics industry.
34
Guo, Bi-wei, and 郭璧瑋. "System Identification for Car-Pendulum by Using Genetic Algorithm." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/85802366073794800985.
Full textAbstract:
碩士義守大學
電子工程學系碩士班
96
In this study, the main purpose is to identified the car-pendulum’s system by using genetic algorithm. For model based fussy control, we should obtain the system model prior to design a stable control. The car-pendulum system is unstable. Hence, we design the stable controller by pole-placement method. And when, we offer chirp signal to the process in order to measure the input and output data adequately. Moreover, identify the parameters of Takagi-Sugeno (T-S) model by the genetic algorithm form the measured data. In order to enable the parameter fast to receive in the search process also has better essence, we considered develops in the genetic algorithm to join some strategies, for example: migration, elite count and so on. The advantages of the proposed methods are illustrated through simulations.
35
Chen, Yi-Tung, and 陳義東. "W-CDMA System Base Station Deployment Using Genetic Algorithm." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/s6br6p.
Full textAbstract:
碩士國立臺北科技大學
資訊與運籌管理研究所
101
Third generation communication system has now been developed over ten years and has several systems in used. In Taiwan, WCDMA system is mainly proposed and tenants are still in growth. According to Government Statistic Report, number of tenants in 3G system aroused over 21 million, which represents the need of 3G base stations to cover the requirement of increasing users. This paper proposed a multi-criteria system that can deploy the base station in different kinds of deploying environment. In WCDMA system, the system can be evaluated through performance and cost, which the performance of the system is divided into signal coverage, user requirement fulfill rate, base station loading and signal interference. The goal of the research is to maximum the value of each criterion, but to find a deployment with all criteria fulfilled is a NP-Hard problem, so we need to solve the problem through heuristic algorithm. This paper proposed Genetic Algorithm, which is often used in network planning. The natural inspire of algorithm makes the result less to be controlled and affect by human factors, also, genetic algorithm has mutation mechanism to escape from local Optimal Solution to gain more opportunity to reach better deployment. This paper prove the availability of system through experiments and finally obtain the results that the system can be proposed in different kind requirement of the system provider and is well performed than Tabu search in some conditions.
36
Tsai, Cheng-Han, and 蔡承翰. "Genetic Algorithm Optimized Elevator Group Control and Simulation System." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/84151072876571716694.
Full text
37
Wan, Yi-Siao, and 萬奕孝. "The Implementation of AutomaticExecuting System for Distributed Genetic Algorithm." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/74093997120964396466.
Full textAbstract:
碩士輔仁大學
資訊管理學系碩士班
105
The current implementations of computer algorithms usually have heavy consuming time. It is hope to achieve the massive computation capacity through the cloud commutating. Lu & Chen (2014) proposed GA cloud to solve the calculation problem of GA; however, it exists some efficiency and stability problems in the implementation of Microsoft Hyper-V. It is necessary to improve the stability of the GA cloud in Lu & Chen (2014); therefore, this study hopes to re-implement the programs of GA cloud with VMWare software for improving the stability of the GA cloud. VMWare is the most stable and efficient IaaS software on the market. The main components of the proposed GA cloud in this study are listed as follows. 1.Core IaaS: VMWare vSphere 2.Use interface: web page rendering 3.You can upload the GA algorithm required to test various combinations of parameters 4.GA Cloud can be under the VM resource is sufficient, automatically assign the appropriate VM, and automate operations 5.Through the back-end server with a decentralized way, so that computing resources to achieve the fastest and most efficient!
38
Wang, Chun-Chi, and 王俊祺. "Genetic Algorithm combining Risky Analysis for Stock Selection System." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/32286058382739360276.
Full textAbstract:
碩士國立暨南國際大學
資訊工程學系
102
In the study, We proposed a stock selection method, based on the theories “Portfolio Selection” and “A Theory of Market Equilibrium under Conditions of Risk” proposed in 1952 and 1964 respectively, by the Economist Nobel Prize-winner in 1990, Harry Markowitz and William F. Sharpe. We used the methods proposed how to assess the risk value, the expected rate of return and Sharpe indicator used to assess the risk of over-expected of units. Then using Genetic Algorithm(GA) to find the best solution for all stock portfolios based on the fitness function which was designed with the risk of over-expected of units based from Sharpe indicator. For finding which set of parameters is the optimal for solving the stock selection problem using GA and which method of stock portfolios is the best, we also made a lot of experiments to find the most optimal set of parameters and the best method of stock portfolio. Finally, we could get a stock portfolio which could give consideration to risk and the return of investment.
39
Wu, Chen-Cheng, and 吳振成. "Develop the Hardware of Genetic Algorithm for Embedded System." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/31334920863787185909.
Full textAbstract:
碩士中華大學
資訊工程學系碩士班
91
In [1], traveling salesman problem (TSP) algorithm can be applied to find the near optimal multiple sequence alignments (MSAs). Although, TSP is a well-known NP-complete problem. However near optimal solution that is within 1% to 2% of the optimum can be calculated by using genetic algorithms (GA) or branch-and-cut algorithm. GA has been applied to many computation intensive optimization problems, such as TSP. However the execution speed of GA is still too slow when the searching space is large. Especially when GA is implemented by using software approach on the general computer. In this dissertation, we develop the hardware of GA for embedded system to improve the speed up of solving TSP further. In this system, initial population and select operation will be processed by using software approach, while crossover, mutation and fitness operation will be processed by hardware. The major parts of our design were simulated using VHDL Language, and verified using Altera MaxPlus II EDA tools. Comparing hardware approach and software approach, speed up is 27 in worst case and 44 in best case.
40
Hsiao, Yu-Ting, and 蕭玉庭. "A Genetic Algorithm Based Non-intrusiveLoad Monitoring System Design." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/99848342271375459110.
Full textAbstract:
碩士中原大學
電機工程研究所
89
Observing the energy consumption of electric loads, convectional load monitoring system needs to install hardware circuit on each load to be monitored. However, non-intrusive load monitoring system (NILMS) only needs to install a monitoring device on the electric power entrance point to collect the data for energy consumption of the loads by analyzing the signal waveforms collected and identifying the loads accordingly. Therefore, the monitoring facilities and cost needed by the NILMS is less than those of the conventional one. In addition, NILMS is also easier to install, remove and maintain. But the techniques needed for load identification are more sophisticated as compared with the convectional one. The load identification in the NILMS mainly depends on the features of real and active powers. To investigate the efficiency of the other features that can be used for load identification, The thesis builds a feature-searching and load-monitoring identification system by integrating adaptive genetic algorithm with pattern recognition techniques. Based on the measured signals and the simulated data by using the electromagnetic transient program, different combinations of feature vectors are examined to improve the accuracy of the load identification. Two case studies are employed to verify the performance of the NILMS developed. From the results obtained, it is found that the real and active powers are verified to be the most efficient features for the load identification. In addition, the features of current harmonics and the wavelet transformed coefficients of the transient signals are found to be helpful for the load identification. Moreover, this system combines and gives suitable weights to the features, which have superior performance of characterizing the loads, to enhance the load identification ability of the system. The methodologies developed by using adaptive genetic algorithm combined with pattern recognition techniques are suitable for a preliminary NILMS.
41
Lin, Chun-Hung, and 林俊宏. "Adaptive Real-coded Genetic Algorithm for Motor System Identification." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/35255717604174019114.
Full textAbstract:
碩士國立高雄第一科技大學
電機工程研究所碩士班
102
In this paper, the main objective is to identify the parameters of motors, which includes a BLDC motor and an induction motor. The real-coded genetic algorithm (RGA) is adopted to identify all parameters of motors, and the standard genetic algorithm (SRGA) and adaptive genetic algorithm (ARGA) are compared in the rotational angular speeds and fitness values, which are the inverse of square difference of angular speeds. From numerical simulations and experimental results, it is found that the SRGA and ARGA are feasible, the ARGA can effectively solve the problems of slow convergent speed and premature phenomenon, and the ARGA is more accurate in identifying system’s parameters than the SRGA. From the comparisons of ARGAs in identifying parameters of motors, the best ARGA method is obtained and could be applied to any other areas of expertise.
42
Chang, Ming-Hui, and 張名輝. "The application of genetic algorithm in control system design." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/45927822895870442289.
Full textAbstract:
碩士國立成功大學
航空太空工程學系
81
Genetic algorithms (GAs), in the spirit of Darwinians survival -of-the-fittest, are searching algorithms based on the mechanics of natural selection and natural genetics. GAs use random choice as a tool to guide a highly exploitative search through a coding of the parameter space. They have shown to be a powerful tool for solving optimization problems. In this paper, an enhancedgenetic algorithm (EGA) is introduced, which can be employed with better efficiency while preserving the fittest. Examples are given to illustrate the effectiveness of the proposed algorithm. Two design cases are demonstrated. One is a nonlinear satellite attitude control system design. The EGA is applied to search the suitable control parameters to meet the minimum ITAE (Integral of Time multiplied by Absolute Error) requirement. The other is a highly coupled MIMO (Multi- Input Multi-Output) system. The EGA is used to search all controller parameters to decouple the MIMO system, and also meet the minimum ITAE requirement. The results show that the proposed enhanced genetic algorithm is capable of solving high- dimentional optimization problems.
43
Liu, Kai-wei, and 柳楷韋. "The Development of Flow Shop Scheduling System Using Genetic Algorithm." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/67944932464467995531.
Full textAbstract:
碩士義守大學
工業工程與管理學系碩士班
96
Scheduling is a type of resource allocation decision-making solution. Under limited resources, it can effectively manage and allocate the production sequence for each task, so as to achieve the optimal overall performance of its production line. Flow shop scheduling problem belongs to NP problem, and in recent years, evolutionary algorithm has been used to solve these type of compositionality problem. While this research integrated genetic algorithm and Matlab calculation software together, to develop a visualized flow shop scheduling teaching system, with the purpose of discussing the minimum makespan and the hope of finding the optimal work schedule. Besides, it enabled teachers to use the scheduling solution in relevant course teaching, through user interface operation and visualization display. Aiming at the solution of the genetic algorithm, four kinds of Crossover and two kinds of Mutation were adopted and were supported by the elite policy, in order to prevent the evolutionary retrogress, to accelerate the constringency speed of the genetic algorithm, and to find a better solution. After running it through the systematic test, the research compared it with GA-Wang and GA-Lian, and then measured it with mean error rate, to discuss its solution performance. The result indicated that, Order Crossover and Order-based Crossover paired up with Exchange Mutation and Shift Mutation created the best constringency effect, followed by the Position Crossover paired up with Exchange Mutation and Shift Mutation, with the second best effect. Furthermore, the poorest effect was generated by the Cycle Crossover paired up with Exchange Mutation and Shift Mutation.
44
Chang, Chia-Tsang, and 張家瑲. "Application of Neural Network and Genetic Algorithm to System Identification." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/73351083036139978352.
Full textAbstract:
碩士朝陽科技大學
營建工程系碩士班
91
Taiwan is a high seismic zone since it is located at the active arc-continent collision region between the Luzon arc of the Philippine Sea plate and the Eurasian plate. The Chi-Chi Earthquake is the largest inland earthquake occurred in Taiwan during this century. Due to the great damage caused by this earthquake, more and more emphases have been put on the earthquake resistant design of buildings. Dynamic behavior of buildings under earthquakes should be considered in the process of design. In order to realize the dynamic behavior of structural systems subjected to earthquakes, we can determine dynamic models and parameters through various system identification techniques. In this study, it is intended to develop new identification techniques by combining the advantages of both neural network (NN) and genetic algorithm (GA). Firstly, the time history of the ground acceleration and the system parameters of a variety of SDOF systems are used as the input data of neural network, and the time history of the relative acceleration of the respective SDOF systems as the neural network outputs. After the training of the neural network, the network topology used to evaluate the time history of the relative acceleration of the SDOF systems will be captured. This network topology is then employed to replace the procedure for solving the governing (differential) equation when GA is used to identify the system parameters. Furthermore, this topology is used in the identification of the MDOF system subjected to the single input by mode superposition technique. On the other hand, the starting weights of NN are randomly selected and the optimization algorithm used in the training of NN may get stuck in the local minimal. GA is a search method based on natural selection and genetics and is different from conventional optimization methods in several ways. The GA is a parallel and global search technique that searches multiple points, so it is more likely to obtain a global solution. In this regard, a new algorithm of combining GA and NN is proposed here. The GA is employed to search for the starting weights and the NN is used to obtain the network topology. Through the iterative process of selection, reproduction, cross over and mutation, the optimal weight can then be obtained. This proposed algorithm is applied to the Duffing oscillator and Wen’s degrading nonlinear systems. Finally, the accuracy of this method is illustrated by comparing the results of the predicted response with the measured one.
45
Chao, Lin-Ting, and 林廷釗. "Structural Topology Optimization by Artificial Immune System and Genetic Algorithm." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/82667639792839286041.
Full textAbstract:
碩士淡江大學
航空太空工程學系碩士班
97
A methodology of topology optimization design by Artificial Immune System and Genetic Algorithm was used in this study. The finite element analysis software ANSYS was used for structural analysis. The optimal topology design was obtained by the concept of material distribution borrowed from density method with Linear Programming, Artificial Immune System and Genetic Algorithm. The first stage topology design was executed by linear programming, then the 2nd stage was used by Genetic Algorithm to improve the unnecessary and discontinuity element. The final stage was used by somatic hypermutation of Artificial Immune System to employ the different mutation range to eliminate indefinite element which obtained by Genetic Algorithm. Finally, the smallest compliance and reasonable topology design shape were obtain by the above techniques. There are six different structures were discussed in this study. The final results of optimum design was better than the first stage design in two dimensional as well as three dimensional structures. The proposed algorithm in this study was proved effectively.
46
Chiu, Chen-Chih, and 邱禎志. "Satellite Receiving System Based on Genetic Algorithm / Travelling Salesman Problem." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/96204266493153770345.
Full textAbstract:
碩士國立高雄應用科技大學
電子工程系
99
Satellite receiving system can automatically adjust the direction of the satellite antenna to the satellite quickly by a simple button, where the satellite has not been sheltered, and provides more multimedia programs of satellite TV. However, the Travelling Salesman Problem (TSP) will occur when searching satellites, which will delay the response time of the whole system. In order to improve the performance of system, the Travelling Salesman Problem must be optimized. In this thesis, we adopt the Genetic Algorithm to solve Travelling Salesman Problem (GA-TSP) of the satellite receiving system, which can shorten the searching time and improve the system performance. Finally, the obtained results are compared favorably with other methods, and the results show that GA-TSP can upgrade the performance effectively.
47
Chen, Tai-Kang, and 陳泰康. "Design an Efficient Fuzzy System Using an Intelligent Genetic Algorithm." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/73445148250087510180.
Full textAbstract:
碩士逢甲大學
資訊工程學系
88
In this thesis, a method for designing an efficient fuzzy system that consists of a minimal number of fuzzy rules with only a few antecedent fuzzy sets using a novel intelligent genetic algorithm (IGA) is proposed. Recently, the GA-based fuzzy approach is shown to be an effective way to design an efficient evolutionary fuzzy system. The existing GA-based approaches are suitable for the problems with small input variables but not the large input variables’ problems because that the number of fuzzy rules will be exploded as the number of input variables increases (curse of dimensionality). The following requirements must be simultaneously satisfied for developing an optimal evolutionary fuzzy system design: (1) An efficient fuzzy partition approach is essential to cope with the curse of dimensionality resulting from the large input variables. (2) Membership functions must be sufficiently flexible so that they can be adjusted or tuned to optimize the performance of the fuzzy system. (3) Simultaneously determine the membership functions and fuzzy rules to design a fuzzy system with high system performance. (4) Select a minimal number of significant fuzzy rules to construct a compact fuzzy system. (5) The use of heuristics may reduce the availability of an approach. It is desirable to develop an efficient system design without domain experts and heuristics. (6) An efficient evolutionary algorithm in solving large parameter optimization problems (LPOPs) is helpful. To fully satisfy the above requirements, our proposed method without domain experts and heuristics has the following merits: (1) A new flexible generic parameterized membership function with hyperbox partition is proposed to cope with the curse of dimensionality. (2) The parametric genes for coding the membership functions and fuzzy rules, and the control genes for selecting useful input variables and significant fuzzy rules are incorporated into a single chromosome. This means that the participated variables, the membership function of each antecedent fuzzy set, and the fuzzy rules of the evolutionary fuzzy system are simultaneously determined to minimize the number of fuzzy rules and maximize the system performance. (3) The optimal fuzzy system design is formulated as an LPOP. The LPOP is solved using a novel IGA which is superior to the conventional genetic algorithms in solving LPOPs. To fast obtain the accurate solution, simulated annealing (SA) is optionally cooperated with IGA to effectively reduce the length of the chromosome during the revolutionary process. The high performance of the proposed method is illustrated by applying the method to two typical problems, a truck controller problem with small input variables and a classification problem with large input variables, and comparing the performance with the existing approaches. It is shown empirically that the proposed method outperforms the existing methods in the design of optimal fuzzy systems. Furthermore, the proposed method without the significant modification is capable of designing various fuzzy systems with high system performance.
48
Lin, Shih-Guei, and 林士貴. "Integration of Neuro-Fuzzy and Genetic Algorithm to System Identification." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/67168451922901049216.
Full textAbstract:
碩士國立成功大學
航空太空工程學系碩博士班
97
It is known that the training process of a neuro-fuzzy system is easily stuck in local minimum, the purpose of this work is to apply genetic algorithm to tune the weights and the membership functions of a neuro-fuzzy system. In this integrated system, the weighting values of neural network will be coded as genetic population size in binary genetic algorithm. In hence, the fitness function can be defined to calculate the optimizing weighting values. The optimizing weight values can be obtained from simulation result, and the error of simulation can also be reduced. Integrating neuro-fuzzy system and genetic algorithm is shown to have better performance in system identification.
49
Tsai, Hsu-Lung, and 蔡旭龍. "The Diagnostic System by incorporating a Genetic Algorithm and ANN." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/43ds8w.
Full textAbstract:
碩士國立臺北科技大學
機電整合研究所
93
A diagnostic System based on the ANN (artificial neural network) and vibration signal inputs is developed for a piping system in this study. We utilize three methods to extract the features of the piping system. They are (1) the statistic moments of higher orders, (2) the harmonic peaks of the frequency spectrum, and (3) the structure damping signals of the vibration signal. The diagnostic system is a standalone system without any other auxiliary software. The major functions of the diagnostic system include generating vibration symptom signals, pre-processing the signals, diagnosing the piping system. In this study, the experiment focuses on the looseness of the flanged joints in which they always exist due to the unbalanced vibration from motors or pumps. Taking the advantages of this operation signals, the current study take them as the ANN inputs so that the ANN can be verified. On the whole, this study used the back propagation network (BPN) for the main structure of ANN. However, it has been found that the BPN alone tends to raise the problem of slow convergence during the ANN training process. And, it even worse that the BPN may not be able to converge if a poor learning rate is set. For this reason, a genetic algorithm (GA) is purposely added to alleviate the short comings of the BPN. The present study has substantiated that the added GA works much better than that of the BPN alone. This study belongs to the problem of system classification. In order to let the synthesizied GA works properly, the study uses the following steps : First, we used the GA to evolve the ANN’s weight matrices as to search the best initial values. Next, we put the weight matrices back to BPN training. Keep on running until the error level runs below the ending condition. The GA+BPN mode has been proved that it can incorporate the advantages of two traditions methods. The real-time experiments diagnosis results can further verify that the method is feasible and increasing the system’s diagnostic ability. Thus, the current system may be applied to the industries.
50
Chen, Guan-Jhong, and 陳冠中. "Application of Genetic Algorithm for Air-Conditioning System Optimal Operation." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/2f5yca.
Full textAbstract:
碩士國立臺北科技大學
能源與冷凍空調工程系碩士班
97
Though many experts have proposed a range of air-conditioning optimization control methods, they are restricted to optimization of the chiller or affiliated units. The air handing unit and pump do not consume as much power as the chiller; however, the accumulated volume of power consumption can not be overlooked. Currently, most manufacturers use inverters to achieve power-saving through adjusting the speed of the motor, but the interrelationships between units and their attributes have not been taken into consideration. Hence, the lowest power consumption is not achieved. In the past researches, control methods for air-conditioning system operation optimization can be classified into three categories: Optimal Chiller Loading (OCL), Optimal Chiller Scheduling (OCS), and Optimal Chilled Water Supply Temperature. No matter which algorithm is used to achieve the purpose of reducing power consumption, most researches targeted only on optimizing control of the chiller. Therefore, this research combines the factors of the chiller, air handing unit, and district pump to derive the optimal chilled water temperature, supply air flow of the air handing unit, and water flow of the district pump through the “natural selection” theory of Genetic Algorithm (GA) without violating the operation constraints. Through this research, we expect to find the optimal operation parameters setting methods for air-conditioning systems under various environments to achieve overall facility efficiency and reduction of power consumption.