To see the other types of publications on this topic, follow the link: Blast furnace inputs.
Journal articles on the topic 'Blast furnace inputs'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Blast furnace inputs.'
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 journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Orre, Joel, Lena Sundqvist Ökvist, Axel Bodén, and Bo Björkman. "Understanding of Blast Furnace Performance with Biomass Introduction." Minerals 11, no. 2 (2021): 157. http://dx.doi.org/10.3390/min11020157.
Full textAbstract:
The blast furnace still dominates the production and supply of metallic units for steelmaking. Coke and coal used in the blast furnace contribute substantially to CO2 emissions from the steel sector. Therefore, blast furnace operators are making great efforts to lower the fossil CO2 emissions and transition to fossil-free steelmaking. In previous studies the use of pre-treated biomass has been indicated to have great potential to significantly lower fossil CO2 emissions. Even negative CO2 emission can be achieved if biomass is used together with carbon capture and storage. Blast furnace conditions will change at substantial inputs of biomass but can be defined through model calculations when using a model calibrated with actual operational data to define the key blast furnace performance parameters. To understand the effect, the modelling results for different biomass cases are evaluated in detail and the overall performance is visualised in Rist- and carbon direct reduction rate (CDRR) diagrams. In this study injection of torrefied biomass or charcoal, top charging of charcoal as well as the use of a combination of both methods are evaluated in model calculations. It was found that significant impact on the blast furnace conditions by the injection of 142 kg/tHM of torrefied biomass could be counteracted by also top-charging 30 kg/tHM of charcoal. With combined use of the latter methods, CO2-emissions can be potentially reduced by up to 34% with moderate change in blast furnace conditions and limited investments.
2
Bozkurt, Erdoğan, İlhami M. Orak, and Yasin Tunçkaya. "Performance analysis of hot metal temperature prediction in a blast furnace and expert suggestion system proposal using neural, statistical and fuzzy models." Metallurgical Research & Technology 118, no. 3 (2021): 321. http://dx.doi.org/10.1051/metal/2021043.
Full textAbstract:
Blast Furnace (BF) production methodology is one of the most complex process of iron & steel plants as it is dependent on multi-variable process inputs and disturbances to be modelled properly. Due to expensive investment costs, it is critical to operate a BF by reducing operational expenses, increasing the performance of raw material and fuel consumptions to optimize overall furnace efficiency and stability, also to maximize the lifetime. The chemical compositions and temperature of hot metal are important indicators while evaluating the operation, therefore, if the future values of hot metal temperature can be predicted in advance instead of subsequent measuring, then the BF staff can take earlier counteractions on several operational parameters such as coke to ore ratio, distribution matrix, oxygen enrichment rate, blast moisture rate, permeability, flame temperature, cold blast temperature, cold blast flow and pulverized coal injection rate, etc. to control the furnace optimally. In this study, Artificial Neural Networks (ANN) model is proposed combined with NARX (Nonlinear autoregressive exogenous model) time series approach to track and predict furnace hot metal temperature by selecting the most suitable process inputs and past values of hot metal temperatures using the real data which is collected from the BF operated in Turkey during 2 months of operation. Various data mining techniques are applied due to requirements of charge cycling and operating speed of the furnace which secures novelty and effectiveness of this study comparing previous articles. Furthermore, a statistical tool, Autoregressive Integrated Moving Average (ARIMA) model, is also executed for comparison. ANN prediction results of 0.92, 8.59 and 0.41 are found very satisfactory comparing ARIMA (1,1,1) model outputs of 0.73, 97.4 and 9.32 for R2 (Coefficient of determination), RMSE (Root mean squared error) and MAPE (Mean absolute percentage error) respectively. Consequently, an expert suggestion system is proposed using fuzzy if-then rules with 5 × 5 probability matrix design using the last predicted HMT value and the average of the last 5 HMT values to decide furnace’s warming or cooling movements state in mid-term and maintain the operational actions interactively in advance.
3
Nurkkala, Antti, Frank Pettersson, and Henrik Sax^|^eacute;n. "Blast Furnace Dynamics Using Multiple Autoregressive Models with Exogenous Inputs." ISIJ International 52, no. 10 (2012): 1764–71. http://dx.doi.org/10.2355/isijinternational.52.1764.
Full text
4
Ravikrishna, V. Chatti, S. Ashrit Shrenivas, and N. Udpa K. "Development of an ICP-AES technique for the determination of nickel content in blast furnace inputs." Journal of Indian Chemical Society Vol. 90, Nov 2013 (2013): 1993–97. https://doi.org/10.5281/zenodo.5792412.
Full textAbstract:
Chemical Laboratory, R & D and Scientific Services, Tata Steel Limited, Jamshedpur-831 001, Jharkhand, India <em>E-mail</em> : r.chatti@tatasteel.com, shrenivas@tatasteel.com, k.udpa@tatasteel.com The importance of nickel in the steel industry is significant due to a wide variety of applications as an alloying component in stainless steel. In this context, the present paper endeavors to determine the nickel content of different blast furnace (BF) inputs such as iron ore, coal, coke and sinter. This has been done by analyzing the different raw materials using Inductively Coupled Plasma-Atomic Emission Spectroscopy (ICP-AES) technique. The ICP-AES technique was chosen because it was observed that as the content of nickel was very low in these raw materials, it would be difficult to analyze the same using classical methods such as the dimethylglyoxime (gravimetric) method. The major objective of the present study was to deliver an accurate and less-time consuming method based on an instrumental technique, namely, the ICP-AES technique for analysis of nickel (low content) in different blast furnace inputs. In this context, the established method was validated by the evaluation of certified reference materials (CRMs) namely ECRM 681-1 and ECRM 679-1 and thus, it was felt that the present method was very much appropriate for determination of nickel content below 0.01 %.
5
Ahmed, Hesham. "New Trends in the Application of Carbon-Bearing Materials in Blast Furnace Iron-Making." Minerals 8, no. 12 (2018): 561. http://dx.doi.org/10.3390/min8120561.
Full textAbstract:
The iron and steel industry is still dependent on fossil coking coal. About 70% of the total steel production relies directly on fossil coal and coke inputs. Therefore, steel production contributes by ~7% of the global CO2 emission. The reduction of CO2 emission has been given highest priority by the iron- and steel-making sector due to the commitment of governments to mitigate CO2 emission according to Kyoto protocol. Utilization of auxiliary carbonaceous materials in the blast furnace and other iron-making technologies is one of the most efficient options to reduce the coke consumption and, consequently, the CO2 emission. The present review gives an insight of the trends in the applications of auxiliary carbon-bearing material in iron-making processes. Partial substitution of top charged coke by nut coke, lump charcoal, or carbon composite agglomerates were found to not only decrease the dependency on virgin fossil carbon, but also improve the blast furnace performance and increase the productivity. Partial or complete substitution of pulverized coal by waste plastics or renewable carbon-bearing materials like waste plastics or biomass help in mitigating the CO2 emission due to its high H2 content compared to fossil carbon. Injecting such reactive materials results in improved combustion and reduced coke consumption. Moreover, utilization of integrated steel plant fines and gases becomes necessary to achieve profitability to steel mill operation from both economic and environmental aspects. Recycling of such results in recovering the valuable components and thereby decrease the energy consumption and the need of landfills at the steel plants as well as reduce the consumption of virgin materials and reduce CO2 emission. On the other hand, developed technologies for iron-making rather than blast furnace opens a window and provide a good opportunity to utilize auxiliary carbon-bearing materials that are difficult to utilize in conventional blast furnace iron-making.
6
Flynn, Eric, and Stefan Reinartz. "Demonstration of Converting Blast Furnace Gas to High Purity Hydrogen." ECS Meeting Abstracts MA2024-02, no. 50 (2024): 4901. https://doi.org/10.1149/ma2024-02504901mtgabs.
Full textAbstract:
This paper reports on a novel technology, eXEROTM, that is being utilized in a demonstration project at an integrated steelworks in North America to produce hydrogen from blast furnace gas in a single process step. The paper provides an overview of the technology, the project implementation, and results obtained from the field trial. Global average temperatures for the 12 months between June 2023 and May 2024 were the highest on record. The continuing warming of our atmosphere heightens the need for decarbonization of existing infrastructure and industrial processes like steel making. With a growing demand for low carbon intensity hydrogen, conventional methods of production face obstacles involving substantial electricity inputs, infrastructure, and CAPEX, which can conflict with operational and business objectives. Our reactor has proven to be an attractive option for existing plant operations by eliminating the need for significant electricity inputs and infrastructure. The zero-electricity electrolysis technology, trademarked eXEROTM, is based on two gas streams, which are separated by an impermeable electrolyte, and counter-exchange of oxygen ions and electrons. Thus, one of the streams undergoes reduction while the other stream simultaneously undergoes oxidation. Unlike traditional fuel cells or electrolyzers, no current is extracted or delivered to the reactor to drive the process. The overall redox reaction is thermodynamically driven by the different gas compositions across the anode and cathode of the cell, fundamentally described by the Nernst Equation. A mixed conducting electrolyte is used to transport electrons from the anode to the cathode and oxygen ions from the cathode to the anode in the eXERO technology platform. Therefore, with certain chemical compositions at the anode, steam in the cathode will spontaneously dissociate into hydrogen ions and oxygen ions without an external circuit. Like in a traditional solid oxide electrolyzer with an applied external overpotential, electrons flow concurrently from the anode to the cathode, forming hydrogen at the cathode. A demonstration plant utilizing the eXERO technology was designed, fabricated, installed, and commissioned on an operating steel mill facility. The paper includes information pertaining to operational results under actual plant conditions, the impact of industrial feedstocks, and other challenges. Data on the hydrogen produced by the eXERO technology will be covered along with the relevance of utilizing the technology to generate clean hydrogen from blast furnace gas, in order to decarbonize integrated steel production. The significance of this milestone for improving industrial processes, mitigating greenhouse gases and creating multiple paths to an effective and affordable energy transition is significant. To our knowledge, this is the first time this direct conversion has been achieved. It represents a much better way for heavy industries to reach environmental and business objectives.
7
Li, Junfang, Chunjie Yang, and Chong Yang. "Consistent Optimization of Blast Furnace Ironmaking Process Based on Controllability Assurance Soft Sensor Modeling." Sensors 22, no. 12 (2022): 4526. http://dx.doi.org/10.3390/s22124526.
Full textAbstract:
The blast furnace ironmaking process is the core of steel manufacturing, and the optimization of this process can bring enormous economic and environmental benefits. However, previous data-driven optimization methods neglect the uncontrollability of part of the variables in the predictive modeling process, which brings great uncertainty to the optimization results and adversely affects the optimization effect. To address this problem, a consistency optimization framework based on controllability assurance soft sensor modeling is proposed. The method achieves the information extraction of uncontrollable variables in a process-supervised way, and improves the posterior distribution prediction accuracy. The method also proposes an integrated self-encoder regression module, which uses the regression to guide the encoding, realize the construction of latent features, and further improve the prediction accuracy of the model. Integrating the prediction module and the multi-objective gray wolf optimizer, the proposed model achieves the optimization of the blast furnace ironmaking process with only controllable variables as prediction model inputs while being capable of giving uncertainty estimates of the solutions. Empirical data validated the optimization model and demonstrated the effectiveness of the proposed algorithm.
8
Hanna, Ivashchyshyn, Sanytsky Myroslav, Kropyvnytska Tetiana, and Rusyn Bohdan. "STUDY OF LOW-EMISSION MULTI-COMPONENT CEMENTS WITH A HIGH CONTENT OF SUPPLEMENTARY CEMENTITIOUS MATERIALS." Eastern-European Journal of Enterprise Technologies 4, no. 6 (100) (2019): 39–47. https://doi.org/10.15587/1729-4061.2019.175472.
Full textAbstract:
The studies have established the influence of various types of supplementary cementitious materials on physical and mechanical properties and structure formation of low-emission multi-component cements. The results of the granulometric composition examination of main components of multi-component cements were obtained and a comprehensive estimation of their particle size distribution relative to volume and specific surface was performed. It was proved that increase in dispersity of supplementary cementitious materials leads to decrease in their bleeding and increase in activity but simultaneously increases water demand and power consumption for mechanical activation. Efficiency of mechanical activation of main non-clinker components having different characters of activity was compared. Experimental studies have confirmed that the problem of increasing hydraulic activity of granulated blast-furnace slag is solved by increasing content of fractions up to 10 μm in size. However, when preparing highly active granulated blast-furnace slag, energy inputs for grinding significantly grow, especially in ball mills. It should be noted that a shortage of quality slag in the cement industry is expected in the coming years. This necessitates the search for new combinations of supplementary cementitious materials, namely natural zeolites and fly ash which possess excellent pozzolanic properties. Studies of partial and complete replacement of granulated blast-furnace slags in the composition of low-emission cements with clinker factor of 0.50 have shown that necessary indices of early and standard strength are ensured due to optimization of granulometric composition of pozzolanic additives. At the same time, binder strength increases significantly with the age of hardening and exceeds standard strength by 30 % in 90 days. This makes it possible to state that due to the pozzolanic reaction between superfine zeolite, fly ash and calcium hydroxide, the processes of formation of hydrate phases in the intergranular space are stimulated and microstructure of the cement matrix is compacted. It was shown that the use of low-emission multi-component cements modified with superplasticizers of polycarboxylate type provides technological, technical, economic and environmental effects. Thus, there are grounds to state feasibility of obtaining clinker-efficient low-emission multi-component cements by optimizing granulometric composition of supplementary cementitious materials of various kinds in order to reduce power inputs in the technological processes of their production.
9
JARADAT, Mohammed, Mohammad MASSOUD, Ahmad MANASRAH, and Yousef JARADAT. "Prediction of Constituents of Concrete Mixtures Containing Fly Ash and Blast Furnace Slag Using Machine Learning Techniques." Eurasia Proceedings of Science Technology Engineering and Mathematics 32 (December 30, 2024): 275–80. https://doi.org/10.55549/epstem.1602030.
Full textAbstract:
The prediction of concrete mix proportions is of the utmost importance to civil engineers to complete the design process of structures. This process is usually done through a trial-and-error process which involves simple regression techniques and is usually done to achieve a specific strength at a specific age. The incorporation of supplementary cementitious materials into concrete mixtures for environmental purposes has deemed the prediction process more complex and created a need to come up with more advanced techniques. Furthermore, the ability to predict the constituents of concrete mixtures given multiple inputs is still limited. Hence, in this work several machine learning algorithms were utilized to make a prediction regarding mix proportions of concrete mixtures based on concrete compressive strength, concrete age, and density as inputs. Random forest, decision tree, and K-neighbors regressors were used to achieve this objective. Mean squared error as well as root squared error were used to measure the accuracy of the constructed models. Random Forest algorithm obtained the highest accuracy with 98.5%.
10
DUHOUX, M., J. SUYKENS, B. DE MOOR, and J. VANDEWALLE. "Improved long-term temperature prediction by chaining of neural networks." International Journal of Neural Systems 11, no. 01 (2001): 1–10. http://dx.doi.org/10.1142/s012906570100045x.
Full textAbstract:
When an artificial neural network (ANN) is trained to predict signals p steps ahead, the quality of the prediction typically decreases for large values of p. In this paper, we compare two methods for prediction with ANNs: the classical recursion of one-step ahead predictors and a new kind of chain structure. When applying both techniques to the prediction of the temperature at the end of a blast furnace, we conclude that the chaining approach leads to an improved prediction of the temperature and avoidance of instabilities, since the chained networks gradually take the prediction of their predecessors in the chain as an extra input. It is observed that instabilities might occur in the iterative case, which does not happen with the chaining approach. To select relevant inputs and decrease the number of weights in this approach, Automatic Relevance Determination (ARD) for multilayer perceptrons is applied.
11
Han, Shaoyong, Dongsong Zheng, Bahareh Mehdizadeh, et al. "Sustainable Design of Self-Consolidating Green Concrete with Partial Replacements for Cement through Neural-Network and Fuzzy Technique." Sustainability 15, no. 6 (2023): 4752. http://dx.doi.org/10.3390/su15064752.
Full textAbstract:
In order to achieve a sustainable mix design, this paper evaluates self-consolidating green concrete (SCGC) properties by experimental tests and then examines the design parameters with an artificial intelligence technique. In this regard, cement was partially replaced in different contents with granulated blast furnace slag (GBFS) powder, volcanic powder, fly ash, and micro-silica. Moreover, fresh and hardened properties tests were performed on the specimens. Finally, an adaptive neuro-fuzzy inference system (ANFIS) was developed to identify the influencing parameters on the compressive strength of the specimens. For this purpose, seven ANFIS models evaluated the input parameters separately, and in terms of optimization, twenty-one models were assigned to different combinations of inputs. Experimental results were reported and discussed completely, where furnace slag represented the most effect on the hardened properties in binary mixes, and volcanic powder played an effective role in slump retention among other cement replacements. However, the combination of micro-silica and volcanic powder as a ternary mix design successfully achieved the most improvement compared to other mix designs. Furthermore, ANFIS results showed that binder content has the highest governing parameters in terms of the strength of SCGC. Finally, when compared with other additive powders, the combination of micro-silica with volcanic powder provided the most strength, which has also been verified and reported by the test results.
12
Sahraoui, Mohamed, and Tayeb Bouziani. "ANN modelling approach for predicting SCC properties - Research considering Algerian experience. Part I. Development and analysis of models." Journal of Building Materials and Structures 7, no. 2 (2020): 188–98. http://dx.doi.org/10.34118/jbms.v7i2.774.
Full textAbstract:
This paper presents research on the use of artificial neural networks (ANNs) to predict fresh and hardened properties of self compacting concrete (SCC) made with Algerian materials. A multi-layer perceptron network with 5 nodes, 12 inputs, and 5 outputs is trained and optimized using a database of 167 mixtures collected from literature. The inputs for the ANN models are ordinary Portland cement (Cm), polycarboxylate ether superplasticizer (Sp), river sand (RS), crushed sand (CS), dune sand (DS), Gravel 3/8 (G1), Gravel 8/15 (G2), Water (W), Limestone filler (Lim), Marble powder (MP), blast furnace slag (Slag) and natural pozzolan (Pz). Instead, Slump flow (Slump), V-funnel, L-Box, static stability (Pi) and 28 days compressive strength (Rc28) were the outputs of the study. Results indicate that ANN models for data sets collected from literature have a strong potential for predicting 28 days compressive strength. Slump flow, V-funnel time and L-Box ratio could be moderately identified while an acceptable prediction has been obtained for static stability. Results have also confirmed by statistical parameters, Regression plots and residual analysis.
13
Adam, F., J. Wood, and R. Andrews. "Processing of Electronic Scrap with Ausmelt TSL Technology." E3S Web of Conferences 543 (2024): 02007. http://dx.doi.org/10.1051/e3sconf/202454302007.
Full textAbstract:
Continued decreasing of the world’s average copper ore grades, coupled with a meteoric rise in the generation of consumer waste streams, has led to the processing of electronic scrap (e-scrap) and other secondaries assuming increasing importance within the global copper industry. Treatment of these secondary feeds has traditionally been carried out in the Blast furnace, Peirce-Smith converter and/or anode furnace. More recently however, bath smelting processes such as the Ausmelt TSL and Outotec Kaldo technologies have emerged as the preferred option for processing these materials due to their superior environmental performance and flexibility to operate under a wide range of conditions. Furthermore, the ability of these processes to handle a wide range of feed inputs make them ideally placed for the processing of not only e-scrap but also other waste streams from the clean energy transition such as end of life e-mobility batteries and photovoltaic systems. This paper focuses on the processing of electronic scrap and other copper secondaries with Ausmelt TSL technology and discusses specific issues facing secondary copper smelters in relation to impurity management and process offgas handling/cleaning.
14
Sahraoui, M., and T. Bouziani. "ANN modelling approach for predicting SCC properties - Research considering Algerian experience. Part I. Development and analysis of models." Journal of Building Materials and Structures 7, no. 2 (2020): 188–98. https://doi.org/10.5281/zenodo.4074773.
Full textAbstract:
<strong>Abstract.</strong> This paper presents research on the use of artificial neural networks (ANNs) to predict fresh and hardened properties of self compacting concrete (SCC) made with Algerian materials. A multi-layer perceptron network with 5 nodes, 12 inputs, and 5 outputs is trained and optimized using a database of 167 mixtures collected from literature. The inputs for the ANN models are ordinary Portland cement (Cem), polycarboxylate ether superplasticizer (Sp), river sand (RS), crushed sand (CS), dune sand (DS), Gravel 3/8 (G<sub>1</sub>), Gravel 8/15 (G<sub>2</sub>), Water (W), Limestone filler (Lim), Marble powder (MP), blast furnace slag (Slag) and natural pozzolan (Pz). Instead, Slump flow (Slump), V-funnel, L-Box, static stability (Pi) and 28 days compressive strength (Rc28) were the outputs of the study. Results indicate that ANN models for data sets collected from literature have a strong potential for predicting 28 days compressive strength. Slump flow, V-funnel time and L-Box ratio could be moderately identified while an acceptable prediction has been obtained for static stability. Results have also confirmed by statistical parameters, Regression plots and residual analysis.
15
Nguyen, Tu Trung, and Kien Dinh. "An artificial intelligence approach for concrete hardened property estimation." Journal of Science and Technology in Civil Engineering (STCE) - NUCE 14, no. 2 (2020): 40–52. http://dx.doi.org/10.31814/stce.nuce2020-14(2)-04.
Full textAbstract:
An alternative method using Artificial Intelligence (AI) to predict the 28-day strength of concrete from its primary ingredients is presented in this research. A series of 424 data samples collected from a previous study were employed for developing, testing, and validation of Adaptive Neuro-Fuzzy Inference System (ANFIS) models. Seven mix parameters, namely Cement, Blast Furnace Slag, Fly Ash, Water, Superplasticizer, Coarse Aggregate, and Fine Aggregate were used as the inputs of the models while the output was the 28-day compressive strength of concrete. In the first step, different models with various input membership functions were explored and compared to obtain an optimal ANFIS model. In the second step, that model was utilized to predict the compressive strength value for each concrete sample, and to compare with those obtained from the compressive test in laboratory. The results showed that the selected ANFIS model can be used as a reliable tool for predicting the compressive strength of concrete with Root Mean Squared Error values of 5.97 MPa and 7.73 MPa, respectively, for the training and test sets. In addition, the sensitivity analysis results revealed that the accuracy of the proposed model improved with an increase in the number of input parameters/variables.
 Keywords:
 artificial intelligence; adaptive neuro-fuzzy inference system; concrete strength; sensitivity analysis.
16
Rajulwar, Vaishnavi Vijay, Tetiana Shyrokykh, Robert Stirling, et al. "Steel, Aluminum, and FRP-Composites: The Race to Zero Carbon Emissions." Energies 16, no. 19 (2023): 6904. http://dx.doi.org/10.3390/en16196904.
Full textAbstract:
As various regions around the world implement carbon taxes, we assert that the competitiveness of steel products in the marketplace will shift according to individual manufacturers’ ability to reduce CO2 emissions as measured by cradle-to-gate Life Cycle Analysis (LCA). This study was performed by using LCA and cost estimate research to compare the CO2 emissions and the additional cost applied to the production of various decarbonized materials used in sheet for automotive industry applications using the bending stiffness-based weight reduction factor. The pre-pandemic year 2019 was used as a baseline for cost estimates. This paper discusses the future cost scenarios based on carbon taxes and hydrogen cost. The pathways to decarbonize steel and alternative materials such as aluminum and reinforced polymer composites were evaluated. Normalized global warming potential (nGWP) estimates were calculated assuming inputs from the current USA electricity grid, and a hypothetical renewables-based grid. For a current electricity grid mix in the US (with 61% fossil fuels, 19% nuclear, 20% renewables), the lowest nGWP was found to be secondary aluminum and 100% recycled scrap melting of steel. This is followed by the natural gas Direct Reduced Iron–Electric Arc Furnace (DRI-EAF) route with carbon capture and the Blast Furnace-Basic Oxygen Furnace (BF-BOF) route with carbon capture. From the cost point of view, the current cheapest decarbonized production route is natural gas DRI-EAF with Carbon Capture and Storage (CCS). For a renewable electricity grid (50% solar photovoltaic and 50% wind), the lowest GWP was found to be 100% recycled scrap melting of steel and secondary aluminum. This is followed by the hydrogen-based DRI-EAF route and natural gas DRI-EAF with carbon capture. The results indicate that, when applying technologies available today, decarbonized steel will remain competitive, at least in the context of automotive sheet selection compared to aluminum and composites.
17
Prakash A, Krishna, Jane Helena H, and Paul Oluwaseun Awoyera. "Optimization of Mix Proportions for Novel Dry Stack Interlocking Concrete Blocks Using ANN." Advances in Civil Engineering 2021 (June 21, 2021): 1–15. http://dx.doi.org/10.1155/2021/9952781.
Full textAbstract:
This paper proposes novel concrete interlocking blocks made of fly ash and GGBS which are an alternative for the conventional concrete blocks. The artificial neural network (ANN) technique is used to estimate the mechanical strength of interlocking blocks and is verified with experimental investigation. The ANN model is based on the Levenberg–Marquardt principle which is executed using MATLAB. The inputs are given in the percentage ratio of cement: fly ash: crushed stone aggregate (FA): coarse aggregate (CA) for the process of learning, testing, and validation. The selected model is subjected to several trials in terms of mean square error, containing 4 input, 2 sets of 10 hidden layers, and one output components. In this study, a total of 2600 blocks of different mixes were tested as per IS 2185-1 (2005) to assess 3, 7, 14, 21, and 28 days’ strength. The experimental investigations were carried out in two phases. In the first phase, experimental investigations to identify the optimum mix proportions of cement, aggregate, fly ash, and ground granulated blast furnace slag to achieve desired compressive strength was carried out. In the second phase, the identified mix proportions were analysed using ANN to predict the compressive strength of interlocking blocks. The results indicate that the proposed ANN model developed to determine the mechanical strength and cost of interlocking blocks has excellent prediction ability.
18
Zeini, Husein Ali, Duaa Al-Jeznawi, Hamza Imran, Luís Filipe Almeida Bernardo, Zainab Al-Khafaji, and Krzysztof Adam Ostrowski. "Random Forest Algorithm for the Strength Prediction of Geopolymer Stabilized Clayey Soil." Sustainability 15, no. 2 (2023): 1408. http://dx.doi.org/10.3390/su15021408.
Full textAbstract:
Unconfined compressive strength (UCS) can be used to assess the applicability of geopolymer binders as ecologically friendly materials for geotechnical projects. Furthermore, soft computing technologies are necessary since experimental research is often challenging, expensive, and time-consuming. This article discusses the feasibility and the performance required to predict UCS using a Random Forest (RF) algorithm. The alkali activator studied was sodium hydroxide solution, and the considered geopolymer source material was ground-granulated blast-furnace slag and fly ash. A database with 283 clayey soil samples stabilized with geopolymer was considered to determine the UCS. The database was split into two sections for the development of the RF model: the training data set (80%) and the testing data set (20%). Several measures, including coefficient of determination (R), mean absolute error (MAE), and root mean square error (RMSE), were used to assess the effectiveness of the RF model. The statistical findings of this study demonstrated that the RF is a reliable model for predicting the UCS value of geopolymer-stabilized clayey soil. Furthermore, based on the obtained values of RMSE = 0.9815 and R2 = 0.9757 for the testing set, respectively, the RF approach showed to provide excellent results for predicting unknown data within the ranges of examined parameters. Finally, the SHapley Additive exPlanations (SHAP) analysis was implemented to identify the most influential inputs and to quantify their behavior of input variables on the UCS.
19
Amar, Mouhamadou, Mahfoud Benzerzour, Rachid Zentar, and Nor-Edine Abriak. "Prediction of the Compressive Strength of Waste-Based Concretes Using Artificial Neural Network." Materials 15, no. 20 (2022): 7045. http://dx.doi.org/10.3390/ma15207045.
Full textAbstract:
In the 21st century, numerous numerical calculation techniques have been discovered and used in several fields of science and technology. The purpose of this study was to use an artificial neural network (ANN) to forecast the compressive strength of waste-based concretes. The specimens studied include different kinds of mineral additions: metakaolin, silica fume, fly ash, limestone filler, marble waste, recycled aggregates, and ground granulated blast furnace slag. This method is based on the experimental results available for 1303 different mixtures gathered from 22 bibliographic sources for the ANN learning process. Based on a multilayer feedforward neural network model, the data were arranged and prepared to train and test the model. The model consists of 18 inputs following the type of cement, water content, water to binder ratio, replacement ratio, the quantity of superplasticizer, etc. The ANN model was built and applied with MATLAB software using the neural network module. According to the results forecast by the proposed neural network model, the ANN shows a strong capacity for predicting the compressive strength of concrete and is particularly precise with satisfactory accuracy (R² = 0.9888, MAPE = 2.87%).
20
Chu, Li Ming, and Gui Mei Cui. "Predicting blast furnace permeability index: a deep learning approach with limited time-series data." Metallurgical Research & Technology 121, no. 2 (2024): 215. http://dx.doi.org/10.1051/metal/2024015.
Full textAbstract:
The blast furnace permeability index is one of the crucial technical indicators in the ironmaking process of a blast furnace. Given that the conventional models are not entirely suitable for accommodating the intricate characteristics of blast furnace production, this paper explores a comprehensive approach that involves data mining, the sparrow search algorithm (SSA), convolutional neural networks (CNNs), and gated recurrent unit networks (GRUs) for predicting the blast furnace permeability index. Initially, to address the multi-noise nature of blast furnaces, outliers are eliminated, and a Kalman filter is devised for denoising purposes. Subsequently, in consideration of the nonlinear and substantial time-delay features of blast furnaces, the maximal information coefficient (MIC) method is employed for time-delay alignment, followed by the selection of model input variables based on process analysis and relevance. Subsequent to this, the SSA-CNN-GRU model is established. Within the modeling process, a one-dimensional convolutional neural network is utilized to extract distinct process variable features, thus further resolving the interdependence among blast furnace data. Ultimately, the effectiveness, accuracy, and advancement of the proposed method are validated using real production data.
21
Chaika, O. L., B. V. Kornilov, V. V. Lebid, A. O. Moskalyna, Ye I. Shumelchyk, and M. H. Dzhyhota. "Implementation of mathematical models of material and heat balances of blast furnace smelting as part of the ACS TP of PJSC "MK "Azovstal"." Fundamental and applied problems of ferrous metallurgy 36 (2022): 82–94. http://dx.doi.org/10.52150/2522-9117-2022-36-82-94.
Full textAbstract:
On the basis of blast furnace operation data of PJSC "MK "Azovstal", an information system has been developed, which is based on mathematical models of material and heat balances of blast furnace smelting developed at the Institute of Ferrous Metallurgy of the National Academy of Sciences of Ukraine. The calculation of the material balance is carried out according to the "accounting system" of V. P. Izhevskii. The thermal energy model of I. D. Semikin is used to calculate the heat balance, which was developed for use in blast furnace production by O. V. Borodulin. The article describes the information system of calculating mathematical models. The information system allows you to calculate balances in automatic mode (collection of data from automatic control system of technological process (ACS TP) and calculation of material and heat balances for the selected period) and in manual mode (calculation of forecast periods to determine reserves for increasing the energy efficiency of blast furnace smelting). The models were adapted by calculating the material and heat balances of blast furnace melting and determining the inconsistencies. Monthly calculations of the material and heat balances of the blast furnaces were performed to adapt the models installed in the ACS TP of the blast furnace workshop of PJSC "MK "Azovstal". Inconsistencies in the overall material balances of the furnaces (the difference between the total input of materials into the furnace and smelting products) and by components (iron, carbon, etc.) were determined. It was established that when using the estimated amount of blast furnace dust at all blast furnaces of PJSC "MK "Azovstal", the amount of discrepancy between the arrival and consumption of materials lies within the credible range of error (<1,5%). Using the results of the calculation of heat balances, a comparison of the Inconsistencies of the blast furnaces was made (the ratio of the calculated indicators to the actual ones). Mathematical models of balances were implemented as part of the ACS TP of the blast furnace workshop of PJSC "MK "Azovstal" and were used to assess deviations from production norms, consumption of coke and conventional fuel, as well as forecast the possibility of improving the technical and economic indicators of smelting.
22
Tran, Van Quan, Hai-Van Thi Mai, Thuy-Anh Nguyen, and Hai-Bang Ly. "Investigation of ANN architecture for predicting the compressive strength of concrete containing GGBFS." PLOS ONE 16, no. 12 (2021): e0260847. http://dx.doi.org/10.1371/journal.pone.0260847.
Full textAbstract:
An extensive simulation program is used in this study to discover the best ANN model for predicting the compressive strength of concrete containing Ground Granulated Blast Furnace Slag (GGBFS). To accomplish this purpose, an experimental database of 595 samples is compiled from the literature and utilized to find the best ANN architecture. The cement content, water content, coarse aggregate content, fine aggregate content, GGBFS content, carboxylic type hyper plasticizing content, superplasticizer content, and testing age are the eight inputs in this database. As a result, the optimal selection of the ANN design is carried out and evaluated using conventional statistical metrics. The results demonstrate that utilizing the best architecture [8–14–4–1] among the 240 investigated architectures, and the best ANN model, is a very efficient predictor of the compressive strength of concrete using GGBFS, with a maximum R2 value of 0.968 on the training part and 0.965 on the testing part. Furthermore, a sensitivity analysis is performed over 500 Monte Carlo simulations using the best ANN model to determine the reliability of ANN model in predicting the compressive strength of concrete. The findings of this research may make it easier and more efficient to apply the ANN model to many civil engineering challenges.
23
Li, Guanghui, Chen Liu, Zhengwei Yu, et al. "Energy Saving of Composite Agglomeration Process (CAP) by Optimized Distribution of Pelletized Feed." Energies 11, no. 9 (2018): 2382. http://dx.doi.org/10.3390/en11092382.
Full textAbstract:
The composite agglomeration process (CAP) aims at sintering a pelletized feed and a matrix feed together to produce a high-quality burden for a blast furnace. The pelletized feed is balled from fine iron concentrate or refractory iron-bearing resources, while the matrix feed is granulated from iron ore fines, fuels, fluxes and so on. Through mathematical calculation, heat accumulation regularity and heat-homogenizing of the sinter bed are acquired in CAP when pelletized feed is uniformly distributed. Then they are studied in the composite agglomeration process with optimized pelletized feed distribution, which is a novel and perfect sinter bed structure. Results show that large heat input gaps exist in the sinter bed under condition of even sinter mixture distribution, and it is very difficult to realize bed heat-homogenization by directly varying the solid fuel dosage among each layer. An optimized pelletized feed distribution realizes more heat in the upper layer together with heat-homogenization of the middle-lower layer when the proportions of pellets increase first in the middle-upper layer and then decrease in the middle-lower layer of the sinter bed. Under these circumstances, the sinter bed has much better available accumulation ratios with a maximum value of 78.29%, and possesses a greater total heat input of 6754.27 MJ when the coke breeze remains at the original dosage. To make full use of the available heat accumulation and adjust the pellet distribution, a good energy saving effect is obtained because the coke breeze mass declines by 13.91 kg/t-sinter. The current gross heat inputs of each unit are reduced remarkably, leading to a total heat input decrease of 25.95%. In pot tests of CAP, the differences of thermal parameters in whole bed are obviously reduced with the optimized pelletized feed distribution, which contributes to sinter homogeneity and energy savings.
24
Esparham, Alireza, Nikolai Ivanovich Vatin, Makhmud Kharun, and Mohammad Hematibahar. "A Study of Modern Eco-Friendly Composite (Geopolymer) Based on Blast Furnace Slag Compared to Conventional Concrete Using the Life Cycle Assessment Approach." Infrastructures 8, no. 3 (2023): 58. http://dx.doi.org/10.3390/infrastructures8030058.
Full textAbstract:
By posing the question of what will be the definition of sustainable development in the future, it can almost be seen that the principle of “no waste” and the production of new materials with less of a negative environmental impact will have a high priority. To further develop environmentally friendly materials, it is necessary to know about the environmental drivers of new materials as well as to evaluate the environmental effects of conventional materials in construction. According to the definitions of sustainable development and sustainable materials, materials with characteristics such as having low energy consumption, sufficient durability, good physical and chemical properties, while simultaneously reducing pollution should be used. Geopolymer materials may be a reasonable option. In this research, two production processes based on blast furnace slag and ordinary concrete (Portland cement) for one cubic meter of geopolymer concrete have been investigated. To investigate, inputs (materials and energy) and outputs (relevant environmental pollutants) of both systems were determined and a life cycle assessment (LCA) was measured using the Center of Environmental Science of Leiden University (CML) and cumulative exergy demand (CED) quantification methods of SimaPro V.9 software. The results showed that the production system of one cubic meter of conventional concrete has maximum environmental effects in all classes except in the destruction of the ozone layer, and the system of producing one cubic meter of geopolymer concrete based on slag has much less environmental effects than the normal concrete system. It also consumes 62% less directly during its lifetime. As a result, geopolymer concrete may be a suitable alternative to traditional concrete as a sustainable material.
25
Spirin, N. A., O. P. Onorin, A. S. Istomin, and I. A. Gurin. "Study of transient processes in a blast furnace based on the heat exchange scheme analysis." Ferrous Metallurgy. Bulletin of Scientific , Technical and Economic Information 76, no. 2 (2020): 132–38. http://dx.doi.org/10.32339/0135-5910-2020-2-132-138.
Full textAbstract:
A blast furnace is a complicated metallurgical facility, which is characterized by considerable delay and inertia in the flow of heat and mass exchange. Therefore, the analysis of transient processes based on modern ideas about heat transfer is an important issue in solving technological problems of blast furnace smelting managing. A two-stage heat transfer scheme along the height of a blast furnace of modern technology presented. When studying the thermal state of a blast furnace as a control object, it is advisable to divide it into two thermal zones - the upper zone and the lower zone. The border between the zones is located in the upper part of the mixed reduction region, between the start level of coke carbon gasification and the horizon below which iron oxides are directly reduced. It was shown, that the upper and lower thermal zones have fundamental differences in heat exchange conditions and are interconnected through the index of iron direct reduction degree. The transient processes of silicon variation in the hot metal studied at variation of iron ore load, natural gas flow rate, temperature and humidity of the hot blast, oxygen content in the hot blast and slag basicity. It was shown that the oscillatory transition process is observed in case, after applying the perturbation, it will have the opposite effect on the thermal conditions of the lower and the upper stages of heat exchange in the blast furnace. The iron ore load, hot blast humidity and slag basicity were found to be the most predictable input parameters affecting the concentration of silicon in hot metal. Change in oxygen concentration in hot blast and natural gas consumption have an alternating character of influence on thermal conditions of the blast-furnace hearth. At that, the characteristics of the transient processes of blast furnaces through various channels of action vary and depend significantly on the properties of the smelted raw materials, design and operational parameters of the furnaces
26
Tunckaya, Yasin. "Performance assessment of permeability index prediction in an ironmaking process via soft computing techniques." Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering 231, no. 6 (2016): 1101–13. http://dx.doi.org/10.1177/0954408916654199.
Full textAbstract:
Permeability index is a crucial productivity indicator of the lower zone in blast furnaces to maintain the operation, energy consumption, and hot liquid metal production rates during the ironmaking process. Blast furnace operation parameters such as coke-to-ore ratio, wall pressures and temperatures, flame temperature, top gas pressure, temperature and composition, hot blast pressure and temperature, sounding levels, etc. and also the level of hot liquid metal and slag in the bottom of furnace, influence the permeability phenomenon directly. Hence, fluctuations and instantenous variations of permeability index parameter should be avoided by controlling inadequate drainage cycles and operational factors to achieve more efficient and stable operation in the furnaces. In this study, permeability index parameter of the Erdemir Blast Furnace #1, located in Turkey, is modeled and experimental computing work is carried out to assess the operation performance of the furnace, depending on selected input parameters. The demanding artificial intelligence and soft computing techniques, artificial neural networks and adaptive neural fuzzy inference system, and a well-known statistical tool, autoregressive integrated moving average model are executed throughout the study using previous furnace data, received during one day of operation. Selected performance measures, coefficient of determination ( R2) and root mean squared error, are used to compare the forecasting accuracy of proposed models. Consequently, the most satisfactory forecasting model of the study, adaptive neural fuzzy inference system, is proposed to be integrated into the plant control system as an expert modeler.
27
Bailera, Manuel, Takao Nakagaki, and Ryoma Kataoka. "Revisiting the Rist diagram for predicting operating conditions in blast furnaces with multiple injections." Open Research Europe 1 (November 29, 2021): 141. http://dx.doi.org/10.12688/openreseurope.14275.1.
Full textAbstract:
Background: The Rist diagram is useful for predicting changes in blast furnaces when the operating conditions are modified. In this paper, we revisit this methodology to provide a general model with additions and corrections. The reason for this is to study a new concept proposal that combines oxygen blast furnaces with Power to Gas technology. The latter produces synthetic methane by using renewable electricity and CO2 to partly replace the fossil input in the blast furnace. Carbon is thus continuously recycled in a closed loop and geological storage is avoided. Methods: The new model is validated with three data sets corresponding to (1) an air-blown blast furnace without auxiliary injections, (2) an air-blown blast furnace with pulverized coal injection and (3) an oxygen blast furnace with top gas recycling and pulverized coal injection. The error is below 8% in all cases. Results: Assuming a 280 tHM/h oxygen blast furnace that produces 1154 kgCO2/tHM, we can reduce the CO2 emissions between 6.1% and 7.4% by coupling a 150 MW Power to Gas plant. This produces 21.8 kg/tHM of synthetic methane that replaces 22.8 kg/tHM of coke or 30.2 kg/tHM of coal. The gross energy penalization of the CO2 avoidance is 27.1 MJ/kgCO2 when coke is replaced and 22.4 MJ/kgCO2 when coal is replaced. Considering the energy content of the saved fossil fuel, and the electricity no longer consumed in the air separation unit thanks to the O2 coming from the electrolyzer, the net energy penalizations are 23.1 MJ/kgCO2 and 17.9 MJ/kgCO2, respectively. Discussion: The proposed integration has energy penalizations greater than conventional amine carbon capture (typically 3.7 – 4.8 MJ/kgCO2), but in return it could reduce the economic costs thanks to diminishing the coke/coal consumption, reducing the electricity consumption in the air separation unit, and eliminating the requirement of geological storage.
28
Zagoruiko, Mikhail Gennadievich, Sergei Anatolievich Pavlov, and Igor Andreevich Bashmakov. "Investigation of aerodynamics in combustion of vegetative waste on isothermal models." Agrarian Scientific Journal, no. 10 (October 25, 2023): 168–73. http://dx.doi.org/10.28983/asj.y2023i10pp168-173.
Full textAbstract:
Modern agricultural vehicles contain a large number of components, which include micro Abstract. Conventional furnaces using alternative fuels, such as vegetable waste (VW), are widely used instead of furnaces operating on conventional fuels. The furnaces aggregated with dryers of SZT and SP type are widely used in agriculture and food industry. Two models with a suspended bed were investigated: with flare-vortex and cyclone-vortex modes. The first model assumes the presence of an inclined grate in a rectangular chamber with a concentrated supply of secondary blast, primary blast with material is supplied above the grate in its lower part, and the second model assumes a cylindrical-shaped chamber with primary air inlet in the center and cyclonic secondary blast inlet at a certain height. This scheme is close to the first, only in the lower part of the model concentrated input of primary blast with material. The methodology of aerodynamics studies included: feeding of material from the hopper; material cutoff after steady-state mode; collection and weighing of fallen particles from the model; determination of the time of material presence in the model by labeled particles. Modeling of aerodynamics for different schemes of furnace process organization showed the possibility of creating two-span or single-span furnace blocks depending on the required operating mode. The results of comparative studies of aerodynamics of flare-vortex and cyclone-vortex modes are given. The results of comparative studies of aerodynamics of flare-vortex and cyclone-vortex modes are given. Optimal blowing parameters, secondary and primary air ratio, furnace design parameters contributing to the maximum specific volume heat stress are determined.
29
Kundu, Chitresh, Prabal Patra, Bipan Tudu, and Dibyayan Patra. "Measurement of Temperature Dependent Dielectric Constant of Coal Samples for Burden Surface Profiling at Blast Furnace." Journal of Experimental Techniques and Instrumentation 4, no. 2 (2021): 38–51. http://dx.doi.org/10.30609/jeti.v4i2.12584.
Full textAbstract:
Blast furnaces (BFs) are the key receptacles of iron and steel smelting. Iron ore, coke and limestone are some of the raw materials that are used in the process of iron making and the charging operation needs to be accomplished by accurately estimating the current depth of the burden surface. To accomplish the goal of global class steel production, burden profile measurement and monitoring is vital. This measuring and monitoring help in augmenting the best usage of charge materials and energy consumptions.
 Radar based measurement is best for determine the level and profile of the burden inside the furnace. However, for the optimal operation of the radar, it is important know the dielectric constant of the material. There are many approaches to determine the dielectric constant like capacitive methods, transmission line methods, cavity resonator methods, open cavity methods and so on. For this study the cavity resonator method is has been used for measuring the permittivity of coal samples. The reflection capability of electromagnetic waves by coal is a function of its dielectric properties which is also has a dependency on temperature. The results presented in this paper will provide essential design input for radar-based measurements at blast furnace, especially for burden profiling at blast furnaces.
30
Tiwari, Hari Prakash, Vishwesh M. Shisani, Bhavendra Kumar Sahu, Rabindra Kumar Sabat, and Damodar Mittal. "Influence of the prime hard coking coal in stamp charge cokemaking: true or false." Metallurgical Research & Technology 117, no. 4 (2020): 412. http://dx.doi.org/10.1051/metal/2020046.
Full textAbstract:
The production of hot metal through the blast furnace route is stilled the most cost-effective and highly productive process and probably remains the coming decades besides developed many alternative ironmaking technologies. In the recent past, the working volume of the blast furnace has been increased drastically to increase the blast furnace productivity. This means the blast furnace performance is more correlated to specific productivity which measures the efficiency in terms of ton hot metal. These modern blast furnaces favour high quality of coke, i.e. high coke CSR and M40 value, high iron content sinter and pellets. These high quality of input raw materials increased blast furnace efficiency and productivity. Generally, cokemakers increases the ratio of prime hard coking coal in the coal blend to achieve the high quality of coke. This increase in prime hard coking coal is not desirable for coke oven batteries because it creates high oven wall pressure and high coke cost and also not suitable for raw material security. The present investigation highlights few cases which clearly show that the high quality of coke (coke CSR: 69–71) may be easily produced with the optimal proportion of prime hard coking coal in the blend if the selection of coals is proper. Results confirmed that upto 30% primary hard coking coal with 15% non-coking coal in the coal blend produce an excellent quality of coke which naturally requires a careful selection on the blend component. The optimum composite coking potential (CCP) value of 4.6–4.9 is the ideal value for producing coke CSR in the range of 69–71 in recovery stamp charge cokemaking process in the real-time plant operation. Therefore, it is necessary to select the right coals for the coal blend based on the adopted cokemaking technologies to conserve the reserve of prime hard coking coal, oven health and cost-effectiveness.
31
Tang, Yi Xuan, Yeong Huei Lee, Mugahed Amran, et al. "Artificial Neural Network-Forecasted Compression Strength of Alkaline-Activated Slag Concretes." Sustainability 14, no. 9 (2022): 5214. http://dx.doi.org/10.3390/su14095214.
Full textAbstract:
The utilization of ordinary Portland cement (OPC) in conventional concretes is synonymous with high carbon emissions. To remedy this, an environmentally friendly concrete, alkaline-activated slag concrete (AASC), where OPC is completely replaced by ground granulated blast-furnace slag (GGBFS) industrial waste, is one of the currently pursued research interests. AASC is not commonly used in the construction industry due to limitations in experience and knowledge on the mix proportions and mechanical properties. To circumvent great labour in the experimental works toward the determination of the optimal properties, this study, therefore, presents the compressive strength prediction of AASC by employing the back-propagation artificial neural network (ANN) modelling technique. To construct this model, a sufficiently equipped experimental databank was built from the literature covering varied mix proportion effects on the compressive strength of AASC. For this, four model variants with different input parameter considerations were examined and the ideal ANN architecture for each model with the best input number–hidden layer neuron number–output number format was identified to improve its prediction accuracy. From such a setting, the most accurate prediction model with the highest determination coefficient, R2, of 0.9817 was determined, with an ANN architecture of 8-18-1 containing inputs such as GGBFS, a fine to total aggregate ratio, sodium silicate, sodium hydroxide, mixing water, silica modulus of activator, percentage of sodium oxide and water–binder ratio. The prediction accuracy of the optimal ANN model was then compared to existing ANN-based models, while the variable selection was compared to existing AASC models with other machine learning algorithms, due to limitations in the ANN-based model. To identify the parametric influence, the individual relative importance of each input variable was determined through a sensitivity analysis using the connection weight approach, whose results indicated that the silica modulus of the activator and sodium silicate greatly affected the AASC compressive strength. The proposed methodology demonstrates that the ANN-based model can predict the AASC compressive strength with a high accuracy and, consequently, aids in promoting the utilization of AASC in the construction industry as green concrete without performing destructive tests. This prediction model can also accelerate the use of AASC without using a cement binder in the concrete matrix, leading to produce a sustainable construction material.
32
Lavercombe, Abigail, Xu Huang, and Sakdirat Kaewunruen. "Machine Learning Application to Eco-Friendly Concrete Design for Decarbonisation." Sustainability 13, no. 24 (2021): 13663. http://dx.doi.org/10.3390/su132413663.
Full textAbstract:
Cement replacement materials can not only benefit the workability of the concrete but can also improve its compressive strength. Reducing the cement content of concrete can also lower CO2 emissions to mitigate the impact of the construction industry on the environment and improve energy consumption. This paper aims to predict the compressive strength (CS) and embodied carbon (EC) of cement replacement concrete using machine learning (ML) algorithms, i.e., deep neural network (DNN), support vector regression (SVR), gradient boosting regression (GBR), random forest (RF), k-nearest neighbors (kNN), and decision tree regression (DTR). Not only is producing an optimal ML model helpful for predicting accurate results, but it also saves time, energy, and costs, compared to conducting experiments. Firstly, 367 pieces of experimental datasets from the open literature were collected, in which cement was replaced with any of the cementitious materials. Secondly, the datasets were imported into the ML models, whose parameters were tuned by the grid search algorithm (GSA). Then, the prediction performance, the coefficient of determination (R2), the prediction accuracy, and the root mean square error (RMSE) were employed to indicate the prediction ability of the ML models. The results demonstrate that the GBR models perform the best prediction of the CS and EC. The R2 of the GBR models for predicting the CS and EC are 0.946 and 0.999, respectively. Thus, it can be concluded that the GBR models have promising abilities for design assistance in cement replacement concrete. Finally, a sensitivity analysis (SA) was conducted in this paper to analyse the effects of the inputs on the CS and EC of the cement replacement concrete. Pulverised fuel ash (PFA), blast-furnace slag (GGBS), Expanded perlite (EP), and Silica fume (SF) were noticed to affect the CS and EC of cement replacement concrete significantly.
33
Salles Melo Lima, Marcio, Enes Eryarsoy, and Dursun Delen. "Predicting and Explaining Pig Iron Production on Charcoal Blast Furnaces: A Machine Learning Approach." INFORMS Journal on Applied Analytics 51, no. 3 (2021): 213–35. http://dx.doi.org/10.1287/inte.2020.1058.
Full textAbstract:
Pig iron, the source for a variety of iron-based products, is traded in commodity markets. Therefore, enhanced productivity has significant economic implications for the producers. Pig iron is mainly produced inside of tall, vertical, thermodynamic reactors called blast furnaces that run 24 hours a day. The blast furnaces are too complex to model explicitly and are generally regarded as black boxes. In this study, we design, develop, and deploy novel machine learning models on a rich data sample covering more than 20 production variables spanning nine years of actual operational period, collected at one of the largest pig iron production plants in Brazil. We show that, given the blast furnace parameters, machine learning models are capable of unveiling novel insights by illuminating the black box and successfully predicting production levels at different configurations. These prediction models can be used as decision aids to improve production efficiencies. We also perform a sensitivity analysis of the trained models to identify and rank the input variables according to their relative importance. We present our findings, which are largely in line with the existing literature, and confirm their validity, practicality, and usefulness through consultations with subject matter experts.
34
Xiaojie, Liu, Zhang Yujie, Li Xin, Liu Ran, Zhang Zhifeng, and Chen Shujun. "Control of silicon content in blast furnace iron based on GRA–LSTM–BAS prediction methods." Ironmaking & Steelmaking: Processes, Products and Applications 51, no. 2 (2024): 127–38. http://dx.doi.org/10.1177/03019233231221676.
Full textAbstract:
In blast furnace smelting, the silicon content in molten iron is an important indicator of the temperature trend of the blast furnace. Due to the multi scale, non-linear, large time delay and strong coupling characteristics of the blast furnace smelting process, the control effect of silicon content in hot metal is often not ideal. Therefore, finding an effective and accurate method for controlling silicon content in hot metal is very important for blast furnace smelting. Based on this, this paper proposes a prediction and control model for silicon content in hot metal of blast furnace based on GRA–LSTM–BAS. Based on this, this paper proposes a prediction and control model for silicon content in hot metal of blast furnace based on GRA–LSTM–BAS. Firstly, the original data set is processed using wavelet analysis and normalisation processing methods. Secondly, the gray relational analysis (GRA) method is used to analyse the correlation between the input variables of the model to determine the input parameters of the model. Subsequently, a long short-term memory (LSTM) prediction model was established to obtain silicon content values at future times through feedback correction. The model was trained and tested by on-site collected data and compared with the support vector machine (SVM) model. The results show that the LSTM model can quickly and accurately predict the silicon content in hot metal, and has a good guiding significance for actual blast furnace production. Finally, the control model for silicon content in molten iron is optimised iteratively by combining the beetle antennae search algorithm (BAS algorithm). Feedback and update of the results in the model are done in real time according to errors, forming a closed-loop controller to maintain the silicon content in molten iron at an appropriate level and achieve optimal control of the silicon content.
35
Liu, Wenhan, Hongli Wang, and Liye Shi. "Predictive control of Si content in blast furnace smelting based on improved SA-BP." Journal of Mines, Metals and Fuels 69, no. 5 (2021): 155. http://dx.doi.org/10.18311/jmmf/2021/28076.
Full textAbstract:
Blast furnace smelting process is a highly complex nonlinear dynamic process, its purpose is to refining the quality of liquid iron. From the point of view of chemical reaction kinetics, the main chemical reactions in the blast furnace are as many as 108 kinds, and the high complexity is obvious. From the point of view of hydrodynamics, there are three-phase mixed compressible viscous fluids in the blast furnace smelting process. The hydrodynamic equation is nonlinear, high-dimensional and high-coupling. In addition, the blast furnace smelting process has the characteristics of time-varying, high-dimensional, distributed parameters and other characteristics of the complex conditions and the failure of the operation under the conditions of the test, making the blast furnace smelting process automation and furnace temperature precision control to become metallurgical workers face the problem. In this study, from the data point of view, to explore the furnace temperature can be characterized by [Si] content prediction. Based on the data of 1000 furnace blast furnace, an accurate and reasonable prediction model of Si content in blast furnace is established. First of all, through the calculation of correlation coefficients of various factors and the time trend diagram, the general lag time between each parameter and Si content in the process of blast furnace production is obtained. Through correlation and analysis of the correlation between lag time, before and after the two largest furnace, with improved simulated annealing algorithm to determine the optimal initial weights, the content of Si, the N furnace of S content, the quantity of coal and air PML FL as input, the contents of Si in n+1 furnace as output to establish dynamic prediction model of improved SA-BP neural network based. Finally, the data used to detect the model is brought into the model to be tested, the error is analyzed, and the error local map is used to express the error visually. The model is tested.
36
Kassim, Daria, Yevhen Chuprynov, Kateryna Shmeltser, Iryna Liakhova, and Maryna Korenko. "Justification of methodical approaches to determining the theoretical fuel combustion temperature in a blast furnace when changing the parameters of the melting mode." Economics and technical engineering 1, no. 2 (2023): 115–27. http://dx.doi.org/10.62911/ete.2023.01.02.09.
Full textAbstract:
Based on the study of the practical experience of blast furnace smelting with the injection of pulverized coal fuel on a blast furnace with a useful volume of 5,000 m3, the causes of frequent cases of deformation and burning of air nozzles and coolers were determined. In particular, such reasons include a significant unevenness of the length of the combustion zones in front of the tuyeres around the mine circle and an irrational change in the gas flow distribution along the blast furnace radius. In turn, this is due to the presence of a large unevenness in the distribution of the costs of blowing and pulverized coal fuel along the tuyeres, and therefore the theoretical temperature and output of mine gas along the circumference and radius of the mine blast furnace. Therefore, when determining the possible consumption of any fuel additive, it will be difficult to focus on the value of the theoretical combustion temperature, as a complex parameter of the fuel regime, which characterizes the temperature-oxidative conditions of the transformations of fuel additives in the nozzle cells. This especially applies to the known methods of determining this parameter, which are not sufficiently reliable in case of significant fluctuations in the input melting conditions. The purpose of this work is to develop methodical approaches to determine the theoretical fuel combustion temperature based on the actually controlled blowing parameters when natural gas and PUT are blown into the blast furnace on the basis of stoichiometric ratios and fuel technical analysis data. A method of determining the theoretical combustion temperature in the tuyere when natural gas and/or pulverized fuel is blown into the blast furnace is proposed, using operational information about blowing parameters, consumption of natural gas and pulverized fuel, which are taken from control and measuring devices and automation systems at the central control panel of the blast furnace. On the basis of the developed method of determining the output of mine gas and the theoretical temperature of fuel combustion, it is possible to solve practical problems related to the optimization of blast parameters of blast furnace smelting, as well as when blowing pulverized coal fuel.
37
Zhang, Wan. "The Static Impact Analysis of a Blast Furnace Equipment Load on the Structure in Taiyuan." Applied Mechanics and Materials 275-277 (January 2013): 1118–22. http://dx.doi.org/10.4028/www.scientific.net/amm.275-277.1118.
Full textAbstract:
There are a variety of forms of industrial construction equipment load .The structural design engineers replace equipment load by equivalent load to analyze structure while it is impossible to reflect the combination of equipment and structure or synthetically dynamic characteristics exactly. This article use SAP2000 to provide three kinds of load input modes for blast furnace equipment in chemical buildings, and that blast furnace equipment should be involved in the overall structure of the modeling analysis in order to obtain accurate load information.
38
Liu, Ran, Zi-Yang Gao, Hong-Yang Li, Xiao-Jie Liu, and Qing Lv. "Research on Molten Iron Quality Prediction Based on Machine Learning." Metals 14, no. 8 (2024): 856. http://dx.doi.org/10.3390/met14080856.
Full textAbstract:
The quality of molten iron not only has a significant impact on the strength, toughness, smelting cost and service life of cast iron but also directly affects the satisfaction of users. The establishment of timely and accurate blast furnace molten iron quality prediction models is of great significance for the improvement of the production efficiency of blast furnace. In this paper, Si, S and P content in molten iron is taken as the important index to measure the quality of molten iron, and the 989 sets of production data from a No.1 blast furnace from August to October 2020 are selected as the experimental data source, predicting the quality of molten iron by the I-GWO-CNN-BiLSTM model. First of all, on the basis of the traditional data processing method, the missing data values are classified into correlation data, temporal data, periodic data and manual input data, and random forest, the Lagrangian interpolation method, the KNN algorithm and the SVD algorithm are used to complete them, so as to obtain a more practical data set. Secondly, CNN and BiLSTM models are integrated and I-GWO optimized hyperparameters are used to form the I-GWO-CNN-BiLSTM model, which is used to predict Si, S and P content in molten iron. Then, it is concluded that using the I-GWO-CNN-BiLSTM model to predict the molten iron quality can obtain high prediction accuracy, which can provide data support for the regulation of blast furnace parameters. Finally, the MCMC algorithm is used to analyze the influence of the input variables on the Si, S and P content in molten iron, which helps the steel staff control the quality of molten iron in a timely manner, which is conducive to the smooth running of blast furnace production.
39
Wang, Heng, Shukun Cao ※, Quancheng Dong, et al. "Optimization and control of working parameters of hot blast furnace." MATEC Web of Conferences 175 (2018): 02030. http://dx.doi.org/10.1051/matecconf/201817502030.
Full textAbstract:
In order to improve the working efficiency of hot blast stoves, reduce environmental pollution, reduce labor intensity and improve combustion efficiency, this paper uses ANSYS software to simulate the temperature field and flow field of the hot blast stove, and uses the PID controller to realize the automatic control of the hot blast stove. The model and working principle of the hot blast stove are briefly introduced. The operating parameters (blowing fan air flow, coal intake) of the hot blast stove are briefly studied. The results show that the amount of air flow of the blast furnace depends on the coal intake of the hot blast stove, which is generally per kilogram of coal. 8m3-10m3- air is required. When the coal intake is 120kg/h and the air volume of the blower is 1200m3/h, the hot blast stove can work stably with high efficiency. The results obtained are input into the database for later combustion. The work provides a theoretical basis.
40
Luo, Shihua, Tianxin Chen, and Ling Jian. "Using Principal Component Analysis and Least Squares Support Vector Machine to Predict the Silicon Content in Blast Furnace System." International Journal of Online Engineering (iJOE) 14, no. 04 (2018): 149. http://dx.doi.org/10.3991/ijoe.v14i04.8397.
Full textAbstract:
Blast furnace system is a typical example of complex industrial system. The silicon ([Si]) content in blast furnace system is an important index to reflect the temperature of furnace. Therefore, it is significant to carry out an accurate predictive control of furnace temperature. In this paper a composite model combining Principal Component Analysis (PCA) and Least Squares Support Vector Machine (LSSVM) is established to predict the furnace temperature. At the very beginning, in order to avoid redundancy and excessive noise pollution, PCA method is applied to reduce the dimensionality of original input variables. Secondly, the dimension-reduced variables are introduced to predict the silicon content by applying the LSSVM model. Finally, the result is compared with direct multivariable LSSVM prediction. The simulation results show that the new algorithm has positive significance as it achieves more obvious prediction hit rate (more than 80%) than direct multivariable LSSVM (with rate lower than 75%).
41
Jak, Evgueni, and Peter Hayes. "The Use of Thermodynamic Modeling to Examine Alkali Recirculation in the Iron Blast Furnace." High Temperature Materials and Processes 31, no. 4-5 (2012): 657–65. http://dx.doi.org/10.1515/htmp-2012-0103.
Full textAbstract:
AbstractIt is widely recognized that alkali metals, such as, potassium and sodium can cause operational problems in the iron blast furnace. These elements can influence properties, such as, the softening and melting of ores, formation of scaffolds, coke properties, and refractory life. It has been established that recirculation of these elements occurs within the furnace. In the lower furnace vaporization occurs in the high temperature hearth and bosch regions, and condensation occurs in the upper furnace below or in the cohesive zone. For these reasons the input of alkalis into the furnace is strictly controlled.Optimized thermodynamic databases describing slags in the system Al2O3-CaO-FeO-Fe2O3-Na2O-K2O-MgO-SiO2 have been developed and, combined with the computer software FactSage; these databases have been used to predict the possible behaviour of alkalis in the blast furnace and to examine the effects of changing process variables on reactor performance. To demonstrate this approach to process modeling the furnace is considered as a two-stage equilibrium reaction system and the results of initial analysis are reported.
42
Mio, Hiroshi, Yoichi Narita, Kaoru Nakano, and Seiji Nomura. "Validation of the Burden Distribution of the 1/3-Scale of a Blast Furnace Simulated by the Discrete Element Method." Processes 8, no. 1 (2019): 6. http://dx.doi.org/10.3390/pr8010006.
Full textAbstract:
The objective of this paper was to develop a prediction tool for the burden distribution in a charging process of a bell-less-type blast furnace using the discrete element method (DEM). The particle behavior on the rotating chute and on the burden surface was modeled, and the burden distribution was analyzed. Furthermore, the measurements of the burden distribution in a 1/3-scale experimental blast furnace were performed to validate the simulated results. Particle size segregation occurred during conveying to the experimental blast furnace. The smaller particles were initially discharged followed by the larger ones later. This result was used as an input in the simulation. The burden profile simulated using DEM was similar to the experimental one. The terrace was found at the burden surface subsequent to ore-charging, and its simulated position simulated agreed with that of the experimental result. The surface angle of the ore layer was mostly similar. The simulated ore to coke mass ratio (O/C) distribution in the radial direction and the mean particle diameter distribution correlated with the experimental results very well. It can be concluded that this method of particle simulation of the bell-less charging process is highly reliable in the prediction of the burden distribution in a blast furnace.
43
Song, Jiale, Xiangdong Xing, Zhuogang Pang, and Ming Lv. "Prediction of Silicon Content in the Hot Metal of a Blast Furnace Based on FPA-BP Model." Metals 13, no. 5 (2023): 918. http://dx.doi.org/10.3390/met13050918.
Full textAbstract:
In the process of blast furnace smelting, the stability of the hearth thermal state is essential. According to the analysis of silicon content in hot metal and its change trend, the operation status of the blast furnace can be judged to ensure the stable and smooth operation of the blast furnace. Based on the error back-propagation neural network (BP), the flower pollination algorithm (FPA) is used to optimize the weight and threshold of the BP neural network, and the prediction model of silicon content is established. At the same time, the principal component analysis method is used to reduce the dimension of the input sequence to obtain relevant indicators. The relevant indicators are used as the input, and silicon content in the hot metal is used as the output, which is substituted into the model for training and utilizes the trained model to predict. The results show that the hit rate of the prediction model is 16% higher than the non-optimized BP prediction model. At the same time, the evaluation indicators and operation speed of the model are improved compared with the BP prediction model, which can be more accurately applied to predict the silicon content of the hot metal.
44
Chernavin, A. Yu, V. A. Kobelev, D. A. Chernavin, and G. A. Nechkin. "Study of blast furnace heat filterability through coke filling." Ferrous Metallurgy. Bulletin of Scientific , Technical and Economic Information 75, no. 3 (2019): 315–21. http://dx.doi.org/10.32339/0135-5910-2019-3-315-321.
Full textAbstract:
Increase of gas permeability of burden materials column lower part is one of the way of blast furnace heat intensification. Filterability of intermediate slag through coke filling determines the gas permeability of the lower zone and the blast furnace heat running. To study the filterability a methodology was elaborated and implemented, which enabled to estimate reliably the iron ore raw materials behavior in the blast furnace at high temperatures. By laboratory studies influence on the filterability of BF slag melt was determined, when MgO, MnO and CaO adding to the burden, depending on the oxides mineralogical composition. The positive influence of magnesium oxide on the slag filterability has an extreme character, at that the sinter basicity has a considerable influence. The mineral form of magnesium-containing additives introduced into the burden substantially influenced the filterability on heat products in blast furnace. Replace ofsiderite and dolomite by other magnesium-containing materials facilitates to improving of slag filterability through coke filling. Additional input of manganese in the form of manganese limestone or manganese-containing ferritic-calcium flux is an effective mean to improve filterability of sinter smelting products through coke filling. Transfer to hot metal smelting from fluxed pellets and sinter will facilitate heat products filterabilityincrease thanks to close physical andchemical properties of BF burden components in respect of smelting and slag filtering through coke filling.
45
Hela, Rudolf, Jiri Zach, and Martin Sedlmajer. "Possibilities of Regulation of Temperature in Concrete during Hydration by Means of Selection of Suitable Input Materials." Applied Mechanics and Materials 507 (January 2014): 199–203. http://dx.doi.org/10.4028/www.scientific.net/amm.507.199.
Full textAbstract:
Paper is focused on development of hydration heat in concrete in time. Possible ways of reduction of temperature during concrete hydration are mentioned. Paper presents study of possibilities of regulation temperature in concrete during hydration by selection of suitable input components. Blast furnace slag and micronized limestone were added to pure Portland cement; several variants of proportions were proposed.
46
Ziebik, A., M. Warzyc, and P. Gładysz. "Determination of the Optimal Structure of Repowering a Metallurgical CHP Plant Fired with Technological Fuel Gases." Archives of Metallurgy and Materials 59, no. 1 (2014): 105–16. http://dx.doi.org/10.2478/amm-2014-0017.
Full textAbstract:
Abstract CHP plants in ironworks are traditionally fired with low-calorific technological fuel gases and hard coal. Among metallurgical fuel gases blast-furnace gas (BFG) dominates. Minor shares of gaseous fuels are converter gas (LDG) and surpluses of coke-oven gas (COG). Metallurgical CHP plant repowering consists in adding a gas turbine to the existing traditional steam CHP plant. It has been assumed that the existing steam turbine and parts of double-fuel steam boilers can be used in modernized CHP plants. Such a system can be applied parallelly with the existing steam cycle, increasing the efficiency of utilizing the metallurgical fuel gases. The paper presents a method and the final results of analyzing the repowering of an existing metallurgical CHP plant fired with low-calorific technological fuel gases mixed with hard coal. The introduction of a gas turbine cycle results in a better effectiveness of the utilization of metallurgical fuel gases. Due to the probabilistic character of the input data (e.g. the duration curve of availability of the chemical energy of blast-furnace gas for CHP plant, the duration curve of ambient temperature) the Monte Carlo method has been applied in order to choose the optimal structure of the gas-and-steam combined cycle CHP unit, using the Gate Cycle software. In order to simplify the optimizing calculation, the described analysis has also been performed basing on the average value of availability of the chemical energy of blast-furnace gas. The fundamental values of optimization differ only slightly from the results of the probabilistic model. The results obtained by means of probabilistic and average input data have been compared using new information and a model applying average input data. The new software Thermoflex has been used. The comparison confirmed that in the choice of the power rating of the gas turbine based on both computer programs the results are similar.
47
Dobiášová, Silvie, and Karel Kubečka. "Risk Analysis of Steel Construction Projects Documentation Blast Furnaces." Advanced Materials Research 899 (February 2014): 564–67. http://dx.doi.org/10.4028/www.scientific.net/amr.899.564.
Full textAbstract:
This paper shows the example of the blast furnace project risk assessment project documentation. Evaluation is performed by expert Universal Matrix of Risk Analysis (UMRA) and in the second part will be aligned with the evaluation using RPN index. Individual analysis of the research questions will reveal whether and to what extent it is necessary to deliver it to the weighting of individual factors or whether it is sufficient to use a constant scale factor input data.
48
Mróz, Jan, Anna Konstanciak, Marek Warzecha, Marcin Więcek, and Artur M. Hutny. "Research on Reduction of Selected Iron-Bearing Waste Materials." Materials 14, no. 8 (2021): 1914. http://dx.doi.org/10.3390/ma14081914.
Full textAbstract:
During the steel production process, nearly twice as many input materials are used as compared to finished products. This creates a large amount of post-production waste, including slag, dust, and sludge. New iron production technologies enable the reuse and recycling of metallurgical waste. This paper presents an investigation on the reduction of selected iron-bearing waste materials in a laboratory rotary furnace. Iron-bearing waste materials in the form of dust, scale, and sludge were obtained from several Polish metallurgical plants as research material. A chemical analysis made it possible to select samples with sufficiently high iron content for testing. The assumed iron content limit in waste materials was 40 wt.% Fe. A sieve analysis of the samples used in the subsequent stages of the research was also performed. The tests carried out with the use of a CO as a reducer, at a temperature of 1000 °C, allowed to obtain high levels of metallization of the samples for scale 91.6%, dust 66.9%, and sludge 97.3%. These results indicate that in the case of sludge and scale, the degree of metallization meets the requirements for charge materials used in both blast furnace (BF) and electric arc furnace (EAF) steelmaking processes, while in the case of reduced dust, this material can be used as enriched charge in the blast furnace process. Reduction studies were also carried out using a gas mixture of CO and H2 (50 vol.% CO + 50 vol.% H2). The introduction of hydrogen as a reducing agent in reduction processes meets the urgent need of reducing CO2 emissions. The obtained results confirm the great importance and influence of the selection of the right amount of reducer on the achievement of a high degree of metallization and that these materials can be a valuable source of metallic charge for blast furnace and steelmaking processes. At an earlier stage of the established research program, experiments of the iron oxides reduction from iron-bearing waste materials in a stationary layer in a Tammann furnace were also conducted.
49
Zhao, Xiang Li, Li Xin Gao, and Jian Feng Li. "Research on Indirect Fault Diagnosis Method of Top Gearbox on Blast Furnace." Advanced Materials Research 823 (October 2013): 9–12. http://dx.doi.org/10.4028/www.scientific.net/amr.823.9.
Full textAbstract:
Aiming at the difficulties in diagnosis for low speed and heavy duty components of furnace top gearbox, an indirect diagnosis method for vibration signal is proposed in this subject, through which the vibration features of high speed rotating parts that near input end of gearbox is effectively utilized and analyzed for fault judgment of low speed components and a useful methodology is also given for fault diagnosis of both furnace top gearbox and low speed and heavy duty equipments. Since the identification for all faults and accurate fault location cannot be realized by using the existing diagnosis methods, a method of vibration analysis for fault diagnosis to furnace top gearbox is presented to realize accurate judgment and fault location. It can be found out that if near the basic frequency and double frequency of characteristic frequency of high speed components of upper gearbox, there were frequency spacing of fault characteristic frequency of low speed components of subordinate transmission chain apparently showing up, which also happened in low frequency range after demodulation, then the fault location can be determined to the low speed parts of subordinate transmission chain.
50
dos Anjos, Patrick, Jorge Luís Coleti, Eduardo Junca, Felipe Fardin Grillo, and Marcelo Lucas Pereira Machado. "Artificial Neural Network-Based Non-Linear Modeling and Simulation of CaO-SiO2-Al2O3-MgO Blast Furnace Slag Viscosity." Minerals 14, no. 11 (2024): 1160. http://dx.doi.org/10.3390/min14111160.
Full textAbstract:
Blast furnace slags are formed by CaO-SiO2-Al2O3-MgO systems and have several physical characteristics, one of which is viscosity. Viscosity is an important variable for the operation and blast furnace performance. This work aimed to model viscosity through linear and non-linear models in order to obtain a model with precision and accuracy. The best model constructed was a non-linear model by artificial neural networks that presented 23 nodes in the first hidden layer and 24 nodes in the second hidden layer with 6 input variables and 1 output variable named ANN 23-24. ANN 23-24 obtained better statistical evaluations in relation to 11 different literature equations for predicting viscosity in CaO-SiO2-Al2O3-MgO systems. ANN 23-24 was also subjected to numerical simulations in order to demonstrate the validation of the non-linear model and presented applications such as viscosity prediction, calculation of the inflection point in the viscosity curve by temperature, the construction of ternary diagrams with viscosity data, and the construction of iso-viscosity curves.