The Experts below are selected from a list of 49728 Experts worldwide ranked by ideXlab platform
Witold Pedrycz - One of the best experts on this subject based on the ideXlab platform.
-
prediction model of burn through point with fuzzy time series for iron ore Sintering Process
Engineering Applications of Artificial Intelligence, 2021Co-Authors: Luefeng Chen, Witold PedryczAbstract:Abstract Burn-through point (BTP) is an essential parameter in the iron ore Sintering Process. Operators usually judge whether the current production is stable by monitoring the BTP. It comes with significant application prospects to predict the BTP accurately. A prediction model of the BTP with fuzzy time series is designed in this paper. First, the fuzzy time series prediction method with the Fuzzy C-Means clustering is presented as the core modeling method. A prediction model of the response is constructed to obtain a timely response to the current BTP. The prediction model of the difference is established to estimate the present unmeasurable disturbance on the BTP. Then, a hybrid prediction model is built, which realizes the composition of these two models by an adjustment factor. Finally, a series of experiments is carried out using the raw time series data from an iron and steel plant. The experimental result shows that the designed model has better prediction performance for the BTP than existing models, which is an advantage resulting from the hybrid structure and the fuzzy time series prediction model with the Fuzzy C-Means clustering. This prediction model of the BTP implies the foundation for the stable control of the iron ore Sintering Process.
-
Weighted Kernel Fuzzy C-Means-Based Broad Learning Model for Time-Series Prediction of Carbon Efficiency in Iron Ore Sintering Process.
IEEE transactions on cybernetics, 2020Co-Authors: Luefeng Chen, Pan Zhang, Zhou Kailong, Witold PedryczAbstract:A key energy consumption in steel metallurgy comes from an iron ore Sintering Process. Enhancing carbon utilization in this Process is important for green manufacturing and energy saving and its prerequisite is a time-series prediction of carbon efficiency. The existing carbon efficiency models usually have a complex structure, leading to a time-consuming training Process. In addition, a complete retraining Process will be encountered if the models are inaccurate or data change. Analyzing the complex characteristics of the Sintering Process, we develop an original prediction framework, that is, a weighted kernel-based fuzzy C-means (WKFCM)-based broad learning model (BLM), to achieve fast and effective carbon efficiency modeling. First, Sintering parameters affecting carbon efficiency are determined, following the Sintering Process mechanism. Next, WKFCM clustering is first presented for the identification of multiple operating conditions to better reflect the system dynamics of this Process. Then, the BLM is built under each operating condition. Finally, a nearest neighbor criterion is used to determine which BLM is invoked for the time-series prediction of carbon efficiency. Experimental results using actual run data exhibit that, compared with other prediction models, the developed model can more accurately and efficiently achieve the time-series prediction of carbon efficiency. Furthermore, the developed model can also be used for the efficient and effective modeling of other industrial Processes due to its flexible structure.
-
prediction performance improvement via anomaly detection and correction of actual production data in iron ore Sintering Process
IEEE Transactions on Industrial Informatics, 2020Co-Authors: Pan Zhang, Witold PedryczAbstract:The accuracy and integrity of the actual production data influence the reliability and stability of Sintering Process in steel industry. However, the actual production data may encounter various outliers due to noise, sensor failure, and operator negligence existing in this Process. To tackle this issue, this article develops an original framework for the detection and correction of abnormal production data in the Sintering Process. First, an improved kernel-based Fuzzy C-Means algorithm is developed to effectively divide normal production data under multiple operating conditions. Then, different one-class support vector machine (SVM) classifiers are constructed for different operating conditions. According to which operating condition the actual production data belongs to, the one-class SVM under this operating condition is called to accurately detect abnormal production data. Finally, the most similar normal historical data in the operating condition is obtained to correct the abnormal data by using $k$ nearest neighbor algorithm based on the Mahalanobis distance. Simulation results involving actual production data illustrate the effectiveness of the proposed method. By taking two existing models of the Sintering Process as examples, their prediction performance becomes improved after detecting and correcting the abnormal production data, so that the proposed framework has important engineering application impact.
-
Operating mode recognition of iron ore Sintering Process based on the clustering of time series data
Control Engineering Practice, 2020Co-Authors: Luefeng Chen, Weihua Cao, Witold PedryczAbstract:Abstract Operators often make different control decisions for different operating modes to meet the production requirement of the iron ore Sintering Process. Recognizing the operating modes is important to improve the quality and quantity of the sinter ore. An operating mode recognition method based on the clustering of time series data for the iron ore Sintering Process is presented in this paper. First, the Spearman rank correlation analysis and the information entropy analysis are combined to select parameters. Next, the operating mode recognition submodel is built by the fuzzy C-Means clustering method based on dynamic time warping distance and the naive Bayesian classifier method. Then, the outputs of the submodels are fused to obtain the final recognized operating mode. Finally, the productivity and combustion efficiency are regarded as the classification criteria, and the raw data collected from an iron and steel plant are used for the experiment. The experimental results show that the proposed method can effectively recognize the operating mode of the Sintering Process.
-
Operating Mode Recognition Based on Fluctuation Interval Prediction for Iron Ore Sintering Process
IEEE ASME Transactions on Mechatronics, 2020Co-Authors: Luefeng Chen, Weihua Cao, Li Jin, Witold PedryczAbstract:The operating mode is an essential factor affecting product quality and yield of the sinter ore, which inspires the realization of operating mode recognition. Taking burn-through point (BTP) as the decision parameter of operating mode, an operating mode recognition method based on the fluctuation interval prediction is presented. First, combining the principal component analysis and the fuzzy information granulation method, a fluctuation interval prediction model of the BTP is established through utilizing the Elman neural network. Then, the operating mode classification rules are built according to the data distribution of the BTP in the fluctuation interval. Finally, experiments are executed with the data collected from a factory. The results indicate that it can effectively predict the fluctuation interval of the BTP, and then successfully recognize the operating mode. In this article, the proposed method provides a valid reference to control the stable operation of the iron ore Sintering Process.
Yi-cheng Liou - One of the best experts on this subject based on the ideXlab platform.
-
synthesis and diffused phase transition of ba0 7sr0 3tio3 ceramics by a reaction Sintering Process
Ceramics International, 2008Co-Authors: Yi-cheng LiouAbstract:Abstract Ba0.7Sr0.3TiO3 (BST) ceramics prepared by a reaction-Sintering Process were investigated. BST ceramics could be obtained after 2–6 h Sintering at 1330–1370 °C without any calcination involved. BST with density 5.68 g/cm3 (99.8% of the theoretic value) was obtained at 1350 °C for 6 h Sintering. Grains of 2–15 μm were formed after 2–6 h Sintering at 1330–1370 °C. A diffused ferroelectric–paraelectric transition was observed in pellets sintered at 1330 °C for 2 h and disappeared at a longer soak time or a higher Sintering temperature.
-
calcium doped mgtio3 mgti2o5 ceramics prepared using a reaction Sintering Process
Materials Science and Engineering B-advanced Functional Solid-state Materials, 2007Co-Authors: Yi-cheng Liou, Songling YangAbstract:Abstract Calcium-doped MgTiO3–MgTi2O5 (MCT) ceramics prepared using a reaction-Sintering Process were investigated. Without any calcination involved, the mixture of MgO, CaCO3, and TiO2 was pressed and sintered directly. MCT ceramics were obtained after 2–6 h Sintering at 1150–1250 °C. MCT containing high percentage of MgTi2O5 phase (45.6%) was observed at 1150 °C/2 h Sintering and the percentage decreased to 37.2% at 1300 °C/2 h Sintering. The maximum density 3.85 g/cm3 could be obtained at 1250 °C. Dielectric constant at 10 MHz reaches 23.7–25.9 in MCT ceramics sintered at 1150 and 1200 °C. ɛr = 22.4 and Q × f ∼ 40,400 GHz (at 9.8 GHz) and a τf value of −9.6 ppm/°C were obtained in MCT ceramic sintered at 1300 °C/2 h. The reaction-Sintering Process has been proven a simple and effective method to produce dense MCT ceramics with good dielectric properties even without the addition of Sintering aid.
-
canb2o6 ceramics prepared by a reaction Sintering Process
Materials Science and Engineering B-advanced Functional Solid-state Materials, 2006Co-Authors: Yi-cheng Liou, Minhang Weng, Chaoyang ShiueAbstract:Abstract CaNb 2 O 6 columbite ceramics produced by a reaction-Sintering Process were investigated. CaCO 3 was mixed with Nb 2 O 5 then pressed and sintered into CaNb 2 O 6 ceramics without any calcination stage involved. Pure columbite CaNb 2 O 6 phase was obtained successfully. After 1420 °C Sintering for 2 h, a density 4.37 g/cm 3 (92% of the theoretical value) were obtained. Some sub-micron CaO particles were segregated at the surfaces of CN grains at 1350–1450 °C. Round grains formed at 1330–1400 °C and long shaped grains are found in CN pellets sintered at temperatures above 1400 °C. 3.9–8.1 μm grain sizes are formed in CN pellets sintered at 1330–1400 °C for 2 and 4 h.
-
microwave ceramics ba5nb4o15 and sr5nb4o15 prepared by a reaction Sintering Process
Materials Science and Engineering B-advanced Functional Solid-state Materials, 2006Co-Authors: Yi-cheng Liou, Wenhau Shiu, Chungyu ShihAbstract:Abstract Ba 5 Nb 4 O 15 (BN) and Sr 5 Nb 4 O 15 (SN) microwave ceramics prepared by a reaction-Sintering Process were investigated. Without any calcination involved, the Nb 2 O 5 mixture of BaCO 3 and SrCO 3 was pressed and sintered directly. BN and SN ceramics could be obtained after 2–6 h Sintering at 1350–1500 °C. A density 6.13 g/cm 3 (97.3% of theoretical value) was obtained in BN for 4 and 6 h Sintering at 1450 °C. The Sintering temperature was 200 °C lowered with the addition of 1 wt.% CuO. For SN, low densification 86.9% was obtained at 1500 °C and became dense with 96% of the theoretical density at 1430 °C after 1 wt.% CuO was added. Dielectric constants 39.5 and 38.1 could be obtained in BN and SN. Q × f values 22,700 GHz at 7.2 GHz and 10,500 GHz at 7.47 GHz are observed in BN and SN.
-
synthesis of bati4o9 ceramics by reaction Sintering Process
Materials Research Bulletin, 2005Co-Authors: Yi-cheng Liou, Ko-hao Tseng, Tzuchin ChungAbstract:Abstract Synthesis of BaTi 4 O 9 ceramics by a reaction-Sintering Process was investigated. The mixture of raw materials for stoichiometric BaTi 4 O 9 were pressed and sintered into ceramics without any calcination stage involved. Pure BaTi 4 O 9 phases were obtained at 1150–1280 °C. High-sintered density, 98.2–99.5% of theoretical value (4.533 g/cm 3 ), can be obtained for pellets sintered at 1200–1280 °C for 2–6 h. Some rod-shaped grains 3–7 μm in the longitudinal axis appear in pellets sintered at 1230 °C. Both the size and the amount of these rod-shaped grains increase at higher Sintering temperature.
Luefeng Chen - One of the best experts on this subject based on the ideXlab platform.
-
prediction model of burn through point with fuzzy time series for iron ore Sintering Process
Engineering Applications of Artificial Intelligence, 2021Co-Authors: Luefeng Chen, Witold PedryczAbstract:Abstract Burn-through point (BTP) is an essential parameter in the iron ore Sintering Process. Operators usually judge whether the current production is stable by monitoring the BTP. It comes with significant application prospects to predict the BTP accurately. A prediction model of the BTP with fuzzy time series is designed in this paper. First, the fuzzy time series prediction method with the Fuzzy C-Means clustering is presented as the core modeling method. A prediction model of the response is constructed to obtain a timely response to the current BTP. The prediction model of the difference is established to estimate the present unmeasurable disturbance on the BTP. Then, a hybrid prediction model is built, which realizes the composition of these two models by an adjustment factor. Finally, a series of experiments is carried out using the raw time series data from an iron and steel plant. The experimental result shows that the designed model has better prediction performance for the BTP than existing models, which is an advantage resulting from the hybrid structure and the fuzzy time series prediction model with the Fuzzy C-Means clustering. This prediction model of the BTP implies the foundation for the stable control of the iron ore Sintering Process.
-
Weighted Kernel Fuzzy C-Means-Based Broad Learning Model for Time-Series Prediction of Carbon Efficiency in Iron Ore Sintering Process.
IEEE transactions on cybernetics, 2020Co-Authors: Luefeng Chen, Pan Zhang, Zhou Kailong, Witold PedryczAbstract:A key energy consumption in steel metallurgy comes from an iron ore Sintering Process. Enhancing carbon utilization in this Process is important for green manufacturing and energy saving and its prerequisite is a time-series prediction of carbon efficiency. The existing carbon efficiency models usually have a complex structure, leading to a time-consuming training Process. In addition, a complete retraining Process will be encountered if the models are inaccurate or data change. Analyzing the complex characteristics of the Sintering Process, we develop an original prediction framework, that is, a weighted kernel-based fuzzy C-means (WKFCM)-based broad learning model (BLM), to achieve fast and effective carbon efficiency modeling. First, Sintering parameters affecting carbon efficiency are determined, following the Sintering Process mechanism. Next, WKFCM clustering is first presented for the identification of multiple operating conditions to better reflect the system dynamics of this Process. Then, the BLM is built under each operating condition. Finally, a nearest neighbor criterion is used to determine which BLM is invoked for the time-series prediction of carbon efficiency. Experimental results using actual run data exhibit that, compared with other prediction models, the developed model can more accurately and efficiently achieve the time-series prediction of carbon efficiency. Furthermore, the developed model can also be used for the efficient and effective modeling of other industrial Processes due to its flexible structure.
-
Operating mode recognition of iron ore Sintering Process based on the clustering of time series data
Control Engineering Practice, 2020Co-Authors: Luefeng Chen, Weihua Cao, Witold PedryczAbstract:Abstract Operators often make different control decisions for different operating modes to meet the production requirement of the iron ore Sintering Process. Recognizing the operating modes is important to improve the quality and quantity of the sinter ore. An operating mode recognition method based on the clustering of time series data for the iron ore Sintering Process is presented in this paper. First, the Spearman rank correlation analysis and the information entropy analysis are combined to select parameters. Next, the operating mode recognition submodel is built by the fuzzy C-Means clustering method based on dynamic time warping distance and the naive Bayesian classifier method. Then, the outputs of the submodels are fused to obtain the final recognized operating mode. Finally, the productivity and combustion efficiency are regarded as the classification criteria, and the raw data collected from an iron and steel plant are used for the experiment. The experimental results show that the proposed method can effectively recognize the operating mode of the Sintering Process.
-
Operating Mode Recognition Based on Fluctuation Interval Prediction for Iron Ore Sintering Process
IEEE ASME Transactions on Mechatronics, 2020Co-Authors: Luefeng Chen, Weihua Cao, Li Jin, Witold PedryczAbstract:The operating mode is an essential factor affecting product quality and yield of the sinter ore, which inspires the realization of operating mode recognition. Taking burn-through point (BTP) as the decision parameter of operating mode, an operating mode recognition method based on the fluctuation interval prediction is presented. First, combining the principal component analysis and the fuzzy information granulation method, a fluctuation interval prediction model of the BTP is established through utilizing the Elman neural network. Then, the operating mode classification rules are built according to the data distribution of the BTP in the fluctuation interval. Finally, experiments are executed with the data collected from a factory. The results indicate that it can effectively predict the fluctuation interval of the BTP, and then successfully recognize the operating mode. In this article, the proposed method provides a valid reference to control the stable operation of the iron ore Sintering Process.
Clive A Randall - One of the best experts on this subject based on the ideXlab platform.
-
water mediated surface diffusion mechanism enables the cold Sintering Process a combined computational and experimental study
Angewandte Chemie, 2019Co-Authors: Mert Y Sengul, Clive A Randall, Jing Guo, Adri C T Van DuinAbstract:The cold Sintering Process (CSP) densifies ceramics at much lower temperatures than conventional Sintering Processes. Several ceramics and composite systems have been successfully densified under cold Sintering. For the grain growth kinetics of zinc oxide, reduced activation energies are shown, and yet the mechanism behind this growth is unknown. Herein, we investigate these mechanisms in more detail with experiments and ReaxFF molecular dynamics simulations. We investigated the recrystallization of zinc cations under various acidic conditions and found that their adsorption to the surface can be a rate-limiting factor for cold Sintering. Our studies show that surface hydroxylation in CSP does not inhibit crystallization; in contrast, by creating a surface complex, it creates an orders of magnitude acceleration in surface diffusion, and in turn, accelerates recrystallization.
-
demonstration of the cold Sintering Process study for the densification and grain growth of zno ceramics
Journal of the American Ceramic Society, 2017Co-Authors: Shuichi Funahashi, Ke Wang, Amanda Baker, Kosuke Shiratsuyu, Clive A RandallAbstract:With the cold Sintering Process (CSP), it was found that adding acetic acid to an aqueous solution dramatically changed both the densities and the grain microstructures of the ZnO ceramics. Bulk densities >90% theoretical were realized below 100°C, and the average conductivity of CSP samples at around 300°C was similar to samples conventionally sintered at 1400°C. Frequently, ZnO is also used as a model ceramic system for fundamental studies for Sintering. By the same procedure as the grain growth of the conventional Sintering, the kinetic grain growth exponent of the CSP samples was determined as N = 3, and the calculated activated energy of grain growth was 43 kJ/mol, which is much lower than that reported using conventional Sintering. The evidence for grain growth under the CSP is important as it indicates that there is a genuine Sintering Process being activated at these low temperatures and it is beyond a pressurized densification Process.
-
cold Sintering Process a novel technique for low temperature ceramic Processing of ferroelectrics
Journal of the American Ceramic Society, 2016Co-Authors: Hanzheng Guo, Amanda Baker, Jing Guo, Clive A RandallAbstract:Research on Sintering of dense ceramic materials has been very active in the past decades and still keeps gaining in popularity. Although a number of new techniques have been developed, the Sintering Process is still performed at high temperatures. Very recently we established a novel protocol, the “Cold Sintering Process (CSP)”, to achieve dense ceramic solids at extraordinarily low temperatures of <300°C. A wide variety of chemistries and composites were successfully densified using this technique. In this article, a comprehensive CSP tutorial will be delivered by employing three classic ferroelectric materials (KH2PO4, NaNO2, and BaTiO3) as examples. Together with detailed experimental demonstrations, fundamental mechanisms, as well as the underlying physics from a thermodynamics perspective, are collaboratively outlined. Such an impactful technique opens up a new way for cost-effective and energy-saving ceramic Processing. We hope that this article will provide a promising route to guide future studies on ultralow temperature ceramic Sintering or ceramic materials related integration.
-
Cold Sintering Process: A new era for ceramic packaging and microwave device development
Journal of the American Ceramic Society, 2016Co-Authors: Jing Guo, Amanda Baker, Hanzheng Guo, Michael T. Lanagan, Clive A RandallAbstract:Cold Sintering Process (CSP) is an extremely low-temperature Sintering Process (room temperature to ~200°C) that uses aqueous-based solutions as transient solvents to aid densification by a nonequilibrium dissolution-precipitation Process. In this work, CSP is introduced to fabricate microwave and packaging dielectric substrates, including ceramics (bulk monolithic substrates and multilayers) and ceramic-polymer composites. Some dielectric materials, namely Li2MoO4, Na2Mo2O7, K2Mo2O7, and (LiBi)0.5MoO4 ceramics, and also (1−x)Li2MoO4−xPTFE and (1−x)(LiBi)0.5MoO4−xPTFE composites, are selected to demonstrate the feasibility of CSP in microwave and packaging substrate applications. Selected dielectric ceramics and composites with high densities (88%-95%) and good microwave dielectric properties (permittivity, 5.6-37.1; Q × f, 1700-30 500 GHz) were obtained by CSP at 120°C. CSP can be also used to potentially develop a new co-fired ceramic technology, namely CSCC. Li2MoO4−Ag multilayer co-fired ceramic structures were successfully fabricated without obvious delamination, warping, or interdiffusion. Numerous materials with different dielectric properties can be densified by CSP, indicating that CSP provides a simple, effective, and energy-saving strategy for the ceramic packaging and microwave device development.
-
utilizing the cold Sintering Process for flexible printable electroceramic device fabrication
Journal of the American Ceramic Society, 2016Co-Authors: Amanda Baker, Jing Guo, Hanzheng Guo, Clive A RandallAbstract:Conventional thermal Sintering of ceramics is generally accomplished at high temperatures in kilns or furnaces. We have recently developed a procedure where the Sintering of a ceramic can take place at temperatures below 200°C, using aqueous solutions as transient solvents to control dissolution and precipitation and enable densification (i.e., Sintering). We have named this approach as the “Cold Sintering Process” because of the drastic reduction in Sintering temperature and time relative to the conventional thermal Process. In this study, we fabricate basic monolithic capacitor array structures using a ceramic paste that is printed on nickel foils and polymer sheets, with silver electrodes. The sintered capacitors, using a dielectric Lithium Molybdenum Oxide ceramic, were then cold sintered and tested for capacitance, loss, and microstructural development. Simple structures demonstrate that this approach could provide a cost-effective strategy to print and densify different materials such as ceramics, polymers, and metals on the same substrate to obtain functional circuitry.
Weihua Cao - One of the best experts on this subject based on the ideXlab platform.
-
Operating Mode Recognition Based on Fluctuation Interval Prediction for Iron Ore Sintering Process
IEEE ASME Transactions on Mechatronics, 2020Co-Authors: Luefeng Chen, Weihua Cao, Li Jin, Witold PedryczAbstract:The operating mode is an essential factor affecting product quality and yield of the sinter ore, which inspires the realization of operating mode recognition. Taking burn-through point (BTP) as the decision parameter of operating mode, an operating mode recognition method based on the fluctuation interval prediction is presented. First, combining the principal component analysis and the fuzzy information granulation method, a fluctuation interval prediction model of the BTP is established through utilizing the Elman neural network. Then, the operating mode classification rules are built according to the data distribution of the BTP in the fluctuation interval. Finally, experiments are executed with the data collected from a factory. The results indicate that it can effectively predict the fluctuation interval of the BTP, and then successfully recognize the operating mode. In this article, the proposed method provides a valid reference to control the stable operation of the iron ore Sintering Process.
-
Operating mode recognition of iron ore Sintering Process based on the clustering of time series data
Control Engineering Practice, 2020Co-Authors: Luefeng Chen, Weihua Cao, Witold PedryczAbstract:Abstract Operators often make different control decisions for different operating modes to meet the production requirement of the iron ore Sintering Process. Recognizing the operating modes is important to improve the quality and quantity of the sinter ore. An operating mode recognition method based on the clustering of time series data for the iron ore Sintering Process is presented in this paper. First, the Spearman rank correlation analysis and the information entropy analysis are combined to select parameters. Next, the operating mode recognition submodel is built by the fuzzy C-Means clustering method based on dynamic time warping distance and the naive Bayesian classifier method. Then, the outputs of the submodels are fused to obtain the final recognized operating mode. Finally, the productivity and combustion efficiency are regarded as the classification criteria, and the raw data collected from an iron and steel plant are used for the experiment. The experimental results show that the proposed method can effectively recognize the operating mode of the Sintering Process.
-
multi model ensemble prediction model for carbon efficiency with application to iron ore Sintering Process
Control Engineering Practice, 2019Co-Authors: Xin Chen, Weihua Cao, Witold PedryczAbstract:Abstract Iron ore Sintering is one of the most energy-consuming Process in steel industry. Accurate prediction of carbon efficiency for this Process is beneficial to energy savings and consumption reduction. Considering the Sintering Process exhibits strong nonlinearities, multiple parameters, multiple operating conditions, etc., a multi-model ensemble prediction model based on the actual run data is developed to achieve the high-precision prediction of carbon efficiency. It takes the comprehensive coke ratio (CCR) as a metric (index) of carbon efficiency in the Sintering Process. First, an affinity propagation clustering algorithm is used to realize the automatic identification of multiple operating conditions. Then, different models are established under different operating conditions by using the proposed least squares support vector machine (LS-SVM) with hybrid kernel modeling method. Finally, a partial least-squares regression method is employed as an ensemble strategy to combine the different models to form the multi-model ensemble prediction model for the CCR. The simulation results involving the actual run data demonstrate that the proposed model can predict the CCR accurately when compared with other prediction methods. The results of actual runs show that the coefficient of determination for the proposed model is 0.877. The proposed model satisfies the requirements of actual Sintering Process and enables the real-time prediction.
-
an intelligent integrated optimization system for the proportioning of iron ore in a Sintering Process
Journal of Process Control, 2014Co-Authors: Xiaoxia Chen, Weihua Cao, Jinhua She, Chunsheng WangAbstract:The proportioning of iron ore is the first step of the Sintering Process. It mixes different kinds of iron ores with coke, limestone, dolomite, and returned sinter to produce a raw mix for the production of qualified sinter. The chemical components and proportions of the raw materials determine the chemical and physical characteristics of the resulting sinter, and thus the quality of the sinter and the amount of SO2 emissions. The prices of the raw materials and their proportions determine the price of the sinter. In this study, an intelligent integrated optimization system (IIOS) was developed for the proportioning step, which contains two phases: the first and second proportionings. First, the Sintering Process was analyzed, and the requirements of the proportioning step were specified. Next, an IIOS with two levels (intelligent integrated optimization, basic automation) was built. In the intelligent integrated optimization level, an intelligent integrated optimizer (IIO) produces an optimal dosing scheme. The IIO has three parts: a cascade integrated quality-prediction model, the optimization of the first proportioning, and the optimization of the second proportioning. Computational intelligence methods predict the quality of sinter. Then, the predicted quality indices are fed back to the optimizations of the first and second proportionings to find feasible optimal dosing schemes. The IIOS was implemented in an iron and steel plant. Actual runs show that the system reduced production costs by 43.014 CNY/t and SO2 emissions by 0.001% on average.
-
Design and application of generalized predictive control strategy with closed-loop identification for burn-through point in Sintering Process
Control Engineering Practice, 2012Co-Authors: Chunsheng Wang, Weihua Cao, Xuzhi Lai, Xin ChenAbstract:Abstract This paper presents a generalized predictive control (GPC) strategy with closed-loop model identification for burn-through point (BTP) control in the Sintering Process. First, the dynamic Auto-Regressive eXogenous (ARX) model structure is defined to describe Sintering Process. Considering the economy and security, a closed-loop identification method is adopted to update the parameters of the model. Then, BTP predictive control model is established based on GPC algorithm to predict BTP accurately and to calculate the strand velocity. Finally, a BTP control system is established and implemented in an iron and steel plant. The running results show that the system effectively guarantees the stability of Sintering Process and suppresses the fluctuation of BTP.