Fuzzy Classifier Design for Development Tendency of Hot Metal Silicon Content in Blast Furnace

Since the hot metal silicon content simultaneously reflects the product quality and the thermal state of the blast furnace, accurately predicting the development tendency of hot metal silicon content has the immensely guiding role for blast furnace operators. This paper focuses on fuzzy classifier design for the development tendency of hot metal silicon content based on blast furnace operation data. The cross characteristic of binary classification problem was found via embedding high-dimensional blast furnace data into a two-dimensional space. Then, presented a nonparallel hyperplanes based fuzzy classifier, which conquered the cross classification still holding the interpretability advantage as fuzzy classifier. The proposed method was tested on No.2 blast furnace of Liuzhou Steel in China, that demonstrated the excellent performance compared with some other classifier algorithms.

[1]  Henrik Saxén,et al.  Identification of switching linear systems using self-organizing models with application to silicon prediction in hot metal , 2016, Appl. Soft Comput..

[2]  M. Machado,et al.  Artificial Neural Network Model for Predict of Silicon Content in Hot Metal Blast Furnace , 2016 .

[3]  Janusz Korniak,et al.  Nearest-Neighbor Spline Approximation (NNSA) Improvement to TSK Fuzzy Systems , 2016, IEEE Transactions on Industrial Informatics.

[4]  Yang Qiyan.  Predicting the silicon content of the hot metal based on dynamic neural network , 2016 .

[5]  Kang Li,et al.  An Efficient LS-SVM-Based Method for Fuzzy System Construction , 2015, IEEE Transactions on Fuzzy Systems.

[6]  Ling Jian,et al.  Adaptive Least Squares Support Vector Machine Predictor for Blast Furnace Ironmaking Process , 2015 .

[7]  Y. Uchida,et al.  Effective Desiliconization Method with Strong Mixing of Agent in Swirling Flow of Hot Metal , 2014 .

[8]  Chuanhou Gao,et al.  Rule Extraction From Fuzzy-Based Blast Furnace SVM Multiclassifier for Decision-Making , 2014, IEEE Transactions on Fuzzy Systems.

[9]  B. Monaghan,et al.  Reactivity of Coke Ash on Aluminosilicate Blast Furnace Hearth Refractories , 2014 .

[10]  Laurens van der Maaten,et al.  Accelerating t-SNE using tree-based algorithms , 2014, J. Mach. Learn. Res..

[11]  Fuchun Sun,et al.  Hierarchical Structured Sparse Representation for T–S Fuzzy Systems Identification , 2013, IEEE Transactions on Fuzzy Systems.

[12]  Chuanhou Gao,et al.  Data-Driven Time Discrete Models for Dynamic Prediction of the Hot Metal Silicon Content in the Blast Furnace—A Review , 2013, IEEE Transactions on Industrial Informatics.

[13]  Chuanhou Gao,et al.  Binary Coding SVMs for the Multiclass Problem of Blast Furnace System , 2013, IEEE Transactions on Industrial Electronics.

[14]  Chuanhou Gao,et al.  Constructing Multiple Kernel Learning Framework for Blast Furnace Automation , 2012, IEEE Transactions on Automation Science and Engineering.

[15]  Bo Fu,et al.  T–S Fuzzy Model Identification With a Gravitational Search-Based Hyperplane Clustering Algorithm , 2012, IEEE Transactions on Fuzzy Systems.

[16]  Chuanhou Gao,et al.  Modeling of the Thermal State Change of Blast Furnace Hearth With Support Vector Machines , 2012, IEEE Transactions on Industrial Electronics.

[17]  Jian Huang,et al.  Identification of the Optimal Control Center for Blast Furnace Thermal State Based on the Fuzzy C-means Clustering , 2011 .

[18]  S. A. Akbar,et al.  A mathematical model to characterise effects of liquid hold-up on bosh silicon transport in the dripping zone of a blast furnace , 2011 .

[19]  Frank Pettersson,et al.  Nonlinear Modeling Method Applied to Prediction of Hot Metal Silicon in the Ironmaking Blast Furnace , 2011 .

[20]  Ling Jian,et al.  A Sliding‐window Smooth Support Vector Regression Model for Nonlinear Blast Furnace System , 2011 .

[21]  Carlos M. Jarque.  Jarque-Bera Test , 2011, International Encyclopedia of Statistical Science.

[22]  Chia-Feng Juang,et al.  An incremental support vector machine-trained TS-type fuzzy system for online classification problems , 2011, Fuzzy Sets Syst..

[23]  W. Chen,et al.  Prediction and control for silicon content in pig iron of blast furnace by integrating artificial neural network with genetic algorithm , 2010 .

[24]  Edwin Lughofer,et al.  SparseFIS: Data-Driven Learning of Fuzzy Systems With Sparsity Constraints , 2010, IEEE Transactions on Fuzzy Systems.

[25]  Ling Zhuang,et al.  Prediction of silicon content in hot metal using support vector regression based on chaos particle swarm optimization , 2009, Expert Syst. Appl..

[26]  Chuanhou Gao,et al.  Improvement of identification of blast furnace ironmaking process by outlier detection and missing value imputation , 2009 .

[27]  Chuanhou Gao,et al.  Wiener Model Identification of Blast Furnace Ironmaking Process , 2008 .

[28]  Chuanhou Gao,et al.  Application of Least Squares Support Vector Machines to Predict the Silicon Content in Blast Furnace Hot Metal , 2008 .

[29]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[30]  Frank Pettersson,et al.  Nonlinear Prediction of the Hot Metal Silicon Content in the Blast Furnace , 2007 .

[31]  F. Pettersson,et al.  Evolving Nonlinear Time-Series Models of the Hot Metal Silicon Content in the Blast Furnace , 2007 .

[32]  Olvi L. Mangasarian,et al.  Multisurface proximal support vector machine classification via generalized eigenvalues , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  T. Bhattacharya.  Prediction of Silicon Content in Blast Furnace Hot Metal Using Partial Least Squares (PLS) , 2005 .

[34]  A. Andersson,et al.  A thermodynamic study of silicon containing gas around a blast furnace raceway , 2005 .

[35]  Liu,et al.  Fuzzy Prediction of Silicon Content for BF Hot Metal , 2005 .

[36]  J.M. Leski,et al.  An /spl epsiv/-margin nonlinear classifier based on fuzzy if-then rules , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[37]  Jacek M Leski.  An epsilon-margin nonlinear classifier based on fuzzy if-then rules. , 2004, IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society.

[38]  Yan Shi,et al.  Some considerations on conventional neuro-fuzzy learning algorithms by gradient descent method , 2000, Fuzzy Sets Syst..

[39]  Henrik Saxén,et al.  On the Development of Predictive Models with Applications to a Metallurgical Process , 2000 .

[40]  Ralf Östermark,et al.  VARMAX-MODELLING OF BLAST FURNACE PROCESS VARIABLES , 1996 .

[41]  Ralf Östermark,et al.  State realization with exogenous variables - A test on blast furnace data , 1996 .

[42]  T. Fukuda,et al.  Self-tuning fuzzy modeling with adaptive membership function, rules, and hierarchical structure based on genetic algorithm , 1995 .

[43]  H. Saxén.  Short-Term Prediction of Silicon Content in Pig Iron , 1994 .

[44]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  Zhou Min,et al.  Adopt Three Criterions to Choose MISO Prediction Model of Blast Furnace Process , 1987 .

[46]  Hsiao-Ping Huang,et al.  THE ADAPTIVE AUTOREGRESSIVE MODELS FOR THE SYSTEM DYNAMICS AND PREDICTION OF BLAST FURNACE , 1986 .

[47]  Heinz Unbehauen,et al.  Application of Mimo-Identification to a Blast Furnace , 1982 .

[48]  S. Wu,et al.  Identification of multiinput-multioutput transfer function and noise model of a blast furnace from closed-loop data , 1974 .