Fuzzy mechanistic model with neural compensation for Estimation of shaft furnace's product quality

Abstract Usually grey-box modeling has better accuracy than black-box identification. The grey-box can be regarded as combination of mechanistic modelling and intelligent identification. But in many cases, mechanistic models are not available, for example the production quality of the shaft furnace which will be discussed in this paper, we can use fuzzy technique to obtain the mechanistic models that can be checked by the physical meanings. In this paper, we propose a novel modeling approach for complex nonlinear systems, it has a fuzzy mechanistic model and a neural compensator. For the training of the neural network, we propose a new fast and stable algorithm. Finally, the above method is successfully applied on estimation of the production quality of the shaft furnace.

[1]  Alain Vande Wouwer,et al.  Modeling and control of cement grinding processes , 2003, IEEE Trans. Control. Syst. Technol..

[2]  Sten Bay Jørgensen,et al.  A systematic approach for soft sensor development , 2007, Comput. Chem. Eng..

[3]  Juan M. Corchado,et al.  Reducing the Memory Size of a Fuzzy Case-Based Reasoning System Applying Rough Set Techniques , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[4]  Olvi L. Mangasarian,et al.  Nonlinear Knowledge in Kernel Approximation , 2007, IEEE Transactions on Neural Networks.

[5]  S. Mitra,et al.  Bioinformatics with soft computing , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[6]  Alexander S. Poznyak,et al.  Multilayer dynamic neural networks for non-linear system on-line identification , 2001 .

[7]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[8]  Lennart Ljung,et al.  Theory and Practice of Recursive Identification , 1983 .

[9]  Wen Yu,et al.  Fuzzy identification using fuzzy neural networks with stable learning algorithms , 2004 .

[10]  Youxian Sun,et al.  A hybrid modeling method based on mechanism analysis, identification and RBF neural networks , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[11]  Wen Yu,et al.  Discrete-time neuro identification without robust modification , 2003 .

[12]  Tzuu-Hseng S. Li,et al.  T–S Fuzzy Bilinear Model and Fuzzy Controller Design for a Class of Nonlinear Systems , 2007, IEEE Transactions on Fuzzy Systems.

[13]  Johan A. K. Suykens,et al.  NLq theory: checking and imposing stability of recurrent neural networks for nonlinear modeling , 1997, IEEE Trans. Signal Process..

[14]  De-Shuang Huang,et al.  A Hybrid Forward Algorithm for RBF Neural Network Construction , 2006, IEEE Transactions on Neural Networks.

[15]  Yanqing Zhang,et al.  Constructive granular systems with universal approximation and fast knowledge discovery , 2005, IEEE Transactions on Fuzzy Systems.

[16]  Jie Huang,et al.  Neural-Network-Based Approximate Output Regulation of Discrete-Time Nonlinear Systems , 2007, IEEE Transactions on Neural Networks.

[17]  Ebrahim Mamdani,et al.  Applications of fuzzy algorithms for control of a simple dynamic plant , 1974 .

[18]  Shonali Krishnaswamy,et al.  A hybrid model for improving response time in distributed data mining , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[19]  Aristidis Likas,et al.  An incremental training method for the probabilistic RBF network , 2006, IEEE Trans. Neural Networks.

[20]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[21]  Thomas Parisini,et al.  Active State Estimation for Nonlinear Systems: A Neural Approximation Approach , 2007, IEEE Transactions on Neural Networks.

[22]  Frank L. Lewis,et al.  Identification of nonlinear dynamical systems using multilayered neural networks , 1996, Autom..

[23]  John Moody,et al.  Learning rate schedules for faster stochastic gradient search , 1992, Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop.

[24]  Jerry M. Mendel,et al.  Generating fuzzy rules by learning from examples , 1992, IEEE Trans. Syst. Man Cybern..

[25]  T. Chai,et al.  Integrated automation system for hematite ores processing and its applications , 2006 .