Soft sensing method for magnetic tube recovery ratio via fuzzy systems and neural networks

A magnetic tube recovery ratio (MTRR) is an important index in mineral processing, though it cannot be measured online. Real-time control for this product index is impossible. In this paper a new soft sensing method is proposed, which uses fuzzy system and neural network techniques. The contributions of our soft sensing method are that a fuzzy mechanism model for MTRR is used, which is obtained from data clustering. We do not update the fuzzy model, but use a neural compensator to improve the modeling accuracy, where the training algorithm for the neural network stable. This soft sensing method has been successfully applied in a metal company in China.

[1]  W. Härdle.  Applied Nonparametric Regression , 1992 .

[2]  Spyros G. Tzafestas,et al.  NeuroFAST: on-line neuro-fuzzy ART-based structure and parameter learning TSK model , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[3]  Zhong-Ping Jiang,et al.  Input-to-state stability for discrete-time nonlinear systems , 1999 .

[4]  Wolfgang Härdle,et al.  Applied Nonparametric Regression , 1991 .

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

[6]  Nikola K. Kasabov,et al.  DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction , 2002, IEEE Trans. Fuzzy Syst..

[7]  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.

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

[9]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control , 1994 .

[10]  Lian Xiaoqin,et al.  The Method of Soft Sensing Based on RBF Neural Network and Intelligent Control for Sewage Disposal Process , 2006, First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06).

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

[12]  Fatih V. Celebi,et al.  Design of a high precision temperature measurement system based on artificial neural network for different thermocouple types , 2006 .

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

[14]  Kauko Leiviskä,et al.  FUZZY MODELLING OF CARBON DIOXIDE IN A BURNING PROCESS , 2002 .

[15]  C. S. George Lee,et al.  Neural fuzzy systems: a neuro-fuzzy synergism to intelligent systems , 1996 .

[16]  Plamen P. Angelov,et al.  Soft sensor for predicting crude oil distillation side streams using evolving takagi-sugeno fuzzy models , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[17]  Chai Tianyou.  Product Quality Monitoring System for Roasting Process of Shaft Furnace , 2007 .

[18]  Z. Zeybek,et al.  Fuzzy temperature control of industrial refineries furnaces through combined feedforward/feedback multivariable cascade systems , 2002 .

[19]  Niko E. C. Verhoest,et al.  Cluster-based fuzzy models for groundwater flow in the unsaturated zone , 2007 .

[20]  Francis J. Doyle,et al.  Neural network-based software sensor: training set design and application to a continuous pulp digester , 2005 .

[21]  Björn Sohlberg,et al.  A method for measuring strip temperature in the steel industry , 2002, IEEE Trans. Instrum. Meas..

[22]  C. A. Harris,et al.  Fuzzy logic expert system for iron ore processing , 1993, Conference Record of the 1993 IEEE Industry Applications Conference Twenty-Eighth IAS Annual Meeting.

[23]  Claudio Garcia,et al.  Hardware/firmware implementation of a soft sensor using an improved version of a fuzzy identification algorithm. , 2008, ISA transactions.

[24]  G. Buzsáki,et al.  Action potential threshold of hippocampal pyramidal cells in vivo is increased by recent spiking activity , 2001, Neuroscience.

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

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

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

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