Comparison of Neural Networks and Support Vector Machine Dynamic Models for State Estimation in Semiautogenous Mills

Development of performant state estimators for industrial processes like copper extraction is a hard and relevant task because of the difficulties to directly measure those variables on-line. In this paper a comparison between a dynamic NARX-type neural network model and a support vector machine (SVM) model with external recurrences for estimating the filling level of the mill for a semiautogenous ore grinding process is performed. The results show the advantages of SVM modeling, especially concerning Model Predictive Output estimations of the state variable (MSE < 1.0), which would favor its application to industrial scale processes.

[1]  I. J. Leontaritis,et al.  Input-output parametric models for non-linear systems Part II: stochastic non-linear systems , 1985 .

[2]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[3]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[4]  Cristiano Cervellera,et al.  Design of Asymptotic Estimators: An Approach Based on Neural Networks and Nonlinear Programming , 2007, IEEE Transactions on Neural Networks.

[5]  A. Zell,et al.  Efficient parameter selection for support vector machines in classification and regression via model-based global optimization , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[6]  Gexiang Zhang,et al.  Application of support vector machines to nonlinear system identification , 2005, Proceedings Autonomous Decentralized Systems, 2005. ISADS 2005..

[7]  Pierre Roussel-Ragot,et al.  Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms , 1993, Neural Computation.

[8]  Gonzalo Acuña,et al.  Estimation of State Variables in Semiautogenous Mills by Means of a Neural Moving Horizon State Estimator , 2007, ISNN.

[9]  Derong Liu,et al.  Advances in Neural Networks - ISNN 2007, 4th International Symposium on Neural Networks, ISNN 2007, Nanjing, China, June 3-7, 2007, Proceedings, Part I , 2007, ISNN.

[10]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[11]  Ming Ge,et al.  An effective learning approach for nonlinear system modeling , 2004, Proceedings of the 2004 IEEE International Symposium on Intelligent Control, 2004..

[12]  Max Chacón,et al.  Support Vector Machine with External Recurrences for Modeling Dynamic Cerebral Autoregulation , 2006, CIARP.

[13]  Johan A. K. Suykens,et al.  Electric Load Forecasting: Using Kernel-Based Modeling for Nonlinear System Identification , 2007 .