A soft sensor modeling approach using support vector machines

Artificial neural networks (ANNs) such as radial basis function networks (RBF NNs) have been successfully used in soft sensor modeling. However, the generalization ability of conventional ANNs is not very well. For this reason, we present a novel soft sensor modeling approach based on support vector machines (SVMs). Since standard SVMs have the limitation of speed and size in training large data set, we hereby propose least squares support vector machines (LS/spl I.bar/SVMs) and apply it to soft sensor modeling. Systematic analysis is performed and indicates that the proposed method provides satisfactory performance with excellent approximation and generalization property. Monte Carlo simulations show that our soft sensor modeling approach achieves superior performance to the conventional method based on RBF NNs.

[1]  Dimitri P. Solomatine,et al.  Model Induction with Support Vector Machines: Introduction and Applications , 2001 .

[2]  L. Ljung,et al.  Overtraining, regularization and searching for a minimum, with application to neural networks , 1995 .

[3]  Tianyou Chai,et al.  Soft sensing based on artificial neural network , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[4]  Christopher M. Bishop,et al.  Current address: Microsoft Research, , 2022 .

[5]  Huihe Shao,et al.  Designing a soft sensor for a distillation column with the fuzzy distributed radial basis function neural network , 1996, Proceedings of 35th IEEE Conference on Decision and Control.

[6]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[7]  J Glassey,et al.  Bioprocess supervision: neural networks and knowledge based systems. , 1997, Journal of biotechnology.

[8]  Noboru Murata,et al.  An Integral Representation of Functions Using Three-layered Networks and Their Approximation Bounds , 1996, Neural Networks.

[9]  L. Ljung,et al.  Overtraining, Regularization, and Searching for Minimum in Neural Networks , 1992 .

[10]  Federico Girosi,et al.  An improved training algorithm for support vector machines , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[11]  Johan A. K. Suykens,et al.  Weighted least squares support vector machines: robustness and sparse approximation , 2002, Neurocomputing.

[12]  Rubens Maciel Filho,et al.  Soft sensors development for on-line bioreactor state estimation , 2000 .

[13]  J. Suykens.  Nonlinear modelling and support vector machines , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

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

[15]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.