Generalized predictive control based on LS-SVM inverse system method

A algorithm of Generalized Predictive Control (GPC) based on Least Squares Support Vector Machines (LS-SVM) inverse system method is presented for a Class of Industrial Process with strong nonlinearity. The method cascades the a th-order inverse model approximated by LS-SVM with the original system to get the composite pseudo-linear system. The predictive model of the pseudo-liear system is built by Identification method for a linear system and the GPC algorithm is employed to implement the predictive control of the pseudo-linear system. The simulation result shows that both of the dynamic and static performance of the system is excellent even when there are some modelling errors, disturbance or large change of model parameters. It is also shown that the system has strong robustness, which is a proof of the validity of the method.

[1]  Yan Wei,et al.  Research on an Algorithm of Support Vector Stepwise Regression , 2006, First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06).

[2]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[3]  Meiying Ye,et al.  Nonlinear dynamic system identification using least squares support vector machine regression , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[4]  Lv Guofang,et al.  Inverse System Control of Nonlinear Systems Using LS-SVM , 2006, 2007 Chinese Control Conference.

[5]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[6]  David W. Clarke,et al.  Generalized predictive control - Part I. The basic algorithm , 1987, Autom..