Nonlinear decoupling controller design based on least squares support vector regression
- 64 Downloads
Support Vector Machines (SVMs) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on a method of least squares SVM (LS-SVM) for multivariate function estimation, a generalized inverse system is developed for the linearization and decoupling control of a general nonlinear continuous system. The approach of inverse modelling via LS-SVM and parameters optimization using the Bayesian evidence framework is discussed in detail. In this paper, complex high-order nonlinear system is decoupled into a number of pseudo-linear Single Input Single Output (SISO) subsystems with linear dynamic components. The poles of pseudo-linear subsystems can be configured to desired positions. The proposed method provides an effective alternative to the controller design of plants whose accurate mathematical model is unknown or state variables are difficult or impossible to measure. Simulation results showed the efficacy of the method.
Key wordsSupport Vector Machine (SVM) Decoupling control Nonlinear system Generalized inverse system
Unable to display preview. Download preview PDF.
- Mackay, D.J.C., 1997. Probable network and plausible predictions—A review of practical Bayesian methods for supervised neural networks. Network Computation in Neural Systems, 6:1222–1267.Google Scholar
- vanGestel, T., Suykens, J.A.K., Baestaens, D., Lambrechts, A., Lanckriet, G., Vandaele, B., de Moor, B., 2001. Financial time series prediction using least squares support vector machines within the evidence framework. IEEE Transaction on Neural Network, 12(4):809–821. [doi:10.1109/72.935093]CrossRefGoogle Scholar
- vanGestel, T., Suykens, J.A.K., Lanckriet, G., Lambrechts, A., de Moor, B., Vandewalle, J., 2002. Bayesian framework for least squares Support Vector Machine classifiers, Gaussian processes and Kernel Fisher discriminant analysis. Neural Computation, 15(5):1115–1148. [doi:10.1162/089976602753633411]CrossRefMATHGoogle Scholar
- Walach, E., Widrow, B., 1983. Adaptive Signal Processing for Adaptive Control. IFAC workshop on Adaptive Systems in Control and Signal Processing, San Francisco, CA.Google Scholar
- Zhang, Y., Ge, S.S., 2003. A General Recurrent Neural Network work Model for Time-varying Matrix Inversion. The IEEE 42nd IEEE Conference on Decision and Control, p.6169-6174.Google Scholar