SVM Inverse Control Method to Nonlinear Systems

Abstract:

In recent years, inverse system method has been achieved some progress. However, it needs not only deterministic mathematical model but also analytical expression of the inverse system. They are often not able to be realized for most of the actual control systems. Therefore, it is necessary to combine the inverse system method and the intelligent control methods which are not relied on or not entirely relied on precise model in order to overcome its "bottleneck" in practical application. The application of support vector machine in inverse system method is mainly studied in this paper. Firstly, the rigorous theory of inverse system method is introduced. Secondly, SVM inverse control method is described. Finally, the additional controller is designed to complete the closed-loop control of the pseudo linear systems. Through simulation in MATLAB, the result shows that the method in this paper is effective and feasible.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 1974-1978
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.1974
• Online since: September 2013
• Authors: Qi Hua Xu, Shuai Geng, Jiao Meng
• Keywords: Inverse Control, MATLAB Simulation, Nonlinear System, Particle Swarm Optimization (PSO), Support Vector Machine (SVM)

References

[1] Lin W. Feedback stabilization of general nonlinear control systems: a passive system approach [J]. Systems & control letters, 1995, 25(1): 41-52.

DOI: 10.1016/0167-6911(94)00056-2

[2] Karer G, Mušič G, Škrjanc I, et al. Feedforward control of a class of hybrid systems using an inverse model [J]. Mathematics and computers in simulation, 2011, 82(3): 414-427.

DOI: 10.1016/j.matcom.2010.10.015

[3] Cortes C, Vapnik V. Support vector machine [J]. Machine learning, 1995, 20(3): 273-297.

DOI: 10.1007/bf00994018

[4] GAO Juan. Artificial Neural Networks Theory and Simulation Examples(2nd Version)[M]. Beijing: China Machine Press, (2007).

[5] LI Chunwen，MIAO Yuan，FENG Yuankun, et al. Inverse System Method for Nonlinear Systems Control (Ⅰ) - Single Variable Control Theory [J]. CONTROL AND DECISION, 1997, 12(5): 529-535.

[6] LI Chunwen，MIAO Yuan，FENG Yuankun, et al. Inverse System Method for Nonlinear Systems Control (Ⅱ) - Multivariable Variable Control Theory [J]. CONTROL AND DECISION, 1997, 12(6), 625-630.

[7] LI Chunwen, FENG Yuankun. Inverse System Method and its Application [J]. Journal of Tsinghua University (Science and Technology), 1986, 26(2): 105-114.

[8] DAI Xianzhong. Control Method of Inversion with Neural Network Used for Multi-Variable Nonlinear Control System [M]. Beijing: Science Press, (2005).

[9] DAI Xianzhong, LIU Jun etc. Neural network α-th order inverse system method for the control of nonlinear continuous systems [J]. IEE Proceedings-Control Theory and Applications, 1998, 145(6): 519-522.

DOI: 10.1049/ip-cta:19982411

[10] Kennedy J, Eberhart R. Particle swarm optimization [C]. Proceedings, IEEE International Conference on. IEEE, 1995, 4: 1942-(1948).

[11] Poli R, Kennedy J, Blackwell T. Particle swarm optimization [J]. Swarm intelligence, 2007, 1(1): 33-57.

DOI: 10.1007/s11721-007-0002-0

[12] SHI Feng, WANG Xiaochuan, YU Lei, et al. MATLAB Analysis of 30 Neural Network Cases [M]. Beijing：Beijing University of Aeronautics and Astronautics Press, (2010).

[13] SHI Feng, WANG Hui, YU Lei, et al. MATLAB Analysis of 30 Intelligent Algorithm Cases [M]. Beijing: Beijing University of Aeronautics and Astronautics Press, (2011).