Model Reference Adaptive Control of HMB Based on PSO-LS-SVM Inverse

Abstract:

To realize the hybrid magnetic bearing (HMB) nonlinear decoupling control with high precision, a strategy of model reference adaptive control (MRAC) based on the least square support vector machine (LS-SVM) inverse is proposed. After analyzing the reversibility of HMB, the LS-SVM regression theory is used to identify the inverse model, the parameters of LS-SVM are optimized by Particle Swarm Optimization (PSO) algorithm. Then the nonlinear system is transformed into a pseudo-linear system by connecting the optimized the inverse model and the original unit. MRAC is designed to realize the compound linear control for HMB. Simulation results confirm that the identified inverse model has high precision and the compound control strategy has good performance.

• Periodical: Applied Mechanics and Materials (Volumes 416-417)
• Pages: 870-875
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.416-417.870
• Online since: September 2013
• Authors: Xian Xing Liu, Jie Chen, Yi Du, Kai Shi
• Keywords: Inverse System, Least Squares Support Vector Machines (Ls-SVM), MRAC, PSO Algorithm

References

[1] Huangqiu Zhu, Yuxiang Shen and Qinghai Wu, et al. Modeling and control system for AC hybrid magnetic bearing, Proceeding of the CSEE. (in Chinese). Vol. 29. No. 18. Jun. 2009, pp.100-105.

[2] Liu Xian xing, Zhu Huang qiu and Quan Li, et. al. Study on digital control system for a permanent magnet biased hybrid magnetic bearing with 3-degrees of freedom, China Mechanical Engineering. Vol. 15. No. 24 Dec. 2004, pp.2225-2228.

[3] Snykens J A K, Vandewalle J. Recurrent least squares support vector machine, IEEE Transaction on Circuits and Systems-I. Vol. 47. No. 7, 2000, pp.1109-1114.

DOI: 10.1109/81.855471

[4] Xia Bian, Liang Mi. Development on genetic algorithm theory and its applications, Application Research of Computers. Vol. 27. No. 7, Jul. 2010, pp.2425-2428.

[5] Marco A. Montes de Oca, Thomas Stutzle and Mauro Birattari. Frankenstein's PSO: a composite particle swarm optimization algorithm, IEEE Transactions on Evolutionary Computation. Vol. 13. No. 5. October. 2009, pp.1120-1132.

DOI: 10.1109/tevc.2009.2021465

[6] Mario di Bernardo, Umberto Montanaro and Stefania Santini. Hybrid model reference adaptive control of piecewise affine systems, IEEE Transactions on Automatic Control. Vol. 58. N0. 2, February. 2013, pp.304-316.

DOI: 10.1109/tac.2012.2212516

[7] Guohai Liu, Beibei Dong and Chenglong Teng et. Model reference adaptive control of PMSM based on support vector machines generalized inverse, Journal of Southeast University (Natural Science Edition). Vol. 40 Sup (I). Sept. 2010, pp.13-18.

DOI: 10.1109/ccdc.2010.5498719

[8] Huangqiu Zhu, Zhong Zhang and Dehong Zhu, et al. Structure and finite element analysis of an AC-DC three degrees of freedom hybrid magnetic bearing, Proceeding of the CSEE. Vol. 27. No. 12. April. 2007, pp.77-81.

DOI: 10.1109/ipemc.2009.5157724

[9] Yukun Sun, Zhiying Zhu. Inverse model Identification and Decoupling Control Based on Least Squares Support Vector Machine for 3 Degree of freedom Hybrid Magnetic Bearing, Proceeding of the CSEE. Vol. 30. No. 15. 2010, pp.112-117.