Technique for Magnetic Bearing Based on Mixed-Kernel Support Vector Machine Forecasting Model

Abstract:

The self-sensing magnetic bearing can reduce the cost and the axial size of the magnetic bearing and increase its reliability. A mixed-kernel least squares support vector machines (LS-SVM) forecasting model is proposed for self-sensing technique of a hybrid magnetic bearing. The structure and mathematical model of the radial-axial hybrid magnetic bearing are introduced. Based on the principle of the mixed-kernel LS-SVM, the nonlinear forecasting model between the current and the displacement which realizes the displacement self-sensing control is built through genetic algorithm. Simulation has done to verify the validity and feasibility of proposed method.

• Periodical: Applied Mechanics and Materials (Volume 529)
• Pages: 349-353
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.529.349
• Online since: June 2014
• Authors: Jie Jin*, Huang Qiu Zhu
• Keywords: Magnetic Bearing, Model, Self-Sensing, Support Vector Machine (SVM)

References

[1] Q. H. Wu, W. Pan, Y. Z. Hong, et al. Principle and parameter design for an innovated radial-axial hybrid magnetic bearing[C]. in Proceedings of International Conference on Electrical Machines and Systems, 2008: 2142-2146.

[2] D. Vischer, A. Bleule. Self-sensing active magnetic levitation[J]. IEEE Transactions on magnetic, 1993, 29(3): 1276-1281.

DOI: 10.1109/20.250632

[3] A. Looser, J. W. Kolar. A hybrid bearing concept for high-speed applications employing aerodynamic gas bearings and a self-sensing active magnetic damper[J]. IEEE Industrial Electronics Society, 2011, 11(1): 1686-1691.

DOI: 10.1109/iecon.2011.6119560

[4] J. Wang, L. X. Xu. Study on detection of rotor displacement of sensor-less magnetic bearing[J]. Mechanical Engineering and Automation, 2005, 128(1): 71-73.

[5] S. Y. Ren, C. Y. Bian, J. Liu. Study on estimation of rotor position of self-sensing active magnetic bearings[J]. Mechanical Science and Technology for Aerospace Engineering, 2008, 27(6): 815-818.

[6] F. Pan, Z. L. Mao. Parameter optimization and application of SVM with mixture kernel based on CPSO[J]. Control Engineering of China, 2011, 18(2): 268-274.

[7] G. T. Yan, G. F. Ma, Y. Z. Xiao. Support vector machines based on hybrid kernel function[J]. Journal of Harbin Institute of Technology, 2007, 39(11): 1704-1706.

[8] H. Zhang, Y. Y. Luo, L. T. Zhang, et al. Cultivated land change forecast based on genetic algorithm and least squares support vector machines [J]. Transactions of the CSAE, 2009, 25(7): 226-231.