High-Performance Speed Control of Induction Motor Using Combined LSSVM Inverse System
In this paper, a new speed control method based on combined least squares support vector machines (LSSVM) inverse system for induction motor is proposed. It is characterized by that feedback of rotor flux and inverse model building are combined through LSSVM training and fitting. Firstly, LSSVM is used to build the inverse model of induction motor from the input–output data, and the inverse mode is served as the basis for the inverse controller design. The combined LSSVM inverse is composed of a LSSVM to approximate nonlinear mapping, an integrator and a differentiator. Cascading the LSSVM inverse with induction motor, induction motor system is transformed to a pseudo-linear system. Finally, simulation of the control method is performed to validate its feasibility. The results show that presented method has clear dynamic structure, which is effective for induction motor control.
KeywordsInduction motor Speed control Rotor flux Stator current Least squares support vector machines inverse
This work was supported by the National Natural Science Foundation of China (NSFC) under Grant 60874014 and 51077066, Science Foundation of Jiangsu Province under Grant BK2010327, and Graduate Education Innovation Project of Jiangsu Province under Grant CX09B_201Z.
- 1.Kirschen DS, Novotny DW, Lipo TA (2009) Optimal efficiency control of an induction motor drive. IEEE Trans Energy Convers EC-2(1):70–76Google Scholar
- 6.Zou HL, Diao XY, Zhu HQ et al (2010) Decoupling control of bearingless synchronous reluctance motor based on support vector machines inverse system. In: The 29th Chinese control conference. IEEE Computer Society, Beijing, pp 711–716Google Scholar
- 8.Cheng CY (2009) Sliding Mode Controller Design of Induction Motor based on Space-Vector Pulsewidth Modulation Method. Int J Innov Comput Inf Control 5:3614–3633Google Scholar
- 10.Shang WF, Zhao SD, Shen YJ (2008) Application of LSSVM with AGA optimizing parameters to nonlinear modeling of SRM. In: The 3rd IEEE Conference on Industrial Electronics and Applications. Inst. of Elec. and Elec. Eng. Computer Society, Singapore, pp 775–780Google Scholar