Title: Artificial neural networks inverse control of 5 degrees of freedom bearingless induction motor

Authors: Xiaodong Sun; Huangqiu Zhu

Addresses: School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China. ' School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China

Abstract: A decoupling control approach based on artificial neural networks (ANN) inverse system method has been developed for the innovative 5 degrees of freedom (DOF) bearingless induction motor, which is multi-variable, non-linear and coupled system. The working principles of 3 DOF magnetic bearing and 2 DOF bearingless induction motor are analysed, and then the mathematical model of 5 DOF bearingless induction motor is given. The reversibility of the model is proved. Combining the ANN inverse system with the 5 DOF bearingless induction motor, the system is decoupled into five independent 2-order linear displacement subsystems, a 1-order linear speed subsystem and a 1-order linear magnetic linkage subsystem. The design of outer loop controller is easier, so the whole system control performance is further improved. In the end, the system is implemented on Matlab7.0/Simulink. The simulation results have showed that this kind of control strategy can realise dynamic decoupling control between torque force and radial suspension forces, and the control system has fine dynamic and static performance.

Keywords: magnetic bearings; bearingless induction motors; artificial neural networks; ANNs; inverse systems; decoupling control; modelling; torque force; radial suspension forces; mathematical modelling.

DOI: 10.1504/IJMIC.2012.045688

International Journal of Modelling, Identification and Control, 2012 Vol.15 No.3, pp.156 - 163

Published online: 29 Nov 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article