Decoupling control for bearingless synchronous reluctance motor based on support vector machine inverse
by Zebin Yang; Xiaodong Sun; Huangqiu Zhu
International Journal of Modelling, Identification and Control (IJMIC), Vol. 23, No. 1, 2015

Abstract: A novel decoupling control method based on least squares support vector machine inverse (LS-SVM) is presented for a bearingless synchronous reluctance motor (BSRM) possessing the characteristics of multi-input-multi-output, nonlinearity, and strong coupling. Based on the analysis of operation principle, the dynamic mathematical models are built, which are verified to be invertible using interactor algorithm. The nonlinear inverse model is then obtained offline using LS-SVM for its ability of function fitting. The LS-SVM inverse is connected in series with original system to decouple the BSRM system to three single-input-single-output pseudo linear systems. To further compensate the modelling error to improve robust performance, the PID feedback controller is designed, which together with inverse feedforward controller gives a composite control strategy. The simulation and experimental results show that the presented LS-SVM inverse control strategy can realise the dynamic decoupling of bearingless synchronous reluctance motors. And the control system has fine dynamic and static performance.

Online publication date: Tue, 31-Mar-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Modelling, Identification and Control (IJMIC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com