Research on inverse model based on ANN and analytic method for induction motor
by Shuo Ding; Qinghui Wu
International Journal of Automation and Control (IJAAC), Vol. 5, No. 4, 2011

Abstract: The robustness of back propagation neural network-based inverse model is researched by simulation in the paper. Firstly, the dynamic model of induction motor is built by state space theory. Secondly, the corresponding inverse model is got by inverse system theory. However, the analytic inverse model is hardly used in the engineering field by excessively depending on the parameters. Finally, an artificial neural network (ANN)-based inverse model, which synthesises artificial intelligent method and analytic method, is suggested. To accelerate the convergence of ANN and enhance its generalisation ability, the non-linear parts are realised by the analytic expressions and the corresponding results act as the inputs of ANN so that the complex-non-linear mapping relation become a simple-linear mapping and the structure of ANN is simplified. A three-layered feed-forward ANN with 12-10-2 structure is introduced to approach the inverse mode of induction motor drives. Finally, the robustness of ANN-based inverse model is verified by simulation in the case of parameter variance and state disturbance.

Online publication date: Fri, 17-Apr-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 Automation and Control (IJAAC):
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