Study on parameters self-tuning of speed servo system based on LS_SVM model
by Pengzhan Chen, Xiaoqi Tang
International Journal of Modelling, Identification and Control (IJMIC), Vol. 10, No. 1/2, 2010

Abstract: Support vector machine (SVM) can approach any of the non-linear functions, so it can be used to reconstruct the dynamic features of the practical system. Driven by the demand of the parameters self-tuning of the speed servo system, a parameters self-tuning method based on least squares support vector machine (LS_SVM) reference model of the practical system had been put forward. In the parameters tuning process, at first, a variable amplitude triangular wave signal of variable frequency was used to stimulate the system and the input and output data sets under the open-loop state of the actual system were collected; then, by using LS_SVM in learning the data sets, a reference model with similar dynamic characteristics to the actual system was established; finally, a coordinate rotation optimisation algorithm was employed to find the optimum parameters of the practical system based on the achieved LS_SVM reference model, the parameters self-tuning process of speed servo system was completed indirectly. The proposed parameters self-tuning method in this paper was proved effective by simulation results.

Online publication date: Fri, 02-Jul-2010

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