Using a neural network controller to control chaos in a non-autonomous mechanical system
by Yan-dong Chu, Jian-gang Zhang, Xian-feng Li, Ying-xiang Chang
International Journal of Modelling, Identification and Control (IJMIC), Vol. 7, No. 3, 2009

Abstract: Complex dynamic behaviours of the centrifugal flywheel governor systems are studied. The centrifugal flywheel governor systems have a rich variety of non-linear behaviour, which are investigated here by numerically integrating the Lagrangian equations of motion. The routes to chaos are analysed using Poincare maps, which are found to be more complicated than those of non-linear rotational machines. Periodic and chaotic motions can be clearly distinguished by all of the analytical tools applied here, namely Poincare sections, bifurcation diagrams, Lyapunov exponents. The chaotic motion of the system is effectively controlled based on NNC with the threshold function of the hyperbolic tangent function, that we obtain the steady periodic orbit of the system. By studying numerical simulations, it is possible to provide reliable theory and effective numerical method for other systems. In addition, the methods and conclusions would be useful for rotational machines designers.

Online publication date: Fri, 17-Jul-2009

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