Optimal neural network-based sliding mode adaptive control for two-link robot
by Siham Massou; Ismail Boumhidi
International Journal of Systems, Control and Communications (IJSCC), Vol. 8, No. 3, 2017

Abstract: This work presents a neural network combined with the adaptive sliding mode control (NNASMC) to design a robust trajectory-tracking controller for the two-link robot system. Sliding mode control (SMC) is well known for its robustness and efficiency to deal with a wide range of control problems with nonlinear dynamics. However, for complex nonlinear systems, when the magnitudes of the neglected dynamics are large, the higher switching gain is needed and can produce higher amplitude of chattering. So, we propose to estimate the neglected functions of the system plant by using neural network (NN) with offline weights training using particle swarm optimisation (PSO) algorithm which allows efficient global search. The needed optimal switching control gain is obtained and updated using the adaptive particle swarm optimisation (APSO) algorithm so that the asymptotical stability of the system can be guaranteed. It is shown by the Lyapunov theory that the tracking error converges to a small L-vicinity of the origin. The effectiveness of the designed NNASMC is illustrated by simulations.

Online publication date: Fri, 28-Jul-2017

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 Systems, Control and Communications (IJSCC):
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