Title: Optimal neural network-based sliding mode adaptive control for two-link robot
Authors: Siham Massou; Ismail Boumhidi
Addresses: LESSI Laboratory, Faculty of Sciences Dhar El Mehraz, University Sidi Mohamed Ben Abdellah, B.P. 1796, 30000 FES-Atlas, Morocco ' LESSI Laboratory, Faculty of Sciences Dhar El Mehraz, University Sidi Mohamed Ben Abdellah, B.P. 1796, 30000 FES-Atlas, Morocco
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.
Keywords: two-link robot; neural network; sliding mode control; SMC; adaptive particle swarm optimisation; APSO.
International Journal of Systems, Control and Communications, 2017 Vol.8 No.3, pp.204 - 216
Received: 28 Dec 2015
Accepted: 18 Jan 2017
Published online: 28 Jul 2017 *