Optimized neural network sliding mode control for two links robot using PSO technique

Abstract

This work presents the neural network combined with the sliding mode control (NNSMC) to design a robust controller for the two-links 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, the uncertainties are large and produce higher amplitude of chattering due to the higher switching gain. In order to reduce this gain, neural network (NN) is used to estimate the uncertain parts of the system plant with on-line training using backpropagation (BP) algorithm. The learning rate is one of the parameters of BP algorithm which have a significant influence on results. Particle swarm optimization (PSO) algorithm with global search capabilities is used in this study to optimize this parameter in order to improve the network performance in term of the speed of convergence. The performance of the proposed approach is investigated in simulations and the control action used did not exhibit any chattering behavior.