Design of Robust Adaptive Controller for Industrial Robot Based on Sliding Mode Control and Neural Network

Abstract

—Today, industrial robots play an important role in industrial production lines. One of the most important problems in motion control of industrial robot systems is the tracking of reference motion trajectories. However, in designing the controller, it is difficult to build an accurate mathematical model for the robot. Especially in the real-time working process, the industrial robot is always affected by external noise, variable load, nonlinear friction, and unexpected changes in model parameters. To solve this problem, the paper which is built a robust adaptive controller based on the sliding mode controller and the RBF neural network. In the controller, the RBF neural network is used to approximate the unknown dynamics and the adaptive update law of the parameters of the network is built based on Lyapunov stability theory. The results of the controller are verified on Matlab Simulink software and show good tracking and high robustness.