Adaptive robust tracking RBF neural networks control for industrial robot minipulators based on backstepping

Abstract

This present study proposes a design and the analysis of the novel adaptive robust neural networks (ARNNs) based on the backstepping control method for industrial robot manipulators (IRMs). In this research, the ARNNs controller has combined the advantages of Radial Basis Function neural network (RBFNN), the robust term, and adaptive backstepping control technique without the requirement of prior knowledge. The RBFNN is used in order to approximate the unknown function to deal with external disturbances and uncertain nonlinearities. In addition, the disturbance of system is compensated by the robust Sliding Mode Control (SMC). All the parameters of ARNNs are determined by the Lyapunov stability theorem, are tuned online by an adaptive training law. Therefore, the stability, robustness, and desired tracking of the performance of ARNNs for IRMs are guaranteed.