Weighted Multiple-Model Neural Network Adaptive Control for Robotic Manipulators with Jumping Parameters

Abstract

This study addresses the tracking control issue for n-link robotic manipulators with largely jumping parameters. Based on radial basis function neural networks (RBFNNs), we propose weighted multiple-model neural network adaptive control (WMNNAC) approach. To cover the variation ranges of the parameters, different models of robotic are constructed. Then, the corresponding local neural network controller is constructed, in which the neural network has been used to approximate the uncertainty part of the control law, and an adaptive observer is implemented to estimate the true external disturbance. The WMNNAC strategy with improved weighting algorithm is adopted to ensure the tracking performance of the robotic manipulator system when parameters jump largely. Through the Lyapunov stability theory and the method of virtual equivalent system (VES), the stability of the closed-loop system is proved. Finally, the simulation results of a two-link manipulator verify the feasibility and efficiency of the proposed WMNNAC strategy.