A better robustness and fast convergence zeroing neural network for solving dynamic nonlinear equations

In this paper, a better fast convergence zeroing neural network (BFCZNN) model with a new activation function (AF) for solving dynamic nonlinear equations (DNE) and applying to control of robot manipulator is presented. The proposed BFCZNN model not only finds the solutions of DNE in fixed time, but also has better robustness than most of the previously reported studies. The numerical simulation results of the proposed BFCZNN and the previously reported robust nonlinear zeroing neural network (RNZNN) for solving third-order DNE in the same condition are presented to demonstrate the better robustness of our new BFCZNN model. Moreover, a successful kinematic control of robot manipulator of our new BFCZNN model is used to verify the realistic availability of the proposed BFCZNN model.

Automated summary

This paper presents a better fast convergence zeroing neural network (BFCZNN) model with a new activation function (AF) for solving dynamic nonlinear equations (DNE) and applying to control robot manipulator. The proposed BFCZNN model not only finds the solutions of DNE in fixed time, but also has better robustness than most of the previously reported studies.