An Efficient Takagi–Sugeno Fuzzy Zeroing Neural Network for Solving Time-Varying Sylvester Equation
Qing Hu, Bing Zheng
Abstract
In this article, we propose an efficient Takagi–Sugeno fuzzy zeroing neural network (TS-FZNN) activated by a new activation function for solving the time-varying Sylvester equation. The self-adaptive convergence parameter is designed by the Takagi–Sugeno fuzzy logic system. Convergence and robustness of the proposed model are analyzed. Theoretical analysis shows that the proposed model not only has less fixed convergence time than the recently suggested ZNN models, but also is noise-tolerant. Numerical experiments are performed to illustrate its efficiency and effectiveness as well as the superior performance over the existing ZNN models for solving the time-varying Sylvester equation, including the applicability of the proposed model to robot manipulator. The effects of model parameters on the dynamic response of the robotic manipulator system are also illustrated by the convergence rate of position errors of the robotic manipulator trajectory.