A New Predefined Time Zeroing Neural Network With Drop Conservatism for Matrix Flows Inversion and Its Application.

Abstract

Zeroing neural network (ZNN) can effectively solve the matrix flows inversion problem. Nevertheless, quite a few related research works focus on the improvement of the convergence and robustness performance of the ZNN models and ignore the conservatism of their predefined time. Therefore, this article adopts a polymorphous activation function (PAF) to construct a new predefined time ZNN (NPTZNN) model. The second method of Lyapunov is utilized to analyze the stability, convergence, and robustness of the NPTZNN model. The Beta function is dexterously employed in the process of calculating the predefined time of the NPTZNN model, reducing its conservatism. Furthermore, the correctness of the theoretical analyses is verified by numerous experiments. Finally, the NPTZNN model is applied to robot manipulator control and can improve the tracking speed, extending the applicability of the model.