A Novel Fuzzy-Power Zeroing Neural Network Model for Time-Variant Matrix Moore–Penrose Inversion With Guaranteed Performance

Abstract

On the strength of the abundant development of zeroing neural network (ZNN) and the wide application of fuzzy logic system (FLS), this article presents a fuzzy-power ZNN (FPZNN) model for addressing the time-variant matrix Moore–Penrose inversion problem. Different from the original constant or time-variant parameters, a fuzzy power parameter is generated from the FLS, and is first embedded into the FPZNN model to adjust the convergence rate. For the purpose of highlighting the superior performance of the FPZNN model, the other three classical neural network models are developed for comparison purposes. The convergence and noise-tolerance of the FPZNN model are analyzed to guarantee its excellent performance, where the model-implementation and differential errors are taken into account in a noisy environment. Besides, simulative experiments including two kinds of examples are provided to display the advantages of the FPZNN model under three commonly used activation functions. Both the presented theorems and the simulative experiments verify the superiority of the FPZNN model.