摘要

A novel de-noising algorithm, based on adaptive neural-fuzzy inference system (ANFIS) is proposed for noise reduction of the lightning current online monitoring system. The paper presents the theory and the implement procedure of the fuzzy neural system. Comparisons among the traditional strategies, such as curve fitting (CF), wavelet transform (WT) methods and the proposed ANFIS strategy are carried out. The simulation results demonstrate the superiority of the proposed method. Moreover, the employed approach has been tested on the practical measured current of lightning current online monitoring system. The testing results validate the proposed approach.

全文