Abstract AC series arc is difficult to detect because of its complex characteristics, and it can easily cause electrical fire or explosion and other accidents. In order to solve the problem that multi-class loads can not be easily recognized when an arc fault occurs, this paper presents a method for AC series arc multi-classification fault diagnosis based on wavelet decomposition and probabilistic neural network (PNN). According to the standard, the experiment platform of fault arc is designed in this paper, and the current waveform data of fault arc and normal operation under different load types are collected. The multi-dimensional characteristics of the high-frequency current waveform are extracted by processing the detail coefficients obtained by wavelet decomposition. According to the load type and working state, multi-classification data sets are built and input into PNN to train and test the fault diagnosis model. The proposed method can not only accurately detect the fault arc, but also effectively identify the fault load line, which has important reference significance for AC series arc fault diagnosis.
Read full abstract