Lightweight Diagnosis of Short-Gap Arcs in Oil-Paper Insulation Based on Depthwise Separable CNN

An electrical arc is a high-energy discharge that produces electromagnetic radiation, acoustic emission (AE), and heat generation. Arc discharges in transformers can lead to a range of serious malfunctions. Therefore, it is necessary to ascertain the category of arc discharge. The conventional diagnostic methods for partial discharges (PDs) are not applicable to arc discharges the distinctive characteristics of the latter. In order to achieve an efficient diagnosis of arc discharges, this article presents a lightweight identification method based on an improved convolutional neural network model. In this model, the modularized depthwise separable convolution (DSC) layers are employed as a replacement for the conventional convolution layers, thereby reducing the operands, parameters, and elapsed time. In addition, the activation function is refined with the objective of further reducing the inferring time. Experiments are conducted on defect models to simulate the arc discharges and capture the multiple signals. The adaptive general Stockwell transform (AGST) is employed to convert the time domain signals into feature maps, which serve as the sample database. The results indicate that the identification model exhibits a 99.3% accuracy rate (AR) with multichannel inputs. The proposed diagnostic method demonstrates an improvement in accuracy of 20% relative to the deep linear neural network (DNN), and exhibits an 88% reduction in the number of parameters and a 47% reduction in the elapsed time compared to the conventional convolutional neural network.