Series arc fault detection based on continuous wavelet transform and DRSN-CW with limited source data

Abstract

When a series arc fault occurs in an indoor power distribution system, the temperature of arc combustion can be as high as thousands of degrees, which can lead to an electrical fire. Deep learning has developed rapidly in recent years and is widely used in fault diagnosis. The problem is that the sourced data is challenging to obtain, and few public data sources affect the application of deep learning models in arc fault diagnosis. In order to solve this problem, an arc fault detection method based on continuous wavelet transform and deep residual shrinkage network with the channel-wise threshold (DRSN-CW) is proposed. First, the grayscale images of source data features are obtained by continuous wavelet transform. Then, the feature images are data enhanced to construct the dataset. Finally, the DRSN-CW model is constructed and used to detect arc fault. The results show that the highest accuracy of arc fault detection is 98.92%, and the average accuracy is 97.72%. This method has excellent performance, which provides a new idea for arc fault detection.