Series arc-fault diagnosis using convolutional neural network via generalized S-transform and power spectral density

Abstract

It is difficult to identify an arc fault accurately when the loads on the user side are more complicated, which hinders the development of low-voltage monitoring and pre-warning inspection. This study acquired a series of arc-fault signals according to IEC 62606. The main time-frequency features were strengthened with high efficiency by applying the generalized S-transform to them with a bi-Gaussian window. Further, the power spectrum density determination allowed for the detection of imperceptible high-frequency harmonic energy reflections, thus increasing the rate of arc-fault diagnosis and making it suitable for arc-fault monitoring of non-linear loads. The final samples were trained and classified using a 2D convolutional neural network and the overall accuracy of identification was observed to be 98.13%, which involved various domestic loads, thus providing a reference for follow-up arc-fault monitoring and inspection research.