Power Grid Fault Diagnosis Method Based on Inception Network

Abstract

With the continuous evolution of grid intelligence, the traditional grid fault diagnosis model can not satisfied the development needs of smart grid in terms of accuracy and diagnosis speed, and how to apply the fault information provided by the supervisory control and data acquisition (SCADA) system to achieve fast and accurate grid fault diagnosis is the main problem at present. In this paper, we propose an Inception network-based fault diagnosis method, in which the alarm information of different fault types is filtered and transformed into a grayscale map as model input to avoid the interference of redundant alarm information to the fault diagnosis, and the Inception network with excellent image feature extraction capability is employed to obtain the grayscale map of the alarm information to achieve fast fault diagnosis. This method has been proven to have excellent fault-type discriminatory capability and is effective in achieving fast and accurate fault diagnosis based on deep learning algorithms.