Fault Diagnosis for Single-phase Grounding in Distribution Network Based on Hilbert-Huang Transform and Siamese Convolution Neural Network

Single-phase grounding fault is the most common fault in distribution network. It is very important to quickly identify the cause of single-phase grounding fault for improving the reliability of power supply in distribution network. For similar types of faults that are not easy to identify, this paper presents a feature extraction method for single-phase grounding faults in distribution network based on Hilbert-Huang transformation. To solve the problem of insufficient training samples, this paper presents a fault diagnosis method for single-phase grounding in distribution networks based on Siamese convolution neural network, which can extract valid fault features under the condition of insufficient fault samples and significantly improve the fault diagnosis results.