Fault diagnosis of voltage source controlled static synchronous compensator based on combination of wavelet scattering transform and IRCA-ICA-Res
DOI：10.19783/j.cnki.pspc.240926
Key Words:wavelet scattering transform  attention module  neural network  fault diagnosis  time-frequency information
Author NameAffiliation
BI Guihong Kunming University of Science and Technology, School of Electric Power Engineering, Kunming 650500, China 
ZHANG Jingchao Kunming University of Science and Technology, School of Electric Power Engineering, Kunming 650500, China 
ZHAO Sihong Kunming University of Science and Technology, School of Electric Power Engineering, Kunming 650500, China 
CHEN Shilong Kunming University of Science and Technology, School of Electric Power Engineering, Kunming 650500, China 
KONG Fanwen Kunming University of Science and Technology, School of Electric Power Engineering, Kunming 650500, China 
CHEN Dongjing Kunming University of Science and Technology, School of Electric Power Engineering, Kunming 650500, China 
Hits: 1496
Download times: 192
Abstract:To fully utilize the time-frequency information contained in the IGBT open-circuit fault current signals of voltage source controlled static synchronous compensator (VSC-STATCOM) and improve the accuracy of fault diagnosis and identification, a novel WST-RCA-ICA-Res algorithm is proposed. This algorithm combines wavelet scattering transform (WST) with an improved residual channel attention (IRCA) module, and an improved coordinate attention (ICA) module with a residual neural network (Resnet). First, the Matlab/Simulink platform is used to simulate 22 types of faults in the VSC-STATCOM module under different operating conditions to obtain the fault sample set. Then, automatic robust feature extraction of fault signals is carried out using WST to construct a feature matrix containing time-frequency information. Finally, the IRCA-ICA-Res model is used to deeply extract, strengthen, and identify the feature matrix. Experimental results show that the proposed method has strong anti-noise performance and can accurately distinguish different IGBT fault types.
View Full Text  View/Add Comment  Download reader