Fault diagnosis method for low-voltage circuit breakers based on BWO-SCN

Low-voltage air circuit breaker is an important part of power system, its hard to detect internal faults under long-term operation condition. Therefore, fault diagnosis of low-voltage circuit breakers has always been a research hotspot. This article takes RGW1 low-voltage universal air circuit breaker as the research object, A fault diagnosis method of low-voltage air circuit breaker based on Multi-Resolution Singular Value Decomposition (MRSVD) denoising and Beluga Whale Optimization (BWO) optimize Stochastic Configuration Networks (SCN) is proposed. Firstly, the closing vibration signals under different fault states are collected and MRSVD is used for noise reduction. Secondly, Variational Mode Decomposition (VMD) was used to decompose the denoised signal, and the sample entropy of each component was extracted as the feature vector. Finally, the BWO was used to optimize the SCN(BWO-SCN), The feature vector was used as the input of the model, and the fault category was used as the output. Accuracy, Confusion Matrix and Receiver Operating Characteristic (ROC) curve were used as evaluation indexes. The results show that the proposed method can identify the vibration signals under different fault states of circuit breakers with high accuracy.