Fault Diagnosis Method of Energy Storage Unit of Circuit Breakers Based on EWT-ISSA-BP

Abstract

Aiming at the problem of energy storage unit failure in the spring operating mechanism of low voltage circuit breakers (LVCBs). A fault diagnosis algorithm based on an improved Sparrow Search Algorithm (ISSA) optimized Backpropagation Neural Network (BPNN) is proposed to improve the operational safety of LVCB. Taking the 1.5kV/4000A/75kA LVCB as an example. According to the current operating characteristics of the energy storage motor, fault characteristics are extracted based on Empirical Wavelet Transform (EWT). Traditional BPNN has problems such as difficulty adjusting network weights and thresholds, being sensitive to initial weights, and quickly falling into local optimal solutions. The Sparrow Search Algorithm (SSA) with self-adjusting weight factors combined with bidirectional mutations is added to optimize the selection of BPNN hyperparameters. The results show that the ISSA-BPNN can accurately and quickly distinguish six conditions of motor voltage reduction: motor voltage increase, motor voltage decrease, energy storage spring stuck, transmission gear stuck, regular state and energy storage spring not locked. It is suitable for fault diagnosis and detection of the energy storage part of LVCB.