Fault Diagnosis Technology of Industrial Circuit Breaker Optimized by Genetic Algorithm in LVQ Network

The current signal of industrial circuit breaker switching-off coil contains rich state information of circuit breaker operating mechanism, which is of great significance to fault diagnosis of operating mechanism. Firstly, the ensemble empirical mode decomposition (EMD) is used to detect the abrupt change point, and the effective current signal segment of the closing coil is determined, and the noise reduction process is carried out adaptively. Secondly, the time domain extremum method is used to process the effective signal segment, and the composite characteristic quantities of current and time are extracted. Finally, the composite feature data is preprocessed by tensor product, so that it can be input into the LVQ network optimized by genetic algorithm for supervised fault state identification and diagnosis. The experimental results show that the current and time composite feature extraction method proposed in this paper is effective, and the genetic algorithm optimized LVQ network algorithm has higher diagnostic accuracy than GA-BP and support vector machine algorithm, which has higher practical application value.