Diagnosis of Inter-Turn Short Circuit Fault Based on Wavelet Transform and PSO-SVM

The inter-turn short circuit fault is a common fault in the drive motor which has a serious hazard to the safe operation of the motor. However, due to the high concealment of the inter-turn short circuit fault, it is difficult to find the fault in the initial stage. Therefore, how to diagnose it in the early stage becomes extremely important. This paper presents a fault diagnosis method of motor inter-turn short circuit based on wavelet transform and optimized support vector machine. First, the wavelet transform is used to decompose the motor phase current, and input the decomposed energy vector of each frequency band as the identification feature into the support vector machine classifier. At the same time, the particle swarm optimization algorithm is used to optimize the penalty factor and kernel parameters of the support vector machine to ensure The model has high diagnostic power.