Particle Swarm Optimization-Support Vector Machine Model for Machinery Fault Diagnoses in High-Voltage Circuit Breakers

According to statistic data, machinery faults contribute to largest proportion of High-voltage circuit breaker failures, and traditional maintenance methods exist some disadvantages for that issue. Therefore, based on the wavelet packet decomposition approach and support vector machines, a new diagnosis model is proposed for such fault diagnoses in this study. The vibration eigenvalue extraction is analyzed through wavelet packet decomposition, and a four-layer support vector machine is constituted as a fault classifier. The Gaussian radial basis function is employed as the kernel function for the classifier. The penalty parameter c and kernel parameter δ of the support vector machine are vital for the diagnostic accuracy, and these parameters must be carefully predetermined. Thus, a particle swarm optimization-support vector machine model is developed in which the optimal parameters c and δ for the support vector machine in each layer are determined by the particle swarm algorithm. The validity of this fault diagnosis model is determined with a real dataset from the operation experiment. Moreover, comparative investigations of fault diagnosis experiments with a normal support vector machine and a particle swarm optimization back-propagation neural network are also implemented. The results indicate that the proposed fault diagnosis model yields better accuracy and efficiency than these other models.