Car assembly line fault diagnosis based on robust wavelet SVC and PSO

摘要

Aiming at some hybrid noises from complex fault diagnosis system, a robust loss function is designed to penalize hybrid noises, a wavelet kernel function is constructed on basis of wavelet base function, and then this paper proposes robust wavelet v-support vector classifier machine (RWv-SVC). To seek the optimal parameter of RWv-SVC, particle swarm optimization (PSO) is proposed. The results of application in fault diagnosis of car assembly line show the hybrid diagnosis model based on RWv-SVC and PSO is effective and feasible, the comparison between the method proposed in this paper and other ones is also given, which proves this method is better than v-SVC and Wv-SVC.