Fault Diagnosis for Rolling Bearing Based on Genetic-SVM Classifier
Fault diagnosis of roller bearings is very complex, so it is difficult to use the mathematical model to describe their faults. Whose developmental changes have dual trends of increase and fluctuation. In this study, support vector machine trained by genetic algorithm based on high frequency demodulation analysis is proposed to fault diagnosis of ball bearing. Genetic algorithm is used to determine training parameters of support vector machine in this model, which can optimize the support vector machine (SVM) an intelligent diagnostic model. The performance of the GSVM system proposed in this study is evaluated by roller bearings in the wood-wool production device. The experimental results indicate that the proposed support vector machine trained by genetic algorithm has good diagnosis results in the application.
Jianmin Zeng, Zhengyi Jiang, Taosen Li, Daoguo Yang and Yun-Hae Kim
Y. J. Xu "Fault Diagnosis for Rolling Bearing Based on Genetic-SVM Classifier", Advanced Materials Research, Vols. 199-200, pp. 620-624, 2011