Prognostics for Ball Bearing Based on Neural Networks and Morlet Wavelet
This paper deals with a new scheme for prognostics of ball bearing based on Self-Organizing Map (SOM), back propagation neural-network and complex Morlet Wavelet methods. It uses complex Morlet wavelet-based envelope to extract successfully the characteristic frequencies of ball bearing. Then the minimum quantization error (MQE) indicator deriving from SOM is used for performance degradation assessment. Based on Weight Application to Failure Times (WAFT) technology, which deriving from back propagation neural networks, a prognostics model of ball bearing is developed successfully. And the experimental results show that the proposed methods are greatly superior to the currently used L10 bearing life prediction.
Wunyuh Jywe, Chieh-Li Chen, Kuang-Chao Fan, R.F. Fung, S.G. Hanson,Wen-Hsiang Hsieh, Chaug-Liang Hsu, You-Min Huang, Yunn-Lin Hwang, Gerd Jäger, Y.R. Jeng, Wenlung Li, Yunn-Shiuan Liao, Chien-Chang Lin, Zong-Ching Lin, Cheng-Kuo Sung and Ching-Huan Tzeng
R. Q. Huang et al., "Prognostics for Ball Bearing Based on Neural Networks and Morlet Wavelet", Materials Science Forum, Vols. 505-507, pp. 1153-1158, 2006