作者: Xin Zhang , Zhiwen Liu , Jiaxu Wang , Jinglin Wang
DOI: 10.1016/J.ISATRA.2018.11.033
关键词: Computer science 、 Bearing (mechanical) 、 Continuous wavelet 、 Morlet wavelet 、 Gabor wavelet 、 Artificial intelligence 、 Continuous wavelet transform 、 Pattern recognition 、 Time–frequency analysis 、 Wavelet transform 、 Fault (power engineering)
摘要: Abstract Rolling element bearings are key and also vulnerable machine elements in rotating machinery. Fault diagnosis of rolling is significant for guaranteeing machinery safety functionality. To accurately extract bearing diagnostic information, a time–frequency analysis method based on continuous wavelet transform (CWT) multiple Q-factor Gabor wavelets (MQGWs) (termed CMQGWT) introduced this paper. In the CMQGWT method, with Q-factors adopted sets coefficients each combined to generate map. By way, resolution CWT map can be greatly increased information identified. Numerical simulation carried out verified effectiveness proposed method. Case studies comparisons Morlet (CMWT) tunable (TQWT) demonstrate superiority extraction fault identification.