Enhanced deep gated recurrent unit and complex wavelet packet energy moment entropy for early fault prognosis of bearing

• Published in: Knowledge-based systems Vol. 188; p. 105022
• Main Authors: Haidong, Shao, Junsheng, Cheng, Hongkai, Jiang, Yu, Yang, Zhantao, Wu
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 05.01.2020; Elsevier Science Ltd
• Subjects: Algorithms; Bearing; Computer simulation; Decay rate; Drift och underhållsteknik; Early fault prognosis; Energy moment entropy; Enhanced deep gated recurrent unit; Entropy; Machine learning; Mapping; Modified training algorithm; Monitoring; Operation and Maintenance; Performance degradation; Prognosis; Rotating machinery; Wavelet analysis; Energy moment entropy; Early fault prognosis; Modified training algorithm; Enhanced deep gated recurrent unit; Bearing
• ISSN: 0950-7051; 1872-7409; 1872-7409
• DOI: 10.1016/j.knosys.2019.105022

Early fault prognosis of bearing is a very meaningful yet challenging task to improve the security of rotating machinery. For this purpose, a novel method based on enhanced deep gated recurrent unit and complex wavelet packet energy moment entropy is proposed in this paper. First, complex wavelet packet energy moment entropy is defined as a new monitoring index to characterize bearing performance degradation. Second, deep gated recurrent unit network is constructed to capture the nonlinear mapping relationship hidden in the defined monitoring index. Finally, a modified training algorithm based on learning rate decay strategy is developed to enhance the prognosis capability of the constructed deep model. The proposed method is applied to analyze the simulated and experimental signals of bearing. The results demonstrate that the proposed method is more superior in sensibility and accuracy to the existing methods. •Complex wavelet packet energy moment entropy is defined as the new monitoring index.•A deep gated recurrent unit network is constructed to model nonlinear time series.•A modified training algorithm is developed to further enhance the capability.•Several cases are used to verify the effectiveness of the proposed method.