Sparse filtering with the generalized lp/lq norm and its applications to the condition monitoring of rotating machinery

• Published in: Mechanical systems and signal processing Vol. 102; pp. 198 - 213
• Main Authors: Jia, Xiaodong, Zhao, Ming, Di, Yuan, Li, Pin, Lee, Jay
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.03.2018
• Subjects: Deep learning; Incipient fault detection; Minimum entropy deconvolution; Rotating machinery; Sparse filtering; Deep learning; Sparse filtering; Rotating machinery; Minimum entropy deconvolution; Incipient fault detection
• ISSN: 0888-3270; 1096-1216
• DOI: 10.1016/j.ymssp.2017.09.018

•The characteristic of lp/lq norm is discussed mathematically.•A novel sparse filtering method is proposed based on the lp/lq norm.•The proposed method is validated for condition monitoring of rotating machines. Sparsity is becoming a more and more important topic in the area of machine learning and signal processing recently. One big family of sparse measures in current literature is the generalized lp/lq norm, which is scale invariant and is widely regarded as normalized lp norm. However, the characteristics of the generalized lp/lq norm are still less discussed and its application to the condition monitoring of rotating devices has been still unexplored. In this study, we firstly discuss the characteristics of the generalized lp/lq norm for sparse optimization and then propose a method of sparse filtering with the generalized lp/lq norm for the purpose of impulsive signature enhancement. Further driven by the trend of industrial big data and the need of reducing maintenance cost for industrial equipment, the proposed sparse filter is customized for vibration signal processing and also implemented on bearing and gearbox for the purpose of condition monitoring. Based on the results from the industrial implementations in this paper, the proposed method has been found to be a promising tool for impulsive feature enhancement, and the superiority of the proposed method over previous methods is also demonstrated.