Sparsity Measures and their Signal Processing Applications for Machine Condition Monitoring

Auteur
Dr Dong Wang has over 15 years of research experience on machine condition monitoring and fault diagnosis. Dr. Wang's research focuses on the theoretical foundations of fault feature extraction and their applications to machine condition monitoring, fault diagnosis and prognostics. Dr. Wang has published over 150 journal papers (the first author for 40+ papers) Bingchang Hou received his B.Eng. degree in Mechanical Engineering from Chongqing University, Chongqing, China, in 2020. Since Sep. 2020, he is pursuing his Ph.D. degree in Department of Industrial Engineering and Management, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China. His research interests include machine condition monitoring and fault diagnosis, prognostics and health management, sparsity measures, signal processing, and machine learning

Texte du rabat
Sparsity measures are effective indicators for quantifying the sparsity of data sequences. They are often used for fault feature characterization in condition monitoring and fault diagnosis of rotating machinery. Sparsity Measures and their Signal Processing Applications for Machine Condition Monitoring introduces newly designed sparsity measures and their advanced signal processing technologies for machine condition monitoring and fault diagnosis. The book systematically introduces: (1) new sparsity measures such as quasi-arithmetic mean ratio framework for fault signatures quantification, generalized Gini index, etc.; (2) classic sparsity measures based on signal processing technologies and cycle-embedded sparsity measure based on new impulsive mode decomposition technology; and (3) a sparsity measure data-driven framework based optimized weights spectrum theory and its relevant advanced signal processing technologies.

Contenu

1. Introduction and background
   
   2. Basic signal processing transforms and analysis
   3. Newly advanced sparsity measures for fault signature quantification
   4. Classic and advanced sparsity measures-based signal processing technologies
   5. Sparsity measures data-driven framework based signal processing technologies
   6. Outlook References