A new methodology for condition monitoring based on perceptual hashing

A common problem that machine condition monitoring encounters is the high data throughput and bandwidth consumption, especially for wave signals sampled with high frequency. In order to reduce the data dimension while retrieve much diagnostic information from the monitored data, a new methodology is proposed based on perceptual hashing, which can take the respective advantage of Cloud computing and Edge computing. The feasibility of this methodology is discussed and demonstrated through a naive perceptual hashing example with bearing vibration signals. Considerations in perceptual hashing of monitored data and modeling for performance assessment, diagnosis and prognosis are further discussed. With perceptual hashing, not only the data dimension can be reduced, but also the diagnostic modeling can benefit from the geometric structure of machine condition hash (MCH).

[1]  Jay Lee,et al.  Recent advances and trends in predictive manufacturing systems in big data environment , 2013 .

[2]  Yaguo Lei,et al.  Machinery health prognostics: A systematic review from data acquisition to RUL prediction , 2018 .

[3]  Yixiang Huang,et al.  Adaptive feature extraction using sparse coding for machinery fault diagnosis , 2011 .

[4]  Zhongkui Zhu,et al.  Detection of signal transients based on wavelet and statistics for machine fault diagnosis , 2009 .

[5]  J. Antoni Cyclostationarity by examples , 2009 .

[6]  Jay Lee,et al.  A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems , 2015 .

[7]  James Hensman,et al.  Natural computing for mechanical systems research: A tutorial overview , 2011 .

[8]  Jay Lee,et al.  Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications , 2014 .

[9]  Jay Lee,et al.  A Reconfigurable Watchdog Agent ® for Machine Health Prognostics , 2008 .

[10]  Geoffrey E. Hinton,et al.  Semantic hashing , 2009, Int. J. Approx. Reason..

[11]  Lihui Wang,et al.  Cloud-Based Cyber-Physical Systems in Manufacturing , 2017 .

[12]  Xi Vincent Wang,et al.  Condition Monitoring for Predictive Maintenance , 2018 .

[13]  Weisong Shi,et al.  Edge Computing: Vision and Challenges , 2016, IEEE Internet of Things Journal.

[14]  Jiao Yu-hua,et al.  An Overview of Perceptual Hashing , 2008 .

[15]  Liu Wei,et al.  Edge Computing—An Emerging Computing Model for the Internet of Everything Era , 2017 .

[16]  Gaoliang Peng,et al.  A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load , 2018, Mechanical Systems and Signal Processing.

[17]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

[18]  Zude Zhou,et al.  Condition monitoring towards energy-efficient manufacturing: a review , 2017 .

[19]  Chin-Chen Chang,et al.  Perceptual hashing for color images based on hybrid extraction of structural features , 2018, Signal Process..