Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring. Yu, J. Mechanical Systems and Signal Processing, 83:149–162, January, 2017.
![Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex
Paper doi abstract bibtex This study proposes an adaptive-learning-based method for machine faulty detection and health degradation monitoring. The kernel of the proposed method is an “evolving” model that uses an unsupervised online learning scheme, in which an adaptive hidden Markov model (AHMM) is used for online learning the dynamic health changes of machines in their full life. A statistical index is developed for recognizing the new health states in the machines. Those new health states are then described online by adding of new hidden states in AHMM. Furthermore, the health degradations in machines are quantified online by an AHMM-based health index (HI) that measures the similarity between two density distributions that describe the historic and current health states, respectively. When necessary, the proposed method characterizes the distinct operating modes of the machine and can learn online both abrupt as well as gradual health changes. Our method overcomes some drawbacks of the HIs (e.g., relatively low comprehensibility and applicability) based on fixed monitoring models constructed in the offline phase. Results from its application in a bearing life test reveal that the proposed method is effective in online detection and adaptive assessment of machine health degradation. This study provides a useful guide for developing a condition-based maintenance (CBM) system that uses an online learning method without considerable human intervention.
@article{yu_adaptive_2017,
title = {Adaptive hidden {Markov} model-based online learning framework for bearing faulty detection and performance degradation monitoring},
volume = {83},
issn = {0888-3270},
url = {https://www.sciencedirect.com/science/article/pii/S0888327016301674},
doi = {10.1016/j.ymssp.2016.06.004},
abstract = {This study proposes an adaptive-learning-based method for machine faulty detection and health degradation monitoring. The kernel of the proposed method is an “evolving” model that uses an unsupervised online learning scheme, in which an adaptive hidden Markov model (AHMM) is used for online learning the dynamic health changes of machines in their full life. A statistical index is developed for recognizing the new health states in the machines. Those new health states are then described online by adding of new hidden states in AHMM. Furthermore, the health degradations in machines are quantified online by an AHMM-based health index (HI) that measures the similarity between two density distributions that describe the historic and current health states, respectively. When necessary, the proposed method characterizes the distinct operating modes of the machine and can learn online both abrupt as well as gradual health changes. Our method overcomes some drawbacks of the HIs (e.g., relatively low comprehensibility and applicability) based on fixed monitoring models constructed in the offline phase. Results from its application in a bearing life test reveal that the proposed method is effective in online detection and adaptive assessment of machine health degradation. This study provides a useful guide for developing a condition-based maintenance (CBM) system that uses an online learning method without considerable human intervention.},
language = {en},
urldate = {2021-11-15},
journal = {Mechanical Systems and Signal Processing},
author = {Yu, Jianbo},
month = jan,
year = {2017},
keywords = {Adaptive learning, Health degradation monitoring, Hidden Markov model, Machine faulty detection},
pages = {149--162},
}Downloads: 0
{"_id":"HpWLZ32DdxjfoYJhn","bibbaseid":"yu-adaptivehiddenmarkovmodelbasedonlinelearningframeworkforbearingfaultydetectionandperformancedegradationmonitoring-2017","author_short":["Yu, J."],"bibdata":{"bibtype":"article","type":"article","title":"Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring","volume":"83","issn":"0888-3270","url":"https://www.sciencedirect.com/science/article/pii/S0888327016301674","doi":"10.1016/j.ymssp.2016.06.004","abstract":"This study proposes an adaptive-learning-based method for machine faulty detection and health degradation monitoring. The kernel of the proposed method is an “evolving” model that uses an unsupervised online learning scheme, in which an adaptive hidden Markov model (AHMM) is used for online learning the dynamic health changes of machines in their full life. A statistical index is developed for recognizing the new health states in the machines. Those new health states are then described online by adding of new hidden states in AHMM. Furthermore, the health degradations in machines are quantified online by an AHMM-based health index (HI) that measures the similarity between two density distributions that describe the historic and current health states, respectively. When necessary, the proposed method characterizes the distinct operating modes of the machine and can learn online both abrupt as well as gradual health changes. Our method overcomes some drawbacks of the HIs (e.g., relatively low comprehensibility and applicability) based on fixed monitoring models constructed in the offline phase. Results from its application in a bearing life test reveal that the proposed method is effective in online detection and adaptive assessment of machine health degradation. This study provides a useful guide for developing a condition-based maintenance (CBM) system that uses an online learning method without considerable human intervention.","language":"en","urldate":"2021-11-15","journal":"Mechanical Systems and Signal Processing","author":[{"propositions":[],"lastnames":["Yu"],"firstnames":["Jianbo"],"suffixes":[]}],"month":"January","year":"2017","keywords":"Adaptive learning, Health degradation monitoring, Hidden Markov model, Machine faulty detection","pages":"149–162","bibtex":"@article{yu_adaptive_2017,\n\ttitle = {Adaptive hidden {Markov} model-based online learning framework for bearing faulty detection and performance degradation monitoring},\n\tvolume = {83},\n\tissn = {0888-3270},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0888327016301674},\n\tdoi = {10.1016/j.ymssp.2016.06.004},\n\tabstract = {This study proposes an adaptive-learning-based method for machine faulty detection and health degradation monitoring. The kernel of the proposed method is an “evolving” model that uses an unsupervised online learning scheme, in which an adaptive hidden Markov model (AHMM) is used for online learning the dynamic health changes of machines in their full life. A statistical index is developed for recognizing the new health states in the machines. Those new health states are then described online by adding of new hidden states in AHMM. Furthermore, the health degradations in machines are quantified online by an AHMM-based health index (HI) that measures the similarity between two density distributions that describe the historic and current health states, respectively. When necessary, the proposed method characterizes the distinct operating modes of the machine and can learn online both abrupt as well as gradual health changes. Our method overcomes some drawbacks of the HIs (e.g., relatively low comprehensibility and applicability) based on fixed monitoring models constructed in the offline phase. Results from its application in a bearing life test reveal that the proposed method is effective in online detection and adaptive assessment of machine health degradation. This study provides a useful guide for developing a condition-based maintenance (CBM) system that uses an online learning method without considerable human intervention.},\n\tlanguage = {en},\n\turldate = {2021-11-15},\n\tjournal = {Mechanical Systems and Signal Processing},\n\tauthor = {Yu, Jianbo},\n\tmonth = jan,\n\tyear = {2017},\n\tkeywords = {Adaptive learning, Health degradation monitoring, Hidden Markov model, Machine faulty detection},\n\tpages = {149--162},\n}\n\n\n\n","author_short":["Yu, J."],"key":"yu_adaptive_2017","id":"yu_adaptive_2017","bibbaseid":"yu-adaptivehiddenmarkovmodelbasedonlinelearningframeworkforbearingfaultydetectionandperformancedegradationmonitoring-2017","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0888327016301674"},"keyword":["Adaptive learning","Health degradation monitoring","Hidden Markov model","Machine faulty detection"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["adaptive learning","health degradation monitoring","hidden markov model","machine faulty detection"],"search_terms":["adaptive","hidden","markov","model","based","online","learning","framework","bearing","faulty","detection","performance","degradation","monitoring","yu"],"title":"Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring","year":2017}