Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition. Purushotham, V., Narayanan, S., & Prasad, S. A. N. NDT & E International, 38(8):654–664, December, 2005.
![Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex
Paper doi abstract bibtex Due to the importance of rolling bearings as the most widely used machine elements, it is necessary to establish a suitable condition monitoring procedure to prevent malfunctions and breakages during operation. This paper presents a new method for detecting localized bearing defects based on wavelet transform. Bearing race faults have been detected by using discrete wavelet transform (DWT). Vibration signals from ball bearings having single and multiple point defects on inner race, outer race, ball fault and combination of these faults have been considered for analysis. Wavelet transform provides a variable resolution time–frequency distribution from which periodic structural ringing due to repetitive force impulses, generated upon the passing of each rolling element over the defect, are detected. It is found that the impulses appear periodically with a time period corresponding to characteristic defect frequencies. In this study, the diagnoses of ball bearing race faults have been investigated using wavelet transform. These results are compared with feature extraction data and results from spectrum analysis. It has been clearly shown that DWT can be used as an effective tool for detecting single and multiple faults in ball bearings. This paper also presents a new method of pattern recognition for bearing fault monitoring using hidden Markov Models (HMMs). Experimental results show that successful bearing fault detection rates as high as 99% can be achieved by this approach.
@article{purushotham_multi-fault_2005,
title = {Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden {Markov} model based fault recognition},
volume = {38},
issn = {0963-8695},
url = {https://www.sciencedirect.com/science/article/pii/S0963869505000666},
doi = {10.1016/j.ndteint.2005.04.003},
abstract = {Due to the importance of rolling bearings as the most widely used machine elements, it is necessary to establish a suitable condition monitoring procedure to prevent malfunctions and breakages during operation. This paper presents a new method for detecting localized bearing defects based on wavelet transform. Bearing race faults have been detected by using discrete wavelet transform (DWT). Vibration signals from ball bearings having single and multiple point defects on inner race, outer race, ball fault and combination of these faults have been considered for analysis. Wavelet transform provides a variable resolution time–frequency distribution from which periodic structural ringing due to repetitive force impulses, generated upon the passing of each rolling element over the defect, are detected. It is found that the impulses appear periodically with a time period corresponding to characteristic defect frequencies. In this study, the diagnoses of ball bearing race faults have been investigated using wavelet transform. These results are compared with feature extraction data and results from spectrum analysis. It has been clearly shown that DWT can be used as an effective tool for detecting single and multiple faults in ball bearings. This paper also presents a new method of pattern recognition for bearing fault monitoring using hidden Markov Models (HMMs). Experimental results show that successful bearing fault detection rates as high as 99\% can be achieved by this approach.},
language = {en},
number = {8},
urldate = {2021-11-04},
journal = {NDT \& E International},
author = {Purushotham, V. and Narayanan, S. and Prasad, Suryanarayana A. N.},
month = dec,
year = {2005},
keywords = {Bearing fault recognition, Discrete wavelet transform, Hidden Markov model, Impulses, Mel frequency complex cepstrum},
pages = {654--664},
}Downloads: 0
{"_id":"iioXxtsQztxXzKTyk","bibbaseid":"purushotham-narayanan-prasad-multifaultdiagnosisofrollingbearingelementsusingwaveletanalysisandhiddenmarkovmodelbasedfaultrecognition-2005","author_short":["Purushotham, V.","Narayanan, S.","Prasad, S. A. N."],"bibdata":{"bibtype":"article","type":"article","title":"Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition","volume":"38","issn":"0963-8695","url":"https://www.sciencedirect.com/science/article/pii/S0963869505000666","doi":"10.1016/j.ndteint.2005.04.003","abstract":"Due to the importance of rolling bearings as the most widely used machine elements, it is necessary to establish a suitable condition monitoring procedure to prevent malfunctions and breakages during operation. This paper presents a new method for detecting localized bearing defects based on wavelet transform. Bearing race faults have been detected by using discrete wavelet transform (DWT). Vibration signals from ball bearings having single and multiple point defects on inner race, outer race, ball fault and combination of these faults have been considered for analysis. Wavelet transform provides a variable resolution time–frequency distribution from which periodic structural ringing due to repetitive force impulses, generated upon the passing of each rolling element over the defect, are detected. It is found that the impulses appear periodically with a time period corresponding to characteristic defect frequencies. In this study, the diagnoses of ball bearing race faults have been investigated using wavelet transform. These results are compared with feature extraction data and results from spectrum analysis. It has been clearly shown that DWT can be used as an effective tool for detecting single and multiple faults in ball bearings. This paper also presents a new method of pattern recognition for bearing fault monitoring using hidden Markov Models (HMMs). Experimental results show that successful bearing fault detection rates as high as 99% can be achieved by this approach.","language":"en","number":"8","urldate":"2021-11-04","journal":"NDT & E International","author":[{"propositions":[],"lastnames":["Purushotham"],"firstnames":["V."],"suffixes":[]},{"propositions":[],"lastnames":["Narayanan"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Prasad"],"firstnames":["Suryanarayana","A.","N."],"suffixes":[]}],"month":"December","year":"2005","keywords":"Bearing fault recognition, Discrete wavelet transform, Hidden Markov model, Impulses, Mel frequency complex cepstrum","pages":"654–664","bibtex":"@article{purushotham_multi-fault_2005,\n\ttitle = {Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden {Markov} model based fault recognition},\n\tvolume = {38},\n\tissn = {0963-8695},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0963869505000666},\n\tdoi = {10.1016/j.ndteint.2005.04.003},\n\tabstract = {Due to the importance of rolling bearings as the most widely used machine elements, it is necessary to establish a suitable condition monitoring procedure to prevent malfunctions and breakages during operation. This paper presents a new method for detecting localized bearing defects based on wavelet transform. Bearing race faults have been detected by using discrete wavelet transform (DWT). Vibration signals from ball bearings having single and multiple point defects on inner race, outer race, ball fault and combination of these faults have been considered for analysis. Wavelet transform provides a variable resolution time–frequency distribution from which periodic structural ringing due to repetitive force impulses, generated upon the passing of each rolling element over the defect, are detected. It is found that the impulses appear periodically with a time period corresponding to characteristic defect frequencies. In this study, the diagnoses of ball bearing race faults have been investigated using wavelet transform. These results are compared with feature extraction data and results from spectrum analysis. It has been clearly shown that DWT can be used as an effective tool for detecting single and multiple faults in ball bearings. This paper also presents a new method of pattern recognition for bearing fault monitoring using hidden Markov Models (HMMs). Experimental results show that successful bearing fault detection rates as high as 99\\% can be achieved by this approach.},\n\tlanguage = {en},\n\tnumber = {8},\n\turldate = {2021-11-04},\n\tjournal = {NDT \\& E International},\n\tauthor = {Purushotham, V. and Narayanan, S. and Prasad, Suryanarayana A. N.},\n\tmonth = dec,\n\tyear = {2005},\n\tkeywords = {Bearing fault recognition, Discrete wavelet transform, Hidden Markov model, Impulses, Mel frequency complex cepstrum},\n\tpages = {654--664},\n}\n\n","author_short":["Purushotham, V.","Narayanan, S.","Prasad, S. A. N."],"key":"purushotham_multi-fault_2005","id":"purushotham_multi-fault_2005","bibbaseid":"purushotham-narayanan-prasad-multifaultdiagnosisofrollingbearingelementsusingwaveletanalysisandhiddenmarkovmodelbasedfaultrecognition-2005","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0963869505000666"},"keyword":["Bearing fault recognition","Discrete wavelet transform","Hidden Markov model","Impulses","Mel frequency complex cepstrum"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["XJ7Gu6aiNbAiJAjbw","XvjRDbrMBW2XJY3p9","3C6BKwtiX883bctx4","5THezwiL4FyF8mm4G","RktFJE9cDa98BRLZF","qpxPuYKLChgB7ox6D","PfM5iniYHEthCfQDH","iwKepCrWBps7ojhDx"],"keywords":["bearing fault recognition","discrete wavelet transform","hidden markov model","impulses","mel frequency complex cepstrum"],"search_terms":["multi","fault","diagnosis","rolling","bearing","elements","using","wavelet","analysis","hidden","markov","model","based","fault","recognition","purushotham","narayanan","prasad"],"title":"Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition","year":2005}