A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions
Abstract Most gear fault diagnosis (GFD) approaches suffer from inefficiency when facing with multiple varying working conditions at the same time. In this paper, a non-negative matrix factorization (NMF)-theoretic co-clustering strategy is proposed specially to classify more than one task at the sa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-02-01
|
| Series: | Chinese Journal of Mechanical Engineering |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s10033-020-00437-3 |
| _version_ | 1819019572547682304 |
|---|---|
| author | Fei Shen Chao Chen Jiawen Xu Ruqiang Yan |
| author_facet | Fei Shen Chao Chen Jiawen Xu Ruqiang Yan |
| author_sort | Fei Shen |
| collection | DOAJ |
| description | Abstract Most gear fault diagnosis (GFD) approaches suffer from inefficiency when facing with multiple varying working conditions at the same time. In this paper, a non-negative matrix factorization (NMF)-theoretic co-clustering strategy is proposed specially to classify more than one task at the same time using the high dimension matrix, aiming to offer a fast multi-tasking solution. The short-time Fourier transform (STFT) is first used to obtain the time-frequency features from the gear vibration signal. Then, the optimal clustering numbers are estimated using the Bayesian information criterion (BIC) theory, which possesses the simultaneous assessment capability, compared with traditional validity indexes. Subsequently, the classical/modified NMF-based co-clustering methods are carried out to obtain the classification results in both row and column tasks. Finally, the parameters involved in BIC and NMF algorithms are determined using the gradient ascent (GA) strategy in order to achieve reliable diagnostic results. The Spectra Quest’s Drivetrain Dynamics Simulator gear data sets were analyzed to verify the effectiveness of the proposed approach. |
| first_indexed | 2024-12-21T03:37:27Z |
| format | Article |
| id | doaj.art-c61c35321db94fb4b8ff4befb7e76572 |
| institution | Directory Open Access Journal |
| issn | 1000-9345 2192-8258 |
| language | English |
| last_indexed | 2024-12-21T03:37:27Z |
| publishDate | 2020-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Chinese Journal of Mechanical Engineering |
| spelling | doaj.art-c61c35321db94fb4b8ff4befb7e765722022-12-21T19:17:18ZengSpringerOpenChinese Journal of Mechanical Engineering1000-93452192-82582020-02-0133111510.1186/s10033-020-00437-3A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working ConditionsFei Shen0Chao Chen1Jiawen Xu2Ruqiang Yan3School of Instrument Science and Engineering, Southeast UniversitySchool of Instrument Science and Engineering, Southeast UniversitySchool of Instrument Science and Engineering, Southeast UniversitySchool of Instrument Science and Engineering, Southeast UniversityAbstract Most gear fault diagnosis (GFD) approaches suffer from inefficiency when facing with multiple varying working conditions at the same time. In this paper, a non-negative matrix factorization (NMF)-theoretic co-clustering strategy is proposed specially to classify more than one task at the same time using the high dimension matrix, aiming to offer a fast multi-tasking solution. The short-time Fourier transform (STFT) is first used to obtain the time-frequency features from the gear vibration signal. Then, the optimal clustering numbers are estimated using the Bayesian information criterion (BIC) theory, which possesses the simultaneous assessment capability, compared with traditional validity indexes. Subsequently, the classical/modified NMF-based co-clustering methods are carried out to obtain the classification results in both row and column tasks. Finally, the parameters involved in BIC and NMF algorithms are determined using the gradient ascent (GA) strategy in order to achieve reliable diagnostic results. The Spectra Quest’s Drivetrain Dynamics Simulator gear data sets were analyzed to verify the effectiveness of the proposed approach.http://link.springer.com/article/10.1186/s10033-020-00437-3Gear fault diagnosisNon-negative matrix factorizationCo-clusteringVarying working conditions |
| spellingShingle | Fei Shen Chao Chen Jiawen Xu Ruqiang Yan A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions Chinese Journal of Mechanical Engineering Gear fault diagnosis Non-negative matrix factorization Co-clustering Varying working conditions |
| title | A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions |
| title_full | A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions |
| title_fullStr | A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions |
| title_full_unstemmed | A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions |
| title_short | A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions |
| title_sort | fast multi tasking solution nmf theoretic co clustering for gear fault diagnosis under variable working conditions |
| topic | Gear fault diagnosis Non-negative matrix factorization Co-clustering Varying working conditions |
| url | http://link.springer.com/article/10.1186/s10033-020-00437-3 |
| work_keys_str_mv | AT feishen afastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions AT chaochen afastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions AT jiawenxu afastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions AT ruqiangyan afastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions AT feishen fastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions AT chaochen fastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions AT jiawenxu fastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions AT ruqiangyan fastmultitaskingsolutionnmftheoreticcoclusteringforgearfaultdiagnosisundervariableworkingconditions |