A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation
Abstract Feature selection is a difficult but highly important preliminary step for bearings remaining useful life (RUL) estimation. To avoid the weights setting problem in hybrid metric, this work devotes to conduct feature selection by using a single metric. Due to noise and outliers, an existing...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-10-01
|
| Series: | SN Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-023-05518-1 |
| _version_ | 1797636788178649088 |
|---|---|
| author | Fei Huang Alexandre Sava Kondo H. Adjallah Dongyang Zhang |
| author_facet | Fei Huang Alexandre Sava Kondo H. Adjallah Dongyang Zhang |
| author_sort | Fei Huang |
| collection | DOAJ |
| description | Abstract Feature selection is a difficult but highly important preliminary step for bearings remaining useful life (RUL) estimation. To avoid the weights setting problem in hybrid metric, this work devotes to conduct feature selection by using a single metric. Due to noise and outliers, an existing feature selection metric, called monotonicity, used for estimating bearings RUL, requires data smoothing processing before adequate implementation. Such a smoothing process may remove significant part of meaningful information from data. To overcome this issue, a mixture distribution analysis-based feature selection metric is proposed. Moreover, based on this new metric, a feature selection approach for bearings RUL estimation is proposed. Numerical experiments benchmarking the proposed method and the existing metric monotonicity method on available real datasets highlight its effectiveness. |
| first_indexed | 2024-03-11T12:39:09Z |
| format | Article |
| id | doaj.art-ec511023047f4b679bb4df591206b4cb |
| institution | Directory Open Access Journal |
| issn | 2523-3963 2523-3971 |
| language | English |
| last_indexed | 2024-03-11T12:39:09Z |
| publishDate | 2023-10-01 |
| publisher | Springer |
| record_format | Article |
| series | SN Applied Sciences |
| spelling | doaj.art-ec511023047f4b679bb4df591206b4cb2023-11-05T12:26:36ZengSpringerSN Applied Sciences2523-39632523-39712023-10-015111910.1007/s42452-023-05518-1A mixture distributions analysis based feature selection approach for bearing remaining useful life estimationFei Huang0Alexandre Sava1Kondo H. Adjallah2Dongyang Zhang3Huaiyin Institute of TechnologyLCOMS, Université de LorraineLCOMS, Université de LorraineXi’an Novastar Tech Co., LtdAbstract Feature selection is a difficult but highly important preliminary step for bearings remaining useful life (RUL) estimation. To avoid the weights setting problem in hybrid metric, this work devotes to conduct feature selection by using a single metric. Due to noise and outliers, an existing feature selection metric, called monotonicity, used for estimating bearings RUL, requires data smoothing processing before adequate implementation. Such a smoothing process may remove significant part of meaningful information from data. To overcome this issue, a mixture distribution analysis-based feature selection metric is proposed. Moreover, based on this new metric, a feature selection approach for bearings RUL estimation is proposed. Numerical experiments benchmarking the proposed method and the existing metric monotonicity method on available real datasets highlight its effectiveness.https://doi.org/10.1007/s42452-023-05518-1Feature selectionMixture distributionsMonotonicityRemaining useful lifeBearing faultDegradation monitoring |
| spellingShingle | Fei Huang Alexandre Sava Kondo H. Adjallah Dongyang Zhang A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation SN Applied Sciences Feature selection Mixture distributions Monotonicity Remaining useful life Bearing fault Degradation monitoring |
| title | A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation |
| title_full | A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation |
| title_fullStr | A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation |
| title_full_unstemmed | A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation |
| title_short | A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation |
| title_sort | mixture distributions analysis based feature selection approach for bearing remaining useful life estimation |
| topic | Feature selection Mixture distributions Monotonicity Remaining useful life Bearing fault Degradation monitoring |
| url | https://doi.org/10.1007/s42452-023-05518-1 |
| work_keys_str_mv | AT feihuang amixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation AT alexandresava amixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation AT kondohadjallah amixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation AT dongyangzhang amixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation AT feihuang mixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation AT alexandresava mixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation AT kondohadjallah mixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation AT dongyangzhang mixturedistributionsanalysisbasedfeatureselectionapproachforbearingremainingusefullifeestimation |