A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation
Remaining useful life is of great value in the industry and is a key component of Prognostics and Health Management (PHM) in the context of the Predictive Maintenance (PdM) strategy. Accurate estimation of the remaining useful life (RUL) is helpful for optimizing maintenance schedules, obtaining ins...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/4/1590 |
| _version_ | 1797476684434243584 |
|---|---|
| author | Diego Nieves Avendano Nathan Vandermoortele Colin Soete Pieter Moens Agusmian Partogi Ompusunggu Dirk Deschrijver Sofie Van Hoecke |
| author_facet | Diego Nieves Avendano Nathan Vandermoortele Colin Soete Pieter Moens Agusmian Partogi Ompusunggu Dirk Deschrijver Sofie Van Hoecke |
| author_sort | Diego Nieves Avendano |
| collection | DOAJ |
| description | Remaining useful life is of great value in the industry and is a key component of Prognostics and Health Management (PHM) in the context of the Predictive Maintenance (PdM) strategy. Accurate estimation of the remaining useful life (RUL) is helpful for optimizing maintenance schedules, obtaining insights into the component degradation, and avoiding unexpected breakdowns. This paper presents a methodology for creating health index models with monotonicity in a semi-supervised approach. The health indexes are then used for enhancing remaining useful life estimation models. The methodology is evaluated on two bearing datasets. Results demonstrate the advantage of using the monotonic health index for obtaining insights into the bearing degradation and for remaining useful life estimation. |
| first_indexed | 2024-03-09T21:05:07Z |
| format | Article |
| id | doaj.art-5a60c56eeeb0482685d6dd76d1ee4a20 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:05:07Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5a60c56eeeb0482685d6dd76d1ee4a202023-11-23T22:01:58ZengMDPI AGSensors1424-82202022-02-01224159010.3390/s22041590A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life EstimationDiego Nieves Avendano0Nathan Vandermoortele1Colin Soete2Pieter Moens3Agusmian Partogi Ompusunggu4Dirk Deschrijver5Sofie Van Hoecke6IDLab, Ghent University—IMEC, 9052 Ghent, BelgiumIDLab, Ghent University—IMEC, 9052 Ghent, BelgiumIDLab, Ghent University—IMEC, 9052 Ghent, BelgiumIDLab, Ghent University—IMEC, 9052 Ghent, BelgiumFlanders Make—Corelab Decision S, 3001 Leuven, BelgiumIDLab, Ghent University—IMEC, 9052 Ghent, BelgiumIDLab, Ghent University—IMEC, 9052 Ghent, BelgiumRemaining useful life is of great value in the industry and is a key component of Prognostics and Health Management (PHM) in the context of the Predictive Maintenance (PdM) strategy. Accurate estimation of the remaining useful life (RUL) is helpful for optimizing maintenance schedules, obtaining insights into the component degradation, and avoiding unexpected breakdowns. This paper presents a methodology for creating health index models with monotonicity in a semi-supervised approach. The health indexes are then used for enhancing remaining useful life estimation models. The methodology is evaluated on two bearing datasets. Results demonstrate the advantage of using the monotonic health index for obtaining insights into the bearing degradation and for remaining useful life estimation.https://www.mdpi.com/1424-8220/22/4/1590predictive maintenancehealth indexremaining useful life estimationbearing degradationapplied machine learning |
| spellingShingle | Diego Nieves Avendano Nathan Vandermoortele Colin Soete Pieter Moens Agusmian Partogi Ompusunggu Dirk Deschrijver Sofie Van Hoecke A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation Sensors predictive maintenance health index remaining useful life estimation bearing degradation applied machine learning |
| title | A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation |
| title_full | A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation |
| title_fullStr | A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation |
| title_full_unstemmed | A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation |
| title_short | A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation |
| title_sort | semi supervised approach with monotonic constraints for improved remaining useful life estimation |
| topic | predictive maintenance health index remaining useful life estimation bearing degradation applied machine learning |
| url | https://www.mdpi.com/1424-8220/22/4/1590 |
| work_keys_str_mv | AT diegonievesavendano asemisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT nathanvandermoortele asemisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT colinsoete asemisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT pietermoens asemisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT agusmianpartogiompusunggu asemisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT dirkdeschrijver asemisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT sofievanhoecke asemisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT diegonievesavendano semisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT nathanvandermoortele semisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT colinsoete semisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT pietermoens semisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT agusmianpartogiompusunggu semisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT dirkdeschrijver semisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation AT sofievanhoecke semisupervisedapproachwithmonotonicconstraintsforimprovedremainingusefullifeestimation |