A semi-supervised approach with monotonic constraints for improved remaining useful life estimation
- Author
- Diego Nieves Avendano (UGent) , Nathan Vandemoortele (UGent) , Colin Soete (UGent) , Pieter Moens (UGent) , Agusmian Partogi Ompusunggu, Dirk Deschrijver (UGent) and Sofie Van Hoecke (UGent)
- Organization
- Abstract
- 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.
- Keywords
- ELEMENT BEARING DIAGNOSTICS, PROGNOSTICS, predictive maintenance, health index, remaining useful life estimation, bearing degradation, applied machine learning
Downloads
-
8062.pdf
- full text (Published version)
- |
- open access
- |
- |
- 7.74 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8744638
- MLA
- Nieves Avendano, Diego, et al. “A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation.” SENSORS, vol. 22, no. 4, 2022, doi:10.3390/s22041590.
- APA
- Nieves Avendano, D., Vandemoortele, N., Soete, C., Moens, P., Ompusunggu, A. P., Deschrijver, D., & Van Hoecke, S. (2022). A semi-supervised approach with monotonic constraints for improved remaining useful life estimation. SENSORS, 22(4). https://doi.org/10.3390/s22041590
- Chicago author-date
- Nieves Avendano, Diego, Nathan Vandemoortele, Colin Soete, Pieter Moens, Agusmian Partogi Ompusunggu, Dirk Deschrijver, and Sofie Van Hoecke. 2022. “A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation.” SENSORS 22 (4). https://doi.org/10.3390/s22041590.
- Chicago author-date (all authors)
- Nieves Avendano, Diego, Nathan Vandemoortele, Colin Soete, Pieter Moens, Agusmian Partogi Ompusunggu, Dirk Deschrijver, and Sofie Van Hoecke. 2022. “A Semi-Supervised Approach with Monotonic Constraints for Improved Remaining Useful Life Estimation.” SENSORS 22 (4). doi:10.3390/s22041590.
- Vancouver
- 1.Nieves Avendano D, Vandemoortele N, Soete C, Moens P, Ompusunggu AP, Deschrijver D, et al. A semi-supervised approach with monotonic constraints for improved remaining useful life estimation. SENSORS. 2022;22(4).
- IEEE
- [1]D. Nieves Avendano et al., “A semi-supervised approach with monotonic constraints for improved remaining useful life estimation,” SENSORS, vol. 22, no. 4, 2022.
@article{8744638,
abstract = {{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.}},
articleno = {{1590}},
author = {{Nieves Avendano, Diego and Vandemoortele, Nathan and Soete, Colin and Moens, Pieter and Ompusunggu, Agusmian Partogi and Deschrijver, Dirk and Van Hoecke, Sofie}},
issn = {{1424-8220}},
journal = {{SENSORS}},
keywords = {{ELEMENT BEARING DIAGNOSTICS,PROGNOSTICS,predictive maintenance,health index,remaining useful life estimation,bearing degradation,applied machine learning}},
language = {{eng}},
number = {{4}},
pages = {{22}},
title = {{A semi-supervised approach with monotonic constraints for improved remaining useful life estimation}},
url = {{http://doi.org/10.3390/s22041590}},
volume = {{22}},
year = {{2022}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: