Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of the international conference on Systems Science and Engineering, Human-Machine Systems, and Cybernetics (IEEE SMC) |
| Untertitel | Improving the Quality of Life, SMC 2023 - Proceedings |
| Seiten | 2907-2912 |
| Seitenumfang | 6 |
| ISBN (elektronisch) | 979-8-3503-3702-0 |
| Publikationsstatus | Veröffentlicht - 1 Okt. 2023 |
Publikationsreihe
| Name | IEEE International Conference on Systems, Man, and Cybernetics |
|---|---|
| ISSN (Print) | 1062-922X |
| ISSN (elektronisch) | 2577-1655 |
Abstract
Being able to predict the remaining useful life (RUL) of an engineering system is an important task in prognostics and health management. Recently, data-driven approaches to RUL predictions are becoming prevalent over model-based approaches since no underlying physical knowledge of the engineering system is required. Yet, this just replaces required expertise of the underlying physics with machine learning (ML) expertise, which is often also not available. Automated machine learning (AutoML) promises to build end-to-end ML pipelines automatically enabling domain experts without ML expertise to create their own models. This paper introduces AutoRUL, an AutoML-driven end-to-end approach for automatic RUL predictions. AutoRUL combines fine-tuned standard regression methods to an ensemble with high predictive power. By evaluating the proposed method on eight real-world and synthetic datasets against state-of-the-art hand-crafted models, we show that AutoML provides a viable alternative to hand-crafted data-driven RUL predictions. Consequently, creating RUL predictions can be made more accessible for domain experts using AutoML by eliminating ML expertise from data-driven model construction.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
- Ingenieurwesen (insg.)
- Steuerungs- und Systemtechnik
- Informatik (insg.)
- Mensch-Maschine-Interaktion
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the international conference on Systems Science and Engineering, Human-Machine Systems, and Cybernetics (IEEE SMC): Improving the Quality of Life, SMC 2023 - Proceedings. 2023. S. 2907-2912 (IEEE International Conference on Systems, Man, and Cybernetics).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Automated Machine Learning for Remaining Useful Life Predictions
AU - Zoeller, Marc
AU - Mauthe, Fabian
AU - Zeiler, Peter
AU - Lindauer, Marius
AU - Huber, Marco
N1 - Publisher Copyright: © 2023 IEEE.
PY - 2023/10/1
Y1 - 2023/10/1
N2 - Being able to predict the remaining useful life (RUL) of an engineering system is an important task in prognostics and health management. Recently, data-driven approaches to RUL predictions are becoming prevalent over model-based approaches since no underlying physical knowledge of the engineering system is required. Yet, this just replaces required expertise of the underlying physics with machine learning (ML) expertise, which is often also not available. Automated machine learning (AutoML) promises to build end-to-end ML pipelines automatically enabling domain experts without ML expertise to create their own models. This paper introduces AutoRUL, an AutoML-driven end-to-end approach for automatic RUL predictions. AutoRUL combines fine-tuned standard regression methods to an ensemble with high predictive power. By evaluating the proposed method on eight real-world and synthetic datasets against state-of-the-art hand-crafted models, we show that AutoML provides a viable alternative to hand-crafted data-driven RUL predictions. Consequently, creating RUL predictions can be made more accessible for domain experts using AutoML by eliminating ML expertise from data-driven model construction.
AB - Being able to predict the remaining useful life (RUL) of an engineering system is an important task in prognostics and health management. Recently, data-driven approaches to RUL predictions are becoming prevalent over model-based approaches since no underlying physical knowledge of the engineering system is required. Yet, this just replaces required expertise of the underlying physics with machine learning (ML) expertise, which is often also not available. Automated machine learning (AutoML) promises to build end-to-end ML pipelines automatically enabling domain experts without ML expertise to create their own models. This paper introduces AutoRUL, an AutoML-driven end-to-end approach for automatic RUL predictions. AutoRUL combines fine-tuned standard regression methods to an ensemble with high predictive power. By evaluating the proposed method on eight real-world and synthetic datasets against state-of-the-art hand-crafted models, we show that AutoML provides a viable alternative to hand-crafted data-driven RUL predictions. Consequently, creating RUL predictions can be made more accessible for domain experts using AutoML by eliminating ML expertise from data-driven model construction.
KW - Automated Machine Learning
KW - AutoML
KW - data-driven
KW - ML
KW - PHM
KW - Remaining Useful Life
KW - RUL
UR - http://www.scopus.com/inward/record.url?scp=85187305689&partnerID=8YFLogxK
U2 - 10.1109/SMC53992.2023.10394031
DO - 10.1109/SMC53992.2023.10394031
M3 - Conference contribution
SN - 979-8-3503-3703-7
T3 - IEEE International Conference on Systems, Man, and Cybernetics
SP - 2907
EP - 2912
BT - Proceedings of the international conference on Systems Science and Engineering, Human-Machine Systems, and Cybernetics (IEEE SMC)
ER -