Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-28223| Publication type: | Conference paper |
| Type of review: | Peer review (publication) |
| Title: | Physics-informed machine learning for predictive maintenance : applied use-cases |
| Authors: | Goren Huber, Lilach Palmé, Thomas Arias Chao, Manuel |
| et. al: | No |
| DOI: | 10.1109/SDS57534.2023.00016 10.21256/zhaw-28223 |
| Proceedings: | 2023 10th IEEE Swiss Conference on Data Science (SDS) |
| Page(s): | 66 |
| Pages to: | 72 |
| Conference details: | 10th IEEE Swiss Conference on Data Science (SDS), Zurich, Switzerland, 22-23 June 2023 |
| Issue Date: | Jun-2023 |
| Publisher / Ed. Institution: | IEEE |
| ISBN: | 979-8-3503-3875-1 |
| Language: | English |
| Subjects: | Predictive maintenance; Deep learning; Physics-informed machine learning; Artificial intelligence; Solar power plant; Gas turbine; Aircraft engine; Fault detection; Fault diagnostics; Remaining useful life |
| Subject (DDC): | 006: Special computer methods 620: Engineering |
| Abstract: | The combination of physics and engineering information with data-driven methods like machine learning (ML) and deep learning is gaining attention in various research fields. One of the promising practical applications of such hybrid methods is for supporting maintenance decision making in the form of condition-based and predictive maintenance. In this paper we focus on the potential of physics-informed data augmentation for ML algorithms. We demonstrate possible implementations of the concept using three use cases, differing in their technical systems, their algorithms and their tasks ranging from anomaly detection, through fault diagnostics up to prognostics of the remaining useful life. We elaborate on the benefits and prerequisites of each technique and provide guidelines for future practical implementations in other systems. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/28223 |
| Fulltext version: | Accepted version |
| License (according to publishing contract): | Licence according to publishing contract |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Data Analysis and Process Design (IDP) |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2023_GorenHuber-etal_PIML-for-predictive-maintenance-usecases_SDS2023.pdf | Accepted Version | 1.11 MB | Adobe PDF |  View/Open |
Show full item record
Goren Huber, L., Palmé, T., & Arias Chao, M. (2023). Physics-informed machine learning for predictive maintenance : applied use-cases [Conference paper]. 2023 10th IEEE Swiss Conference on Data Science (SDS), 66–72. https://doi.org/10.1109/SDS57534.2023.00016
Goren Huber, L., Palmé, T. and Arias Chao, M. (2023) ‘Physics-informed machine learning for predictive maintenance : applied use-cases’, in 2023 10th IEEE Swiss Conference on Data Science (SDS). IEEE, pp. 66–72. Available at: https://doi.org/10.1109/SDS57534.2023.00016.
L. Goren Huber, T. Palmé, and M. Arias Chao, “Physics-informed machine learning for predictive maintenance : applied use-cases,” in 2023 10th IEEE Swiss Conference on Data Science (SDS), Jun. 2023, pp. 66–72. doi: 10.1109/SDS57534.2023.00016.
GOREN HUBER, Lilach, Thomas PALMÉ und Manuel ARIAS CHAO, 2023. Physics-informed machine learning for predictive maintenance : applied use-cases. In: 2023 10th IEEE Swiss Conference on Data Science (SDS). Conference paper. IEEE. Juni 2023. S. 66–72. ISBN 979-8-3503-3875-1
Goren Huber, Lilach, Thomas Palmé, and Manuel Arias Chao. 2023. “Physics-Informed Machine Learning for Predictive Maintenance : Applied Use-Cases.” Conference paper. In 2023 10th IEEE Swiss Conference on Data Science (SDS), 66–72. IEEE. https://doi.org/10.1109/SDS57534.2023.00016.
Goren Huber, Lilach, et al. “Physics-Informed Machine Learning for Predictive Maintenance : Applied Use-Cases.” 2023 10th IEEE Swiss Conference on Data Science (SDS), IEEE, 2023, pp. 66–72, https://doi.org/10.1109/SDS57534.2023.00016.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.