Generalizable Temperature Nowcasting with Physics-Constrained RNNs for Predictive Maintenance of Wind Turbine Components
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911828589674496 |
|---|---|
| author | Exenberger, Johannes Di Salvo, Matteo Hirsch, Thomas Wotawa, Franz Schweiger, Gerald |
| author_facet | Exenberger, Johannes Di Salvo, Matteo Hirsch, Thomas Wotawa, Franz Schweiger, Gerald |
| contents | Machine learning plays an important role in the operation of current wind energy production systems. One central application is predictive maintenance to increase efficiency and lower electricity costs by reducing downtimes. Integrating physics-based knowledge in neural networks to enforce their physical plausibilty is a promising method to improve current approaches, but incomplete system information often impedes their application in real world scenarios. We describe a simple and efficient way for physics-constrained deep learning-based predictive maintenance for wind turbine gearbox bearings with partial system knowledge. The approach is based on temperature nowcasting constrained by physics, where unknown system coefficients are treated as learnable neural network parameters. Results show improved generalization performance to unseen environments compared to a baseline neural network, which is especially important in low data scenarios often encountered in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_04126 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generalizable Temperature Nowcasting with Physics-Constrained RNNs for Predictive Maintenance of Wind Turbine Components Exenberger, Johannes Di Salvo, Matteo Hirsch, Thomas Wotawa, Franz Schweiger, Gerald Machine Learning Systems and Control Machine learning plays an important role in the operation of current wind energy production systems. One central application is predictive maintenance to increase efficiency and lower electricity costs by reducing downtimes. Integrating physics-based knowledge in neural networks to enforce their physical plausibilty is a promising method to improve current approaches, but incomplete system information often impedes their application in real world scenarios. We describe a simple and efficient way for physics-constrained deep learning-based predictive maintenance for wind turbine gearbox bearings with partial system knowledge. The approach is based on temperature nowcasting constrained by physics, where unknown system coefficients are treated as learnable neural network parameters. Results show improved generalization performance to unseen environments compared to a baseline neural network, which is especially important in low data scenarios often encountered in real-world applications. |
| title | Generalizable Temperature Nowcasting with Physics-Constrained RNNs for Predictive Maintenance of Wind Turbine Components |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2404.04126 |