Increasing transparency and robustness of machine learning methods for SCADA based condition monitoring in wind turbines
| Main Author: | Letzgus, Simon |
|---|---|
| Format: | info Proceeding |
| Bahasa: | eng |
| Terbitan: |
, 2019
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/3443752 |
Daftar Isi:
- SCADA data analytics has attracted considerable research interest for monitoring wind turbine condition without additional equipment. Above all, normal behaviour models using artificial neural networks (ANNs) have shown promising results. However, their robustness and transparency can be challenged by changepoints in training data and ambient conditions the models were not trained for. The presentation introduces methods to tackle these key issues.