Journal article
Using Transfer Learning to Build Physics-Informed Machine Learning Models for Improved Wind Farm Monitoring
Department of Wind Energy, Technical University of Denmark1
Structural Integrity and Loads Assessment, Wind Energy Materials and Components Division, Department of Wind Energy, Technical University of Denmark2
Response, Aeroelasticity, Control and Hydrodynamics, Wind Turbine Design Division, Department of Wind Energy, Technical University of Denmark3
Department of Engineering Technology and Didactics, Technical University of Denmark4
AI, Mathematics and Software, Department of Engineering Technology and Didactics, Technical University of Denmark5
This paper introduces a novel, transfer-learning-based approach to include physics into data-driven normal behavior monitoring models which are used for detecting turbine anomalies. For this purpose, a normal behavior model is pretrained on a large simulation database and is recalibrated on the available SCADA data via transfer learning.
For two methods, a feed-forward artificial neural network (ANN) and an autoencoder, it is investigated under which conditions it can be helpful to include simulations into SCADA-based monitoring systems. The results show that when only one month of SCADA data is available, both the prediction accuracy as well as the prediction robustness of an ANN are significantly improved by adding physics constraints from a pretrained model.
As the autoencoder reconstructs the power from itself, it is already able to accurately model the normal behavior power. Therefore, including simulations into the model does not improve its prediction performance and robustness significantly. The validation of the physics-informed ANN on one month of raw SCADA data shows that it is able to successfully detect a recorded blade angle anomaly with an improved precision due to fewer false positives compared to its purely SCADA data-based counterpart.
Language: | English |
---|---|
Publisher: | MDPI AG |
Year: | 2022 |
Pages: | 558 |
ISSN: | 19961073 |
Types: | Journal article |
DOI: | 10.3390/en15020558 |
ORCIDs: | Schröder, Laura , Dimitrov, Nikolay Krasimirov , Verelst, David Robert and Sørensen, John Aasted |