IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v15y2022i2p558-d723940.html
   My bibliography  Save this article

Using Transfer Learning to Build Physics-Informed Machine Learning Models for Improved Wind Farm Monitoring

Author

Listed:
  • Laura Schröder

    (DTU Wind Energy, Technical University of Denmark, 4000 Roskilde, Denmark)

  • Nikolay Krasimirov Dimitrov

    (DTU Wind Energy, Technical University of Denmark, 4000 Roskilde, Denmark)

  • David Robert Verelst

    (DTU Wind Energy, Technical University of Denmark, 4000 Roskilde, Denmark)

  • John Aasted Sørensen

    (DTU Engineering Technology, Technical University of Denmark, 2750 Ballerup, Denmark)

Abstract

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.

Suggested Citation

  • Laura Schröder & Nikolay Krasimirov Dimitrov & David Robert Verelst & John Aasted Sørensen, 2022. "Using Transfer Learning to Build Physics-Informed Machine Learning Models for Improved Wind Farm Monitoring," Energies, MDPI, vol. 15(2), pages 1-21, January.
    • Handle: RePEc:gam:jeners:v:15:y:2022:i:2:p:558-:d:723940
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/15/2/558/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/15/2/558/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Stetco, Adrian & Dinmohammadi, Fateme & Zhao, Xingyu & Robu, Valentin & Flynn, David & Barnes, Mike & Keane, John & Nenadic, Goran, 2019. "Machine learning methods for wind turbine condition monitoring: A review," Renewable Energy, Elsevier, vol. 133(C), pages 620-635.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Reddy, Sohail R., 2021. "A machine learning approach for modeling irregular regions with multiple owners in wind farm layout design," Energy, Elsevier, vol. 220(C).
    2. Camila Correa-Jullian & Sergio Cofre-Martel & Gabriel San Martin & Enrique Lopez Droguett & Gustavo de Novaes Pires Leite & Alexandre Costa, 2022. "Exploring Quantum Machine Learning and Feature Reduction Techniques for Wind Turbine Pitch Fault Detection," Energies, MDPI, vol. 15(8), pages 1-29, April.
    3. Ahmed Al-Ajmi & Yingzhao Wang & Siniša Djurović, 2021. "Wind Turbine Generator Controller Signals Supervised Machine Learning for Shaft Misalignment Fault Detection: A Doubly Fed Induction Generator Practical Case Study," Energies, MDPI, vol. 14(6), pages 1-15, March.
    4. Wang, Anqi & Pei, Yan & Qian, Zheng & Zareipour, Hamidreza & Jing, Bo & An, Jiayi, 2022. "A two-stage anomaly decomposition scheme based on multi-variable correlation extraction for wind turbine fault detection and identification," Applied Energy, Elsevier, vol. 321(C).
    5. Chen, Wanqiu & Qiu, Yingning & Feng, Yanhui & Li, Ye & Kusiak, Andrew, 2021. "Diagnosis of wind turbine faults with transfer learning algorithms," Renewable Energy, Elsevier, vol. 163(C), pages 2053-2067.
    6. Zhu, Yongchao & Zhu, Caichao & Tan, Jianjun & Tan, Yong & Rao, Lei, 2022. "Anomaly detection and condition monitoring of wind turbine gearbox based on LSTM-FS and transfer learning," Renewable Energy, Elsevier, vol. 189(C), pages 90-103.
    7. Meng, Debiao & Yang, Shiyuan & Jesus, Abílio M.P. de & Zhu, Shun-Peng, 2023. "A novel Kriging-model-assisted reliability-based multidisciplinary design optimization strategy and its application in the offshore wind turbine tower," Renewable Energy, Elsevier, vol. 203(C), pages 407-420.
    8. Lorin Jenkel & Stefan Jonas & Angela Meyer, 2023. "Privacy-Preserving Fleet-Wide Learning of Wind Turbine Conditions with Federated Learning," Energies, MDPI, vol. 16(17), pages 1-29, September.
    9. Zhu, Yongchao & Zhu, Caichao & Tan, Jianjun & Wang, Yili & Tao, Jianquan, 2022. "Operational state assessment of wind turbine gearbox based on long short-term memory networks and fuzzy synthesis," Renewable Energy, Elsevier, vol. 181(C), pages 1167-1176.
    10. Lei Fu & Tiantian Zhu & Kai Zhu & Yiling Yang, 2019. "Condition Monitoring for the Roller Bearings of Wind Turbines under Variable Working Conditions Based on the Fisher Score and Permutation Entropy," Energies, MDPI, vol. 12(16), pages 1-20, August.
    11. Kisvari, Adam & Lin, Zi & Liu, Xiaolei, 2021. "Wind power forecasting – A data-driven method along with gated recurrent neural network," Renewable Energy, Elsevier, vol. 163(C), pages 1895-1909.
    12. Phong B. Dao, 2023. "On Cointegration Analysis for Condition Monitoring and Fault Detection of Wind Turbines Using SCADA Data," Energies, MDPI, vol. 16(5), pages 1-17, March.
    13. Adaiton Oliveira-Filho & Ryad Zemouri & Philippe Cambron & Antoine Tahan, 2023. "Early Detection and Diagnosis of Wind Turbine Abnormal Conditions Using an Interpretable Supervised Variational Autoencoder Model," Energies, MDPI, vol. 16(12), pages 1-21, June.
    14. Ti, Zilong & Deng, Xiao Wei & Zhang, Mingming, 2021. "Artificial Neural Networks based wake model for power prediction of wind farm," Renewable Energy, Elsevier, vol. 172(C), pages 618-631.
    15. Wang, Zhenya & Yao, Ligang & Cai, Yongwu & Zhang, Jun, 2020. "Mahalanobis semi-supervised mapping and beetle antennae search based support vector machine for wind turbine rolling bearings fault diagnosis," Renewable Energy, Elsevier, vol. 155(C), pages 1312-1327.
    16. Alan Turnbull & Conor McKinnon & James Carrol & Alasdair McDonald, 2022. "On the Development of Offshore Wind Turbine Technology: An Assessment of Reliability Rates and Fault Detection Methods in a Changing Market," Energies, MDPI, vol. 15(9), pages 1-20, April.
    17. Purohit, Shantanu & Ng, E.Y.K. & Syed Ahmed Kabir, Ijaz Fazil, 2022. "Evaluation of three potential machine learning algorithms for predicting the velocity and turbulence intensity of a wind turbine wake," Renewable Energy, Elsevier, vol. 184(C), pages 405-420.
    18. Lu, Xuefei & Baraldi, Piero & Zio, Enrico, 2020. "A data-driven framework for identifying important components in complex systems," Reliability Engineering and System Safety, Elsevier, vol. 204(C).
    19. Phong B. Dao, 2021. "A CUSUM-Based Approach for Condition Monitoring and Fault Diagnosis of Wind Turbines," Energies, MDPI, vol. 14(11), pages 1-19, June.
    20. Dao, Phong B., 2022. "On Wilcoxon rank sum test for condition monitoring and fault detection of wind turbines," Applied Energy, Elsevier, vol. 318(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:15:y:2022:i:2:p:558-:d:723940. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.