Abstract
The energy system is in a transformation for a sustainable society. The overall targets are to meet climate goals and to reach energy independence. Wind turbines provide a main solution converting renewable energy resources into electricity with a resulting enormous global growth. A challenge is however to reduce operation and maintenance costs for wind generation to ensure good investments. Asset management (AM) aims to handle assets in an optimal way in order to fulfil an organization’s goal whilst considering risk. This chapter proposes a novel method for AM and preventive maintenance using condition monitoring. The suggested model is an autoencoder-based anomaly detection method for tracking the condition of wind turbines. First, the technique uses supervisory control and data acquisition (SCADA) signals as its data input. The method then analyses the discrepancies between the acquired data from the SCADA system and the estimated values by the autoencoder models. The distribution of the output error is then calculated using the Kernel Density Estimation. Finally, a novel dynamic thresholding approach is employed to effectively extract anomalies in the data in the data. The results show that the approach can identify significant irregularities before a breakdown happens. Additionally, it confirms that the method may notify operators of prospective changes in wind turbines even in the absence of alarm recordings.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Global Energy Review: Assessing the effects of economic recoveries on global energy demand and CO2 emissions in 2021, available: https://www.iea.org/ (2021)
GWEC: GLOBAL WIND REPORT 2021, available: https://gwec.net/
Renström, N., Bangalore, P., Highcock, E.: System-wide anomaly detection in wind turbines using deep autoencoders. Renew. Energy. 157, 647–659 (2020)
Tjernberg, L.B.: Infrastructure Asset Management with Power System Applications. CRC Press Taylor & Francis (2018)
Cui, Y., Bangalore, P., Tjernberg, L.Bertling: An Anomaly Detection Approach Using Wavelet Transform and Artificial Neural Networks for Condition Monitoring of Wind Turbines’ Gearboxes. In: 2018 Power Systems Computation Conference (PSCC), pp. 1–7 (2018). https://doi.org/10.23919/PSCC.2018.8442916
Wang, L., Zhang, Z., Long, H., Xu, J., Liu, R.: Wind turbine gearbox failure identification with deep neural networks. IEEE Trans. Industr. Inform. 13(3), 1360–1368 (2017). https://doi.org/10.1109/TII.2016.2607179
Bangalore, P., Tjernberg, L.B.: An artificial neural network approach for early fault detection of gearbox bearings. IEEE Transactions on Smart Grid. 6(2), 980–987 (2015). https://doi.org/10.1109/TSG.2014.2386305
Huang, Q., Cui, Y., Tjernberg, L.B., Bangalore, P.: Wind Turbine Health Assessment Framework Based on Power Analysis Using Machine Learning Method. In: 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe), pp. 1–5 (2019). https://doi.org/10.1109/ISGTEurope.2019.8905495
Cui, Y., Bangalore, P., Tjernberg, L.B.: An Anomaly Detection Approach Based on Machine Learning and SCADA Data for Condition Monitoring of Wind Turbines. In: 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), pp. 1–6 (2018). https://doi.org/10.1109/PMAPS.2018.8440525
Cui, Y., Bangalore, P., Tjernberg, L.B.: A fault detection framework using recurrent neural networks for condition monitoring of wind turbines. Wind Energy. 24(11), 1249–1262 (2021). https://doi.org/10.1002/we.2628
Lal Senanayaka, J.S., Van Khang, H., Robbersmyr, K.G.: Autoencoders and Recurrent Neural Networks Based Algorithm for Prognosis of Bearing Life. In: 2018 21st International Conference on Electrical Machines and Systems (ICEMS), pp. 537–542 (2018). https://doi.org/10.23919/ICEMS.2018.8549006
Sun, Z., Sun, H.: Stacked denoising autoencoder with density-grid based clustering method for detecting outlier of wind turbine components. IEEE Access. 7, 13078–13091 (2019). https://doi.org/10.1109/ACCESS.2019.2893206
Wu, X., Jiang, G., Wang, X., Xie, P., Li, X.: A multi-level-Denoising autoencoder approach for wind turbine fault detection. IEEE Access. 7, 59376–59387 (2019). https://doi.org/10.1109/ACCESS.2019.2914731
Urrea Cabus, J.E., Cui, Y., Tjernberg, L.B.: An Anomaly Detection Approach Based on Autoencoders for Condition Monitoring of Wind Turbines. In: 2022 17th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), pp. 1–6 (2022). https://doi.org/10.1109/PMAPS53380.2022.9810575
Li, T. et al.: A Stacked Predictor and Dynamic Thresholding Algorithm for Anomaly Detection in Spacecraft. In: MILCOM 2019–2019 IEEE Military Communications Conference (MILCOM), pp. 165–170 (2019). https://doi.org/10.1109/MILCOM47813.2019.9021055
Li, T. et al.: Anomaly Scoring for Prediction-Based Anomaly Detection in Time Series. In: 2020 IEEE Aerospace Conference, pp. 1–7 (2020). https://doi.org/10.1109/AERO47225.2020.9172442
Hundman, K., et al.: Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD’18), pp. 387–395. Association for Computing Machinery, New York (2018). https://doi.org/10.1145/3219819.3219845
Yıldırım, S.: DBSCAN Clustering—Explained, available: https://towardsdatascience.com/dbscan-clustering-explained-97556a2ad556; https://en.wikipedia.org/wiki/Power_transform
Sakurada, M., Yairi, T.: Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction. In: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis (MLSDA’14), pp. 4–11. Association for Computing Machinery, New York (2014). https://doi.org/10.1145/2689746.2689747
Wang, Y., Yao, H., Zhao, S.: Auto-encoder based dimensionality reduction. Neurocomputing. 184, 232–242 (2016). https://doi.org/10.1016/j.neucom.2015.08.104
Nguyen, H.D., Tran, K.P., Thomassey, S., Hamad, M.: Forecasting and anomaly detection approaches using LSTM and LSTM autoencoder techniques with the applications in supply chain management. Int. J. Inf. Manag. 57, 102282 (2021). https://doi.org/10.1016/j.ijinfomgt.2020.102282
Autoencoder. https://en.wikipedia.org/wiki/Autoencoder (Visited 2022-06-30)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Cui, Y., Urrea Cabus, J.E., Tjernberg, L.B. (2023). A Fault Detection Approach Based on Autoencoders for Condition Monitoring of Wind Turbines. In: Wang, K.T., Tietjen, J.S. (eds) Women in Renewable Energy. Women in Engineering and Science. Springer, Cham. https://doi.org/10.1007/978-3-031-28543-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-28543-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28542-4
Online ISBN: 978-3-031-28543-1
eBook Packages: EnergyEnergy (R0)