Diagnosing and PredictingWind Turbine Faults from SCADA Data Using Support Vector Machines



Published Nov 19, 2020
Kevin Leahy R. Lily Hu Ioannis C. Konstantakopoulos Costas J. Spanos Alice M. Agogino Dominic T. J. O’Sullivan


Unscheduled or reactive maintenance on wind turbines due to component failure incurs significant downtime and, in turn, loss of revenue. To this end, it is important to be able to perform
maintenance before it’s needed. To date, a strong effort has been applied to developing Condition Monitoring Systems (CMSs) which rely on retrofitting expensive vibration or oil analysis sensors to the turbine. Instead, by performing complex analysis of existing data from the turbine’s Supervisory Control and Data Acquisition (SCADA) system, valuable insights into turbine performance can be obtained at a much lower cost.
In this paper, fault and alarm data from a turbine on the Southern coast of Ireland is analysed to identify periods of nominal and faulty operation. Classification techniques are then applied to detect and diagnose faults by taking into account other SCADA data such as temperature, pitch and rotor data. This is then extended to allow prediction and diagnosis in advance of specific faults. Results are provided which show recall scores generally above 80% for fault detection and diagnosis, and prediction up to 24 hours in advance of specific faults, representing significant improvement over previous techniques.

Abstract 533 | PDF Downloads 384



fault diagnosis, support vector machines, Wind Turbines, fault prediction

Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A Training Algorithm for Optimal Margin Classifiers. Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, 144–152. doi:
Breiman, L. (1996). Bagging Predictors. Machine Learning, 24(421), 123–140. doi: 10.1007/BF00058655
Chang, C.-c., & Lin, C.-j. (2011). LIBSVM : A Library for Support Vector Machines. ACM Transactions on Intelligent Systems and Technology (TIST), 2, 1–39. doi: 10.1145/1961189.1961199
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority oversampling technique. Journal of Artificial Intelligence Research, 16, 321–357. doi: 10.1613/jair.953
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. doi: 10.1007/BF00994018
Du, M., Tjernberg, L. B., Ma, S., He, Q., Cheng, L., & Guo, J. (2016). A SOM based Anomaly Detection Method for Wind Turbines Health Management through SCADA Data. International Journal of Prognostics and Health Management, 7, 1–13.
European Wind Energy Association (EWEA). (2009). The Economics of Wind Energy (Tech. Rep.).
Freund, Y., & Schapire, R. (1995). A desicion-theoretic generalization of on-line learning and an application to boosting. Computational learning theory, 55(1), 119– 139. doi: 10.1006/jcss.1997.1504
Gayo, J. B. (2011). ReliaWind Project final report (Tech. Rep.).
Gill, S., Stephen, B., & Galloway, S. (2012). Wind turbine condition assessment through power curve copula modeling. IEEE Transactions on Sustainable Energy, 3(1), 94–101. doi: 10.1109/TSTE.2011.2167164
Godwin, J. L., & Matthews, P. (2013). Classification and Detection of Wind Turbine Pitch Faults Through SCADA Data Analysis. International Journal of Prognostics and Health Management, 4, 11.
Hu, R. L., Leahy, K., Konstantakopoulos, I. C., Auslander, D. M., Spanos, C. J., & Agogino, A. M. (2016). Using Domain Knowledge Features for Wind Turbine Diagnostics. In Icmla.
Knerr, S., Personnaz, L., & Dreyfus, G. (1990). Single-layer learning revisited: a stepwise procedure for building and training a neural network. Neurocomputing(68), 41–50.
Kusiak, A., & Li,W. (2011). The prediction and diagnosis of wind turbine faults. Renewable Energy, 36(1), 16–23. doi: 10.1016/j.renene.2010.05.014
Kusiak, A., & Verma, A. (2011). A data-driven approach for monitoring blade pitch faults in wind turbines. IEEE Transactions on Sustainable Energy, 2(1), 87–96. doi: 10.1109/TSTE.2010.2066585
Laouti, N., Sheibat-othman, N., & Othman, S. (2011). Support Vector Machines for Fault Detection in Wind Turbines. 18th IFAC World Congress, 7067–7072.
Lapira, E., Brisset, D., Davari Ardakani, H., Siegel, D., & Lee, J. (2012). Wind turbine performance assessment using multi-regime modeling approach. Renewable Energy, 45, 86–95. doi: 10.1016/j.renene.2012.02.018
Leahy, K., Hu, R. L., Konstantakopoulos, I. C., Spanos, C. J., & Agogino, A. M. (2016). Diagnosing Wind Turbine Faults Using Machine Learning Techniques Applied to Operational Data. In Ieee international conference on prognostics and health management.
Liu, X. Y., Wu, J., & Zhou, Z. H. (2006). Exploratory under-sampling for class-imbalance learning. Proceedings - IEEE International Conference on Data Mining, ICDM, 39(2), 965–969. doi: 10.1109/ICDM.2006.68
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., . . . Duchesnay, ´ E. (2012, jan). Scikit-learn: Machine Learning in Python. The Journal of Machine Learning Research, 12, 2825–2830. doi: 10.1007/s13398-014-0173-7.2
Saxena, A., Celaya, J., Balaban, E., Goebel, K., Saha, B., Saha, S., & Schwabacher, M. (2008). Metrics for evaluating performance of prognostic techniques. 2008 International Conference on Prognostics and Health Management, PHM 2008. doi: 10.1109/PHM.2008.4711436
Skrimpas, G. A., Sweeney, C. W., Marhadi, K. S., Jensen, B. B., Mijatovic, N., & Holboll, J. (2015). Employment of Kernel Methods on Wind Turbine Power Performance Assessment. IEEE Transactions on Sustainable Energy, 6(3), 698–706. doi: 10.1109/TSTE.2015.2405971
Tamilselvan, P., Wang, P., Sheng, S., & Twomey, J. M. (2013). A Two-Stage Diagnosis Framework for Wind Turbine Gearbox Condition Monitoring. International Journal of Prognostics and Health Management( Special Issue on Wind Turbines PHM).
Tomek, I. (1976). Two Modifications of CNN. IEEE Transactions on Systems, Man and Cybernetics 6, 769–772. doi: 10.1109/TSMC.1976.4309452
Uluyol, O., Parthasarathy, G., Foslien,W., & Kim, K. (2011). Power Curve Analytic for Wind Turbine Performance Monitoring and Prognostics. Annual Conference of the Prognostics and Health Management Society, 1–8.
Widodo, A.,&Yang, B.-S. (2007). Support vector machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing, 21(6), 2560– 2574. doi: 10.1016/j.ymssp.2006.12.007
Wilson, D. L. (1972). Asymptotic Properties of Nearest Neighbor Rules Using Edited Data. IEEE Transactions on Systems, Man and Cybernetics, 2(3), 408–421. doi: 10.1109/TSMC.1972.4309137
Yang, W., Tavner, P. J., Crabtree, C. J., Feng, Y., & Qiu, Y. (2014). Wind turbine condition monitoring: Technical and commercial challenges. Wind Energy, 17(5), 673–693. doi: 10.1002/we.1508
Zaher, A., McArthur, S., Infield, D., & Patel, Y. (2009, sep). Online wind turbine fault detection through automated SCADA data analysis. Wind Energy, 12(6), 574–593. doi: 10.1002/we.31911
Technical Papers