Labelling Drifts in a Fault Detection System for Wind Turbine Maintenance
A failure detection system is the first step towards predictive maintenance strategies. A popular data-driven method to detect incipient failures and anomalies is the training of normal behaviour models by applying a machine learning technique like feed-forward neural networks (FFNN) or extreme learning machines (ELM). However, the performance of any of these modelling techniques can be deteriorated by the unexpected rise of non-stationarities in the dynamic environment in which industrial assets operate. This unpredictable statistical change in the measured variable is known as concept drift. In this article a wind turbine maintenance case is presented, where non-stationarities of various kinds can happen unexpectedly. Such concept drift events are desired to be detected by means of statistical detectors and window-based approaches. However, in real complex systems, concept drifts are not as clear and evident as in artificially generated datasets. In order to evaluate the effectiveness of current drift detectors and also to design an appropriate novel technique for this specific industrial application, it is essential to dispose beforehand of a characterization of the existent drifts. Under the lack of information in this regard, a methodology for labelling concept drift events in the lifetime of wind turbines is proposed. This methodology will facilitate the creation of a drift database that will serve both as a training ground for concept drift detectors and as a valuable information to enhance the knowledge about maintenance of complex systems.
KeywordsFailure detection Predictive maintenance Concept drift Supervised learning Neural networks Extreme learning machine Wind turbine Expert labelling
This research has been supported by NEM Solutions, a technology-based company focused that provides intelligent maintenance of complex systems to O&M businesses.
- 3.Zio, E., Kadry, S.: Diagnostics and prognostics of engineering systems: methods and techniques, pp. 333–356 (2012). https://doi.org/10.4018/978-1-4666-2095-7.ch017>
- 8.Sheng, S., Veers, P.: Machinery Failure Prevention Technology (MFPT): The Applied Systems Health Management Conference 2011, vol. 2, p. 5, October 2011Google Scholar
- 11.Liu, Z., Gao, W., Wan, Y.H., Muljadi, E.: IEEE Energy Conversion Congress and Exposition (ECCE) (August), 3154 (2012). https://doi.org/10.1109/ECCE.2012.6342351
- 13.Qian, P., Ma, X., Wang, Y.: Autom. Comput. (ICAC) 11 (2015). https://doi.org/10.1109/IConAC.2015.7313974
- 19.Žliobaite, I.: International Conference on Machine Learning, pp. 1009–1017 (2010). https://doi.org/10.1002/sam
- 21.Tsymbal, A.: Computer Science Department, Trinity College Dublin 4(C), 2004 (2004). http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.9085
- 28.Sebastião, R., Gama, J.: 14th Portuguese Conference on Artificial Intelligence, pp. 353–364 (2009). http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.233.1180
- 29.Santos, S., Barros, R., Gonçalves, P.: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, vol. 2016, pp. 1077–1084, January 2016. https://doi.org/10.1109/ICTAI.2015.153
- 35.Bifet, A., Holmes, G., Kirkby, R., Pfahringer, B.: J. Mach. Learn. Res. 11, 1601 (2010). http://portal.acm.org/citation.cfm?id=1859903
- 36.Maciel, B.I.F., Santos, S.G.T.C., Barros, R.S.M.: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, vol. 2016, pp. 1061–1068, January 2016. https://doi.org/10.1109/ICTAI.2015.151
- 37.Sobolewski, P., Woźniak, M.: J. Univ. Comput. Sci. 19(4), 462 (2013)Google Scholar