Skip to main content
SpringerLink
Log in

Ensembles Learning Algorithms with K-Fold Cross Validation to Detect False Alarms in Wind Turbines

  • Conference paper
  • First Online:
Proceedings of the Sixteenth International Conference on Management Science and Engineering Management – Volume 1 (ICMSEM 2022)

Part of the book series: Lecture Notes on Data Engineering and Communications Technologies ((LNDECT,volume 144))

Abstract

Wind farms demand a specialized maintenance management. Supervisory control and data acquisition and condition monitoring systems are used to control wind turbines, which generate vast volumes of data. Large amounts of complex data can be efficiently classified using machine learning techniques. Several machine learning algorithms have been applied to fault detection and energy prediction in wind turbines, but the literature is scarce for alarm classification, and almost non-existent for the detection and diagnosis of false alarms. The innovation of this paper is the implementation of ensemble tree algorithms for the prediction and classification of alarms and detection of false alarms. To analyze the methodology, three different ensemble algorithms have been evaluated: Bagging, Boosted and RUSBoost; and different K-fold cross validation has been applied to validate the results and compared with holdout validation. The methodology is evaluated on a real dataset from three wind turbines. The results indicate an accuracy of 99.1%, and the \(F_1\) is 0.995, this demonstrates that the ensemble tree algorithm is a reliable method for the prediction of alarms in wind turbines. Subsequently, the misclassifications produced by the higher accuracy algorithm are studied. The causes of these misclassifications are analyzed, together with the maintenance log and the alarm log. The case study proves that the proposed methodology detects that more than 17% of false alarms. These results demonstrate that the proposed methodology is effective at detecting and identifying false alarms.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 259.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 329.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Abdallah, I., Ntertimanis, V., et al.: Fault diagnosis of wind turbine structures using decision tree learning algorithms with big data. In: Safety and Reliability-Safe Societies in a Changing World, pp. 3053–3061 (2018)

    Google Scholar 

  2. Albuquerque, S.L., Miosso, C.J., et al.: Classification of electrocardiography signals for user authentication based on ensembles with random undersampling. In: 2021 International Wireless Communications and Mobile Computing (IWCMC), pp. 364–369. IEEE (2021)

    Google Scholar 

  3. Alfaro, E., Gamez, M., Garcia, N.: adabag: an R package for classification with boosting and bagging. J. Stat. Softw. 54, 1–35 (2013)

    Article  Google Scholar 

  4. Ashour, A.S., Guo, Y., Hawas, A.R., Xu, G.: Ensemble of subspace discriminant classifiers for schistosomal liver fibrosis staging in mice microscopic images. Health Inf. Sci. Syst. 6(1), 1–10 (2018). https://doi.org/10.1007/s13755-018-0059-8

    Article  Google Scholar 

  5. Beretta, M., Vidal, Y., et al.: Improved ensemble learning for wind turbine main bearing fault diagnosis. Appl. Sci. 11(16), 7523 (2021)

    Article  Google Scholar 

  6. Bernalte Sánchez, P.J., Garcia Marquez, F.P.: New approaches on maintenance management for wind turbines based on acoustic inspection. In: Xu, J., Duca, G., Ahmed, S.E., García Márquez, F.P., Hajiyev, A. (eds.) ICMSEM 2020. AISC, vol. 1191, pp. 791–800. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-49889-4_61

    Chapter  Google Scholar 

  7. Chacón, A.M.P., Ramírez, I.S., Márquez, F.P.G.: False alarms analysis of wind turbine bearing system. Sustainability 12(19), 7867 (2020)

    Article  Google Scholar 

  8. Chen, W., Qiu, Y., et al.: Diagnosis of wind turbine faults with transfer learning algorithms. Renew. Energy 163, 2053–2067 (2021)

    Article  Google Scholar 

  9. Cusidó, J., López, A., Beretta, M.: Fault-tolerant control of a wind turbine generator based on fuzzy logic and using ensemble learning. Energies 14(16), 5167 (2021)

    Article  Google Scholar 

  10. DSRS: Digital science & research solutions (2021). https://app.dimensions.ai/analytics/public-ation/overview/timeline?search_mode

  11. Freund, Y., Schapire, R.E., et al.: Experiments with a new boosting algorithm. In: ICML, vol. 96, pp. 148–156. Citeseer (1996)

    Google Scholar 

  12. García Márquez, F.P., Segovia Ramírez, I., et al.: Reliability dynamic analysis by fault trees and binary decision diagrams. Information 11(6), 324 (2020)

    Article  Google Scholar 

  13. Harrou, F., Saidi, A., Sun, Y.: Wind power prediction using bootstrap aggregating trees approach to enabling sustainable wind power integration in a smart grid. Energy Convers. Manag. 201(112), 077 (2019)

    Google Scholar 

  14. Hastie, T., Tibshirani, R., et al.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, vol. 2. Springer, Heidelberg (2009). https://doi.org/10.1007/978-0-387-21606-5

    Book  MATH  Google Scholar 

  15. Heinermann, J., Kramer, O.: Machine learning ensembles for wind power prediction. Renew. Energy 89, 671–679 (2016)

    Article  Google Scholar 

  16. Jean, N., Burke, M., et al.: Combining satellite imagery and machine learning to predict poverty. Science 353(6301), 790–794 (2016)

    Article  Google Scholar 

  17. Jiménez, A.A., Muñoz, C.Q.G., Márquez, F.P.G.: Dirt and mud detection and diagnosis on a wind turbine blade employing guided waves and supervised learning classifiers. Reliabil. Eng. Syst. Saf. 184, 2–12 (2019)

    Article  Google Scholar 

  18. Kiziloz, H.E.: Classifier ensemble methods in feature selection. Neurocomputing 419, 97–107 (2021)

    Article  Google Scholar 

  19. Loh, W.Y.: Classification and regression trees. Wiley Interdisc. Rev. Data Min. Knowl. Disc. 1(1), 14–23 (2011)

    Article  Google Scholar 

  20. Márquez, F.P.G., Chacón, A.M.P.: A review of non-destructive testing on wind turbines blades. Renew. Energy 161, 998–1010 (2020)

    Article  Google Scholar 

  21. Márquez, F.P.G., Tobias, A.M., et al.: Condition monitoring of wind turbines: techniques and methods. Renew. energy 46, 169–178 (2012)

    Article  Google Scholar 

  22. Marugán, A.P., Márquez, F.P.G., Papaelias, M.: Multivariable analysis for advanced analytics of wind turbine management. In: Xu, J., Hajiyev, A., Nickel, S., Gen, M. (eds.) Proceedings of the Tenth International Conference on Management Science and Engineering Management. AISC, vol. 502, pp. 319–328. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-1837-4_28

    Chapter  Google Scholar 

  23. Marugán, A.P., Márquez, F.P.G., et al.: A survey of artificial neural network in wind energy systems. Appl. Energy 228, 1822–1836 (2018)

    Article  Google Scholar 

  24. Moreno, S.R., Coelho, L.S., et al.: Wind turbines anomaly detection based on power curves and ensemble learning. IET Renew. Power Gener. 14(19), 4086–4093 (2020)

    Article  Google Scholar 

  25. Peco Chacón, A.M., García Márquez, F.P.: False alarms management by data science. In: García Márquez, F.P., Lev, B. (eds.) Data Science and Digital Business, pp. 301–316. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-95651-0_15

    Chapter  Google Scholar 

  26. Rajesh, K.N., Dhuli, R.: Classification of imbalanced ECG beats using re-sampling techniques and AdaBoost ensemble classifier. Biomed. Signal Process. Control 41, 242–254 (2018)

    Article  Google Scholar 

  27. Ramirez, I.S., Mohammadi-Ivatloob, B., Márqueza, F.P.G.: Alarms management by supervisory control and data acquisition system for wind turbines. Eksploatacja i Niezawodność 23(1), 110–1106 (2021)

    Article  Google Scholar 

  28. Ramirez, I.S., et al.: Motif analysis in internet of the things platform for wind turbine maintenance management. In: Xu, J., García Márquez, F.P., Ali Hassan, M.H., Duca, G., Hajiyev, A., Altiparmak, F. (eds.) ICMSEM 2021. LNDECT, vol. 78, pp. 74–86. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-79203-9_7

    Chapter  Google Scholar 

  29. Reddy, G.T., Bhattacharya, S., et al.: An ensemble based machine learning model for diabetic retinopathy classification. In: 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), pp. 1–6. IEEE (2020)

    Google Scholar 

  30. Reder, M.D., Gonzalez, E., Melero, J.J.: Wind turbine failures-tackling current problems in failure data analysis. J. Phys. Conf. Ser. 753, 072027 (2016)

    Google Scholar 

  31. Schlechtingen, M., Santos, I.F.: Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection. Mech. Syst. Signal Process. 25(5), 1849–1875 (2011)

    Article  Google Scholar 

  32. Seiffert, C., Khoshgoftaar, T.M., et al.: Rusboost: a hybrid approach to alleviating class imbalance. IEEE Trans. Syst. Man Cybern.-Part A: Syst. Hum. 40(1), 185–197 (2009)

    Article  Google Scholar 

  33. Shu, L., Li, H., et al.: Study of ice accretion feature and power characteristics of wind turbines at natural icing environment. Cold Reg. Sci. Technol. 147, 45–54 (2018)

    Article  Google Scholar 

  34. Stetco, A., Dinmohammadi, F., et al.: Machine learning methods for wind turbine condition monitoring: a review. Renew. Energy 133, 620–635 (2019)

    Article  Google Scholar 

  35. Tang, M., Chen, Y., et al.: Cost-sensitive extremely randomized trees algorithm for online fault detection of wind turbine generators. Front. Energy Res. 9, 234 (2021)

    Google Scholar 

  36. Verma, A., Kusiak, A.: Fault monitoring of wind turbine generator brushes: a data-mining approach. J. Solar Energy Eng. 134(2), 021001 (2012)

    Article  Google Scholar 

  37. Vidal, Y., Pozo, F., Tutivén, C.: Wind turbine multi-fault detection and classification based on scada data. Energies 11(11), 3018 (2018)

    Article  Google Scholar 

  38. Sm, W., Zhou, J., et al.: Rockburst prediction in hard rock mines developing bagging and boosting tree-based ensemble techniques. J. Central South Univ. 28(2), 527–542 (2021)

    Article  Google Scholar 

  39. Wong, T.T., Yang, N.Y.: Dependency analysis of accuracy estimates in k-fold cross validation. IEEE Trans. Knowl. Data Eng. 29(11), 2417–2427 (2017)

    Article  Google Scholar 

  40. Xu, Z., Saleh, J.H.: Machine learning for reliability engineering and safety applications: review of current status and future opportunities. Reliabil. Eng. Syst. Saf. 211(107), 530 (2021)

    Google Scholar 

  41. Yang, K., Yu, Z., et al.: Hybrid classifier ensemble for imbalanced data. IEEE Trans. Neural Netw. Learn. Syst. 31(4), 1387–1400 (2019)

    Article  MathSciNet  Google Scholar 

  42. Yang, X., Zhang, Y., et al.: Image recognition of wind turbine blade damage based on a deep learning model with transfer learning and an ensemble learning classifier. Renew. Energy 163, 386–397 (2021)

    Article  Google Scholar 

Download references

The work reported herewith has been financially by the Direccin General de Universidades, Investigacin e Innovacin of Castilla-La Mancha, under Research Grant ProSeaWind project (Ref.: SBPLY/19/180501/000102).

Author information

Authors and Affiliations

  1. Ingenium Research Group, Universidad Castilla -La Mancha, 13071, Ciudad Real, Spain

    Ana María Peco Chacon & Fausto Pedro García Márquez

Authors
  1. Ana María Peco Chacon
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fausto Pedro García Márquez
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ana María Peco Chacon .

Editor information

Editors and Affiliations

  1. Business School, Sichuan University, Chengdu, Sichuan, China

    Jiuping Xu

  2. Department of Industrial Engineering, Gazi University, Faculty of Engineering, Ankara, Turkey

    Fulya Altiparmak

  3. School of Mathematical Sciences, University of Khartoum, Khartoum, Sudan

    Mohamed Hag Ali Hassan

  4. University of Castilla-La Mancha (UCLM), Ciudad Real, Spain

    Fausto Pedro García Márquez

  5. Institute of Control Systems, Azerbaijan National Academy of Sciences, Baku, Azerbaijan

    Asaf Hajiyev

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chacon, A.M.P., Márquez, F.P.G. (2022). Ensembles Learning Algorithms with K-Fold Cross Validation to Detect False Alarms in Wind Turbines. In: Xu, J., Altiparmak, F., Hassan, M.H.A., García Márquez, F.P., Hajiyev, A. (eds) Proceedings of the Sixteenth International Conference on Management Science and Engineering Management – Volume 1. ICMSEM 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 144. Springer, Cham. https://doi.org/10.1007/978-3-031-10388-9_33

Download citation

Publish with us

Policies and ethics

Search

Navigation