Skip to main content

Advertisement

SpringerLink
Log in

Comparative Study of Deep Learning Models Versus Machine Learning Models for Wind Turbine Intelligent Health Diagnosis Systems

  • Research Article-Computer Engineering and Computer Science
  • Published:
Arabian Journal for Science and Engineering Aims and scope Submit manuscript

Abstract

Wind turbines technology is one of the current solutions and a promising one for renewable green energy. Due to its typical remote installations either on land or off-shore, there is a great interest in autonomously monitoring their system’s health. The gearbox of the turbine is the primary source of major failures that render the system unsafe, inefficient and/or dysfunctional. Although there have been number of attempts in addressing this problem, number of gaps exist including the lack of detecting early signs of abnormal signals, deep learning (DL) solutions which are rare in this specific area of interest, the impact of number of features in convolution neural networks (CNNs) which was never studied, and the lack of comparative studies between DL versus conventional machine learning (ML) models for this problem of interest. This work presents an investigation that will help close the gap in literature by addressing all four aforementioned issues. Our approach is to propose a CNN model and test it against 6 conventional ML models of supervised learning models (multilayered perceptron, discriminant analysis classification and K-nearest neighbors) and unsupervised learning models (self-organizing maps, K-means clustering and Gaussian mixture model). For model testing, real data were acquired from the US National Renewable Energy Laboratory which includes sensor readings for number of critical parts of the gearbox for healthy and abnormal scenarios. Significant experimentation was conducted on all the 7 models, and observations and results discussion are presented. Among our interesting findings, the auto-learning ability of the CNN model was superior to the most powerful feature extraction technique in digital signal processing, the FFT.

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

Access this article

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

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

All data used in this study are available through the corresponding author of this work.

References

  1. Chraye, H.: A critical role for R I for clean energy for the EU green and digital recovery. In: 2020 22nd European Conference on Power Electronics and Applications (EPE'20 ECCE Europe), pp. P.1–P.1 (2020)

  2. Elavarasan, R.M.; Shafiullah, G.M.; Padmanaban, S.; Kumar, N.M.; Annam, A.; Vetrichelvan, A.M.; Mihet-Popa, L.; Holm-Nielsen, J.B.: A comprehensive review on renewable energy development, challenges, and policies of leading Indian States with an international perspective. IEEE Access 8, 74432–74457 (2020)

    Article  Google Scholar 

  3. Rababaah, A.R.; Arumala, J.; Dabipi, I.K.; Fotouhi, K.; Hura, G.; Dudi, A.: Mechanical system fault detection using intelligent digital signal processing. J. Mach. Manuf. Autom. JMMA 5(1), 27–39 (2016)

    Google Scholar 

  4. Shepherd, D.G.: Historical development of the windmill. U.S. Department of Energy, Office of Scientific and Technical Information. https://doi.org/10.2172/6342767. https://www.osti.gov/biblio/6342767 (1990). Accessed 6 Jan 2023

  5. US-DOE. www.energy.gov. https://www.energy.gov/eere/wind/wind-market-reports-2022-edition (2023). Accessed 06 Jan 2023

  6. WTMS. Wind Turbine Market Analysis, www.mordorintelligence.com. https://www.mordorintelligence.com/industry-reports/wind-turbine-market (2023). Accessed 06 Jan 2023

  7. GWER. Global Wind Report, gwec.net. https://gwec.net/global-wind-report-2022/ (2023). Accessed 06 Jan 2023

  8. Wang, Y.; Infield, D.: Supervisory control and data acquisition data-based non-linear state estimation technique for wind turbine gearbox condition monitoring. IET Renew. Power Gener. 7(4), 350–358 (2013)

    Article  Google Scholar 

  9. Jiang, G.; He, H.; Yan, J.; Xie, P.: Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox. IEEE Trans. Ind. Electron. 66(4), 3196–3207 (2019)

    Article  Google Scholar 

  10. Dongzhu, Z.; Hua, Z.; Shiqiang, D.; Yafei, S.: Aero-engine bearing fault diagnosis based on deep neural networks. In: 2020 11th International Conference on Mechanical and Aerospace Engineering (ICMAE) (pp. 145–149) (2020)

  11. Wikipedia Contributors. SCADA. In Wikipedia, the free encyclopedia. https://en.wikipedia.org/w/index.php?title=SCADA&oldid=1022693481 (2021). Accessed 12 May 2021

  12. NREL. Wind turbine gearbox sensory data. https://www.nrel.gov/grid/eastern-wind-data.html (2021). Accessed 17 May 2021

  13. Yu, M.; Dai, B.; Yu, G.; Zhang, H.: Fault diagnosis of wearable temperature sensors based on multi-scale feature extraction. In: 2020 IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), pp. 1053–1057 (2020)

  14. Tang, S.; Yuan, S.; Zhu, Y.: Data preprocessing techniques in convolutional neural network based on fault diagnosis towards rotating machinery. IEEE Access 8, 149487–149496 (2020)

    Article  Google Scholar 

  15. Rababaah, A.: Deep learning of human posture image classification using convolutional neural networks. Int. J. Comput. Sci. Math. 15(3), 273–288 (2022)

    Article  Google Scholar 

  16. Qian, Y.; Yan, R.: Gearbox fault diagnosis in a wind turbine using single sensor based blind source separation. J. Sens. 2016, 1–14 (2016). https://doi.org/10.1155/2016/6971952. (Article ID 6971952)

    Article  Google Scholar 

  17. Liang, H.; Zhao, X.: Rolling bearing fault diagnosis based on one-dimensional dilated convolution network with residual connection. IEEE Access 9, 31078–31091 (2021)

    Article  Google Scholar 

  18. Jiang, W.; Wang, H.; Liu, G.; Liu, Y.; Cai, B.; Li, Z.: A novel method for mechanical fault diagnosis of underwater pump motors based on power flow theory. IEEE Trans. Instrum. Meas. 70, 1–17 (2021)

    Google Scholar 

  19. Zhang, Y.; Feng, Q.; Huang, Q.: Machine fault diagnosis based on wavelet packet coefficients and 1D convolutional neural networks. In: 2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS), pp. 113–117 (2020)

  20. Astolfi, D.; Lorenzo, S.; Ludovico, T.: Fault diagnosis of wind turbine gearboxes through temperature and vibration data. Int. J. Renew. Energy Res. 7(2), 965–976 (2017)

    Google Scholar 

  21. Wang, X.; Lin, X.; Zhou, K.; Lu, Y.: CNN based mechanical fault diagnosis of high voltage circuit breaker using sound and current signal. In: 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE), pp. 1–4 (2020)

  22. Wu, X.; Peng, Z.; Ren, J.; Cheng, C.; Zhang, W.; Wang, D.: Rub-impact fault diagnosis of rotating machinery based on 1-D convolutional neural networks. IEEE Sens. J. 20(15), 8349–8363 (2020)

    Article  Google Scholar 

  23. Huang, C.; Qin, N.; Huang, D.; Liang, K.: Convolutional neural network for fault diagnosis of high-speed train bogie. In: 2019 Chinese Control Conference (CCC), pp. 4937–4941 (2019)

  24. Cheng, Z.; Hu, N.; Chen, J.; Gao, M.; Zhu, Q.: Fault detection of planetary gearboxes based on deep convolutional neural network. In: 2019 Prognostics and System Health Management Conference (PHM-Qingdao), pp. 1–5 (2019)

  25. Nandi, A.; Biswas, S.; Samanta, K.; Roy, S.; Chatterjee, S.: Diagnosis of induction motor faults using frequency occurrence image plots—a deep learning approach. In: 2019 International Conference on Electrical, Electronics and Computer Engineering (UPCON), pp. 1–4 (2019)

  26. Liu, Y.; Pan, Q.; Wang, H.; He, T.: Fault diagnosis of satellite flywheel bearing based on convolutional neural network. In: 2019 Prognostics and System Health Management Conference (PHM-Qingdao), pp. 1–6 (2019)

  27. Pang, Y.; Jiang, G.; He, Q.; Xie, P.: Multi kernel fusion convolutional neural network for wind turbine fault diagnosis. In: 2019 Chinese Automation Congress (CAC), pp. 2871–2876 (2019)

  28. Lv, M.; Liu, S.; Su, X.; Chen, C.: Deep transfer network with multi-kernel dynamic distribution adaptation for cross-machine fault diagnosis. IEEE Access 9, 16392–16409 (2021)

    Article  Google Scholar 

  29. Sharma, D.K.; Rababaah, A.: Stock market predictive model based on integration of signal processing and artificial neural network. Acad. Inf. Manag. Sci. J. 17(1), 51–70 (2014)

    Google Scholar 

  30. Shirkhodaie, A.; Elangovan, V.; Rababaah, A.: Acoustic semantic labeling and fusion of human–vehicle interactions. In: Proceedings Volume 8050, Signal Processing, Sensor Fusion, and Target Recognition XX; 80500Q. Event: SPIE Defense, Security, and Sensing, 2011, Orlando, Florida, United States (2011) https://doi.org/10.1117/12.883544.

  31. Shen, Y.; Wu, Q.; Huang, D.; Dong, S.; Chen, B.: Fault detection method based on multi-scale convolutional neural network for wind turbine gearbox. In: 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp. 838–842 (2020)

  32. Fang, H.; Deng, J.; Zhao, B.; Shi, Y.; Zhou, J.; Shao, S.: LEFE-Net: a lightweight efficient feature extraction network with strong robustness for bearing fault diagnosis. IEEE Trans. Instrum. Meas. 70, 1–11 (2021)

    Google Scholar 

  33. Wang, Y.; Ding, X.; Zeng, Q.; Wang, L.; Shao, Y.: Intelligent rolling bearing fault diagnosis via vision ConvNet. IEEE Sens. J. 21(5), 6600–6609 (2021)

    Article  Google Scholar 

  34. Wang, J.; Wang, D.; Wang, S.; Li, W.; Song, K.: Fault diagnosis of bearings based on multi-sensor information fusion and 2D convolutional neural network. IEEE Access 9, 23717–23725 (2021)

    Article  Google Scholar 

  35. Li, J.; Deng, A.; Yang, Y.; & Cheng, Q.: Fault diagnosis of wind turbine drive train using time-frequency estimation and CNN. In: 2019 Prognostics and System Health Management Conference (PHM-Qingdao), pp. 1–5 (2019)

  36. Ali, H.; ElBasuony, G.; Kamal, N.: Maximum power production operation of doubly fed induction generator wind turbine using adaptive neural network and conventional controllers. Int. J. Comput. Appl. Technol. 65(2), 77–91 (2021)

    Article  Google Scholar 

  37. Madubuike, K.; Mayhew, C.; Zhang, Q.; Gomm, B.; Yu, D.L.: Fault diagnosis for wind turbine systems using a neural network estimator. In: 2019 25th International Conference on Automation and Computing (ICAC), pp. 1–7 (2019)

  38. Shulian, Y.; Li, W.; Wang, C.: The intelligent fault diagnosis of wind turbine gearbox based on artificial neural network. In: 2008 International Conference on Condition Monitoring and Diagnosis, pp. 1327–1330 (2008).

  39. Blanco-M, A.; Gibert, K.; Marti-Puig, P.; Cusidó, J.; Solé-Casals, J.: Identifying health status of wind turbines by using self organizing maps and interpretation-oriented post-processing tools. J. Energies 11, 723 (2018). https://doi.org/10.3390/en11040723

    Article  Google Scholar 

  40. Catmull, S.: Self-organising map based condition monitoring of wind turbines. In: Proceedings of European Wind Energy Association, Jan 2011, pp. 22–28 (2011)

  41. He, J.; Wu, P.; Gao, J.; Zhang, X.; Lou, S.: Wind turbine gearbox fault detection based on dilated convolutional neural networks. In: 2020 7th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS), pp. 517–521 (2020)

  42. Ng, E.Y.-K.; Lim, J.T.: Machine learning on fault diagnosis in wind turbines. Fluids 2022(7), 371 (2022). https://doi.org/10.3390/fluids712037

    Article  Google Scholar 

  43. Malik, H.: Wavelet and Hilbert Huang transform based wind turbine imbalance fault classification model using k-nearest neighbor algorithm. Int. J. Renew. Energy Technol. 9(1), 66–83 (2018). https://doi.org/10.1504/IJRET.2018.090105

    Article  MathSciNet  Google Scholar 

  44. Ren, L.; Yong, B.: Wind turbines fault classification treatment method. Symmetry 14(4), 688 (2022). https://doi.org/10.3390/sym14040688

    Article  Google Scholar 

  45. Jin, G.; Wang, T.; Amirat, Y.; Zhou, Z.; Xie, T.: A layering linear discriminant analysis-based fault diagnosis method for grid-connected inverter. J. Mar. Sci. Eng. 10(7), 939 (2022). https://doi.org/10.3390/jmse10070939

    Article  Google Scholar 

  46. Avendano-Valencia, L.; Fassois, S.: Damage/fault diagnosis in an operating wind turbine under uncertainty via a vibration response Gaussian mixture random coefficient model-based framework. Mech. Syst. Signal Process. 91, 326–353 (2016). https://doi.org/10.1016/j.ymssp.2016.11.028

    Article  Google Scholar 

  47. Tang, M.; Meng, C.; Wu, H.; Zhu, H.; Yi, J.; Tang, J.; Wang, Y.: Fault detection for wind turbine blade bolts based on GSG combined with CS-light GBM. Sensors 22, 6763 (2022). https://doi.org/10.3390/s22186763

    Article  Google Scholar 

  48. Aggarwa, C.C.: Neural Networks and Deep Learning: A Textbook. Springer (2018)

    Book  Google Scholar 

  49. Campos, P.G.; Oliveira, E.M.; Ludermir, T.B.; Araujo, A.F.: MLP networks for classification and prediction with rule extraction mechanism. In: IEEE International Joint Conference on Neural Networks, pp. 1387–1392. IEEE, Budapest (2004)

  50. Hasan, S.; Erdal, A.; Taskin, K.: Design of feedforward neural networks in the classification of hyperspectral imagery using superstructural optimization. Remote Sens. (2020). https://doi.org/10.3390/rs12060956

    Article  Google Scholar 

  51. Rababaah, A.: CS MS Thesis. www.iusb.edu: https://clas.iusb.edu/math-compsci/_prior-thesis/HRababaah_thesis.pdf (2020)

  52. Haykin, S.: Neural Networks and Learning Machines. Pearson, New York City (2008)

    Google Scholar 

  53. Kohonen, T.: The self-organizing map. Proc. IEEE (1990). https://doi.org/10.1109/5.58325

    Article  MATH  Google Scholar 

  54. Proakis, J.: Digital Signal Processing: Principles, Algorithms, and Applications, 3rd edn. Prentice Hall (2007)

    Google Scholar 

  55. Krizhevsky, A.; Sutskever, I.; Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Neural Information Processing Systems Conference. https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf (2013). Accessed 5 Sept 2022

  56. Szegedy, C.: Going deeper with convolutions. In: Computer Vision Foundation. https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/43022.pdf (2015). Accessed 5 Sept 2022

  57. MATLAB.: 9.4.0.813654 (R2018a). Natick. The MathWorks Inc, Massachusetts. https://www.mathworks.com (2018)

  58. Rababaah, A.; Sharma, D.K.: Integration of two different signal processing techniques with artificial neural network for stock market forecasting. J. Manag. Inf. Decis. Sci. 18(2), 63–80 (2015)

    Google Scholar 

  59. Rababaah, A.; Tebekaemi, E.: Electric load monitoring of residential buildings using goodness of fit and multi-layer perceptron neural networks. In: 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE), pp. 733–737 (2012). https://doi.org/10.1109/CSAE.2012.6272871

Download references

Funding

No funding is applicable for this research work.

Author information

Authors and Affiliations

  1. College of Engineering and Applied Sciences, American University of Kuwait, Salmiya, Kuwait

    Aaron Rasheed Rababaah

Authors
  1. Aaron Rasheed Rababaah
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Aaron Rasheed Rababaah.

Ethics declarations

Conflict of interest

The authors disclosed no conflicts of interest.

Human and/or Animals Rights

The authors declared that this article does not contain any studies involving human subjects or animals.

Informed Consent

Not applicable.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rababaah, A.R. Comparative Study of Deep Learning Models Versus Machine Learning Models for Wind Turbine Intelligent Health Diagnosis Systems. Arab J Sci Eng 48, 10875–10899 (2023). https://doi.org/10.1007/s13369-023-07810-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13369-023-07810-z

Keywords

Search

Navigation