Skip to main content

Advertisement

SpringerLink
Log in

Semi-supervised deep learning recognition method for the new classes of faults in wind turbine system

  • Original Submission
  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Traditional fault recognition algorithms can only identify the known classes of fault in wind turbine systems(WTs). These faults have already appearedin the WTs, thus, the fault recognition algorithm can identify the classesof them. However, if a new classfault didnot happen in the WTs before, the traditional fault recognition algorithm can only identify it as known class of fault, which results in an incorrect identification. Toaddress this problem, a new class fault recognition method based on semi-supervised deep learning(SDL-NCFR)is proposed. Firstly, multiple WTs signals are used as input and features are extracted by convolutional autoencoder network; secondly, the initialization model is built with compressed features as input to the classifier and error feature map as input to the detector; finally, the detector will put new class fault instances into the buffer. When the buffer overflows, the algorithm starts to update, thus achieving the purpose of identifying new class faults. The experimental results show that the average accuracy of the initialized model could reach more than 98%. The accuracy of updated model could still reach 89.39%, and the detection rate could reach 99.50%, the recall reached 88.76%, the precision reached 92.03%, and the F1 score reached 90.36% respectively. The experimental results show that the proposed algorithm can effectively solve the problem of identifying new class faults in WTs, and the accuracy is much higher than that of traditional detection methods.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Zhou B, Duan H et al (2021) Short-term prediction of wind power and its ramp events based on semi-supervised generative adversarial network. International Journal of Electrical Power & Energy Systems 125:106411. https://doi.org/10.1016/j.ijepes.2020.106411

    Article  Google Scholar 

  2. World Wind Energy statistics (2020) https://wwindea.org/blog/2020/04/16/world-wind-capacity-at-650-gw/

  3. Qiao W, Lu D (2015) A survey on wind turbine condition monitoring and fault diagnosis—Part I: Components and subsystems. IEEE Transactions on Industrial Electronics 62(10):6536–6545. https://doi.org/10.1109/TIE.2015.2422112

    Article  Google Scholar 

  4. Alizadeh E, Meskin N, Khorasani K (2016) A negative selection immune system inspired methodology for fault diagnosis of wind turbines. IEEE transactions on cybernetics 47(11):3799–3813. https://doi.org/10.1109/TCYB.2016.2582384

    Article  Google Scholar 

  5. Artigao E, Honrubia-Escribano A, Gómez-Lázaro E (2019) In-service wind turbine DFIG diagnosis using current signature analysis. IEEE Transactions on Industrial Electronics 67(3):2262–2271. https://doi.org/10.1109/TIE.2019.2905821

    Article  Google Scholar 

  6. Mojallal A, Lotfifard S (2017) Multi-physics graphical model-based fault detection and isolation in wind turbines. IEEE transactions on smart grid 9(6):5599–5612. https://doi.org/10.1109/TSG.2017.2691782

    Article  Google Scholar 

  7. Catelani M, Ciani L, Galar D, Patrizi G (2020) Optimizing maintenance policies for a yaw system using reliability-centered maintenance and data-driven condition monitoring. IEEE Transactions on Instrumentation and Measurement 69(9):6241–6249. https://doi.org/10.1109/TIM.2020.2968160

    Article  Google Scholar 

  8. Yu X, Tang B, Zhang K (2021) Fault diagnosis of wind turbine gearbox using a novel method of fast deep graph convolutional networks. IEEE Transactions on Instrumentation and Measurement 70:1–14. https://doi.org/10.1109/TIM.2020.3048799

    Google Scholar 

  9. Mukherjee N, Chattopadhyaya A, Chattopadhyay S, Sengupta S (2020) Discrete-wavelet-transform and Stockwell-transform-based statistical parameters estimation for fault analysis in grid-connected wind power system. IEEE Systems Journal 14(3):4320–4328. https://doi.org/10.1109/JSYST.2020.2984132

    Article  Google Scholar 

  10. Vasquez S, Kinnaert M, Pintelon R (2017) Active fault diagnosis on a hydraulic pitch system based on frequency-domain identification. IEEE Transactions on Control Systems Technology 27(2):663–678. https://doi.org/10.1109/TCST.2017.2772890

    Article  Google Scholar 

  11. Nayana BR, Geethanjali P (2019) Improved identification of various conditions of induction motor bearing faults. IEEE Transactions on Instrumentation and Measurement 99:1–1. https://doi.org/10.1109/TIM.2019.2917981

    Google Scholar 

  12. Sharma S, Tiwari SK, Singh S (2021) Integrated approach based on flexible analytical wavelet transform and permutation entropy for fault detection in rotary machines. Measurement 169:108389. https://doi.org/10.1016/j.measurement.2020.108389

    Article  Google Scholar 

  13. Hoang DT, Kang HJ (2019) A motor current signal-based bearing fault diagnosis using deep learning and information fusion. IEEE Transactions on Instrumentation and Measurement 69(6):3325–3333. https://doi.org/10.1109/TIM.2019.2933119

    Article  Google Scholar 

  14. Sohaib M, Kim JM (2019) Fault diagnosis of rotary machine bearings under inconsistent working conditions. IEEE Trans Instrum Meas 69(6):3334–3347. https://doi.org/10.1109/TIM.2019.2933342

    Article  Google Scholar 

  15. Long Z, Zhang X et al (2021) Motor fault diagnosis using attention mechanism and improved adaboost driven by multi-sensor information. Measurement 170:108718. https://doi.org/10.1016/j.measurement.2020.108718

    Article  Google Scholar 

  16. Huang N, Chen Q et al (2020) Fault diagnosis of bearing in wind turbine gearbox under actual operating conditions driven by limited data with noise labels. IEEE Transactions on Instrumentation and Measurement https://doi.org/10.1109/TIM.2020.3025396

  17. He Q, Zhao J, Jiang G, Xie P (2020) An unsupervised multiview sparse filtering approach for current-based wind turbine gearbox fault diagnosis. IEEE Transactions on Instrumentation and Measurement 69 (8):5569–5578. https://doi.org/10.1109/TIM.2020.2964064

    Article  Google Scholar 

  18. Guo Q, Li Y, Song Y, Wang D, Chen W (2019) Intelligent fault diagnosis method based on full 1-D convolutional generative adversarial network. IEEE Transactions on Industrial Informatics 16 (3):2044–2053. https://doi.org/10.1109/TII.2019.2934901

    Article  Google Scholar 

  19. Pu Z, Li C, Zhang S, Bai Y (2020) Fault diagnosis for wind turbine gearboxes by using deep enhanced fusion network. IEEE Trans Instrum Meas 70:1–11. https://doi.org/10.1109/TIM.2020.3024048

    Google Scholar 

  20. Yang L, Zhang Z (2020) Wind turbine gearbox failure detection based on scada data: a deep learning based approach. IEEE Transactions on Instrumentation and Measurement 99:1–1. https://doi.org/10.1109/TIM.2020.3045800

    Article  Google Scholar 

  21. Liu X, et al. (2017) Multiple Kernel k-means with Incomplete Kernels. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–1, https://doi.org/10.1109/TPAMI.2019.2892416

  22. Yu X, Lu YH, Gao Q (2021) Pipeline image diagnosis algorithm based on neural immune ensemble learning. International Journal of Pressure Vessels and Piping 189:104249. https://doi.org/10.1016/j.ijpvp.2020.104249

    Article  Google Scholar 

  23. Yang S et al (2018) Real-Time Neuromorphic system for Large-Scale Conductance-Based spiking neural networks. IEEE Transactions on Cybernetics: 1-14. https://doi.org/10.1109/TCYB.2018.2823730

  24. Yang S et al (2021) Neuromorphic Context-Dependent learning framework with Fault-Tolerant spike routing. IEEE Transactions on Neural Networks and Learning Systems:, 1–15, https://doi.org/10.1109/TNNLS.2021.3084250

  25. Masud M, Gao J, Khan L, Han J, Thuraisingham BM (2011) Classification and novel class detection in concept-drifting data streams under time constraints. IEEE Transactions on Knowledge & Data Engineering 23(6):859–874. https://doi.org/10.1109/TKDE.2010.61

    Article  Google Scholar 

  26. Mu X, Ting KM, Zhou ZH (2017) Classification under streaming emerging new classes: a solution using completely-random trees. IEEE Transactions on Knowledge and Data Engineering 29(8):1605–1618. https://doi.org/10.1109/TKDE.2017.2691702

    Article  Google Scholar 

  27. Zhu Y, Ting KM, Zhou ZH (2018) Multi-label learning with emerging new labels. IEEE Transactions on Knowledge and Data Engineering 30(10):1901–1914. https://doi.org/10.1109/TKDE.2018.2810872

    Article  Google Scholar 

  28. Luo L, Xie L, Su H (2020) Deep learning with tensor factorization layers for sequential fault diagnosis and industrial process monitoring. IEEE Access 8:105494–105506. https://doi.org/10.1109/ACCESS.2020.3000004

    Article  Google Scholar 

  29. Odgaard PF, Johnson KE (2013) Wind turbine fault detection and fault tolerant control-an enhanced benchmark challenge. In: 2013 American Control Conference, pp 4447–4452, https://doi.org/10.1109/ACC.2013.6580525

  30. Zhao X, Wu Y, Lee DL, Cui W (2018) iforest: Interpreting random forests via visual analytics. IEEE transactions on visualization and computer graphics 25(1):407–416. https://doi.org/10.1109/TVCG.2018.2864475

    Article  Google Scholar 

  31. Zhu J, Wang Y (2018) Zhou, D.,and Gao, F Batch process modeling and monitoring with local outlier factor. IEEE Transactions on Control Systems Technology 27(4):1552–1565. https://doi.org/10.1109/TCST.2018.2815545

    Article  Google Scholar 

  32. Devi D, Biswas SK, Purkayastha B (2019) Learning in presence of class imbalance and class overlapping by using one-class SVM and undersampling technique. Connection Science 31(2):105–142. https://doi.org/10.1080/09540091.2018.1560394

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, 411201, China

    Jun Liu, Wenxin Yu, Zhenheng Wang, Guang’an Zhong & Feng He

  2. School of Physics and Electronics, Hunan University of Science and Technology, Xiangtan, 411201, China

    Junnian Wang

Authors
  1. Jun Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Junnian Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wenxin Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhenheng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Guang’an Zhong
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Feng He
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Junnian Wang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, J., Wang, J., Yu, W. et al. Semi-supervised deep learning recognition method for the new classes of faults in wind turbine system. Appl Intell 52, 9212–9224 (2022). https://doi.org/10.1007/s10489-021-03024-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-03024-8

Keywords

Search

Navigation