Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

SpringerLink
Log in

Prediction of wind turbine blades icing based on feature Selection and 1D-CNN-SBiGRU

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Wind turbine blades icing detection has the very practical effect for ensuring the safety, reliability, and stability of operation. The drawbacks of traditional icing prediction methods that are established using complex mathematical models require manual extraction of features. The ReliefF and one-dimensional convolution and stacked bidirectional Gated Recurrent Unit (1D-CNN-SBiGRU) is proposed and applied to wind turbine blade icing prediction. Firstly, in order to solve the problem that the high-dimension data collected by the SCADA system of the wind turbine that causes the much lower processing efficiency, and the extremely unbalanced data leads to the large prediction error, this paper conducts a correlation analysis on the 28-dimensional original feature data and obtains 20-dimension feature data. Moreover, 15-dimension features are selected from the processed data by ReliefF algorithm to sort the features by weight. Secondly, considering the sequential characteristic of sensor data, this paper uses a sliding window with step size to reconstruct the data. Then, 1D-CNN is applied for extracting sequential characteristic features again. Finally, this paper employs SBiGRU to predict the icing of the wind turbine blades. In order to deal with the consistency of unbalanced data evaluation, this paper proposes the Weighted Accuracy (WA) index to evaluate the proposed method in this paper. The experimental results show that compared with SVM/ CNN/ BiLSTM, the WA of the method proposed in this paper is improved by 43.08%/34.61%/14.44% respectively.

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

Similar content being viewed by others

Explore related subjects

Find the latest articles, discoveries, and news in related topics.

References

  1. Bailey D, Wright E (2003) Landlines - practical SCADA for industry - 4. Practical Scada for Industry 49(22):100–141

    Article  Google Scholar 

  2. Battishti L (2015) Wind turbines in cold climates. Springer International Publishing, Switzerland

    Google Scholar 

  3. Becerra-Rico J, Aceves-Fernández MA, Esquivel-Escalante K et al (2020) Airborne particle pollution predictive model using Gated Recurrent Unit (GRU) deep neural networks. Earth Sci Inf:1–14

  4. Chen X, Lei D, Xu G (2020) Prediction of Icing Fault of Wind Turbine Blades Based on Deep Learning. 2019 IEEE 2nd International Conference on Automation, Electronics and Electrical Engineering (AUTEEE). IEEE

  5. Eren L, Ince T, Kiranyaz S (2019) A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier. J Signal Process Syst 91(2):179–189

    Article  Google Scholar 

  6. Feng X, Liu X (2019) Sentiment classification of reviews based on BiGRU neural network and fine-grained attention. J Phys Conf Ser

  7. Gao H, Rose JL (2009) Ice detection and classification on an aircraft wing with ultrasonic shear horizontal guided waves. IEEE Trans Ultrason Ferroelectr Freq Control 56(2):334–344

    Article  Google Scholar 

  8. Gers, Felix A., Jürgen Schmidhuber, and Fred Cummins. "Learning to forget: Continual prediction with LSTM." (1999): 850–855.

  9. He J, Li Y, Cao J et al (2020) An improved particle filter propeller fault prediction method based on grey prediction for underwater vehicles. Trans Inst Meas Control 42(4):014233121990120

    Google Scholar 

  10. Homola Matthew C, Virk Muhammad S, Nicklasson Per J et al (2011) Modelling of ice induced power losses and comparison with observations. Winterwind

  11. Hongyuan X, Yuejia S, Yibo J et al (2018) Optimization about fault prediction and diagnosis of wind turbine based on support vector machine. International Conference on Measuring Technology & Mechatronics Automation. IEEE Computer Society

  12. Hu L, Chen J, Shen X, Zhu X, Zhaohui D (2020) Calculation of freezing water droplet collection coefficient on wind turbine blades. Acta Solar Sinica 41(03):22–28

    Google Scholar 

  13. Kang C, Yao L (2017) Key scientific issues and theoretical research framework for power systems with high proportion of renewable energy. Autom Electr Power Syst

  14. Kingma D P and Ba J 2014 Adam: a method for stochastic optimization (arXiv:1412.6980).

  15. Kononenko I (1994) Estimating attributes: analysis and extensions of RELIEF. European Conference on Machine Learning on Machine Learning. Springer, Berlin, Heidelberg

  16. Li X, Chen M, Wang Q (2018) Self-tuned discrimination-aware method for unsupervised feature selection. IEEE Transactions on Neural Networks and Learning Systems 30(8):2275–2284

    Article  MathSciNet  Google Scholar 

  17. Lishuang L, Jia W, Jieqiong Z et al (2018) Biomedical event extraction based on GRU integrating attention mechanism. Bmc Bioinformatics 19(S9):177–184

    Google Scholar 

  18. Lu W, Li Y, Cheng Y, Meng D, Liang B, Zhou P (2018) Early fault detection approach with deep architectures. IEEE Trans Instrum Meas 67(7):1679–1689. https://doi.org/10.1109/TIM.2018.2800978

  19. Peng D et al (2018) A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains. IEEE Access 7:10278–10293

    Article  Google Scholar 

  20. Peng C, Tang Z, Chen Q et al (2019) Short-Term Prediction of Generator Blade Ice Fault Based on Multi-AN. In: 2019 Seventh International Conference on Advanced Cloud and Big Data (CBD)

    Google Scholar 

  21. Robnik-ikonja M, Kononenko I (2003) Theoretical and empirical analysis of ReliefF and RReliefF. Mach Learn 53:23–69

    Article  Google Scholar 

  22. Rostami M, Berahmand K, Forouzandeh S (2020) A novel method of constrained feature selection by the measurement of pairwise constraints uncertainty. J Big Data 7(1):1–21

    Article  Google Scholar 

  23. Rostami M et al (2021) Review of swarm intelligence-based feature selection methods. Eng Appl Artif Intell 100:104210

    Article  Google Scholar 

  24. Shen HT et al (2020) Half-quadratic minimization for unsupervised feature selection on incomplete data. IEEE Trans Neural Netw Learn Syst

  25. Simani S, Farsoni S, Castaldi P (2018) Data-driven techniques for the fault diagnsis of a wind turbine benchmark. International Journal of Applied Mathematics and Computerence 28(2):247–268

    MATH  Google Scholar 

  26. Wang Q et al (2018) Hierarchical feature selection for random projection. IEEE Trans Neural Netw Learn Syst 30(5):1581–1586

    Article  Google Scholar 

  27. Wei C, Jingshan H, Zheng L, Cong W, Jiahao W (2021) Research on transmission line trip prediction based on logistic regression algorithm under icing condition. 2021 IEEE 4th advanced information management, Communicates, Electronic and Automation Control Conference (IMCEC), pp 565–569, https://doi.org/10.1109/IMCEC51613.2021.9482230

  28. Wu J-S et al (2021) Joint adaptive manifold and embedding learning for unsupervised feature selection. Pattern Recogn 112:107742

    Article  Google Scholar 

  29. Xie Y, Zhao J, Qiang B et al (2021) Attention mechanism-based CNN-LSTM model for wind turbine fault prediction using SSN ontology annotation. Wirel Commun Mob Comput 2021(1):1–12

    Google Scholar 

  30. Xu C, Wang G, Liu XG et al (2016) Health status assessment and failure prediction for hard drives with recurrent neural networks. IEEE Trans Comput:1–1

  31. Xu J, Tan W, Li T (2020) Predicting fan blade icing by using particle swarm optimization and support vector machine algorithm. Comput Electr Eng 87:106751

    Article  Google Scholar 

  32. Zaremba, Wojciech, Ilya Sutskever, and Oriol Vinyals. "Recurrent neural network regularization." arXiv preprint arXiv:1409.2329 (2014).

  33. Zhang Y, Zheng Y, Meng K et al (2017) Flexible operation planning scheme considering wind power generation forecasting uncertainties. Electric Power Components and Systems

  34. Zhang Y, Ren X, Zhang J (2019) Intrusion detection method based on information gain and ReliefF feature selection.2019 International Joint Conference on Neural Networks (IJCNN)

  35. Zhang Y, Cheng C, Chen T (2019) Multi-Channel Physiological Signal Emotion Recognition Based on ReliefF Feature Selection.2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS). IEEE, 2019.

  36. Zhang C et al (2021) Feature selection for cross-scene hyperspectral image classification using cross-domain I-ReliefF. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

  37. Zhong S-s, Song F, Lin L (2019) A novel gas turbine fault diagnosis method based on transfer learning with CNN. Measurement 137:435–453

    Article  Google Scholar 

Download references

Acknowledgments

The author would like to express their gratitude to the National Key R&D Program of China (Grant No. 2020AAA0109300) for the finantial support provided for this work.

Author information

Authors and Affiliations

  1. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, No.333 Longteng Road, Songjiang District, Shanghai, China

    Yuanyuan Li, Lingyu Hou, Ming Tang, Qichun Sun, Jiahang Chen, Wanqing Song, Wei Yao & Le Cao

Authors
  1. Yuanyuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lingyu Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ming Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qichun Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jiahang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wanqing Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Wei Yao
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Le Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, Y.L, L.H, M.T, Q.S and J.C; methldology, Y.L, M.T, L.H and Q.S;software, Y.L, L.H, M.T and Q.S;validation, Y.L, W.S, L.C and W.Y; writing-original draft preparation, Y.L, L.H, Q.S, M.T and J.C; writing-review and editing, Y.L, W.Y, W.S and L.C;supervison, Y.L, W.S and L.C. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Yuanyuan Li.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

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

Li, Y., Hou, L., Tang, M. et al. Prediction of wind turbine blades icing based on feature Selection and 1D-CNN-SBiGRU. Multimed Tools Appl 81, 4365–4385 (2022). https://doi.org/10.1007/s11042-021-11700-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11700-7

Keywords

Search

Navigation