A novel NMF-DiCCA deep learning method and its application in wind turbine blade icing failure identification

• Autorzy: Yang Chuangyan , Li Peng , Lang Xun , Wu Jiande , Wang Hancheng

Identyfikatory

DOI

10.17531/ein/190381

• Języki publikacji: EN

Abstrakty

EN

Wind turbine blade icing data has the characteristics of multi-source and multi-variable. It is difficult to characterize and identify the icing failure with multi-scale features. In this paper, a novel Non-negative Matrix Factorization-Dynamic-inner Canonical Correlation Analysis (NMF-DiCCA) based on Gated Recurrent Unit (GRU) and Stack Sparse Autoencoder (SSAE) algorithm is proposed to solve this problem. Firstly, using NMF instead of Singular Value Decomposition(SVD) decomposition method in DiCCA algorithm, the NMF-DiCCA is applied to obtain the dynamic latent variable of time serie. Secondly, the latent structure features S of dynamic latent variable is captured by SSAE. Thirdly, the temporal correlation hidden feature H of dynamic latent variable is extracted by GRU. Finally, the attention weight distribution between latent structure S and temporal correlation hidden feature H is integrated using the attention mechanism, and the fusion feature is reconstructed using the improved SSAE(ISSAE) based on GRU and SSAE. For the first time, dynamic latent variable analysis and deep learning representation algorithm are applied to icing failure identification of wind turbine blade, and effective results are obtained.

Słowa kluczowe

EN

wind turbine blade icing; NMF-DiCCA; dynamic latent variable; deep learning representation; improved SSAE

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2024
• Tom: Vol. 26, no. 4
• Strony: art. no. 190381
• Opis fizyczny: Bibliogr. 41 poz., rys., tab., wykr.

Twórcy

autor

Yang Chuangyan

• School of information science and engineering, Yunnan University, China

• https://orcid.org/0000-0002-7532-6836

autor

Li Peng

• School of information science and engineering, Yunnan University, China

• https://orcid.org/0000-0001-9432-8995

autor

Lang Xun

• School of information science and engineering, Yunnan University, China

• https://orcid.org/0000-0001-7380-6935

autor

Wu Jiande

• The School of Engineering, and Yunnan Key Laboratory of Intelligent Systems and Computing, Yunnan University, China

• https://orcid.org/0000-0003-2780-4925

autor

Wang Hancheng

• School of information science and engineering, Yunnan University, China

• https://orcid.org/0009-0006-1944-456X

Bibliografia

• 1. Meng D, Yang S, Jesus A, Fazeres-Ferradosa T, Zhu S. A novel hybrid adaptive Kriging and water cycle algorithm for reliability-based design and optimization strategy: Application in offshore wind turbine monopile. Computer Methods in Applied Mechanics and Engineering 2023 412: 116083. https://doi.org/10.1016/j.cma.2023.116083.
• 2. Meng D , Yang S , Jesus A, Zhu S. A novel Kriging-model-assisted reliability-based multidisciplinary design optimization strategy and its application in the offshore wind turbine tower. Renewable energy 2023 203, 407-420. https://doi.org/10.1016/j.renene.2022.12.062.
• 3. Meng, D., Wang, H., Yang, S., Lv, Z., Hu, Z. Fault Analysis of Wind Power Rolling Bearing Based on EMD Feature Extraction. CMES-Computer Modeling in Engineering and Sciences 2022 130(1), 543–558. https://doi.org/10.32604/cmes.2022.018123.
• 4. Tao T, Liu Y, Qiao Y. Wind turbine blade icing diagnosis using hybrid features and Stacked- XGBoost algorithm. Renewable Energy 2021 180: 1004-1013. https://doi.org/10.1016/j.renene.2021.09.008.
• 5. Liu L, Guan D, Wang Y, Ding C, Wang M, Chu M. Data-Driven Prediction of Wind Turbine Blade Icing, 2021 China Automation Congress, Beijing, China 2021 5211-5216, https://doi: 10.1109/CAC53003.2021.9727866.
• 6. Yi H, Jiang Q. Discriminative feature learning for blade icing fault detection of wind turbine. Measurement Science and Technology 2020 31(11). https://doi.10.1088/1361-6501/ab9bb8.
• 7. Xu C, Fan S, Liu Y, Liu X, Huang L. Wind turbine blade icing detection: a federated learning approach. Energy 2022 254:124441. https://doi.org/10.1016/j.energy.2022.124441.
• 8. Chen W, Qiu Y. Diagnosis of wind turbine faults with transfer learning algorithms. Renewable Energy 2021 163:2053-2067 https://doi.org/10.1016/j.renene.2020.10.121.
• 9. Yang X, Ye T. Diagnosis of Blade Icing Using Multiple Intelligent Algorithms. Energies 2020 13(11):2975. https://doi:10.3390/en13112975.
• 10. Yoon T Kang Y. Proper orthogonal decomposition of continuum-dominated emission spectra for simultaneous multi-property measurements. Energy 2022 254:124458. https://doi.org/10.1016/j.energy.2022.124458.
• 11. Zhang S, Lang Z. SCADA-data-based wind turbine fault detection: A dynamic model sensor method. Control Engineering Practice 2020 102. https://doi. 10.1016/j.conengprac.2020.104546.
• 12. Jing L, Zhao M, Li P. A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox.Measurement 2017 111:1-10. https://doi.org/10.1016/j.measurement.2017.07.017.
• 13. Kemal H, Hasan B. Intelligent ice detection on wind turbine blades using semantic segmentation and class activation map approaches based on deep learning method, Renewable Energy 2022 182:1-16. https://doi.org/10.1016/j.renene.2021.10.025.
• 14. Yuan B, Wang C. WaveletFCNN: A Deep Time Series Classification Model for Wind Turbine Blade Icing Detection. ArXiv, 2019.
• 15. He Z, Shi T, Xuan J. Milling tool wear prediction using multi-sensor feature fusion based on stacked sparse autoencoders. Measurement 2022 190:110719. https://doi.org/10.1016/j.measurement.2022.110719.
• 16. Priyatharishini M. A deep learning based malicious module identification using stacked sparse autoencoder network for VLSI circuit reliability. Measurement 2022 194:111055. https://doi.org/10.1016/j.measurement.2022.111055.
• 17. Zhan X, Liu Z. A novel method of health indicator construction and remaining useful life prediction based on deep learning. Eksploatacja i Niezawodnosc-Maintenance and Reliability 2023.
• 18. Lei J, Liu C. Fault diagnosis of wind turbine based on Long Short-term memory networks. Renewable Energy 2019 133:422-432. https://doi.org/10.1016/j.renene.2018.10.031.
• 19. Xiang L, Wang P. Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism[J]. Measurement 2021 175(8):109094. https://doi:10.1016/J.MEASUREMENT.2021.109094.
• 20. Kong Z, Tang B. Condition monitoring of wind turbines based on spatio-temporal fusion of SCADA data by convolutional neural networks and gated recurrent units. Econpapers 2020 146: 760-768, https://doi.org/10.1016/j.renene.2019.07.033.
• 21. Zhang J, Kong X, Cheng L, Qi H, Yu M. Intelligent fault diagnosis of rolling bearings based on continuous wavelet transform-multiscale feature fusion and improved channel attention mechanism. Eksploatacja i Niezawodność – Maintenance and Reliability 2023 25(1):16. https://doi:10.17531/ein.2023.1.16.
• 22. Yang S, Meng D,Wang H, Yang C. A novel learning function foradaptive surrogate-model-basedreliability evaluation. Phil. Trans. R.Soc 2024 382: 20220395.http://doi.org/10.1098/rsta.2022.0395.
• 23. Xu J, Xiang L. Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images. IEEE Transactions on Medical Imaging 2016 35(1):119-130. https://doi: 10.1109/TMI.2015.2458702.
• 24. Chen Z, Zhang K, Ding S X. Improved canonical correlation analysis-based fault detection methods for industrial processes. Journal of Process Control 2016 41:26-34. https://doi.org/10.1016/j.jprocont.2016.02.006.
• 25. Chen Z, Steven. Canonical correlation analysis-based fault detection methods with application to alumina evaporation process. Control Engineering Practice 2016 46:51-58. https://doi.org/10.1016/j.conengprac.2015.10.006.
• 26. Dong Y, Qin S. Dynamic-Inner Canonical Correlation and Causality Analysis for High Dimensional Time Series Data. IFAC-PapersOnLine 2018 51(18):476-481. https://doi.org/10.1016/j.ifacol.2018.09.379.
• 27. Févotte, Cédric, Idier, Jérôme. Algorithms for nonnegative matrix factorization with the beta-divergence.Neural Computation 2010 23(9):2421 - 2456. https://doi: 10.1162/NECO_a_00168.
• 28. Yang C, Nie K, Qiao J, Danlei Wang. Robust echo state network with sparse online learning. Information Sciences 2022 594. https://doi.org/10.1016/j.ins.2022.02.009.
• 29. Hei Z, Sun B, Wang G, Lou Y, Zhou Y. Multi-feature spatial distribution alignment enhanced domain adaptive method for tool condition monitoring. Eksploatacja i Niezawodność – Maintenance and Reliability 2023 25(4). https://doi:10.17531/ein/171750.
• 30. Y. Dong, Y. Liu S, Qin J. Efficient Dynamic Latent Variable Analysis for High-Dimensional Time Series Data. in IEEE Transactions on Industrial Informatics 2020 16(6): 4068-4076, https://doi: 10.1109/TII.2019.2958074.
• 31. Wu Y, Zhang Y, Zou X. Estimated date of delivery with electronic medical records by a hybrid GBDT-GRU model. ISA transactions2022. https://doi.org/10.1038/s41598-022-08664-5.
• 32. Zheng G, Sun W, Zhang H, Zhou Y, Gao C. Tool wear condition monitoring in milling process based on data fusion enhanced long short-term memory network under different cutting conditions. Eksploatacja i Niezawodność – Maintenance and Reliability 2021 23(4):612-618. https://doi:10.17531/ein.2021.4.3.
• 33. Lyu Y, Zhang Q, Chen A, Wen Z. Interval Prediction of Remaining Useful Life based on Convolutional Auto-Encode and Lower Upper Bound Estimation. Eksploatacja i Niezawodność – Maintenance and Reliability 2023 25(2). https://doi:10.17531/ein/165811.
• 34. Li Y, Li Y. A homotopy gated recurrent unit for predicting high dimensional hyperchaos. Communications in Nonlinear Science and Numerical Simulation 2022 115. https://doi.org/10.1016/j.cnsns.2022.106716.
• 35. Dai G, Wang X. MRGAT: Multi-Relational Graph Attention Network for knowledge graph completion. Neural Networks 2022 154: 234-245. https://doi.org/10.1016/j.neunet.2022.07.014.
• 36. Sun C, Zhang Y, Huang G, Lin Liu, Xiaochen Hao. A soft sensor model based on long&short-term memory dual pathways convolutional gated recurrent unit network for predicting cement specific surface area. ISA Transactions 2022. https://doi.org/10.1016/j.isatra.2022.03.013.
• 37. Zhang H, Song C. Image-Model-Based Fault Identification for Wind Turbines Using Feature Engineering and MuSnet . IEEE Transactions on Industrial Informatics 2022 18(10): 6592-6601. https://doi: 10.1109/TII.2022.3157748.
• 38. Wang H, Li P, Lang X, FTGAN: A Novel GAN-Based Data Augmentation Method Coupled Time–Frequency Domain for Imbalanced Bearing Fault Diagnosis. IEEE Transactions on Instrumentation and Measurement 2023 72:1-14. https://doi: 10.1109/TIM.2023.3234095.
• 39. Dong Y, Qin, S. New Dynamic Predictive Monitoring Schemes Based on Dynamic Latent Variable Models. Industrial and Engineering Chemistry Research 2020 59(6), 2353-2365. Advance online publication. https://doi.org/10.1021/acs.iecr.9b04741.
• 40. Tong R, Li P, Gao L, Lang X, A. Miao and X. Shen. A Novel Ellipsoidal Semisupervised Extreme Learning Machine Algorithm and Its Application in Wind Turbine Blade Icing Fault Detection. IEEE Transactions on Instrumentation and Measurement 2022 71:1-16. Eksploatacja i Niezawodność – Maintenance and Reliability Vol. 26, No. 4, 2024 https://doi: 10.1109/TIM.2022.3205920.
• 41. Tong R, Li P, Lang X, Liang J, Cao M. A novel adaptive weighted kernel extreme learning machine algorithm and its application in wind turbine blade icing fault detection. Measurement 2021 185:110009. https://doi.org/10.1016/j.measurement.2021.110009.