Dianming WANG1This email address is being protected from spambots. You need JavaScript enabled to view it., Xue PAN1, Jian MA2, Yuzhang DAI2, Chengjun SUN2, Shibin LI2, and Xiaoju YIN1
1School of Renewable Energy, Shenyang Institute of Engineering, Shenyang 110136, Liaoning Province, China
2Huaneng International Power Company Limited Dandong Power Plant, Donggang 110167, Liaoning Province, China
Received: December 31, 2024 Accepted: March 19, 2025 Publication Date: April 23, 2025
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.
Aiming at the safety hidden danger caused by blade faults that are difficult to be detected, the fault prevention detection technology based on blade image intelligent processing is investigated. A wind turbine blade fault prevention detection method is designed to analyses wind turbine blade images by combining DenseNet, Transfer Learning (TL) and Extreme Learning Machines (ELM), and collect image samples as a training set. The image samples are collected as training set, and the image features are effectively extracted using the improved DenseNet, which is combined with Extreme Learning Machines to improve the classification accuracy of the detection. 8000 images were collected, and the analysis results for the test set of images show that the detection accuracy of this model is higher than that of the DenseNet, ResNet and AlexNet models of migration learning, reaching more than 99%, and obtaining a more accurate preventive detection of wind turbine blade faults.
[1] L. Qingmin, Y. Wanshui, and Z. Jiyao, (2021) “Key technologies for the safe operation of wind and solar power generation equipment in support of the “peak CO2 emissions and carbon neutrality” policy" High Voltage Engineering 47(09): 3047–3060. DOI: 10.13336/j.1003 6520.hve.20211083.
[2] S. Tan, L. Cheng, Z. He, and S. Chen, (2021) “Review of research and application on the wind power-generation system" Journal of Machine Design 38(08): 1–8. DOI: 10.13841/j.cnki.jxsj.2021.08.001.
[3] S. Liu, B. Hu, Z. Hu, and Y. Li, (2015) “Comparison and Evaluation on the Non-destructive Testing Methods for the Wind Turbine Blades Defects" Nondestructive Testing 37(3): 47–51.
[4] Y.Jiahuan, Z. Zheying, W. Zhen, L. Guoqiang, and H. Qing, (2020) “A review of research on detecting the wind turbine blades" Composites Science and Engineering (6): 109–113. DOI: 10.3969/j.issn.1003-0999.2020.06. 019.
[5] C. Yang and L. Li, (2020) “Research progress on blade damage fault detection technology of wind turbine" Power Generation Technology 41(06): 599–607. DOI: 10.12096/j.2096-4528.pgt.20044.
[6] A. Castorrini, A. Ortolani, and M. S. Campobasso, (2023) “Assessing the progression of wind turbine energy yield losses due to blade erosion by resolving damage geometries from lab tests and field observations" Renew able Energy 218: 119256. DOI: 10.1016/j.renene.2023.119256.
[7] S. Jiao, J. Bai, and Y. Shou, (2023) “Research on UAV Control Strategy for Accurate Inspection of Wind Turbine Blades" Proceedings of the CSEE 43(10): 3822–3832. DOI: 10.13334/j.0258-8013.pcsee.213369.
[8] B. Zhao, K. Liao, C. Deng, Y. Tan, and S. Cao. “Image convolutional neural learning based image recognition and analysis method for dust on photovoltaic panel”. In: Proceedings of the CSEE. 39. 23. 2019, 6981 6989+. DOI: 10.13334/j.0258-8013.pcsee.190279.
[9] Z.-X. Yang, X.-B. Wang, and J.-H. Zhong, (2016) “Rep resentational learning for fault diagnosis of wind turbine equipment: A multi-layered extreme learning machines approach" Energies 9(6): 379. DOI: 10.3390/en9060379.
[10] Y. She, P. Li, J. Liang, and J. Yang, (2022) “Detection method onblade icing fault of wind turbine based on multi scale permutation entropy and extreme learning machine" Journal of Safety Science and Technology 18(12): 19–25. DOI: 10.11731/j.issn.1673-193x.2022.12.003.
[11] Z. Tang, Y. Xiao, and Y. Li, (2022) “Wind turbine blade icing diagnosis method based on deep learning" Modern Electronics Technique 45(11): 77–82. DOI: 10.16652/j.issn.1004-373x.2022.11.015.
[12] Y. Chen, X. Jiang, T. Huang, T. Jiang, and Q. Hu, (2023) “Study of the effect of pulsed coil structures on transient electromagnetic fields for aircraft and wind tur bine blade de-icing" Trans. China Electrotech. Soc 38: 4221–4232.
[13] Y. Zhou, S. Lichun, H. Qin, et al., (2023) “De-icing calculation model of pneumatic impulse de-icing structure for wind turbine blades and experiment verification" Transactions of China Electrotechnical Society 38(13): 3630 3639. DOI: 10.19595/j.cnki.1000-6753.tces.220520.
[14] Q. Hu, H. Wang, G. Qiu, et al., (2022) “Quantitative analysis of wind turbine blade icing and its application" Trans. China Electrotech. Soc 37(21): 5607–5616. DOI: 10.19595/j.cnki.1000-6753.tces.211234.
[15] A. A. Jiménez, C. Q. G. Muñoz, and F. P. G. Márquez, (2019) “Dirt and mud detection and diagnosis on a wind turbine blade employing guided waves and supervised learning classifiers" Reliability Engineering & System Safety 184: 2–12. DOI: 10.1016/j.ress.2018.02.013.
[16] Y. Liu, X. Ding, and J. Fang, (2019) “Wind turbine blade crack identification based on migration learning" Transducer and Microsystem Technologies 38(8): 107–110. DOI: 10.13873/J.1000-9787(2019)08-0107-04.
[17] L.Huan, X.Tao, M.Aisong,etal., (2023) “Rolling bearing fault diagnosis method based on improved DenseNet and transfer learning under load changes" Light Indus try Machinery 41(1): 53–58. DOI: 10.3969/j.issn.1005 2895.2023.01.009.
[18] P. Marti-Puig, A. Blanco-M, M. Serra-Serra, and J. Solé-Casals, (2021) “Wind turbine prognosis models based on SCADA data and extreme learning machines" Applied Sciences 11(2): 590. DOI: 10.3390/app11020590.
[19] L. Zou, H. Cheng, and Q. Sun, (2023) “Surface dam age identification of wind turbine blade based on improved lightweight asymmetric convolutional neural network" Applied Sciences 13(10): 6330. DOI: 10.3390/ app13106330.
[20] H.Wei, Q. Zhang, M. Shang, and Y. Gu, (2021) “Ex treme learning Machine-based classifier for fault diagnosis of rotating Machinery using a residual network and continuous wavelet transform" Measurement 183: 109864. DOI: 10.1016/j.measurement.2021.109864.
[21] R. Dong, (2023) “Fault detection method of belt conveyor idler based on transfer learning and Densenet" Coal Technology 42(01): 250–252. DOI: 10.13301/j.cnki.ct.2023.01.054.
[22] Z. Li, F. Wang, and J. Zhang, (2024) “A strong generalized fault diagnosis method for PMSM drives with image fusion and transfer learning" Proceedings of the CSEE 44(12): 4933–4945. DOI: 10.13334/j.0258-8013.pcsee.230139.
[23] S. Ye, Z. Zeming, and L. Xiaoyue, (2023) “Fault diagnosis method of wind turbine gearbox based on ResNet ELM and transfer learning" Journal of Mechanical &Electrical Engineering 40(07): 978–987+1078. DOI: 10.3969/j.issn.1001-4551.2023.07.002.
We use cookies on this website to personalize content to improve your user experience and analyze our traffic. By using this site you agree to its use of cookies.
