{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:08:47Z","timestamp":1782313727989,"version":"3.54.5"},"reference-count":55,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Wind power plays an increasingly vital role in sustainable energy production, yet the harsh environments in which turbines operate often lead to mechanical or structural degradation. Detecting such faults early is essential to reducing maintenance expenses and extending operational lifetime. In this work, we propose a deep learning-based image classification framework designed to assess turbine condition directly from drone-acquired imagery. Unlike object detection pipelines, which require locating specific damage regions, the proposed strategy focuses on recognizing global visual cues that indicate the overall turbine state. A comprehensive comparison is performed among several lightweight and transformer-based architectures, including MobileNetV3, ResNet, EfficientNet, ConvNeXt, ShuffleNet, ViT, DeiT, and DINOv2, to identify the most suitable model for real-time deployment. The MobileNetV3-Large network achieved the best trade-off between performance and efficiency, reaching 98.9% accuracy while maintaining a compact size of 5.4 million parameters. These results highlight the capability of compact CNNs to deliver accurate and efficient turbine monitoring, paving the way for autonomous, drone-based inspection solutions at the edge.<\/jats:p>","DOI":"10.3390\/fi17110528","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:17:27Z","timestamp":1763551047000},"page":"528","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["AI-Driven Damage Detection in Wind Turbines: Drone Imagery and Lightweight Deep Learning Approaches"],"prefix":"10.3390","volume":"17","author":[{"given":"Ahmed","family":"Hamdi","sequence":"first","affiliation":[{"name":"Institut FEMTO-ST (UMR 6174), Universit\u00e9 Marie et Louis Pasteur, CNRS, F-90000 Belfort, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2589-5053","authenticated-orcid":false,"given":"Hassan N.","family":"Noura","sequence":"additional","affiliation":[{"name":"Institut FEMTO-ST (UMR 6174), Universit\u00e9 Marie et Louis Pasteur, CNRS, F-90000 Belfort, France"},{"name":"Department of Electrical and Computer Engineering, American University of Beirut, Beirut 1107 2020, Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.rser.2015.07.200","article-title":"Wind energy: Trends and enabling technologies","volume":"53","author":"Kumar","year":"2016","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_2","unstructured":"U.S. Energy Information Administration (EIA) (2025, June 10). Renewables Account for Most New U.S. Electricity Generating Capacity in 2021, Available online: https:\/\/www.eia.gov\/todayinenergy\/detail.php?id=46416."},{"key":"ref_3","unstructured":"U.S. Energy Information Administration (EIA) (2025, June 10). Electricity Generation from Wind, Available online: https:\/\/www.eia.gov\/energyexplained\/wind\/electricity-generation-from-wind.php."},{"key":"ref_4","unstructured":"United Nations Framework Convention on Climate Change (UNFCCC) (2025, June 10). The Paris Agreement. Available online: https:\/\/unfccc.int\/process-and-meetings\/the-paris-agreement."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Heier, S. (2014). Grid Integration of Wind Energy: Onshore and Offshore Conversion Systems, John Wiley & Sons.","DOI":"10.1002\/9781118703274"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2326296","DOI":"10.1080\/14786451.2024.2326296","article-title":"A review of artificial intelligence applications in wind turbine health monitoring","volume":"43","author":"Sasinthiran","year":"2024","journal-title":"Int. J. Sustain. Energy"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.1016\/j.rser.2015.06.060","article-title":"Grid-integrated permanent magnet synchronous generator based wind energy conversion systems: A technology review","volume":"51","author":"Tripathi","year":"2015","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lu, B., Li, Y., Wu, X., and Yang, Z. (2009, January 24\u201326). A review of recent advances in wind turbine condition monitoring and fault diagnosis. Proceedings of the 2009 IEEE Power Electronics and Machines in Wind Applications, Lincoln, NE, USA.","DOI":"10.1109\/PEMWA.2009.5208325"},{"key":"ref_9","unstructured":"U.S. Department of Energy (DOE) (2023). Land-Based Wind Market Report: 2023 Edition, Technical report."},{"key":"ref_10","unstructured":"European Wind Energy Association (EWEA) (2025, June 10). \u201cWind Energy\u2014The Facts\u201d. Available online: https:\/\/www.wind-energy-the-facts.org\/images\/090522bdwetflatvia.pdf."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.rser.2015.04.137","article-title":"Impacts of wind energy on environment: A review","volume":"49","author":"Wang","year":"2015","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, H., Li, Q., Wang, X., Zhou, Z., Xu, H., Zhang, D., and Qian, P. (2025). Overview of Condition Monitoring Technology for Variable-Speed Offshore Wind Turbines. Energies, 18.","DOI":"10.3390\/en18051026"},{"key":"ref_13","unstructured":"Nord-Lock Group (2025, October 13). \u201cOffshore Floating Wind Energy,\u201d Nord-Lock Knowledge Blog. Available online: https:\/\/www.nord-lock.com\/cs-cz\/zajimavosti\/knowledge\/2020\/offshore-floating-wind-energy\/."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.ymssp.2018.03.052","article-title":"Gearbox condition monitoring in wind turbines: A review","volume":"111","author":"Salameh","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"128305","DOI":"10.1016\/j.eswa.2025.128305","article-title":"Progressive contrastive representation learning for defect diagnosis in aluminum disk substrates with a bio-inspired vision sensor","volume":"249","author":"Chen","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tu, H., Wang, X., and Li, Y. (2025). Handling Multi-Source Uncertainty in Accelerated Degradation Through a Wiener-Based Robust Modeling Scheme. Sensors, 25.","DOI":"10.3390\/s25216654"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"111209","DOI":"10.1016\/j.ress.2025.111209","article-title":"Attention-guided graph isomorphism learning: A multi-task framework for fault diagnosis and remaining useful life prediction","volume":"250","author":"Qi","year":"2025","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Burton, T., Jenkins, N., Sharpe, D., and Bossanyi, E. (2011). Wind Energy Handbook, John Wiley & Sons.","DOI":"10.1002\/9781119992714"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Manwell, J.F., McGowan, J.G., and Rogers, A.L. (2010). Wind Energy Explained: Theory, Design and Application, John Wiley & Sons.","DOI":"10.1002\/9781119994367"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ackermann, T. (2012). Wind Power in Power Systems, John Wiley & Sons.","DOI":"10.1002\/9781119941842"},{"key":"ref_21","first-page":"200372","article-title":"Wind turbine fault detection and identification using a two-tier machine learning framework","volume":"22","author":"Allal","year":"2024","journal-title":"Intell. Syst. Appl."},{"key":"ref_22","first-page":"12","article-title":"Review of recent advances of wind energy","volume":"8","author":"Alabdali","year":"2020","journal-title":"Sustain. Energy"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Knudsen, H., and Nielsen, J.N. (2012). Introduction to the modelling of wind turbines. Wind Power in Power Systems, John Wiley & Sons.","DOI":"10.1002\/9781119941842.ch34"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"012086","DOI":"10.1088\/1742-6596\/524\/1\/012086","article-title":"Yaw Systems for wind turbines\u2014Overview of concepts, current challenges and design methods","volume":"524","author":"Kim","year":"2014","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103981","DOI":"10.1016\/j.jweia.2019.103981","article-title":"Effect of turbine nacelle and tower on the near wake of a utility-scale wind turbine","volume":"193","author":"Abraham","year":"2019","journal-title":"J. Wind Eng. Ind. Aerodyn."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"105544","DOI":"10.1016\/j.ijepes.2019.105544","article-title":"Modeling and analysis of grid-synchronizing stability of a Type-IV wind turbine under grid faults","volume":"117","author":"Zhang","year":"2020","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, F., Chen, M., Zhu, Y., Zhang, K., and Li, Q. (2023). A review of fault diagnosis, status prediction, and evaluation technology for wind turbines. Energies, 16.","DOI":"10.3390\/en16031125"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s40537-023-00863-9","article-title":"Plant disease detection and classification techniques: A comparative study of the performances","volume":"11","author":"Demilie","year":"2024","journal-title":"J. Big Data"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"121449","DOI":"10.1109\/ACCESS.2024.3453664","article-title":"Deep Learning and Computer Vision Techniques for Enhanced Quality Control in Manufacturing Processes","volume":"12","author":"Islam","year":"2024","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e7140","DOI":"10.1002\/cam4.7140","article-title":"Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis","volume":"13","author":"Wu","year":"2024","journal-title":"Cancer Med."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Yang, B., Zhang, L., Zhang, W., and Ai, Y. (2013, January 19\u201321). Non-destructive testing of wind turbine blades using an infrared thermography: A review. Proceedings of the 2013 International Conference on Materials for Renewable Energy and Environment, Chengdu, China.","DOI":"10.1109\/ICMREE.2013.6893694"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Han, Y., Liu, T., and Li, K. (2025). Fault diagnosis of wind turbine blades under wide-weather multi-operating conditions based on multi-modal information fusion and deep learning. Struct. Health Monit., online ahead of print.","DOI":"10.1177\/14759217251333761"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.1038\/s41597-024-03934-5","article-title":"Wind turbine condition monitoring dataset of Fraunhofer LBF","volume":"11","author":"Mostafavi","year":"2024","journal-title":"Sci. Data"},{"key":"ref_34","first-page":"7136","article-title":"Detection of solar panel defects based on separable convolution and convolutional block attention module","volume":"45","author":"Yang","year":"2023","journal-title":"Energy Sources Part A Recover. Util. Environ. Eff."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"107836","DOI":"10.1016\/j.engappai.2023.107836","article-title":"Identification of surface defects on solar pv panels and wind turbine blades using attention based deep learning model","volume":"131","author":"Dwivedi","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Mansoor, M., Tan, X., Mirza, A.F., Gong, T., Song, Z., and Irfan, M. (2025). WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection. Machines, 13.","DOI":"10.3390\/machines13060453"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Saci, A., Nadour, M., Cherroun, L., Hafaifa, A., Kouzou, A., Rodriguez, J., and Abdelrahem, M. (2024). Condition Monitoring Using Digital Fault-Detection Approach for Pitch System in Wind Turbines. Energies, 17.","DOI":"10.3390\/en17164016"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"100153","DOI":"10.1016\/j.grets.2024.100153","article-title":"Online condition monitoring and fault diagnosis in wind turbines: A comprehensive review on structure, failures, health monitoring techniques, and signal processing methods","volume":"3","author":"Kanaan","year":"2025","journal-title":"Green Technol. Sustain."},{"key":"ref_39","unstructured":"DTU Wind Energy (2025, July 03). Nordtank Dataset for Wind Turbine Blade Damage Detection. Available online: https:\/\/gitlab.windenergy.dtu.dk\/fair-data\/winddata-revamp\/winddata-documentation\/-\/blob\/master\/nordtank.md."},{"key":"ref_40","unstructured":"Bdhsn, A. (2025, June 15). Wind Turbine Faults Detection\u2014Computer Vision Project Dataset. Available online: https:\/\/universe.roboflow.com\/detectionanas\/wind-turbine-faults-detection."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Koonce, B. (2021). ResNet 50. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, Springer.","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_44","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_45","first-page":"15","article-title":"Diagnostic performance of EfficientNetV2-S method for staging liver fibrosis based on multiparametric MRI","volume":"10","author":"Zhao","year":"2024","journal-title":"Heliyon"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201323). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_47","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., and Sun, J. (2018, January 8\u201314). Shufflenet v2: Practical guidelines for efficient cnn architecture design. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"13711","DOI":"10.1109\/ACCESS.2024.3356551","article-title":"A study of convnext architectures for enhanced image captioning","volume":"12","author":"Ramos","year":"2024","journal-title":"IEEE Access"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Dewangkoro, H.I., Rohmadi, A., and Yudha, E.P. (2025, January 5\u20137). Integrating Efficient Channel Attention Plus into ConvNeXt Network for Remote Sensing Image Scene Classification. Proceedings of the 2025 International Electronics Symposium (IES), Surabaya, Indonesia.","DOI":"10.1109\/IES67184.2025.11161549"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_53","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., and J\u00e9gou, H. (2021, January 18\u201324). Training data-efficient image transformers & distillation through attention. Proceedings of the International conference on Machine Learning, Virtually."},{"key":"ref_54","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). Dinov2: Learning robust visual features without supervision. arXiv."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Demidovskij, A., Tugaryov, A., Trutnev, A., Kazyulina, M., Salnikov, I., and Pavlov, S. (2023). Lightweight and Elegant Data Reduction Strategies for Training Acceleration of Convolutional Neural Networks. Mathematics, 11.","DOI":"10.3390\/math11143120"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/11\/528\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:36:39Z","timestamp":1763552199000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/11\/528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":55,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["fi17110528"],"URL":"https:\/\/doi.org\/10.3390\/fi17110528","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,19]]}}}