{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:14:17Z","timestamp":1781532857309,"version":"3.54.5"},"reference-count":44,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51778104"],"award-info":[{"award-number":["51778104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["51778104"],"award-info":[{"award-number":["51778104"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["DL202005"],"award-info":[{"award-number":["DL202005"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]},{"award":["DL202005"],"award-info":[{"award-number":["DL202005"]}],"id":[{"id":"https:\/\/ror.org\/0022v2454","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>This paper introduces CMA-YOLO, a network that integrates multi-scale features with dual attention mechanisms to address weak feature representation, low detection accuracy, and loss of fine-grained details in deep networks for wind turbine blade surface defect detection. First, we construct the C2MSA module by designing a Multi-scale Feature-enhanced Attention Convolution Mix (MS-ACmix) based on ACmix and embedding it into the C2PSA block. This lets the network capture local and global contextual features, strengthening multi-scale target recognition and lowering missed detections. Second, we devise a Monte Carlo Dual Attention (MCDA) mechanism combining random sampling with dual attention. This approach retains the regularization benefits of the Monte Carlo method while leveraging dual attention selection, enabling improved detection accuracy with low computational cost. Finally, we substitute the original downsampling layers in the backbone and neck with the ADown module. This lightweight design, together with efficient feature extraction and fusion, reduces fine-grained detail loss and improves defect detection capability. Quantitative results reveal that, compared to YOLO11n, CMA-YOLO yields improvements of 3.4% in mAP@0.5, 6.1% in mAP@0.5:0.95, and 8.8% in recall, with a 0.7 GFLOPs reduction in computational cost, thus validating the proposed algorithm. Overall, CMA-YOLO provides a lightweight and effective approach for inspecting blade surface defects on wind turbines operating in resource-limited settings.<\/jats:p>","DOI":"10.3390\/info17050512","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:02:27Z","timestamp":1779375747000},"page":"512","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CMA-YOLO: A Network for Wind Turbine Blade Surface Defect Detection with Multi-Scale Features and Dual Attention"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9802-3926","authenticated-orcid":false,"given":"Weining","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Engineering, Dalian Ocean University, Dalian 116023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songsong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Dalian Ocean University, Dalian 116023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingshuo","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Dalian Ocean University, Dalian 116023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4511-114X","authenticated-orcid":false,"given":"Xu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Dalian Ocean University, Dalian 116023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Dalian Ocean University, Dalian 116023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5717-8438","authenticated-orcid":false,"given":"Xiaoming","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Optoelectronic Engineering and Instrumentation Science of DUT, Dalian University of Technology, Dalian 116024, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mao, Y., Shi, Y., Wang, Z., Xia, M., and Zhou, W. (2026). DBFP-Net: Dynamic Graph and Bidirectional Temporal-Frequency Fusion Network for Wind Power Prediction with Physics Constraints. Information, 17.","DOI":"10.3390\/info17040338"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3534","DOI":"10.1038\/s41598-025-33608-0","article-title":"A Two-Stage Surface Defect Segmentation Method for Wind Turbine Blades Based on Deeplabv3+","volume":"16","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"114661","DOI":"10.1016\/j.measurement.2024.114661","article-title":"Analysis of Damage Localization Based on Acoustic Emission Data from Test of Wind Turbine Blades","volume":"231","author":"Mielke","year":"2024","journal-title":"Measurement"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.renene.2012.08.072","article-title":"Review of Structural Health and Cure Monitoring Techniques for Large Wind Turbine Blades","volume":"51","author":"Schubel","year":"2013","journal-title":"Renew. Energy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"106166","DOI":"10.1016\/j.ultras.2020.106166","article-title":"Ultrasound-Based Identification of Damage in Wind Turbine Blades Using Novelty Detection","volume":"108","author":"Oliveira","year":"2020","journal-title":"Ultrasonics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1016\/j.rser.2012.12.056","article-title":"Testing, Inspecting and Monitoring Technologies for Wind Turbine Blades: A Survey","volume":"22","author":"Yang","year":"2013","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1080\/00218464.2014.900449","article-title":"Composite Repair in Wind Turbine Blades: An Overview","volume":"91","author":"Katnam","year":"2015","journal-title":"J. Adhes."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rangel-Rodriguez, A.H., Amezquita-Sanchez, J.P., Granados-Lieberman, D., Camarena-Martinez, D., Bueno-Lopez, M., and Valtierra-Rodriguez, M. (2025). A Gramian Angular Field-Based Convolutional Neural Network Approach for Crack Detection in Low-Power Turbines from Vibration Signals. Information, 16.","DOI":"10.3390\/info16090775"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1007\/s10443-016-9545-9","article-title":"Microwaves Sensor for Wind Turbine Blade Inspection","volume":"24","author":"Li","year":"2017","journal-title":"Appl. Compos. Mater."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kasmire, J., and Zhao, A. (2021). Discovering the Arrow of Time in Machine Learning. Information, 12.","DOI":"10.20944\/preprints202108.0516.v1"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"9201","DOI":"10.1007\/s10499-024-01610-4","article-title":"Cross-Modal Feature Fusion Mask R-CNN and Point Cloud Normalization Segmentation Transformation for Fish Length Estimation","volume":"32","author":"Li","year":"2024","journal-title":"Aquac. Int."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Choi, J.Y., and Han, J.M. (2024). Deep Learning (Fast R-CNN)-Based Evaluation of Rail Surface Defects. Appl. Sci., 14.","DOI":"10.3390\/app14051874"},{"key":"ref_14","first-page":"56","article-title":"Spotting Congenital Heart Diseases Using Palm Print Based on Faster R-CNN and Spatial Method","volume":"16","author":"Mahesha","year":"2024","journal-title":"Int. J. Med. Eng. Inform."},{"key":"ref_15","first-page":"101050","article-title":"A Multicentric Study on a Dosimetric Comparison of Extended SSD Technique, VMAT-Based and Helical Tomotherapy (HT) for Total Body Irradiation (TBI)","volume":"17","author":"Ayata","year":"2024","journal-title":"J. Radiat. Res. Appl. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Guo, Z., Goh, H.H., Li, X., Zhang, M., and Li, Y. (2023). WeedNet-R: A Sugar Beet Field Weed Detection Algorithm Based on Enhanced RetinaNet and Context Semantic Fusion. Front. Plant Sci., 14.","DOI":"10.3389\/fpls.2023.1226329"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., and Mark Liao, H.Y. (2024). YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref_19","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024, January 10\u201315). YOLOv10: Real-Time End-to-End Object Detection. Proceedings of the Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Vancouver, BC, Canada."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cosma, G., and Watkins, J. (2021). Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification. J. Imaging, 7.","DOI":"10.3390\/jimaging7030046"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"123378","DOI":"10.1109\/ACCESS.2022.3224446","article-title":"Efficient and Accurate Damage Detector for Wind Turbine Blade Images","volume":"10","author":"Lv","year":"2022","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2100631","DOI":"10.1002\/adts.202100631","article-title":"SOD-YOLO: A Small Target Defect Detection Algorithm for Wind Turbine Blades Based on Improved YOLOV5","volume":"5","author":"Zhang","year":"2022","journal-title":"Adv. Theory Simul."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018). CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e70029","DOI":"10.1002\/we.70029","article-title":"GCB-YOLO: A Lightweight Algorithm for Wind Turbine Blade Defect Detection","volume":"28","author":"Zhang","year":"2025","journal-title":"Wind Energy"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020). GhostNet: More Features from Cheap Operations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"111645","DOI":"10.1016\/j.engappai.2025.111645","article-title":"Wind Turbine Blade Surface Defect Detection Model Based on Improved You Only Look Once Version 10 Small and Integrated Compression","volume":"159","author":"Liu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TMM.2021.3068576","article-title":"Spatial Pyramid Attention for Deep Convolutional Neural Networks","volume":"23","author":"Ma","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ouyang, D., He, S., Zhang, G., Luo, M., Guo, H., Zhan, J., and Huang, Z. (2023). Efficient Multi-Scale Attention Module with Cross-Spatial Learning. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Mao, M., and Hong, M. (2025). YOLO Object Detection for Real-Time Fabric Defect Inspection in the Textile Industry: A Review of YOLOv1 to YOLOv11. Sensors, 25.","DOI":"10.3390\/s25072270"},{"key":"ref_32","unstructured":"Khanam, R., and Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Pan, X., Ge, C., Lu, R., Song, S., Chen, G., Huang, Z., and Huang, G. (2022). On the Integration of Self-Attention and Convolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"7185","DOI":"10.1609\/aaai.v36i7.20679","article-title":"Fast Monte-Carlo Approximation of the Attention Mechanism","volume":"Volume 36","author":"Kim","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_35","unstructured":"Shihavuddin, A.S.M., and Chen, X. (2018). DTU\u2014Drone Inspection Images of Wind Turbine. Mendeley Data."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, J., Kan, M., Shan, S., and Chen, X. (2020). Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"108784","DOI":"10.1016\/j.compbiomed.2024.108784","article-title":"Channel Prior Convolutional Attention for Medical Image Segmentation","volume":"178","author":"Huang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Lin, X., Ma, L., Liu, W., and Chang, S.F. (2020). Context-Gated Convolution. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-58523-5_41"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., and Liu, Z. (2020). Dynamic Convolution: Attention over Convolution Kernels. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref_40","unstructured":"Li, C., Zhou, A., and Yao, A. (2022, January 25\u201329). Omni-Dimensional Dynamic Convolution. Proceedings of the International Conference on Learning Representations (ICLR 2022), Virtual."},{"key":"ref_41","unstructured":"Jocher, G., Chaurasia, A., and Stoken, A. (2022). Ultralytics\/YOLOv5, version 7.0; YOLOv5 SOTA Realtime Instance Segmentation, Zenodo."},{"key":"ref_42","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., and Wei, X. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv."},{"key":"ref_43","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics YOLOv8, version 8.0.0, Zenodo."},{"key":"ref_44","unstructured":"Tian, Y., Ye, Q., and Doermann, D. (2025, January 24\u201328). YOLOv12: Attention-Centric Real-Time Object Detectors. Proceedings of the International Conference on Learning Representations (ICLR 2025), Singapore."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/512\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:18:06Z","timestamp":1779376686000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/512"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":44,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["info17050512"],"URL":"https:\/\/doi.org\/10.3390\/info17050512","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]}}}