{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:48:20Z","timestamp":1785797300205,"version":"3.56.0"},"reference-count":43,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T00:00:00Z","timestamp":1660176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Recently, the machine-vision-based blades surface damage detection technique has received great attention for its low cost, easy operation, and lack of a need for prior knowledge. The rapid progress of deep learning has contributed to the promotion of this technology with automatic feature extraction, a broader scope of application, and stronger expansibility. An image recognition method of wind turbine blade defects using attention-based MobileNetv1-YOLOv4 and transfer learning is proposed in this paper. The backbone convolution neural network of YOLOv4 is replaced by the lightweight MobileNetv1 for feature extraction to reduce complexity and computation. Attention-based feature refinement with three distinctive modules, SENet, ECANet, and CBAM, is introduced to realize adaptive feature optimization. To solve the problem of slow network convergence and low detection accuracy caused by insufficient data, a two-stage transfer learning approach is introduced to fine-tune the pre-trained network. Comparative experiments verify the efficacy of the proposed model, with higher detection accuracy but a significantly faster response speed and less computational complexity, compared with other state-of-the-art networks by using images of the wind turbine blades taken by an unmanned aerial vehicle (UAV). A sensitivity study is also conducted to present the effects of different training dataset sizes on the model performance.<\/jats:p>","DOI":"10.3390\/s22166009","type":"journal-article","created":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T23:05:49Z","timestamp":1660259149000},"page":"6009","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Image Recognition of Wind Turbine Blade Defects Using Attention-Based MobileNetv1-YOLOv4 and Transfer Learning"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6570-5947","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"first","affiliation":[{"name":"Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment, Hubei University of Technology, Wuhan 430068, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Energy and Power Engineering, Changchun Institute of Technology, Changchun 130012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110886","DOI":"10.1016\/j.rser.2021.110886","article-title":"Offshore wind turbine operations and maintenance: A state-of-the-art review","volume":"144","author":"Ren","year":"2021","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_2","unstructured":"GWEC (2022). Global Wind Report 2021, Global Wind Energy Council."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.measurement.2018.06.045","article-title":"Fatigue damage assessment of wind turbine composite blades using corrected blade element momentum theory","volume":"129","author":"Zhang","year":"2018","journal-title":"Measurement"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.renene.2018.12.066","article-title":"Reliability Improvement of Wind Turbine Power Generation using Model-based Fault Detection and Fault Tolerant Control: A review","volume":"135","author":"Habibi","year":"2019","journal-title":"Renew. Energy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1016\/j.renene.2020.07.145","article-title":"A Review of Non-destructive Testing on Wind Turbines Blades","volume":"161","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_6","first-page":"100522","article-title":"Defect Detection Using Hyperspectral Imaging Technology on Wind Turbine Blade","volume":"22","author":"Rizk","year":"2021","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107950","DOI":"10.1016\/j.measurement.2020.107950","article-title":"Reliability analysis of wind turbine blades based on non-Gaussian wind load impact competition failure model","volume":"164","author":"Zhao","year":"2020","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.compstruct.2015.08.137","article-title":"Damage and nonlinearities detection in wind turbine blades based on strain field pattern recognition. FBGs, OBR and strain gauges comparison","volume":"135","author":"Gueemes","year":"2016","journal-title":"Compos. Struct."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"19992","DOI":"10.3390\/s150819992","article-title":"Damage Detection Based on Static Strain Responses Using FBG in a Wind Turbine Blade","volume":"15","author":"Tian","year":"2015","journal-title":"Sensors"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.renene.2014.11.004","article-title":"Experimental and theoretical analysis of the stress-strain state of anisotropic multilayer composite panels for wind turbine blade","volume":"79","author":"Bitkina","year":"2015","journal-title":"Renew. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.renene.2016.06.048","article-title":"An experimental study of acoustic emission methodology for in service condition monitoring of wind turbine blades","volume":"99","author":"Tang","year":"2016","journal-title":"Renew. Energy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6630","DOI":"10.1109\/TIM.2020.2969062","article-title":"Fault Diagnosis of Industrial Wind Turbine Blade Bearing Using Acoustic Emission Analysis","volume":"69","author":"Liu","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1016\/j.renene.2015.05.025","article-title":"A dual de-icing system for wind turbine blades combining high-power ultrasonic guided waves and low-frequency forced vibrations","volume":"83","author":"Habibi","year":"2015","journal-title":"Renew. Energy"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.renene.2017.03.052","article-title":"Wavelet transforms and pattern recognition on ultrasonic guides waves for frozen surface state diagnosis","volume":"116","year":"2018","journal-title":"Renew. Energy"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"107295","DOI":"10.1016\/j.measurement.2019.107295","article-title":"A Lazy Learning Approach for Condition Monitoring of Wind Turbine Blade Using Vibration Signals and Histogram Features","volume":"152","author":"Joshuva","year":"2020","journal-title":"Measurement"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107076","DOI":"10.1016\/j.measurement.2019.107076","article-title":"Effect and Detection of Cracks on Small Wind Turbine Blade Vibration Using Special Kriging Analysis of Spectral Shifts","volume":"151","author":"Awadallah","year":"2019","journal-title":"Measurement"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.renene.2019.06.094","article-title":"Vibration analysis for large-scale wind turbine blade bearing fault detection with an empirical wavelet thresholding method","volume":"146","author":"Liu","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.measurement.2016.06.064","article-title":"Ice detection using thermal infrared radiometry on wind turbine blades","volume":"93","year":"2016","journal-title":"Measurement"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1007\/s40684-020-00192-9","article-title":"Remote Inspection of Internal Delamination in Wind Turbine Blades using Continuous Line Laser Scanning Thermography","volume":"7","author":"Hwang","year":"2020","journal-title":"Int. J. Precis. Eng. Manuf.-Green Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106445","DOI":"10.1016\/j.ymssp.2019.106445","article-title":"Damage detection techniques for wind turbine blades: A review","volume":"141","author":"Du","year":"2020","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"053305","DOI":"10.1063\/1.5113532","article-title":"Wind turbine blade surface inspection based on deep learning and UAV-taken images","volume":"11","author":"Xu","year":"2019","journal-title":"J. Renew. Sustain. Energy"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107604","DOI":"10.1016\/j.engfracmech.2021.107604","article-title":"Deep learning-based planar crack damage evaluation using convolutional neural networks","volume":"246","author":"Long","year":"2021","journal-title":"Eng. Fract. Mech."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1111\/mice.12263","article-title":"Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks","volume":"32","author":"Cha","year":"2017","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8535","DOI":"10.1007\/s12652-020-02587-7","article-title":"Wind Turbine Blade Structural State Evaluation by Hybrid Object Detector Relying on Deep Learning Models","volume":"12","author":"Gunturi","year":"2021","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.1109\/TMECH.2019.2908233","article-title":"A Two-Stage Data-Driven Approach for Image-Based Wind Turbine Blade Crack Inspections","volume":"24","author":"Wang","year":"2019","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, D., Zhang, Y., and Yang, X. (2022). Image Recognition of Wind Turbines Blade Surface Defects Based on Mask-RCNN. Advanced Intelligent Technologies for Industry, Springer.","DOI":"10.1007\/978-981-16-9735-7_57"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"106823","DOI":"10.1016\/j.measurement.2019.07.051","article-title":"Detection of Cracks and damage in wind turbine blades using artificial intelligence-based image analytics","volume":"147","author":"Reddy","year":"2019","journal-title":"Measurement"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"116827","DOI":"10.1016\/j.eswa.2022.116827","article-title":"Fabric defect detection based on completed local quartet patterns and majority decision algorithm","volume":"198","author":"Pourkaramdel","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2164","DOI":"10.1109\/TNNLS.2019.2929059","article-title":"Real-Time Object Detection with Reduced Region Proposal Network via Multi-Feature Concatenation","volume":"31","author":"Shih","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3366","DOI":"10.1109\/TGRS.2019.2953936","article-title":"Saliency-Guided Single Shot Multibox Detector for Target Detection in SAR Images","volume":"58","author":"Du","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/s13349-020-00447-8","article-title":"One stage detector (RetinaNet)-based crack detection for asphalt pavements considering pavement distresses and surface objects","volume":"11","author":"Tran","year":"2021","journal-title":"J. Civ. Struct. Health Monit."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.eswa.2017.11.028","article-title":"A new image classification method using CNN transfer learning and web data augmentation","volume":"95","author":"Han","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017, January 21\u201326). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"102117","DOI":"10.1016\/j.aquaeng.2020.102117","article-title":"A modified YOLOv3 model for fish detection based on MobileNetv1v1 as backbone","volume":"91","author":"Cai","year":"2020","journal-title":"Aquac. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"106135","DOI":"10.1016\/j.compag.2021.106135","article-title":"Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network","volume":"185","author":"Hu","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","article-title":"Squeeze-and-Excitation Networks","volume":"42","author":"Hu","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sultana, F., Sufian, A., and Dutta, P. (2018, January 22\u201323). Advancements in Image Classification using Convolutional Neural Network. Proceedings of the 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks, Kolkata, India.","DOI":"10.1109\/ICRCICN.2018.8718718"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13\u201319). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.renene.2020.08.125","article-title":"Image recognition of wind turbine blade damage based on a deep learning model with transfer learning and an ensemble learning classifier","volume":"163","author":"Yang","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.autcon.2017.09.018","article-title":"Detecting non-hardhat-use by a deep learning method from far-field surveillance videos","volume":"85","author":"Fang","year":"2018","journal-title":"Autom. Constr."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"22163","DOI":"10.1007\/s11042-021-11280-6","article-title":"YOLOv4 algorithm for the real-time detection of fire and personal protective equipments at construction sites","volume":"81","author":"Kumar","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"ref_43","first-page":"220","article-title":"Isolation and characterization of lytic bacteriophages infecting Pseudomonas aeruginosa from sewage water","volume":"9","author":"Alsaffar","year":"2016","journal-title":"Int. J. PharmTech Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6009\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:07:25Z","timestamp":1760141245000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,11]]},"references-count":43,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["s22166009"],"URL":"https:\/\/doi.org\/10.3390\/s22166009","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,11]]}}}