IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v17y2024i8p1796-d1372611.html
   My bibliography  Save this article

Improved YOLOv5 Based on Multi-Strategy Integration for Multi-Category Wind Turbine Surface Defect Detection

Author

Listed:
  • Mingwei Lei

    (School of Computer, Beijing Information Science and Technology University, Beijing 102206, China
    These authors contributed equally to this work.)

  • Xingfen Wang

    (Institute of Business Intelligence, Beijing Information Science and Technology University, Beijing 102206, China
    These authors contributed equally to this work.)

  • Meihua Wang

    (School of Computer, Beijing Information Science and Technology University, Beijing 102206, China)

  • Yitao Cheng

    (School of Computer, Beijing Information Science and Technology University, Beijing 102206, China)

Abstract

Wind energy is a renewable resource with abundant reserves, and its sustainable development and utilization are crucial. The components of wind turbines, particularly the blades and various surfaces, require meticulous defect detection and maintenance due to their significance. The operational status of wind turbine generators directly impacts the efficiency and safe operation of wind farms. Traditional surface defect detection methods for wind turbines often involve manual operations, which suffer from issues such as high subjectivity, elevated risks, low accuracy, and inefficiency. The emergence of computer vision technologies based on deep learning has provided a novel approach to surface defect detection in wind turbines. However, existing datasets designed for wind turbine surface defects exhibit overall category scarcity and an imbalance in samples between categories. The algorithms designed face challenges, with low detection rates for small samples. Hence, this study first constructs a benchmark dataset for wind turbine surface defects comprising seven categories that encompass all common surface defects. Simultaneously, a wind turbine surface defect detection algorithm based on improved YOLOv5 is designed. Initially, a multi-scale copy-paste data augmentation method is proposed, introducing scale factors to randomly resize the bounding boxes before copy-pasting. This alleviates sample imbalances and significantly enhances the algorithm’s detection capabilities for targets of different sizes. Subsequently, a dynamic label assignment strategy based on the Hungarian algorithm is introduced that calculates the matching costs by weighing different losses, enhancing the network’s ability to learn positive and negative samples. To address overfitting and misrecognition resulting from strong data augmentation, a two-stage progressive training method is proposed, aiding the model’s natural convergence and improving generalization performance. Furthermore, a multi-scenario negative-sample-guided learning method is introduced that involves incorporating unlabeled background images from various scenarios into training, guiding the model to learn negative samples and reducing misrecognition. Finally, slicing-aided hyper inference is introduced, facilitating large-scale inference for wind turbine surface defects in actual industrial scenarios. The improved algorithm demonstrates a 3.1% increase in the mean average precision (mAP) on the custom dataset, achieving 95.7% accuracy in mAP_50 (the IoU threshold is half of the mAP). Notably, the mAPs for small, medium, and large targets increase by 18.6%, 16.4%, and 6.8%, respectively. The experimental results indicate that the enhanced algorithm exhibits high detection accuracy, providing a new and more efficient solution for the field of wind turbine surface defect detection.

Suggested Citation

  • Mingwei Lei & Xingfen Wang & Meihua Wang & Yitao Cheng, 2024. "Improved YOLOv5 Based on Multi-Strategy Integration for Multi-Category Wind Turbine Surface Defect Detection," Energies, MDPI, vol. 17(8), pages 1-25, April.
  • Handle: RePEc:gam:jeners:v:17:y:2024:i:8:p:1796-:d:1372611
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/17/8/1796/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/17/8/1796/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yuan Yao & Guozhong Wang & Jinhui Fan, 2023. "WT-YOLOX: An Efficient Detection Algorithm for Wind Turbine Blade Damage Based on YOLOX," Energies, MDPI, vol. 16(9), pages 1-15, April.
    2. H. W. Kuhn, 1955. "The Hungarian method for the assignment problem," Naval Research Logistics Quarterly, John Wiley & Sons, vol. 2(1‐2), pages 83-97, March.
    3. Tang, Jialin & Soua, Slim & Mares, Cristinel & Gan, Tat-Hean, 2016. "An experimental study of acoustic emission methodology for in service condition monitoring of wind turbine blades," Renewable Energy, Elsevier, vol. 99(C), pages 170-179.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Weiqiang Shen & Chuanlin Zhang & Xiaona Zhang & Jinglun Shi, 2019. "A fully distributed deployment algorithm for underwater strong k-barrier coverage using mobile sensors," International Journal of Distributed Sensor Networks, , vol. 15(4), pages 15501477198, April.
    2. András Frank, 2005. "On Kuhn's Hungarian Method—A tribute from Hungary," Naval Research Logistics (NRL), John Wiley & Sons, vol. 52(1), pages 2-5, February.
    3. Amit Kumar & Anila Gupta, 2013. "Mehar’s methods for fuzzy assignment problems with restrictions," Fuzzy Information and Engineering, Springer, vol. 5(1), pages 27-44, March.
    4. Nisse, Nicolas & Salch, Alexandre & Weber, Valentin, 2023. "Recovery of disrupted airline operations using k-maximum matching in graphs," European Journal of Operational Research, Elsevier, vol. 309(3), pages 1061-1072.
    5. Parvin Ahmadi & Iman Gholampour & Mahmoud Tabandeh, 2018. "Cluster-based sparse topical coding for topic mining and document clustering," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 12(3), pages 537-558, September.
    6. García Márquez, Fausto Pedro & Peco Chacón, Ana María, 2020. "A review of non-destructive testing on wind turbines blades," Renewable Energy, Elsevier, vol. 161(C), pages 998-1010.
    7. Bachtenkirch, David & Bock, Stefan, 2022. "Finding efficient make-to-order production and batch delivery schedules," European Journal of Operational Research, Elsevier, vol. 297(1), pages 133-152.
    8. Omar Zatarain & Jesse Yoe Rumbo-Morales & Silvia Ramos-Cabral & Gerardo Ortíz-Torres & Felipe d. J. Sorcia-Vázquez & Iván Guillén-Escamilla & Juan Carlos Mixteco-Sánchez, 2023. "A Method for Perception and Assessment of Semantic Textual Similarities in English," Mathematics, MDPI, vol. 11(12), pages 1-20, June.
    9. Chenchen Ma & Jing Ouyang & Gongjun Xu, 2023. "Learning Latent and Hierarchical Structures in Cognitive Diagnosis Models," Psychometrika, Springer;The Psychometric Society, vol. 88(1), pages 175-207, March.
    10. Winker, Peter, 2023. "Visualizing Topic Uncertainty in Topic Modelling," VfS Annual Conference 2023 (Regensburg): Growth and the "sociale Frage" 277584, Verein für Socialpolitik / German Economic Association.
    11. Tran Hoang Hai, 2020. "Estimation of volatility causality in structural autoregressions with heteroskedasticity using independent component analysis," Statistical Papers, Springer, vol. 61(1), pages 1-16, February.
    12. P. Senthil Kumar & R. Jahir Hussain, 2016. "A Simple Method for Solving Fully Intuitionistic Fuzzy Real Life Assignment Problem," International Journal of Operations Research and Information Systems (IJORIS), IGI Global, vol. 7(2), pages 39-61, April.
    13. Caplin, Andrew & Leahy, John, 2020. "Comparative statics in markets for indivisible goods," Journal of Mathematical Economics, Elsevier, vol. 90(C), pages 80-94.
    14. Biró, Péter & Gudmundsson, Jens, 2021. "Complexity of finding Pareto-efficient allocations of highest welfare," European Journal of Operational Research, Elsevier, vol. 291(2), pages 614-628.
    15. Sallam, Gamal & Baroudi, Uthman, 2020. "A two-stage framework for fair autonomous robot deployment using virtual forces," Transportation Research Part A: Policy and Practice, Elsevier, vol. 141(C), pages 35-50.
    16. Péter Biró & Flip Klijn & Xenia Klimentova & Ana Viana, 2021. "Shapley-Scarf Housing Markets: Respecting Improvement, Integer Programming, and Kidney Exchange," Working Papers 1235, Barcelona School of Economics.
    17. Michal Brylinski, 2014. "eMatchSite: Sequence Order-Independent Structure Alignments of Ligand Binding Pockets in Protein Models," PLOS Computational Biology, Public Library of Science, vol. 10(9), pages 1-15, September.
    18. Chen, Bin & Yu, Songhao & Yu, Yang & Zhou, Yilin, 2020. "Acoustical damage detection of wind turbine blade using the improved incremental support vector data description," Renewable Energy, Elsevier, vol. 156(C), pages 548-557.
    19. Chiwei Yan & Helin Zhu & Nikita Korolko & Dawn Woodard, 2020. "Dynamic pricing and matching in ride‐hailing platforms," Naval Research Logistics (NRL), John Wiley & Sons, vol. 67(8), pages 705-724, December.
    20. Fanrong Xie & Anuj Sharma & Zuoan Li, 2022. "An alternate approach to solve two-level priority based assignment problem," Computational Optimization and Applications, Springer, vol. 81(2), pages 613-656, March.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:17:y:2024:i:8:p:1796-:d:1372611. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.