IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v17y2024i5p982-d1342099.html
   My bibliography  Save this article

Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms

Author

Listed:
  • Bridger Altice

    (Information Dynamics Lab., Electrical and Computer Engineering Department, Utah State University, Logan, UT 84322, USA)

  • Edwin Nazario

    (Machine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USA)

  • Mason Davis

    (Machine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USA)

  • Mohammad Shekaramiz

    (Machine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USA)

  • Todd K. Moon

    (Information Dynamics Lab., Electrical and Computer Engineering Department, Utah State University, Logan, UT 84322, USA)

  • Mohammad A. S. Masoum

    (Machine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USA)

Abstract

Wind turbine blade maintenance is expensive, dangerous, time-consuming, and prone to misdiagnosis. A potential solution to aid preventative maintenance is using deep learning and drones for inspection and early fault detection. In this research, five base deep learning architectures are investigated for anomaly detection on wind turbine blades, including Xception, Resnet-50, AlexNet, and VGG-19, along with a custom convolutional neural network. For further analysis, transfer learning approaches were also proposed and developed, utilizing these architectures as the feature extraction layers. In order to investigate model performance, a new dataset containing 6000 RGB images was created, making use of indoor and outdoor images of a small wind turbine with healthy and damaged blades. Each model was tuned using different layers, image augmentations, and hyperparameter tuning to achieve optimal performance. The results showed that the proposed Transfer Xception outperformed other architectures by attaining 99.92% accuracy on the test data of this dataset. Furthermore, the performance of the investigated models was compared on a dataset containing faulty and healthy images of large-scale wind turbine blades. In this case, our results indicated that the best-performing model was also the proposed Transfer Xception, which achieved 100% accuracy on the test data. These accuracies show promising results in the adoption of machine learning for wind turbine blade fault identification.

Suggested Citation

  • Bridger Altice & Edwin Nazario & Mason Davis & Mohammad Shekaramiz & Todd K. Moon & Mohammad A. S. Masoum, 2024. "Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms," Energies, MDPI, vol. 17(5), pages 1-21, February.
  • Handle: RePEc:gam:jeners:v:17:y:2024:i:5:p:982-:d:1342099
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/17/5/982/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/17/5/982/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Cristian Velandia-Cardenas & Yolanda Vidal & Francesc Pozo, 2021. "Wind Turbine Fault Detection Using Highly Imbalanced Real SCADA Data," Energies, MDPI, vol. 14(6), pages 1-26, March.
    2. Ahmed Samour & Usman Mehmood & Magdalena Radulescu & Radu Alexandru Budu & Rares Mihai Nitu, 2023. "Examining the Role of Renewable Energy, Technological Innovation, and the Insurance Market in Environmental Sustainability in the United States: A Step toward COP26 Targets," Energies, MDPI, vol. 16(17), pages 1-15, August.
    3. Xu, Xiaofeng & Wei, Zhifei & Ji, Qiang & Wang, Chenglong & Gao, Guowei, 2019. "Global renewable energy development: Influencing factors, trend predictions and countermeasures," Resources Policy, Elsevier, vol. 63(C), pages 1-1.
    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. Camila Correa-Jullian & Sergio Cofre-Martel & Gabriel San Martin & Enrique Lopez Droguett & Gustavo de Novaes Pires Leite & Alexandre Costa, 2022. "Exploring Quantum Machine Learning and Feature Reduction Techniques for Wind Turbine Pitch Fault Detection," Energies, MDPI, vol. 15(8), pages 1-29, April.
    2. Feng Dong & Yuling Pan, 2020. "Evolution of Renewable Energy in BRI Countries: A Combined Econometric and Decomposition Approach," IJERPH, MDPI, vol. 17(22), pages 1-18, November.
    3. Jorge Maldonado-Correa & Marcelo Valdiviezo-Condolo & Estefanía Artigao & Sergio Martín-Martínez & Emilio Gómez-Lázaro, 2024. "Classification of Highly Imbalanced Supervisory Control and Data Acquisition Data for Fault Detection of Wind Turbine Generators," Energies, MDPI, vol. 17(7), pages 1-20, March.
    4. Yijing Chu & Yingying Wang & Zucheng Zhang & Shengli Dai, 2022. "Decoupling of Economic Growth and Industrial Water Use in Hubei Province: From an Ecological–Economic Interaction Perspective," Sustainability, MDPI, vol. 14(20), pages 1-15, October.
    5. Liobikienė, Genovaitė & Miceikienė, Astrida, 2022. "The role of financial, social and informational mechanisms on willingness to use bioenergy," Renewable Energy, Elsevier, vol. 194(C), pages 21-27.
    6. Dogan, Eyup & Chishti, Muhammad Zubair & Karimi Alavijeh, Nooshin & Tzeremes, Panayiotis, 2022. "The roles of technology and Kyoto Protocol in energy transition towards COP26 targets: Evidence from the novel GMM-PVAR approach for G-7 countries," Technological Forecasting and Social Change, Elsevier, vol. 181(C).
    7. Ankrah, Isaac & Lin, Boqiang, 2020. "Renewable energy development in Ghana: Beyond potentials and commitment," Energy, Elsevier, vol. 198(C).
    8. Jun Hao & Xiaolei Sun & Qianqian Feng, 2020. "A Novel Ensemble Approach for the Forecasting of Energy Demand Based on the Artificial Bee Colony Algorithm," Energies, MDPI, vol. 13(3), pages 1-25, January.
    9. Ana Rita Nunes & Hugo Morais & Alberto Sardinha, 2021. "Use of Learning Mechanisms to Improve the Condition Monitoring of Wind Turbine Generators: A Review," Energies, MDPI, vol. 14(21), pages 1-22, November.
    10. Depraiter, Lisa & Goutte, Stephane, 2023. "The role and challenges of rare earths in the energy transition," Resources Policy, Elsevier, vol. 86(PB).
    11. Adaiton Oliveira-Filho & Monelle Comeau & James Cave & Charbel Nasr & Pavel Côté & Antoine Tahan, 2024. "Wind Turbine SCADA Data Imbalance: A Review of Its Impact on Health Condition Analyses and Mitigation Strategies," Energies, MDPI, vol. 18(1), pages 1-23, December.
    12. Karolis Andriuškevičius & Dalia Štreimikienė, 2022. "Energy M&A Market in the Baltic States Analyzed through the Lens of Sustainable Development," Energies, MDPI, vol. 15(21), pages 1-21, October.
    13. Ruozhen Qiu & Shunpeng Shi & Yue Sun, 2019. "A p -Robust Green Supply Chain Network Design Model under Uncertain Carbon Price and Demand," Sustainability, MDPI, vol. 11(21), pages 1-22, October.
    14. Zhang, Chenxi & Zhou, Dequn & Wang, Qunwei & Ding, Hao & Zhao, Siqi, 2022. "Will fiscal decentralization stimulate renewable energy development? Evidence from China," Energy Policy, Elsevier, vol. 164(C).
    15. Zhang, Qianxiao & Shah, Syed Ale Raza & Yang, Ling, 2022. "Modeling the effect of disaggregated renewable energies on ecological footprint in E5 economies: Do economic growth and R&D matter?," Applied Energy, Elsevier, vol. 310(C).
    16. Mohd Ziaur Rehman & Shabeer Khan & Uzair Abdullah Khan & Wadi B. Alonazi & Abul Ala Noman, 2023. "How Do Global Uncertainties Spillovers Affect Leading Renewable Energy Indices? Evidence from the Network Connectedness Approach," Sustainability, MDPI, vol. 15(18), pages 1-15, September.
    17. Xu, Xiaofeng & Liu, Zhiting & Liu, Wenzhi & Pei, Chuantao & Wu, Xiangfan & Nie, Zhengya, 2024. "A sustainable development benchmarking framework for energy companies based on topic mining and knowledge graph: The case of oil and gas industry," Renewable and Sustainable Energy Reviews, Elsevier, vol. 196(C).
    18. Silva, Nuno & Fuinhas, José Alberto & Koengkan, Matheus, 2021. "Assessing the advancement of new renewable energy sources in Latin American and Caribbean countries," Energy, Elsevier, vol. 237(C).
    19. Xiaoyan Peng & Xin Guan & Yanzhao Zeng & Jiali Zhang, 2024. "Artificial Intelligence-Driven Multi-Energy Optimization: Promoting Green Transition of Rural Energy Planning and Sustainable Energy Economy," Sustainability, MDPI, vol. 16(10), pages 1-20, May.
    20. Junshuai Yan & Yongqian Liu & Xiaoying Ren, 2023. "An Early Fault Detection Method for Wind Turbine Main Bearings Based on Self-Attention GRU Network and Binary Segmentation Changepoint Detection Algorithm," Energies, MDPI, vol. 16(10), pages 1-23, May.

    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:5:p:982-:d:1342099. 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.