IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v9y2016i6p379-d70673.html
   My bibliography  Save this article

Representational Learning for Fault Diagnosis of Wind Turbine Equipment: A Multi-Layered Extreme Learning Machines Approach

Author

Listed:
  • Zhi-Xin Yang

    (Department of Electromechanical Engineering, Faculty of Science and Technology, University of Macau, Macau SAR 999078, China
    These authors contributed equally to this work.)

  • Xian-Bo Wang

    (Department of Electromechanical Engineering, Faculty of Science and Technology, University of Macau, Macau SAR 999078, China
    These authors contributed equally to this work.)

  • Jian-Hua Zhong

    (Department of Electromechanical Engineering, Faculty of Science and Technology, University of Macau, Macau SAR 999078, China)

Abstract

Reliable and quick response fault diagnosis is crucial for the wind turbine generator system (WTGS) to avoid unplanned interruption and to reduce the maintenance cost. However, the conditional data generated from WTGS operating in a tough environment is always dynamical and high-dimensional. To address these challenges, we propose a new fault diagnosis scheme which is composed of multiple extreme learning machines (ELM) in a hierarchical structure, where a forwarding list of ELM layers is concatenated and each of them is processed independently for its corresponding role. The framework enables both representational feature learning and fault classification. The multi-layered ELM based representational learning covers functions including data preprocessing, feature extraction and dimension reduction. An ELM based autoencoder is trained to generate a hidden layer output weight matrix, which is then used to transform the input dataset into a new feature representation. Compared with the traditional feature extraction methods which may empirically wipe off some “insignificant’ feature information that in fact conveys certain undiscovered important knowledge, the introduced representational learning method could overcome the loss of information content. The computed output weight matrix projects the high dimensional input vector into a compressed and orthogonally weighted distribution. The last single layer of ELM is applied for fault classification. Unlike the greedy layer wise learning method adopted in back propagation based deep learning (DL), the proposed framework does not need iterative fine-tuning of parameters. To evaluate its experimental performance, comparison tests are carried out on a wind turbine generator simulator. The results show that the proposed diagnostic framework achieves the best performance among the compared approaches in terms of accuracy and efficiency in multiple faults detection of wind turbines.

Suggested Citation

  • Zhi-Xin Yang & Xian-Bo Wang & Jian-Hua Zhong, 2016. "Representational Learning for Fault Diagnosis of Wind Turbine Equipment: A Multi-Layered Extreme Learning Machines Approach," Energies, MDPI, vol. 9(6), pages 1-17, May.
    • Handle: RePEc:gam:jeners:v:9:y:2016:i:6:p:379-:d:70673
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/9/6/379/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/9/6/379/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Amirat, Y. & Benbouzid, M.E.H. & Al-Ahmar, E. & Bensaker, B. & Turri, S., 2009. "A brief status on condition monitoring and fault diagnosis in wind energy conversion systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 13(9), pages 2629-2636, December.
    2. Wong, Pak Kin & Wong, Ka In & Vong, Chi Man & Cheung, Chun Shun, 2015. "Modeling and optimization of biodiesel engine performance using kernel-based extreme learning machine and cuckoo search," Renewable Energy, Elsevier, vol. 74(C), pages 640-647.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Muhammad Ali & Dae-Hee Son & Sang-Hee Kang & Soon-Ryul Nam, 2017. "An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy," Energies, MDPI, vol. 10(11), pages 1-24, November.
    2. Yuri Merizalde & Luis Hernández-Callejo & Oscar Duque-Perez & Víctor Alonso-Gómez, 2019. "Maintenance Models Applied to Wind Turbines. A Comprehensive Overview," Energies, MDPI, vol. 12(2), pages 1-41, January.
    3. Saari, Juhamatti & Odelius, Johan, 2018. "Detecting operation regimes using unsupervised clustering with infected group labelling to improve machine diagnostics and prognostics," Operations Research Perspectives, Elsevier, vol. 5(C), pages 232-244.
    4. Juan D. Velásquez & Lorena Cadavid & Carlos J. Franco, 2023. "Intelligence Techniques in Sustainable Energy: Analysis of a Decade of Advances," Energies, MDPI, vol. 16(19), pages 1-45, October.
    5. Hong Wang & Hongbin Wang & Guoqian Jiang & Jimeng Li & Yueling Wang, 2019. "Early Fault Detection of Wind Turbines Based on Operational Condition Clustering and Optimized Deep Belief Network Modeling," Energies, MDPI, vol. 12(6), pages 1-22, March.
    6. Antonio Lorenzo-Espejo & Alejandro Escudero-Santana & María-Luisa Muñoz-Díaz & Alicia Robles-Velasco, 2022. "Machine Learning-Based Analysis of a Wind Turbine Manufacturing Operation: A Case Study," Sustainability, MDPI, vol. 14(13), pages 1-25, June.
    7. Mingzhu Tang & Qi Zhao & Steven X. Ding & Huawei Wu & Linlin Li & Wen Long & Bin Huang, 2020. "An Improved LightGBM Algorithm for Online Fault Detection of Wind Turbine Gearboxes," Energies, MDPI, vol. 13(4), pages 1-16, February.

    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. Liu, W.Y. & Zhang, W.H. & Han, J.G. & Wang, G.F., 2012. "A new wind turbine fault diagnosis method based on the local mean decomposition," Renewable Energy, Elsevier, vol. 48(C), pages 411-415.
    2. Chen, Xuejun & Yang, Yongming & Cui, Zhixin & Shen, Jun, 2019. "Vibration fault diagnosis of wind turbines based on variational mode decomposition and energy entropy," Energy, Elsevier, vol. 174(C), pages 1100-1109.
    3. Izquierdo, J. & Márquez, A. Crespo & Uribetxebarria, J. & Erguido, A., 2020. "On the importance of assessing the operational context impact on maintenance management for life cycle cost of wind energy projects," Renewable Energy, Elsevier, vol. 153(C), pages 1100-1110.
    4. Ahmed Al-Ajmi & Yingzhao Wang & Siniša Djurović, 2021. "Wind Turbine Generator Controller Signals Supervised Machine Learning for Shaft Misalignment Fault Detection: A Doubly Fed Induction Generator Practical Case Study," Energies, MDPI, vol. 14(6), pages 1-15, March.
    5. Xueli An & Dongxiang Jiang, 2014. "Bearing fault diagnosis of wind turbine based on intrinsic time-scale decomposition frequency spectrum," Journal of Risk and Reliability, , vol. 228(6), pages 558-566, December.
    6. Simona Stojanova & Nina Cvar & Jurij Verhovnik & Nataša Božić & Jure Trilar & Andrej Kos & Emilija Stojmenova Duh, 2022. "Rural Digital Innovation Hubs as a Paradigm for Sustainable Business Models in Europe’s Rural Areas," Sustainability, MDPI, vol. 14(21), pages 1-20, November.
    7. Najafi, Gholamhassan & Ghobadian, Barat & Yusaf, Talal & Safieddin Ardebili, Seyed Mohammad & Mamat, Rizalman, 2015. "Optimization of performance and exhaust emission parameters of a SI (spark ignition) engine with gasoline–ethanol blended fuels using response surface methodology," Energy, Elsevier, vol. 90(P2), pages 1815-1829.
    8. Iftikhar Ahmad & Adil Sana & Manabu Kano & Izzat Iqbal Cheema & Brenno C. Menezes & Junaid Shahzad & Zahid Ullah & Muzammil Khan & Asad Habib, 2021. "Machine Learning Applications in Biofuels’ Life Cycle: Soil, Feedstock, Production, Consumption, and Emissions," Energies, MDPI, vol. 14(16), pages 1-27, August.
    9. Fan Zhang & Juchuan Dai & Deshun Liu & Linxing Li & Xin Long, 2019. "Investigation of the Pitch Load of Large-Scale Wind Turbines Using Field SCADA Data," Energies, MDPI, vol. 12(3), pages 1-20, February.
    10. Chen, Jinglong & Pan, Jun & Li, Zipeng & Zi, Yanyang & Chen, Xuefeng, 2016. "Generator bearing fault diagnosis for wind turbine via empirical wavelet transform using measured vibration signals," Renewable Energy, Elsevier, vol. 89(C), pages 80-92.
    11. Liang, Jinping & Zhang, Ke & Al-Durra, Ahmed & Zhou, Daming, 2020. "A novel fault diagnostic method in power converters for wind power generation system," Applied Energy, Elsevier, vol. 266(C).
    12. Hui Wang & Jingxuan Sun & Jianbo Sun & Jilong Wang, 2017. "Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models," Energies, MDPI, vol. 10(10), pages 1-13, October.
    13. Peng Guo & Nan Bai, 2011. "Wind Turbine Gearbox Condition Monitoring with AAKR and Moving Window Statistic Methods," Energies, MDPI, vol. 4(11), pages 1-17, November.
    14. Wakui, Tetsuya & Yokoyama, Ryohei, 2013. "Wind speed sensorless performance monitoring based on operating behavior for stand-alone vertical axis wind turbine," Renewable Energy, Elsevier, vol. 53(C), pages 49-59.
    15. Abedin, M.J. & Kalam, M.A. & Masjuki, H.H. & Sabri, M.F.M. & Rahman, S.M. Ashrafur & Sanjid, A. & Fattah, I.M. Rizwanul, 2016. "Production of biodiesel from a non-edible source and study of its combustion, and emission characteristics: A comparative study with B5," Renewable Energy, Elsevier, vol. 88(C), pages 20-29.
    16. Mohamed Benbouzid & Tarek Berghout & Nur Sarma & Siniša Djurović & Yueqi Wu & Xiandong Ma, 2021. "Intelligent Condition Monitoring of Wind Power Systems: State of the Art Review," Energies, MDPI, vol. 14(18), pages 1-33, September.
    17. Faiz, Jawad & Moosavi, S.M.M., 2016. "Eccentricity fault detection – From induction machines to DFIG—A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 55(C), pages 169-179.
    18. Gharehghani, Ayatallah & Mirsalim, Mostafa & Hosseini, Reza, 2017. "Effects of waste fish oil biodiesel on diesel engine combustion characteristics and emission," Renewable Energy, Elsevier, vol. 101(C), pages 930-936.
    19. Yang, Zhimin & Chai, Yi, 2016. "A survey of fault diagnosis for onshore grid-connected converter in wind energy conversion systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 66(C), pages 345-359.
    20. Artigao, Estefania & Martín-Martínez, Sergio & Honrubia-Escribano, Andrés & Gómez-Lázaro, Emilio, 2018. "Wind turbine reliability: A comprehensive review towards effective condition monitoring development," Applied Energy, Elsevier, vol. 228(C), pages 1569-1583.

    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:9:y:2016:i:6:p:379-:d:70673. 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.