IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v17y2024i16p4098-d1458537.html
   My bibliography  Save this article

An Unsupervised Fault Warning Method Based on Hybrid Information Gain and a Convolutional Autoencoder for Steam Turbines

Author

Listed:
  • Jinxing Zhai

    (Tongliao Huolinhe Pithead Power Generation Co., Ltd., State Power Investment Inner Mongolia Energy Co., Ltd., HuoLinguole 029200, China)

  • Jing Ye

    (Shanghai Power Equipment Research Institue Co., Ltd., Shanghai 200240, China)

  • Yue Cao

    (Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education, School of Energy and Environment, Southeast University, Nanjing 210096, China)

Abstract

Renewable energy accommodation in power grids leads to frequent load changes in power plants. Sensitive turbine fault monitoring technology is critical to ensure the stable operation of the power system. Existing techniques do not use information sufficiently and are not sensitive to early fault signs. To solve this problem, an unsupervised fault warning method based on hybrid information gain and a convolutional autoencoder (CAE) for turbine intermediate flux is proposed. A high-precision intermediate-stage flux prediction model is established using the CAE. The hybrid information gain calculation method is proposed to filter the features of multi-dimensional sensors. The Hampel filter for time series outlier detection is introduced to deal with factors such as sensor faults and noise. The proposed method achieves the highest fault diagnosis accuracy through experiments on real data compared to traditional methods. Real data experiments show that the proposed method relatively improves the diagnostic accuracy by an average of 2.12% compared to the gate recurrent unit networks, long short-term memory networks, and other traditional models. Meanwhile, the proposed hybrid information gain can effectively improve the detection accuracy of the traditional models, with a maximum of 1.89% relative accuracy improvement. The proposed method is noteworthy for its superiority and applicability.

Suggested Citation

  • Jinxing Zhai & Jing Ye & Yue Cao, 2024. "An Unsupervised Fault Warning Method Based on Hybrid Information Gain and a Convolutional Autoencoder for Steam Turbines," Energies, MDPI, vol. 17(16), pages 1-17, August.
    • Handle: RePEc:gam:jeners:v:17:y:2024:i:16:p:4098-:d:1458537
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/17/16/4098/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/17/16/4098/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Huang, Bo & Peng, Yun-Hong & Hu, Li-Sheng & Liang, Xiao-Chi, 2024. "Incipient fault detection approach based on piecewise linear shape-based global embedding for steam turbine plants," Applied Energy, Elsevier, vol. 370(C).
    2. Li, Xingshuo & Liu, Jinfu & Bai, Mingliang & Li, Jiajia & Li, Xianling & Yan, Peigang & Yu, Daren, 2021. "An LSTM based method for stage performance degradation early warning with consideration of time-series information," Energy, Elsevier, vol. 226(C).
    3. Chen, Chen & Liu, Ming & Li, Mengjie & Wang, Yu & Wang, Chaoyang & Yan, Junjie, 2024. "Digital twin modeling and operation optimization of the steam turbine system of thermal power plants," Energy, Elsevier, vol. 290(C).
    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. Salman Khalid & Muhammad Muzammil Azad & Heung Soo Kim, 2025. "A Generalized Autonomous Power Plant Fault Detection Model Using Deep Feature Extraction and Ensemble Machine Learning," Mathematics, MDPI, vol. 13(3), pages 1-19, January.

    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. Wang, Pengfei & Zhang, Jiaxuan & Wan, Jiashuang & Wu, Shifa, 2022. "A fault diagnosis method for small pressurized water reactors based on long short-term memory networks," Energy, Elsevier, vol. 239(PC).
    2. Ming Cheng & Qiang Zhang & Yue Cao, 2024. "An Early Warning Model for Turbine Intermediate-Stage Flux Failure Based on an Improved HEOA Algorithm Optimizing DMSE-GRU Model," Energies, MDPI, vol. 17(15), pages 1-16, July.
    3. Bai, Mingliang & Yang, Xusheng & Liu, Jinfu & Liu, Jiao & Yu, Daren, 2021. "Convolutional neural network-based deep transfer learning for fault detection of gas turbine combustion chambers," Applied Energy, Elsevier, vol. 302(C).
    4. Xin, Yong-Lin & Zhao, Tian & Sun, Qing-Han & Chen, Qun, 2024. "An efficient yet accurate optimization algorithm for thermal systems integrating heat current method and generalized Benders decomposition," Energy, Elsevier, vol. 304(C).
    5. Long, Zhenhua & Bai, Mingliang & Ren, Minghao & Liu, Jinfu & Yu, Daren, 2023. "Fault detection and isolation of aeroengine combustion chamber based on unscented Kalman filter method fusing artificial neural network," Energy, Elsevier, vol. 272(C).
    6. Chen, Chen & Zhao, Chenyu & Liu, Ming & Wang, Chaoyang & Yan, Junjie, 2024. "Enhancing the load cycling rate of subcritical coal-fired power plants: A novel control strategy based on data-driven feedwater active regulation," Energy, Elsevier, vol. 312(C).
    7. Wojciech Włodarski & Marian Piwowarski, 2024. "A Model Modification for a Microturbine Set with Partial Admission Stages," Energies, MDPI, vol. 17(8), pages 1-16, April.
    8. Xu, Zifei & Bashir, Musa & Yang, Yang & Wang, Xinyu & Wang, Jin & Ekere, Nduka & Li, Chun, 2022. "Multisensory collaborative damage diagnosis of a 10 MW floating offshore wind turbine tendons using multi-scale convolutional neural network with attention mechanism," Renewable Energy, Elsevier, vol. 199(C), pages 21-34.

    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:16:p:4098-:d:1458537. 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.