IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v15y2022i2p605-d725473.html
   My bibliography  Save this article

Degradation Trend Prediction of Pumped Storage Unit Based on MIC-LGBM and VMD-GRU Combined Model

Author

Listed:
  • Peng Chen

    (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China)

  • Yumin Deng

    (China Yangtze Three Gorges Group Co. Ltd., Wuhan 430010, China)

  • Xuegui Zhang

    (China Yangtze Three Gorges Group Co. Ltd., Wuhan 430010, China)

  • Li Ma

    (China Yangtze Three Gorges Group Co. Ltd., Wuhan 430010, China)

  • Yaoliang Yan

    (China Yangtze Three Gorges Group Co. Ltd., Wuhan 430010, China)

  • Yifan Wu

    (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China)

  • Chaoshun Li

    (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China)

Abstract

The harsh operating environment aggravates the degradation of pumped storage units (PSUs). Degradation trend prediction (DTP) provides important support for the condition-based maintenance of PSUs. However, the complexity of the performance degradation index (PDI) sequence poses a severe challenge of the reliability of DTP. Additionally, the accuracy of healthy model is often ignored, resulting in an unconvincing PDI. To solve these problems, a combined DTP model that integrates the maximal information coefficient (MIC), light gradient boosting machine (LGBM), variational mode decomposition (VMD) and gated recurrent unit (GRU) is proposed. Firstly, MIC-LGBM is utilized to generate a high-precision healthy model. MIC is applied to select the working parameters with the most relevance, then the LGBM is utilized to construct the healthy model. Afterwards, a performance degradation index (PDI) is generated based on the LGBM healthy model and monitoring data. Finally, the VMD-GRU prediction model is designed to achieve precise DTP under the complex PDI sequence. The proposed model is verified by applying it to a PSU located in Zhejiang province, China. The results reveal that the proposed model achieves the highest precision healthy model and the best prediction performance compared with other comparative models. The absolute average ( | A V G | ) and standard deviation ( S T D ) of fitting errors are reduced to 0.0275 and 0.9245, and the RMSE, MAE, and R 2 are 0.00395, 0.0032, and 0.9226 respectively, on average for two operating conditions.

Suggested Citation

  • Peng Chen & Yumin Deng & Xuegui Zhang & Li Ma & Yaoliang Yan & Yifan Wu & Chaoshun Li, 2022. "Degradation Trend Prediction of Pumped Storage Unit Based on MIC-LGBM and VMD-GRU Combined Model," Energies, MDPI, vol. 15(2), pages 1-21, January.
    • Handle: RePEc:gam:jeners:v:15:y:2022:i:2:p:605-:d:725473
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/15/2/605/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/15/2/605/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Lai, Xinjie & Li, Chaoshun & Zhou, Jianzhong & Zhang, Nan, 2019. "Multi-objective optimization of the closure law of guide vanes for pumped storage units," Renewable Energy, Elsevier, vol. 139(C), pages 302-312.
    2. Guangyi Wu & Xiangxin Shao & Hong Jiang & Shaoxin Chen & Yibing Zhou & Hongyang Xu, 2020. "Control Strategy of the Pumped Storage Unit to Deal with the Fluctuation of Wind and Photovoltaic Power in Microgrid," Energies, MDPI, vol. 13(2), pages 1-23, January.
    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. Liu, Baonan & Zhou, Jianzhong & Xu, Yanhe & Lai, Xinjie & Shi, Yousong & Li, Mengyao, 2022. "An optimization decision-making framework for the optimal operation strategy of pumped storage hydropower system under extreme conditions," Renewable Energy, Elsevier, vol. 182(C), pages 254-273.
    2. Li, Chaoshun & Tang, Geng & Xue, Xiaoming & Chen, Xinbiao & Wang, Ruoheng & Zhang, Chu, 2020. "The short-term interval prediction of wind power using the deep learning model with gradient descend optimization," Renewable Energy, Elsevier, vol. 155(C), pages 197-211.
    3. Lei, Liuwei & Li, Feng & Kheav, Kimleng & Jiang, Wei & Luo, Xingqi & Patelli, Edoardo & Xu, Beibei & Chen, Diyi, 2021. "A start-up optimization strategy of a hydroelectric generating system: From a symmetrical structure to asymmetric structure on diversion pipes," Renewable Energy, Elsevier, vol. 180(C), pages 1148-1165.
    4. Xin Xia & Jie Ji & Chao-shun Li & Xiaoming Xue & Xiaolu Wang & Chu Zhang, 2019. "Multiobjective Optimal Control for Hydraulic Turbine Governing System Based on an Improved MOGWO Algorithm," Complexity, Hindawi, vol. 2019, pages 1-14, May.
    5. Jiawei Ye & Wei Zeng & Zhigao Zhao & Jiebin Yang & Jiandong Yang, 2020. "Optimization of Pump Turbine Closing Operation to Minimize Water Hammer and Pulsating Pressures During Load Rejection," Energies, MDPI, vol. 13(4), pages 1-18, February.
    6. Wang, Wenjie & Tai, Geyuan & Pei, Ji & Pavesi, Giorgio & Yuan, Shouqi, 2022. "Numerical investigation of the effect of the closure law of wicket gates on the transient characteristics of pump-turbine in pump mode," Renewable Energy, Elsevier, vol. 194(C), pages 719-733.
    7. Zhang, Yuquan & Sun, Jie & Zheng, Yuan & Ge, Xinfeng & Peng, Xuyi & Hong, Yunlai & Fernandez-Rodriguez, E., 2022. "Unsteady characteristics of lubricating oil in thrust bearing tank under different rotational speeds in pumped storage power station," Renewable Energy, Elsevier, vol. 201(P1), pages 904-915.
    8. Xin Wu & Yanhe Xu & Jie Liu & Cong Lv & Jianzhong Zhou & Qing Zhang, 2019. "Characteristics Analysis and Fuzzy Fractional-Order PID Parameter Optimization for Primary Frequency Modulation of a Pumped Storage Unit Based on a Multi-Objective Gravitational Search Algorithm," Energies, MDPI, vol. 13(1), pages 1-20, December.
    9. Lai, Xinjie & Li, Chaoshun & Zhou, Jianzhong & Zhang, Yongchuan & Li, Yonggang, 2020. "A multi-objective optimization strategy for the optimal control scheme of pumped hydropower systems under successive load rejections," Applied Energy, Elsevier, vol. 261(C).
    10. Li, Chaoshun & Wang, Wenxiao & Wang, Jinwen & Chen, Deshu, 2019. "Network-constrained unit commitment with RE uncertainty and PHES by using a binary artificial sheep algorithm," Energy, Elsevier, vol. 189(C).
    11. Zhao, Zhigao & Yang, Jiandong & Huang, Yifan & Yang, Weijia & Ma, Weichao & Hou, Liangyu & Chen, Man, 2021. "Improvement of regulation quality for hydro-dominated power system: quantifying oscillation characteristic and multi-objective optimization," Renewable Energy, Elsevier, vol. 168(C), pages 606-631.
    12. Huang, Yifan & Yang, Weijia & Liao, Yiwen & Zhao, Zhigao & Ma, Weichao & Yang, Jiebin & Yang, Jiandong, 2022. "Improved transfer function method for flexible simulation of hydraulic-mechanical-electrical transient processes of hydro-power plants," Renewable Energy, Elsevier, vol. 196(C), pages 390-404.

    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:15:y:2022:i:2:p:605-:d:725473. 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.