IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v254y2022ipcs0360544222013433.html
   My bibliography  Save this article

Integrated graph deep learning framework for flow field reconstruction and performance prediction of turbomachinery

Author

Listed:
  • Li, Jinxing
  • Liu, Tianyuan
  • Wang, Yuqi
  • Xie, Yonghui

Abstract

The performance and reliability of turbomachinery directly affect the efficiency and safety of energy conversion systems. A dual graph neural network (DGNN) for turbomachinery flow field reconstruction and performance prediction is proposed, which utilizes flow field data at grid vertices and characterizes the neighborhood relationships of grids through the adjacency matrix. Different from previous work, this work extends deep learning methods to the reconstruction of global turbomachinery fields defined on arbitrary structured/unstructured grids. The flow field reconstruction and performance prediction of low aspect ratio rotors are used to verify the generalizability of DGNN. The proposed method can not only accurately predict performance parameters, but also achieve excellent performance in flow field reconstruction. The superiority of DGNN over the artificial neural network (ANN) in flow field reconstruction is clarified. The optimal GNN operator with the highest accuracy and lowest computation costs is obtained as SAGE. A well-trained DGNN can give the flow field distribution as well as the performance of turbines within 0.05 s. The proposed approach could be a real-time simulation and analysis approach to assist turbomachinery design and optimization. It may provide an efficient solution for establishing the digital twin system of turbomachinery in the future.

Suggested Citation

  • Li, Jinxing & Liu, Tianyuan & Wang, Yuqi & Xie, Yonghui, 2022. "Integrated graph deep learning framework for flow field reconstruction and performance prediction of turbomachinery," Energy, Elsevier, vol. 254(PC).
    • Handle: RePEc:eee:energy:v:254:y:2022:i:pc:s0360544222013433
    DOI: 10.1016/j.energy.2022.124440
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544222013433
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.energy.2022.124440?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Park, Junyoung & Park, Jinkyoo, 2019. "Physics-induced graph neural network: An application to wind-farm power estimation," Energy, Elsevier, vol. 187(C).
    2. Wang, Yuqi & Du, Qiuwan & Li, Yunzhu & Zhang, Di & Xie, Yonghui, 2022. "Field reconstruction and off-design performance prediction of turbomachinery in energy systems based on deep learning techniques," Energy, Elsevier, vol. 238(PB).
    3. Kim, Do-Yeop & Kim, You-Taek, 2017. "Preliminary design and performance analysis of a radial inflow turbine for ocean thermal energy conversion," Renewable Energy, Elsevier, vol. 106(C), pages 255-263.
    4. Jankowski, Marcin & Klonowicz, Piotr & Borsukiewicz, Aleksandra, 2021. "Multi-objective optimization of an ORC power plant using one-dimensional design of a radial-inflow turbine with backswept rotor blades," Energy, Elsevier, vol. 237(C).
    5. Song, Yanping & Sun, Xiaojing & Huang, Diangui, 2017. "Preliminary design and performance analysis of a centrifugal turbine for Organic Rankine Cycle (ORC) applications," Energy, Elsevier, vol. 140(P1), pages 1239-1251.
    6. Larwood, Scott & van Dam, C.P. & Schow, Daniel, 2014. "Design studies of swept wind turbine blades," Renewable Energy, Elsevier, vol. 71(C), pages 563-571.
    7. Huang, Renfang & Zhang, Zhen & Zhang, Wei & Mou, Jiegang & Zhou, Peijian & Wang, Yiwei, 2020. "Energy performance prediction of the centrifugal pumps by using a hybrid neural network," Energy, Elsevier, vol. 213(C).
    8. Liu, Zuming & Karimi, Iftekhar A., 2020. "Gas turbine performance prediction via machine learning," Energy, Elsevier, vol. 192(C).
    9. Kadhim, Hakim T. & Rona, Aldo, 2018. "Design optimization workflow and performance analysis for contoured endwalls of axial turbines," Energy, Elsevier, vol. 149(C), pages 875-889.
    10. de Oliveira Nogueira, Tiago & Palacio, Gilderlânio Barbosa Alves & Braga, Fabrício Damasceno & Maia, Pedro Paulo Nunes & de Moura, Elineudo Pinho & de Andrade, Carla Freitas & Rocha, Paulo Alexandre C, 2022. "Imbalance classification in a scaled-down wind turbine using radial basis function kernel and support vector machines," Energy, Elsevier, vol. 238(PC).
    11. Tang, Xinzi & Wang, Zhe & Xiao, Peng & Peng, Ruitao & Liu, Xiongwei, 2020. "Uncertainty quantification based optimization of centrifugal compressor impeller for aerodynamic robustness under stochastic operational conditions," Energy, Elsevier, vol. 195(C).
    12. Al Jubori, Ayad M. & Al-Dadah, Raya & Mahmoud, Saad, 2017. "Performance enhancement of a small-scale organic Rankine cycle radial-inflow turbine through multi-objective optimization algorithm," Energy, Elsevier, vol. 131(C), pages 297-311.
    13. Saeed, Muhammad & Kim, Man-Hoe, 2018. "Analysis of a recompression supercritical carbon dioxide power cycle with an integrated turbine design/optimization algorithm," Energy, Elsevier, vol. 165(PA), pages 93-111.
    14. Sun, Hongchuang & Qin, Jiang & Hung, Tzu-Chen & Huang, Hongyan & Yan, Peigang, 2019. "Performance analysis of low speed axial impulse turbine using two type nozzles for small-scale organic Rankine cycle," Energy, Elsevier, vol. 169(C), pages 1139-1152.
    15. Witanowski, Ł. & Klonowicz, P. & Lampart, P. & Suchocki, T. & Jędrzejewski, Ł. & Zaniewski, D. & Klimaszewski, P., 2020. "Optimization of an axial turbine for a small scale ORC waste heat recovery system," Energy, Elsevier, vol. 205(C).
    16. Gao, Lei & Liu, Tianyuan & Cao, Tao & Hwang, Yunho & Radermacher, Reinhard, 2021. "Comparing deep learning models for multi energy vectors prediction on multiple types of building," Applied Energy, Elsevier, vol. 301(C).
    17. Han, Wanlong & Zhang, Yifan & Li, Hongzhi & Yao, Mingyu & Wang, Yueming & Feng, Zhenping & Zhou, Dong & Dan, Guangju, 2019. "Aerodynamic design of the high pressure and low pressure axial turbines for the improved coal-fired recompression SCO2 reheated Brayton cycle," Energy, Elsevier, vol. 179(C), pages 442-453.
    18. Wang, Xiaojing & Zou, Zhengping, 2019. "Uncertainty analysis of impact of geometric variations on turbine blade performance," Energy, Elsevier, vol. 176(C), pages 67-80.
    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. Li, Jinxing & Li, Yunzhu & Liu, Tianyuan & Zhang, Di & Xie, Yonghui, 2023. "Multi-fidelity graph neural network for flow field data fusion of turbomachinery," Energy, Elsevier, vol. 285(C).
    2. Cheng, Hongzhi & Zhou, Chuangxin & Lu, Xingen & Zhao, Shengfeng & Han, Ge & Yang, Chengwu, 2023. "Robust aerodynamic optimization and design exploration of a wide-chord transonic fan under geometric and operational uncertainties," Energy, Elsevier, vol. 278(PB).
    3. Cheng, Hongzhi & Li, Ziliang & Duan, Penghao & Lu, Xingen & Zhao, Shengfeng & Zhang, Yanfeng, 2023. "Robust optimization and uncertainty quantification of a micro axial compressor for unmanned aerial vehicles," Applied Energy, Elsevier, vol. 352(C).
    4. Li, Jinxing & Liu, Tianyuan & Zhu, Guangya & Li, Yunzhu & Xie, Yonghui, 2023. "Uncertainty quantification and aerodynamic robust optimization of turbomachinery based on graph learning methods," Energy, Elsevier, vol. 273(C).
    5. Hao, Yichen & Xie, Xinyu & Zhao, Pu & Wang, Xiaofang & Ding, Jiaqi & Xie, Rong & Liu, Haitao, 2023. "Forecasting three-dimensional unsteady multi-phase flow fields in the coal-supercritical water fluidized bed reactor via graph neural networks," Energy, Elsevier, vol. 282(C).

    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, Yuqi & Liu, Tianyuan & Meng, Yue & Zhang, Di & Xie, Yonghui, 2022. "Integrated optimization for design and operation of turbomachinery in a solar-based Brayton cycle based on deep learning techniques," Energy, Elsevier, vol. 252(C).
    2. Li, Jinxing & Liu, Tianyuan & Zhu, Guangya & Li, Yunzhu & Xie, Yonghui, 2023. "Uncertainty quantification and aerodynamic robust optimization of turbomachinery based on graph learning methods," Energy, Elsevier, vol. 273(C).
    3. Witanowski, Łukasz & Ziółkowski, Paweł & Klonowicz, Piotr & Lampart, Piotr, 2023. "A hybrid approach to optimization of radial inflow turbine with principal component analysis," Energy, Elsevier, vol. 272(C).
    4. Du, Qiuwan & Yang, Like & Li, Liangliang & Liu, Tianyuan & Zhang, Di & Xie, Yonghui, 2022. "Aerodynamic design and optimization of blade end wall profile of turbomachinery based on series convolutional neural network," Energy, Elsevier, vol. 244(PA).
    5. Wang, Yuqi & Du, Qiuwan & Li, Yunzhu & Zhang, Di & Xie, Yonghui, 2022. "Field reconstruction and off-design performance prediction of turbomachinery in energy systems based on deep learning techniques," Energy, Elsevier, vol. 238(PB).
    6. Wang, Qi & Yang, Li & Rao, Yu, 2021. "Establishment of a generalizable model on a small-scale dataset to predict the surface pressure distribution of gas turbine blades," Energy, Elsevier, vol. 214(C).
    7. Li, Yunzhu & Liu, Tianyuan & Wang, Yuqi & Xie, Yonghui, 2022. "Deep learning based real-time energy extraction system modeling for flapping foil," Energy, Elsevier, vol. 246(C).
    8. Jiang, Chiju & Zhang, Weihao & Li, Ya & Li, Lele & Wang, Yufan & Huang, Dongming, 2023. "Multi-scale Pix2Pix network for high-fidelity prediction of adiabatic cooling effectiveness in turbine cascade," Energy, Elsevier, vol. 265(C).
    9. Peng Song & Jinju Sun & Shengyuan Wang & Xuesong Wang, 2022. "Multipoint Design Optimization of a Radial-Outflow Turbine for Kalina Cycle System Considering Flexible Operating Conditions and Variable Ammonia-Water Mass Fraction," Energies, MDPI, vol. 15(22), pages 1-19, November.
    10. Peng Li & Zhonghe Han & Xiaoqiang Jia & Zhongkai Mei & Xu Han, 2018. "Analysis of the Effects of Blade Installation Angle and Blade Number on Radial-Inflow Turbine Stator Flow Performance," Energies, MDPI, vol. 11(9), pages 1-15, August.
    11. Jun-Seong Kim & Do-Yeop Kim, 2020. "Preliminary Design and Off-Design Analysis of a Radial Outflow Turbine for Organic Rankine Cycles," Energies, MDPI, vol. 13(8), pages 1-18, April.
    12. Enhua Wang & Ningjian Peng, 2023. "A Review on the Preliminary Design of Axial and Radial Turbines for Small-Scale Organic Rankine Cycle," Energies, MDPI, vol. 16(8), pages 1-20, April.
    13. Du, Qiuwan & Li, Yunzhu & Yang, Like & Liu, Tianyuan & Zhang, Di & Xie, Yonghui, 2022. "Performance prediction and design optimization of turbine blade profile with deep learning method," Energy, Elsevier, vol. 254(PA).
    14. Witanowski, Łukasz & Klonowicz, Piotr & Lampart, Piotr & Klimaszewski, Piotr & Suchocki, Tomasz & Jędrzejewski, Łukasz & Zaniewski, Dawid & Ziółkowski, Paweł, 2023. "Impact of rotor geometry optimization on the off-design ORC turbine performance," Energy, Elsevier, vol. 265(C).
    15. Qin, Kan & Wang, Hanwei & Qi, Jianhui & Sun, Junliang & Luo, Kai, 2022. "Aerodynamic design and experimental validation of high pressure ratio partial admission axial impulse turbines for unmanned underwater vehicles," Energy, Elsevier, vol. 239(PD).
    16. Mahdi Erfanian Nakhchi & Shine Win Naung & Mohammad Rahmati, 2023. "Direct Numerical Simulations of Turbulent Flow over Low-Pressure Turbine Blades with Aeroelastic Vibrations and Inflow Wakes," Energies, MDPI, vol. 16(6), pages 1-21, March.
    17. Zhou, Kai & Zheng, Xinqian, 2022. "Novel wave-shaped tip-shroud contours towards reducing turbine leakage loss," Energy, Elsevier, vol. 254(PA).
    18. Witanowski, Łukasz & Klonowicz, Piotr & Lampart, Piotr & Ziółkowski, Paweł, 2023. "Multi-objective optimization of the ORC axial turbine for a waste heat recovery system working in two modes: cogeneration and condensation," Energy, Elsevier, vol. 264(C).
    19. Cheng, Hongzhi & Zhou, Chuangxin & Lu, Xingen & Zhao, Shengfeng & Han, Ge & Yang, Chengwu, 2023. "Robust aerodynamic optimization and design exploration of a wide-chord transonic fan under geometric and operational uncertainties," Energy, Elsevier, vol. 278(PB).
    20. Peng, Ningjian & Wang, Enhua & Wang, Wenli, 2023. "Design and analysis of a 1.5 kW single-stage partial-admission impulse turbine for low-grade energy utilization," Energy, Elsevier, vol. 268(C).

    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:eee:energy:v:254:y:2022:i:pc:s0360544222013433. 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: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/energy .

    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.