IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v14y2022i10p6373-d822243.html
   My bibliography  Save this article

A Thermodynamics-Oriented and Neural Network-Based Hybrid Model for Military Turbofan Engines

Author

Listed:
  • Likun Ren

    (Department of Mechanical Engineering, Qingdao Campus, Naval Aviation University, Qingdao 266041, China)

  • Haiqin Qin

    (Department of Mechanical Engineering, Qingdao Campus, Naval Aviation University, Qingdao 266041, China)

  • Zhenbo Xie

    (Department of Mechanical Engineering, Qingdao Campus, Naval Aviation University, Qingdao 266041, China)

  • Jing Xie

    (Department of Mechanical Engineering, Qingdao Campus, Naval Aviation University, Qingdao 266041, China)

  • Bianjiang Li

    (Department of Mechanical Engineering, Qingdao Campus, Naval Aviation University, Qingdao 266041, China)

Abstract

Traditional thermodynamic models for military turbofans suffer from non-convergence and inaccuracy due to inaccuracy of the component maps and the instability of the iterative process. To address these problems, a thermodynamically oriented and neural network-based hybrid model for military turbofans is proposed. Different from iteration-based thermodynamic models, the proposed hybrid model transforms the iteration process into a multi-objective optimization and training process for a component-level neural network in order to improve convergence and modeling accuracy. The experiment shows that the accuracy of the proposed hybrid model can reach about 7%, 5% better than the map-fitting-based thermodynamic model and 8% better than the purely data-driven method, with a similar number of network neutrons, verifying its effectiveness. The contributions of this work mainly lie in the following aspects: a new component-level neural network structure is proposed to improve convergence and computational efficiency; a multi-objective loss function based on component co-working is proposed to direct the model to converge toward the physical thermodynamic process; a fusion training method of multiple data sources is established to train the model with good convergence and high computational accuracy.

Suggested Citation

  • Likun Ren & Haiqin Qin & Zhenbo Xie & Jing Xie & Bianjiang Li, 2022. "A Thermodynamics-Oriented and Neural Network-Based Hybrid Model for Military Turbofan Engines," Sustainability, MDPI, vol. 14(10), pages 1-15, May.
    • Handle: RePEc:gam:jsusta:v:14:y:2022:i:10:p:6373-:d:822243
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/14/10/6373/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2071-1050/14/10/6373/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Tsoutsanis, Elias & Meskin, Nader & Benammar, Mohieddine & Khorasani, Khashayar, 2014. "A component map tuning method for performance prediction and diagnostics of gas turbine compressors," Applied Energy, Elsevier, vol. 135(C), pages 572-585.
    2. Yu, Youhong & Chen, Lingen & Sun, Fengrui & Wu, Chih, 2007. "Neural-network based analysis and prediction of a compressor's characteristic performance map," Applied Energy, Elsevier, vol. 84(1), pages 48-55, January.
    3. Jiajie Chen & Zhongzhi Hu & Jiqiang Wang, 2021. "Aero-Engine Real-Time Models and Their Applications," Mathematical Problems in Engineering, Hindawi, vol. 2021, pages 1-17, August.
    4. Ghorbanian, K. & Gholamrezaei, M., 2009. "An artificial neural network approach to compressor performance prediction," Applied Energy, Elsevier, vol. 86(7-8), pages 1210-1221, July.
    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. Wenxiang Zhou & Sangwei Lu & Wenjie Kai & Jichang Wu & Chenyang Zhang & Feng Lu, 2023. "A Novel Adaptive Generation Method for Initial Guess Values of Component-Level Aero-Engine Start-Up Models," Sustainability, MDPI, vol. 15(4), pages 1-25, 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. Tahan, Mohammadreza & Tsoutsanis, Elias & Muhammad, Masdi & Abdul Karim, Z.A., 2017. "Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review," Applied Energy, Elsevier, vol. 198(C), pages 122-144.
    2. Balerna, Camillo & Lanzetti, Nicolas & Salazar, Mauro & Cerofolini, Alberto & Onder, Christopher, 2020. "Optimal low-level control strategies for a high-performance hybrid electric power unit," Applied Energy, Elsevier, vol. 276(C).
    3. Yazar, Isil & Yavuz, Hasan Serhan & Yavuz, Arzu Altin, 2017. "Comparison of various regression models for predicting compressor and turbine performance parameters," Energy, Elsevier, vol. 140(P2), pages 1398-1406.
    4. Cortés, O. & Urquiza, G. & Hernández, J.A., 2009. "Optimization of operating conditions for compressor performance by means of neural network inverse," Applied Energy, Elsevier, vol. 86(11), pages 2487-2493, November.
    5. Li, Zhihui & Liu, Yanming, 2017. "Blade-end treatment for axial compressors based on optimization method," Energy, Elsevier, vol. 126(C), pages 217-230.
    6. Safiyullah, F. & Sulaiman, S.A. & Naz, M.Y. & Jasmani, M.S. & Ghazali, S.M.A., 2018. "Prediction on performance degradation and maintenance of centrifugal gas compressors using genetic programming," Energy, Elsevier, vol. 158(C), pages 485-494.
    7. Guan, Cong & Theotokatos, Gerasimos & Zhou, Peilin & Chen, Hui, 2014. "Computational investigation of a large containership propulsion engine operation at slow steaming conditions," Applied Energy, Elsevier, vol. 130(C), pages 370-383.
    8. Tsoutsanis, Elias & Meskin, Nader & Benammar, Mohieddine & Khorasani, Khashayar, 2014. "A component map tuning method for performance prediction and diagnostics of gas turbine compressors," Applied Energy, Elsevier, vol. 135(C), pages 572-585.
    9. Kim, Jeong Ho & Kim, Tong Seop, 2019. "A new approach to generate turbine map data in the sub-idle operation regime of gas turbines," Energy, Elsevier, vol. 173(C), pages 772-784.
    10. Artur M. Schweidtmann & Alexander Mitsos, 2019. "Deterministic Global Optimization with Artificial Neural Networks Embedded," Journal of Optimization Theory and Applications, Springer, vol. 180(3), pages 925-948, March.
    11. Son, Seongmin & Jeong, Yongju & Cho, Seong Kuk & Lee, Jeong Ik, 2020. "Development of supercritical CO2 turbomachinery off-design model using 1D mean-line method and Deep Neural Network," Applied Energy, Elsevier, vol. 263(C).
    12. Zhang, Yi & Xu, Yujie & Zhou, Xuezhi & Guo, Huan & Zhang, Xinjing & Chen, Haisheng, 2019. "Compressed air energy storage system with variable configuration for accommodating large-amplitude wind power fluctuation," Applied Energy, Elsevier, vol. 239(C), pages 957-968.
    13. Kang, Do Won & Kim, Tong Seop, 2018. "Model-based performance diagnostics of heavy-duty gas turbines using compressor map adaptation," Applied Energy, Elsevier, vol. 212(C), pages 1345-1359.
    14. Cheng, Xianda & Zheng, Haoran & Yang, Qian & Zheng, Peiying & Dong, Wei, 2023. "Surrogate model-based real-time gas path fault diagnosis for gas turbines under transient conditions," Energy, Elsevier, vol. 278(PA).
    15. Zhang, Weihao & Zou, Zhengping & Ye, Jian, 2012. "Leading-edge redesign of a turbomachinery blade and its effect on aerodynamic performance," Applied Energy, Elsevier, vol. 93(C), pages 655-667.
    16. Finn, Joshua & Wagner, John & Bassily, Hany, 2010. "Monitoring strategies for a combined cycle electric power generator," Applied Energy, Elsevier, vol. 87(8), pages 2621-2627, August.
    17. Cody Allen & Mauricio Oliveira, 2022. "A Minimal Cardinality Solution to Fitting Sawtooth Piecewise-Linear Functions," Journal of Optimization Theory and Applications, Springer, vol. 192(3), pages 930-959, March.
    18. Mo, Huadong & Sansavini, Giovanni, 2019. "Impact of aging and performance degradation on the operational costs of distributed generation systems," Renewable Energy, Elsevier, vol. 143(C), pages 426-439.
    19. Lazrak, Amine & Leconte, Antoine & Chèze, David & Fraisse, Gilles & Papillon, Philippe & Souyri, Bernard, 2015. "Numerical and experimental results of a novel and generic methodology for energy performance evaluation of thermal systems using renewable energies," Applied Energy, Elsevier, vol. 158(C), pages 142-156.
    20. Wei Shao & Shuo Wang & Wenpu Wang & Kun Shao & Qi Xiao & Zheng Cui, 2023. "Experiment and Simulation on a Refrigeration Ventilation System for Deep Metal Mines," Sustainability, MDPI, vol. 15(10), pages 1-20, 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:jsusta:v:14:y:2022:i:10:p:6373-:d:822243. 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.