Performance prediction and design optimization of a transonic rotor based on deep transfer learning

被引:1
|
作者
Deng, Hefang [1 ]
Zhang, Songan [2 ]
Xia, Kailong [1 ]
Qiang, Xiaoqing [1 ]
Zhu, Mingmin [1 ]
Teng, Jinfang [1 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Aeronaut & Astronaut, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, Global Inst Future Technol, Shanghai 200240, Peoples R China
基金
中国国家自然科学基金;
关键词
Compendex;
D O I
10.1063/5.0221767
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
Deep transfer learning is frequently employed to address the challenges arising from limited or hard-to-obtain training data in the target domain, but its application in axial compressors has been scarcely explored thus far. In this paper, a multi-objective optimization framework of a transonic rotor is established using deep transfer learning. This framework first pre-trains deep neural networks based on the peak efficiency condition of 100% design speed and then fine-tunes the networks to predict the performance of off-design conditions based on the small training dataset. Finally, the design optimization of the transonic rotor is carried out through non-dominated sorting genetic algorithm II. Compared to neural networks that are trained directly, transfer learning models can achieve higher prediction accuracy, particularly in scenarios with small training datasets. This is because the pre-trained weights can offer a better initial state for transfer learning models. Moreover, transfer learning models can use fewer samples to obtain an approximate Pareto front, making the optimized rotor increase the isentropic efficiency at both peak efficiency and high loading conditions. The efficiency improvement of the optimized rotor is attributed to the reduction of the loss associated with the tip leakage flow by adjusting the tip loading distribution. Overall, this study fully demonstrates the effectiveness of transfer learning in predicting compressor performance, which provides a promising approach to solving high-cost compressor design problems.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] Deep Gaussian process with multitask and transfer learning for performance optimization
    Sid-Lakhdar, Wissam M.
    Aznaveh, Mohsen
    Luszczek, Piotr
    Dongarra, Jack
    2022 IEEE HIGH PERFORMANCE EXTREME COMPUTING VIRTUAL CONFERENCE (HPEC), 2022,
  • [22] A deep learning-based optimization framework of two-dimensional hydrofoils for tidal turbine rotor design
    Wang, Longyan
    Xu, Jian
    Luo, Wei
    Luo, Zhaohui
    Xie, Junhang
    Yuan, Jianping
    Tan, Andy C. C.
    ENERGY, 2022, 253
  • [23] A deep learning-based optimization framework of two-dimensional hydrofoils for tidal turbine rotor design
    Wang, Longyan
    Xu, Jian
    Luo, Wei
    Luo, Zhaohui
    Xie, Junhang
    Yuan, Jianping
    Tan, Andy C.C.
    Energy, 2022, 253
  • [24] Heat transfer performance prediction for heat pipe using deep learning based on wick type
    Jin, Ik Jae
    Park, Ye Yeong
    Bang, In Cheol
    INTERNATIONAL JOURNAL OF THERMAL SCIENCES, 2024, 197
  • [25] Three-Dimensional Design and Optimization of a Transonic Rotor in Axial Flow Compressors
    Okui, Hidetaka
    Verstraete, Tom
    Van den Braembussche, R. A.
    Alsalihi, Zuheyr
    JOURNAL OF TURBOMACHINERY-TRANSACTIONS OF THE ASME, 2013, 135 (03):
  • [26] Prediction and multi-objective optimization of sieve tray hydrodynamic performance based on deep learning
    Yuan, Xing
    Deng, Xuan
    Wang, Kehan
    Ding, Zhongwei
    Zhao, Hongkang
    Xue, Jiaxing
    Li, Qunsheng
    CHEMICAL ENGINEERING SCIENCE, 2025, 309
  • [27] Optimization design of highway route based on deep learning
    Zhang, Jiankang
    FRONTIERS IN FUTURE TRANSPORTATION, 2024, 5
  • [28] Optimization of Deep Learning Hyperparameters with Experimental Design in Exchange Rate Prediction
    Midilli, Yunus Emre
    Parsutins, Sergejs
    2020 61ST INTERNATIONAL SCIENTIFIC CONFERENCE ON INFORMATION TECHNOLOGY AND MANAGEMENT SCIENCE OF RIGA TECHNICAL UNIVERSITY (ITMS), 2020,
  • [29] Rotor design for the performance optimization of Canard Rotor/Wing aircraft
    Lee, JW
    Jeon, KS
    Kim, MJ
    Byun, YH
    Kim, CJ
    Yu, YH
    COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2006, PT 5, 2006, 3984 : 932 - 941
  • [30] Propeller hydrodynamic performance optimization based on deep learning
    Gao, Nan
    Chuang, Zhenju
    Hu, Ankang
    OCEANS 2024 - SINGAPORE, 2024,