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
  • [31] Prediction of Activated Sludge Sedimentation Performance Using Deep Transfer Learning
    Wang, Jin
    Yang, Xiao
    Chen, Wenkang
    Zhao, Yifan
    Gong, Sai
    Dong, Deyuan
    Wang, Jinfeng
    Ren, Hongqiang
    ACS ES&T ENGINEERING, 2024, 4 (06): : 1367 - 1377
  • [32] Temperature Prediction of Heating Furnace Based on Deep Transfer Learning
    Zhai, Naiju
    Zhou, Xiaofeng
    SENSORS, 2020, 20 (17) : 1 - 27
  • [33] Generalizable epileptic seizures prediction based on deep transfer learning
    Zargar, Bahram Sarvi
    Mollaei, Mohammad Reza Karami
    Ebrahimi, Farideh
    Rasekhi, Jalil
    COGNITIVE NEURODYNAMICS, 2023, 17 (01) : 119 - 131
  • [34] Generalizable epileptic seizures prediction based on deep transfer learning
    Bahram Sarvi Zargar
    Mohammad Reza Karami Mollaei
    Farideh Ebrahimi
    Jalil Rasekhi
    Cognitive Neurodynamics, 2023, 17 : 119 - 131
  • [35] Cancer Drug Sensitivity Prediction Based on Deep Transfer Learning
    Meng, Weijun
    Xu, Xinyu
    Xiao, Zhichao
    Gao, Lin
    Yu, Liang
    INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2025, 26 (06)
  • [36] On the performance of deep learning for numerical optimization: An application to protein structure prediction
    Rakhshani, Hojjat
    Idoumghar, Lhassane
    Ghambari, Soheila
    Lepagnot, Julien
    Brevilliers, Mathieu
    APPLIED SOFT COMPUTING, 2021, 110
  • [37] Deep Learning-Based Traffic Prediction for Network Optimization
    Troia, Sebastian
    Alvizu, Rodolfo
    Zhou, Youduo
    Maier, Guido
    Pattavina, Achille
    2018 20TH ANNIVERSARY INTERNATIONAL CONFERENCE ON TRANSPARENT OPTICAL NETWORKS (ICTON), 2018,
  • [38] MULTI-OBJECTIVE AERODYNAMIC DESIGN OPTIMIZATION BASED ON CAMBER LINE AND THICKNESS DISTRIBUTION FOR A TRANSONIC COMPRESSOR ROTOR
    Wang, Xiangfeng
    Wang, Songtao
    Han, Wanjin
    IMECE 2008: PROCEEDINGS OF THE ASME INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, VOL 5, 2009, : 25 - 32
  • [39] Fast prediction of transonic flow field using deep learning method
    Yi J.
    Deng F.
    Qin N.
    Liu X.
    Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica, 2022, 43 (11):
  • [40] Improving transonic performance with adjoint-based NACA 0012 airfoil design optimization
    Ntantis, Efstratios L.
    Xezonakis, Vasileios
    RESULTS IN ENGINEERING, 2024, 24