Data-driven framework for prediction and optimization of gas turbine blade film cooling

被引:3
|
作者
Wang, Yaning [1 ,2 ,3 ]
Wang, Zirui [4 ]
Qian, Shuyang [5 ]
Qiu, Xubin [2 ]
Shen, Weiqi [2 ]
Zhang, Xinshuai [6 ]
Lyu, Benshuai [7 ]
Cui, Jiahuan [1 ,2 ]
机构
[1] Zhejiang Univ, Sch Aeronaut & Astronaut, Hangzhou, Peoples R China
[2] Zhejiang Univ, Zhejiang Univ Univ Illinois Urbana Champaign Inst, Haining, Peoples R China
[3] Natl Univ Singapore, Coll Design & Engn, Singapore, Singapore
[4] Univ Illinois, Dept Mech Sci & Engn, Urbana, IL 61801 USA
[5] Imperial Coll London, Dept Mech Engn, London, England
[6] Xian Modern Control Technol Res Inst, Xian, Peoples R China
[7] Peking Univ, Coll Engn, Beijing, Peoples R China
基金
中国国家自然科学基金; 美国国家科学基金会;
关键词
HEAT-TRANSFER; ANGLE; TIP;
D O I
10.1063/5.0186087
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
Film cooling is a crucial technique for protecting critical components of gas turbines from excessive temperatures. Multiparameter film cooling optimization is still relatively time-consuming owing to the substantial computational demands of computational fluid dynamics (CFD) methods. To reduce the computational cost, the present study develops a data-driven framework for predicting and optimizing the film cooling effectiveness of high-pressure turbines based on deep learning. Multiple rows of cooling holes located on the pressure surface of the turbine blade are optimized, with the coolant hole diameter, the incline angle, and the compound angle as design parameters. A conditional generative adversarial network model combining a gated recurrent unit and a convolutional neural network is designed to establish the complex nonlinear regression between the design parameters and the film cooling effectiveness. The surrogate model is trained and tested using independent CFD results. A sparrow search algorithm and the well-trained surrogate model are combined to acquire the optimal film cooling parameters. The proposed framework is found to improve multi-row film cooling effectiveness by 21.2% at an acceptable computational cost.
引用
收藏
页数:16
相关论文
共 50 条
  • [41] Film superposition prediction method for film cooling layouts with same opening ratio on the turbine blade
    Zhang, Fan
    Liu, Cunliang
    Wang, Wenxuan
    Ye, Lin
    Li, Bingran
    Liu, Feng
    APPLIED THERMAL ENGINEERING, 2023, 233
  • [42] MODELLING OF FILM COOLING FOR TURBINE BLADE DESIGN
    Tartinville, B.
    Hirsch, Ch.
    PROCEEDINGS OF THE ASME TURBO EXPO 2008, VOL 6, PT A, 2008, : 2219 - 2228
  • [43] Gas turbine film cooling
    Bogard, DG
    Thole, KA
    JOURNAL OF PROPULSION AND POWER, 2006, 22 (02) : 249 - 270
  • [44] A new data-driven topology optimization framework for structural optimization
    Zhou, Ying
    Zhan, Haifei
    Zhang, Weihong
    Zhu, Jihong
    Bai, Jinshuai
    Wang, Qingxia
    Gu, Yuantong
    COMPUTERS & STRUCTURES, 2020, 239
  • [45] Data-driven turbulence anisotropy in film and effusion cooling flows
    Ellis, Christopher D.
    Xia, Hao
    PHYSICS OF FLUIDS, 2023, 35 (10)
  • [46] Effect of rotation on leading edge region film cooling of a gas turbine blade with three rows of film cooling holes
    Ahn, Jaeyong
    Schobeiri, M. T.
    Han, Je-Chin
    Moon, Hee-Koo
    INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER, 2007, 50 (1-2) : 15 - 25
  • [47] Advances in gas turbine blade cooling technology
    Amano, R. S.
    ADVANCED COMPUTATIONAL METHODS AND EXPERIMENTS IN HEAT TRANSFER X, 2008, 61 : 149 - 157
  • [48] TURBINE BLADE TIP COOLING MODELLING AND OPTIMIZATION
    Vogel, Gregory
    Agrawal, Anmol
    Nannapaneni, Praneetha
    PROCEEDINGS OF THE ASME TURBO EXPO 2009, VOL 3, PTS A AND B, 2009, : 139 - 147
  • [49] Thermodynamic modeling of gas turbine blade cooling
    Sanaye, Sepehr
    Darvishi, Mehdi
    PROCEEDINGS OF THE ASME TURBO EXPO, VOL 3, 2007, : 811 - 819
  • [50] A data-driven framework for intonational phrase break prediction
    Maragoudakis, M
    Zervas, P
    Fakotakis, N
    Kokkinakis, G
    TEXT, SPEECH AND DIALOGUE, PROCEEDINGS, 2003, 2807 : 189 - 197