基于深度学习的单排孔气膜冷却性能预测

李左飙; 温风波; 唐晓雷; 苏良俊; 王松涛

doi:10.7527/S1000-6893.2020.24331

航空学报 >

2021 , Vol. 42 >Issue 4: 524331 - 524331

DOI: https://doi.org/10.7527/S1000-6893.2020.24331

流体力学与飞行力学

基于深度学习的单排孔气膜冷却性能预测

李左飙 ,
温风波 ,
唐晓雷 ,
苏良俊 ,
王松涛

展开

哈尔滨工业大学能源科学与工程学院, 哈尔滨 150001

收稿日期: 2020-06-01

修回日期: 2020-06-30

网络出版日期: 2020-07-27

基金资助

国家科技重大专项（2017-I-0005-0006）

收起

Prediction of single-row hole film cooling performance based on deep learning

LI Zuobiao ,
WEN Fengbo ,
TANG Xiaolei ,
SU Liangjun ,
WANG Songtao

Expand

School of Energy Science and Engineering, Harbin Institute of Technology, Harbin 150001, China

Received date: 2020-06-01

Revised date: 2020-06-30

Online published: 2020-07-27

Supported by

National Science and Technology Major Project(2017-I-0005-0006)

Fold

摘要

气膜冷却是增强涡轮叶片的高温耐受力，间接提高涡轮进口温度的有效手段之一。目前气膜冷却孔布局的主流设计方法是先通过计算流体力学（CFD）筛选和优化初始方案，再进行模型实验。这种方法设计周期长，时间成本高。传统上用于快速评估冷却效率的经验公式法存在函数形式复杂，拟合精度有限，参数适用范围较窄等问题。因此基于深度学习原理，设计了一种基于多层感知器模型（MLP）的深度神经网络，建立了绝热气膜冷却效率的预测模型。使用CFD数据训练网络，结果表明：深度学习模型在训练集和验证集上具有大于0.95的拟合度，在测试集上具有大于0.99的拟合度，可以较好地识别数据集中的抽象特征，具有较高的精度和较好的泛化能力。此外，在满足精度要求的前提下，一个完成训练的深度学习模型能够有效减少预测耗时，提高预测效率，在快速评估冷却布局性能方面具有较好的应用前景。

关键词： 气膜冷却; 绝热气膜冷却效率; 计算流体力学(CFD); 神经网络; 深度学习; 多层感知器(MLP); 预测

本文引用格式

李左飙 , 温风波 , 唐晓雷 , 苏良俊 , 王松涛 . 基于深度学习的单排孔气膜冷却性能预测[J]. 航空学报, 2021 , 42(4) : 524331 -524331 . DOI: 10.7527/S1000-6893.2020.24331

Abstract

Film cooling is an effective way to enhance the high temperature resistance of turbine blades and indirectly increase the inlet temperature of the turbine. Currently, the mainstream design method of the film cooling hole layout is to select and optimize the initial schemes with Computational Fluid Dynamics (CFD), followed by model experiments. However, this method has a long design period and thus is time-consuming. The traditional empirical formula method for rapid evaluation of cooling efficiency is problematic in that the function form is complex, the fitting precision is low and the applicable range of parameters is narrow. This paper designs a deep neural network with a Multi-Layer Perceptron model (MLP) based on the principle of deep learning, and establishes a prediction model for adiabatic film cooling efficiency. The calculation of CFD is utilized to train the network, and the results obtained from the modeling efforts indicate that the deep learning model has a fitting degree of more than 0.95 on the training set and the verification set, and more than 0.99 on the test set. Hence, it can effectively identify the abstract features of the data set with high precision and good generalization ability. Additionally, on the premise of meeting the requirement of sufficient precision, the deep learning model takes only 1/1000 of the time of CFD to complete the prediction process, exhibiting a good application prospect in the rapid evaluation of cooling layout performance.

Key words： film cooling; adiabatic film cooling efficiency; Computational Fluid Dynamics (CFD); neural networks; deep learning; Multi-Layer Perceptron (MLP); prediction

参考文献

[1] 倪萌, 朱惠人, 裘云, 等. 航空发动机涡轮叶片冷却技术综述[J]. 燃气轮机技术, 2005, 18(4):25-33, 38. NI M, ZHU H R, QIU Y, et al. Review of aero-turbine blade cooling technology[J]. Gas Turbine Technology, 2005, 18(4):25-33, 38(in Chinese).
[2] 戴萍, 林枫. 燃气轮机叶片气膜冷却研究进展[J]. 热能动力工程, 2009, 24(1):1-6. DAI P, LIN F. Recent advances in the study of air-film-cooled gas turbine blades[J]. Journal of Engineering for Thermal Energy and Power, 2009, 24(1):1-6(in Chinese).
[3] WIEGHARDT K. Hot-air discharge for de-icing[M]. Wright-Patterson AFB:Air Force Materiel Command, 1946:1-44.
[4] METZGER D E, TAKEUCHI D I, KUENSTLER P A. Effectiveness and heat transfer with full-coverage film cooling[J]. Journal of Engineering for Gas Turbines and Power, 1973, 95(3):180-184.
[5] MUSKA J F, FISH R W, SUO M. The additive nature of film cooling from rows of holes[J]. Journal of Engineering for Gas Turbines and Power, 1976, 98(4):457-463.
[6] GRITSCH M, BALDAUF S, MARTINY M, et al. The superposition approach to local heat transfer coefficients in high density ratio film cooling flows[C]//ASME 1999 International Gas Turbine and Aeroengine Congress and Exhibition. New York:ASME, 1999.
[7] GOLDSTEIN R J, ECKERT E R G, ERIKSEN V L, et al. Film cooling following injection through inclined circular tubes[J]. Israel Journal of Technology, 1970, 8(1):145-154.
[8] PEDERSEN D R, ECKERT E R G, GOLDSTEIN R J. Film cooling with large density differences between the mainstream and the secondary fluid measured by the heat-mass transfer analogy[J]. Journal of Heat Transfer, 1977, 99(4):620-627.
[9] SINHA A K, BOGARD D G, CRAWFORD M E. Film-cooling effectiveness downstream of a single row of holes with variable density ratio[J]. Journal of Turbomachinery, 1991, 113(3):442-449.
[10] WALTERS D K, LEYLEK J H. A systematic computational methodology applied to a three-dimensional film-cooling flowfield[J]. Journal of Turbomachinery, 1997, 119(4):777-785.
[11] WALTERS D K, LEYLEK J H. A detailed analysis of film-cooling physics:Part I-Streamwise injection with cylindrical holes[J]. Journal of Turbomachinery, 2000, 122(1):102-112.
[12] WALTERS D K, LEYLEK J H. A detailed analysis of film-cooling physics:Part Ⅱ-Compound-angle injection with cylindrical holes[J]. Journal of Turbomachinery, 2000, 122(1):113-121.
[13] WALTERS D K, LEYLEK J H. A detailed analysis of film-cooling physics:Part Ⅲ-Streamwise injection with shaped holes[J]. Journal of Turbomachinery, 2000, 122(1):122-132.
[14] WALTERS D K, LEYLEK J H. A detailed analysis of film-cooling physics:Part IV-Compound-angle injection with shaped holes[J]. Journal of Turbomachinery, 2000, 122(1):133-145.
[15] ACHARYA S, TYAGI M, HODA A. Flow and heat transfer predictions for film cooling[J]. Annals of the New York Academy of Sciences, 2001, 934(1):110-125.
[16] BALDAUF S, SCHEURLEN M, SCHULZ A, et al. Correlation of film-cooling effectiveness from thermographic measurements at enginelike conditions[J]. Journal of Turbomachinery, 2002, 124(4):686-698.
[17] GUO X, LI W, IORIO F. Convolutional neural networks for steady flow approximation[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2016:481-490.
[18] SEKAR V, JIANG Q H, SHU C, et al. Fast flow field prediction over airfoils using deep learning approach[J]. Physics of Fluids, 2019, 31(5):057103.
[19] 陈海, 钱炜祺, 何磊. 基于深度学习的翼型气动系数预测[J]. 空气动力学学报, 2018, 36(2):294-299. CHEN H, QIAN W Q, HE L. Aerodynamic coefficient prediction of airfoils based on deep learning[J]. Acta Aerodynamica Sinica, 2018, 36(2):294-299(in Chinese).
[20] 廖鹏, 姚磊江, 白国栋, 等. 基于深度学习的混合翼型前缘压力分布预测[J]. 航空动力学报, 2019, 34(8):1751-1758. LIAO P, YAO L J, BAI G D, et al. Prediction of hybrid airfoil leading edge pressure distribution based on deep learning[J]. Journal of Aerospace Power, 2019, 34(8):1751-1758(in Chinese).
[21] 陈海昕, 邓凯文, 李润泽. 机器学习技术在气动优化中的应用[J]. 航空学报, 2019, 40(1):522480. CHEN H X, DENG K W, LI R Z, Utilization of machine learning technology in aerodynamic optimization[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(1):522480(in Chinese).
[22] WANG C H, ZHANG J Z, ZHOU J H, et al. Prediction of film-cooling effectiveness based on support vector machine[J]. Applied Thermal Engineering, 2015, 84:82-93.
[23] 秦晏旻, 李雪英, 任静, 等. 基于BP神经网络的多参数气膜冷却效率研究[J]. 工程热物理学报, 2011,32(7):49-52. QIN Y M, LI X Y, REN J, et al. Prediction of the adiabatic film cooling effectiveness influenced by multi parameters based on BP neural network[J]. Journal of Engineering Thermophysics, 2011,32(7):49-52(in Chinese).
[24] DOLATI S, AMANIFARD N, DEYLAMI H M. Numerical study and GMDH-type neural networks modeling of plasma actuator effects on the film cooling over a flat plate[J]. Applied Thermal Engineering, 2017, 123:734-745.
[25] DáVALOS J O, GARCíA J C, URQUIZA G, et al. Prediction of film cooling effectiveness on a gas turbine blade leading edge using ANN and CFD[J]. International Journal of Turbo and Jet Engines, 2018, 35(2):101-111.
[26] MILANI P M, LING J, SAEZ-MISCHLICH G, et al. A machine learning approach for determining the turbulent diffusivity in film cooling flows[J]. Journal of Turbomachinery, 2018, 140(2):021006.
[27] MILANI P M, LING J, EATON J K. Generalization of machine-learned turbulent heat flux models applied to film cooling flows[J]. Journal of Turbomachinery, 2020, 142(1):011007.
[28] YANG L, DAI W, RAO Y, et al. Optimization of the hole distribution of an effusively cooled surface facing non-uniform incoming temperature using deep learning approaches[J]. International Journal of Heat and Mass Transfer, 2019, 145:118749.
[29] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[30] CYBENKO G. Approximation by superpositions of a sigmoidal function[J]. Mathematics of Control, Signals and Systems, 1989, 2(4):303-314.
[31] HORNIK K. Approximation capabilities of multilayer feedforward networks[J]. Neural networks, 1991, 4(2):251-257.
[32] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[33] LUTUM E, JOHNSON B V. Influence of the hole length-to-diameter ratio on film cooling with cylindrical holes[J]. Journal of Turbomachinery, 1999, 121(2):209-216.
[34] GRITSCH M, SCHULZ A, WITTIG S. Wall effectiveness measurements of film-cooling holes with expanded exits[J]. Journal of Turbomachinery, 1998, 120(3):549-556.
[35] MA Y, YU D, WU T, et al. PaddlePaddle:An open-source deep learning platform from industrial practice[J]. Frontiers of Data and Domputing, 2019, 1(1):105-115.
[36] KINGMA D P, BA J. Adam:A method for stochastic optimization[EB/OL]. (2017-01-30)[2020-05-01]. http://arxiv.org/abs/1412.6980.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献