Dual-convolutional neural network based aerodynamic prediction and multi-objective optimization of a compact turbine rotor

被引:59
作者
Wang, Yuqi [1 ]
Liu, Tianyuan [2 ]
Zhang, Di [1 ]
Xie, Yonghui [2 ]
机构
[1] Xi An Jiao Tong Univ, Sch Energy & Power Engn, MOE Key Lab Thermofluid Sci & Engn, Xian, Peoples R China
[2] Xi An Jiao Tong Univ, Sch Energy & Power Engn, Shaanxi Engn Lab Turbomachinery & Power Equipment, Xian, Peoples R China
关键词
Aerodynamic prediction; Multi-objective optimization; Turbine; Deep learning; Convolution neural network; SUPERCRITICAL CARBON-DIOXIDE; MULTIPOINT; DESIGN; CYCLES; EFFICIENCY; ENERGY;
D O I
10.1016/j.ast.2021.106869
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
With the development of neural network technology, surrogate models and dimensionality reduction strategies based on machine learning have become the research hotspots of aerodynamic shape optimization recently. In order to further improve the accuracy and interpretability of the traditional surrogate models, this research establishes a deep learning model, named Dual Convolutional Neural Network (Dual-CNN) for the aero-engine turbines. The aerodynamic performances are predicted and the pressure, temperature fields are reconstructed for multiple rotor profile conditions. The prediction of efficiency is compared with the accuracy of Gaussian Process Regression (GPR) and Artificial Neural Network (ANN) models. The results show that the proposed Dual-CNN model can accurately reconstruct the fields, thus interpreting the mechanism for the change of aerodynamic performance. Dual-CNN is more accurate than GPR and ANN in predicting efficiency and torque, whose error is within an acceptable range of optimization. Then, efficiency and torque are selected as the objective functions to perform a gradient-based multi-objective optimization by the automatic differentiation method and a Pareto solution is obtained. The trained Dual-CNN provides rapid and accurate prediction of performance without CFD calculation in the optimization. Finally, the sensitivity to train size is analyzed for the Dual CNN model, which indicates that the sampling of 1500 cases for eight design variables in this dataset enables Dual-CNN to achieve favorable effect of field reconstruction and performance prediction. (C) 2021 Elsevier Masson SAS. All rights reserved.
引用
收藏
页数:13
相关论文
共 47 条
[1]   REVIEW OF SUPERCRITICAL CO2 POWER CYCLE TECHNOLOGY AND CURRENT STATUS OF RESEARCH AND DEVELOPMENT [J].
Ahn, Yoonhan ;
Bae, Seong Jun ;
Kim, Minseok ;
Cho, Seong Kuk ;
Baik, Seungjoon ;
Lee, Jeong Ik ;
Cha, Jae Eun .
NUCLEAR ENGINEERING AND TECHNOLOGY, 2015, 47 (06) :647-661
[2]   Centrifugal Compressor Design for Near-Critical Point Applications [J].
Ameli, Alireza ;
Afzalifar, Ali ;
Turunen-Saaresti, Teemu ;
Backman, Jari .
JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER-TRANSACTIONS OF THE ASME, 2019, 141 (03)
[3]   Dynamic modeling of exergy efficiency of turboprop engine components using hybrid genetic algorithm-artificial neural networks [J].
Baklacioglu, Tolga ;
Turan, Onder ;
Aydin, Hakan .
ENERGY, 2015, 86 :709-721
[4]   Supercritical carbon dioxide cycles for power generation: A review [J].
Crespi, Francesco ;
Gavagnin, Giacomo ;
Sanchez, David ;
Martinez, Gonzalo S. .
APPLIED ENERGY, 2017, 195 :152-183
[5]   Optimal rectangular microchannel design, using simulated annealing, unified particle swarm and spiral algorithms, in the presence of spreading resistance [J].
Cruz, Jorge ;
Amaya, Ivan ;
Correa, Rodrigo .
APPLIED THERMAL ENGINEERING, 2015, 84 :126-137
[6]   Study on performances of supercritical CO2 recompression Brayton cycles with multi-objective optimization [J].
Deng, Q. H. ;
Wang, D. ;
Zhao, H. ;
Huang, W. T. ;
Shao, S. ;
Feng, Z. P. .
APPLIED THERMAL ENGINEERING, 2017, 114 :1335-1342
[7]   Novel method and model for dynamic reliability optimal design of turbine blade deformation [J].
Fei, Cheng-Wei ;
Tang, Wen-Zhong ;
Bai, Guang-Chen .
AEROSPACE SCIENCE AND TECHNOLOGY, 2014, 39 :588-595
[8]   Recent advances in surrogate-based optimization [J].
Forrester, Alexander I. J. ;
Keane, Andy J. .
PROGRESS IN AEROSPACE SCIENCES, 2009, 45 (1-3) :50-79
[9]  
Gardner J, 2018, ADV NEUR IN
[10]   Adjoint -based aerodynamic shape optimization including transition to turbulence effects [J].
Halila, Gustavo L. O. ;
Martins, Joaquim R. R. A. ;
Fidkowski, Krzysztof J. .
AEROSPACE SCIENCE AND TECHNOLOGY, 2020, 107