Explainability analysis of neural network-based turbulence modeling for transonic axial compressor rotor flows

doi:10.1016/j.ast.2023.108542

CORC > 力学研究所 > 中国科学院力学研究所 > 非线性力学国家重点实验室

	Explainability analysis of neural network-based turbulence modeling for transonic axial compressor rotor flows
	Wu CT(吴楚畋); Wang SZ(王士召); Zhang XL(张鑫磊); He GW(何国威)
刊名	AEROSPACE SCIENCE AND TECHNOLOGY
	2023-10-01
卷号	141 页码:108542
关键词	Explainability Ensemble Kalman method Turbulence model Axial compressor rotor Neural network Machine learning
ISSN号	1270-9638
DOI	10.1016/j.ast.2023.108542
英文摘要	Model-consistent training has become trending for data-driven turbulence modeling since it can improve model generalizability and reduce data requirements by involving the Reynolds-averaged Navier-Stokes (RANS) equation during model learning. Neural networks are often used for the Reynolds stress representation due to their great expressive power, while they lack interpretability for the causal relationship between model inputs and outputs. Some post-hoc methods have been used to explain the neural network by indicating input feature importance. However, for the model-consistent training, the model explainability involves the analysis of both the neural network inputs and outputs. That is, the effects of model output on the RANS predictions should also be explained in addition to the input feature analysis. In this work, we investigate the explainability of the model-consistent learned model for the internal flow prediction of NASA Rotor 37 at its peak efficiency operating condition. The neural-network-based corrections for the Spalart-Allmaras turbulence model are learned from various experimental data based on the ensemble Kalman method. The learned model can noticeably improve the velocity prediction near the shroud. The explainability of the trained neural network is analyzed in terms of the model correction and the input feature importance. Specifically, the learned model correction increases the local turbulence production in the vortex breakdown region due to non-equilibrium effects, which capture the blockage effects near the shroud. Besides, the ratio of production to destruction and the helicity are shown to have relatively high importance for accurately predicting the compressor rotor flows based on the Shapley additive explanations method.& COPY; 2023 Elsevier Masson SAS. All rights reserved.
分类号	一类
WOS研究方向	Engineering
语种	英语
WOS记录号	WOS:001062553400001
资助机构	NSFC Basic Science Center Program for Multiscale Problems in Nonlinear Mechanics [11988102] ; National Natural Science Foundation of China [12102435] ; China Post-doctoral Science Foundation [2021M690154] ; Young Elite Scientists Sponsorship Program by CAST [2022QNRC001]
其他责任者	Zhang, XL ; He, GW (corresponding author), Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China.
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/92665]
专题	力学研究所_非线性力学国家重点实验室
作者单位	1.{Wu Chutian, Wang Shizhao, Zhang Xin-Lei, He Guowei} Univ Chinese Acad Sci Sch Engn Sci Beijing 100049 Peoples R China 2.{Wu Chutian, Wang Shizhao, Zhang Xin-Lei, He Guowei} Chinese Acad Sci Inst Mech State Key Lab Nonlinear Mech Beijing 100190 Peoples R China
推荐引用方式 GB/T 7714	Wu CT,Wang SZ,Zhang XL,et al. Explainability analysis of neural network-based turbulence modeling for transonic axial compressor rotor flows[J]. AEROSPACE SCIENCE AND TECHNOLOGY,2023,141:108542.
APA	吴楚畋,王士召,张鑫磊,&何国威.(2023).Explainability analysis of neural network-based turbulence modeling for transonic axial compressor rotor flows.AEROSPACE SCIENCE AND TECHNOLOGY,141,108542.
MLA	吴楚畋,et al."Explainability analysis of neural network-based turbulence modeling for transonic axial compressor rotor flows".AEROSPACE SCIENCE AND TECHNOLOGY 141(2023):108542.