Machine Learning-Assisted Optimization of Generalized <italic style="font-style: italic">k-ω</italic> Turbulence Model for Transonic Compressor Rotors

FAN Zhixiang; ZHANG Xiawen; LI Zhen; JU Yaping; ZHANG Chuhua

doi:10.7652/xjtuxb202601018

您当前的位置：

首页 >

文章列表页 >

Machine Learning-Assisted Optimization of Generalized k-ω Turbulence Model for Transonic Compressor Rotors

Special Topic Pollution Control and Resource Utilization in the “Dual Carbon”Context | 更新时间：2026-01-15

- Machine Learning-Assisted Optimization of Generalized k-ω Turbulence Model for Transonic Compressor Rotors
- Journal of Xi'an Jiaotong University Vol. 60, Issue 1, Pages: 180-189(2026)
- 作者机构：
  
  西安交通大学能源与动力工程学院，710049，西安
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202601018
  CLC： TK05
- Received：06 April 2025，
  
  Published：10 January 2026
- 稿件说明：
移动端阅览
FAN Zhixiang, ZHANG Xiawen, LI Zhen, et al. Machine Learning-Assisted Optimization of Generalized k-ω Turbulence Model for Transonic Compressor Rotors[J]. Journal of Xi'an Jiaotong University, 2026, 60(1): 180-189. DOI: 10.7652/xjtuxb202601018.
DOI：

FAN Zhixiang, ZHANG Xiawen, LI Zhen, et al. Machine Learning-Assisted Optimization of Generalized k-ω Turbulence Model for Transonic Compressor Rotors[J]. Journal of Xi'an Jiaotong University, 2026, 60(1): 180-189. DOI: 10.7652/xjtuxb202601018. DOI：

摘要

针对雷诺平均纳维-斯托克斯（RANS）方法中现有涡黏湍流模型普遍存在对压气机非设计工况下气动特性及复杂流动计算精度不足的共性问题，通用

k-ω

（GEKO）湍流模型引入了6个自由参数，可根据不同类型流动进行校准，提高了压气机内流计算精度。针对跨声速轴流压气机转子NASA Rotor 67近堵塞、设计点和近失速3个工况进行GEKO湍流模型自由参数的机器学习及多目标优化，并对比分析优化后的GEKO湍流模型、默认的GEKO湍流模型及标准的剪切应力传输（SST）湍流模型的计算精度。结果表明：相较于默认的GEKO湍流模型，优化后的GEKO湍流模型在气动性能曲线、转子出口平面展向参数分布和流场细节方面的计算精度都显著提高；相较于SST湍流模型，优化后的GEKO湍流模型对性能曲线计算更精准，特别对失速裕度的计算精度提高了5.4%，对激波位置和强度的计算精度更高。GEKO湍流模型对于提高跨声速轴流压气机转子的数值模拟精度效果显著，可为发展高精度的RANS湍流模型提供参考。

Abstract

To address the common issue of insufficient computational accuracy in aerodynamic characteristics and complex flows under off-design conditions of compressors using existing eddy-viscosity turbulence models in Reynolds-averaged Navier-Stokes (RANS)methods，the generalized

k-ω

(GEKO)turbulence model introduces six free parameters that can be calibrated for different types of flows，improves the computational accuracy of internal flows in compressors.This study focuses on machine learning and multi-objective optimization of the free parameters of the GEKO turbulence model for a transonic axial compressor rotor (NASA Rotor 67)under three operating conditions：near-choke，design point，and near-stall.The computational accuracy of the optimized GEKO turbulence model is compared with that of the default GEKO turbulence model and the standard shear stress transport (SST)turbulence model.The results show that compared to the default GEKO turbulence model，the optimized GEKO turbulence model significantly improves computational accuracy in terms of aerodynamic performance curves，spanwise parameter distributions at the rotor outlet plane，and flow field details.Compared to the SST turbulence model，the optimiz

ed GEKO turbulence model provides more accurate performance curve calculations，with a 5.4% improvement in stall margin calculation accuracy.Additionally，the optimized GEKO turbulence model achieves higher accuracy in calculating shock wave locations and intensities. The GEKO turbulence model demonstrates significant effectiveness in enhancing the numerical simulation accuracy of transonic axial compressor rotors，providing a reference for the development of high-precision RANS turbulence models.

关键词

Keywords

references

张楚华,琚亚平.流体机械内流理论与计算[M].北京:机械工业出版社,2016.

SPOTTS N,GAO Xinfeng.A comparative study of turbulence models for RANS simulations of rotor 67[C]//54th AIAA Aerospace Sciences Meeting.Reston,VA,USA:AIAA,2016 :AIAA2016-0608.

GOURDAIN N,SICOT F,DUCHAINE F,et al. Large eddy simulation of flows in industrial compressors:a path from 2015 to 2035[J].Philosophical Transactions of the Royal Society:A Mathematical, Physical and Engineering Sciences,2014,372(2022):20130323.

WILCOX D C.Reassessment of the scale-determining equation for advanced turbulence models[J].AIAA Journal,1988,26(11):1299-1310.

JONES W P,LAUNDER B E.The prediction of laminarization with a two-equation model of turbulence[J]. International Journal of Heat and Mass Transfer,1972, 15(2):301-314.

MENTER F R. Two-equation eddy-viscosity turbulence models for engineering applications[J].AIAA Journal,1994,32(8):1598-1605.

QUEUTEY P,GUILMINEAU E,VISONNEAU M, et al. RANS and hybrid RANS-LES simulations around the Japan bulk carrier of the Tokyo 2015 CFD workshop[C]//19th Numerical Towing Tank Symposium (NuTTS 2016).North Rhine-Westphalia,Ger many:University of Duisburg-Essen,2016:02566735.

MENTER F R,LECHNER R,MATYUSHENKO A. Best practice: generalized k-ω two-equation turbulence model in ansysCFD[EB/OL ] .[2025-02-10 ] .https://www.ansys.com/content/dam/amp/2022/march/quick-request/Best-Practice-GEKO-Turbulence-Modeling-in-Ansys-CFD.pdf.

MENTER F R,MATYUSHENKO A,LECHNER R.Development of a generalized k-ω two-equation turbulence model[C ] //New Results in Numerical and Experimental Fluid Mechanics:Ⅻ Cham,Switzerland:Springer International Publishing,2020:101-109.

SHARKEY P S,MENTER F R.Anumerical investigation of the turbulent flow around a scale model JBC hull using the generalized k -omega (GEKO)turbulence model[C ] //11th International Workshop on Ship and Marine Hydrodynamics.Hamburg,Germany:TUHH,2019:16.

LI Ziyan,LIU Yudan,ZHOU Wenwu,et al.Thermal pollution level reduction by sweeping jet-based enhanced heat dissipation:a numerical study with calibrated generalized k-ω (GEKO)model[J ] .Applied Thermal Engineering,2022,204:117990.

吴培利,杨小武,霍鹏飞,等.基于数据驱动的湍流神经网络模型参数优化[J].探测与控制学报,2025 , 47(1):110-118.

WU Peili,YANG Xiaowu,HUO Pengfei,et al.Datadriven parameter optimization for turbulence neural network model[J].Journal of Detection & Control, 2025,47(1):110-118.

AMSTAD P,SO K K,FISCHER M.Machine-learning assisted optimization of generalized K -omega (GEKO)turbulence model parameters for turbocharger radial compressor[C ] //ASME Turbo Expo 2022:Turbomachinery Technical Conference and Exposition. New York,USA:ASME,2022:V10DT34A002.

STRAZISAR A J,WOOD J R,HATHAWAY M D, et al.Laser anemometer measurements in a transonic axial-flow fan rotor:NASA-TP-2879[R].Washington,D.C.,USA:NASA,1989.

ROBERTS W B,THORP S A,PRAHST P S,et al. The effect of ultrapolish on a transonic axial rotor[J]. Journal of Turbomachinery,2013,135(1):011001.

GARUD S S,KARIMI I A,KRAFT M.Design of computer experiments:a review[J].Computers &Chemical Engineering,2017,106:71-95.

BURKOV A. Machine learning engineering[M]. Montreal,Canada:True Positive Incorporated,2020.

CHEN Tianqi,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:Association for Computing Machinery,2016:785-794.

ZHANG Xiawen,JU Yaping,LI Zhen,et al.Metamodel-interpreted data mining for stability and efficiency enhancement of multistage axial-flow compressors[J]. Journal of Turbomachinery,2023,145(4):041001.

DEB K,JAIN H.An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach:partⅠ solving problems with box constraints[J].IEEE Transactions on Evolutionary Computation,2014,18(4):577-601.

陈玲,琚亚平,李震,等.多级轴流压气机末级串列静子三维优化设计与分析[J].西安交通大学学报, 2023,57(1):164-174.

CHEN Ling,JU Yaping,LI Zhen,et al.Threedimensional design optimization and analysis for last stator of multi-stage axial flow compressor[J].Journal of Xi'an Jiaotong University,2023,57(1):164-174.

张倩,黄秀全,王丁喜.针对叶轮机流场分析的不同Spalart-Allmaras湍流模型评价[J].推进技术,2022 , 43(4):75-87.

ZHANG Qian,HUANG Xiuquan,WANG Dingxi. Evaluation of different Spalart-Allmaras turbulence models for turbomachinery flow field analysis[J].Journal of Propulsion Technology,2022,43(4):75-87.

PORRO M,JEFFERSON-LOVEDAY R,BENINI E. Axial flow compressor stability enhancement:circumferential T-shape grooves performance investigation[J].Aerospace,2021 ,8(1):12.

SUDER K L.Blockage development in a transonic,axial compressor rotor[J].Journal of Turbomachinery, 1998,120(3):465-476.

FIDALGO V J,HALL C A,COLIN Y.A study of fan-distortion interaction within the NASA Rotor 67 transonic stage[J]. Journal of Turbomachinery, 2012,134(5):051011.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Advances in the Application of Machine Learning to Boiling Heat Transfer

Influence of Bionic Front Grille Inspired by Long-Eared Owl Wing on Performance of Circulation Fan with Annular Impeller

Research on Adsorbents for CO2 Capture：From Traditional Design to Machine Learning

Study on the Applicability of Turbulence Model to Transient Evolution Characteristics of Cloud Cavitation in Nozzle

Uncertainty Quantification of Reynolds-Averaged Navier-Stokes Turbulence Model in Predicting Centrifugal Compressor Performance

Related Author

CHU Wenxiao

TANG Weifeng

BI Xiaolong

ZHOU Chenjie

SURTAEV Anton Sergeevich

WANG Qiuwang

PAVLENKO Alexander Nikolaevich

WU Xianpeng

Related Institution

Kutateladze Institute of Thermophysics，Siberian Branch of the Russian Academy of Sciences

MOE Key Laboratory of Thermo-Fluid Science and Engineering，Xi’an Jiaotong University

GD Midea Environmental Electrical Appliance MFG Co., Ltd.

中船（邯郸)派瑞特种气体股份有限公司，056000，河北邯郸Peric Special Gases Co., Ltd., Handan, Hebei 056000, China

西安交通大学能源与动力工程学院，710049，西安School of Energy and Power Engineering, Xi'an Jiaotong University, Xi'an 710049, China

⁰

Machine Learning-Assisted Optimization of Generalized k-ω Turbulence Model for Transonic Compressor Rotors

DOI：10.7652/xjtuxb202601018

摘要

Abstract

关键词

Keywords

references