Application of neural network model in compressor through⁃flow analysis

Teng FEI; Lucheng JI; Ling ZHOU

doi:10.13224/j.cnki.jasp.20210105

Chinese

您当前的位置：

首页 >

文章列表页 >

Application of neural network model in compressor through⁃flow analysis

Turbomachinery | 更新时间：2025-04-07

- Application of neural network model in compressor through⁃flow analysis
- Journal of Aerospace Power Vol. 37, Issue 6, Pages: 1260-1272(2022)
- 作者机构：
  
  1.北京理工大学宇航学院，北京 100081
  2.清华大学航空发动机研究院，北京 100084
- 作者简介：
- 基金信息：
- DOI：10.13224/j.cnki.jasp.20210105
  CLC：
- 稿件说明：
移动端阅览
Teng FEI, Lucheng JI, Ling ZHOU. Application of neural network model in compressor through⁃flow analysis[J]. Journal of Aerospace Power, 2022, 37(6): 1260-1272.
DOI：

Teng FEI, Lucheng JI, Ling ZHOU. Application of neural network model in compressor through⁃flow analysis[J]. Journal of Aerospace Power, 2022, 37(6): 1260-1272. DOI： 10.13224/j.cnki.jasp.20210105.

摘要

为了解决通流特性分析程序中原始模型对压气机性能预测精度不足的问题，提高压气机通流特性分析过程的可靠性，基于对大量多圆弧叶栅的数值模拟结果建立了压气机叶栅性能数据库，并以该数据库为依托，采用神经网络建模方法建立了压气机叶栅基准损失系数和基准落后角模型。结果显示：两模型对叶栅基准损失系数和基准落后角的预测精度均满足工程应用要求，其精度分别为±0.002和±1°。在对采用神经网络模型的通流特性分析程序校验过程中发现，其无论对压气机整机性能还是对流动细节的预测精度上都获得了显著提高，尤其是在主流区。此外从压气机整体特性上看，基准损失系数和基准落后角精度的提高对非设计工况损失系数和落后角的预测精度影响是积极的。

Abstract

To solve the problem of insufficient prediction accuracy of the compressor performance by the original model in the through⁃flow analysis program，and to improve the reliability of the compressor through⁃flow analysis process，a compressor cascade performance database was established based on the numerical simulation results of a large number of multiple circular arc cascades.Based on this database，neural network modeling method was used to establish the baseline loss coefficient and baseline deviation angle models of compressor cascade.Results showed that，the prediction accuracy of the two models for the baseline loss coefficient and baseline deviation angle of cascade met the requirements of engineering applications，with the accuracy of ±0.002 and ±1°，respectively.During the verification process，it could be found that the neural network models significantly improved the prediction accuracy of both compressor's overall performance and the flow details，especially at the core flow region.Moreover，the improvement of the accuracy of baseline loss coefficient and baseline deviation angle had a positive effect on the prediction accuracy of loss coefficient and deviation angle at off⁃design conditions.

关键词

Keywords

references

DENTON J D ， DAWES W N . Computational fluid dynamics for turbomachinery design [J]. Journal of Mechanical Engineering Science ， 1998 , 213 （ 2 ）: 107 ⁃ 124 .

LIEBLEIN S . Aerodynamic design of axial‑flow compressors VI⁃experimental flow in two⁃dimensional cascades [R]. NACA⁃RM⁃E 55 K 01 a， 1965 .

CREVELING H F ， CARMODY R H . Axial⁃flow compressor computer program for calculating off⁃design performance [R]. NASA CR⁃72472 ， 1968 .

PACHIDIS V ， PILIDIS P ， TEMPLALEXIS I ， et al . An iterative method for blade profile loss model adaptation using streamline curvature [J]. Journal of Engineering for Gas Turbines and Power ， 2007 , 130 （ 1 ）: 183 ⁃ 193 .

LEVINE P . The two dimensional inflow conditions for a supersonic compressor with curved blades [R]. AFB TR 55⁃387 ， 1956 .

CETIN M , UCER A S , HIRSCH C H , et al . Application of modified loss and deviation correlations to transonic axial compressors [R]. AGARD⁃R⁃745 , 1987 .

CARTER A D S . The low speed performance of related aerofoils in cascades [R]. ARC⁃CP⁃29 ， 1950 .

LIEBLEIN S . Incidence and deviation⁃angle correlations for compressor cascades [J]. Journal of Basic Engineering ， 1960 , 82 （ 3 ）: 575 ⁃ 584 .

PACHIDIS V . Gas turbine advanced performance simulation [D]. Cranfield,UK : Cranfield University ， 2006 .

POLLARD D ， GOSTELOW J P . Some experiments at low speed on compressor cascades [J]. Journal of Engineering for Power ， 1967 , 89 （ 3 ）: 427 ⁃ 436 .

CETIN M ， HIRSCH C ， SEROVY G K ， et al . An off⁃design loss and deviation prediction study for transonic axial compressors [R]. ASME Paper 89⁃GT⁃324 ， 1989 .

刘波，马乃行，杨小东 , 等 . 适应较大叶型弯角范围的轴流压气机落后角模型 [J]. 航空动力学报， 2014 , 29 （ 8 ）: 1824 ⁃ 1831 .

LIU Bo ， MA Naixing ， YANG Xiaodong ， et al . Deviation angle models suitable for wider range of blade profile camber in axial⁃flow compressor [J]. Journal of Aerospace Power ， 2014 , 29 （ 8 ）: 1824 ⁃ 1831 . （in Chinese）

ZIMMEY C M ， LAPPI V M . Data for design of entrance vanes from two⁃dimensional tests of airfoils in cascade [R]. ACR No .L5G18， 1945 .

WALTKE U . Meridional flow field simulation in axial compressors using the finite element method [D]. Hanover，Germany : University of Hanover ， 1995 . （in German）

BANIAC M ， PETROVIC M V ， WIEDERMANN A . A new loss and deviation model for axial compressor inlet guide vanes [J]. Journal of Turbomachinery ， 2014 ， 136 （ 7 ）: 1 ⁃ 13 .

LIEBLEIN S ， ROUDEBUSH W H . Theoretical loss relations for low⁃speed two⁃dimensional⁃cascade flow [R].NACA TN 3662， 1956 .

KOCH C C ， SMITH L H . Loss sources and magnitudes in axial⁃flow compressors [J]. Journal of Engineering for Power ， 1976 , 98 （ 3 ）: 411 ⁃ 424 .

LIEBLEIN S . Analysis of experimental low⁃speed loss and stall characteristics of two⁃dimensional compressor blade cascades [R].NACA RM E5 7A28， 1957 .

LIEBLEIN S . Loss and stall analysis of compressor cascades [J]. Journal of Basic Engineering ， 1959 , 81 （ 3 ）: 287 ⁃ 397 .

SWAN W C . A practical method of predicting transonic⁃compressor performance [J]. Journal of Engineering for Power ， 1961 , 83 （ 3 ）: 322 ⁃ 330 .

MONSARRAT N T ， KEENAN M J ， TRAMM P C . Single‑stage evaluation of highly⁃loaded high⁃Mach⁃number compressor stages [R]. NASA CR⁃72562 ， 1969 .

JANSEN W , MOFFATT W C . The off⁃design analysis of axial⁃flow compressors [J]. Journal of Engineering for Power ， 1967 , 89 （ 4 ）: 453 ⁃ 462 .

OLDHAM R K . Some design data for double circular arc compressor blading [R]. NGTE Notes NT . 589 ，1965.

严汝群，钱肇琰 . 高亚音速二元叶栅损失的理论分析和实验研究 [J]. 工程热物理学报， 1981 , 2 （ 1 ）: 20 ⁃ 27 .

YAN Ruqun ， QIAN Zhaoyan . Theoretical analysis and experimental study on loss of high subsonic two⁃dimensional cascade [J]. Journal of Engineering Thermalphysics ， 1981 , 2 （ 1 ）: 20 ⁃ 27 . （in Chinese）

STEINERT W ， EISENBERG B ， STARKEN H . Design and testing of a controlled diffusion airfoil cascade for industrial axial flow compressor application [J]. Journal of Turbomachinery ， 1991 , 4 （ 10 ）: 583 ⁃ 590 .

ISMAILOV V E . On the approximation by neural networks with bounded number of neurons in hidden layers [J]. Journal of Mathematical Analysis and Applications ， 2014 , 417 （ 2 ）: 963 ⁃ 969 .

LI Y L ， SAYMA A . Numerical investigation of VSVs mal⁃schedule effects in a three‑stage axial compressor [R]. GT 2014⁃25145 ， 2014 .

张玙璠 . 叶轮机端区流动控制措施研究 [D]. 北京 : 北京理工大学， 2018 .

ZHANG Yufan . Research on flow control methods in the endwall region of turbomachinery [D]. Beijing : Beijing Institute of Technology ， 2018 . （in Chinese）

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design of thrust estimator in the solid rocket ramjet based on PSO⁃BP neural network

Experiment of Reynolds number effects on subsonic compressor plane cascade

Position rule of turboshaft engine surge based on bench test

Aero⁃engine on⁃board adaptive steady⁃state model base on NN⁃PSM

Analysis of dynamic characteristics of sand particles in air intake and compressor cascade of aero⁃engine

Related Author

Zhao WANG

Xiaotao TIAN

Meng HUANG

Bo ZHANG

Wei WEI

Siyuan REN

Husheng MA

Xuechen LI

Related Institution

Xi'an Modern Control Technology Research Institute，China North Industries Group Corporation Limited

Key Laboratory for Modern Control Technology，China North Industries Group Corporation Limited

Aerospace Technology Institute，China Aerodynamics Research and Development Center

Aeronautical Foundation Institute，Naval Aviation University

Unit ，People's Liberation Army

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰