基于神经网络的表面热流辨识三维效应修正

潘学浩; 陈伟芳; 彭玉酌; 杨华

doi:10.7638/kqdlxxb-2017.0069

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于神经网络的表面热流辨识三维效应修正

研究论文 | 更新时间：2026-05-28

- 基于神经网络的表面热流辨识三维效应修正
- Study on three-dimensional effect correction of surface heat flux estimation based on neural network
- 空气动力学学报 2019年37卷第4期页码：555-562
- 作者机构：
  
  1. 浙江大学航空航天学院,杭州,310027
  2. 航空工业第一飞机设计研究院,西安,710089
- 作者简介：
  
  潘学浩(1994-), 男, 硕士, 主要研究方向为高超声速气动辨识.E-mail:xhpan_16@zju.edu.cn
  陈伟芳(1970-), 男, 教授、博士生导师, E-mail:chenwfnudt@163.com
- 基金信息：
  
  国家自然科学基金(51575487);国家科技部973计划(2014CB340201)
- DOI：10.7638/kqdlxxb-2017.0069
  中图分类号： V211.3
- 纸质出版：2019
- 稿件说明：
移动端阅览
潘学浩, 陈伟芳, 彭玉酌, 杨华. 基于神经网络的表面热流辨识三维效应修正[J]. 空气动力学学报, 2019, 37(4): 555-562.

PAN Xuehao, CHEN Weifang, PENG Yuzhuo, et al. Study on three-dimensional effect correction of surface heat flux estimation based on neural network[J]. 2019, 37(4): 555-562.
潘学浩, 陈伟芳, 彭玉酌, 杨华. 基于神经网络的表面热流辨识三维效应修正[J]. 空气动力学学报, 2019, 37(4): 555-562. DOI： 10.7638/kqdlxxb-2017.0069.

PAN Xuehao, CHEN Weifang, PENG Yuzhuo, et al. Study on three-dimensional effect correction of surface heat flux estimation based on neural network[J]. 2019, 37(4): 555-562. DOI： 10.7638/kqdlxxb-2017.0069.

摘要

在已有顺序函数法对一维、二维表面热流辨识的研究基础上，考虑到三维辨识实时性的困难，提出神经网络和顺序函数法结合的方法。在顺序函数法一维辨识结果的基础上，利用人工神经网络对热传导三维效应进行修正，从而获得峰值热流实时准确的辨识结果。为了获得更优的神经网络模型，引入粒子群算法优化神经网络的初始权值和阈值。通过数值仿真的算例测试结果可以看出，本文提出的方法对于峰值热流的辨识结果准确度在4%以内，避免了三维辨识的时间复杂性，同时具有良好的抗噪性和稳定性。

Abstract

Based on the existing sequential function method for one-dimensional and two-dimensional surface heat flux identification

this paper presents a combination of neural network and sequential function method considering the real-time difficulty of three-dimensional identification. In this paper

a neural network is designed to correct the three-dimensional effects based on the results of one-dimensional identification

which can get accurate real-time results of peak heat flux. Moreover

PSO algorithm is introduced to optimize the initial weights and thresholds of the neural network in order to obtain a better model. It can be seen from the test results that the method presented for the peak heat flux is accurate with errors less than 4%. The method avoids time complexity of three-dimensional identification and has good noise immunity and stability at the same time.

关键词

Keywords

references

ALIFANOV O M. Inverse heat transfer problems[M]. Berlin:Springer Science Business Media, 2012.

ZENG L. Study on data processing method and error mechanism analysis of heat flux measurement in wind tunnel[D]. Mianyang: China Aerodynamics Research and Development Center, 2012. (in Chinese)

NEUMANN R D, ERBLAND P J, KRETZ L O. Instrumentation of hypersonic structures a review of past application and need of the future. AIAA 88-2612[R]. Reston: AIAA, 1988.

MENG S H, DING X H, YI F J, et al. Overview of heat measurement technology for hypersonic vehicle surfaces[J]. Acta Aeronautica et Astronautica Sinica, 2014, 35(7):1759-1775. (in Chinese)

WRIGHT R L, ZOBY E V. Flight boundary layer transition measurements on a slender cone at Mach 20[R]. AIAA-77-719, 1977.

QIAN W Q, ZHOU Y, HE K F. Estimation of surface heat flux for nonlinear inverse heat conduction problem[J]. Acta Aerodynamica Sinica, 2012, 30(2):145-150. (in Chinese)

QIAN W Q, CAI J S. Solving two-dimensional transient inverse heat conduction problem with sequential function method[J]. Acta Aerodynamica Sinica, 2002, 20(3):274-280. (in Chinese)

QIAN W Q, HE K F, WANG Q. Inverse estimation of heat source term in three-dimensional transient heat conduction problem[J]. Chinese Journal of Theoretical and Applied Mechanics, 2008, 40(5):611-617. (in Chinese)

XUE Q W, WEI W. Parameters identification of non-linear inverse heat conduction problem[J]. Engineering Mechanics, 2010, 27(8):5-9. (in Chinese)

DENG S, WANG Y H. Applying neural networks to the solution of forward and inverse heat conduction problems[J]. International Journal of Heat and Mass Transfer, 2006, 49(25-26):4732-4750.

ZHI H Q. Application of neural networks and genetic algorithms in inverse heat conduction problem[D]. Tianjin: Hebei University of Technology, 2004. (in Chinese)

CUI M, LI N, LIU Y F, et al. Robust inverse approach for two-dimensional nonliner heat conduction problem[J]. Journal of Thermophysics and Heat Transfer, 2015, 29(2):253-262.

QIAN W Q, ZHOU Y, HE K F. Heat flux estimation for heat transfer problem with ablation[J]. Acta Aerodynamica Sinica, 2014, 32(6):772-776. (in Chinese)

ZHANG C. Identification method investigation of supersonic combustor wall heat flux[D]. Harbin: Harbin Institute of Technology, 2011. (in Chinese)

ZHANG L H, WANG G J, CHEN H, et al. Solving transient inverse heat conduction problems based on optimal number of future time steps[J]. Proceedings of the CSEE, 2012, 32(2):99-103. (in Chinese)

MAO J, ZHAO H D, YAO J J. Application and prospect of artificial neural network[J]. Electronic Design Engineering, 2011, 19(24):62-65. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于卷积神经网络的合成双射流控制机翼分离流场识别与参数优化

高空长航时无人机螺旋桨后掠桨叶气动研究

风扇叶片颗粒侵蚀特性的多因素分析与模拟

安装效应对螺旋桨纯音噪声的影响

热防护材料动态烧蚀形貌结构光视觉测量技术