卷积神经网络在风洞天平静态校准中的应用

汪运鹏; 聂少军; 王粤; 姜宗林

doi:10.7638/kqdlxxb-2022.0096

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 >

卷积神经网络在风洞天平静态校准中的应用

研究论文 | 更新时间：2026-05-28

- 卷积神经网络在风洞天平静态校准中的应用
- Application of convolutional neural network in static calibration of wind tunnel balance
- 空气动力学学报 2023年41卷第3期页码：25-32
- 作者机构：
  
  1. 中国科学院力学研究所高温气体动力学国家重点实验室,北京,100190
  2. 中国科学院大学工程科学学院,北京,100049
- 作者简介：
  
  汪运鹏*（1978-），男，正高级工程师，研究方向：脉冲风洞天平测力. E-mail：wangyunpeng@imech.ac.cn
- 基金信息：
  
  国家自然科学基金（11672357，11727901）
- DOI：10.7638/kqdlxxb-2022.0096
  中图分类号： TP183;V211.752
- 纸质出版：2023
- 稿件说明：
移动端阅览
汪运鹏, 聂少军, 王粤, 等. 卷积神经网络在风洞天平静态校准中的应用[J]. 空气动力学学报, 2023, 41(3): 25−32.

WANG Yunpeng, NIE Shaojun, WANG Yue, et al. Application of convolutional neural network in static calibration of wind tunnel balance[J]. 2023, 41(3): 25-32.
汪运鹏, 聂少军, 王粤, 等. 卷积神经网络在风洞天平静态校准中的应用[J]. 空气动力学学报, 2023, 41(3): 25−32. DOI： 10.7638/kqdlxxb-2022.0096

WANG Yunpeng, NIE Shaojun, WANG Yue, et al. Application of convolutional neural network in static calibration of wind tunnel balance[J]. 2023, 41(3): 25-32. DOI： 10.7638/kqdlxxb-2022.0096.

摘要

风洞天平是气动试验中用于测量作用在模型上的空气动力载荷（力与力矩）的大小、方向和作用点的装置，测量结果的精准度与天平的静态校准性能直接相关，天平的静态校准是通过校测设备建立天平测量信号与所受气动载荷的映射关系。由于多分量风洞天平的各个分量间存在相互干扰，并且通常二次干扰和组合干扰会出现非线性特性，采用线性拟合方法会产生一定的误差，使得风洞天平静态校准性能因受到数据处理方法（线性拟合）的局限而较难进一步提高。因此，为了进一步提升应变天平静态校准的性能，本文探索深度学习方法在风洞天平静态校准中的应用。利用中国科学院力学研究所风洞天平校准系统AiBCS，对六分量应变天平开展基于卷积神经网络的静态校准研究，采用深度学习训练模型代替传统风洞天平校准公式并获取更高性能指标。同时，对人工智能建模方法在天平静态校准中的适用条件、有效性及可靠性等方面进行了讨论和评估分析。数据结果显示：相较于传统的基于最小二乘多项式的拟合方法，卷积神经网络天平校准方法有效降低了天平各个分量间的载荷干扰，使校准结果的精准度得到了较大幅度的提升。

Abstract

As the most important measuring device in aerodynamic testing

the wind tunnel balance is used to measure the magnitude

direction

and point of the aerodynamic loads (forces and moments) acting on the test model. The accuracy of the measurement is directly related to the static calibration of the wind tunnel balance

which establishes the mapping relationship between the balance output signals and aerodynamic loads on the calibration equipment. This paper explores the possibility of improving the calibration performance of the strain-gauge balance in the calibration system AiBCS

developed by Institute of Mechanics of Chinese Academy of Science

using the convolutional neural network (CNN). The applicable conditions

validity

and reliability of CNN in the balance calibration are discussed and evaluated. Results obtained by the CNN-based calibration method and the traditional polynomial fitting method are analyzed and compared. It turns out that the CNN-based calibration method can effectively reduce the load interference between various balance components

yielding a significantly improved performance. Consequently

the deep-learning technology shows great application potential in calibrating wind tunnel balance.

关键词

Keywords

references

战培国. 国外风洞天平技术研究进展[J]. 飞航导弹, 2018(10): 63-68. Doi: 10.16338/j.issn.1009-1319.20180123

ZHAN P G. Development of wind tunnel balance calibration techniques[J]. Aeronautical Science Technology, 2012, 23(2): 18-20. (in Chinese)

武家騊. 应变天平多元校中几种数据处理方法的比较[J]. 气动实验与测量控制, 1994, 8(3): 55-58.

CHE B H, YIN X F, PENG X M, et al. Research on data processing method of balance calibration based on BP neural network[J]. Computer Measurement Control, 2020, 28(10): 165-169. (in Chinese)

GUO L H, ZHOU Y. The design of BP neural network based on MATLAB toolbox[J]. Information Technology and Informatization, 2009(3): 20-22. (in Chinese)

汪晓东, 万旭, 赵鹏程, 王骥程. 基于神经网络的传感器静态误差综合修正法[J]. 仪器仪表学报, 1997, 18(3): 310-313. doi: 10.19650/j.cnki.cjsi.1997.03.018

YU Z, YU W C. A static calibration system of torque sensor based on BP neural network[J]. Chinese Journal of Sensors and Actuators, 2020, 33(2): 238-244. (in Chinese)

贺德馨. 风洞天平[M]. 北京: 国防工业出版社, 2001.

中华人民解放军总装备部. 风洞应变天平规范[S]. GJB 2244A—2011.

WANG Y P, LI X G, JIANG Z L. High-accuracy fully automatic calibration system for impulse balance[J]. Scientia Sinica (Physica, Mechanica Astronomica), 2020, 50(6): 064702. (in Chinese)

WANG Y P, HU Z M, LIU Y F, et al. Starting process in a large-scale shock tunnel[J]. AIAA Journal, 2016, 54(4): 1240-1249. DOI:10.2514/1.J054145

YAN W F, ZHANG C K, JIANG K, et al. Experimental investigation on technology of force measurement using a distributed-sting-balance in wind tunnel[J]. Advances in Aeronautical Science and Engineering, 2021, 12(6): 101-109. (in Chinese)

WANG Y P, YANG R X, NIE S J, et al. Deep-learning-based intelligent force measurement system using in a shock tunnel[J]. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(5): 1304-1313. (in Chinese)

HANG B, JOHNSON I. An investigation of method on strain gauge wind tunnel balance calibration for a rig without repositioning, Part I: Deduction of algorithms for component corrections[R]. FFA TN 1988-06, 1988.

HANG B, JOHNSON I. An investigation on methods of wind tunnel balance calibration for a rig without repositioning after loading, Part II: Comparison of three methods using measured data[R]. FFA TN 1988-14, 1988.

郑泽宇, 梁博文, 顾思宇. TensorFlow: 实战Google深度学习框架[M]. 第2版. 北京: 电子工业出版社, 2018.

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

基于多元正交函数的风洞天平校准建模方法

飞行器模型表面三维温度场重建方法

基于卷积时序网络的防冰翼面瞬态温度场预测

基于神经网络的线性稳定性分析方法

基于深度学习的超分辨率重构方法在CAARC标模绕流流场重构中的应用