首页|表面应变重构的视觉识别方法

表面应变重构的视觉识别方法

扫码查看
原文链接
  • 万方数据
  • 维普
针对全断面岩石隧道掘进机刀盘在恶劣工况下的应变监测，本文提出了一种表面应变重构的视觉识别方法。通过图像中圆形标距中心点之间像素点数量的变化，得到标距的实际变形，并在此基础上结合柯西-格林公式进行表面应力重构。本文以隧道掘进机刀盘刀座和筋板 2 个关键位置为研究对象，设计了 4330V和Q345-D共 2种材料不同尺寸标准样件，搭建了基于视觉识别和基于应变片的 2 套测量系统，进行了拉伸载荷作用下的应变对比及样件表面应力重构。研究表明:本文基于视觉识别方法测得的 2 种材料标准件变形的误差范围为 1。28%～3。23%，在此基础上，进行的材料表面应力重构的误差范围为 2。20%～4。76%。本文方法可以实现变形的准确测量及实现多方向的应变和变形重构，为实现复杂结构的应变和变形测量奠定了坚实基础。
Visual recognition method for surface strain reconstruction
To monitor the strain of a full-section rock tunnel boring machine cutterhead under harsh working condi-tions,a visual recognition method for surface strain reconstruction is proposed.This paper details the process of ob-taining actual deformation of the gauge length by measuring the change in pixel count between the center points of circular gauge lengths in the image.Based on these measurements,surface stress is reconstructed using the Cauchy-Green formula.Focusing on two key positions,the tunnel boring machine cutterhead and the rib plate,the study designed two standard samples of different sizes using 4330V and Q345-D materials.Two measurement sys-tems,one based on visual recognition and the other on strain gauges,were constructed to compare strain under ten-sile load and to reconstruct the surface stress of the samples.The error range for the deformation of standard parts made of the two materials,measured using the visual recognition method,was 1.28%～3.23%.Subsequently,through the proposed method,surface strain reconstruction was conducted for the 4330V materials,with an error range of 2.20%～4.76%.The results demonstrated that this method could achieve accurate measurement of de-formation and multidirectional strain and deformation reconstruction,providing a solid foundation for the strain and deformation measurement of complex structures.

tunnel boring machine cutter headimage identificationcamera calibrationdistortion correctioncon-tour recognitiondeformation measurementstrain measurementstrain reconstruction

霍军周、李高瑞、胡清华、张占葛、葛利涵

展开 >

大连理工大学 机械工程学院,辽宁 大连 116024

中国航天员科研训练中心,北京 100094

隧道掘进机刀盘 图像识别 相机标定 畸变矫正 轮廓识别 变形测量 应变测量 应变重构

国家自然科学基金项目辽宁省重大科技专项辽宁省科技计划联合计划

522752362022HJ2/104000312023JH2/101700286

2024

10.11990/jheu.202205013

哈尔滨工程大学学报
哈尔滨工程大学

哈尔滨工程大学学报

CSTPCD北大核心
影响因子：0.655
ISSN：1006-7043
年,卷(期)：2024.45(8)