表面应变重构的视觉识别方法

Visual recognition method for surface strain reconstruction

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。

To monitor the strain of a full-section rock tunnel boring machine cutterhead under harsh working conditions,a visual recognition method for surface strain reconstruction is proposed.This paper details the process of obtaining 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 systems,one based on visual recognition and the other on strain gauges,were constructed to compare strain under tensile 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 deformation and multidirectional strain and deformation reconstruction,providing a solid foundation for the strain and deformation measurement of complex structures.