基于网格点扩散的二维DIC连续变形测量方法研究  

Continuous deformation measurement of 2D-DIC based on grid point diffusion

作　　者：高山[1] 陈泰铮 陈立伟[1] 崔颖[1] GAO Shan;CHEN Taizheng;CHEN Liwei;CUI Ying(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《应用科技》2023年第3期37-43,共7页Applied Science and Technology

基　　金：国家自然科学基金项目(U20A20213);中央高校基本科研业务费项目(3072021CFT0802).

摘　　要：为提高数字图像相关法(digital image correlation,DIC)测量二维连续变形时的计算效率,本文在种子点扩散法的基础上提出了网格点扩散法,实现了二维区域连续位移场以及应变场的高效测量;通过反向组合高斯牛顿法(inverse compositional Gauss-Newton method,IC-GN)实现相关匹配,结合网格点扩散以及三次样条插值得到位移场;研究多项式拟合平滑去噪方法,计算得出格林-拉格朗日应变场;对比分析网格点扩散和传统逐点相关匹配算法的计算速度以及位移测量精度。计算结果表明:本文中所提出的网格点扩散法在保证测量结果准确的同时极大地提高了计算效率。In order to improve the computational efficiency of digital image correlation(DIC)measurement of two-dimensional continuous deformation,this paper proposes a grid point diffusion method based on the seed point diffusion method,which realizes high-efficiency measurement of continuous displacement fields and strain fields in two-dimensional regions;Relevant matching is achieved by inverse compositional Gauss-Newton method(IC-GN)algorithm,and displacement field is obtained by combining grid point diffusion and cubic spline interpolation;Polynomial fitting smoothing denoising method is studied to calculate green-lagrangian strain field;The grid point diffusion and traditional point-by-point correlation matching algorithms are compared and analyzed to get the computational speed and displacement measurement accuracy.The calculation results show that the grid point diffusion method proposed in this paper can greatly improve the calculation efficiency,and in the meantime,ensure the accuracy of the measurement results.

关 键 词：数字图像相关 子集变形 相关函数 变形函数 相关匹配 亚像素位移 扩散法 应变场 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]