基于桥梁自然纹理的全场位移监测方法  

Full⁃field Displacement Monitoring Method Based on Bridge Natural Texture

作　　者：楚玺 周志祥 段鑫 朱伟铸 CHU Xi;ZHOU Zhixiang;DUAN Xin;ZHU Weizhu(College of Civil and Transportation Engineering,Shenzhen University,Shenzhen 518060,China)

机构地区：[1]深圳大学土木与交通工程学院,广东深圳518060

出　　处：《防灾减灾工程学报》2023年第5期965-971,共7页Journal of Disaster Prevention and Mitigation Engineering

基　　金：国家自然科学基金项目(51778094;51708068;52208182);深圳市科技计划重点项目(JCYJ20220818095608018)资助。

摘　　要：结构健康监测系统在桥梁上的测点十分有限,测试数据不完备导致结构安全状态评价困难。提出一种自然纹理条件下的结构全场位移监测方法。通过尺度不变特征变换算法提取结构表面自然纹理特征点,将提取的自然纹理特征点作为结构变形前后的点源数据,通过特征点匹配建立起变形前后特征点的位置关系。进一步,建立结构变形前后自然纹理特征点相对位置变化数学模型,提出结构全场位移矢量计算理论。最后,通过试验梁对方法进行验证,获得了试验梁的全场位移监测结果。验证结果显示,结构边缘挠度最大误差4.94%,平均误差为2.08%,全场位移矢量最大长度误差0.68 mm,最大角度误差0.76°,计算得到的全场位移矢量与结构实际变形一致。The measurement points for bridge structural health monitoring are limited,and the incomplete test data leads to the difficulty in evaluating the state of structural safety.Hence,a method of structural full-field displacement monitoring under the natural texture is proposed herein.The natural texture feature points on the surface of the structure are extracted by scale-invariant feature transformation(SIFT)algorithm.The extracted natural texture feature points are used as the point source data before and after structure deformation.The correlation between the feature points before and after deformation is established using feature point matching.Furthermore,we analyze the mathematical model of the relative position change of the feature points before and after deformation,and propose a calculation theory for the structure’s full-field displacement vector.Finally,the method is verified by the test beam's load test and the test beam's full-field displacement vector monitoring results are obtained.Validation results show that the maximum error of structural edge deflection is 4.94%,and the average error is 2.08%,the maximum length error of the full-field displacement vector is 0.68 mm and the maximum angle error is 0.76°.The calculated full-field displacement vector is in agreement with the actual structural deformation.This study is the first to to realize full-field displacement monitoring of structures under natural texture conditions,extending the traditional single-point monitoring of the structure to the two-dimensional plane monitoring,and significantly improving the completeness of the monitoring data.

关 键 词：桥梁安全 健康监测 机器视觉 特征提取 全场位移 

分 类 号：U446.2[建筑科学—桥梁与隧道工程]