基于计算机视觉的人行桥损伤识别

兰州理工大学学报 ›› 2025, Vol. 51 ›› Issue (6): 116-124.

基于计算机视觉的人行桥损伤识别

崔德鹏, 王翠云, 朱前坤^*

兰州理工大学防震减灾研究所, 甘肃兰州 730050

收稿日期:2022-03-03 发布日期:2025-12-31
通讯作者: 朱前坤(1981-),男,江苏徐州人,教授,博导.Email:zhuqk@lut.edu.cn
基金资助:
国家自然科学基金(52168041,51868046),研究生教育质量工程(56-256017)

Damage identification of footbridge based on computer vision

CUI De-peng, WANG Cui-yun, ZHU Qian-kun

Institute of Earthquake Protection and Disaster Mitigation, Lanzhou University of Technology, Lanzhou 730050, China

Received:2022-03-03 Published:2025-12-31

摘要/Abstract

摘要： 针对现有的桥梁振动损伤识别系统效率低、对微小振动识别效果差等问题, 提出了基于计算机视觉的人行桥损伤非接触识别方案. 采用基于相位的运动放大技术和分段光流法, 并结合基于附加质量的结构损伤识别方法识别结构的损伤. 在实验室人行桥模型上进行了三种不同工况的试验, 验证方案对结构振动识别的可行性,方案通过结构模态MAC值的变化以及振型变化判断出结构是否损伤和损伤发生的位置. 结果表明:由方案识别得到的在三种工况下人行桥在振动时程内的模态信息更为完整, 较传统HS光流法精度更高, 且可以判断出结构是否损伤和损伤发生的位置, 可达到工程结构损伤质量评估的第二层次;方案鲁棒性强且经济性好, 具备广泛的应用前景.

关键词: 计算机视觉, 损伤识别, 光流法, 运动放大, 非接触

Abstract: A noncontact damage identification scheme for footbridges based on computer vision is established to solve the problems of low-efficiency of the existing bridge vibration damage identification system and poor identification effect of small vibration. The phase-based motion magnification technique and the segmented optical flow method are combined with the additional mass method for structural damage identification to identify structural damage. The feasibility of the proposed method for structural vibration identification is verified by the experiments under three different working conditions on the laboratory footbridge model. The system can judge whether the structure is damaged and the location of damage by the change of modal MAC values and mode shapes. The results show that the modal information of the footbridge in the vibration time-history is more complete and accurate than that of the HS optical flow method under the three conditions, and successfully identifies both the presence and location of structural damage, which can reach the second level of damage quality evaluation of engineering structures. The scheme has a wide application prospect for its robustness and economics.

Key words: computer vision, damage identification, optical flow method, motion magnification, non-contact

中图分类号:

U441

崔德鹏, 王翠云, 朱前坤. 基于计算机视觉的人行桥损伤识别[J]. 兰州理工大学学报, 2025, 51(6): 116-124.

CUI De-peng, WANG Cui-yun, ZHU Qian-kun. Damage identification of footbridge based on computer vision[J]. Journal of Lanzhou University of Technology, 2025, 51(6): 116-124.

参考文献

[1] CHAPUIS B.Introduction to structural health monitoring[M]//Sensors,Algorithms and Applications for Structural Health Monitoring.Cham:Springer International Publishing,2018:1-11.
[2] PATHIRAGE C S N,LI J,LI L,et al.Structural damage identification based on autoencoder neural networks and deep learning[J].Engineering Structures,2018,172:13-28.
[3] SONY S,LAVENTURE S,SADHU A.A literature review of next-generation smart sensing technology in structural health monitoring[J].Structural Control and Health Monitoring,2019,26(3):2321.
[4] HOU R,XIA Y.Review on the new development of vibration-based damage identification for civil engineering structures:2010-2019[J].Journal of Sound and Vibration,2021,491:115741.
[5] 李慧民,董美美,熊雄,等.基于振动的结构损伤识别研究综述[J].建筑结构,2021,51(4):45-50.
[6] DONG C Z,YE X W,JIN T.Identification of structural dynamic characteristics based on machine vision technology[J].Measurement,2018,126:405-416.
[7] FENG D,FENG M Q.Computer vision for SHM of civil infrastructure:from dynamic response measurement to damage detection-a review[J].Engineering Structures,2018,156:105-117.
[8] 朱前坤,崔德鹏,张琼,等.利用计算机视觉识别人行桥时变模态参数[J].振动工程学报,2023,36(1):52-61.
[9] 曾雅颖,周奎.基于曲率模态和柔度曲率的梁结构损伤识别[J].武汉理工大学学报,2013,35(5):99-104.
[10] 张冬兵,江祥林,曾国良.附加质量对桁架桥频率影响研究[J].武汉理工大学学报,2012,34(3):97-100.
[11] 张青霞,ŁUKASZ J.基于移动质量-频率曲线的结构损伤识别方法[J].中国测试,2019,45(3):1-6.
[12] 路平,王龙,段静波,等.基于附加质量的梁损伤识别影响因素分析[J].解放军理工大学学报(自然科学版),2017,18(3):295-301.
[13] WADHWA N,RUBINSTEIN M,DURAND F,et al.Phase-based video motion processing[J].ACM Transactions on Graphics,2013,32(4):1-10.
[14] HUANG G,XU L,CHEN Q L,et al.Research on image enhancement model based on variable order fractional differential CLAHE[C]//Quality,Reliability,Security and Robustnessin Heterogeneous Systems.Cham:Springer International Publishing,2021:209-226.
[15] 吕钧澔,校金友,文立华,等.基于视觉分区的结构振动模态测试方法[J].工程力学,2022,39(3):249-256.
[16] 朱前坤,崔德鹏,杜永峰.基于网络摄像机的桥梁挠度非接触识别[J].工程力学,2022,39(6):146-155.
[17] HERMANS L,VAN DER AUWERAER H.Modal testing and analysis of structures under operational conditions:industrial applications[J].Mechanical Systems and Signal Processing,1999,13(2):193-216.
[18] 杨秋伟,刘济科.结构损伤识别的附加质量方法[J].工程力学,2009,26(5):159-163.
[19] 李书明,何亮,程关兵.基于振动分析的结构损伤检测方法研究[J].中国民航学院学报,2006,24(5):26-29.
[20] WANG L,LIE S T,ZHANG Y.Damage detection using frequency shift path[J].Mechanical Systems and Signal Processing,2016,66:298-313.
[21] YANG C,OYADIJI S O.Delamination detection in composite laminate plates using 2d wavelet analysis of modal frequency surface[J].Computers and Structures,2017,179(C):109-126.
[22] LI W,CHEN Y,LU Z R,et al.Parameter identification of nonlinear structural systems through frequency response sensitivity analysis[J].Nonlinear Dynamics,2021,104(4):3975-3990.