Estimation of full‐field, full‐order experimental modal model of cable vibration from digital video measurements with physics‐guided unsupervised machine learning and computer vision

Abstract

Cables are critical components for a variety of structures such as stay cables and suspenders of cable-stayed bridges and suspension bridges. When in operational service, they are vulnerable to cumulative fatigue damage induced by dynamic loads (e.g., the cyclic vehicle loads and wind excitation). To accurately analyze and predict their dynamics behaviors and performance that could be spatially local and temporal transient, it is essential to perform highresolution vibration measurements, from which their dynamics properties are identified and, subsequently, a high spatial resolution, full-modal-order dynamics model of cable vibration can be established. This study develops a physics-guided, unsupervised machine learning-based video processing approach that can blindly and efficiently extract the fullfield (as many points as the pixel number of the video frame) modal parameters of cable vibration using only the video of an operating (output-only) cable. In particular, by incorporating the physics of cable vibration (taut string model), a novel automated modal motion filtering method is proposed to enable autonomous identification of full-order (as many modes as possible) dynamic parameters, including those weakly excited modes that used to be challenging to identify in operational modal analysis. Therefore, a full-field, full-order modal model of cable vibration is established by the proposed method. Furthermore, this new approach provides a low-cost and noncontact technique to estimate the cable tension using only the video of the vibrating cable where the fundamental frequency is automatically and efficiently estimated to compute the cable tension according to the taut string equation. Laboratory experiments on a bench-scale cable are conducted to validate the developed approach.

Machine learning paradigm for structural health monitoring

“…Yang's group has done systematic work on this topic and used video motion processing combined with structural dynamics models to enable extraction and visualization of fullfield, high spatial resolution modal parameters in a relatively efficient and automated manner. This work has been further adapted to extract high-dimensional modal parameters from sub-Nyquist videos 58 and cable vibration videos 59 and for neuromorphic event-based imaging 60 and detecting small damage. 61 Hoskere et al 62 proposed a divide-and-conquer technique for system identification of full-scale civil infrastructure using a UAV video survey.…”

Computer vision‐based real‐time cable tension estimation in Dubrovnik cable‐stayed bridge using moving handheld video camera

“…Basic optical flow‐based technique 28 and robust subpixel orientation code matching (OCM) algorithm 29 are recently developed for motion estimation of a cable. Video‐based motion estimation combined with blind source separation techniques are used for structural response estimation in Yang et al 30 Modal identification and the constant tension force estimation of the cable are executed using phase‐based motion estimation in Yang et al 30 Tension force in cable can also be calculated using a recently published full‐field edge response estimation algorithm using static camera 31,32 . Vision‐based measurements give rise to big data, which is beneficial for intensive structural health monitoring of such bridges 33,34 …”

Computer vision‐based monitoring of the 3‐D structural deformation of an ancient structure induced by shield tunneling construction

“…Many kinds of research work have been done to explore the application of this method in the field of civil engineering [14–18]. Up to now, most of these studies mainly focus on the one‐dimensional or two‐dimensional investigations using cameras or unmanned aerial vehicles (UAVs) [19–21].…”