Structural Health Monitoring (SHM) techniques can provide vital information on the performance and capacity of new and existing structures. Generally sensors are embedded or surface mounted to assess the integrity of the structure and provide a means of damage detection or failure prediction. However, existing systems are limited by the need for contact with the structure and demand onerous set up procedures. This paper details the field and laboratory testing of a low-cost camera based SHM system. The system has been developed to provide bridge deflection data. A post-processing method has been developed within MATLAB to allow for damage and associated losses in stiffness to be successfully located on the structure, enhancing the damage identification process. The displacement identification algorithms have been tested and validated through a series of laboratory trials. On completion of the laboratory calibration this vision based system was subsequently tested using live traffic on an existing 19m span beam and slab bridge in Northern Ireland. The findings of the field trial confirm the ability of this system to accurately relate measured bridge deflections. The developed algorithms transform the measured camera or video images into a form that is highly damage-sensitive/change-sensitive for bridge assessment within the context of Structural Identification with input and output characterization. This research will significantly advance current sensor-based structural health monitoring with computer-vision techniques, leading to practical applications for damage detection of complex structures with a novel approach.
|Publication status||Published - 08 Dec 2017|
|Event||8th International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2017 - Queensland University of Technology, Brisbane, Australia|
Duration: 05 Dec 2017 → 08 Dec 2017
|Conference||8th International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2017|
|Period||05/12/2017 → 08/12/2017|