Due to the increase in aging structures and the decrease in construction workforce, there is an increasing interest in automating structural damage monitoring. Surface damage on concrete structures, such as cracks, delamination, and rebar exposure, is one of the important parameters that can be used to estimate the condition of the structure. In this paper, deep learning-based detection and quantification of structural damage using structured lights and a depth camera is proposed. The proposed monitoring system is composed of four lasers and a depth camera. The lasers are projected on the surface of the structures, and the camera captures images of the structures while measuring distance. By calculating an image homography, the captured images are calibrated when the structure and sensing system are not in parallel. The Faster RCNN (Region-based Convolutional Neural Network) with Inception Resnet v2 architecture is used to detect three types of surface damage: (i) cracks; (ii) delamination; and (iii) rebar exposure. The detected damage is quantified by calculating the positions of the projected laser beams with the measured distance. The experimental results show that structural damage was detected with an F1 score of 0.83 and a median value of the quantified relative error of less than 5%.
25 March 2016 in Structural Monitoring and Maintenance
Recent R&D activities on structural health monitoring in Korea smart sensors;structural health monitoring;damage detection;civil infrastructure; In this paper, recent research trends and activities on structural health monitoring (SHM) of civil infrastructure in Korea are reviewed. Recently, there has been increasing need for adopting smart sensing technologies to SHM, so this review focuses on smart sensing, monitoring, and assessment for civil infrastructure. Firstly, the research activities on smart sensor technology is reviewed including optical fiber sensors, piezoelectric sensors, wireless smart sensors, and vision-based sensing system. Then, a brief overview is given to the recent advances in smart monitoring and assessment techniques such as vibration-based global monitoring techniques, local monitoring with piezoelectric materials, decentralized monitoring techniques for wireless sensors, wireless power supply and energy harvest. Finally, recent joint SHM activities on several test beds in Korea are discussed to share the up-to-date information and to promote the smart sensors and monitoring technologies for applications to civil infrastructure. It includes a Korea-US joint research on test bridges of the Korea Expressway Corporation (KEC), a Korea-US-Japan joint research on Jindo cable-stayed bridge, and a comparative study for cable tension measurement techniques on Hwamyung cable-stayed bridge, and a campaign test for displacement measurement techniques on Sorok suspension bridge.
In this study, we present a method to estimate the depth of near-surface shallow delamination in concrete using a noncontact micro-electromechanical system (MEMS) ultrasonic sensor array and an optimization-based data processing approach. The proposed approach updates the bulk wave velocities of the tested concrete element by solving an optimization problem using reference ultrasonic scanning data collected from a full-depth concrete region. Subsequently, the depth of concrete delamination is estimated by solving a separate optimization problem. Numerical simulations and laboratory experiments were conducted to evaluate the performance of the proposed ultrasonic data processing approach. The results demonstrated that the depth of shallow delamination in concrete structures could be accurately estimated.
A vision sensor-based 6-DOF displacement evaluation method incorporating a genetic algorithm was proposed to monitor the critical defects of port infrastructure, such as deflection, slope, and slip. The 6-DOF behavior of the port structure, including subsidence, was estimated based on the specification of the target and fixed structures nearby. The method calculates the relative position of the target port structure and measures the movement of the structure over time. To improve the measurement accuracy, a genetic algorithm was used to adjust the intrinsic parameters that were previously estimated using the checkerboards. The results of measuring 6-DOF displacements based on the tuned intrinsic parameters confirmed that it has the potential to accurately measure the 6-DOF behavior of port facilities. The possibility of field application was examined through an artificial movement that was induced in the image of the port facility to create an arbitrary displacement between two points.
1 July 2016 in Construction and Building Materials