Fatigue cracks developed under repetitive loads are one of the major threats to structural integrity of steel bridges. Human inspection is the most commonly applied approach for fatigue crack detection, but is time consuming, labor intensive, and lacks reliability. In this study, we propose a computer vision-based fatigue crack detection approach using a short video stream taken by a consumer-grade digital camera. A feature tracking technology is applied to the video for tracking the surface motion of the monitored structure under repetitive load. Then, a crack detection and localization algorithm is established to effectively search differential features at different video frames caused by the crack opening and closing. The effectiveness of the proposed approach is validated through testing two experimental specimens with in-plane and out-of-plane fatigue cracks, respectively. Results indicate that the proposed approach can robustly identify the fatigue crack, even when the crack is under ambient lighting conditions, surrounded by other crack-like edges, covered by complex surface textures, or invisible to human eyes due to crack closure. Furthermore, our proposed approach enables accurate quantification of the crack opening under fatigue loading with submillimeter accuracy. However, due to the capacity of the camera resolution in this study, accurate detection of crack tip remains challenging.

Self-loosening of bolts caused by repetitive loads and vibrations is one of the common defects that can weaken the structural integrity of bolted steel joints in civil structures. Many existing approaches for detecting loosening bolts are based on physical sensors and, hence, require extensive sensor deployment, which limit their abilities to cost-effectively detect loosened bolts in a large number of steel joints. Recently, computer vision-based structural health monitoring (SHM) technologies have demonstrated great potential for damage detection due to the benefits of being low cost, easy to deploy, and contactless. In this study, we propose a vision-based non-contact bolt loosening detection method that uses a consumer-grade digital camera. Two images of the monitored steel joint are first collected during different inspection periods and then aligned through two image registration processes. If the bolt experiences rotation between inspections, it will introduce differential features in the registration errors, serving as a good indicator for bolt loosening detection. The performance and robustness of this approach have been validated through a series of experimental investigations using three laboratory setups including a gusset plate on a cross frame, a column flange, and a girder web. The bolt loosening detection results are presented for easy interpretation such that informed decisions can be made about the detected loosened bolts.

This paper presents a novel large-area strain sensing technology for monitoring fatigue cracks in steel bridges. The technology is based on a soft elastomeric capacitor (SEC), which serves as a flexible and large-area strain gauge. Previous experiments have verified the SEC’s capability to monitor low-cycle fatigue cracks experiencing large plastic deformation and large crack opening. Here an investigation into further extending the SEC’s capability for long-term monitoring of fatigue cracks in steel bridges subject to traffic loading, which experience smaller crack openings. It is proposed that the peak-to-peak amplitude (pk–pk amplitude) of the sensor’s capacitance measurement as the indicator of crack growth to achieve robustness against capacitance drift during long-term monitoring. Then a robust crack monitoring algorithm is developed to reliably identify the level of pk–pk amplitudes through frequency analysis, from which a crack growth index (CGI) is obtained for monitoring fatigue crack growth under various loading conditions. To generate representative fatigue cracks in a laboratory, loading protocols were designed based on constant ranges of stress intensity to limit plastic deformations at the crack tip. A series of small-scale fatigue tests were performed under the designed loading protocols with various stress intensity ratios. Test results under the realistic fatigue crack conditions demonstrated the proposed crack monitoring algorithm can generate robust CGIs which are positively correlated with crack lengths and independent from loading conditions.

The field of structural engineering is vast, spanning areas from the design of new infrastructure to the assessment of existing infrastructure. From the onset, traditional entry-level university courses teach students to analyse structural responses given data including external forces, geometry, member sizes, restraint, etc.—characterizing a forward problem (structural causalities → structural response). Shortly thereafter, junior engineers are introduced to structural design where they aim to, for example, select an appropriate structural form for members based on design criteria, which is the inverse of what they previously learned. Similar inverse realizations also hold true in structural health monitoring and a number of structural engineering sub-fields (response → structural causalities). In this light, we aim to demonstrate that many structural engineering sub-fields may be fundamentally or partially viewed as inverse problems and thus benefit via the rich and established methodologies from the inverse problems community. To this end, we conclude that the future of inverse problems in structural engineering is inexorably linked to engineering education and machine learning developments.

Distortion-induced fatigue cracks represent the majority of fatigue cracks in steel bridges in the United States. Currently, bridge owners, such as the state departments of transportation, rely on human inspection to detect, monitor, and quantify these cracks so that appropriate repairs can be applied before cracks reach critical sizes. However, visual inspections are costly, labor intensive, and may be prone to error due to inconsistent skills among bridge inspectors. In this study, we represent a novel strain-based approach for sensing distortion-induced fatigue cracks in steel bridges using soft elastomeric capacitor (SEC) arrays. Compared with traditional foil strain gauges, the SEC technology is a large-area and flexible skin-type strain sensor that can measure a wide range of strain over a large surface. Previous investigations have verified the suitability of a single SEC for sensing an in-plane fatigue crack in a small-scale steel specimen. In this paper, we further demonstrate the ability of SECs for sensing distortion-induced fatigue cracks. The proposed strategy consists of deploying an array of SECs to cover a large fatigue-susceptible region and establishing a fatigue sensing algorithm by constructing a crack growth index (CGI) map. The effectiveness of the strategy was experimentally validated through fatigue tests of bridge girder to cross-frame connection models with distortion-induced fatigue cracks. Test results verified that by deploying an SEC array, multiple CGIs can be obtained over the fatigue-susceptible region, offering a more comprehensive picture of fatigue damage. Furthermore, by monitoring a series of CGI maps constructed under different fatigue cycles, the fatigue crack growth can be clearly visualized through the intensity change in the CGI maps.