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.

Fatigue cracks on steel components may have strong consequences on the structure's serviceability and strength. Their detection and localization is a difficult task. Existing technologies enabling structural health monitoring have a complex link signal-to-damage or have economic barriers impeding large-scale deployment. A solution is to develop sensing methods that are inexpensive, scalable, with signals that can directly relate to damage. The authors have recently proposed a smart sensing skin for structural health monitoring applications to mesosystems. The sensor is a thin film soft elastomeric capacitor (SEC) that transduces strain into a measurable change in capacitance. Arranged in a network configuration, the SEC would have the capacity to detect and localize damage by detecting local deformation over a global surface, analogous to biological skin. In this paper, the performance of the SEC at detecting and localizing fatigue cracks in steel structures is investigated. Fatigue cracks are induced in steel specimens equipped with SECs, and data measured continuously. Test results show that the fatigue crack can be detected at an early stage. The smallest detectable crack length and width are 27.2 and 0.254 mm, respectively, and the average detectable crack length and width are 29.8 and 0.432 mm, respectively. Results also show that, when used in a network configuration, only the sensor located over the formed fatigue crack detect the damage, thus validating the capacity of the SEC at damage localization. Fatigue cracks on steel components may have strong consequences on the structure's serviceability and strength. Their detection and localization is a dicult task. Existing technologies enabling structural health monitoring have a complex link signalto-damage or have economic barriers impeding large-scale deployment. A solution is to develop sensing methods that are inexpensive, scalable, with signals that can directly relate to damage. The authors have recently proposed a smart sensing skin for structural health monitoring applications to mesosystems. The sensor is a thin lm soft elastomeric capacitor (SEC) that transduces strain into a measurable change in capacitance. Arranged in a network conguration, the SEC would have the capacity to detect and localize damage by detecting local deformation over a global surface, analogous to biological skin. In this paper, the performance of the SEC at detecting and localizing fatigue cracks in steel structures is investigated. Fatigue cracks are induced in steel specimens equipped with SECs, and data measured continuously. Test results show that the fatigue crack can be detected at an early stage. The smallest detectable crack length and width are 27.2 mm and 0.254 mm, respectively, and the average detectable crack length and width are 29.8 mm and 0.432 mm, respectively. Results also show that, when used in a network conguration, only the sensor located over the formed fatigue crack detect the damage, thus validating the capacity of the SEC at damage localizat...

No abstract

No abstract

No abstract