Online monitoring of crack dynamic development using attention-based deep networks

Abstract

Crack inspection is an essential means to guarantee the healthy service state of infrastructure. However, conventional methods suffer from bottlenecks such as wide blind inspection areas and low efficiency, which make it difficult to reveal the real-time development of cracks. This paper proposes an online crack analysis framework based on deep learning, aiming to effectively broaden the inspectable area and provide real-time feedback on crack development information. The proposed framework includes: (1) Lightweight attention-based crack segmentation U-shape network (CrackSeU). CrackSeU, in comparison to conventional segmentation networks, demonstrates improved fusion between multi-level and multi-scale features. According to the experimental results, CrackSeU achieves enhanced crack segmentation with reduced computation and parameters compared to several advanced network models. (2) Simple and efficient quantitative characterization algorithm. In light of the crack segmentation results, the algorithm can further quantify the actual size of cracks in the physical world, which is convenient for engineers to grasp the structural security status. (3) An online crack monitoring system incorporating the above algorithms. It enables visualization and quantitative monitoring of crack development and establishes a solid foundation for structural safety evaluation. The engineering feasibility and broad application prospect of the proposed framework are further verified by an indoor full-scale concrete beam loading test.