Crack identification plays a vital role in preventive maintenance strategies during highway pavement maintenance. Therefore, accurate of cracks images is the key to work. In this paper, an improved U-Net network adopting multi-scale feature prediction fusion and parallel attention module was put forward better identify concrete cracks. Multiscale combines multiple features generated by intermed...

Crack detection on bridges is an important part of assessing whether a bridge safe for service. The methods using manual inspection and bridge-inspection vehicles have disadvantages, such as low efficiency affecting road traffic. We conducted in-depth study bridge-crack proposed crack identification algorithm Unet, called the CBAM-Unet algorithm. CBAM (Convolutional Block Attention Module) ligh...

Civil infrastructure can suffer from concrete cracks due to the creep, shrinkage, diverse natural loading, aging, and corrosion of reinforcement. Concrete cracks are one of the important features when analyzing the current condition of concrete structures. The shape, length, and width information on concrete cracks are possible to conduct an initial maintenance for the structure safety. General...

This paper proposes a novel Lamb wave line sensing technique for crack detection in a welded stiffener. The proposed technique overcomes one of the biggest technical challenges of Lamb wave crack detection for real structure applications: crack-induced Lamb waves are often mixed with multiple reflections from complex waveguides. In particular, crack detection in a welded joint, one of the struc...