ABSTRACT
The corrosion of reinforcing bar in concrete has been regarded as one of the most predominant factors for the degradation of reinforced concrete (RC) bridges. The accurate predictions of corrosion damages are the basis for the safety assessment of in-service bridges and the enhancement of new bridge designs. X-ray computed tomography (XCT) has been widely utilized to understand the corrosion process inside the concrete, offering three-dimensional (3D) visualization of steel corrosion. This study uses U-net model to detect various phases of steel corrosion evolution in concrete. The developed U-net model has shown superior segmentation performance on XCT images relating to steel corrosion in concrete. This significant advancement has automated the process of visualizing and 3D reconstructing the steel corrosion process inside the concrete. It enables the quantification of the volumetric expansion ratio of corrosion products.
