土木分野におけるAIの活用(2)

[CS15-26] Development of crack detection system for shotcrete surfaces using AI in tunnel excavation surface

〇Shunsuke Uke¹, Hemmi Ryo¹, Dohta Awaji¹ (1.SHIMIZU CORPORATION)

Keywords:tunnel, the collapse of excavation surface, AI, training date

The collapse of excavation surface in the tunnel construction may lead to serious disasters. It is effective as a disaster prevention measure to recognize the crack generated in the shotcrete surface instantly as a sign of the collapse of excavation surface, and to raise the alarm. Therefore, we developed a system that can detect cracks in shotcrete surfaces in real time by image analysis using AI.In order to construct an AI model, a crack image depicted by the image editing software was used as teacher data.
As a result of the verification, it is thought that it is possible to construct an AI model that can detect the actual cracks.