Method for tunnel cross-section deformation monitoring based on distributed fiber optic sensing and neural network

Abstract Tunnel deformation monitoring is an important process for ensuring the safety of the tunnel structure. This study presents a method for sensing tunnel cross-section deformation based on distributed fiber optic sensing and a neural network. To verify the feasibility of the proposed method, a laboratory test is conducted on a tunnel model made of polymethyl methacrylate. The test results confirm that the proposed method can accurately obtain the deformation of the tunnel structure, with a maximum deviation of 5.7%. Based on this result, a field application trial is conducted in a section of an actual subway tunnel to further verify the effectiveness of the method. The field observation result confirms the feasibility of applying the proposed method to tunnel cross-section deformation monitoring.