Physics-informed neural network based damage identification for truss railroad bridges

Railroad bridges are a crucial component of the U.S. freight rail system, which moves over 40% of the nation’s freight. However, ageing bridge infrastructure pose significant safety hazards and risk service disruptions. The U.S. rail network includes over 100,000 railroad bridges, averaging one every 1.4 miles of track, with steel bridges comprising over 50% of the network’s total bridge length. Early identification of damage in these bridges remain challenging tasks. This study proposes a physics-informed neural network (PINN) based approach for damage identification in steel truss railroad bridges. The proposed approach employs an unsupervised learning scheme that utilises train wheel load data and bridge response during train crossing events as inputs for damage identification. The PINN model explicitly incorporates the governing differential equations of the linear time-varying bridge-train system. Herein, this model employs a recurrent neural network based architecture incorporating a custom Runge-Kutta integrator cell, designed for gradient-based learning. A case study on the Calumet Bridge in Chicago, Illinois, with simulated damage scenarios, is used to demonstrate the model’s effectiveness in identifying damage while maintaining low false-positive rates. Furthermore, the damage identification pipeline is designed to integrate prior knowledge for enabling context-aware assessment of bridge’s condition.