Seismic Response Prediction of Instrumented Pre-1971 Highway Bridges in California

Recent earthquake disasters have demonstrated the seismic vulnerability of highway bridge systems and the significance of the ensuing social impact. Rapid seismic assessment of regional highway bridges is critical to help reduce the severe loss of life and property. Firstly, the typical modeling technique for reinforcement concrete highway bridges is introduced using specific elements for different components. However, the modeling procedures are material-level parameter-dependent and time-consuming. The nonlinear analysis convergence is also a frustrating problem for numerical simulation. Due to these realistic limitations, a simple, fast, and robust numerical model that can be developed with only component-level information needs to be adopted. It’s shown that the bridge bent representation can be simplified as a single degree of freedom system. The force-displacement relationship of the bridge can be roughly approximated by a bilinear curve. So a simplified 2D bilinear model is adopted for highway bridges throughout the study. Secondly, the statistical distributions for selected bridge input parameters can be derived based on the regional bridge inventory. Then an iterative process by sampling and filtering input parameters can be used to generate as many bridge candidates as possible for a specific region. The proposed bridge models and selected historical ground motions will be utilized to develop a seismic response prediction model using machine learning for an instrumented highway bridge. This study investigates the optimal features to represent the highway bridge and ground motion. Different regression models are applied for bridges with near-fault motion, and it’s shown the accuracy of the guided machine learning prediction model has exceeded the performance of traditional methods. A discounted accuracy is observed when applying the same machine learning prediction model in the highway bridge with far-field ground motion, And a two-layer LSTM network is developed with a new representation of far-field ground motion as the input