Real-time reliability forecast of bridge structures based on multiple BDLMs

Based on the monitored extreme stress of bridges, a combinational forecasting model of extreme stress is constructed with the Bayesian dynamic linear model (BDLM). Then, the proposed model is used to forecast the structural reliability indices in real time. Moreover, a project case is provided to analyze the forecasting precisions of the combinational forecasting model and the existing single forecasting models. The results show that, though the proposed model is of an one-step forecasting value close to that of the single forecasting models and the mean point forecasting model, it is of higher forecasting precision, and that, as compared with the deterministic reliability indices for extreme stress monitoring, the combinational forecasting model fully considers the uncertainty and randomness of monitored stress and helps to obtain smaller reliability indices, so that it is more effective in forecasting the structural safety.