Data-driven time-variant reliability assessment of bridge girders based on deep learning

This article presents a new data-driven reliability analysis framework through combining the sample convolution and interaction network (SCINet) with Bayesian probability recursion to predict the time-variant reliability of bridge girders. The structural response predicted by SCINet and the state parameter (i.e., the variance of normal distribution) estimated by Bayesian dynamic linear model (BDLM) are used to form the limit state function to predict time-variant reliability. The results with a practical bridge show that the proposed method can predict future structural responses and time-variant reliability more accurately than BDLM, long short-term memory (LSTM), and long- and short-term time-series network (LSTNet) methods.

Automated summary

This article proposes a new data-driven reliability analysis framework for predicting the time-variant reliability of bridge girders by combining SCINet and Bayesian probability recursion. The structural response predicted by SCINet and the state parameter estimated by BDLM are used to predict time-variant reliability. Experimental results show that the proposed method performs more accurately than BDLM, LSTM, and LSTNet methods in predicting future structural responses and time-variant reliability.