Reliability evaluation of concrete‐filled steel tube arch bridge based on DBN‐PSOSA hybrid algorithm

Abstract When traditional response surface method is used to evaluate the reliability of concrete‐filled steel tubular arch bridge, due to its complex structure and highly nonlinear implicit function, the response surface fitting accuracy is not high, and the reliability accuracy is difficult to meet the requirements of design specifications. In order to solve the above problems, this paper chooses dynamic Bayesian networks (DBN) which is suitable for solving the problem of multiple state unit or system uncertainty to build implicit function of the response surface function. And this paper combines DBN and particle swarm optimization algorithm based on simulated annealing algorithm (PSOSA) to improve efficiency of model parameter optimization. It can make the construction of implicit function simulate the real structure of the limit state function. Then this paper verifies the suitability for this kind of complex structure reliability assessment of DBN‐PSOSA hybrid algorithm. A numerical example is given to demonstrate the effectiveness of the proposed method, and the reliability of a concrete filled steel tube arch bridge project is evaluated. The results show that this method improves the calculation accuracy and efficiency.