Time-dependent reliability calculation method of RC bridges based on the dual neural network

Time-dependent reliability is a key index for reliability evaluation and life prediction of existing bridges, which can reflect the service status of bridges. Therefore, the time-dependent reliability of the bridge must be calculated and analyzed in time to ensure the safety of the bridge. Many scholars have established different time-dependent reliability models, but the model contains complex multiple integrals and is difficult to calculate. In this case, the current method for calculating time-dependent reliability is Monte Carlo method, which is inefficient and cannot meet the engineering needs. In order to solve the problem that time-dependent reliability is difficult to solve, this manuscript proposes a method for solving time-dependent reliability of bridges using neural networks, which is suitable for existing time-dependent reliability models. Then, compared with the results of Monte Carlo method, the results show that the neural network used in this paper is accurate. At the same time, it can also significantly improve the computational efficiency and has significant advantages compared with the existing calculation methods. Graphic abstract