Reliability Analysis of Cable-stayed Bridge Based on Improved PSO-SVM Method
The complexity of the structural system of cable-stayed bridges and the difficulty of revealing the structural function,which leads to the difficulty of accurately and efficiently evaluating the reliability of cable-stayed bridges in practical applications,necessitates the development of a reliability analysis method based on the improved PSO-SVM(particle swarm optimization-support vector machine).The objective of this method is to enhance the global search capability and optimize the support vector machine parameters in order to obtain implicit functional function agent models of the overdisplacement failure in the span of deflection steel-hybrid composite beams and the strength failure of a single diagonal cable,this is achieved by introducing particle swarm algorithms with two strategies of nonlinear decreasing inertia weights and asynchronous linearly varying learning factors,Monte-Carlo sampling is employed to obtain the probability distribution and statistical parameters,which are then utilized to solve the reliability index.By comparing the arithmetic examples,the method shows better results in terms of overall computation time and accuracy,and has obvious advantages over traditional methods.The reliability analysis of Yinzhou Lake Bridge was conducted using this method,and the results showed that under the action of vehicle load,the reliability index of the cable-stayed bridge with excessive displacement failure at the mid span of the main beam was 4.203,and the reliability index of each cable strength failure was 4.623-5.812,all of which meet the requirements of the specifications.The elastic modulus of cable-stayed cables and the capacity weight of cable-stayed cables have the greatest influence on the reliability index of cable-stayed bridges,and the mean values of their variables are basically linearly positively correlated with the reliability index.The reliability index of cable-stayed bridges with mid-span displacement failure decreases with the increase of the mean coefficient of elastic modulus of the cable-stayed cables,and the reliability index of cable-stayed bridges with strength failure of the cable-stayed cables 41#decreases with the increase of the mean coefficient of the cable-stayed cable-stayed weight.
万方数据
维普
