Reliability Analysis of Concrete Gravity Dams Based on Least Squares Support Vector Machines with an Improved Particle Swarm Optimization Algorithm

A reliability analysis method based on least squares support vector machines with an improved particle swarm optimization algorithm (IPSO-LSSVM) is proposed to calculate the of concrete gravity dams when explicit nonlinear limit-state functions are difficult obtain accurately. First, main failure modes and their influencing factors determined. Second, Latin hypercube sampling used create samples. finite element calculation batch program written safety indexes each sample. Third, samples, IPSO-LSSVM model established replace calculation. Finally, probability obtained by using Monte Carlo (MC) method. The case study for a typical dam in Yunnan Province China shows that reliable because 8.87 × 10−5. efficient feasible calculating dams.