Neural network method in parametric probabilistic sensitivity analysis and its application

The analysis of parametric probabilistic sensitivity analysis is important for reliability-based design, which shows changes of system reliability caused by the change of basic variances.In this paper,the commerical FE simulation-neural network-Monte Carlo methods were used together,based on the quick-response model,the parametric probabilistic sensitivity was analyzed too,and a new scaling parameter was presented here considering the global disperisty of stochastic parameters.The sensitivity indices can be computed by the simple and approximate formula in engineering.A numerical example is presented to verify the feasibility and the effectivity by comparing with the analysis of ANSYS.