Quantile-based optimization under uncertainties for complex engineering structures using active learning basis-adaptive PC-Kriging model

Abstract

The reliability-based design optimization (RBDO) of complex engineering structures considering uncertainty has problems of high-dimensional, highly nonlinear and time-consuming, which requires a significant amount of sampling simulation computation. In this paper, a basis-adaptive PC-Kriging surrogate model is proposed, in order to relieve the computational burden and enhance predictive accuracy of metamodel. The active learning basis-adaptive PC-Kriging model is combined with quantile-based RBDO framework. Finally, four engineering cases have been implemented, including a benchmark RBDO problem, two high dimensional explicit problems and a high dimensional implicit problem. Compared with SVM, Kriging and polynomial chaos expansion models, the results show that the proposed basis-adaptive PC-Kriging model is more robust and efficient for RBDO problems of complex engineering structures.