A Subdomain Uncertainty-Guided Kriging Method with Subset Simulation for Reliability Estimation

Abstract

Direct Monte Carlo Simulation for reliability estimation of rare failure event is challenged by the complicated performance function evaluations and large candidate sample pool. To address these challenges, a subdomain uncertainty- guided Kriging method with subset simulation is proposed. With a concise uncertainty assessment function, efficient subdomain uncertainty-guided sampling strategy is first developed to refine the Kriging model that is used to replace real performance function approximately. Moreover, the number of candidate samples required by subset simulation is also significantly reduced. By sequentially exploiting within the candidate sample pools generated in the first intermediate failure event and other intermediate failure events, an accurate Kriging model can be constructed subsequently. The ingenious method of coupling Kriging and subset simulation can greatly improve the efficiency of reliability estimation. Finally, three classical examples are investigated as benchmark to explore the performance of the proposed method. The comparison results demonstrate the good capability and applicability of the proposed method.