Release time:2024-10-25
Impact Factor:8.1
DOI number:10.1016/j.ress.2023.109664
Journal:Reliability Engineering and System Safety
Key Words:Adaptive design of experiment Failure probability Normalizing flows
Abstract:Failure probability (FP) estimation problem is a crucial task in engineering. In this work we consider this problem in the situation that the underlying computer models are extremely expensive, which often arises in the practice, and in this setting, reducing the calls of computer model is of essential importance. We formulate the problem of estimating the failure probability with expensive computer models as an sequential experimental design for the limit state (i.e., the failure boundary) and propose a series of efficient adaptive design criteria to solve the design of experiment (DOE). Considering the remarkable achievements of neural networks, we aim to leverage this powerful tool for surrogate modeling and sampling purposes. In particular, the proposed method employs the deep neural network (DNN) as the surrogate of limit state function for efficiently reducing the calls of expensive computer experiment. A map from the Gaussian distribution to the posterior approximation of the limit state is learned by the normalizing flows for the ease of experimental design. Three normalizingflows-based design criteria are proposed in this work for deciding the design locations based on the different assumption of generalization error. The accuracy and performance of the proposed method is demonstrated by both theory and practical examples. The relative error of FP estimation achieved by the proposed methods is consistently below ten percent.
Co-author:Hongji Wang, Jinglai Li
First Author:Tiexin Guo
Indexed by:Journal paper
Correspondence Author:Hongqiao Wang
Document Code:109664
Discipline:Natural Science
First-Level Discipline:Mathematics
Document Type:J
Volume:241
ISSN No.:0951-8320
Translation or Not:no
Date of Publication:2023-09-19
Included Journals:SCI
Links to published journals:https://linkinghub.elsevier.com/retrieve/pii/S0951832023005781
-
MOBILE Version
