A failure boundary exploration and exploitation framework combining adaptive Kriging model and sample space partitioning strategy for efficient reliability analysis. (December 2021)

• Record Type: Journal Article
• Authors: Song, Kunling; Zhang, Yugang; Shen, Linjie; Zhao, Qingyan; Song, Bifeng
• Is Part Of: Reliability engineering & system safety. Volume 216(2021)
• Publication Date: 2021-12
• Subjects: Failure boundary -- Adaptive Kriging model -- Exploration and exploitation -- K-means clustering -- Leave-one-out method -- Dynamic candidate samples; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2021.108009
• Languages: English
• ISSNs: 0951-8320

Abstract

Highlights: A failure boundary exploration and exploitation framework is proposed. A partitioning strategy is proposed with slice sampling and K-means clustering. The construction process of adaptive Kriging model is divided into two phases. Different candidate samples are used to enrich DoE in different phases. A new stopping criterion based on maximum failure probability error is developed. Abstract: Surrogate model-based methods have gradually become a vital method to assess reliability. However, the existing methods usually ignore the memory problems of matching candidate samples with the level of failure probability, which leads to inefficiency and even restricts their applicability. Therefore, this work combining the adaptive Kriging model and sample space partitioning strategy proposes a failure boundary exploration and exploitation framework (FBEEF), which divides the construction process of the adaptive Kriging model into two phases using different candidate samples to enrich training samples. In the exploration phase, a sample space partitioning strategy combining K-means clustering and slice sampling is employed to obtain several subsets and static candidate samples. In the exploitation phase, the approximate distances between the static candidate samples and the failure boundary are calculated to identify important subsets, whose samples are named dynamic candidate samples. Furthermore, a new stopping criterion is developed by combining leave-one-out method and weighted simulation method. To improve the efficiency of FBEEF Monte Carlo simulation or Importance Sampling is selected to estimate the final failure probability. Five examples were analyzed to test the effectiveness of FBEEF, and the results show that FBEEF can obtain good results with fewer training samples and lower analysis time.