An active-learning reliability method based on support vector regression and cross validation. (February 2023)

• Record Type: Journal Article
• Authors: Zhou, Tong; Peng, Yongbo
• Is Part Of: Computers & structures. Volume 276(2023)
• Publication Date: 2023-02
• Subjects: Support vector regression -- Cross validation -- Probability density evolution method -- Pseudo-interpolation replacement -- Structural reliability; Structural engineering -- Data processing -- Periodicals; Electronic data processing -- Structures, Theory of -- Periodicals; 624.171
• DOI: 10.1016/j.compstruc.2022.106943
• Languages: English
• ISSNs: 0045-7949

Abstract

Highlights: An active-learning reliability algorithm combining the SVR and the PDEM is proposed. Cross validation strategy deriving empirical probability distribution of SVR is detailed. Expected function based learning functions accommodate to any type of metamodels. The treatment of pseudo-interpolation replacement enables to reduce the prediction error. The proposed method has superiority of dealing with complex reliability problems. Abstract: To reduce the high computational cost of the probability density evolution method (PDEM) for structural reliability analysis, an active-learning reliability method that combines the support vector regression (SVR) and the PDEM is proposed, which is abbreviated as the ASVR-PDEM. First, the empirical probability distribution of the SVR is proposed based on the leave-one-out cross-validation (LOOCV) strategy. On this basis, two different learning functions are proposed according to the concept of the PDEM-oriented expected improvement function, which accommodate to any type of metamodels in essence. Then, the pseudo-interpolation replacement is devised to avoid the prediction error of the SVR at the representative points in the region of interest and, thus, maintains the precision of failure probability. Moreover, the influences of four key ingredients on the proposed method are investigated, namely the type of metamodels, the form of learning functions, the deployment of the pseudo-interpolation replacement and the training scheme in the LOOCV strategy. Three numerical examples are investigated to show the feasibility of the ASVR-PDEM. Comparisons are made against several conventional reliability methods. The results highlight the superiority of the ASVR-PDEM in terms of computational accuracy, efficiency and computational time, especially in the case of the time-consuming dynamic reliability problems.