Adaptive learning for reliability analysis using Support Vector Machines

• Published in: Reliability engineering & system safety Vol. 226; p. 108635
• Main Authors: Pepper, Nick, Crespo, Luis, Montomoli, Francesco
• Format: Journal Article
• Language: English
• Published: Barking Elsevier Ltd 01.10.2022; Elsevier BV
• Subjects: Adaptive learning; Algorithms; Computer applications; Failure probability; Iterative methods; Learning; Limit states; Probability learning; Reliability analysis; Reliability engineering; Support Vector Machines; Upper bounds; Adaptive learning; Reliability analysis; Support Vector Machines; Failure probability
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2022.108635

Given an expensive computational model of a system subject to reliability requirements, this work shows how to approximate the failure probability by learning adaptively the high-likelihood regions of the Limit State Function using Support Vector Machines. To this end, an algorithm is proposed that selects informative parameter points to add to training data at each iteration to improve the accuracy of the approximation. Furthermore, we provide a means to quantify the uncertainty in the Limit State Function, using geometrical arguments to estimate an upper bound to the failure probability. •A novel algorithm for adaptive learning of a Limit State Function (LSF) is proposed, using Support Vector Machines (SVMs).•Informative parameter points are identified through an optimisation process.•The uncertainty in the SVM is expressed using geometrical arguments in feature space.