EPrints - Publications Repository

Roy, Atin and Chakraborty, Subrata (2024) Seismic reliability analysis of structures by an adaptive support vector regression based metamodel. Journal of Earthquake Engineering, 28 (6). pp. 1590-1614. ISSN 1363-2469

AI Summary:

The proposed adaptive support vector regression-based metamodeling approach selects new training samples near the failure boundary, considering accuracy and efficiency. The effectiveness of this approach is compared with direct Monte Carlo simulation and active learning-based Kriging.

AI Topics:

The following topics are generate through an AI service. Clicking on them will take you to a search result page with related items.

Abstract

The dual metamodeling approach is usually adopted to tackle the stochastic nature of earthquakes in seismic reliability analysis relying on the lognormal response assumption. Alternatively, a direct response approximation approach where separate metamodels are constructed for each earthquake is attempted here avoiding prior distribution assumption. Further, an adaptive support vector regression-based metamodeling is proposed that selects new training samples near the failure boundary with due consideration to accuracy and efficiency. The effectiveness of the approach is elucidated by comparing it with the results obtained by the direct Monte Carlo simulation technique and a state-of-the-art active learning-based Kriging approach.

People