Abstract
AbstractThe paper proposes the use of supervised machine learning (ML) methods for quickly predicting the seismic response of rocking systems when subjected to seismic excitations. Different supervised ML algorithms are discussed, while a relatively simple and a more sophisticated algorithm are examined in detail. Specifically, the two algorithms compared are thek-Nearest Neighbor (k-NN) and the Support Vector Machine (SVM). The performance of the ML models is demonstrated considering both sine pulses and different sets of natural ground motion records. The results are practically perfect for sine pulses, while accurate results were also obtained for the case of natural ground motions. The proposed ML-based tool allows to quickly assess the risk of damage for rocking systems, while it is also very important when a large number of rocking blocks have to be studied, e.g. in the case of a building’s inventory.
Funder
National Technical University of Athens
Publisher
Springer Science and Business Media LLC
Subject
Geophysics,Geotechnical Engineering and Engineering Geology,Building and Construction,Civil and Structural Engineering
Reference36 articles.
1. Altman NS (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 46:175–185. https://doi.org/10.2307/2685209
2. Avci O, Abdeljaber O, Kiranyaz S (2022) Structural damage detection in civil engineering with machine learning: Current state of the art. In: Walber C, Stefanski M, Seidlitz S (eds) Sensors and instrumentation, aircraft/aerospace, energy harvesting & dynamic environments testing, vol 7. Springer, Cham, pp 223–229
3. Avgenakis E, Psycharis IN (2020) Modeling of inelastic rocking bodies under cyclic loading. J Eng Mech 146:04020020. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001751
4. Advanced texts in econometrics;C Bishop,1995
5. Cevik A, Kurtoǧlu AE, Bilgehan M, Gülşan ME, Albegmprli HM (2015) Support vector machines in structural engineering: a review. J Civ Eng Manag 21:261–281. https://doi.org/10.3846/13923730.2015.1005021
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献