Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Using Machine Learning to Predict the Seismic Response of an SDOF RC Structure with Superelastic Dampers

Using Machine Learning to Predict the Seismic Response of an SDOF RC Structure with Superelastic... This study investigates the efficacy of using an artificial neural network (ANN) to predict the seismic response of a single degree of freedom (SDOF) system comprising a reinforced concrete (RC) column supporting a mass and equipped with a superelastic shape memory alloy (SMA) damper. Nonlinear time history simulations are first conducted to build the training dataset for the ANN by analyzing the structural response under 200 ground motion (GM) records. Properties of the column, the SMA damper, and the GM records are considered as input parameters while the maximum mass displacement is the output parameter. The neural network is then trained and used to make predictions on the structural response under different GM records. The results show that using only 200 records, the root-mean-square error (RMSE) and the average error of the prediction can be as low as 0.1012 and 6.55%, respectively. Parametric studies are conducted next using the developed ANN to investigate the accuracy of the network’s predictions and its ability to capture the impact of a wide range of structural, SMA, and ground motion parameters on the structural response. The results show that the network can predict the structural response under different ambient temperatures and predict the area of the SMA damper needed to achieve a target structural drift. The results of this study demonstrate the potential of using ANNs to predict the seismic behavior of concrete structural systems with superelastic SMA dampers. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Civil Engineering Springer Journals

Using Machine Learning to Predict the Seismic Response of an SDOF RC Structure with Superelastic Dampers

Download PDF
16 pages

Loading next page...
 
/lp/springer-journals/using-machine-learning-to-predict-the-seismic-response-of-an-sdof-rc-PgNzb8g2No

References (43)

Publisher
Springer Journals
Copyright
Copyright © Iran University of Science and Technology 2022
ISSN
1735-0522
eISSN
2383-3874
DOI
10.1007/s40999-022-00724-1
Publisher site
See Article on Publisher Site

Abstract

This study investigates the efficacy of using an artificial neural network (ANN) to predict the seismic response of a single degree of freedom (SDOF) system comprising a reinforced concrete (RC) column supporting a mass and equipped with a superelastic shape memory alloy (SMA) damper. Nonlinear time history simulations are first conducted to build the training dataset for the ANN by analyzing the structural response under 200 ground motion (GM) records. Properties of the column, the SMA damper, and the GM records are considered as input parameters while the maximum mass displacement is the output parameter. The neural network is then trained and used to make predictions on the structural response under different GM records. The results show that using only 200 records, the root-mean-square error (RMSE) and the average error of the prediction can be as low as 0.1012 and 6.55%, respectively. Parametric studies are conducted next using the developed ANN to investigate the accuracy of the network’s predictions and its ability to capture the impact of a wide range of structural, SMA, and ground motion parameters on the structural response. The results show that the network can predict the structural response under different ambient temperatures and predict the area of the SMA damper needed to achieve a target structural drift. The results of this study demonstrate the potential of using ANNs to predict the seismic behavior of concrete structural systems with superelastic SMA dampers.

Journal

International Journal of Civil Engineering – Springer Journals

Published: Oct 1, 2022

Keywords: Concrete; Shape memory alloy; Superelasticity; Machine learning; Damping; Self-centering

There are no references for this article.