Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildings

The seismic design of low-rise RC building frames often relies on elastic procedures, limiting the evaluation of nonlinear behavior due to practical constraints such as computational cost. While the research community has applied Machine Learning (ML) to predict the seismic response, existing tools...

Full description

Saved in:
Bibliographic Details
Main Authors: Carlos Angarita, Carlos Montes, Orlando Arroyo
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:SoftwareX
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352711025000895
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849326052344594432
author Carlos Angarita
Carlos Montes
Orlando Arroyo
author_facet Carlos Angarita
Carlos Montes
Orlando Arroyo
author_sort Carlos Angarita
collection DOAJ
description The seismic design of low-rise RC building frames often relies on elastic procedures, limiting the evaluation of nonlinear behavior due to practical constraints such as computational cost. While the research community has applied Machine Learning (ML) to predict the seismic response, existing tools often require prior knowledge and expertise to manage dependencies, configure programming environments, and execute code in languages such as Python. This paper introduces Pushover-ML, a graphical user interface (GUI) designed to efficiently predict a trilinear approximation of pushover curves for low-rise RC frames using an ML-based approach. The user-friendly executable provides insights into the structure's seismic capacity through the yielding, maximum capacity, and collapse points of the pushover curve. Pushover-ML bridges the gap between advanced ML techniques and practical engineering applications, enabling accurate and efficient seismic response predictions.
format Article
id doaj-art-8d6ec00e7a674e589f3fae723bf5eb9e
institution Kabale University
issn 2352-7110
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series SoftwareX
spelling doaj-art-8d6ec00e7a674e589f3fae723bf5eb9e2025-08-20T03:48:14ZengElsevierSoftwareX2352-71102025-05-013010212210.1016/j.softx.2025.102122Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildingsCarlos Angarita0Carlos Montes1Orlando Arroyo2Energy, Materials and Environment Laboratory, Faculty of Engineering, Universidad de La Sabana, Chía, ColombiaEnergy, Materials and Environment Laboratory, Faculty of Engineering, Universidad de La Sabana, Chía, Colombia; Corresponding author at: Energy, Materials and Environment Laboratory, Faculty of Engineering, Universidad de La Sabana, 250001, Chía, Cundinamarca, Colombia.Universidad Industrial de Santander, Bucaramanga, Colombia; Colombian Earthquake Engineering Research Network, Bogotá, ColombiaThe seismic design of low-rise RC building frames often relies on elastic procedures, limiting the evaluation of nonlinear behavior due to practical constraints such as computational cost. While the research community has applied Machine Learning (ML) to predict the seismic response, existing tools often require prior knowledge and expertise to manage dependencies, configure programming environments, and execute code in languages such as Python. This paper introduces Pushover-ML, a graphical user interface (GUI) designed to efficiently predict a trilinear approximation of pushover curves for low-rise RC frames using an ML-based approach. The user-friendly executable provides insights into the structure's seismic capacity through the yielding, maximum capacity, and collapse points of the pushover curve. Pushover-ML bridges the gap between advanced ML techniques and practical engineering applications, enabling accurate and efficient seismic response predictions.http://www.sciencedirect.com/science/article/pii/S2352711025000895Pushover analysisSeismic response Machine LearningReinforced concrete frame buildings
spellingShingle Carlos Angarita
Carlos Montes
Orlando Arroyo
Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildings
SoftwareX
Pushover analysis
Seismic response Machine Learning
Reinforced concrete frame buildings
title Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildings
title_full Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildings
title_fullStr Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildings
title_full_unstemmed Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildings
title_short Pushover-ML: A Machine Learning approach to predict a trilinear approximation of pushover curves for low-rise reinforced concrete frame buildings
title_sort pushover ml a machine learning approach to predict a trilinear approximation of pushover curves for low rise reinforced concrete frame buildings
topic Pushover analysis
Seismic response Machine Learning
Reinforced concrete frame buildings
url http://www.sciencedirect.com/science/article/pii/S2352711025000895
work_keys_str_mv AT carlosangarita pushovermlamachinelearningapproachtopredictatrilinearapproximationofpushovercurvesforlowrisereinforcedconcreteframebuildings
AT carlosmontes pushovermlamachinelearningapproachtopredictatrilinearapproximationofpushovercurvesforlowrisereinforcedconcreteframebuildings
AT orlandoarroyo pushovermlamachinelearningapproachtopredictatrilinearapproximationofpushovercurvesforlowrisereinforcedconcreteframebuildings