Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

In this study, firstly, the behavior of a high steel frame equipped with tuned mass damper (TMD) due to several seismic records is investigated considering the structural and seismic uncertainties. Then, machine learning methods including artificial neural networks (ANN), decision tree (DT), Naïve B...

Full description

Bibliographic Details
Main Authors: Farrokhi Farshid, Rahimi Sepideh
Format: Article
Language:English
Published: Sciendo 2020-09-01
Series:Studia Geotechnica et Mechanica
Subjects:
failure analysis
supervised machine learning
feature selection
tuned mass damper
Online Access:https://doi.org/10.2478/sgem-2019-0043
id doaj-8e7a3a0fd9774841b49bbf06bb247bb7
record_format Article
spelling doaj-8e7a3a0fd9774841b49bbf06bb247bb72021-09-05T14:01:52ZengSciendoStudia Geotechnica et Mechanica2083-831X2020-09-0142317919010.2478/sgem-2019-0043sgem-2019-0043Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methodsFarrokhi Farshid0Rahimi Sepideh1Department of Civil Engineering, Noor Branch, Islamic Azad University, IranDepartment of Civil Engineering, Noor Branch, Islamic Azad University, IranIn this study, firstly, the behavior of a high steel frame equipped with tuned mass damper (TMD) due to several seismic records is investigated considering the structural and seismic uncertainties. Then, machine learning methods including artificial neural networks (ANN), decision tree (DT), Naïve Bayes (NB) and support vector machines (SVM) are used to predict the behavior of the structure. Results showed that among the machine learning models, SVM with Gaussian kernel has better performance since it is capable of predicting the drift of stories and the failure probability with R2 value equal to 0.99. Furthermore, results of feature selection algorithms revealed that when using TMD in high steel structures, seismic uncertainties have greater influences on drift of stories in comparison with structural uncertainties. Findings of this study can be used in design and probabilistic analysis of high steel frames equipped with TMDs.https://doi.org/10.2478/sgem-2019-0043failure analysissupervised machine learningfeature selectiontuned mass damper
collection DOAJ
language English
format Article
sources DOAJ
author Farrokhi Farshid
Rahimi Sepideh
spellingShingle Farrokhi Farshid
Rahimi Sepideh
Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods
Studia Geotechnica et Mechanica
failure analysis
supervised machine learning
feature selection
tuned mass damper
author_facet Farrokhi Farshid
Rahimi Sepideh
author_sort Farrokhi Farshid
title Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods
title_short Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods
title_full Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods
title_fullStr Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods
title_full_unstemmed Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods
title_sort supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods
publisher Sciendo
series Studia Geotechnica et Mechanica
issn 2083-831X
publishDate 2020-09-01
description In this study, firstly, the behavior of a high steel frame equipped with tuned mass damper (TMD) due to several seismic records is investigated considering the structural and seismic uncertainties. Then, machine learning methods including artificial neural networks (ANN), decision tree (DT), Naïve Bayes (NB) and support vector machines (SVM) are used to predict the behavior of the structure. Results showed that among the machine learning models, SVM with Gaussian kernel has better performance since it is capable of predicting the drift of stories and the failure probability with R2 value equal to 0.99. Furthermore, results of feature selection algorithms revealed that when using TMD in high steel structures, seismic uncertainties have greater influences on drift of stories in comparison with structural uncertainties. Findings of this study can be used in design and probabilistic analysis of high steel frames equipped with TMDs.
topic failure analysis
supervised machine learning
feature selection
tuned mass damper
url https://doi.org/10.2478/sgem-2019-0043
work_keys_str_mv AT farrokhifarshid supervisedprobabilisticfailurepredictionoftunedmassdamperequippedhighsteelframesusingmachinelearningmethods
AT rahimisepideh supervisedprobabilisticfailurepredictionoftunedmassdamperequippedhighsteelframesusingmachinelearningmethods
_version_ 1717809408592838656

Similar Items