Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation

Classical explicit and implicit time integration methods, such as the central difference method and Newmark method, are widely used for dynamic response analysis of systems. However, their computational accuracy and stability are highly sensitive to the time step size. To address this issue, a novel...

Full description

Saved in:
Bibliographic Details
Main Authors: Yao Wang, Huaiman Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/15/9/1399
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155762296291328
author Yao Wang
Huaiman Li
author_facet Yao Wang
Huaiman Li
author_sort Yao Wang
collection DOAJ
description Classical explicit and implicit time integration methods, such as the central difference method and Newmark method, are widely used for dynamic response analysis of systems. However, their computational accuracy and stability are highly sensitive to the time step size. To address this issue, a novel dynamics-guided support vector machine (DG-SVM) method is proposed, which embeds an optimization process to reduce dependence on the time step size. Unlike traditional machine learning approaches, the DG-SVM model incorporates initial conditions and dynamic equilibrium equations at each time step as physical constraints, ensuring that inertial forces, damping forces, resistance forces, and external dynamics satisfy equilibrium without relying on system dynamic response data. Furthermore, a solution algorithm combining DG-SVM with static condensation and mode decomposition methods is developed to enhance computational efficiency for the analysis of multi-degree-of-freedom systems. The superior accuracy and reliability of the proposed method are validated using a three-story steel frame structure subjected to sinusoidal excitation, where the numerical results obtained by DG-SVM are compared with those computed from classical integration methods, with analytical solutions serving as benchmarks.
format Article
id doaj-art-32d4efd4ea28430e996d120486b9cbef
institution OA Journals
issn 2075-5309
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-32d4efd4ea28430e996d120486b9cbef2025-08-20T02:24:47ZengMDPI AGBuildings2075-53092025-04-01159139910.3390/buildings15091399Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave ExcitationYao Wang0Huaiman Li1School of Civil Engineering and Architecture, Three Gorges University, Yichang 443005, ChinaSchool of Civil Engineering and Architecture, Three Gorges University, Yichang 443005, ChinaClassical explicit and implicit time integration methods, such as the central difference method and Newmark method, are widely used for dynamic response analysis of systems. However, their computational accuracy and stability are highly sensitive to the time step size. To address this issue, a novel dynamics-guided support vector machine (DG-SVM) method is proposed, which embeds an optimization process to reduce dependence on the time step size. Unlike traditional machine learning approaches, the DG-SVM model incorporates initial conditions and dynamic equilibrium equations at each time step as physical constraints, ensuring that inertial forces, damping forces, resistance forces, and external dynamics satisfy equilibrium without relying on system dynamic response data. Furthermore, a solution algorithm combining DG-SVM with static condensation and mode decomposition methods is developed to enhance computational efficiency for the analysis of multi-degree-of-freedom systems. The superior accuracy and reliability of the proposed method are validated using a three-story steel frame structure subjected to sinusoidal excitation, where the numerical results obtained by DG-SVM are compared with those computed from classical integration methods, with analytical solutions serving as benchmarks.https://www.mdpi.com/2075-5309/15/9/1399dynamic responsesteel framesupport vector machinesstatic condensation methodmode decomposition method
spellingShingle Yao Wang
Huaiman Li
Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation
Buildings
dynamic response
steel frame
support vector machines
static condensation method
mode decomposition method
title Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation
title_full Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation
title_fullStr Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation
title_full_unstemmed Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation
title_short Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation
title_sort dynamics guided support vector machines for response analysis of steel frame under sine wave excitation
topic dynamic response
steel frame
support vector machines
static condensation method
mode decomposition method
url https://www.mdpi.com/2075-5309/15/9/1399
work_keys_str_mv AT yaowang dynamicsguidedsupportvectormachinesforresponseanalysisofsteelframeundersinewaveexcitation
AT huaimanli dynamicsguidedsupportvectormachinesforresponseanalysisofsteelframeundersinewaveexcitation