Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data

This study introduces a machine learning (ML)-based surrogate model for finite element analysis, designed to predict structural strain distributions using a minimal number of strategically placed virtual sensors. The proposed approach eliminates the dependency on external force measurements, leverag...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Hashemi, Javad Beheshti, Mahdieh Mohammadi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11084809/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849245879313104896
author Ali Hashemi
Javad Beheshti
Mahdieh Mohammadi
author_facet Ali Hashemi
Javad Beheshti
Mahdieh Mohammadi
author_sort Ali Hashemi
collection DOAJ
description This study introduces a machine learning (ML)-based surrogate model for finite element analysis, designed to predict structural strain distributions using a minimal number of strategically placed virtual sensors. The proposed approach eliminates the dependency on external force measurements, leveraging local strain measurements to infer global strain responses across a two-dimensional truss structure. Various regression algorithms, including decision trees and deep neural networks (DNNs), were evaluated, with DNNs achieving superior accuracy (<inline-formula> <tex-math notation="LaTeX">$\text {R}^{2}$ </tex-math></inline-formula> &#x003E; 0.996, MAE &#x003C; 4%, RMSE &#x003C; 5.5%). The methodology significantly reduces sensor requirements and computational overhead, offering a practical, scalable solution for structural health monitoring (SHM) in complex mechanical systems. The results underscore the potential of ML-based surrogate models to enhance the efficiency and accuracy of continuous monitoring and dynamic analysis in large-scale infrastructure applications, setting the stage for future advancements in sensor optimization and three-dimensional system extensions.
format Article
id doaj-art-beb8e083f7954406a3c7d54677fffe64
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-beb8e083f7954406a3c7d54677fffe642025-08-20T03:58:40ZengIEEEIEEE Access2169-35362025-01-011313058513060210.1109/ACCESS.2025.359066411084809Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor DataAli Hashemi0https://orcid.org/0000-0003-1115-5393Javad Beheshti1https://orcid.org/0009-0006-0600-766XMahdieh Mohammadi2Department of Civil, Environmental and Geomatics Engineering, Florida Atlantic University, Boca Raton, FL, USAIT and Computer Engineering Department, Islamic Azad University, Tafresh, IranFaculty of Built Environment, University of Malaya, Kuala Lumpur, MalaysiaThis study introduces a machine learning (ML)-based surrogate model for finite element analysis, designed to predict structural strain distributions using a minimal number of strategically placed virtual sensors. The proposed approach eliminates the dependency on external force measurements, leveraging local strain measurements to infer global strain responses across a two-dimensional truss structure. Various regression algorithms, including decision trees and deep neural networks (DNNs), were evaluated, with DNNs achieving superior accuracy (<inline-formula> <tex-math notation="LaTeX">$\text {R}^{2}$ </tex-math></inline-formula> &#x003E; 0.996, MAE &#x003C; 4%, RMSE &#x003C; 5.5%). The methodology significantly reduces sensor requirements and computational overhead, offering a practical, scalable solution for structural health monitoring (SHM) in complex mechanical systems. The results underscore the potential of ML-based surrogate models to enhance the efficiency and accuracy of continuous monitoring and dynamic analysis in large-scale infrastructure applications, setting the stage for future advancements in sensor optimization and three-dimensional system extensions.https://ieeexplore.ieee.org/document/11084809/Machine learningsurrogate modelsfinite element methodsstructural dynamicsvirtual sensor placementartificial neural networks
spellingShingle Ali Hashemi
Javad Beheshti
Mahdieh Mohammadi
Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data
IEEE Access
Machine learning
surrogate models
finite element methods
structural dynamics
virtual sensor placement
artificial neural networks
title Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data
title_full Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data
title_fullStr Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data
title_full_unstemmed Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data
title_short Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data
title_sort physics based ai driven surrogate modeling for structural displacement prediction in mechanical systems with limited sensor data
topic Machine learning
surrogate models
finite element methods
structural dynamics
virtual sensor placement
artificial neural networks
url https://ieeexplore.ieee.org/document/11084809/
work_keys_str_mv AT alihashemi physicsbasedaidrivensurrogatemodelingforstructuraldisplacementpredictioninmechanicalsystemswithlimitedsensordata
AT javadbeheshti physicsbasedaidrivensurrogatemodelingforstructuraldisplacementpredictioninmechanicalsystemswithlimitedsensordata
AT mahdiehmohammadi physicsbasedaidrivensurrogatemodelingforstructuraldisplacementpredictioninmechanicalsystemswithlimitedsensordata