Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects

Structural health in civil engineering involved maintaining a structure's integrity and performance over time, resisting loads and environmental effects. Ensuring long-term functionality was vital to prevent accidents, economic losses, and service interruptions. Structural health monitoring (SH...

Full description

Saved in:
Bibliographic Details
Main Authors: A. Presno Vélez, M. Z. Fernández Muñiz, J. L. Fernández Martínez
Format: Article
Language:English
Published: AIMS Press 2024-10-01
Series:AIMS Mathematics
Subjects:
Online Access:https://www.aimspress.com/article/doi/10.3934/math.20241472?viewType=HTML
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199395116515328
author A. Presno Vélez
M. Z. Fernández Muñiz
J. L. Fernández Martínez
author_facet A. Presno Vélez
M. Z. Fernández Muñiz
J. L. Fernández Martínez
author_sort A. Presno Vélez
collection DOAJ
description Structural health in civil engineering involved maintaining a structure's integrity and performance over time, resisting loads and environmental effects. Ensuring long-term functionality was vital to prevent accidents, economic losses, and service interruptions. Structural health monitoring (SHM) systems used sensors to detect damage indicators such as vibrations and cracks, which were crucial for predicting service life and planning maintenance. Machine learning (ML) enhanced SHM by analyzing sensor data to identify damage patterns often missed by human analysts. ML models captured complex relationships in data, leading to accurate predictions and early issue detection. This research aimed to develop a methodology for training an artificial intelligence (AI) system to predict the effects of retrofitting on civil structures, using data from the KW51 bridge (Leuven). Dimensionality reduction with the Welch transform identified the first seven modal frequencies as key predictors. Unsupervised principal component analysis (PCA) projections and a K-means algorithm achieved $ 70 \% $ accuracy in differentiating data before and after retrofitting. A random forest algorithm achieved $ 99.19 \% $ median accuracy with a nearly perfect receiver operating characteristic (ROC) curve. The final model, tested on the entire dataset, achieved $ 99.77 \% $ accuracy, demonstrating its effectiveness in predicting retrofitting effects for other civil structures.
format Article
id doaj-art-20b4c56dbc1b4f04bc99cbffc8549c5e
institution OA Journals
issn 2473-6988
language English
publishDate 2024-10-01
publisher AIMS Press
record_format Article
series AIMS Mathematics
spelling doaj-art-20b4c56dbc1b4f04bc99cbffc8549c5e2025-08-20T02:12:38ZengAIMS PressAIMS Mathematics2473-69882024-10-01911304933051410.3934/math.20241472Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effectsA. Presno Vélez0M. Z. Fernández Muñiz1 J. L. Fernández Martínez2Department of Mathematics, Group of inverse problems, optimization and machine learning, Oviedo University, c/Federico García Lorca 18, Oviedo 33007, SpainDepartment of Mathematics, Group of inverse problems, optimization and machine learning, Oviedo University, c/Federico García Lorca 18, Oviedo 33007, SpainDepartment of Mathematics, Group of inverse problems, optimization and machine learning, Oviedo University, c/Federico García Lorca 18, Oviedo 33007, SpainStructural health in civil engineering involved maintaining a structure's integrity and performance over time, resisting loads and environmental effects. Ensuring long-term functionality was vital to prevent accidents, economic losses, and service interruptions. Structural health monitoring (SHM) systems used sensors to detect damage indicators such as vibrations and cracks, which were crucial for predicting service life and planning maintenance. Machine learning (ML) enhanced SHM by analyzing sensor data to identify damage patterns often missed by human analysts. ML models captured complex relationships in data, leading to accurate predictions and early issue detection. This research aimed to develop a methodology for training an artificial intelligence (AI) system to predict the effects of retrofitting on civil structures, using data from the KW51 bridge (Leuven). Dimensionality reduction with the Welch transform identified the first seven modal frequencies as key predictors. Unsupervised principal component analysis (PCA) projections and a K-means algorithm achieved $ 70 \% $ accuracy in differentiating data before and after retrofitting. A random forest algorithm achieved $ 99.19 \% $ median accuracy with a nearly perfect receiver operating characteristic (ROC) curve. The final model, tested on the entire dataset, achieved $ 99.77 \% $ accuracy, demonstrating its effectiveness in predicting retrofitting effects for other civil structures. https://www.aimspress.com/article/doi/10.3934/math.20241472?viewType=HTMLhealth monitoringretrofittingmachine learning
spellingShingle A. Presno Vélez
M. Z. Fernández Muñiz
J. L. Fernández Martínez
Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects
AIMS Mathematics
health monitoring
retrofitting
machine learning
title Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects
title_full Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects
title_fullStr Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects
title_full_unstemmed Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects
title_short Enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects
title_sort enhancing structural health monitoring with machine learning for accurate prediction of retrofitting effects
topic health monitoring
retrofitting
machine learning
url https://www.aimspress.com/article/doi/10.3934/math.20241472?viewType=HTML
work_keys_str_mv AT apresnovelez enhancingstructuralhealthmonitoringwithmachinelearningforaccuratepredictionofretrofittingeffects
AT mzfernandezmuniz enhancingstructuralhealthmonitoringwithmachinelearningforaccuratepredictionofretrofittingeffects
AT jlfernandezmartinez enhancingstructuralhealthmonitoringwithmachinelearningforaccuratepredictionofretrofittingeffects