A review of bridge health monitoring based on machine learning

Emad Soltani; Ehsan Ahmadi; Florimond Gueniat; Mohammad Reza Salami

doi:10.1680/jbren.22.00030

A review of bridge health monitoring based on machine learning

Emad Soltani^*, Ehsan Ahmadi, Florimond Gueniat, Mohammad Reza Salami

^*Corresponding author for this work

Civil Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

This paper reviews structural health monitoring (SHM) techniques of bridge structures based on machine learning (ML) algorithms. Regular inspections or using non-destructive testing are still the common damage detection methods; they are susceptible to subjectivity, human error, and prolonged duration. With emerging technologies such as artificial intelligence (AI) and the development of wireless sensors, SHM has shifted from offline model-driven damage detection to online/real-time data-driven damage detection. In this paper, both supervised and unsupervised ML algorithms are studied to determine which of the latest methods would be the most suitable and effective to be used for the SHM of bridge structures. This review paper investigates recent studies on data acquisition, data imputation, data compression, feature extraction, and pattern recognition using supervised/unsupervised ML algorithms.

Original language	English
Journal	Proceedings of the Institution of Civil Engineers: Bridge Engineering
Early online date	21 Dec 2022
DOIs	https://doi.org/10.1680/jbren.22.00030
Publication status	E-pub ahead of print - 21 Dec 2022

Bibliographical note

Publisher Copyright:
© 2022 ICE Publishing: All rights reserved.

ASJC Scopus subject areas

Civil and Structural Engineering
Building and Construction

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1680/jbren.22.00030Licence: None: All rights reserved

Cite this

@article{dc3d8310a865409197537999e3f37552,

title = "A review of bridge health monitoring based on machine learning",

abstract = "This paper reviews structural health monitoring (SHM) techniques of bridge structures based on machine learning (ML) algorithms. Regular inspections or using non-destructive testing are still the common damage detection methods; they are susceptible to subjectivity, human error, and prolonged duration. With emerging technologies such as artificial intelligence (AI) and the development of wireless sensors, SHM has shifted from offline model-driven damage detection to online/real-time data-driven damage detection. In this paper, both supervised and unsupervised ML algorithms are studied to determine which of the latest methods would be the most suitable and effective to be used for the SHM of bridge structures. This review paper investigates recent studies on data acquisition, data imputation, data compression, feature extraction, and pattern recognition using supervised/unsupervised ML algorithms.",

author = "Emad Soltani and Ehsan Ahmadi and Florimond Gueniat and Salami, {Mohammad Reza}",

year = "2022",

month = dec,

day = "21",

doi = "10.1680/jbren.22.00030",

language = "English",

journal = "Proceedings of the Institution of Civil Engineers: Bridge Engineering",

issn = "1478-4637",

publisher = "ICE Publishing",

}

TY - JOUR

T1 - A review of bridge health monitoring based on machine learning

AU - Soltani, Emad

AU - Ahmadi, Ehsan

AU - Gueniat, Florimond

AU - Salami, Mohammad Reza

PY - 2022/12/21

Y1 - 2022/12/21

N2 - This paper reviews structural health monitoring (SHM) techniques of bridge structures based on machine learning (ML) algorithms. Regular inspections or using non-destructive testing are still the common damage detection methods; they are susceptible to subjectivity, human error, and prolonged duration. With emerging technologies such as artificial intelligence (AI) and the development of wireless sensors, SHM has shifted from offline model-driven damage detection to online/real-time data-driven damage detection. In this paper, both supervised and unsupervised ML algorithms are studied to determine which of the latest methods would be the most suitable and effective to be used for the SHM of bridge structures. This review paper investigates recent studies on data acquisition, data imputation, data compression, feature extraction, and pattern recognition using supervised/unsupervised ML algorithms.

AB - This paper reviews structural health monitoring (SHM) techniques of bridge structures based on machine learning (ML) algorithms. Regular inspections or using non-destructive testing are still the common damage detection methods; they are susceptible to subjectivity, human error, and prolonged duration. With emerging technologies such as artificial intelligence (AI) and the development of wireless sensors, SHM has shifted from offline model-driven damage detection to online/real-time data-driven damage detection. In this paper, both supervised and unsupervised ML algorithms are studied to determine which of the latest methods would be the most suitable and effective to be used for the SHM of bridge structures. This review paper investigates recent studies on data acquisition, data imputation, data compression, feature extraction, and pattern recognition using supervised/unsupervised ML algorithms.

UR - http://www.scopus.com/inward/record.url?scp=85143893339&partnerID=8YFLogxK

U2 - 10.1680/jbren.22.00030

DO - 10.1680/jbren.22.00030

M3 - Article

AN - SCOPUS:85143893339

SN - 1478-4637

JO - Proceedings of the Institution of Civil Engineers: Bridge Engineering

JF - Proceedings of the Institution of Civil Engineers: Bridge Engineering

ER -