Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment

In this paper, a new structural damage detection framework is proposed based on vibration analysis and pattern recognition, which consists of two stages: (1) signal processing and feature extraction and (2) damage detection by combining the classification result. In the first stage, discriminative f...

Full description

Saved in:
Bibliographic Details
Main Authors: Hossein Babajanian Bisheh, Gholamreza Ghodrati Amiri, Ehsan Darvishan
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2020/8899487
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304380895920128
author Hossein Babajanian Bisheh
Gholamreza Ghodrati Amiri
Ehsan Darvishan
author_facet Hossein Babajanian Bisheh
Gholamreza Ghodrati Amiri
Ehsan Darvishan
author_sort Hossein Babajanian Bisheh
collection DOAJ
description In this paper, a new structural damage detection framework is proposed based on vibration analysis and pattern recognition, which consists of two stages: (1) signal processing and feature extraction and (2) damage detection by combining the classification result. In the first stage, discriminative features were extracted as a set of proposed descriptors related to the statistical moment of the spectrum and spectral shape properties using five competitive time-frequency techniques including fast S-transform, synchrosqueezed wavelet transform, empirical wavelet transform, wavelet transform, and short-time Fourier transform. Then, forward feature selection was employed to remove the redundant information and select damage features from vibration signals. By applying different classifiers, the capability of the feature sets for damage identification was investigated. In the second stage, ensemble-based classifiers were used to improve the overall performance of damage detection based on individual classifiers and increase the number of detectable damages. The proposed framework was verified by a suite of numerical and full-scale studies (a bridge health monitoring benchmark problem, IASC-ASCE SHM benchmark structure, and a cable-stayed bridge in China). The results showed that the proposed framework was superior to the existing single classifier and could assess the damage with reduced false alarms.
format Article
id doaj-art-1935aae9cbb143dea054ab7bba09c6a9
institution Kabale University
issn 1070-9622
1875-9203
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-1935aae9cbb143dea054ab7bba09c6a92025-08-20T03:55:45ZengWileyShock and Vibration1070-96221875-92032020-01-01202010.1155/2020/88994878899487Ensemble Classifiers and Feature-Based Methods for Structural Damage AssessmentHossein Babajanian Bisheh0Gholamreza Ghodrati Amiri1Ehsan Darvishan2School of Civil Engineering, Iran University of Science and Technology, Tehran, IranNatural Disasters Prevention Research Center, School of Civil Engineering, Iran University of Science & Technology, Tehran, IranDepartment of Civil Engineering, Roudehen Branch, Islamic Azad University, Roudehen, IranIn this paper, a new structural damage detection framework is proposed based on vibration analysis and pattern recognition, which consists of two stages: (1) signal processing and feature extraction and (2) damage detection by combining the classification result. In the first stage, discriminative features were extracted as a set of proposed descriptors related to the statistical moment of the spectrum and spectral shape properties using five competitive time-frequency techniques including fast S-transform, synchrosqueezed wavelet transform, empirical wavelet transform, wavelet transform, and short-time Fourier transform. Then, forward feature selection was employed to remove the redundant information and select damage features from vibration signals. By applying different classifiers, the capability of the feature sets for damage identification was investigated. In the second stage, ensemble-based classifiers were used to improve the overall performance of damage detection based on individual classifiers and increase the number of detectable damages. The proposed framework was verified by a suite of numerical and full-scale studies (a bridge health monitoring benchmark problem, IASC-ASCE SHM benchmark structure, and a cable-stayed bridge in China). The results showed that the proposed framework was superior to the existing single classifier and could assess the damage with reduced false alarms.http://dx.doi.org/10.1155/2020/8899487
spellingShingle Hossein Babajanian Bisheh
Gholamreza Ghodrati Amiri
Ehsan Darvishan
Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment
Shock and Vibration
title Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment
title_full Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment
title_fullStr Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment
title_full_unstemmed Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment
title_short Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment
title_sort ensemble classifiers and feature based methods for structural damage assessment
url http://dx.doi.org/10.1155/2020/8899487
work_keys_str_mv AT hosseinbabajanianbisheh ensembleclassifiersandfeaturebasedmethodsforstructuraldamageassessment
AT gholamrezaghodratiamiri ensembleclassifiersandfeaturebasedmethodsforstructuraldamageassessment
AT ehsandarvishan ensembleclassifiersandfeaturebasedmethodsforstructuraldamageassessment