Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis

Today, health monitoring of structures has been standardized in many countries. Such systems for large and complex structures are equipped and include numerous sensors. Therefore, they are not yet practical in our country due to large final expenses. The main purpose of this paper is to introduce a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Ehsan Darvishan
Formato:	article
Lenguaje:	FA
Publicado:	Iranian Society of Structrual Engineering (ISSE) 2019
Materias:	health monitoring damage detection damage index yonghe bridge signal proceesing Bridge engineering TG1-470 Building construction TH1-9745
Acceso en línea:	https://doaj.org/article/d1434dcf15ec4ff587cadf1ddf474d70
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d1434dcf15ec4ff587cadf1ddf474d70
record_format	dspace
spelling	oai:doaj.org-article:d1434dcf15ec4ff587cadf1ddf474d702021-11-08T15:51:06ZLow cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis2476-39772538-261610.22065/jsce.2017.94398.1280https://doaj.org/article/d1434dcf15ec4ff587cadf1ddf474d702019-02-01T00:00:00Zhttps://www.jsce.ir/article_51826_0d9fd4377fc2fbfb50675fcc91bd44fe.pdfhttps://doaj.org/toc/2476-3977https://doaj.org/toc/2538-2616Today, health monitoring of structures has been standardized in many countries. Such systems for large and complex structures are equipped and include numerous sensors. Therefore, they are not yet practical in our country due to large final expenses. The main purpose of this paper is to introduce a low-cost health monitoring algorithm for structures based on signal processing. Accordingly, only three sensors are utilized to detect damage. Since the accuracy of signal processing method can affect the results of damage detection, in the first part of the paper, five signal processing methods are investigated. Among these procedures two methods are older and have widely used in damage detection. The three others are more recent and are fully investigated in civil engineering. In the second part, a new damage detection method is proposed. This method is a combination of signal processing methods by synchrosqeezed wavelet transform, clustering, and regression with autoassociative artificial neural networks. For this reason, data from Yonghe bridge is utilized which is recorded based on real vibration of the bridge. Results show that the proposed signal processing method is capable to effectively extract signal features. Also the damage detection method is capable to detect damage with acceptable accuracyEhsan DarvishanIranian Society of Structrual Engineering (ISSE)articlehealth monitoringdamage detectiondamage indexyonghe bridgesignal proceesingBridge engineeringTG1-470Building constructionTH1-9745FAJournal of Structural and Construction Engineering, Vol 5, Iss شماره ویژه 4, Pp 193-216 (2019)
institution	DOAJ
collection	DOAJ
language	FA
topic	health monitoring damage detection damage index yonghe bridge signal proceesing Bridge engineering TG1-470 Building construction TH1-9745
spellingShingle	health monitoring damage detection damage index yonghe bridge signal proceesing Bridge engineering TG1-470 Building construction TH1-9745 Ehsan Darvishan Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis
description	Today, health monitoring of structures has been standardized in many countries. Such systems for large and complex structures are equipped and include numerous sensors. Therefore, they are not yet practical in our country due to large final expenses. The main purpose of this paper is to introduce a low-cost health monitoring algorithm for structures based on signal processing. Accordingly, only three sensors are utilized to detect damage. Since the accuracy of signal processing method can affect the results of damage detection, in the first part of the paper, five signal processing methods are investigated. Among these procedures two methods are older and have widely used in damage detection. The three others are more recent and are fully investigated in civil engineering. In the second part, a new damage detection method is proposed. This method is a combination of signal processing methods by synchrosqeezed wavelet transform, clustering, and regression with autoassociative artificial neural networks. For this reason, data from Yonghe bridge is utilized which is recorded based on real vibration of the bridge. Results show that the proposed signal processing method is capable to effectively extract signal features. Also the damage detection method is capable to detect damage with acceptable accuracy
format	article
author	Ehsan Darvishan
author_facet	Ehsan Darvishan
author_sort	Ehsan Darvishan
title	Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis
title_short	Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis
title_full	Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis
title_fullStr	Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis
title_full_unstemmed	Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis
title_sort	low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis
publisher	Iranian Society of Structrual Engineering (ISSE)
publishDate	2019
url	https://doaj.org/article/d1434dcf15ec4ff587cadf1ddf474d70
work_keys_str_mv	AT ehsandarvishan lowcosthealthmonitoringofcablestayedbridgesusingsynchrosqueezedwavelettransformandnonlinearprincipalcomponentanalysis
_version_	1718441703254261760

Low cost health monitoring of cable stayed bridges using synchrosqueezed wavelet transform and nonlinear principal component analysis

Ejemplares similares