Application of deep autoencoder model for structural condition monitoring

Damage detection in structures is performed via vibration based structural identification. Modal information, such as frequencies and mode shapes, are widely used for structural damage detection to indicate the health conditions of civil structures. The deep learning algorithm that works on a multip...

Full description

Bibliographic Details
Main Authors: Pathirage, C., Li, Jun, Li, L., Hao, Hong, Liu, Wan-Quan
Format: Journal Article
Published: 2018
Online Access:http://hdl.handle.net/20.500.11937/71450
_version_ 1848762482915540992
author Pathirage, C.
Li, Jun
Li, L.
Hao, Hong
Liu, Wan-Quan
author_facet Pathirage, C.
Li, Jun
Li, L.
Hao, Hong
Liu, Wan-Quan
author_sort Pathirage, C.
building Curtin Institutional Repository
collection Online Access
description Damage detection in structures is performed via vibration based structural identification. Modal information, such as frequencies and mode shapes, are widely used for structural damage detection to indicate the health conditions of civil structures. The deep learning algorithm that works on a multiple layer neural network model termed as deep autoencoder is proposed to learn the relationship between the modal information and structural stiffness parameters. This is achieved via dimension reduction of the modal information feature and a non-linear regression against the structural stiffness parameters. Numerical tests on a symmetrical steel frame model are conducted to generate the data for the training and validation, and to demonstrate the efficiency of the proposed approach for vibration based structural damage detection.
first_indexed 2025-11-14T10:48:17Z
format Journal Article
id curtin-20.500.11937-71450
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:48:17Z
publishDate 2018
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-714502019-03-06T05:52:51Z Application of deep autoencoder model for structural condition monitoring Pathirage, C. Li, Jun Li, L. Hao, Hong Liu, Wan-Quan Damage detection in structures is performed via vibration based structural identification. Modal information, such as frequencies and mode shapes, are widely used for structural damage detection to indicate the health conditions of civil structures. The deep learning algorithm that works on a multiple layer neural network model termed as deep autoencoder is proposed to learn the relationship between the modal information and structural stiffness parameters. This is achieved via dimension reduction of the modal information feature and a non-linear regression against the structural stiffness parameters. Numerical tests on a symmetrical steel frame model are conducted to generate the data for the training and validation, and to demonstrate the efficiency of the proposed approach for vibration based structural damage detection. 2018 Journal Article http://hdl.handle.net/20.500.11937/71450 10.21629/JSEE.2018.04.22 fulltext
spellingShingle Pathirage, C.
Li, Jun
Li, L.
Hao, Hong
Liu, Wan-Quan
Application of deep autoencoder model for structural condition monitoring
title Application of deep autoencoder model for structural condition monitoring
title_full Application of deep autoencoder model for structural condition monitoring
title_fullStr Application of deep autoencoder model for structural condition monitoring
title_full_unstemmed Application of deep autoencoder model for structural condition monitoring
title_short Application of deep autoencoder model for structural condition monitoring
title_sort application of deep autoencoder model for structural condition monitoring
url http://hdl.handle.net/20.500.11937/71450