Cargando…

High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring

In order to accurately diagnose the health of high-order statically indeterminate structures, most existing structural health monitoring (SHM) methods require multiple sensors to collect enough information. However, comprehensive data collection from multiple sensors for high degree-of-freedom struc...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Yen-Lin, Chiang, Yuan, Chiu, Pei-Hsin, Huang, I-Chen, Xiao, Yu-Bai, Chang, Shu-Wei, Huang, Chang-Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8158099/
https://www.ncbi.nlm.nih.gov/pubmed/34070068
http://dx.doi.org/10.3390/s21103514
_version_ 1783699811983163392
author Chen, Yen-Lin
Chiang, Yuan
Chiu, Pei-Hsin
Huang, I-Chen
Xiao, Yu-Bai
Chang, Shu-Wei
Huang, Chang-Wei
author_facet Chen, Yen-Lin
Chiang, Yuan
Chiu, Pei-Hsin
Huang, I-Chen
Xiao, Yu-Bai
Chang, Shu-Wei
Huang, Chang-Wei
author_sort Chen, Yen-Lin
collection PubMed
description In order to accurately diagnose the health of high-order statically indeterminate structures, most existing structural health monitoring (SHM) methods require multiple sensors to collect enough information. However, comprehensive data collection from multiple sensors for high degree-of-freedom structures is not typically available in practice. We propose a method that reconciles the two seemingly conflicting difficulties. Takens’ embedding theorem is used to augment the dimensions of data collected from a single sensor. Taking advantage of the success of machine learning in image classification, high-dimensional reconstructed attractors were converted into images and fed into a convolutional neural network (CNN). Attractor classification was performed for 10 damage cases of a 3-story shear frame structure. Numerical results show that the inherently high dimension of the CNN model allows the handling of higher dimensional data. Information on both the level and the location of damage was successfully embedded. The same methodology will allow the extraction of data with unsupervised CNN classification to be consistent with real use cases.
format Online
Article
Text
id pubmed-8158099
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81580992021-05-28 High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring Chen, Yen-Lin Chiang, Yuan Chiu, Pei-Hsin Huang, I-Chen Xiao, Yu-Bai Chang, Shu-Wei Huang, Chang-Wei Sensors (Basel) Article In order to accurately diagnose the health of high-order statically indeterminate structures, most existing structural health monitoring (SHM) methods require multiple sensors to collect enough information. However, comprehensive data collection from multiple sensors for high degree-of-freedom structures is not typically available in practice. We propose a method that reconciles the two seemingly conflicting difficulties. Takens’ embedding theorem is used to augment the dimensions of data collected from a single sensor. Taking advantage of the success of machine learning in image classification, high-dimensional reconstructed attractors were converted into images and fed into a convolutional neural network (CNN). Attractor classification was performed for 10 damage cases of a 3-story shear frame structure. Numerical results show that the inherently high dimension of the CNN model allows the handling of higher dimensional data. Information on both the level and the location of damage was successfully embedded. The same methodology will allow the extraction of data with unsupervised CNN classification to be consistent with real use cases. MDPI 2021-05-18 /pmc/articles/PMC8158099/ /pubmed/34070068 http://dx.doi.org/10.3390/s21103514 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chen, Yen-Lin
Chiang, Yuan
Chiu, Pei-Hsin
Huang, I-Chen
Xiao, Yu-Bai
Chang, Shu-Wei
Huang, Chang-Wei
High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring
title High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring
title_full High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring
title_fullStr High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring
title_full_unstemmed High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring
title_short High-Dimensional Phase Space Reconstruction with a Convolutional Neural Network for Structural Health Monitoring
title_sort high-dimensional phase space reconstruction with a convolutional neural network for structural health monitoring
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8158099/
https://www.ncbi.nlm.nih.gov/pubmed/34070068
http://dx.doi.org/10.3390/s21103514
work_keys_str_mv AT chenyenlin highdimensionalphasespacereconstructionwithaconvolutionalneuralnetworkforstructuralhealthmonitoring
AT chiangyuan highdimensionalphasespacereconstructionwithaconvolutionalneuralnetworkforstructuralhealthmonitoring
AT chiupeihsin highdimensionalphasespacereconstructionwithaconvolutionalneuralnetworkforstructuralhealthmonitoring
AT huangichen highdimensionalphasespacereconstructionwithaconvolutionalneuralnetworkforstructuralhealthmonitoring
AT xiaoyubai highdimensionalphasespacereconstructionwithaconvolutionalneuralnetworkforstructuralhealthmonitoring
AT changshuwei highdimensionalphasespacereconstructionwithaconvolutionalneuralnetworkforstructuralhealthmonitoring
AT huangchangwei highdimensionalphasespacereconstructionwithaconvolutionalneuralnetworkforstructuralhealthmonitoring