Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks

This article proposes a novel dynamic response reconstruction approach for structural health monitoring using densely connected convolutional networks. Skip connection and dense block techniques are carefully applied in the designed network architecture, which greatly facilitates the information flo...

Full description

Bibliographic Details
Main Authors: Fan, Gao, Li, Jun, Hao, Hong
Format: Journal Article
Language:English
Published: SAGE PUBLICATIONS LTD 2021
Subjects:
Online Access:http://purl.org/au-research/grants/arc/FT190100801
http://hdl.handle.net/20.500.11937/90889
_version_ 1848765452253134848
author Fan, Gao
Li, Jun
Hao, Hong
author_facet Fan, Gao
Li, Jun
Hao, Hong
author_sort Fan, Gao
building Curtin Institutional Repository
collection Online Access
description This article proposes a novel dynamic response reconstruction approach for structural health monitoring using densely connected convolutional networks. Skip connection and dense block techniques are carefully applied in the designed network architecture, which greatly facilitates the information flow, and increases the training efficiency and accuracy of feature extraction and propagation with fewer parameters in the network. Sub-pixel shuffling and dropout techniques are used in the designed network and applied to reduce the computational demand and improve training efficiency. The network is trained in a supervised manner, where the input and output are the measurements of the available channels at response available locations and desired channels at response unavailable locations. The proposed densely connected convolutional networks automatically extract the high-level features of the input data and construct the complicated nonlinear relationship between the responses of available and desired locations. Experimental studies are conducted using the measured acceleration responses from Guangzhou New Television Tower to investigate the effects of the locations of available responses, the numbers of available and unavailable channels, and measurement noise. The results demonstrate that the proposed approach can accurately reconstruct the responses in both time and frequency domains with strong noise immunity. The reconstructed response is further used for modal identification to demonstrate the usability and accuracy of the reconstructed responses. The applicability of the proposed approach for structural health monitoring is further proved by the highly consistent modal parameters identified from the reconstructed and true responses.
first_indexed 2025-11-14T11:35:28Z
format Journal Article
id curtin-20.500.11937-90889
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:35:28Z
publishDate 2021
publisher SAGE PUBLICATIONS LTD
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-908892023-05-05T05:54:10Z Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks Fan, Gao Li, Jun Hao, Hong Science & Technology Technology Engineering, Multidisciplinary Instruments & Instrumentation Engineering Dynamic response reconstruction structural health monitoring densely connected convolutional networks deep learning experimental validation MULTITYPE SENSOR PLACEMENT DAMAGE IDENTIFICATION NEURAL-NETWORKS MODAL-ANALYSIS RECOVERY This article proposes a novel dynamic response reconstruction approach for structural health monitoring using densely connected convolutional networks. Skip connection and dense block techniques are carefully applied in the designed network architecture, which greatly facilitates the information flow, and increases the training efficiency and accuracy of feature extraction and propagation with fewer parameters in the network. Sub-pixel shuffling and dropout techniques are used in the designed network and applied to reduce the computational demand and improve training efficiency. The network is trained in a supervised manner, where the input and output are the measurements of the available channels at response available locations and desired channels at response unavailable locations. The proposed densely connected convolutional networks automatically extract the high-level features of the input data and construct the complicated nonlinear relationship between the responses of available and desired locations. Experimental studies are conducted using the measured acceleration responses from Guangzhou New Television Tower to investigate the effects of the locations of available responses, the numbers of available and unavailable channels, and measurement noise. The results demonstrate that the proposed approach can accurately reconstruct the responses in both time and frequency domains with strong noise immunity. The reconstructed response is further used for modal identification to demonstrate the usability and accuracy of the reconstructed responses. The applicability of the proposed approach for structural health monitoring is further proved by the highly consistent modal parameters identified from the reconstructed and true responses. 2021 Journal Article http://hdl.handle.net/20.500.11937/90889 10.1177/1475921720916881 English http://purl.org/au-research/grants/arc/FT190100801 SAGE PUBLICATIONS LTD unknown
spellingShingle Science & Technology
Technology
Engineering, Multidisciplinary
Instruments & Instrumentation
Engineering
Dynamic response reconstruction
structural health monitoring
densely connected convolutional networks
deep learning
experimental validation
MULTITYPE SENSOR PLACEMENT
DAMAGE IDENTIFICATION
NEURAL-NETWORKS
MODAL-ANALYSIS
RECOVERY
Fan, Gao
Li, Jun
Hao, Hong
Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks
title Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks
title_full Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks
title_fullStr Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks
title_full_unstemmed Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks
title_short Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks
title_sort dynamic response reconstruction for structural health monitoring using densely connected convolutional networks
topic Science & Technology
Technology
Engineering, Multidisciplinary
Instruments & Instrumentation
Engineering
Dynamic response reconstruction
structural health monitoring
densely connected convolutional networks
deep learning
experimental validation
MULTITYPE SENSOR PLACEMENT
DAMAGE IDENTIFICATION
NEURAL-NETWORKS
MODAL-ANALYSIS
RECOVERY
url http://purl.org/au-research/grants/arc/FT190100801
http://hdl.handle.net/20.500.11937/90889