Vibration signal denoising for structural health monitoring by residual convolutional neural networks

In vibration based structural health monitoring (SHM), measurement noise inevitably exists in the vibration data, which significantly influences the usability and quality of measured vibration signals for structural identification and condition monitoring. As a result, there is a high demand for dev...

Full description

Bibliographic Details
Main Authors: Fan, G., Li, Jun, Hao, Hong
Format: Journal Article
Language:English
Published: ELSEVIER SCI LTD 2020
Subjects:
Online Access:http://purl.org/au-research/grants/arc/FL180100196
http://hdl.handle.net/20.500.11937/91514
_version_ 1848765535200739328
author Fan, G.
Li, Jun
Hao, Hong
author_facet Fan, G.
Li, Jun
Hao, Hong
author_sort Fan, G.
building Curtin Institutional Repository
collection Online Access
description In vibration based structural health monitoring (SHM), measurement noise inevitably exists in the vibration data, which significantly influences the usability and quality of measured vibration signals for structural identification and condition monitoring. As a result, there is a high demand for developing effective methods to reduce noise effect, especially in harsh and extreme environment. This paper proposes a vibration signal denoising approach for SHM based on a specialized Residual Convolutional Neural Networks (ResNet). Dropout, skip connection and sub-pixel shuffling techniques are used to improve the performance. The effectiveness and robustness of this developed approach are validated with acceleration data measured from Guangzhou New TV Tower. The results show that the proposed approach is effective in improving the quality of the acceleration data with varying levels of noises and different types of noises. Modal identifications based on signals contaminated with intensive noise and de-noised signals are conducted. Modal information of weakly excited modes masked by noise and closely spaced modes can be clearly and accurately identified from the de-noised signals, which could not be reliably identified with the original signal, indicating the effectiveness of using this developed approach for SHM. Besides white noise, a group of data contaminated with pink noise, which is not included in the training data, is also tested. Good results are obtained. The developed ResNet extracts high-level features from the vibration signal and learns the modal information of structures automatically, therefore it can well preserve the most important vibration characteristics in vibration signals, and can assist in distinguishing the physical modes from the spurious modes in structural modal identification.
first_indexed 2025-11-14T11:36:47Z
format Journal Article
id curtin-20.500.11937-91514
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:36:47Z
publishDate 2020
publisher ELSEVIER SCI LTD
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-915142023-05-04T07:12:53Z Vibration signal denoising for structural health monitoring by residual convolutional neural networks Fan, G. Li, Jun Hao, Hong Science & Technology Technology Engineering, Multidisciplinary Instruments & Instrumentation Engineering Denoising Modal identification Noise Residual convolutional neural network Structural health monitoring Vibration signal DAMAGE IDENTIFICATION FREQUENCY-DOMAIN SPEECH ENHANCEMENT FEATURE-EXTRACTION MODAL-ANALYSIS WAVELET SUBSTRUCTURE In vibration based structural health monitoring (SHM), measurement noise inevitably exists in the vibration data, which significantly influences the usability and quality of measured vibration signals for structural identification and condition monitoring. As a result, there is a high demand for developing effective methods to reduce noise effect, especially in harsh and extreme environment. This paper proposes a vibration signal denoising approach for SHM based on a specialized Residual Convolutional Neural Networks (ResNet). Dropout, skip connection and sub-pixel shuffling techniques are used to improve the performance. The effectiveness and robustness of this developed approach are validated with acceleration data measured from Guangzhou New TV Tower. The results show that the proposed approach is effective in improving the quality of the acceleration data with varying levels of noises and different types of noises. Modal identifications based on signals contaminated with intensive noise and de-noised signals are conducted. Modal information of weakly excited modes masked by noise and closely spaced modes can be clearly and accurately identified from the de-noised signals, which could not be reliably identified with the original signal, indicating the effectiveness of using this developed approach for SHM. Besides white noise, a group of data contaminated with pink noise, which is not included in the training data, is also tested. Good results are obtained. The developed ResNet extracts high-level features from the vibration signal and learns the modal information of structures automatically, therefore it can well preserve the most important vibration characteristics in vibration signals, and can assist in distinguishing the physical modes from the spurious modes in structural modal identification. 2020 Journal Article http://hdl.handle.net/20.500.11937/91514 10.1016/j.measurement.2020.107651 English http://purl.org/au-research/grants/arc/FL180100196 ELSEVIER SCI LTD fulltext
spellingShingle Science & Technology
Technology
Engineering, Multidisciplinary
Instruments & Instrumentation
Engineering
Denoising
Modal identification
Noise
Residual convolutional neural network
Structural health monitoring
Vibration signal
DAMAGE IDENTIFICATION
FREQUENCY-DOMAIN
SPEECH ENHANCEMENT
FEATURE-EXTRACTION
MODAL-ANALYSIS
WAVELET
SUBSTRUCTURE
Fan, G.
Li, Jun
Hao, Hong
Vibration signal denoising for structural health monitoring by residual convolutional neural networks
title Vibration signal denoising for structural health monitoring by residual convolutional neural networks
title_full Vibration signal denoising for structural health monitoring by residual convolutional neural networks
title_fullStr Vibration signal denoising for structural health monitoring by residual convolutional neural networks
title_full_unstemmed Vibration signal denoising for structural health monitoring by residual convolutional neural networks
title_short Vibration signal denoising for structural health monitoring by residual convolutional neural networks
title_sort vibration signal denoising for structural health monitoring by residual convolutional neural networks
topic Science & Technology
Technology
Engineering, Multidisciplinary
Instruments & Instrumentation
Engineering
Denoising
Modal identification
Noise
Residual convolutional neural network
Structural health monitoring
Vibration signal
DAMAGE IDENTIFICATION
FREQUENCY-DOMAIN
SPEECH ENHANCEMENT
FEATURE-EXTRACTION
MODAL-ANALYSIS
WAVELET
SUBSTRUCTURE
url http://purl.org/au-research/grants/arc/FL180100196
http://hdl.handle.net/20.500.11937/91514