SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORK

A damage detection method based on wavelet packet transform and replicator neural networks is proposed to carry out real-time damage detection of structures. Firstly,wavelet packet transform is used to decompose original vibration response signals to calculate the relative band energy of each band....

Full description

Saved in:
Bibliographic Details
Main Authors: ZHANG Xiang, CHEN RenWen
Format: Article
Language:zho
Published: Editorial Office of Journal of Mechanical Strength 2020-01-01
Series:Jixie qiangdu
Subjects:
Online Access:http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2020.03.001
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841535792167518208
author ZHANG Xiang
CHEN RenWen
author_facet ZHANG Xiang
CHEN RenWen
author_sort ZHANG Xiang
collection DOAJ
description A damage detection method based on wavelet packet transform and replicator neural networks is proposed to carry out real-time damage detection of structures. Firstly,wavelet packet transform is used to decompose original vibration response signals to calculate the relative band energy of each band. The distribution of relative band energy reflects the characteristics of the structure to be detected. Secondly,the relative energy from healthy structure is taken as input to training replicator neural networks. Finally,the trained networks are used for damage detection in real-time. Experiments showed that the proposed method can detect single-position damage even under noise interference.
format Article
id doaj-art-89448be211b14a47b4925abc190c9ef9
institution Kabale University
issn 1001-9669
language zho
publishDate 2020-01-01
publisher Editorial Office of Journal of Mechanical Strength
record_format Article
series Jixie qiangdu
spelling doaj-art-89448be211b14a47b4925abc190c9ef92025-01-15T02:27:45ZzhoEditorial Office of Journal of Mechanical StrengthJixie qiangdu1001-96692020-01-014250951530607788SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORKZHANG XiangCHEN RenWenA damage detection method based on wavelet packet transform and replicator neural networks is proposed to carry out real-time damage detection of structures. Firstly,wavelet packet transform is used to decompose original vibration response signals to calculate the relative band energy of each band. The distribution of relative band energy reflects the characteristics of the structure to be detected. Secondly,the relative energy from healthy structure is taken as input to training replicator neural networks. Finally,the trained networks are used for damage detection in real-time. Experiments showed that the proposed method can detect single-position damage even under noise interference.http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2020.03.001Replicator Neural Network(RNN)Wavelet packet transformRelative band energyDamage detection
spellingShingle ZHANG Xiang
CHEN RenWen
SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORK
Jixie qiangdu
Replicator Neural Network(RNN)
Wavelet packet transform
Relative band energy
Damage detection
title SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORK
title_full SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORK
title_fullStr SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORK
title_full_unstemmed SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORK
title_short SINGLE-POSITION DAMAGE DETECTION BASED ON WAVELET PACKET TRANSFORM AND REPLICATOR NEURAL NETWORK
title_sort single position damage detection based on wavelet packet transform and replicator neural network
topic Replicator Neural Network(RNN)
Wavelet packet transform
Relative band energy
Damage detection
url http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2020.03.001
work_keys_str_mv AT zhangxiang singlepositiondamagedetectionbasedonwaveletpackettransformandreplicatorneuralnetwork
AT chenrenwen singlepositiondamagedetectionbasedonwaveletpackettransformandreplicatorneuralnetwork