Delamination prediction in composite panels using unsupervised-feature learning methods with wavelet-enhanced guided wave representations

With the introduction of damage tolerance-based design philosophies, the demand for reliable and robust structural health monitoring (SHM) procedures for aerospace composite structures is increasing rapidly. The performance of supervised learning algorithms for SHM depends on the amount of labeled a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Composite structures Jg. 291; S. 115579
Hauptverfasser: Rautela, Mahindra, Senthilnath, J., Monaco, Ernesto, Gopalakrishnan, S.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.07.2022
Schlagworte:
ISSN:0263-8223, 1879-1085
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract With the introduction of damage tolerance-based design philosophies, the demand for reliable and robust structural health monitoring (SHM) procedures for aerospace composite structures is increasing rapidly. The performance of supervised learning algorithms for SHM depends on the amount of labeled and balanced datasets. Apart from this, collecting datasets accommodating all possible damage scenarios is cumbersome, costly, and inaccessible for aerospace applications. In this paper, we have proposed two different unsupervised-feature learning approaches where the algorithms are trained only on the baseline scenarios to learn the distribution of baseline signals. The trained unsupervised feature learner is used for delamination prediction with an anomaly detection philosophy. In the first approach, we have combined dimensionality reduction techniques (principal component analysis and independent component analysis) with a one-class support vector machine. In another approach, we have utilized deep learning-based deep convolutional autoencoders (CAE). These state-of-the-art algorithms are applied on three different guided wave-based experimental datasets. The raw guided wave signals present in the datasets are converted into wavelet-enhanced higher-order representations for training unsupervised feature-learning algorithms. We have also compared different techniques, and it is seen that CAE generates better reconstructions with lower mean squared error and can provide higher accuracy on all the datasets.
AbstractList With the introduction of damage tolerance-based design philosophies, the demand for reliable and robust structural health monitoring (SHM) procedures for aerospace composite structures is increasing rapidly. The performance of supervised learning algorithms for SHM depends on the amount of labeled and balanced datasets. Apart from this, collecting datasets accommodating all possible damage scenarios is cumbersome, costly, and inaccessible for aerospace applications. In this paper, we have proposed two different unsupervised-feature learning approaches where the algorithms are trained only on the baseline scenarios to learn the distribution of baseline signals. The trained unsupervised feature learner is used for delamination prediction with an anomaly detection philosophy. In the first approach, we have combined dimensionality reduction techniques (principal component analysis and independent component analysis) with a one-class support vector machine. In another approach, we have utilized deep learning-based deep convolutional autoencoders (CAE). These state-of-the-art algorithms are applied on three different guided wave-based experimental datasets. The raw guided wave signals present in the datasets are converted into wavelet-enhanced higher-order representations for training unsupervised feature-learning algorithms. We have also compared different techniques, and it is seen that CAE generates better reconstructions with lower mean squared error and can provide higher accuracy on all the datasets.
ArticleNumber 115579
Author Gopalakrishnan, S.
Rautela, Mahindra
Senthilnath, J.
Monaco, Ernesto
Author_xml – sequence: 1
  givenname: Mahindra
  orcidid: 0000-0002-2678-9682
  surname: Rautela
  fullname: Rautela, Mahindra
  email: mrautela@iisc.ac.in
  organization: Department of Aerospace Engineering, Indian Institute of Science, Bangalore, India
– sequence: 2
  givenname: J.
  orcidid: 0000-0002-1737-7985
  surname: Senthilnath
  fullname: Senthilnath, J.
  email: j_senthilnath@i2r.a-star.edu.sg
  organization: Institute for Infocomm Research, ASTAR, Singapore
– sequence: 3
  givenname: Ernesto
  surname: Monaco
  fullname: Monaco, Ernesto
  email: ermonaco@unina.it
  organization: Department of Industrial Engineering, University of Naples Federico II, Italy
– sequence: 4
  givenname: S.
  surname: Gopalakrishnan
  fullname: Gopalakrishnan, S.
  email: krishnan@iisc.ac.in
  organization: Department of Aerospace Engineering, Indian Institute of Science, Bangalore, India
BookMark eNqNkN9OwyAUh4mZidv0HXiBTqBroTcmOv8mS7zRa8LgdGNpaQN0i4_gW9uuJibe6NUhHM73O3wzNHGNA4QwJQtKaH69X-imbkP0nY4LRhhbUJplvDhDUyp4kVAisgmaEpaniWAsvUCzEPaEELGkdIo-76FStXUq2sbh1oOx-nS0Dg_gJtgIuFUOqoC7YN0Wdy50LfiDDWCSElTsPOAKlHdDt4a4a0zARxt3-KgOUEFMwO2U02DwtrOmL8M99tDHBXDxlB0u0XmpqgBX33WO3h8f3lbPyfr16WV1u040E2mRCEoIoxlnZlmY_nNa5SkHBUA2aWaYUjkYVarCmEJogJwDywnlm4Jrzkut0zm6GbnaNyF4KKW24wrRK1tJSuQgVu7lj1g5iJWj2B4gfgFab2vlP_4zejeO9jbhYMHLoC0MZqyH_q1p7N-QL-dkomQ
CitedBy_id crossref_primary_10_1016_j_ndteint_2023_102961
crossref_primary_10_1177_14759217231183143
crossref_primary_10_1016_j_compositesb_2023_110907
crossref_primary_10_1016_j_ress_2024_110586
crossref_primary_10_1177_14759217251324107
crossref_primary_10_1016_j_coco_2025_102542
crossref_primary_10_1007_s11831_024_10146_y
crossref_primary_10_1038_s41598_024_54418_w
crossref_primary_10_1016_j_tws_2025_113914
crossref_primary_10_1016_j_ultras_2025_107688
crossref_primary_10_1016_j_ymssp_2022_109910
crossref_primary_10_1177_14759217251317747
crossref_primary_10_1177_14759217221111977
crossref_primary_10_1002_pc_29055
crossref_primary_10_1016_j_paerosci_2024_100994
crossref_primary_10_1016_j_compstruct_2023_117792
crossref_primary_10_1016_j_engstruct_2024_119192
crossref_primary_10_1177_00368504221146081
crossref_primary_10_1016_j_measurement_2024_115061
crossref_primary_10_1080_09243046_2023_2215474
crossref_primary_10_3390_sym17010091
crossref_primary_10_1016_j_compstruct_2025_119163
crossref_primary_10_1038_s41598_024_68944_0
crossref_primary_10_1109_TAI_2022_3229653
crossref_primary_10_1016_j_ultras_2023_106931
crossref_primary_10_1016_j_istruc_2024_107823
crossref_primary_10_1016_j_ultras_2023_107014
crossref_primary_10_3389_feart_2023_1298758
crossref_primary_10_1016_j_ultras_2025_107632
crossref_primary_10_1016_j_ymssp_2024_111645
crossref_primary_10_1038_s43588_024_00632_5
crossref_primary_10_1109_TIM_2023_3348884
crossref_primary_10_1016_j_matdes_2023_111686
crossref_primary_10_1016_j_ymssp_2023_110432
crossref_primary_10_1016_j_ymssp_2024_112076
Cites_doi 10.1002/stc.150
10.1117/1.OE.55.1.011007
10.1177/1475921717737971
10.1177/1475921720934051
10.1145/1390156.1390294
10.1023/A:1022627411411
10.1109/JSEN.2020.3009194
10.1177/1475921718817169
10.1088/1361-665X/ab58d6
10.1007/s42791-019-0012-2
10.1177/1475921704041876
10.1177/1475921714532989
10.1038/s41598-021-00326-2
10.1088/0964-1726/25/5/053001
10.1162/089976601750264965
10.1016/j.eswa.2020.114189
10.1016/j.aei.2020.101105
10.3390/aerospace5040111
10.1016/j.ultras.2021.106451
10.1177/1475921716639587
10.1088/0964-1726/22/12/125019
10.1016/S0893-6080(00)00026-5
10.1002/stc.2714
ContentType Journal Article
Copyright 2022 Elsevier Ltd
Copyright_xml – notice: 2022 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.compstruct.2022.115579
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1879-1085
ExternalDocumentID 10_1016_j_compstruct_2022_115579
S026382232200366X
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5GY
5VS
6TJ
7-5
71M
8P~
9JN
AABNK
AABXZ
AACTN
AAEDT
AAEDW
AAEPC
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
ABMAC
ABXRA
ABYKQ
ACDAQ
ACGFS
ACRLP
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEKER
AENEX
AEZYN
AFKWA
AFRZQ
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
JJJVA
KOM
LY7
M24
M41
MAGPM
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SSM
SST
SSZ
T5K
XPP
ZMT
~02
~G-
29F
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABFNM
ABJNI
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADIYS
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
G-2
HVGLF
HZ~
R2-
SET
SEW
SMS
WUQ
~HD
ID FETCH-LOGICAL-c2839-810021572d49d108ca637eaee0b35d2aa6edafa9dd98cee67e26017b97c77fcc3
ISSN 0263-8223
IngestDate Tue Nov 18 22:11:18 EST 2025
Sat Nov 29 07:20:04 EST 2025
Fri Feb 23 02:39:42 EST 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Delamination detection
Independent component analysis (ICA)
One-class support vector machines (ocSVM)
Principal component analysis (PCA)
Convolutional autoencoders (CAE)
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c2839-810021572d49d108ca637eaee0b35d2aa6edafa9dd98cee67e26017b97c77fcc3
ORCID 0000-0002-2678-9682
0000-0002-1737-7985
OpenAccessLink https://www.sciencedirect.com/science/article/pii/S026382232200366X
ParticipantIDs crossref_citationtrail_10_1016_j_compstruct_2022_115579
crossref_primary_10_1016_j_compstruct_2022_115579
elsevier_sciencedirect_doi_10_1016_j_compstruct_2022_115579
PublicationCentury 2000
PublicationDate 2022-07-01
2022-07-00
PublicationDateYYYYMMDD 2022-07-01
PublicationDate_xml – month: 07
  year: 2022
  text: 2022-07-01
  day: 01
PublicationDecade 2020
PublicationTitle Composite structures
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Peng, Saxena, Goebel, Xiang, Sankararaman, Liu (b20) 2013; 22
Schölkopf, Platt, Shawe-Taylor, Smola, Williamson (b25) 2001; 13
Zang, Friswell, Imregun (b10) 2004; 3
Khoa, Zhang, Wang, Chen, Mustapha (b11) 2014; 13
Chow, Su, Wu, Tan, Mao, Wang (b14) 2020; 45
Liu, Zhang (b3) 2019; 29
Wuttke, Lyu, Sattari, Rizvi (b18) 2021; 11
Rautela, Jayavelu, Moll, Gopalakrishnan (b1) 2021
Wang, Cha (b12) 2021; 20
He, Yan (b8) 2007; 14
Gopalakrishnan, Mitra (b32) 2010
Rautela, Senthilnath, Moll, Gopalakrishnan (b6) 2021; 115
Kingma, Ba (b33) 2014
Rautela, Gopalakrishnan (b16) 2021; 167
Wang, Taal, Fink (b29) 2021
Goodfellow, Bengio, Courville, Bengio (b28) 2016
Memmolo, Maio, Boffa, Monaco, Ricci (b21) 2015; 55
Ruiz, Mujica, Sierra, Pozo, Rodellar (b7) 2018; 17
Zhang, Hong, Liu (b5) 2020; 20
Rautela, Monaco, Gopalakrishnan (b17) 2021
Moll, Kathol, Fritzen, Moix-Bonet, Rennoch, Koerdt (b19) 2019; 18
Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning. 2008, p. 1096–103.
Silva, Santos, Santos, Figueiredo, Costa (b13) 2021; 28
Garcia GR, Michau G, Ducoffe M, Gupta JS, Fink O. Temporal signals to images: Monitoring the condition of industrial assets with deep learning image processing algorithms. Proc Inst Mech Eng O 1748006X21994446.
Ghiasi, Torkzadeh, Noori (b9) 2016; 15
Mitra, Gopalakrishnan (b2) 2016; 25
Rautela, Huber, Senthilnath, Gopalakrishnan (b26) 2021
Khan, Kim, Shin, Kim, Youn (b4) 2019; 1
Cortes, Vapnik (b24) 1995; 20
Bishop (b22) 2006; 128
Abbate, Frankel, Das (b31) 1995
Hyvärinen, Oja (b23) 2000; 13
Memmolo, Boffa, Maio, Monaco, Ricci (b30) 2018; 5
He (10.1016/j.compstruct.2022.115579_b8) 2007; 14
Wang (10.1016/j.compstruct.2022.115579_b12) 2021; 20
Wang (10.1016/j.compstruct.2022.115579_b29) 2021
Rautela (10.1016/j.compstruct.2022.115579_b16) 2021; 167
Khan (10.1016/j.compstruct.2022.115579_b4) 2019; 1
Wuttke (10.1016/j.compstruct.2022.115579_b18) 2021; 11
Moll (10.1016/j.compstruct.2022.115579_b19) 2019; 18
10.1016/j.compstruct.2022.115579_b15
Goodfellow (10.1016/j.compstruct.2022.115579_b28) 2016
Rautela (10.1016/j.compstruct.2022.115579_b26) 2021
Silva (10.1016/j.compstruct.2022.115579_b13) 2021; 28
Zhang (10.1016/j.compstruct.2022.115579_b5) 2020; 20
Zang (10.1016/j.compstruct.2022.115579_b10) 2004; 3
Memmolo (10.1016/j.compstruct.2022.115579_b30) 2018; 5
Gopalakrishnan (10.1016/j.compstruct.2022.115579_b32) 2010
Hyvärinen (10.1016/j.compstruct.2022.115579_b23) 2000; 13
Bishop (10.1016/j.compstruct.2022.115579_b22) 2006; 128
Ghiasi (10.1016/j.compstruct.2022.115579_b9) 2016; 15
Peng (10.1016/j.compstruct.2022.115579_b20) 2013; 22
Memmolo (10.1016/j.compstruct.2022.115579_b21) 2015; 55
Mitra (10.1016/j.compstruct.2022.115579_b2) 2016; 25
10.1016/j.compstruct.2022.115579_b27
Chow (10.1016/j.compstruct.2022.115579_b14) 2020; 45
Khoa (10.1016/j.compstruct.2022.115579_b11) 2014; 13
Rautela (10.1016/j.compstruct.2022.115579_b6) 2021; 115
Rautela (10.1016/j.compstruct.2022.115579_b17) 2021
Ruiz (10.1016/j.compstruct.2022.115579_b7) 2018; 17
Liu (10.1016/j.compstruct.2022.115579_b3) 2019; 29
Cortes (10.1016/j.compstruct.2022.115579_b24) 1995; 20
Rautela (10.1016/j.compstruct.2022.115579_b1) 2021
Schölkopf (10.1016/j.compstruct.2022.115579_b25) 2001; 13
Abbate (10.1016/j.compstruct.2022.115579_b31) 1995
Kingma (10.1016/j.compstruct.2022.115579_b33) 2014
References_xml – year: 2021
  ident: b1
  article-title: Temperature compensation for guided waves using convolutional denoising autoencoders
  publication-title: Health monitoring of structural and biological systems XV, vol. 11593
– year: 2021
  ident: b17
  article-title: Delamination detection in aerospace composite panels using convolutional autoencoders
  publication-title: Health monitoring of structural and biological systems XV, vol. 11593
– volume: 18
  start-page: 1903
  year: 2019
  end-page: 1914
  ident: b19
  article-title: Open guided waves: online platform for ultrasonic guided wave measurements
  publication-title: Struct Health Monit
– volume: 55
  year: 2015
  ident: b21
  article-title: Damage detection tomography based on guided waves in composite structures using a distributed sensor network
  publication-title: Opt Eng
– volume: 20
  start-page: 406
  year: 2021
  end-page: 425
  ident: b12
  article-title: Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage
  publication-title: Struct Health Monit
– year: 2010
  ident: b32
  article-title: Wavelet methods for dynamical problems: with application to metallic, composite, and nano-composite structures
– volume: 11
  start-page: 1
  year: 2021
  end-page: 15
  ident: b18
  article-title: Wave based damage detection in solid structures using spatially asymmetric encoder–decoder network
  publication-title: Sci Rep
– volume: 29
  year: 2019
  ident: b3
  article-title: Deep learning based crack damage detection technique for thin plate structures using guided lamb wave signals
  publication-title: Smart Mater Struct
– volume: 5
  start-page: 111
  year: 2018
  ident: b30
  article-title: Damage localization in composite structures using a guided waves based multi-parameter approach
  publication-title: Aerospace
– volume: 3
  start-page: 69
  year: 2004
  end-page: 83
  ident: b10
  article-title: Structural damage detection using independent component analysis
  publication-title: Struct Health Monit
– start-page: 751
  year: 1995
  end-page: 755
  ident: b31
  article-title: Wavelet transform signal processing for dispersion analysis of ultrasonic signals
  publication-title: 1995 IEEE Ultrasonics symposium. proceedings. an international symposium, vol. 1
– start-page: 1
  year: 2021
  end-page: 17
  ident: b26
  article-title: Inverse characterization of composites using guided waves and convolutional neural networks with dual-branch feature fusion
  publication-title: Mech Adv Mater Struct
– volume: 14
  start-page: 162
  year: 2007
  end-page: 176
  ident: b8
  article-title: Structural damage detection with wavelet support vector machine: introduction and applications
  publication-title: Struct Control Health Monit
– volume: 167
  year: 2021
  ident: b16
  article-title: Ultrasonic guided wave based structural damage detection and localization using model assisted convolutional and recurrent neural networks
  publication-title: Expert Syst Appl
– reference: Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning. 2008, p. 1096–103.
– year: 2014
  ident: b33
  article-title: Adam: A method for stochastic optimization
– volume: 22
  year: 2013
  ident: b20
  article-title: A novel Bayesian imaging method for probabilistic delamination detection of composite materials
  publication-title: Smart Mater Struct
– volume: 45
  year: 2020
  ident: b14
  article-title: Anomaly detection of defects on concrete structures with the convolutional autoencoder
  publication-title: Adv Eng Inf
– year: 2016
  ident: b28
  article-title: Deep learning, vol. 1, no. 2
– volume: 15
  start-page: 302
  year: 2016
  end-page: 316
  ident: b9
  article-title: A machine-learning approach for structural damage detection using least square support vector machine based on a new combinational kernel function
  publication-title: Struct Health Monit
– volume: 20
  start-page: 273
  year: 1995
  end-page: 297
  ident: b24
  article-title: Support-vector networks
  publication-title: Mach Learn
– volume: 25
  year: 2016
  ident: b2
  article-title: Guided wave based structural health monitoring: A review
  publication-title: Smart Mater Struct
– volume: 20
  start-page: 14391
  year: 2020
  end-page: 14400
  ident: b5
  article-title: Multi-task deep transfer learning method for guided wave-based integrated health monitoring using piezoelectric transducers
  publication-title: IEEE Sens J
– volume: 28
  year: 2021
  ident: b13
  article-title: Damage-sensitive feature extraction with stacked autoencoders for unsupervised damage detection
  publication-title: Struct Control Health Monit
– volume: 13
  start-page: 411
  year: 2000
  end-page: 430
  ident: b23
  article-title: Independent component analysis: algorithms and applications
  publication-title: Neural Netw
– volume: 17
  start-page: 1151
  year: 2018
  end-page: 1165
  ident: b7
  article-title: Multiway principal component analysis contributions for structural damage localization
  publication-title: Struct Health Monit
– reference: Garcia GR, Michau G, Ducoffe M, Gupta JS, Fink O. Temporal signals to images: Monitoring the condition of industrial assets with deep learning image processing algorithms. Proc Inst Mech Eng O 1748006X21994446.
– volume: 128
  year: 2006
  ident: b22
  article-title: Pattern recognition
  publication-title: Mach Learn
– volume: 1
  start-page: 107
  year: 2019
  end-page: 124
  ident: b4
  article-title: Damage assessment of smart composite structures via machine learning: a review
  publication-title: JMST Adv
– year: 2021
  ident: b29
  article-title: Integrating expert knowledge with domain adaptation for unsupervised fault diagnosis
  publication-title: IEEE Trans Instrum Meas
– volume: 13
  start-page: 1443
  year: 2001
  end-page: 1471
  ident: b25
  article-title: Estimating the support of a high-dimensional distribution
  publication-title: Neural Comput
– volume: 13
  start-page: 406
  year: 2014
  end-page: 417
  ident: b11
  article-title: Robust dimensionality reduction and damage detection approaches in structural health monitoring
  publication-title: Struct Health Monit
– volume: 115
  year: 2021
  ident: b6
  article-title: Combined two-level damage identification strategy using ultrasonic guided waves and physical knowledge assisted machine learning
  publication-title: Ultrasonics
– volume: 14
  start-page: 162
  issue: 1
  year: 2007
  ident: 10.1016/j.compstruct.2022.115579_b8
  article-title: Structural damage detection with wavelet support vector machine: introduction and applications
  publication-title: Struct Control Health Monit
  doi: 10.1002/stc.150
– volume: 55
  issue: 1
  year: 2015
  ident: 10.1016/j.compstruct.2022.115579_b21
  article-title: Damage detection tomography based on guided waves in composite structures using a distributed sensor network
  publication-title: Opt Eng
  doi: 10.1117/1.OE.55.1.011007
– year: 2016
  ident: 10.1016/j.compstruct.2022.115579_b28
– volume: 128
  issue: 9
  year: 2006
  ident: 10.1016/j.compstruct.2022.115579_b22
  article-title: Pattern recognition
  publication-title: Mach Learn
– year: 2010
  ident: 10.1016/j.compstruct.2022.115579_b32
– volume: 17
  start-page: 1151
  issue: 5
  year: 2018
  ident: 10.1016/j.compstruct.2022.115579_b7
  article-title: Multiway principal component analysis contributions for structural damage localization
  publication-title: Struct Health Monit
  doi: 10.1177/1475921717737971
– volume: 20
  start-page: 406
  issue: 1
  year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b12
  article-title: Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage
  publication-title: Struct Health Monit
  doi: 10.1177/1475921720934051
– ident: 10.1016/j.compstruct.2022.115579_b27
  doi: 10.1145/1390156.1390294
– volume: 20
  start-page: 273
  issue: 3
  year: 1995
  ident: 10.1016/j.compstruct.2022.115579_b24
  article-title: Support-vector networks
  publication-title: Mach Learn
  doi: 10.1023/A:1022627411411
– volume: 20
  start-page: 14391
  issue: 23
  year: 2020
  ident: 10.1016/j.compstruct.2022.115579_b5
  article-title: Multi-task deep transfer learning method for guided wave-based integrated health monitoring using piezoelectric transducers
  publication-title: IEEE Sens J
  doi: 10.1109/JSEN.2020.3009194
– volume: 18
  start-page: 1903
  issue: 5–6
  year: 2019
  ident: 10.1016/j.compstruct.2022.115579_b19
  article-title: Open guided waves: online platform for ultrasonic guided wave measurements
  publication-title: Struct Health Monit
  doi: 10.1177/1475921718817169
– volume: 29
  issue: 1
  year: 2019
  ident: 10.1016/j.compstruct.2022.115579_b3
  article-title: Deep learning based crack damage detection technique for thin plate structures using guided lamb wave signals
  publication-title: Smart Mater Struct
  doi: 10.1088/1361-665X/ab58d6
– start-page: 1
  year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b26
  article-title: Inverse characterization of composites using guided waves and convolutional neural networks with dual-branch feature fusion
  publication-title: Mech Adv Mater Struct
– volume: 1
  start-page: 107
  issue: 1
  year: 2019
  ident: 10.1016/j.compstruct.2022.115579_b4
  article-title: Damage assessment of smart composite structures via machine learning: a review
  publication-title: JMST Adv
  doi: 10.1007/s42791-019-0012-2
– volume: 3
  start-page: 69
  issue: 1
  year: 2004
  ident: 10.1016/j.compstruct.2022.115579_b10
  article-title: Structural damage detection using independent component analysis
  publication-title: Struct Health Monit
  doi: 10.1177/1475921704041876
– start-page: 751
  year: 1995
  ident: 10.1016/j.compstruct.2022.115579_b31
  article-title: Wavelet transform signal processing for dispersion analysis of ultrasonic signals
– year: 2014
  ident: 10.1016/j.compstruct.2022.115579_b33
– volume: 13
  start-page: 406
  issue: 4
  year: 2014
  ident: 10.1016/j.compstruct.2022.115579_b11
  article-title: Robust dimensionality reduction and damage detection approaches in structural health monitoring
  publication-title: Struct Health Monit
  doi: 10.1177/1475921714532989
– year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b1
  article-title: Temperature compensation for guided waves using convolutional denoising autoencoders
– volume: 11
  start-page: 1
  issue: 1
  year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b18
  article-title: Wave based damage detection in solid structures using spatially asymmetric encoder–decoder network
  publication-title: Sci Rep
  doi: 10.1038/s41598-021-00326-2
– volume: 25
  issue: 5
  year: 2016
  ident: 10.1016/j.compstruct.2022.115579_b2
  article-title: Guided wave based structural health monitoring: A review
  publication-title: Smart Mater Struct
  doi: 10.1088/0964-1726/25/5/053001
– volume: 13
  start-page: 1443
  issue: 7
  year: 2001
  ident: 10.1016/j.compstruct.2022.115579_b25
  article-title: Estimating the support of a high-dimensional distribution
  publication-title: Neural Comput
  doi: 10.1162/089976601750264965
– volume: 167
  year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b16
  article-title: Ultrasonic guided wave based structural damage detection and localization using model assisted convolutional and recurrent neural networks
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2020.114189
– year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b17
  article-title: Delamination detection in aerospace composite panels using convolutional autoencoders
– volume: 45
  year: 2020
  ident: 10.1016/j.compstruct.2022.115579_b14
  article-title: Anomaly detection of defects on concrete structures with the convolutional autoencoder
  publication-title: Adv Eng Inf
  doi: 10.1016/j.aei.2020.101105
– year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b29
  article-title: Integrating expert knowledge with domain adaptation for unsupervised fault diagnosis
  publication-title: IEEE Trans Instrum Meas
– volume: 5
  start-page: 111
  issue: 4
  year: 2018
  ident: 10.1016/j.compstruct.2022.115579_b30
  article-title: Damage localization in composite structures using a guided waves based multi-parameter approach
  publication-title: Aerospace
  doi: 10.3390/aerospace5040111
– volume: 115
  year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b6
  article-title: Combined two-level damage identification strategy using ultrasonic guided waves and physical knowledge assisted machine learning
  publication-title: Ultrasonics
  doi: 10.1016/j.ultras.2021.106451
– volume: 15
  start-page: 302
  issue: 3
  year: 2016
  ident: 10.1016/j.compstruct.2022.115579_b9
  article-title: A machine-learning approach for structural damage detection using least square support vector machine based on a new combinational kernel function
  publication-title: Struct Health Monit
  doi: 10.1177/1475921716639587
– volume: 22
  issue: 12
  year: 2013
  ident: 10.1016/j.compstruct.2022.115579_b20
  article-title: A novel Bayesian imaging method for probabilistic delamination detection of composite materials
  publication-title: Smart Mater Struct
  doi: 10.1088/0964-1726/22/12/125019
– ident: 10.1016/j.compstruct.2022.115579_b15
– volume: 13
  start-page: 411
  issue: 4–5
  year: 2000
  ident: 10.1016/j.compstruct.2022.115579_b23
  article-title: Independent component analysis: algorithms and applications
  publication-title: Neural Netw
  doi: 10.1016/S0893-6080(00)00026-5
– volume: 28
  issue: 5
  year: 2021
  ident: 10.1016/j.compstruct.2022.115579_b13
  article-title: Damage-sensitive feature extraction with stacked autoencoders for unsupervised damage detection
  publication-title: Struct Control Health Monit
  doi: 10.1002/stc.2714
SSID ssj0008411
Score 2.5839198
Snippet With the introduction of damage tolerance-based design philosophies, the demand for reliable and robust structural health monitoring (SHM) procedures for...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 115579
SubjectTerms Convolutional autoencoders (CAE)
Delamination detection
Independent component analysis (ICA)
One-class support vector machines (ocSVM)
Principal component analysis (PCA)
Title Delamination prediction in composite panels using unsupervised-feature learning methods with wavelet-enhanced guided wave representations
URI https://dx.doi.org/10.1016/j.compstruct.2022.115579
Volume 291
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect database
  customDbUrl:
  eissn: 1879-1085
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008411
  issn: 0263-8223
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nb9NAEF2FlgMcEJ-ifGkP3KqNHNvZtcWpgiJAqEJKQblZ69114zZyrCYu_Qv8F34kM95d2wqRKEJcrMjKepy8l9nx5M0MIa-FDPO4KCTjJsxZnGvJEi45U9Fkkk9MyIv2H_xvn8XJSTKfp19Go5--FuZqKaoqub5O6_8KNZwDsLF09i_g7i4KJ-A1gA5HgB2ONwL-nQGQS5vkwxYAulRe0Ij6cRRpmUPwAbApHjZtpqCp1k2NPmNtNCtM2-rTj5M4czOmXRXcd4mDKjbMVAsrHThrSo0Kdhxi1DbI9MVMLgvomyB0lm3DWrDQi-xls4F7tpVDi7LSl91WMYOLLcolJvhbuo07fsADhFpZR17hcJxOR7Sq5VJegOtauMnLs_EwsxH2KliXbvMlN72-ad12io0YRDXWKxrrtRORMiyjGLr10E4B-22LsNmKc0S4th95jMZh75hO7VybrQbcMzSJFkMU8nE-v0X2QzFNwYfuH308nn_qdv4kbuc9d7folGNWT7jb3u5waBDinN4n99yzCT2ynHpARqZ6SO4OOlY-Ij-G7KI9u2hZ0Y5d1LKLtuyiu9hFPbuoYxdFdtFtdlHLrvY83WLXY_L1_fHp2w_MTfNgCkJYzDW38aUIdZxqAEtJHgkjjQnyaKpDKbnRspCp1mkCkRsXBrvdiTwVSohCqegJ2atWlXlKaKCwo3JgcER6rIMkneiCS5FEuYQA2gQHRPgvNVOu1T1OXFlmXtN4nvVwZAhHZuE4IJNuZW3bvdxgzRuPW-bCVhuOZkC5P65-9k-rn5M7_S_nBdmDN5iX5La62pTry1eOn78AEuHPZw
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Delamination+prediction+in+composite+panels+using+unsupervised-feature+learning+methods+with+wavelet-enhanced+guided+wave+representations&rft.jtitle=Composite+structures&rft.au=Rautela%2C+Mahindra&rft.au=Senthilnath%2C+J.&rft.au=Monaco%2C+Ernesto&rft.au=Gopalakrishnan%2C+S.&rft.date=2022-07-01&rft.pub=Elsevier+Ltd&rft.issn=0263-8223&rft.eissn=1879-1085&rft.volume=291&rft_id=info:doi/10.1016%2Fj.compstruct.2022.115579&rft.externalDocID=S026382232200366X
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0263-8223&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0263-8223&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0263-8223&client=summon