Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2018-07

AUTHORS

Nauman Munir, Hak-Joon Kim, Sung-Jin Song, Sung-Sik Kang

ABSTRACT

Ultrasonic signal classification of defects in weldment, in automatic fashion, is an active area of research and many pattern recognition approaches have been developed to classify ultrasonic signals correctly. However, most of the developed algorithms depend on some statistical or signal processing techniques to extract the suitable features for them. In this work, data driven approaches are used to train the neural network for defect classification without extracting any feature from ultrasonic signals. Firstly, the performance of single hidden layer neural network was evaluated as almost all the prior works have applied it for classification then its performance was compared with deep neural network with drop out regularization. The results demonstrate that given deep neural network architecture is more robust and the network can classify defects with high accuracy without extracting any feature from ultrasonic signals. More... »

PAGES

3073-3080

References to SciGraph publications

  • 1992-06. Ultrasonic flaw classification in weldments using probabilistic neural networks in JOURNAL OF NONDESTRUCTIVE EVALUATION
  • 2015-05. Deep learning in NATURE
  • 2011-03. Automatic Defect Classification in Ultrasonic NDT Using Artificial Intelligence in JOURNAL OF NONDESTRUCTIVE EVALUATION
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s12206-018-0610-1

    DOI

    http://dx.doi.org/10.1007/s12206-018-0610-1

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1105681502


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Sungkyunkwan University", 
              "id": "https://www.grid.ac/institutes/grid.264381.a", 
              "name": [
                "Department of Mechanical Engineering, Sungkyunkwan University, 16419, Suwon, Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Munir", 
            "givenName": "Nauman", 
            "id": "sg:person.011015503754.10", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015503754.10"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Sungkyunkwan University", 
              "id": "https://www.grid.ac/institutes/grid.264381.a", 
              "name": [
                "Department of Mechanical Engineering, Sungkyunkwan University, 16419, Suwon, Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kim", 
            "givenName": "Hak-Joon", 
            "id": "sg:person.01247741307.92", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01247741307.92"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Sungkyunkwan University", 
              "id": "https://www.grid.ac/institutes/grid.264381.a", 
              "name": [
                "Department of Mechanical Engineering, Sungkyunkwan University, 16419, Suwon, Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Song", 
            "givenName": "Sung-Jin", 
            "id": "sg:person.013311573076.90", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013311573076.90"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Korea Institute of Nuclear Safety", 
              "id": "https://www.grid.ac/institutes/grid.464612.3", 
              "name": [
                "Korea Institute of Nuclear Safety, 34142, Daejeon, Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kang", 
            "givenName": "Sung-Sik", 
            "id": "sg:person.010267441273.38", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010267441273.38"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.ultras.2016.08.017", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003065562"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14539", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010020120", 
              "https://doi.org/10.1038/nature14539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0029-5493(01)00495-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012746253"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neunet.2014.09.003", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013219854"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10921-010-0086-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017093228", 
              "https://doi.org/10.1007/s10921-010-0086-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0963-8695(95)00053-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018033578"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0263-2241(98)00075-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022944587"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0963-8695(02)00041-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023976414"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0963-8695(02)00041-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023976414"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ndteint.2015.12.001", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035767083"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00568290", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050478318", 
              "https://doi.org/10.1007/bf00568290"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00568290", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050478318", 
              "https://doi.org/10.1007/bf00568290"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ias.2005.1518382", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094965077"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-07", 
        "datePublishedReg": "2018-07-01", 
        "description": "Ultrasonic signal classification of defects in weldment, in automatic fashion, is an active area of research and many pattern recognition approaches have been developed to classify ultrasonic signals correctly. However, most of the developed algorithms depend on some statistical or signal processing techniques to extract the suitable features for them. In this work, data driven approaches are used to train the neural network for defect classification without extracting any feature from ultrasonic signals. Firstly, the performance of single hidden layer neural network was evaluated as almost all the prior works have applied it for classification then its performance was compared with deep neural network with drop out regularization. The results demonstrate that given deep neural network architecture is more robust and the network can classify defects with high accuracy without extracting any feature from ultrasonic signals.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s12206-018-0610-1", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1295111", 
            "issn": [
              "1011-8861", 
              "1226-4865"
            ], 
            "name": "Journal of Mechanical Science and Technology", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "7", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "32"
          }
        ], 
        "name": "Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments", 
        "pagination": "3073-3080", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "6b302140c54d135469c00401093aca16946304d3699e93231e7d70f2ae22b222"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s12206-018-0610-1"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1105681502"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s12206-018-0610-1", 
          "https://app.dimensions.ai/details/publication/pub.1105681502"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T09:54", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000347_0000000347/records_89798_00000003.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs12206-018-0610-1"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s12206-018-0610-1'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s12206-018-0610-1'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12206-018-0610-1'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12206-018-0610-1'


     

    This table displays all metadata directly associated to this object as RDF triples.

    121 TRIPLES      21 PREDICATES      38 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s12206-018-0610-1 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nb1e55813ffb342f9ba7831a583a546c1
    4 schema:citation sg:pub.10.1007/bf00568290
    5 sg:pub.10.1007/s10921-010-0086-0
    6 sg:pub.10.1038/nature14539
    7 https://doi.org/10.1016/0963-8695(95)00053-4
    8 https://doi.org/10.1016/j.ndteint.2015.12.001
    9 https://doi.org/10.1016/j.neunet.2014.09.003
    10 https://doi.org/10.1016/j.ultras.2016.08.017
    11 https://doi.org/10.1016/s0029-5493(01)00495-2
    12 https://doi.org/10.1016/s0263-2241(98)00075-x
    13 https://doi.org/10.1016/s0963-8695(02)00041-5
    14 https://doi.org/10.1109/ias.2005.1518382
    15 schema:datePublished 2018-07
    16 schema:datePublishedReg 2018-07-01
    17 schema:description Ultrasonic signal classification of defects in weldment, in automatic fashion, is an active area of research and many pattern recognition approaches have been developed to classify ultrasonic signals correctly. However, most of the developed algorithms depend on some statistical or signal processing techniques to extract the suitable features for them. In this work, data driven approaches are used to train the neural network for defect classification without extracting any feature from ultrasonic signals. Firstly, the performance of single hidden layer neural network was evaluated as almost all the prior works have applied it for classification then its performance was compared with deep neural network with drop out regularization. The results demonstrate that given deep neural network architecture is more robust and the network can classify defects with high accuracy without extracting any feature from ultrasonic signals.
    18 schema:genre research_article
    19 schema:inLanguage en
    20 schema:isAccessibleForFree false
    21 schema:isPartOf N53d81cc03741454eafb99a03e9d23971
    22 Nc34571c2f3a2439b8f7898868255fc17
    23 sg:journal.1295111
    24 schema:name Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments
    25 schema:pagination 3073-3080
    26 schema:productId N77ea9931fdd9427c87231e22956d60e4
    27 N93d8ade958d2498b95cb5b06e18d7417
    28 Nfdab575f73b248388b1c8be1efc8997b
    29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105681502
    30 https://doi.org/10.1007/s12206-018-0610-1
    31 schema:sdDatePublished 2019-04-11T09:54
    32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    33 schema:sdPublisher Nb57f04517a67406aa474b4e413afb614
    34 schema:url https://link.springer.com/10.1007%2Fs12206-018-0610-1
    35 sgo:license sg:explorer/license/
    36 sgo:sdDataset articles
    37 rdf:type schema:ScholarlyArticle
    38 N1a7d0a0bc0ff44ed8bc5d6f74aba1128 rdf:first sg:person.01247741307.92
    39 rdf:rest N5271ca719c374ad5b7c60efd1cea3b74
    40 N45d756b4c866452b955842b64066ebcc rdf:first sg:person.010267441273.38
    41 rdf:rest rdf:nil
    42 N5271ca719c374ad5b7c60efd1cea3b74 rdf:first sg:person.013311573076.90
    43 rdf:rest N45d756b4c866452b955842b64066ebcc
    44 N53d81cc03741454eafb99a03e9d23971 schema:issueNumber 7
    45 rdf:type schema:PublicationIssue
    46 N77ea9931fdd9427c87231e22956d60e4 schema:name doi
    47 schema:value 10.1007/s12206-018-0610-1
    48 rdf:type schema:PropertyValue
    49 N93d8ade958d2498b95cb5b06e18d7417 schema:name dimensions_id
    50 schema:value pub.1105681502
    51 rdf:type schema:PropertyValue
    52 Nb1e55813ffb342f9ba7831a583a546c1 rdf:first sg:person.011015503754.10
    53 rdf:rest N1a7d0a0bc0ff44ed8bc5d6f74aba1128
    54 Nb57f04517a67406aa474b4e413afb614 schema:name Springer Nature - SN SciGraph project
    55 rdf:type schema:Organization
    56 Nc34571c2f3a2439b8f7898868255fc17 schema:volumeNumber 32
    57 rdf:type schema:PublicationVolume
    58 Nfdab575f73b248388b1c8be1efc8997b schema:name readcube_id
    59 schema:value 6b302140c54d135469c00401093aca16946304d3699e93231e7d70f2ae22b222
    60 rdf:type schema:PropertyValue
    61 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    62 schema:name Information and Computing Sciences
    63 rdf:type schema:DefinedTerm
    64 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    65 schema:name Artificial Intelligence and Image Processing
    66 rdf:type schema:DefinedTerm
    67 sg:journal.1295111 schema:issn 1011-8861
    68 1226-4865
    69 schema:name Journal of Mechanical Science and Technology
    70 rdf:type schema:Periodical
    71 sg:person.010267441273.38 schema:affiliation https://www.grid.ac/institutes/grid.464612.3
    72 schema:familyName Kang
    73 schema:givenName Sung-Sik
    74 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010267441273.38
    75 rdf:type schema:Person
    76 sg:person.011015503754.10 schema:affiliation https://www.grid.ac/institutes/grid.264381.a
    77 schema:familyName Munir
    78 schema:givenName Nauman
    79 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015503754.10
    80 rdf:type schema:Person
    81 sg:person.01247741307.92 schema:affiliation https://www.grid.ac/institutes/grid.264381.a
    82 schema:familyName Kim
    83 schema:givenName Hak-Joon
    84 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01247741307.92
    85 rdf:type schema:Person
    86 sg:person.013311573076.90 schema:affiliation https://www.grid.ac/institutes/grid.264381.a
    87 schema:familyName Song
    88 schema:givenName Sung-Jin
    89 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013311573076.90
    90 rdf:type schema:Person
    91 sg:pub.10.1007/bf00568290 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050478318
    92 https://doi.org/10.1007/bf00568290
    93 rdf:type schema:CreativeWork
    94 sg:pub.10.1007/s10921-010-0086-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017093228
    95 https://doi.org/10.1007/s10921-010-0086-0
    96 rdf:type schema:CreativeWork
    97 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
    98 https://doi.org/10.1038/nature14539
    99 rdf:type schema:CreativeWork
    100 https://doi.org/10.1016/0963-8695(95)00053-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018033578
    101 rdf:type schema:CreativeWork
    102 https://doi.org/10.1016/j.ndteint.2015.12.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035767083
    103 rdf:type schema:CreativeWork
    104 https://doi.org/10.1016/j.neunet.2014.09.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013219854
    105 rdf:type schema:CreativeWork
    106 https://doi.org/10.1016/j.ultras.2016.08.017 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003065562
    107 rdf:type schema:CreativeWork
    108 https://doi.org/10.1016/s0029-5493(01)00495-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012746253
    109 rdf:type schema:CreativeWork
    110 https://doi.org/10.1016/s0263-2241(98)00075-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1022944587
    111 rdf:type schema:CreativeWork
    112 https://doi.org/10.1016/s0963-8695(02)00041-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023976414
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1109/ias.2005.1518382 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094965077
    115 rdf:type schema:CreativeWork
    116 https://www.grid.ac/institutes/grid.264381.a schema:alternateName Sungkyunkwan University
    117 schema:name Department of Mechanical Engineering, Sungkyunkwan University, 16419, Suwon, Korea
    118 rdf:type schema:Organization
    119 https://www.grid.ac/institutes/grid.464612.3 schema:alternateName Korea Institute of Nuclear Safety
    120 schema:name Korea Institute of Nuclear Safety, 34142, Daejeon, Korea
    121 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...