Deep learning-based classification of production defects in automated-fiber-placement processes View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03-21

AUTHORS

Carsten Schmidt, Tristan Hocke, Berend Denkena

ABSTRACT

This paper presents a deep learning-based approach for the detection and classification of production defects that complements an existing thermographic online monitoring system for Automated-Fiber-Placement (AFP) processes. The detection and classification procedure is performed in two stages. In the first stage, the system monitors each tow individually and classifies its process status. Furthermore, it detects and classifies production defects that affect individual tows such as a tow-twist. In the second stage, the system monitors the total width of the faultless tows. In this stage, production defects effecting multiple tows, for example gaps or overlaps, are detected and classified. Twelve different deep convolution neural networks (CNN) with three various architectures are learned supervised relating to different data sets. The performance of both identification stages is explored separately before the entire system will be set up. Therefore, the thermal images of the data sets are superimposed by noise to test the performance of the selected CNN. More... »

PAGES

1-9

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11740-019-00893-4

DOI

http://dx.doi.org/10.1007/s11740-019-00893-4

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1112948521


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": "University of Hannover", 
          "id": "https://www.grid.ac/institutes/grid.9122.8", 
          "name": [
            "Institute of Production Engineering and Machine Tools, Leibniz Universit\u00e4t Hannover, Ottenbecker Damm 12, 21684, Stade, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Schmidt", 
        "givenName": "Carsten", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Hannover", 
          "id": "https://www.grid.ac/institutes/grid.9122.8", 
          "name": [
            "Institute of Production Engineering and Machine Tools, Leibniz Universit\u00e4t Hannover, Ottenbecker Damm 12, 21684, Stade, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hocke", 
        "givenName": "Tristan", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Hannover", 
          "id": "https://www.grid.ac/institutes/grid.9122.8", 
          "name": [
            "Institute of Production Engineering and Machine Tools, Leibniz Universit\u00e4t Hannover, Ottenbecker Damm 12, 21684, Stade, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Denkena", 
        "givenName": "Berend", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.procir.2014.01.138", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012367914"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.compositesb.2016.04.076", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014626694"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cirp.2016.04.072", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015362307"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.4271/2014-01-2272", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1072436050"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/is.2016.7737471", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093416129"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ijcnn.2012.6252468", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095683967"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.17265/2328-2223/2018.02.006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101485285"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11740-018-0821-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101674430", 
          "https://doi.org/10.1007/s11740-018-0821-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11740-018-0821-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101674430", 
          "https://doi.org/10.1007/s11740-018-0821-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11740-018-0821-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101674430", 
          "https://doi.org/10.1007/s11740-018-0821-4"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-03-21", 
    "datePublishedReg": "2019-03-21", 
    "description": "This paper presents a deep learning-based approach for the detection and classification of production defects that complements an existing thermographic online monitoring system for Automated-Fiber-Placement (AFP) processes. The detection and classification procedure is performed in two stages. In the first stage, the system monitors each tow individually and classifies its process status. Furthermore, it detects and classifies production defects that affect individual tows such as a tow-twist. In the second stage, the system monitors the total width of the faultless tows. In this stage, production defects effecting multiple tows, for example gaps or overlaps, are detected and classified. Twelve different deep convolution neural networks (CNN) with three various architectures are learned supervised relating to different data sets. The performance of both identification stages is explored separately before the entire system will be set up. Therefore, the thermal images of the data sets are superimposed by noise to test the performance of the selected CNN.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s11740-019-00893-4", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1136430", 
        "issn": [
          "0944-6524", 
          "1863-7353"
        ], 
        "name": "Production Engineering", 
        "type": "Periodical"
      }
    ], 
    "name": "Deep learning-based classification of production defects in automated-fiber-placement processes", 
    "pagination": "1-9", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "d13b742e545d16c30c150773a699a770af671a8819fdc53db6a91f9c7a55a446"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11740-019-00893-4"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1112948521"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11740-019-00893-4", 
      "https://app.dimensions.ai/details/publication/pub.1112948521"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T12:54", 
    "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/v90/0000000364_0000000364/records_72862_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs11740-019-00893-4"
  }
]
 

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/s11740-019-00893-4'

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/s11740-019-00893-4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11740-019-00893-4'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11740-019-00893-4'


 

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

91 TRIPLES      21 PREDICATES      32 URIs      16 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11740-019-00893-4 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N6506fcf84a944b1ca6181d5a3f278c97
4 schema:citation sg:pub.10.1007/s11740-018-0821-4
5 https://doi.org/10.1016/j.cirp.2016.04.072
6 https://doi.org/10.1016/j.compositesb.2016.04.076
7 https://doi.org/10.1016/j.procir.2014.01.138
8 https://doi.org/10.1109/ijcnn.2012.6252468
9 https://doi.org/10.1109/is.2016.7737471
10 https://doi.org/10.17265/2328-2223/2018.02.006
11 https://doi.org/10.4271/2014-01-2272
12 schema:datePublished 2019-03-21
13 schema:datePublishedReg 2019-03-21
14 schema:description This paper presents a deep learning-based approach for the detection and classification of production defects that complements an existing thermographic online monitoring system for Automated-Fiber-Placement (AFP) processes. The detection and classification procedure is performed in two stages. In the first stage, the system monitors each tow individually and classifies its process status. Furthermore, it detects and classifies production defects that affect individual tows such as a tow-twist. In the second stage, the system monitors the total width of the faultless tows. In this stage, production defects effecting multiple tows, for example gaps or overlaps, are detected and classified. Twelve different deep convolution neural networks (CNN) with three various architectures are learned supervised relating to different data sets. The performance of both identification stages is explored separately before the entire system will be set up. Therefore, the thermal images of the data sets are superimposed by noise to test the performance of the selected CNN.
15 schema:genre research_article
16 schema:inLanguage en
17 schema:isAccessibleForFree false
18 schema:isPartOf sg:journal.1136430
19 schema:name Deep learning-based classification of production defects in automated-fiber-placement processes
20 schema:pagination 1-9
21 schema:productId N2fe6f36430d845e9ac02a037102c1fea
22 N56d29d82bbf3436fb3595dc2ebb93bd0
23 Nd2597d3cec1a44f09884054360fd74a0
24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112948521
25 https://doi.org/10.1007/s11740-019-00893-4
26 schema:sdDatePublished 2019-04-11T12:54
27 schema:sdLicense https://scigraph.springernature.com/explorer/license/
28 schema:sdPublisher Nc971575cb0114fbeb6c3457708995e85
29 schema:url https://link.springer.com/10.1007%2Fs11740-019-00893-4
30 sgo:license sg:explorer/license/
31 sgo:sdDataset articles
32 rdf:type schema:ScholarlyArticle
33 N0f6628ca01b0444f997aee7a58283d8f schema:affiliation https://www.grid.ac/institutes/grid.9122.8
34 schema:familyName Schmidt
35 schema:givenName Carsten
36 rdf:type schema:Person
37 N2fe6f36430d845e9ac02a037102c1fea schema:name readcube_id
38 schema:value d13b742e545d16c30c150773a699a770af671a8819fdc53db6a91f9c7a55a446
39 rdf:type schema:PropertyValue
40 N38cdeb38b5084bc097339851132a1c66 schema:affiliation https://www.grid.ac/institutes/grid.9122.8
41 schema:familyName Denkena
42 schema:givenName Berend
43 rdf:type schema:Person
44 N527390c2a29444f29e2f03ca0b894dbb rdf:first Nc715939f215a4a4c885adc83d93f344e
45 rdf:rest Ndf84e51490bc4d67a50b8c0d8540b889
46 N56d29d82bbf3436fb3595dc2ebb93bd0 schema:name doi
47 schema:value 10.1007/s11740-019-00893-4
48 rdf:type schema:PropertyValue
49 N6506fcf84a944b1ca6181d5a3f278c97 rdf:first N0f6628ca01b0444f997aee7a58283d8f
50 rdf:rest N527390c2a29444f29e2f03ca0b894dbb
51 Nc715939f215a4a4c885adc83d93f344e schema:affiliation https://www.grid.ac/institutes/grid.9122.8
52 schema:familyName Hocke
53 schema:givenName Tristan
54 rdf:type schema:Person
55 Nc971575cb0114fbeb6c3457708995e85 schema:name Springer Nature - SN SciGraph project
56 rdf:type schema:Organization
57 Nd2597d3cec1a44f09884054360fd74a0 schema:name dimensions_id
58 schema:value pub.1112948521
59 rdf:type schema:PropertyValue
60 Ndf84e51490bc4d67a50b8c0d8540b889 rdf:first N38cdeb38b5084bc097339851132a1c66
61 rdf:rest rdf:nil
62 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
63 schema:name Information and Computing Sciences
64 rdf:type schema:DefinedTerm
65 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
66 schema:name Artificial Intelligence and Image Processing
67 rdf:type schema:DefinedTerm
68 sg:journal.1136430 schema:issn 0944-6524
69 1863-7353
70 schema:name Production Engineering
71 rdf:type schema:Periodical
72 sg:pub.10.1007/s11740-018-0821-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101674430
73 https://doi.org/10.1007/s11740-018-0821-4
74 rdf:type schema:CreativeWork
75 https://doi.org/10.1016/j.cirp.2016.04.072 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015362307
76 rdf:type schema:CreativeWork
77 https://doi.org/10.1016/j.compositesb.2016.04.076 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014626694
78 rdf:type schema:CreativeWork
79 https://doi.org/10.1016/j.procir.2014.01.138 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012367914
80 rdf:type schema:CreativeWork
81 https://doi.org/10.1109/ijcnn.2012.6252468 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095683967
82 rdf:type schema:CreativeWork
83 https://doi.org/10.1109/is.2016.7737471 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093416129
84 rdf:type schema:CreativeWork
85 https://doi.org/10.17265/2328-2223/2018.02.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101485285
86 rdf:type schema:CreativeWork
87 https://doi.org/10.4271/2014-01-2272 schema:sameAs https://app.dimensions.ai/details/publication/pub.1072436050
88 rdf:type schema:CreativeWork
89 https://www.grid.ac/institutes/grid.9122.8 schema:alternateName University of Hannover
90 schema:name Institute of Production Engineering and Machine Tools, Leibniz Universität Hannover, Ottenbecker Damm 12, 21684, Stade, Germany
91 rdf:type schema:Organization
 




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


...