Restricted Boltzmann machine and softmax regression for fault detection and classification View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-03

AUTHORS

Praveen Chopra, Sandeep Kumar Yadav

ABSTRACT

A unique technique is proposed based on restricted Boltzmann machine (RBM) and softmax regression for automated fault detection and classification using the acoustic signal generated from IC (Internal Combustion) engines. This technique uses RBM for unsupervised fault feature extraction from the frequency spectrum of the noisy acoustic signal. These extracted features are then used to reduce the dimensionality of the training and testing data vectors. These reduced dimensionality data vectors are used by softmax regression-based classifier for classification of the engine into faulty and healthy class. The proposed technique does not require any hand-engineered feature extraction, as usually done. This technique performs very well with a small number of training data. The overall performance of this technique for four different fault classes is more than 99% on the industrial IC engine data. In a typical case, with only 38 training data sets and 210 test data sets, the performance is 99.52%. More... »

PAGES

67-77

References to SciGraph publications

  • 1992-03. Multinomial logistic regression algorithm in ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS
  • 2015-12. Fault detection and classification by unsupervised feature extraction and dimensionality reduction in COMPLEX & INTELLIGENT SYSTEMS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s40747-017-0054-8

    DOI

    http://dx.doi.org/10.1007/s40747-017-0054-8

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1091052761


    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": "Defence Research and Development Organisation", 
              "id": "https://www.grid.ac/institutes/grid.418551.c", 
              "name": [
                "DRDO, Delhi, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chopra", 
            "givenName": "Praveen", 
            "id": "sg:person.011003267537.22", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011003267537.22"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Indian Institute of Technology Jodhpur", 
              "id": "https://www.grid.ac/institutes/grid.462385.e", 
              "name": [
                "Indian Institute of Technology Jodhpur, Rajasthan, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yadav", 
            "givenName": "Sandeep Kumar", 
            "id": "sg:person.012376230537.26", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012376230537.26"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1145/1273496.1273596", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003950612"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1126/science.1127647", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004607132"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/089976602760128018", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007443228"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00048682", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022236209", 
              "https://doi.org/10.1007/bf00048682"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00048682", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022236209", 
              "https://doi.org/10.1007/bf00048682"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s40747-015-0004-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033956032", 
              "https://doi.org/10.1007/s40747-015-0004-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.eswa.2008.03.008", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046075046"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1273496.1273592", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052861703"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tim.2010.2082750", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061638551"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2005.127", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742796"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icma.2015.7237857", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093856354"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ijcnn.1999.836202", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094212044"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2014.39", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095359197"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cisp.2014.7003829", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095433397"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ispa.2009.5297766", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1096204521"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-03", 
        "datePublishedReg": "2018-03-01", 
        "description": "A unique technique is proposed based on restricted Boltzmann machine (RBM) and softmax regression for automated fault detection and classification using the acoustic signal generated from IC (Internal Combustion) engines. This technique uses RBM for unsupervised fault feature extraction from the frequency spectrum of the noisy acoustic signal. These extracted features are then used to reduce the dimensionality of the training and testing data vectors. These reduced dimensionality data vectors are used by softmax regression-based classifier for classification of the engine into faulty and healthy class. The proposed technique does not require any hand-engineered feature extraction, as usually done. This technique performs very well with a small number of training data. The overall performance of this technique for four different fault classes is more than 99% on the industrial IC engine data. In a typical case, with only 38 training data sets and 210 test data sets, the performance is 99.52%.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s40747-017-0054-8", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1136144", 
            "issn": [
              "2199-4536", 
              "2198-6053"
            ], 
            "name": "Complex & Intelligent Systems", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "4"
          }
        ], 
        "name": "Restricted Boltzmann machine and softmax regression for fault detection and classification", 
        "pagination": "67-77", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "d4d1565428d05abcb7725548c5305f1deaa80072ffa17af1a1ed29f9b6b25733"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s40747-017-0054-8"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1091052761"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s40747-017-0054-8", 
          "https://app.dimensions.ai/details/publication/pub.1091052761"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T10:19", 
        "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/v90/0000000348_0000000348/records_54322_00000001.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs40747-017-0054-8"
      }
    ]
     

    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/s40747-017-0054-8'

    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/s40747-017-0054-8'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s40747-017-0054-8'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s40747-017-0054-8'


     

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

    115 TRIPLES      21 PREDICATES      41 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s40747-017-0054-8 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N7c7a1a9f7a0348bf8e667918b44caa68
    4 schema:citation sg:pub.10.1007/bf00048682
    5 sg:pub.10.1007/s40747-015-0004-2
    6 https://doi.org/10.1016/j.eswa.2008.03.008
    7 https://doi.org/10.1109/cisp.2014.7003829
    8 https://doi.org/10.1109/icma.2015.7237857
    9 https://doi.org/10.1109/icpr.2014.39
    10 https://doi.org/10.1109/ijcnn.1999.836202
    11 https://doi.org/10.1109/ispa.2009.5297766
    12 https://doi.org/10.1109/tim.2010.2082750
    13 https://doi.org/10.1109/tpami.2005.127
    14 https://doi.org/10.1126/science.1127647
    15 https://doi.org/10.1145/1273496.1273592
    16 https://doi.org/10.1145/1273496.1273596
    17 https://doi.org/10.1162/089976602760128018
    18 schema:datePublished 2018-03
    19 schema:datePublishedReg 2018-03-01
    20 schema:description A unique technique is proposed based on restricted Boltzmann machine (RBM) and softmax regression for automated fault detection and classification using the acoustic signal generated from IC (Internal Combustion) engines. This technique uses RBM for unsupervised fault feature extraction from the frequency spectrum of the noisy acoustic signal. These extracted features are then used to reduce the dimensionality of the training and testing data vectors. These reduced dimensionality data vectors are used by softmax regression-based classifier for classification of the engine into faulty and healthy class. The proposed technique does not require any hand-engineered feature extraction, as usually done. This technique performs very well with a small number of training data. The overall performance of this technique for four different fault classes is more than 99% on the industrial IC engine data. In a typical case, with only 38 training data sets and 210 test data sets, the performance is 99.52%.
    21 schema:genre research_article
    22 schema:inLanguage en
    23 schema:isAccessibleForFree true
    24 schema:isPartOf N3966da789c1b4e85b69a8e51e9a61b56
    25 N81a6329ca0594c0b894f0680d45844e1
    26 sg:journal.1136144
    27 schema:name Restricted Boltzmann machine and softmax regression for fault detection and classification
    28 schema:pagination 67-77
    29 schema:productId N38cc5b12db7647e8a985c2adcdf030a0
    30 N8efbb01f34354de8b0b5b18e5052da10
    31 Na14cc00ba59b40d6b0dd4600c72a5c0f
    32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091052761
    33 https://doi.org/10.1007/s40747-017-0054-8
    34 schema:sdDatePublished 2019-04-11T10:19
    35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    36 schema:sdPublisher Nb5b28d34f4bb46f688647da1285e0a7f
    37 schema:url https://link.springer.com/10.1007%2Fs40747-017-0054-8
    38 sgo:license sg:explorer/license/
    39 sgo:sdDataset articles
    40 rdf:type schema:ScholarlyArticle
    41 N17b615cd1d61432c86ca6aca07237806 rdf:first sg:person.012376230537.26
    42 rdf:rest rdf:nil
    43 N38cc5b12db7647e8a985c2adcdf030a0 schema:name readcube_id
    44 schema:value d4d1565428d05abcb7725548c5305f1deaa80072ffa17af1a1ed29f9b6b25733
    45 rdf:type schema:PropertyValue
    46 N3966da789c1b4e85b69a8e51e9a61b56 schema:issueNumber 1
    47 rdf:type schema:PublicationIssue
    48 N7c7a1a9f7a0348bf8e667918b44caa68 rdf:first sg:person.011003267537.22
    49 rdf:rest N17b615cd1d61432c86ca6aca07237806
    50 N81a6329ca0594c0b894f0680d45844e1 schema:volumeNumber 4
    51 rdf:type schema:PublicationVolume
    52 N8efbb01f34354de8b0b5b18e5052da10 schema:name dimensions_id
    53 schema:value pub.1091052761
    54 rdf:type schema:PropertyValue
    55 Na14cc00ba59b40d6b0dd4600c72a5c0f schema:name doi
    56 schema:value 10.1007/s40747-017-0054-8
    57 rdf:type schema:PropertyValue
    58 Nb5b28d34f4bb46f688647da1285e0a7f schema:name Springer Nature - SN SciGraph project
    59 rdf:type schema:Organization
    60 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    61 schema:name Information and Computing Sciences
    62 rdf:type schema:DefinedTerm
    63 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    64 schema:name Artificial Intelligence and Image Processing
    65 rdf:type schema:DefinedTerm
    66 sg:journal.1136144 schema:issn 2198-6053
    67 2199-4536
    68 schema:name Complex & Intelligent Systems
    69 rdf:type schema:Periodical
    70 sg:person.011003267537.22 schema:affiliation https://www.grid.ac/institutes/grid.418551.c
    71 schema:familyName Chopra
    72 schema:givenName Praveen
    73 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011003267537.22
    74 rdf:type schema:Person
    75 sg:person.012376230537.26 schema:affiliation https://www.grid.ac/institutes/grid.462385.e
    76 schema:familyName Yadav
    77 schema:givenName Sandeep Kumar
    78 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012376230537.26
    79 rdf:type schema:Person
    80 sg:pub.10.1007/bf00048682 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022236209
    81 https://doi.org/10.1007/bf00048682
    82 rdf:type schema:CreativeWork
    83 sg:pub.10.1007/s40747-015-0004-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033956032
    84 https://doi.org/10.1007/s40747-015-0004-2
    85 rdf:type schema:CreativeWork
    86 https://doi.org/10.1016/j.eswa.2008.03.008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046075046
    87 rdf:type schema:CreativeWork
    88 https://doi.org/10.1109/cisp.2014.7003829 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095433397
    89 rdf:type schema:CreativeWork
    90 https://doi.org/10.1109/icma.2015.7237857 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093856354
    91 rdf:type schema:CreativeWork
    92 https://doi.org/10.1109/icpr.2014.39 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095359197
    93 rdf:type schema:CreativeWork
    94 https://doi.org/10.1109/ijcnn.1999.836202 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094212044
    95 rdf:type schema:CreativeWork
    96 https://doi.org/10.1109/ispa.2009.5297766 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096204521
    97 rdf:type schema:CreativeWork
    98 https://doi.org/10.1109/tim.2010.2082750 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061638551
    99 rdf:type schema:CreativeWork
    100 https://doi.org/10.1109/tpami.2005.127 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742796
    101 rdf:type schema:CreativeWork
    102 https://doi.org/10.1126/science.1127647 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004607132
    103 rdf:type schema:CreativeWork
    104 https://doi.org/10.1145/1273496.1273592 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052861703
    105 rdf:type schema:CreativeWork
    106 https://doi.org/10.1145/1273496.1273596 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003950612
    107 rdf:type schema:CreativeWork
    108 https://doi.org/10.1162/089976602760128018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007443228
    109 rdf:type schema:CreativeWork
    110 https://www.grid.ac/institutes/grid.418551.c schema:alternateName Defence Research and Development Organisation
    111 schema:name DRDO, Delhi, India
    112 rdf:type schema:Organization
    113 https://www.grid.ac/institutes/grid.462385.e schema:alternateName Indian Institute of Technology Jodhpur
    114 schema:name Indian Institute of Technology Jodhpur, Rajasthan, India
    115 rdf:type schema:Organization
     




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


    ...