A comparison of feature ranking techniques for fault diagnosis of ball bearing View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2015-02-10

AUTHORS

V. Vakharia, V. K. Gupta, P. K. Kankar

ABSTRACT

In rotating machinery one of the prominent causes of malfunction is faults generated in ball bearings, therefore, diagnosis and interpretation of these faults is essential before they become severe. Feature extraction methodology has been presented in this paper based on application of lifting wavelet transform. Minimum permutation entropy is considered as decision making for selecting level of lifting wavelet transform. Sixteen features are calculated from measured vibration signals for various bearing conditions like defect in inner race, outer race, ball defect, combined defect and no defect condition. To achieve better fault identification accuracy selection of features carrying useful information is needed. To select highly distinguished features various ranking methodologies such as Fisher score, ReliefF, Wilcoxon rank, Gain ratio and Memetic feature selection are used. The ranked feature sets that are fed to machine learning algorithms support vector machine, learning vector quantization and artificial neural network for identification of bearing conditions. Tenfold cross-validation results show that selected features give enhanced accuracy for detecting faults. Features selected through Fisher score-support vector machine and ReliefF-artificial neural network gives 100 % cross-validation accuracy. Result shows that proposed methodology is feasible and effective for fault diagnosis of bearing with reduced feature set. More... »

PAGES

1601-1619

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00500-015-1608-6

DOI

http://dx.doi.org/10.1007/s00500-015-1608-6

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1039946743


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India", 
          "id": "http://www.grid.ac/institutes/grid.444467.1", 
          "name": [
            "Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Vakharia", 
        "givenName": "V.", 
        "id": "sg:person.016063016177.43", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016063016177.43"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India", 
          "id": "http://www.grid.ac/institutes/grid.444467.1", 
          "name": [
            "Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gupta", 
        "givenName": "V. K.", 
        "id": "sg:person.011615526211.26", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011615526211.26"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India", 
          "id": "http://www.grid.ac/institutes/grid.444467.1", 
          "name": [
            "Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kankar", 
        "givenName": "P. K.", 
        "id": "sg:person.011621346722.57", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011621346722.57"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s00500-005-0009-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005942954", 
          "https://doi.org/10.1007/s00500-005-0009-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-008-0331-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004146361", 
          "https://doi.org/10.1007/s00500-008-0331-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1025667309714", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005679960", 
          "https://doi.org/10.1023/a:1025667309714"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf02476026", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035406320", 
          "https://doi.org/10.1007/bf02476026"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-005-0481-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044396612", 
          "https://doi.org/10.1007/s00500-005-0481-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2105-7-320", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1011761722", 
          "https://doi.org/10.1186/1471-2105-7-320"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-013-1055-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008229602", 
          "https://doi.org/10.1007/s00500-013-1055-1"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2015-02-10", 
    "datePublishedReg": "2015-02-10", 
    "description": "In rotating machinery one of the prominent causes of malfunction is faults generated in ball bearings, therefore, diagnosis and interpretation of these faults is essential before they become severe. Feature extraction methodology has been presented in this paper based on application of lifting wavelet transform. Minimum permutation entropy is considered as decision making for selecting level of lifting wavelet transform. Sixteen features are calculated from measured vibration signals for various bearing conditions like defect in inner race, outer race, ball defect, combined defect and no defect condition. To achieve better fault identification accuracy selection of features carrying useful information is needed. To select highly distinguished features various ranking methodologies such as Fisher score, ReliefF, Wilcoxon rank, Gain ratio and Memetic feature selection are used. The ranked feature sets that are fed to machine learning algorithms support vector machine, learning vector quantization and artificial neural network for identification of bearing conditions. Tenfold cross-validation results show that selected features give enhanced accuracy for detecting faults. Features selected through Fisher score-support vector machine and ReliefF-artificial neural network gives 100\u00a0% cross-validation accuracy. Result shows that proposed methodology is feasible and effective for fault diagnosis of bearing with reduced feature set.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s00500-015-1608-6", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1050238", 
        "issn": [
          "1432-7643", 
          "1433-7479"
        ], 
        "name": "Soft Computing", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "20"
      }
    ], 
    "keywords": [
      "neural network", 
      "vector machine", 
      "wavelet transform", 
      "feature ranking techniques", 
      "feature extraction methodology", 
      "fault diagnosis", 
      "tenfold cross-validation results", 
      "artificial neural network", 
      "ball bearings", 
      "cross-validation accuracy", 
      "minimum permutation entropy", 
      "feature sets", 
      "reduced features", 
      "feature selection", 
      "vector quantization", 
      "ranking techniques", 
      "cross-validation results", 
      "Fisher score", 
      "vibration signals", 
      "outer race", 
      "inner race", 
      "ball defect", 
      "bearing conditions", 
      "distinguished features", 
      "defect conditions", 
      "machine", 
      "network", 
      "extraction methodology", 
      "useful information", 
      "ranking methodology", 
      "accuracy", 
      "faults", 
      "features", 
      "methodology", 
      "algorithm", 
      "bearing", 
      "permutation entropy", 
      "transform", 
      "quantization", 
      "selection", 
      "information", 
      "set", 
      "conditions", 
      "applications", 
      "decisions", 
      "defects", 
      "technique", 
      "signals", 
      "results", 
      "malfunction", 
      "entropy", 
      "ratio", 
      "one", 
      "rank", 
      "identification", 
      "comparison", 
      "interpretation", 
      "prominent cause", 
      "diagnosis", 
      "levels", 
      "scores", 
      "Wilcoxon rank", 
      "cause", 
      "race", 
      "paper"
    ], 
    "name": "A comparison of feature ranking techniques for fault diagnosis of ball bearing", 
    "pagination": "1601-1619", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1039946743"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00500-015-1608-6"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00500-015-1608-6", 
      "https://app.dimensions.ai/details/publication/pub.1039946743"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-06-01T22:15", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220601/entities/gbq_results/article/article_674.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s00500-015-1608-6"
  }
]
 

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/s00500-015-1608-6'

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/s00500-015-1608-6'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00500-015-1608-6'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00500-015-1608-6'


 

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

165 TRIPLES      22 PREDICATES      97 URIs      82 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00500-015-1608-6 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N3416c166706a41c080ac2de41dd55916
4 schema:citation sg:pub.10.1007/bf02476026
5 sg:pub.10.1007/s00500-005-0009-7
6 sg:pub.10.1007/s00500-005-0481-0
7 sg:pub.10.1007/s00500-008-0331-y
8 sg:pub.10.1007/s00500-013-1055-1
9 sg:pub.10.1023/a:1025667309714
10 sg:pub.10.1186/1471-2105-7-320
11 schema:datePublished 2015-02-10
12 schema:datePublishedReg 2015-02-10
13 schema:description In rotating machinery one of the prominent causes of malfunction is faults generated in ball bearings, therefore, diagnosis and interpretation of these faults is essential before they become severe. Feature extraction methodology has been presented in this paper based on application of lifting wavelet transform. Minimum permutation entropy is considered as decision making for selecting level of lifting wavelet transform. Sixteen features are calculated from measured vibration signals for various bearing conditions like defect in inner race, outer race, ball defect, combined defect and no defect condition. To achieve better fault identification accuracy selection of features carrying useful information is needed. To select highly distinguished features various ranking methodologies such as Fisher score, ReliefF, Wilcoxon rank, Gain ratio and Memetic feature selection are used. The ranked feature sets that are fed to machine learning algorithms support vector machine, learning vector quantization and artificial neural network for identification of bearing conditions. Tenfold cross-validation results show that selected features give enhanced accuracy for detecting faults. Features selected through Fisher score-support vector machine and ReliefF-artificial neural network gives 100 % cross-validation accuracy. Result shows that proposed methodology is feasible and effective for fault diagnosis of bearing with reduced feature set.
14 schema:genre article
15 schema:inLanguage en
16 schema:isAccessibleForFree false
17 schema:isPartOf N7b8ce656eff3484d9ca9a3bb87ca7a68
18 Nb16d4ea313524d408685d8fcc1bb1c0d
19 sg:journal.1050238
20 schema:keywords Fisher score
21 Wilcoxon rank
22 accuracy
23 algorithm
24 applications
25 artificial neural network
26 ball bearings
27 ball defect
28 bearing
29 bearing conditions
30 cause
31 comparison
32 conditions
33 cross-validation accuracy
34 cross-validation results
35 decisions
36 defect conditions
37 defects
38 diagnosis
39 distinguished features
40 entropy
41 extraction methodology
42 fault diagnosis
43 faults
44 feature extraction methodology
45 feature ranking techniques
46 feature selection
47 feature sets
48 features
49 identification
50 information
51 inner race
52 interpretation
53 levels
54 machine
55 malfunction
56 methodology
57 minimum permutation entropy
58 network
59 neural network
60 one
61 outer race
62 paper
63 permutation entropy
64 prominent cause
65 quantization
66 race
67 rank
68 ranking methodology
69 ranking techniques
70 ratio
71 reduced features
72 results
73 scores
74 selection
75 set
76 signals
77 technique
78 tenfold cross-validation results
79 transform
80 useful information
81 vector machine
82 vector quantization
83 vibration signals
84 wavelet transform
85 schema:name A comparison of feature ranking techniques for fault diagnosis of ball bearing
86 schema:pagination 1601-1619
87 schema:productId Nc5babe3119b543559db360b9b3a596ae
88 Ne25100cef64a47b58b4d8c69aeccee80
89 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039946743
90 https://doi.org/10.1007/s00500-015-1608-6
91 schema:sdDatePublished 2022-06-01T22:15
92 schema:sdLicense https://scigraph.springernature.com/explorer/license/
93 schema:sdPublisher N5f561ece3d0a4617a962dcd4fdf8c30e
94 schema:url https://doi.org/10.1007/s00500-015-1608-6
95 sgo:license sg:explorer/license/
96 sgo:sdDataset articles
97 rdf:type schema:ScholarlyArticle
98 N3416c166706a41c080ac2de41dd55916 rdf:first sg:person.016063016177.43
99 rdf:rest N7a441a7b703948218876f3862edb84f8
100 N5f561ece3d0a4617a962dcd4fdf8c30e schema:name Springer Nature - SN SciGraph project
101 rdf:type schema:Organization
102 N7a441a7b703948218876f3862edb84f8 rdf:first sg:person.011615526211.26
103 rdf:rest N7e62c0e3abcf4ef4963bbb663e2b340f
104 N7b8ce656eff3484d9ca9a3bb87ca7a68 schema:volumeNumber 20
105 rdf:type schema:PublicationVolume
106 N7e62c0e3abcf4ef4963bbb663e2b340f rdf:first sg:person.011621346722.57
107 rdf:rest rdf:nil
108 Nb16d4ea313524d408685d8fcc1bb1c0d schema:issueNumber 4
109 rdf:type schema:PublicationIssue
110 Nc5babe3119b543559db360b9b3a596ae schema:name dimensions_id
111 schema:value pub.1039946743
112 rdf:type schema:PropertyValue
113 Ne25100cef64a47b58b4d8c69aeccee80 schema:name doi
114 schema:value 10.1007/s00500-015-1608-6
115 rdf:type schema:PropertyValue
116 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
117 schema:name Information and Computing Sciences
118 rdf:type schema:DefinedTerm
119 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
120 schema:name Artificial Intelligence and Image Processing
121 rdf:type schema:DefinedTerm
122 sg:journal.1050238 schema:issn 1432-7643
123 1433-7479
124 schema:name Soft Computing
125 schema:publisher Springer Nature
126 rdf:type schema:Periodical
127 sg:person.011615526211.26 schema:affiliation grid-institutes:grid.444467.1
128 schema:familyName Gupta
129 schema:givenName V. K.
130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011615526211.26
131 rdf:type schema:Person
132 sg:person.011621346722.57 schema:affiliation grid-institutes:grid.444467.1
133 schema:familyName Kankar
134 schema:givenName P. K.
135 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011621346722.57
136 rdf:type schema:Person
137 sg:person.016063016177.43 schema:affiliation grid-institutes:grid.444467.1
138 schema:familyName Vakharia
139 schema:givenName V.
140 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016063016177.43
141 rdf:type schema:Person
142 sg:pub.10.1007/bf02476026 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035406320
143 https://doi.org/10.1007/bf02476026
144 rdf:type schema:CreativeWork
145 sg:pub.10.1007/s00500-005-0009-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005942954
146 https://doi.org/10.1007/s00500-005-0009-7
147 rdf:type schema:CreativeWork
148 sg:pub.10.1007/s00500-005-0481-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044396612
149 https://doi.org/10.1007/s00500-005-0481-0
150 rdf:type schema:CreativeWork
151 sg:pub.10.1007/s00500-008-0331-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1004146361
152 https://doi.org/10.1007/s00500-008-0331-y
153 rdf:type schema:CreativeWork
154 sg:pub.10.1007/s00500-013-1055-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008229602
155 https://doi.org/10.1007/s00500-013-1055-1
156 rdf:type schema:CreativeWork
157 sg:pub.10.1023/a:1025667309714 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005679960
158 https://doi.org/10.1023/a:1025667309714
159 rdf:type schema:CreativeWork
160 sg:pub.10.1186/1471-2105-7-320 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011761722
161 https://doi.org/10.1186/1471-2105-7-320
162 rdf:type schema:CreativeWork
163 grid-institutes:grid.444467.1 schema:alternateName Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India
164 schema:name Mechanical Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, 482005, Jabalpur, India
165 rdf:type schema:Organization
 




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


...