Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree

Maintenance planning and control should prioritize predictive techniques (e.g., vibration analysis on critical components such as belt conveyors and idlers) for addressing the low reliability of bulk transportation systems. The extensive length of the belt conveyor hampers manual inspections and mac...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of advanced manufacturing technology 2024-06, Vol.132 (7-8), p.3479-3488
Hauptverfasser: Soares, João L. L., Costa, Thiago B., Moura, Lis S., Sousa, Walter S., Mesquita, Alexandre L. A., Mesquita, André L. A., de Figueiredo, Jullyane M. S., Braga, Danilo S.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 3488
container_issue 7-8
container_start_page 3479
container_title International journal of advanced manufacturing technology
container_volume 132
creator Soares, João L. L.
Costa, Thiago B.
Moura, Lis S.
Sousa, Walter S.
Mesquita, Alexandre L. A.
Mesquita, André L. A.
de Figueiredo, Jullyane M. S.
Braga, Danilo S.
description Maintenance planning and control should prioritize predictive techniques (e.g., vibration analysis on critical components such as belt conveyors and idlers) for addressing the low reliability of bulk transportation systems. The extensive length of the belt conveyor hampers manual inspections and machine learning based on vibration measurements becomes an effective method for fault diagnosis. Models that classify faults, such as Gradient Boosting Decision Tree (GBDT), offer flexible algorithms that optimize decision tree classification through gradient-based techniques for minimizing predictive function errors. However, in case of non-stationary and nonlinear vibration signals, traditional techniques like Fourier Transform can hinder vibration analysis. Methods such as Wavelet Packet Decomposition (WPD) have emerged as an alternative to improve defect detection by extracting energy from signal frequency bands. This paper proposes a combination of WPD and GBDT for feature extraction and classification, respectively, for diagnosing two different failure modes in laboratory belt conveyor idlers, namely, bearing faults and surface wear. GBDT hyperparameters were well-fitted from 21 boosting stages, corroborating the high flexibility of the classification algorithm applied for less robust datasets. Furthermore, GBDT models achieved diagnosis accuracies of 100% for bearing defects and 97.5% for surface wear, showing the effectiveness of the combination for fault identification.
doi_str_mv 10.1007/s00170-024-13549-0
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3053367408</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3053367408</sourcerecordid><originalsourceid>FETCH-LOGICAL-c270t-425037a66bb8dc4cf66f45da5fb3c66deeddc3172c3f216622e536a4f6dd6e1d3</originalsourceid><addsrcrecordid>eNp9kE1LAzEQhoMoWKt_wFPAczRfO7sepVgVCnrQc8gmkyWlbmqyFfrvjVbw5mlg5nnfgYeQS8GvBeftTeFctJxxqZlQjb5l_IjMhFaKKS6aYzLjEjqmWuhOyVkp64qDgG5GXpZ2t5moj3YYU4mFpkB7rBuXxk_cp0yj32AutLcFPU0jHbL1EceJ9imVKY4D9ehiifU0ZcRzchLspuDF75yTt-X96-KRrZ4fnhZ3K-ZkyyemZcNVawH6vvNOuwAQdONtE3rlADyi906JVjoVpACQEhsFVgfwHlB4NSdXh95tTh87LJNZp10e60ujeKMUtJp3lZIHyuVUSsZgtjm-27w3gptvc-ZgzlRz5sec4TWkDqFS4XHA_Ff9T-oLl4txqA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3053367408</pqid></control><display><type>article</type><title>Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree</title><source>Springer Nature - Complete Springer Journals</source><creator>Soares, João L. L. ; Costa, Thiago B. ; Moura, Lis S. ; Sousa, Walter S. ; Mesquita, Alexandre L. A. ; Mesquita, André L. A. ; de Figueiredo, Jullyane M. S. ; Braga, Danilo S.</creator><creatorcontrib>Soares, João L. L. ; Costa, Thiago B. ; Moura, Lis S. ; Sousa, Walter S. ; Mesquita, Alexandre L. A. ; Mesquita, André L. A. ; de Figueiredo, Jullyane M. S. ; Braga, Danilo S.</creatorcontrib><description>Maintenance planning and control should prioritize predictive techniques (e.g., vibration analysis on critical components such as belt conveyors and idlers) for addressing the low reliability of bulk transportation systems. The extensive length of the belt conveyor hampers manual inspections and machine learning based on vibration measurements becomes an effective method for fault diagnosis. Models that classify faults, such as Gradient Boosting Decision Tree (GBDT), offer flexible algorithms that optimize decision tree classification through gradient-based techniques for minimizing predictive function errors. However, in case of non-stationary and nonlinear vibration signals, traditional techniques like Fourier Transform can hinder vibration analysis. Methods such as Wavelet Packet Decomposition (WPD) have emerged as an alternative to improve defect detection by extracting energy from signal frequency bands. This paper proposes a combination of WPD and GBDT for feature extraction and classification, respectively, for diagnosing two different failure modes in laboratory belt conveyor idlers, namely, bearing faults and surface wear. GBDT hyperparameters were well-fitted from 21 boosting stages, corroborating the high flexibility of the classification algorithm applied for less robust datasets. Furthermore, GBDT models achieved diagnosis accuracies of 100% for bearing defects and 97.5% for surface wear, showing the effectiveness of the combination for fault identification.</description><identifier>ISSN: 0268-3768</identifier><identifier>EISSN: 1433-3015</identifier><identifier>DOI: 10.1007/s00170-024-13549-0</identifier><language>eng</language><publisher>London: Springer London</publisher><subject>Algorithms ; Belt conveyors ; CAE) and Design ; Component reliability ; Computer-Aided Engineering (CAD ; Critical components ; Decision trees ; Defects ; Effectiveness ; Engineering ; Failure modes ; Fault detection ; Fault diagnosis ; Feature extraction ; Fourier transforms ; Frequencies ; Idlers ; Industrial and Production Engineering ; Machine learning ; Mechanical Engineering ; Media Management ; Original Article ; Predictive control ; Predictive maintenance ; Signal classification ; System reliability ; Transportation systems ; Vibration analysis ; Vibration measurement ; Wavelet analysis ; Wavelet transforms</subject><ispartof>International journal of advanced manufacturing technology, 2024-06, Vol.132 (7-8), p.3479-3488</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c270t-425037a66bb8dc4cf66f45da5fb3c66deeddc3172c3f216622e536a4f6dd6e1d3</cites><orcidid>0000-0001-5605-8381 ; 0000-0001-5559-5580 ; 0000-0003-0260-6770 ; 0009-0006-6964-7242 ; 0000-0002-8092-1525 ; 0009-0003-0461-3664 ; 0009-0001-4326-5151 ; 0009-0005-9631-1552</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00170-024-13549-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00170-024-13549-0$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Soares, João L. L.</creatorcontrib><creatorcontrib>Costa, Thiago B.</creatorcontrib><creatorcontrib>Moura, Lis S.</creatorcontrib><creatorcontrib>Sousa, Walter S.</creatorcontrib><creatorcontrib>Mesquita, Alexandre L. A.</creatorcontrib><creatorcontrib>Mesquita, André L. A.</creatorcontrib><creatorcontrib>de Figueiredo, Jullyane M. S.</creatorcontrib><creatorcontrib>Braga, Danilo S.</creatorcontrib><title>Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree</title><title>International journal of advanced manufacturing technology</title><addtitle>Int J Adv Manuf Technol</addtitle><description>Maintenance planning and control should prioritize predictive techniques (e.g., vibration analysis on critical components such as belt conveyors and idlers) for addressing the low reliability of bulk transportation systems. The extensive length of the belt conveyor hampers manual inspections and machine learning based on vibration measurements becomes an effective method for fault diagnosis. Models that classify faults, such as Gradient Boosting Decision Tree (GBDT), offer flexible algorithms that optimize decision tree classification through gradient-based techniques for minimizing predictive function errors. However, in case of non-stationary and nonlinear vibration signals, traditional techniques like Fourier Transform can hinder vibration analysis. Methods such as Wavelet Packet Decomposition (WPD) have emerged as an alternative to improve defect detection by extracting energy from signal frequency bands. This paper proposes a combination of WPD and GBDT for feature extraction and classification, respectively, for diagnosing two different failure modes in laboratory belt conveyor idlers, namely, bearing faults and surface wear. GBDT hyperparameters were well-fitted from 21 boosting stages, corroborating the high flexibility of the classification algorithm applied for less robust datasets. Furthermore, GBDT models achieved diagnosis accuracies of 100% for bearing defects and 97.5% for surface wear, showing the effectiveness of the combination for fault identification.</description><subject>Algorithms</subject><subject>Belt conveyors</subject><subject>CAE) and Design</subject><subject>Component reliability</subject><subject>Computer-Aided Engineering (CAD</subject><subject>Critical components</subject><subject>Decision trees</subject><subject>Defects</subject><subject>Effectiveness</subject><subject>Engineering</subject><subject>Failure modes</subject><subject>Fault detection</subject><subject>Fault diagnosis</subject><subject>Feature extraction</subject><subject>Fourier transforms</subject><subject>Frequencies</subject><subject>Idlers</subject><subject>Industrial and Production Engineering</subject><subject>Machine learning</subject><subject>Mechanical Engineering</subject><subject>Media Management</subject><subject>Original Article</subject><subject>Predictive control</subject><subject>Predictive maintenance</subject><subject>Signal classification</subject><subject>System reliability</subject><subject>Transportation systems</subject><subject>Vibration analysis</subject><subject>Vibration measurement</subject><subject>Wavelet analysis</subject><subject>Wavelet transforms</subject><issn>0268-3768</issn><issn>1433-3015</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE1LAzEQhoMoWKt_wFPAczRfO7sepVgVCnrQc8gmkyWlbmqyFfrvjVbw5mlg5nnfgYeQS8GvBeftTeFctJxxqZlQjb5l_IjMhFaKKS6aYzLjEjqmWuhOyVkp64qDgG5GXpZ2t5moj3YYU4mFpkB7rBuXxk_cp0yj32AutLcFPU0jHbL1EceJ9imVKY4D9ehiifU0ZcRzchLspuDF75yTt-X96-KRrZ4fnhZ3K-ZkyyemZcNVawH6vvNOuwAQdONtE3rlADyi906JVjoVpACQEhsFVgfwHlB4NSdXh95tTh87LJNZp10e60ujeKMUtJp3lZIHyuVUSsZgtjm-27w3gptvc-ZgzlRz5sec4TWkDqFS4XHA_Ff9T-oLl4txqA</recordid><startdate>20240601</startdate><enddate>20240601</enddate><creator>Soares, João L. L.</creator><creator>Costa, Thiago B.</creator><creator>Moura, Lis S.</creator><creator>Sousa, Walter S.</creator><creator>Mesquita, Alexandre L. A.</creator><creator>Mesquita, André L. A.</creator><creator>de Figueiredo, Jullyane M. S.</creator><creator>Braga, Danilo S.</creator><general>Springer London</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-5605-8381</orcidid><orcidid>https://orcid.org/0000-0001-5559-5580</orcidid><orcidid>https://orcid.org/0000-0003-0260-6770</orcidid><orcidid>https://orcid.org/0009-0006-6964-7242</orcidid><orcidid>https://orcid.org/0000-0002-8092-1525</orcidid><orcidid>https://orcid.org/0009-0003-0461-3664</orcidid><orcidid>https://orcid.org/0009-0001-4326-5151</orcidid><orcidid>https://orcid.org/0009-0005-9631-1552</orcidid></search><sort><creationdate>20240601</creationdate><title>Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree</title><author>Soares, João L. L. ; Costa, Thiago B. ; Moura, Lis S. ; Sousa, Walter S. ; Mesquita, Alexandre L. A. ; Mesquita, André L. A. ; de Figueiredo, Jullyane M. S. ; Braga, Danilo S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c270t-425037a66bb8dc4cf66f45da5fb3c66deeddc3172c3f216622e536a4f6dd6e1d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Belt conveyors</topic><topic>CAE) and Design</topic><topic>Component reliability</topic><topic>Computer-Aided Engineering (CAD</topic><topic>Critical components</topic><topic>Decision trees</topic><topic>Defects</topic><topic>Effectiveness</topic><topic>Engineering</topic><topic>Failure modes</topic><topic>Fault detection</topic><topic>Fault diagnosis</topic><topic>Feature extraction</topic><topic>Fourier transforms</topic><topic>Frequencies</topic><topic>Idlers</topic><topic>Industrial and Production Engineering</topic><topic>Machine learning</topic><topic>Mechanical Engineering</topic><topic>Media Management</topic><topic>Original Article</topic><topic>Predictive control</topic><topic>Predictive maintenance</topic><topic>Signal classification</topic><topic>System reliability</topic><topic>Transportation systems</topic><topic>Vibration analysis</topic><topic>Vibration measurement</topic><topic>Wavelet analysis</topic><topic>Wavelet transforms</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Soares, João L. L.</creatorcontrib><creatorcontrib>Costa, Thiago B.</creatorcontrib><creatorcontrib>Moura, Lis S.</creatorcontrib><creatorcontrib>Sousa, Walter S.</creatorcontrib><creatorcontrib>Mesquita, Alexandre L. A.</creatorcontrib><creatorcontrib>Mesquita, André L. A.</creatorcontrib><creatorcontrib>de Figueiredo, Jullyane M. S.</creatorcontrib><creatorcontrib>Braga, Danilo S.</creatorcontrib><collection>CrossRef</collection><jtitle>International journal of advanced manufacturing technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Soares, João L. L.</au><au>Costa, Thiago B.</au><au>Moura, Lis S.</au><au>Sousa, Walter S.</au><au>Mesquita, Alexandre L. A.</au><au>Mesquita, André L. A.</au><au>de Figueiredo, Jullyane M. S.</au><au>Braga, Danilo S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree</atitle><jtitle>International journal of advanced manufacturing technology</jtitle><stitle>Int J Adv Manuf Technol</stitle><date>2024-06-01</date><risdate>2024</risdate><volume>132</volume><issue>7-8</issue><spage>3479</spage><epage>3488</epage><pages>3479-3488</pages><issn>0268-3768</issn><eissn>1433-3015</eissn><abstract>Maintenance planning and control should prioritize predictive techniques (e.g., vibration analysis on critical components such as belt conveyors and idlers) for addressing the low reliability of bulk transportation systems. The extensive length of the belt conveyor hampers manual inspections and machine learning based on vibration measurements becomes an effective method for fault diagnosis. Models that classify faults, such as Gradient Boosting Decision Tree (GBDT), offer flexible algorithms that optimize decision tree classification through gradient-based techniques for minimizing predictive function errors. However, in case of non-stationary and nonlinear vibration signals, traditional techniques like Fourier Transform can hinder vibration analysis. Methods such as Wavelet Packet Decomposition (WPD) have emerged as an alternative to improve defect detection by extracting energy from signal frequency bands. This paper proposes a combination of WPD and GBDT for feature extraction and classification, respectively, for diagnosing two different failure modes in laboratory belt conveyor idlers, namely, bearing faults and surface wear. GBDT hyperparameters were well-fitted from 21 boosting stages, corroborating the high flexibility of the classification algorithm applied for less robust datasets. Furthermore, GBDT models achieved diagnosis accuracies of 100% for bearing defects and 97.5% for surface wear, showing the effectiveness of the combination for fault identification.</abstract><cop>London</cop><pub>Springer London</pub><doi>10.1007/s00170-024-13549-0</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0001-5605-8381</orcidid><orcidid>https://orcid.org/0000-0001-5559-5580</orcidid><orcidid>https://orcid.org/0000-0003-0260-6770</orcidid><orcidid>https://orcid.org/0009-0006-6964-7242</orcidid><orcidid>https://orcid.org/0000-0002-8092-1525</orcidid><orcidid>https://orcid.org/0009-0003-0461-3664</orcidid><orcidid>https://orcid.org/0009-0001-4326-5151</orcidid><orcidid>https://orcid.org/0009-0005-9631-1552</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0268-3768
ispartof International journal of advanced manufacturing technology, 2024-06, Vol.132 (7-8), p.3479-3488
issn 0268-3768
1433-3015
language eng
recordid cdi_proquest_journals_3053367408
source Springer Nature - Complete Springer Journals
subjects Algorithms
Belt conveyors
CAE) and Design
Component reliability
Computer-Aided Engineering (CAD
Critical components
Decision trees
Defects
Effectiveness
Engineering
Failure modes
Fault detection
Fault diagnosis
Feature extraction
Fourier transforms
Frequencies
Idlers
Industrial and Production Engineering
Machine learning
Mechanical Engineering
Media Management
Original Article
Predictive control
Predictive maintenance
Signal classification
System reliability
Transportation systems
Vibration analysis
Vibration measurement
Wavelet analysis
Wavelet transforms
title Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T19%3A27%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Fault%20diagnosis%20of%20belt%20conveyor%20idlers%20based%20on%20gradient%20boosting%20decision%20tree&rft.jtitle=International%20journal%20of%20advanced%20manufacturing%20technology&rft.au=Soares,%20Jo%C3%A3o%20L.%20L.&rft.date=2024-06-01&rft.volume=132&rft.issue=7-8&rft.spage=3479&rft.epage=3488&rft.pages=3479-3488&rft.issn=0268-3768&rft.eissn=1433-3015&rft_id=info:doi/10.1007/s00170-024-13549-0&rft_dat=%3Cproquest_cross%3E3053367408%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3053367408&rft_id=info:pmid/&rfr_iscdi=true