Fault detection in flotation processes based on deep learning and support vector machine

Effective fault detection techniques can help flotation plant reduce reagents consumption, increase mineral recovery, and reduce labor intensity. Traditional, online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation, like col...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of Central South University 2019-09, Vol.26 (9), p.2504-2515
Hauptverfasser: Li, Zhong-mei, Gui, Wei-hua, Zhu, Jian-yong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2515
container_issue 9
container_start_page 2504
container_title Journal of Central South University
container_volume 26
creator Li, Zhong-mei
Gui, Wei-hua
Zhu, Jian-yong
description Effective fault detection techniques can help flotation plant reduce reagents consumption, increase mineral recovery, and reduce labor intensity. Traditional, online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation, like color, shape, size and texture, always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case. In this work, a new integrated method based on convolution neural network (CNN) combined with transfer learning approach and support vector machine (SVM) is proposed to automatically recognize the flotation condition. To be more specific, CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection. As compared with the existed recognition methods, it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy. Hence, a CNN-SVM based, real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.
doi_str_mv 10.1007/s11771-019-4190-8
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2305525721</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2305525721</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-92f641f64236146b742b1084c0dcf17d208d989a13d3ae4b9f52437058bb29ea3</originalsourceid><addsrcrecordid>eNp1kEFLxDAQhYMouKz7A7wFPEczk7ZpjrK4Kix4UfAW0iZdK7tpTVLBf2_WCp48DDMZ3nsTPkIugV8D5_ImAkgJjINiBSjO6hOyQETJSkRxmmeuSoa1UudkFWPfcAFYiUpVC_K6MdM-UeuSa1M_eNp72u2HZH4eYxhaF6OLtDHRWZpX1rmR7p0Jvvc7arylcRrHIST6mROGQA-mfeu9uyBnndlHt_rtS_KyuXteP7Dt0_3j-nbLWgFVYgq7qoBcKCooqkYW2ACvi5bbtgNpkddW1cqAsMK4olFdiYWQvKybBpUzYkmu5tz814_JxaTfhyn4fFKj4GWJpUTIKphVbRhiDK7TY-gPJnxp4PrIUM8MdWaojwx1nT04e2LW-p0Lf8n_m74BKjFztg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2305525721</pqid></control><display><type>article</type><title>Fault detection in flotation processes based on deep learning and support vector machine</title><source>Alma/SFX Local Collection</source><source>SpringerNature Complete Journals</source><creator>Li, Zhong-mei ; Gui, Wei-hua ; Zhu, Jian-yong</creator><creatorcontrib>Li, Zhong-mei ; Gui, Wei-hua ; Zhu, Jian-yong</creatorcontrib><description>Effective fault detection techniques can help flotation plant reduce reagents consumption, increase mineral recovery, and reduce labor intensity. Traditional, online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation, like color, shape, size and texture, always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case. In this work, a new integrated method based on convolution neural network (CNN) combined with transfer learning approach and support vector machine (SVM) is proposed to automatically recognize the flotation condition. To be more specific, CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection. As compared with the existed recognition methods, it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy. Hence, a CNN-SVM based, real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.</description><identifier>ISSN: 2095-2899</identifier><identifier>EISSN: 2227-5223</identifier><identifier>DOI: 10.1007/s11771-019-4190-8</identifier><language>eng</language><publisher>Changsha: Central South University</publisher><subject>Algorithms ; Antimony ; Artificial neural networks ; Chemical reduction ; Convolution ; Deep learning ; Engineering ; Fault detection ; Feature extraction ; Flotation ; Image detection ; Image segmentation ; Metallic Materials ; Reagents ; Support vector machines</subject><ispartof>Journal of Central South University, 2019-09, Vol.26 (9), p.2504-2515</ispartof><rights>Central South University Press and Springer-Verlag GmbH Germany, part of Springer Nature 2019</rights><rights>Copyright Springer Nature B.V. 2019</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-92f641f64236146b742b1084c0dcf17d208d989a13d3ae4b9f52437058bb29ea3</citedby><cites>FETCH-LOGICAL-c316t-92f641f64236146b742b1084c0dcf17d208d989a13d3ae4b9f52437058bb29ea3</cites><orcidid>0000-0003-0312-436X</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/s11771-019-4190-8$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11771-019-4190-8$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Li, Zhong-mei</creatorcontrib><creatorcontrib>Gui, Wei-hua</creatorcontrib><creatorcontrib>Zhu, Jian-yong</creatorcontrib><title>Fault detection in flotation processes based on deep learning and support vector machine</title><title>Journal of Central South University</title><addtitle>J. Cent. South Univ</addtitle><description>Effective fault detection techniques can help flotation plant reduce reagents consumption, increase mineral recovery, and reduce labor intensity. Traditional, online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation, like color, shape, size and texture, always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case. In this work, a new integrated method based on convolution neural network (CNN) combined with transfer learning approach and support vector machine (SVM) is proposed to automatically recognize the flotation condition. To be more specific, CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection. As compared with the existed recognition methods, it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy. Hence, a CNN-SVM based, real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.</description><subject>Algorithms</subject><subject>Antimony</subject><subject>Artificial neural networks</subject><subject>Chemical reduction</subject><subject>Convolution</subject><subject>Deep learning</subject><subject>Engineering</subject><subject>Fault detection</subject><subject>Feature extraction</subject><subject>Flotation</subject><subject>Image detection</subject><subject>Image segmentation</subject><subject>Metallic Materials</subject><subject>Reagents</subject><subject>Support vector machines</subject><issn>2095-2899</issn><issn>2227-5223</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp1kEFLxDAQhYMouKz7A7wFPEczk7ZpjrK4Kix4UfAW0iZdK7tpTVLBf2_WCp48DDMZ3nsTPkIugV8D5_ImAkgJjINiBSjO6hOyQETJSkRxmmeuSoa1UudkFWPfcAFYiUpVC_K6MdM-UeuSa1M_eNp72u2HZH4eYxhaF6OLtDHRWZpX1rmR7p0Jvvc7arylcRrHIST6mROGQA-mfeu9uyBnndlHt_rtS_KyuXteP7Dt0_3j-nbLWgFVYgq7qoBcKCooqkYW2ACvi5bbtgNpkddW1cqAsMK4olFdiYWQvKybBpUzYkmu5tz814_JxaTfhyn4fFKj4GWJpUTIKphVbRhiDK7TY-gPJnxp4PrIUM8MdWaojwx1nT04e2LW-p0Lf8n_m74BKjFztg</recordid><startdate>20190901</startdate><enddate>20190901</enddate><creator>Li, Zhong-mei</creator><creator>Gui, Wei-hua</creator><creator>Zhu, Jian-yong</creator><general>Central South University</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-0312-436X</orcidid></search><sort><creationdate>20190901</creationdate><title>Fault detection in flotation processes based on deep learning and support vector machine</title><author>Li, Zhong-mei ; Gui, Wei-hua ; Zhu, Jian-yong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-92f641f64236146b742b1084c0dcf17d208d989a13d3ae4b9f52437058bb29ea3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Antimony</topic><topic>Artificial neural networks</topic><topic>Chemical reduction</topic><topic>Convolution</topic><topic>Deep learning</topic><topic>Engineering</topic><topic>Fault detection</topic><topic>Feature extraction</topic><topic>Flotation</topic><topic>Image detection</topic><topic>Image segmentation</topic><topic>Metallic Materials</topic><topic>Reagents</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Zhong-mei</creatorcontrib><creatorcontrib>Gui, Wei-hua</creatorcontrib><creatorcontrib>Zhu, Jian-yong</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of Central South University</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Zhong-mei</au><au>Gui, Wei-hua</au><au>Zhu, Jian-yong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Fault detection in flotation processes based on deep learning and support vector machine</atitle><jtitle>Journal of Central South University</jtitle><stitle>J. Cent. South Univ</stitle><date>2019-09-01</date><risdate>2019</risdate><volume>26</volume><issue>9</issue><spage>2504</spage><epage>2515</epage><pages>2504-2515</pages><issn>2095-2899</issn><eissn>2227-5223</eissn><abstract>Effective fault detection techniques can help flotation plant reduce reagents consumption, increase mineral recovery, and reduce labor intensity. Traditional, online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation, like color, shape, size and texture, always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case. In this work, a new integrated method based on convolution neural network (CNN) combined with transfer learning approach and support vector machine (SVM) is proposed to automatically recognize the flotation condition. To be more specific, CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection. As compared with the existed recognition methods, it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy. Hence, a CNN-SVM based, real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.</abstract><cop>Changsha</cop><pub>Central South University</pub><doi>10.1007/s11771-019-4190-8</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0003-0312-436X</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 2095-2899
ispartof Journal of Central South University, 2019-09, Vol.26 (9), p.2504-2515
issn 2095-2899
2227-5223
language eng
recordid cdi_proquest_journals_2305525721
source Alma/SFX Local Collection; SpringerNature Complete Journals
subjects Algorithms
Antimony
Artificial neural networks
Chemical reduction
Convolution
Deep learning
Engineering
Fault detection
Feature extraction
Flotation
Image detection
Image segmentation
Metallic Materials
Reagents
Support vector machines
title Fault detection in flotation processes based on deep learning and support vector machine
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T10%3A44%3A11IST&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%20detection%20in%20flotation%20processes%20based%20on%20deep%20learning%20and%20support%20vector%20machine&rft.jtitle=Journal%20of%20Central%20South%20University&rft.au=Li,%20Zhong-mei&rft.date=2019-09-01&rft.volume=26&rft.issue=9&rft.spage=2504&rft.epage=2515&rft.pages=2504-2515&rft.issn=2095-2899&rft.eissn=2227-5223&rft_id=info:doi/10.1007/s11771-019-4190-8&rft_dat=%3Cproquest_cross%3E2305525721%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=2305525721&rft_id=info:pmid/&rfr_iscdi=true