Loading…
A new online approach for classification of pumps vibration patterns based on intelligent IoT system
•A new approach for classification of pumps vibration patterns using an Intelligent IoT Systems.•In order to identify a normal stage of cavitation, we use vibration signal as an image.•Combinations with feature extractors and classifiers for detect incipient cavitation.•The results showed that our a...
Saved in:
Published in: | Measurement : journal of the International Measurement Confederation 2020-02, Vol.151, p.107138, Article 107138 |
---|---|
Main Authors: | , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c402t-d003490291870c521d6948e1ae06310f789b387419e2d638c6049dd3305d40493 |
---|---|
cites | cdi_FETCH-LOGICAL-c402t-d003490291870c521d6948e1ae06310f789b387419e2d638c6049dd3305d40493 |
container_end_page | |
container_issue | |
container_start_page | 107138 |
container_title | Measurement : journal of the International Measurement Confederation |
container_volume | 151 |
creator | Hu, Qinhua Ohata, Elene F. Silva, Francisco H.S. Ramalho, Geraldo L.B. Han, Tao Rebouças Filho, Pedro P. |
description | •A new approach for classification of pumps vibration patterns using an Intelligent IoT Systems.•In order to identify a normal stage of cavitation, we use vibration signal as an image.•Combinations with feature extractors and classifiers for detect incipient cavitation.•The results showed that our approach is reliable and efficient to detect cavitation in pumps.
Machine condition monitoring is a primordial field of study. It allows to avoid downtime in industrial plants, avoiding financial and time losses. In this article, we use an IoT framework to classify the pump’s vibration signal, in order to identify a normal stage of operation, an incipient cavitation stage and a severe cavitation stage. Our approach uses the vibration signal, which is collected with a MEMS sensor, as an image. The feature extractors used in this study: Hu’s Moments, Gray Level Co-occurrence Matrix, Local Binary Patterns, DenseNet169, ResNet50, VGG19 and MobileNet. The classifiers used in this paper were: Gaussian Naive Bayes, Support Vector Machines, Random Forest, Multilayer Perceptron and k-Nearest Neighbors (kNN). The results showed that Hu’s Moments combined with kNN achieved the best accuracy (99.47%) with a score time of 17 ms. Thus, our approach is reliable and efficient to detect cavitation in pumps. |
doi_str_mv | 10.1016/j.measurement.2019.107138 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2338160026</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0263224119310048</els_id><sourcerecordid>2338160026</sourcerecordid><originalsourceid>FETCH-LOGICAL-c402t-d003490291870c521d6948e1ae06310f789b387419e2d638c6049dd3305d40493</originalsourceid><addsrcrecordid>eNqNkE9LAzEQxYMoWKvfIeJ56yRZt5tjKf4DwYuCt5Ams5qym6xJWvHbm7IePHqaYZh5896PkEsGCwasud4uBtRpF3FAnxccmCzzJRPtEZmxdimqmvG3YzID3oiK85qdkrOUtgDQCNnMiF1Rj180-N55pHocY9Dmg3YhUtPrlFznjM4ueBo6Ou6GMdG928RpNOqcMfpENzqhLSLU-Yx9796LGfoYXmj6ThmHc3LS6T7hxW-dk9e725f1Q_X0fP-4Xj1VpgaeKwsgaglcFuNgbjizjaxbZBqLWQbdspUb0S5rJpHbRrSmgVpaKwTc2Lq0Yk6uJt2S4nOHKatt2EVfXiouRMsaOGCYEzltmRhSitipMbpBx2_FQB2gqq36A1UdoKoJarldT7dYYuwdRpWMQ2_QuogmKxvcP1R-AIzQhd8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2338160026</pqid></control><display><type>article</type><title>A new online approach for classification of pumps vibration patterns based on intelligent IoT system</title><source>ScienceDirect Journals</source><creator>Hu, Qinhua ; Ohata, Elene F. ; Silva, Francisco H.S. ; Ramalho, Geraldo L.B. ; Han, Tao ; Rebouças Filho, Pedro P.</creator><creatorcontrib>Hu, Qinhua ; Ohata, Elene F. ; Silva, Francisco H.S. ; Ramalho, Geraldo L.B. ; Han, Tao ; Rebouças Filho, Pedro P.</creatorcontrib><description>•A new approach for classification of pumps vibration patterns using an Intelligent IoT Systems.•In order to identify a normal stage of cavitation, we use vibration signal as an image.•Combinations with feature extractors and classifiers for detect incipient cavitation.•The results showed that our approach is reliable and efficient to detect cavitation in pumps.
Machine condition monitoring is a primordial field of study. It allows to avoid downtime in industrial plants, avoiding financial and time losses. In this article, we use an IoT framework to classify the pump’s vibration signal, in order to identify a normal stage of operation, an incipient cavitation stage and a severe cavitation stage. Our approach uses the vibration signal, which is collected with a MEMS sensor, as an image. The feature extractors used in this study: Hu’s Moments, Gray Level Co-occurrence Matrix, Local Binary Patterns, DenseNet169, ResNet50, VGG19 and MobileNet. The classifiers used in this paper were: Gaussian Naive Bayes, Support Vector Machines, Random Forest, Multilayer Perceptron and k-Nearest Neighbors (kNN). The results showed that Hu’s Moments combined with kNN achieved the best accuracy (99.47%) with a score time of 17 ms. Thus, our approach is reliable and efficient to detect cavitation in pumps.</description><identifier>ISSN: 0263-2241</identifier><identifier>EISSN: 1873-412X</identifier><identifier>DOI: 10.1016/j.measurement.2019.107138</identifier><language>eng</language><publisher>London: Elsevier Ltd</publisher><subject>Cavitation ; Condition monitoring ; Downtime ; Fault detection ; Feature extraction ; Industrial plants ; Intelligent systems ; Internet of Things ; Machine learning ; Machinery condition monitoring ; Microelectromechanical systems ; Multilayer perceptrons ; Predictive maintenance ; Pumps ; Support vector machines ; Vibration analysis ; Vibration monitoring</subject><ispartof>Measurement : journal of the International Measurement Confederation, 2020-02, Vol.151, p.107138, Article 107138</ispartof><rights>2019 Elsevier Ltd</rights><rights>Copyright Elsevier Science Ltd. Feb 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c402t-d003490291870c521d6948e1ae06310f789b387419e2d638c6049dd3305d40493</citedby><cites>FETCH-LOGICAL-c402t-d003490291870c521d6948e1ae06310f789b387419e2d638c6049dd3305d40493</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Hu, Qinhua</creatorcontrib><creatorcontrib>Ohata, Elene F.</creatorcontrib><creatorcontrib>Silva, Francisco H.S.</creatorcontrib><creatorcontrib>Ramalho, Geraldo L.B.</creatorcontrib><creatorcontrib>Han, Tao</creatorcontrib><creatorcontrib>Rebouças Filho, Pedro P.</creatorcontrib><title>A new online approach for classification of pumps vibration patterns based on intelligent IoT system</title><title>Measurement : journal of the International Measurement Confederation</title><description>•A new approach for classification of pumps vibration patterns using an Intelligent IoT Systems.•In order to identify a normal stage of cavitation, we use vibration signal as an image.•Combinations with feature extractors and classifiers for detect incipient cavitation.•The results showed that our approach is reliable and efficient to detect cavitation in pumps.
Machine condition monitoring is a primordial field of study. It allows to avoid downtime in industrial plants, avoiding financial and time losses. In this article, we use an IoT framework to classify the pump’s vibration signal, in order to identify a normal stage of operation, an incipient cavitation stage and a severe cavitation stage. Our approach uses the vibration signal, which is collected with a MEMS sensor, as an image. The feature extractors used in this study: Hu’s Moments, Gray Level Co-occurrence Matrix, Local Binary Patterns, DenseNet169, ResNet50, VGG19 and MobileNet. The classifiers used in this paper were: Gaussian Naive Bayes, Support Vector Machines, Random Forest, Multilayer Perceptron and k-Nearest Neighbors (kNN). The results showed that Hu’s Moments combined with kNN achieved the best accuracy (99.47%) with a score time of 17 ms. Thus, our approach is reliable and efficient to detect cavitation in pumps.</description><subject>Cavitation</subject><subject>Condition monitoring</subject><subject>Downtime</subject><subject>Fault detection</subject><subject>Feature extraction</subject><subject>Industrial plants</subject><subject>Intelligent systems</subject><subject>Internet of Things</subject><subject>Machine learning</subject><subject>Machinery condition monitoring</subject><subject>Microelectromechanical systems</subject><subject>Multilayer perceptrons</subject><subject>Predictive maintenance</subject><subject>Pumps</subject><subject>Support vector machines</subject><subject>Vibration analysis</subject><subject>Vibration monitoring</subject><issn>0263-2241</issn><issn>1873-412X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNqNkE9LAzEQxYMoWKvfIeJ56yRZt5tjKf4DwYuCt5Ams5qym6xJWvHbm7IePHqaYZh5896PkEsGCwasud4uBtRpF3FAnxccmCzzJRPtEZmxdimqmvG3YzID3oiK85qdkrOUtgDQCNnMiF1Rj180-N55pHocY9Dmg3YhUtPrlFznjM4ueBo6Ou6GMdG928RpNOqcMfpENzqhLSLU-Yx9796LGfoYXmj6ThmHc3LS6T7hxW-dk9e725f1Q_X0fP-4Xj1VpgaeKwsgaglcFuNgbjizjaxbZBqLWQbdspUb0S5rJpHbRrSmgVpaKwTc2Lq0Yk6uJt2S4nOHKatt2EVfXiouRMsaOGCYEzltmRhSitipMbpBx2_FQB2gqq36A1UdoKoJarldT7dYYuwdRpWMQ2_QuogmKxvcP1R-AIzQhd8</recordid><startdate>20200201</startdate><enddate>20200201</enddate><creator>Hu, Qinhua</creator><creator>Ohata, Elene F.</creator><creator>Silva, Francisco H.S.</creator><creator>Ramalho, Geraldo L.B.</creator><creator>Han, Tao</creator><creator>Rebouças Filho, Pedro P.</creator><general>Elsevier Ltd</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20200201</creationdate><title>A new online approach for classification of pumps vibration patterns based on intelligent IoT system</title><author>Hu, Qinhua ; Ohata, Elene F. ; Silva, Francisco H.S. ; Ramalho, Geraldo L.B. ; Han, Tao ; Rebouças Filho, Pedro P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c402t-d003490291870c521d6948e1ae06310f789b387419e2d638c6049dd3305d40493</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Cavitation</topic><topic>Condition monitoring</topic><topic>Downtime</topic><topic>Fault detection</topic><topic>Feature extraction</topic><topic>Industrial plants</topic><topic>Intelligent systems</topic><topic>Internet of Things</topic><topic>Machine learning</topic><topic>Machinery condition monitoring</topic><topic>Microelectromechanical systems</topic><topic>Multilayer perceptrons</topic><topic>Predictive maintenance</topic><topic>Pumps</topic><topic>Support vector machines</topic><topic>Vibration analysis</topic><topic>Vibration monitoring</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hu, Qinhua</creatorcontrib><creatorcontrib>Ohata, Elene F.</creatorcontrib><creatorcontrib>Silva, Francisco H.S.</creatorcontrib><creatorcontrib>Ramalho, Geraldo L.B.</creatorcontrib><creatorcontrib>Han, Tao</creatorcontrib><creatorcontrib>Rebouças Filho, Pedro P.</creatorcontrib><collection>CrossRef</collection><jtitle>Measurement : journal of the International Measurement Confederation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hu, Qinhua</au><au>Ohata, Elene F.</au><au>Silva, Francisco H.S.</au><au>Ramalho, Geraldo L.B.</au><au>Han, Tao</au><au>Rebouças Filho, Pedro P.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A new online approach for classification of pumps vibration patterns based on intelligent IoT system</atitle><jtitle>Measurement : journal of the International Measurement Confederation</jtitle><date>2020-02-01</date><risdate>2020</risdate><volume>151</volume><spage>107138</spage><pages>107138-</pages><artnum>107138</artnum><issn>0263-2241</issn><eissn>1873-412X</eissn><abstract>•A new approach for classification of pumps vibration patterns using an Intelligent IoT Systems.•In order to identify a normal stage of cavitation, we use vibration signal as an image.•Combinations with feature extractors and classifiers for detect incipient cavitation.•The results showed that our approach is reliable and efficient to detect cavitation in pumps.
Machine condition monitoring is a primordial field of study. It allows to avoid downtime in industrial plants, avoiding financial and time losses. In this article, we use an IoT framework to classify the pump’s vibration signal, in order to identify a normal stage of operation, an incipient cavitation stage and a severe cavitation stage. Our approach uses the vibration signal, which is collected with a MEMS sensor, as an image. The feature extractors used in this study: Hu’s Moments, Gray Level Co-occurrence Matrix, Local Binary Patterns, DenseNet169, ResNet50, VGG19 and MobileNet. The classifiers used in this paper were: Gaussian Naive Bayes, Support Vector Machines, Random Forest, Multilayer Perceptron and k-Nearest Neighbors (kNN). The results showed that Hu’s Moments combined with kNN achieved the best accuracy (99.47%) with a score time of 17 ms. Thus, our approach is reliable and efficient to detect cavitation in pumps.</abstract><cop>London</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.measurement.2019.107138</doi></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0263-2241 |
ispartof | Measurement : journal of the International Measurement Confederation, 2020-02, Vol.151, p.107138, Article 107138 |
issn | 0263-2241 1873-412X |
language | eng |
recordid | cdi_proquest_journals_2338160026 |
source | ScienceDirect Journals |
subjects | Cavitation Condition monitoring Downtime Fault detection Feature extraction Industrial plants Intelligent systems Internet of Things Machine learning Machinery condition monitoring Microelectromechanical systems Multilayer perceptrons Predictive maintenance Pumps Support vector machines Vibration analysis Vibration monitoring |
title | A new online approach for classification of pumps vibration patterns based on intelligent IoT system |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T19%3A16%3A10IST&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=A%20new%20online%20approach%20for%20classification%20of%20pumps%20vibration%20patterns%20based%20on%20intelligent%20IoT%20system&rft.jtitle=Measurement%20:%20journal%20of%20the%20International%20Measurement%20Confederation&rft.au=Hu,%20Qinhua&rft.date=2020-02-01&rft.volume=151&rft.spage=107138&rft.pages=107138-&rft.artnum=107138&rft.issn=0263-2241&rft.eissn=1873-412X&rft_id=info:doi/10.1016/j.measurement.2019.107138&rft_dat=%3Cproquest_cross%3E2338160026%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c402t-d003490291870c521d6948e1ae06310f789b387419e2d638c6049dd3305d40493%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2338160026&rft_id=info:pmid/&rfr_iscdi=true |