Design and application of Soft Sensor using Ensemble Methods

Industries are faced with the choice of suitable process control policies to improve costs, quality and raw material consumption. In the paper pulp industry, it is important to estimate quickly the Chemical Oxygen Demand (COD), a parameter that is highly correlated to product quality. Soft Sensors (...

Full description

Saved in:
Bibliographic Details
Main Authors: Soares, S., Araujo, R., Sousa, P., Souza, F.
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Chemicals
Diversity reception
Noise
Paper pulp
Predictive models
Training
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c266t-a246c89cfcca3c53b92a15cce5373ff4a78585544e88e45b541f6be24ca5e3b3
cites
container_end_page 8
container_issue
container_start_page 1
container_title
container_volume
creator Soares, S.
Araujo, R.
Sousa, P.
Souza, F.
description Industries are faced with the choice of suitable process control policies to improve costs, quality and raw material consumption. In the paper pulp industry, it is important to estimate quickly the Chemical Oxygen Demand (COD), a parameter that is highly correlated to product quality. Soft Sensors (SSs) have been established as alternative to hardware sensors and laboratory measurements for monitoring and control purposes. However, in real setups it is often difficult to get sufficient data for SS development. This work proposes Ensemble Methods (EMs) as a way to improve the SS performance for small datasets. EMs use a set of models to obtain better prediction. Their success is usually attributed to the diversity. Bootstrap and noise injection are used to produce diverse models. Several combinations of EMs are compared. The SS is successfully applied to estimate COD in a pulp process.
doi_str_mv 10.1109/ETFA.2011.6059061
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6059061</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6059061</ieee_id><sourcerecordid>6059061</sourcerecordid><originalsourceid>FETCH-LOGICAL-c266t-a246c89cfcca3c53b92a15cce5373ff4a78585544e88e45b541f6be24ca5e3b3</originalsourceid><addsrcrecordid>eNpFkE9LwzAYh-M_cM59APGSL9CaNHmTBryMrXODiYf1PtLszYx0aWnqwW-v4NDTA78HfoeHkAfOcs6Zearq1TwvGOe5YmCY4hfkjkvQmjGu1CWZcCNVxjSYq3-h5fWfkOyWzFL6YD87M8oIMyHPS0zhGKmNB2r7vg3OjqGLtPN01_mR7jCmbqCfKcQjrWLCU9MifcXxvTuke3LjbZtwduaU1KuqXqyz7dvLZjHfZq5QasxsIZUrjfPOWeFANKawHJxDEFp4L60uoQSQEssSJTQguVcNFtJZQNGIKXn8vQ2IuO-HcLLD1_4cQXwDXbdLpA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Design and application of Soft Sensor using Ensemble Methods</title><source>IEEE Xplore All Conference Series</source><creator>Soares, S. ; Araujo, R. ; Sousa, P. ; Souza, F.</creator><creatorcontrib>Soares, S. ; Araujo, R. ; Sousa, P. ; Souza, F.</creatorcontrib><description>Industries are faced with the choice of suitable process control policies to improve costs, quality and raw material consumption. In the paper pulp industry, it is important to estimate quickly the Chemical Oxygen Demand (COD), a parameter that is highly correlated to product quality. Soft Sensors (SSs) have been established as alternative to hardware sensors and laboratory measurements for monitoring and control purposes. However, in real setups it is often difficult to get sufficient data for SS development. This work proposes Ensemble Methods (EMs) as a way to improve the SS performance for small datasets. EMs use a set of models to obtain better prediction. Their success is usually attributed to the diversity. Bootstrap and noise injection are used to produce diverse models. Several combinations of EMs are compared. The SS is successfully applied to estimate COD in a pulp process.</description><identifier>ISSN: 1946-0740</identifier><identifier>ISBN: 1457700174</identifier><identifier>ISBN: 9781457700170</identifier><identifier>EISSN: 1946-0759</identifier><identifier>EISBN: 1457700166</identifier><identifier>EISBN: 9781457700163</identifier><identifier>EISBN: 9781457700187</identifier><identifier>EISBN: 1457700182</identifier><identifier>DOI: 10.1109/ETFA.2011.6059061</identifier><language>eng</language><publisher>IEEE</publisher><subject>Artificial neural networks ; Chemicals ; Diversity reception ; Noise ; Paper pulp ; Predictive models ; Training</subject><ispartof>ETFA2011, 2011, p.1-8</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c266t-a246c89cfcca3c53b92a15cce5373ff4a78585544e88e45b541f6be24ca5e3b3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6059061$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6059061$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Soares, S.</creatorcontrib><creatorcontrib>Araujo, R.</creatorcontrib><creatorcontrib>Sousa, P.</creatorcontrib><creatorcontrib>Souza, F.</creatorcontrib><title>Design and application of Soft Sensor using Ensemble Methods</title><title>ETFA2011</title><addtitle>ETFA</addtitle><description>Industries are faced with the choice of suitable process control policies to improve costs, quality and raw material consumption. In the paper pulp industry, it is important to estimate quickly the Chemical Oxygen Demand (COD), a parameter that is highly correlated to product quality. Soft Sensors (SSs) have been established as alternative to hardware sensors and laboratory measurements for monitoring and control purposes. However, in real setups it is often difficult to get sufficient data for SS development. This work proposes Ensemble Methods (EMs) as a way to improve the SS performance for small datasets. EMs use a set of models to obtain better prediction. Their success is usually attributed to the diversity. Bootstrap and noise injection are used to produce diverse models. Several combinations of EMs are compared. The SS is successfully applied to estimate COD in a pulp process.</description><subject>Artificial neural networks</subject><subject>Chemicals</subject><subject>Diversity reception</subject><subject>Noise</subject><subject>Paper pulp</subject><subject>Predictive models</subject><subject>Training</subject><issn>1946-0740</issn><issn>1946-0759</issn><isbn>1457700174</isbn><isbn>9781457700170</isbn><isbn>1457700166</isbn><isbn>9781457700163</isbn><isbn>9781457700187</isbn><isbn>1457700182</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpFkE9LwzAYh-M_cM59APGSL9CaNHmTBryMrXODiYf1PtLszYx0aWnqwW-v4NDTA78HfoeHkAfOcs6Zearq1TwvGOe5YmCY4hfkjkvQmjGu1CWZcCNVxjSYq3-h5fWfkOyWzFL6YD87M8oIMyHPS0zhGKmNB2r7vg3OjqGLtPN01_mR7jCmbqCfKcQjrWLCU9MifcXxvTuke3LjbZtwduaU1KuqXqyz7dvLZjHfZq5QasxsIZUrjfPOWeFANKawHJxDEFp4L60uoQSQEssSJTQguVcNFtJZQNGIKXn8vQ2IuO-HcLLD1_4cQXwDXbdLpA</recordid><startdate>20110101</startdate><enddate>20110101</enddate><creator>Soares, S.</creator><creator>Araujo, R.</creator><creator>Sousa, P.</creator><creator>Souza, F.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20110101</creationdate><title>Design and application of Soft Sensor using Ensemble Methods</title><author>Soares, S. ; Araujo, R. ; Sousa, P. ; Souza, F.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c266t-a246c89cfcca3c53b92a15cce5373ff4a78585544e88e45b541f6be24ca5e3b3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Artificial neural networks</topic><topic>Chemicals</topic><topic>Diversity reception</topic><topic>Noise</topic><topic>Paper pulp</topic><topic>Predictive models</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Soares, S.</creatorcontrib><creatorcontrib>Araujo, R.</creatorcontrib><creatorcontrib>Sousa, P.</creatorcontrib><creatorcontrib>Souza, F.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Soares, S.</au><au>Araujo, R.</au><au>Sousa, P.</au><au>Souza, F.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Design and application of Soft Sensor using Ensemble Methods</atitle><btitle>ETFA2011</btitle><stitle>ETFA</stitle><date>2011-01-01</date><risdate>2011</risdate><spage>1</spage><epage>8</epage><pages>1-8</pages><issn>1946-0740</issn><eissn>1946-0759</eissn><isbn>1457700174</isbn><isbn>9781457700170</isbn><eisbn>1457700166</eisbn><eisbn>9781457700163</eisbn><eisbn>9781457700187</eisbn><eisbn>1457700182</eisbn><abstract>Industries are faced with the choice of suitable process control policies to improve costs, quality and raw material consumption. In the paper pulp industry, it is important to estimate quickly the Chemical Oxygen Demand (COD), a parameter that is highly correlated to product quality. Soft Sensors (SSs) have been established as alternative to hardware sensors and laboratory measurements for monitoring and control purposes. However, in real setups it is often difficult to get sufficient data for SS development. This work proposes Ensemble Methods (EMs) as a way to improve the SS performance for small datasets. EMs use a set of models to obtain better prediction. Their success is usually attributed to the diversity. Bootstrap and noise injection are used to produce diverse models. Several combinations of EMs are compared. The SS is successfully applied to estimate COD in a pulp process.</abstract><pub>IEEE</pub><doi>10.1109/ETFA.2011.6059061</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1946-0740
ispartof ETFA2011, 2011, p.1-8
issn 1946-0740
1946-0759
language eng
recordid cdi_ieee_primary_6059061
source IEEE Xplore All Conference Series
subjects Artificial neural networks
Chemicals
Diversity reception
Noise
Paper pulp
Predictive models
Training
title Design and application of Soft Sensor using Ensemble Methods
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T16%3A38%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Design%20and%20application%20of%20Soft%20Sensor%20using%20Ensemble%20Methods&rft.btitle=ETFA2011&rft.au=Soares,%20S.&rft.date=2011-01-01&rft.spage=1&rft.epage=8&rft.pages=1-8&rft.issn=1946-0740&rft.eissn=1946-0759&rft.isbn=1457700174&rft.isbn_list=9781457700170&rft_id=info:doi/10.1109/ETFA.2011.6059061&rft.eisbn=1457700166&rft.eisbn_list=9781457700163&rft.eisbn_list=9781457700187&rft.eisbn_list=1457700182&rft_dat=%3Cieee_CHZPO%3E6059061%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c266t-a246c89cfcca3c53b92a15cce5373ff4a78585544e88e45b541f6be24ca5e3b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6059061&rfr_iscdi=true