Virtual Analyzers for MI and Density Based on Neural Networks Improved through an Integrated Strategy Involving a Constructive Algorithm and Definition of Initial Weights

This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene (LPE). Both models are based on Feedforward Neural Networks which are improved through a strat...

Full description

Saved in:

Bibliographic Details
Published in:	Macromolecular reaction engineering Vol. 17; no. 4
Main Authors:	da Silva, Adilton Lopes, Fontes, Cristiano Hora, Embiruçu, Marcelo
Format:	Journal Article
Language:	English
Published:	Weinheim Wiley Subscription Services, Inc 01.08.2023
Subjects:	Algorithms Analyzers Artificial neural networks constructive algorithm Density feedforward neural network linear polyethylene Neural networks Optimization quality parameters Regression models virtual analyser
ISSN:	1862-832X, 1862-8338
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene (LPE). Both models are based on Feedforward Neural Networks which are improved through a strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units. The initialization strategy is based on linearization of the neural model with only one hidden unit (nonlinear model) and subsequent optimization of this model by maximizing its similarity to the standard linear regression model whose solution is obtained analytically. The Initial Neural Model (INM) is then used as a starting point for a gradual increase in the number of hidden units. In a validation test involving MI and density values collected over 2 years of operation, the neural model is able to predict these properties with mean percentage errors equal to 0.81% (MI) and 0.04% (density) and determination coefficients equal to 0.970 (MI) and 0.983 (density). The population coefficient estimated in all tests involving grade transitions (0.96) shows a strong linear correlation between the proposed model and laboratory measurements. Two virtual analyzers (density and Melt Index) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene are developed and validated. Both models are based on Feedforward Neural Networks which are improved through a systematic strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units.
AbstractList	This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene (LPE). Both models are based on Feedforward Neural Networks which are improved through a strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units. The initialization strategy is based on linearization of the neural model with only one hidden unit (nonlinear model) and subsequent optimization of this model by maximizing its similarity to the standard linear regression model whose solution is obtained analytically. The Initial Neural Model (INM) is then used as a starting point for a gradual increase in the number of hidden units. In a validation test involving MI and density values collected over 2 years of operation, the neural model is able to predict these properties with mean percentage errors equal to 0.81% (MI) and 0.04% (density) and determination coefficients equal to 0.970 (MI) and 0.983 (density). The population coefficient estimated in all tests involving grade transitions (0.96) shows a strong linear correlation between the proposed model and laboratory measurements. This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene (LPE). Both models are based on Feedforward Neural Networks which are improved through a strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units. The initialization strategy is based on linearization of the neural model with only one hidden unit (nonlinear model) and subsequent optimization of this model by maximizing its similarity to the standard linear regression model whose solution is obtained analytically. The Initial Neural Model (INM) is then used as a starting point for a gradual increase in the number of hidden units. In a validation test involving MI and density values collected over 2 years of operation, the neural model is able to predict these properties with mean percentage errors equal to 0.81% (MI) and 0.04% (density) and determination coefficients equal to 0.970 (MI) and 0.983 (density). The population coefficient estimated in all tests involving grade transitions (0.96) shows a strong linear correlation between the proposed model and laboratory measurements. Two virtual analyzers (density and Melt Index) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene are developed and validated. Both models are based on Feedforward Neural Networks which are improved through a systematic strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units.
Author	Fontes, Cristiano Hora da Silva, Adilton Lopes Embiruçu, Marcelo
Author_xml	– sequence: 1 givenname: Adilton Lopes surname: da Silva fullname: da Silva, Adilton Lopes organization: Universidade Federal da Bahia (Federal University of Bahia) – sequence: 2 givenname: Cristiano Hora orcidid: 0000-0001-8020-6815 surname: Fontes fullname: Fontes, Cristiano Hora email: cfontes@ufba.br organization: Universidade Federal da Bahia (Federal University of Bahia) – sequence: 3 givenname: Marcelo orcidid: 0000-0002-8453-1014 surname: Embiruçu fullname: Embiruçu, Marcelo organization: Universidade Federal da Bahia (Federal University of Bahia)
BookMark	eNqFkU9PwjAYxhuDiYBePTfxDLYd67ojIioJYOL_21K2bhRHi203Mj-Sn9ISCB7toe-bt8-vT9qnA1pKKwHAJUZ9jBC5Xhuh-gQRghCi9AS0MaOkx4KAtY49-TgDHWtXCIV-xW3w8yaNq3gJh4qXzbcwFubawNkEcpXBW6GsdA284VZkUCs4F5Xx4rlwW20-LZysN0bX_swtja6KpafgRDlRGO789NntatH4Wa3LWqoCcjjSyjpTpU7WAg7LQhvpluuDXy6VdNI76dxDvvVu70IWS2fPwWnOSysuDrULXu_GL6OH3vTxfjIaTnspiQjtLVLC44EIKcsWjMaYxmmAshzHaEFpHnAa-x0FEV2EUYazAfMUDhBKOQtZxEnQBVf7e_3TviphXbLSlfHfYxPCQsJwFKKdqr9XpUZba0SebIxcc9MkGCW7PJJdHskxDw_Ee2ArS9H8o05mT-P5H_sL4SiTWQ
Cites_doi	10.1016/j.compchemeng.2021.107469 10.1016/j.chemolab.2019.103813 10.1016/j.procs.2020.03.321 10.1213/ANE.0000000000002864 10.1016/j.neucom.2017.08.040 10.1016/j.asoc.2021.107100 10.1016/j.asoc.2020.106622 10.1016/j.ifacol.2022.07.552 10.1016/j.chemolab.2018.01.008 10.1016/j.cjche.2016.05.030 10.1016/j.cie.2017.01.030 10.1016/j.neucom.2021.11.029 10.1108/IMDS-07-2019-0361 10.1016/j.neucom.2014.03.056 10.1016/j.jmsy.2020.12.016 10.1108/IMDS-06-2019-0351 10.1016/0893-6080(89)90020-8 10.1016/j.engappai.2021.104495 10.1016/j.engappai.2022.105242 10.1016/j.matpr.2020.09.238 10.1016/j.neucom.2013.10.006 10.1016/j.jprocont.2013.02.008 10.1016/j.chemolab.2013.04.018 10.1016/j.matpr.2022.02.037 10.1016/B978-0-323-85159-6.50287-6 10.1016/j.compchemeng.2019.106664 10.1016/j.chemolab.2012.12.003 10.1016/j.aej.2022.04.032
ContentType	Journal Article
Copyright	2023 Wiley‐VCH GmbH
Copyright_xml	– notice: 2023 Wiley‐VCH GmbH
DBID	AAYXX CITATION
DOI	10.1002/mren.202200066
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList	CrossRef
DeliveryMethod	fulltext_linktorsrc
Discipline	Chemistry
EISSN	1862-8338
EndPage	n/a
ExternalDocumentID	10_1002_mren_202200066 MREN202200066
Genre	article
GroupedDBID	05W 0R~ 1OC 31~ 33P 3SF 4.4 52U 53G 5GY 8-1 8UM A00 AAESR AAEVG AAHHS AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCUV ABIJN ACAHQ ACBWZ ACCFJ ACCZN ACGFS ACIWK ACPOU ACRPL ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN AEEZP AEIGN AEIMD AENEX AEQDE AEUYR AFBPY AFFPM AFGKR AFPWT AFWVQ AHBTC AITYG AIURR AIWBW AJBDE AJXKR ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ASPBG ATUGU AUFTA AVWKF AZFZN AZVAB BDRZF BFHJK BHBCM BMNLL BMXJE BNHUX BOGZA BRXPI CS3 DCZOG DRFUL DRSTM EBS EJD FEDTE G-S GODZA HGLYW HVGLF HZ~ I-F LATKE LAW LEEKS LH4 LITHE LOXES LUTES LW6 LYRES MEWTI MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM MY~ O66 O9- OIG P2P P2W P4E ROL SUPJJ TUS WBKPD WFSAM WIH WIK WOHZO WXSBR WYISQ WYJ XV2 ZZTAW ~S- AAMMB AAYXX ADMLS AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY CITATION
ID	FETCH-LOGICAL-c2726-bc2a94e568db869169c30df190b66f3a696f30376b57d1d482721300ca8587a23
IEDL.DBID	DRFUL
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000906705300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1862-832X
IngestDate	Fri Jul 25 11:13:39 EDT 2025 Sat Nov 29 01:32:42 EST 2025 Wed Jan 22 16:17:21 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2726-bc2a94e568db869169c30df190b66f3a696f30376b57d1d482721300ca8587a23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-8453-1014 0000-0001-8020-6815
PQID	2852817502
PQPubID	1016393
PageCount	9
ParticipantIDs	proquest_journals_2852817502 crossref_primary_10_1002_mren_202200066 wiley_primary_10_1002_mren_202200066_MREN202200066
PublicationCentury	2000
PublicationDate	August 2023 2023-08-00 20230801
PublicationDateYYYYMMDD	2023-08-01
PublicationDate_xml	– month: 08 year: 2023 text: August 2023
PublicationDecade	2020
PublicationPlace	Weinheim
PublicationPlace_xml	– name: Weinheim
PublicationTitle	Macromolecular reaction engineering
PublicationYear	2023
Publisher	Wiley Subscription Services, Inc
Publisher_xml	– name: Wiley Subscription Services, Inc
References	1989; 2 2019; 192 2021; 42 2021; 102 2020; 120 2013; 23 2021; 106 2013; 126 2018; 126 2013; 122 2022; 63 2020; 167 2021; 482 2014; 131 2022; 49 2022; 115 2018; 25 2021; 58 2018; 174 2018; 275 2013; 119 2020; 96 2022; 61 2020 2020; 133 2022; 55 2021; 154 2014; 142 2016; 24 2017; 106 e_1_2_9_31_1 e_1_2_9_11_1 e_1_2_9_10_1 e_1_2_9_13_1 e_1_2_9_12_1 e_1_2_9_15_1 e_1_2_9_14_1 e_1_2_9_17_1 e_1_2_9_16_1 e_1_2_9_19_1 e_1_2_9_18_1 Belciug S. (e_1_2_9_30_1) 2020 e_1_2_9_20_1 Vahidi O. (e_1_2_9_3_1) 2018; 25 e_1_2_9_22_1 e_1_2_9_21_1 Jiang H. (e_1_2_9_6_1) 2013; 119 e_1_2_9_24_1 e_1_2_9_23_1 e_1_2_9_8_1 e_1_2_9_7_1 e_1_2_9_5_1 e_1_2_9_4_1 e_1_2_9_2_1 e_1_2_9_1_1 e_1_2_9_9_1 e_1_2_9_26_1 e_1_2_9_25_1 e_1_2_9_28_1 e_1_2_9_27_1 e_1_2_9_29_1
References_xml	– volume: 275 start-page: 278 year: 2018 publication-title: Neurocomputing – volume: 61 year: 2022 publication-title: Alexandria Eng. J. – volume: 167 start-page: 2606 year: 2020 publication-title: Procedia Comput. Sci. – volume: 102 year: 2021 publication-title: Appl. Soft Comput. J. – volume: 106 year: 2021 publication-title: Eng. Appl. Artif. Intell. – volume: 126 start-page: 83 year: 2013 publication-title: Chemom. Intell. Lab. Syst. – volume: 154 year: 2021 publication-title: Comput. Chem. Eng. – volume: 96 year: 2020 publication-title: Appl. Soft Comput. J. – volume: 133 year: 2020 publication-title: Comput. Chem. Eng. – volume: 106 start-page: 123 year: 2017 publication-title: Comput. Ind. Eng. – volume: 23 start-page: 664 year: 2013 publication-title: J. Process Control – volume: 482 start-page: 139 year: 2021 publication-title: Neurocomputing – volume: 122 start-page: 12 year: 2013 publication-title: Chemom. Intell. Lab. Syst. – volume: 126 start-page: 1763 year: 2018 publication-title: Anesth. Analg. – volume: 142 start-page: 291 year: 2014 publication-title: Neurocomputing – volume: 120 start-page: 164 year: 2020 publication-title: Ind. Manag. Data Syst. – volume: 174 start-page: 15 year: 2018 publication-title: Chemom. Intell. Lab. Syst. – volume: 119 start-page: 468 year: 2013 publication-title: Neurocomputing – volume: 49 start-page: 1723 year: 2022 publication-title: Comput.‐Aided Chem. Eng. – volume: 25 start-page: 21 year: 2018 publication-title: Indian J. Chem. Technol. – volume: 58 start-page: 335 year: 2021 publication-title: J. Manuf. Syst. – volume: 2 start-page: 359 year: 1989 publication-title: Neural Networks – year: 2020 – volume: 120 start-page: 128 year: 2020 publication-title: Ind. Manag. Data Syst. – volume: 131 start-page: 368 year: 2014 publication-title: Neurocomputing – volume: 192 year: 2019 publication-title: Chemom. Intell. Lab. Syst. – volume: 42 start-page: 39 year: 2021 publication-title: Mater. Today: Proc. – volume: 24 start-page: 1013 year: 2016 publication-title: Chin. J. Chem. Eng. – volume: 63 start-page: S95 year: 2022 publication-title: Mater. Today: Proc. – volume: 55 start-page: 857 year: 2022 publication-title: IFAC‐PapersOnLine – volume: 115 year: 2022 publication-title: Eng. Appl. Artif. Intell. – ident: e_1_2_9_16_1 doi: 10.1016/j.compchemeng.2021.107469 – ident: e_1_2_9_15_1 doi: 10.1016/j.chemolab.2019.103813 – ident: e_1_2_9_24_1 doi: 10.1016/j.procs.2020.03.321 – ident: e_1_2_9_29_1 doi: 10.1213/ANE.0000000000002864 – ident: e_1_2_9_21_1 doi: 10.1016/j.neucom.2017.08.040 – volume: 25 start-page: 21 year: 2018 ident: e_1_2_9_3_1 publication-title: Indian J. Chem. Technol. – ident: e_1_2_9_22_1 doi: 10.1016/j.asoc.2021.107100 – ident: e_1_2_9_23_1 doi: 10.1016/j.asoc.2020.106622 – ident: e_1_2_9_9_1 doi: 10.1016/j.ifacol.2022.07.552 – ident: e_1_2_9_14_1 doi: 10.1016/j.chemolab.2018.01.008 – ident: e_1_2_9_13_1 doi: 10.1016/j.cjche.2016.05.030 – ident: e_1_2_9_2_1 doi: 10.1016/j.cie.2017.01.030 – ident: e_1_2_9_25_1 doi: 10.1016/j.neucom.2021.11.029 – ident: e_1_2_9_27_1 doi: 10.1108/IMDS-07-2019-0361 – ident: e_1_2_9_12_1 doi: 10.1016/j.neucom.2014.03.056 – ident: e_1_2_9_7_1 doi: 10.1016/j.jmsy.2020.12.016 – ident: e_1_2_9_26_1 doi: 10.1108/IMDS-06-2019-0351 – ident: e_1_2_9_28_1 doi: 10.1016/0893-6080(89)90020-8 – ident: e_1_2_9_19_1 doi: 10.1016/j.engappai.2021.104495 – ident: e_1_2_9_20_1 doi: 10.1016/j.engappai.2022.105242 – volume-title: Artificial Intelligence in Cancer: Diagnostic to Tailored Treatment year: 2020 ident: e_1_2_9_30_1 – ident: e_1_2_9_18_1 doi: 10.1016/j.matpr.2020.09.238 – ident: e_1_2_9_11_1 doi: 10.1016/j.neucom.2013.10.006 – volume: 119 start-page: 468 year: 2013 ident: e_1_2_9_6_1 publication-title: Neurocomputing – ident: e_1_2_9_5_1 doi: 10.1016/j.jprocont.2013.02.008 – ident: e_1_2_9_10_1 doi: 10.1016/j.chemolab.2013.04.018 – ident: e_1_2_9_17_1 doi: 10.1016/j.matpr.2022.02.037 – ident: e_1_2_9_8_1 doi: 10.1016/B978-0-323-85159-6.50287-6 – ident: e_1_2_9_1_1 doi: 10.1016/j.compchemeng.2019.106664 – ident: e_1_2_9_31_1 doi: 10.1016/j.chemolab.2012.12.003 – ident: e_1_2_9_4_1 doi: 10.1016/j.aej.2022.04.032
SSID	ssj0055559
Score	2.283446
Snippet	This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final...
SourceID	proquest crossref wiley
SourceType	Aggregation Database Index Database Publisher
SubjectTerms	Algorithms Analyzers Artificial neural networks constructive algorithm Density feedforward neural network linear polyethylene Neural networks Optimization quality parameters Regression models virtual analyser
Title	Virtual Analyzers for MI and Density Based on Neural Networks Improved through an Integrated Strategy Involving a Constructive Algorithm and Definition of Initial Weights
URI	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmren.202200066 https://www.proquest.com/docview/2852817502
Volume	17
WOSCitedRecordID	wos000906705300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1862-8338 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0055559 issn: 1862-832X databaseCode: DRFUL dateStart: 20070101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB50FfTiW1xfzEHwVOymTdoefS0Kuoj42FvJq7qgXdkugv4kf6WTPlY9CdpDadomKclk5mM6-QZgj2k_sswmXmJj44Uq7HjSCO5lhL0l960JSofb3UXU68X9fnL1bRd_xQ8xcbi5lVHqa7fApSoOvkhDn0fW8Zeycq-JmIYZRsIbtmDm5Lp7e9FoY06Hg8AdQu4eSW-_IW702cHPFn4api-0-R2zlkanu_j_z12ChRpw4mElIcswZfMVmDtu8rytwsfdYOQ2kWDJT_JOcBAJyOLlOcrc4IkLcB-_4RFZO4PDHB2bB73cq8LHC6y8EvSszvhDtfC84aAwWLPfvtE9UoTOe4ESXZbQirf21eLh08NwNBg_Ptf9ZYO8DCPDYUaV6JJ6uy8duMUa3HZPb47PvDqDg6dZxISnNJNJaLmIjYoFIdFEB77JCIQoIbJAioTOPuk4xSPTMY6SlLn_a1rGPI4kC9ahlQ9zuwHoa6ZEEgQq4CJUXKpQ2FBrX0hLoEyLNuw305e-VEQdaUXJzFI39ulk7Nuw3cxuWi_YImUxZzFBKZ-1gZXz-Esr6eX1aW9S2vxLpS2Yd8nrq3DCbWjRwNsdmNWv40Ex2q0F-RNn2PYt
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9tAEB7RgASX8mhRAxTmUImThbP2ru1jGoiISKwKAc3N2pchUnFQEiHBT-qv7KwfoZyQED5YXtu7a-3Mzn4az34D8INpP7LMJl5iY-OFKux40gju5YS9JfetCUqH280wStN4PE5-1dGEbi9MxQ-xdLi5mVHaazfBnUP65IU19H5mHYEpKzebiE-wGpIu8Rasnl72r4eNOeZ0OAzcIejukfqOG-ZGn528buH1yvQCN_8HreWq09_8gO_dgs815MRupSPbsGKLHVjvNZnevsDfm8nMbSPBkqHkmQAhEpTF0QBlYfDUhbgvnvAnrXcGpwU6Pg96Oa0CyOdY-SXoWZ3zh2rhoGGhMFjz3z7RPTKFzn-BEl2e0Iq59tFi98_tdDZZ3N3X_eWTogwkw2lOleiSevtdunDnX-G6f3bVO_fqHA6eZhETntJMJqHlIjYqFoRFEx34JicYooTIAykSOvtk5RSPTMc4UlLm_rBpGfM4kizYhVYxLew3QF8zJZIgUAEXoeJShcKGWvtCWoJlWrThuJFf9lBRdWQVKTPL3Nhny7Fvw0Ej3qyesvOMxZzFBKZ81gZWCvKNVrLR5Vm6LO29p9IRrJ9fjYbZcJBe7MOGS2VfBRceQIuEYL_Dmn5cTOazw1qr_wEoc_od
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT-MwEB7xEnBZHruIsjzmgMQpInViJzkCpaKiRAjx6C3yK2wlSFFbIcFP2l-54zzKclppRQ5RnMR25PGMP03G3wAcMu1HltnES2xsvFCFbU8awb2csLfkvjVB6XC770dpGg8GyXUdTej2wlT8EDOHm9OM0l47BbcvJj_-YA19HltHYMrKzSZiHhZDngjSzcXOTfeu35hjTofDwG2C7h5N30HD3Oiz488tfF6ZPuDm36C1XHW6a1_wvevwrYaceFLNkQ2Ys8UmrJw1md6-w-_74dhtI8GSoeSdACESlMWrHsrCYMeFuE_f8JTWO4OjAh2fB72cVgHkE6z8EvSszvlDtbDXsFAYrPlv3-gemULnv0CJLk9oxVz7avHk6XE0Hk5_Pdf95cOiDCTDUU6V6JJ6eyhduJMfcNc9vz278OocDp5mEROe0kwmoeUiNioWhEUTHfgmJxiihMgDKRI6-2TlFI9M2zhSUub-sGkZ8ziSLNiChWJU2G1AXzMlkiBQAReh4lKFwoZa-0JagmVatOCokV_2UlF1ZBUpM8vc2GezsW_BbiPerFbZScZizmICUz5rASsF-Y9Wsqub83RW2vmfSgewfN3pZv1eevkTVl0m-yq2cBcWSAZ2D5b063Q4Ge_Xk_oPu875mA
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Virtual+Analyzers+for+MI+and+Density+Based+on+Neural+Networks+Improved+through+an+Integrated+Strategy+Involving+a+Constructive+Algorithm+and+Definition+of+Initial+Weights&rft.jtitle=Macromolecular+reaction+engineering&rft.au=da+Silva%2C+Adilton+Lopes&rft.au=Fontes%2C+Cristiano+Hora&rft.au=Embiru%C3%A7u%2C+Marcelo&rft.date=2023-08-01&rft.issn=1862-832X&rft.eissn=1862-8338&rft.volume=17&rft.issue=4&rft_id=info:doi/10.1002%2Fmren.202200066&rft.externalDBID=n%2Fa&rft.externalDocID=10_1002_mren_202200066
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1862-832X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1862-832X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1862-832X&client=summon