Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process

Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based o...

Full description

Saved in:
Bibliographic Details
Published in:ACS omega Vol. 8; no. 6; pp. 5437 - 5450
Main Authors: Long, Jian, Chen, Yifan, Cao, Dengke, Chen, Pengyu, Yang, Minglei
Format: Journal Article
Language:English
Published: United States American Chemical Society 14.02.2023
ISSN:2470-1343, 2470-1343
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with R 2 > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.
AbstractList Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.
Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with R 2 > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.
Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with R 2 > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with R 2 > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.
Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven model. Therefore, this paper proposes a time lag process prediction model with multiple operation modes to solve the above problem. First, based on random forests, the relative importance of initial input variables in the SDA process on DAO yield and Conradson carbon residual are studied and features are selected according to the results. Then, the stack denoising autoencoder (SDAE) is used to reconstruct the data and obtain the nonlinear mapping information of hidden layers of SDAE and achieve feature dimension reduction. SDAE can improve clustering accuracy of fuzzy c-means, and the operation mode of SDA process is accurately divided. Long short-term memory (LSTM) is used to establish a multicondition LSTM model. Compared with the traditional LSTM model, the multicondition LSTM model has a higher prediction accuracy with R2 > 0.95. The sensitivity analyses of the properties of feed and operating conditions on DAO yield are consistent with the principle of two-phase countercurrent extraction in the SDA process. In addition, the benchmark test of the Tennessee Eastman process shows that the proposed method is also effective in the fault detection of other processes. Because the multicondition LSTM can predict the future process measurement data according to operating mode, it can better avoid the false alarm problem and predict the fault earlier.
Author Cao, Dengke
Long, Jian
Yang, Minglei
Chen, Pengyu
Chen, Yifan
AuthorAffiliation Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education
AuthorAffiliation_xml – name: Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education
Author_xml – sequence: 1
  givenname: Jian
  orcidid: 0000-0002-3221-309X
  surname: Long
  fullname: Long, Jian
– sequence: 2
  givenname: Yifan
  surname: Chen
  fullname: Chen, Yifan
– sequence: 3
  givenname: Dengke
  surname: Cao
  fullname: Cao, Dengke
– sequence: 4
  givenname: Pengyu
  surname: Chen
  fullname: Chen, Pengyu
– sequence: 5
  givenname: Minglei
  surname: Yang
  fullname: Yang, Minglei
  email: mlyang@ecust.edu.cn
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36816643$$D View this record in MEDLINE/PubMed
BookMark eNp9kctvEzEQxi1URB_0zgntkUNT_IrXviBBy0tKBFLLgZPltWcTF8cO9m4l_vs6TYJKpXLyyPP7vhl9c4wOYoqA0CuCzwmm5K2xJa1gYc6pxUJQ_gwdUd7iCWGcHTyoD9FpKTcYYyIklVS8QIdMSCIEZ0fo108PwTUmuuZ7TmvIg4dSS3DeDj7F5oMp4JpaDEto5mMYvE3R-fve7Op63syTg9D0Kd8TVyncQhyaSzBlvTQVj4uNs4VSXqLnvQkFTnfvCfrx6eP1xZfJ7NvnrxfvZxPDGRsmogMgQPvOtS3vKZ7yDshUWIkVV1gq7Jy0gCmmm5-O0X4qpFTKKGK7CrIT9G7rux67FThb98km6HX2K5P_6GS8_rcT_VIv0q1WijEiZTV4szPI6fcIZdArXyyEYCKksWjatqoGyyWr6OuHs_4O2SdcAbEFbE6lZOi19YPZxFdH-6AJ1ptr6v019e6aVYgfCffe_5GcbSW1o2_SmGON-Wn8DrmktFE
CitedBy_id crossref_primary_10_1016_j_ces_2024_120656
crossref_primary_10_1016_j_ces_2024_120733
crossref_primary_10_1016_j_aei_2023_102199
crossref_primary_10_1061_JOEEDU_EEENG_7445
crossref_primary_10_1016_j_measurement_2024_115371
Cites_doi 10.1007/s10489-022-03175-2
10.1016/j.cherd.2022.09.022
10.1021/acs.iecr.9b04737
10.1016/j.oceaneng.2022.111400
10.1002/prs.11609
10.1021/acs.iecr.8b04821
10.1021/acsomega.2c01108
10.1016/j.compchemeng.2020.107116
10.1016/j.jlp.2020.104343
10.1007/s11705-021-2083-5
10.1007/s10489-021-02696-6
10.1007/s00170-021-08109-9
10.1016/j.apenergy.2022.118936
10.1016/j.psep.2021.08.022
10.1016/j.neunet.2021.01.010
10.1016/j.datak.2022.102050
10.1016/j.cogsys.2019.01.011
10.1109/SGES51519.2020.00169
10.1021/ie2004169
10.1016/j.jrras.2022.01.015
10.1016/j.fuproc.2013.11.014
10.3182/20131218-3-IN-2045.00099
10.1016/j.jcou.2020.101206
10.1016/j.engappai.2020.104073
10.1016/j.chemolab.2022.104678
10.1109/TII.2022.3172902
10.1021/acsomega.2c03249
10.1021/acs.energyfuels.2c00195
10.1007/s10489-021-02518-9
10.1016/j.compchemeng.2021.107639
10.1021/acs.iecr.0c01236
10.1021/acs.iecr.1c04712
10.1021/acsomega.2c01747
10.1016/j.ins.2022.05.097
10.1016/j.jprocont.2021.12.011
10.1021/acs.iecr.6b01916
10.1016/j.cej.2014.07.037
10.1016/j.ijheatmasstransfer.2022.122628
10.1016/j.psep.2022.01.021
10.1021/ie202407u
10.1016/j.infrared.2021.103731
10.1021/ie202880w
10.1016/j.clet.2021.100187
ContentType Journal Article
Copyright 2023 The Authors. Published by American Chemical Society
2023 The Authors. Published by American Chemical Society.
2023 The Authors. Published by American Chemical Society 2023 The Authors
Copyright_xml – notice: 2023 The Authors. Published by American Chemical Society
– notice: 2023 The Authors. Published by American Chemical Society.
– notice: 2023 The Authors. Published by American Chemical Society 2023 The Authors
DBID N~.
AAYXX
CITATION
NPM
7X8
5PM
DOI 10.1021/acsomega.2c06624
DatabaseName American Chemical Society (ACS) Open Access
CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed

MEDLINE - Academic

Database_xml – sequence: 1
  dbid: N~.
  name: American Chemical Society (ACS) Open Access
  url: https://pubs.acs.org
  sourceTypes: Publisher
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Chemistry
EISSN 2470-1343
EndPage 5450
ExternalDocumentID PMC9933188
36816643
10_1021_acsomega_2c06624
c272284797
Genre Journal Article
GrantInformation_xml – fundername: ;
  grantid: NA
– fundername: ;
  grantid: 61973124
– fundername: ;
  grantid: 222202317006
– fundername: ;
  grantid: 2021YFE0112800
– fundername: ;
  grantid: 62073142
GroupedDBID 53G
ABFRP
ABUCX
ACS
ADBBV
AFEFF
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BCNDV
EBS
GROUPED_DOAJ
HYE
N~.
OK1
RPM
VF5
AAFWJ
AAHBH
AAYXX
ABBLG
ADUCK
AFPKN
CITATION
M~E
NPM
7X8
5PM
ID FETCH-LOGICAL-a433t-6bee1e2fbd774f2054be156c809490890dd8ce02028094b32f568899a91cb1563
IEDL.DBID N~.
ISICitedReferencesCount 6
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000928772100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2470-1343
IngestDate Tue Sep 30 17:16:22 EDT 2025
Wed Oct 01 14:57:29 EDT 2025
Mon Jul 21 05:54:25 EDT 2025
Sat Nov 29 02:39:06 EST 2025
Tue Nov 18 21:00:00 EST 2025
Thu Feb 16 05:45:47 EST 2023
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
License https://creativecommons.org/licenses/by-nc-nd/4.0
2023 The Authors. Published by American Chemical Society.
Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a433t-6bee1e2fbd774f2054be156c809490890dd8ce02028094b32f568899a91cb1563
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-3221-309X
OpenAccessLink http://dx.doi.org/10.1021/acsomega.2c06624
PMID 36816643
PQID 2779343483
PQPubID 23479
PageCount 14
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_9933188
proquest_miscellaneous_2779343483
pubmed_primary_36816643
crossref_citationtrail_10_1021_acsomega_2c06624
crossref_primary_10_1021_acsomega_2c06624
acs_journals_10_1021_acsomega_2c06624
PublicationCentury 2000
PublicationDate 2023-02-14
PublicationDateYYYYMMDD 2023-02-14
PublicationDate_xml – month: 02
  year: 2023
  text: 2023-02-14
  day: 14
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle ACS omega
PublicationTitleAlternate ACS Omega
PublicationYear 2023
Publisher American Chemical Society
Publisher_xml – name: American Chemical Society
References ref9/cit9
ref6/cit6
ref36/cit36
ref3/cit3
ref27/cit27
ref18/cit18
ref11/cit11
ref25/cit25
ref16/cit16
ref29/cit29
ref32/cit32
ref23/cit23
ref39/cit39
ref14/cit14
ref8/cit8
ref5/cit5
ref31/cit31
ref2/cit2
ref43/cit43
ref34/cit34
ref37/cit37
ref28/cit28
ref40/cit40
ref20/cit20
ref17/cit17
ref10/cit10
ref26/cit26
ref35/cit35
ref19/cit19
ref21/cit21
ref12/cit12
ref15/cit15
ref42/cit42
ref41/cit41
ref22/cit22
ref13/cit13
ref33/cit33
ref4/cit4
ref30/cit30
ref1/cit1
ref24/cit24
ref38/cit38
ref7/cit7
References_xml – ident: ref32/cit32
  doi: 10.1007/s10489-022-03175-2
– ident: ref12/cit12
  doi: 10.1016/j.cherd.2022.09.022
– ident: ref37/cit37
  doi: 10.1021/acs.iecr.9b04737
– ident: ref40/cit40
  doi: 10.1016/j.oceaneng.2022.111400
– ident: ref10/cit10
  doi: 10.1002/prs.11609
– ident: ref2/cit2
  doi: 10.1021/acs.iecr.8b04821
– ident: ref38/cit38
  doi: 10.1021/acsomega.2c01108
– ident: ref11/cit11
  doi: 10.1016/j.compchemeng.2020.107116
– ident: ref17/cit17
  doi: 10.1016/j.jlp.2020.104343
– ident: ref21/cit21
  doi: 10.1007/s11705-021-2083-5
– ident: ref39/cit39
  doi: 10.1007/s10489-021-02696-6
– ident: ref42/cit42
  doi: 10.1007/s00170-021-08109-9
– ident: ref43/cit43
  doi: 10.1016/j.apenergy.2022.118936
– ident: ref18/cit18
  doi: 10.1016/j.psep.2021.08.022
– ident: ref27/cit27
  doi: 10.1016/j.neunet.2021.01.010
– ident: ref28/cit28
  doi: 10.1016/j.datak.2022.102050
– ident: ref26/cit26
  doi: 10.1016/j.cogsys.2019.01.011
– ident: ref31/cit31
  doi: 10.1109/SGES51519.2020.00169
– ident: ref3/cit3
  doi: 10.1021/ie2004169
– ident: ref30/cit30
  doi: 10.1016/j.jrras.2022.01.015
– ident: ref19/cit19
  doi: 10.1016/j.fuproc.2013.11.014
– ident: ref13/cit13
  doi: 10.3182/20131218-3-IN-2045.00099
– ident: ref5/cit5
  doi: 10.1016/j.jcou.2020.101206
– ident: ref22/cit22
  doi: 10.1016/j.engappai.2020.104073
– ident: ref35/cit35
  doi: 10.1016/j.chemolab.2022.104678
– ident: ref25/cit25
  doi: 10.1109/TII.2022.3172902
– ident: ref41/cit41
  doi: 10.1021/acsomega.2c03249
– ident: ref1/cit1
  doi: 10.1021/acs.energyfuels.2c00195
– ident: ref36/cit36
  doi: 10.1007/s10489-021-02518-9
– ident: ref7/cit7
  doi: 10.1016/j.compchemeng.2021.107639
– ident: ref6/cit6
  doi: 10.1021/acs.iecr.0c01236
– ident: ref33/cit33
  doi: 10.1021/acs.iecr.1c04712
– ident: ref24/cit24
  doi: 10.1021/acsomega.2c01747
– ident: ref29/cit29
  doi: 10.1016/j.ins.2022.05.097
– ident: ref16/cit16
  doi: 10.1016/j.jprocont.2021.12.011
– ident: ref14/cit14
  doi: 10.1021/acs.iecr.6b01916
– ident: ref20/cit20
  doi: 10.1016/j.cej.2014.07.037
– ident: ref8/cit8
  doi: 10.1016/j.ijheatmasstransfer.2022.122628
– ident: ref34/cit34
  doi: 10.1016/j.psep.2022.01.021
– ident: ref4/cit4
  doi: 10.1021/ie202407u
– ident: ref23/cit23
  doi: 10.1016/j.infrared.2021.103731
– ident: ref9/cit9
  doi: 10.1021/ie202880w
– ident: ref15/cit15
  doi: 10.1016/j.clet.2021.100187
SSID ssj0001682826
Score 2.251654
Snippet Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven...
Solvent deasphalting (SDA) is a complex multiscale continuous process. The operation mode of the SDA process is not considered in the related data-driven...
SourceID pubmedcentral
proquest
pubmed
crossref
acs
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 5437
Title Yield and Properties Prediction Based on the Multicondition LSTM Model for the Solvent Deasphalting Process
URI http://dx.doi.org/10.1021/acsomega.2c06624
https://www.ncbi.nlm.nih.gov/pubmed/36816643
https://www.proquest.com/docview/2779343483
https://pubmed.ncbi.nlm.nih.gov/PMC9933188
Volume 8
WOSCitedRecordID wos000928772100001&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: PRVABC
  databaseName: American Chemical Society (ACS) Open Access
  customDbUrl:
  eissn: 2470-1343
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001682826
  issn: 2470-1343
  databaseCode: N~.
  dateStart: 20160731
  isFulltext: true
  titleUrlDefault: https://pubs.acs.org
  providerName: American Chemical Society
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2470-1343
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001682826
  issn: 2470-1343
  databaseCode: DOA
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 2470-1343
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001682826
  issn: 2470-1343
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwEB7xkuDC-1EelZHYA4dAYrtxeuSpPSwVEqxUTpFjO4AoKWoKR347M25aKLtCcIvisZV4xp5vPOMZgD2R55Yq7AV5nqlAokIImi7MaTMMlTKhFlb6YhOq1Ura7eble5qczx58Hh1qU3Yf3a0-4IaylctJmOaIckmCW68H7-cpMdoOvroalyoMIiFF5ZX83yCki0w5rov-AZif4yQ_KJ7zhZ988iLMV_CSHQ3kYQkmXLEMsyfDqm4r8HBDIWtMF5Zd0jl8jxKq4iP5a4hH7BjVmmX4gMiQ-eu5aDFbH9jF_lxdXzCqntZhiHU9xVW3QxGT7NTp8ol876gKWXX7YBX-np9dn_wOqoILgZZC9IM4cy5yPM8sgsKcI5rLHNp3JkEbkPyDobWJcQgwOb3JBM8bcYIGm25GJkNCsQZTRbdwG8CSrKHQdrG44g1aOEY3mrFziOWsQIRhZQ1-4Syl1YIpU-8L51E6nLq0mroaHA5ZlJoqazkVz-h80WN_1ONpkLHjC9rdIddT5AP5SnThus9lyhVuXFLIRNRgfSAFo9FETM5WiS1qTD5GBJSye7yluL_zqbsRDeImmmx-8--3YI7K21OUeCS3Yarfe3Y7MGNe-vdlrw6Tqp3U_SlC3S-GN2B7BUA
linkProvider American Chemical Society
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3JTsMwEB1BQYIL-1JWI8GBQyCJ3SQ9sgpEqSq1SHCKEtuBipKipnDk25lxk0IBIcTNcmzL8TZv_MYzALs8SRRF2LOSJPYtgQLBqmo7ocPQ9n1pR1wJE2zCr9eD29tqYwyc4i0MdiLDljJD4n94F3AOMa_7pO-jA1eS03IxDhMVTxhmtv528HGt4qEKYYKsucK3LYcLnpOTPzVCIklmoyLpG878ai75Sf6cz_6j53Mwk4NNdjRYHfMwptMFmDopYrwtwuMdGbCxKFWsQbfyPXKviklib2jG2DEKOcUwgTiRmce6qD8rY-bFas3WNaNYah2GyNeUaHY7ZD_JTnWUPRMTj4KR5W8RluDm_Kx1cmHl4ResSHDet7xYa0e7SawQIiYuYrtYo7YnA9QIiS20lQqkRrjpUk7M3aTiBai-RVVHxliQL0Mp7aZ6FVgQV3zUZBTuf4n6jowqVU9rRHaKI95Qogx7OEphvn2y0DDjrhMWQxfmQ1eGw2KmQpn7MKdQGp1fauwPazwP_Hf8UnanmPwQ54GYkyjV3ZcsdH08xgQXAS_DymAxDFvjHlGvAr_4I8tkWIAceI9-SdsPxpE3YkM8UoO1P_79NkxdtK5rYe2yfrUO0xT4nuzHHbEBpX7vRW_CpHztt7PeltkT72xKC8I
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LbxMxEB6lAbW9lEdbSMvDSHDgsMnu2vvIsU2IQIQoUoIUTqtdPyAibKJs0mN_e2ec3dAAqipulte2vPbY840_ewbgLTdGUYQ9x5gscgQqBKetXUOboRtF0k25EjbYRDQYxJNJe1iDoHoLg50osKXCkvi0qhfKlB4GvBbmz3_p72nTl-S4XOzBgyAUIQn24Lr5-2glRDPCBlrzReQ6Hhe8JCj_1QipJVnsqqW_sOafVyZv6aDeo__s_WM4KkEnu9hIyROo6fwpHHSqWG_H8PMbXWRjaa7YkE7nl-RmFZPE4tDMsUtUdophAvEis4920Y5W9roX64_GXxjFVJsxRMC2xGg-o3uUrKvTYkGMPCpIVr5JOIGvvQ_jzkenDMPgpILzlRNmWnvaN5lCqGh8xHiZRqtPxmgZEmvoKhVLjbDTp5yM-yYIYzTj0rYnMyzIT6Gez3P9HFicBRFaNAr3AYl2j0yDdqg1IjzFEXco0YB3OEpJuYyKxDLkvpdUQ5eUQ9eAVjVbiSx9mVNIjdkdNd5vayw2fjzuKPumEoAE54EYlDTX83WR-BFuZ4KLmDfg2UYgtq3xkChYgV-iHVHZFiBH3rtf8ukP69AbMSJurfHZPf_-NewPu72k_2nw-RwOcdyJiXc88QLqq-Vav4SH8mo1LZav7LK4AQlnDkU
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=Yield+and+Properties+Prediction+Based+on+the+Multicondition+LSTM+Model+for+the+Solvent+Deasphalting+Process&rft.jtitle=ACS+omega&rft.au=Long%2C+Jian&rft.au=Chen%2C+Yifan&rft.au=Cao%2C+Dengke&rft.au=Chen%2C+Pengyu&rft.date=2023-02-14&rft.pub=American+Chemical+Society&rft.eissn=2470-1343&rft.volume=8&rft.issue=6&rft.spage=5437&rft.epage=5450&rft_id=info:doi/10.1021%2Facsomega.2c06624&rft.externalDocID=PMC9933188
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2470-1343&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2470-1343&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2470-1343&client=summon