Deep Learning Model Predictive Control Frameworks: Application to a Fluid Catalytic Cracker–Fractionator Process
The present study proposes two model predictive control (MPC) frameworks that incorporate deep learning models: (i) deep learning MPC (implements only deep learning models) and (ii) hybrid MPC (implements deep learning and linear models, which provide improved model-based interpretability). The prop...
Saved in:
| Published in | Industrial & engineering chemistry research Vol. 62; no. 27; pp. 10587 - 10600 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
American Chemical Society
12.07.2023
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | The present study proposes two model predictive control (MPC) frameworks that incorporate deep learning models: (i) deep learning MPC (implements only deep learning models) and (ii) hybrid MPC (implements deep learning and linear models, which provide improved model-based interpretability). The proposed frameworks are successfully applied to a large-scale fluid catalytic cracker–fractionator process. The results demonstrate economic improvement (with respect to the current industrial MPC practice) under various disturbance scenarios. The solution time of the proposed frameworks is promising, particularly for hybrid MPC, which is expected to promote industrial implementation. |
|---|---|
| AbstractList | The present study proposes two model predictive control (MPC) frameworks that incorporate deep learning models: (i) deep learning MPC (implements only deep learning models) and (ii) hybrid MPC (implements deep learning and linear models, which provide improved model-based interpretability). The proposed frameworks are successfully applied to a large-scale fluid catalytic cracker–fractionator process. The results demonstrate economic improvement (with respect to the current industrial MPC practice) under various disturbance scenarios. The solution time of the proposed frameworks is promising, particularly for hybrid MPC, which is expected to promote industrial implementation. |
| Author | Harrison, Christopher A. Baldea, Michael Santander, Omar Kuppuraj, Vidyashankar |
| AuthorAffiliation | Marathon Petroleum Corporation McKetta Department of Chemical Engineering Oden Institute for Computational Engineering and Sciences |
| AuthorAffiliation_xml | – name: Oden Institute for Computational Engineering and Sciences – name: McKetta Department of Chemical Engineering – name: Marathon Petroleum Corporation |
| Author_xml | – sequence: 1 givenname: Omar surname: Santander fullname: Santander, Omar organization: McKetta Department of Chemical Engineering – sequence: 2 givenname: Vidyashankar surname: Kuppuraj fullname: Kuppuraj, Vidyashankar organization: Marathon Petroleum Corporation – sequence: 3 givenname: Christopher A. surname: Harrison fullname: Harrison, Christopher A. organization: Marathon Petroleum Corporation – sequence: 4 givenname: Michael orcidid: 0000-0001-6400-0315 surname: Baldea fullname: Baldea, Michael email: mbaldea@che.utexas.edu organization: Oden Institute for Computational Engineering and Sciences |
| BookMark | eNp1kLFOwzAQhi1UJNrCzugHIOWc2NhhqwIFpCIYYI5cx0Fu0zg6u6BuvANvyJOQqF1Z7ob7v1-nb0JGrW8tIZcMZgxSdq1NmDlrcJYZYIzBCRkzkUIigIsRGYNSKhFKiTMyCWENAEJwPiZ4Z21Hl1Zj69oP-uwr29BXtJUz0X1aWvg2om_oAvXWfnnchFs677rGGR2db2n0VNNFs3MVLXTUzT46QwvUZmPx9_unx8yQ09FjX-uNDeGcnNa6CfbiuKfkfXH_Vjwmy5eHp2K-THSqICbZDZe11CsuNTO2MkbyjHMmcwG5ZDlImaWyHyspdVZzriqmoM6YULbKV6zOpgQOvQZ9CGjrskO31bgvGZSDs7J3Vg7OyqOzHrk6IMNl7XfY9g_-H_8DAzFzfg |
| CitedBy_id | crossref_primary_10_1016_j_aej_2023_08_066 crossref_primary_10_1016_j_dche_2024_100161 crossref_primary_10_1021_acs_iecr_3c01835 |
| Cites_doi | 10.1016/j.compchemeng.2022.107900 10.23919/ACC.2017.7963782 10.1016/j.compchemeng.2020.106801 10.1002/aic.17436 10.1021/ie502271r 10.1007/978-0-85729-977-2 10.1073/pnas.1900654116 10.1021/acs.iecr.1c04251 10.1021/ie200743c 10.1016/j.compchemeng.2020.106834 10.1016/S0967-0661(02)00186-7 10.1016/S0255-2701(02)00017-X 10.1109/JSAC.2020.3036950 10.1021/acs.iecr.1c04339 10.1007/978-1-4842-4470-8_7 10.1016/j.compchemeng.2014.09.002 10.1021/acs.iecr.2c02715 10.1016/0098-1354(95)00030-5 10.1016/S1570-7946(00)80041-3 10.1016/j.cep.2004.08.008 10.1016/j.compchemeng.2019.04.003 10.1186/s40537-014-0007-7 10.1016/j.compchemeng.2019.106627 10.3390/math6110242 10.1016/j.ifacol.2018.11.038 10.1016/j.jprocont.2020.03.013 10.1016/j.compchemeng.2021.107360 10.1016/j.compchemeng.2017.10.008 10.1016/S0255-2701(02)00055-7 10.1016/j.compchemeng.2008.08.007 10.15607/RSS.2020.XVI.087 10.1016/j.jprocont.2014.03.010 10.1021/ie9603575 10.1016/S0098-1354(01)00756-6 10.1109/ICCUBEA.2018.8697857 10.1016/j.neucom.2020.07.061 10.1016/0005-1098(94)90230-5 10.1016/j.ifacol.2018.09.373 10.1016/j.compchemeng.2009.06.007 10.1109/TNNLS.2020.3015869 10.1002/aic.16734 10.1002/aic.690490213 10.1021/ie00036a022 |
| ContentType | Journal Article |
| Copyright | 2023 American Chemical Society |
| Copyright_xml | – notice: 2023 American Chemical Society |
| DBID | AAYXX CITATION |
| DOI | 10.1021/acs.iecr.3c01110 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1520-5045 |
| EndPage | 10600 |
| ExternalDocumentID | 10_1021_acs_iecr_3c01110 b644795615 |
| GroupedDBID | -~X .DC .K2 4.4 55A 5GY 5VS 6TJ 7~N AABXI ABFRP ABMVS ABPTK ABQRX ABUCX ACGFO ACJ ACS ADHLV AEESW AENEX AFEFF AGXLV AHGAQ ALMA_UNASSIGNED_HOLDINGS AQSVZ CS3 DU5 EBS ED~ F5P GGK GNL IH9 JG~ LG6 P2P ROL TAE TN5 UI2 VF5 VG9 W1F WH7 ~02 53G AAYXX BAANH CITATION CUPRZ |
| ID | FETCH-LOGICAL-a280t-3647f7ab47a1cedcc74344179509719077327773b77a3f448d180f3158ed9b1f3 |
| IEDL.DBID | ACS |
| ISSN | 0888-5885 |
| IngestDate | Fri Aug 23 02:14:29 EDT 2024 Fri Jul 14 08:04:35 EDT 2023 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 27 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a280t-3647f7ab47a1cedcc74344179509719077327773b77a3f448d180f3158ed9b1f3 |
| ORCID | 0000-0001-6400-0315 |
| PageCount | 14 |
| ParticipantIDs | crossref_primary_10_1021_acs_iecr_3c01110 acs_journals_10_1021_acs_iecr_3c01110 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-07-12 |
| PublicationDateYYYYMMDD | 2023-07-12 |
| PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-12 day: 12 |
| PublicationDecade | 2020 |
| PublicationTitle | Industrial & engineering chemistry research |
| PublicationTitleAlternate | Ind. Eng. Chem. Res |
| PublicationYear | 2023 |
| Publisher | American Chemical Society |
| Publisher_xml | – name: American Chemical Society |
| References | ref9/cit9 ref45/cit45 ref3/cit3 ref27/cit27 ref16/cit16 Liu T. (ref42/cit42) 2012 ref23/cit23 ref8/cit8 ref31/cit31 ref2/cit2 ref37/cit37 ref20/cit20 ref17/cit17 ref10/cit10 ref35/cit35 ref19/cit19 ref21/cit21 ref46/cit46 ref49/cit49 ref13/cit13 ref24/cit24 ref38/cit38 Rosenthal R. (ref48/cit48) 2008 ref6/cit6 ref36/cit36 ref18/cit18 ref11/cit11 ref25/cit25 ref29/cit29 ref32/cit32 ref39/cit39 ref14/cit14 ref5/cit5 ref43/cit43 ref28/cit28 ref40/cit40 Gulli A. (ref34/cit34) 2017 ref26/cit26 ref12/cit12 ref15/cit15 ref41/cit41 ref22/cit22 ref33/cit33 ref4/cit4 ref30/cit30 ref47/cit47 ref1/cit1 ref44/cit44 ref7/cit7 |
| References_xml | – ident: ref14/cit14 – volume-title: GAMS: A User’s Guide year: 2008 ident: ref48/cit48 contributor: fullname: Rosenthal R. – volume-title: Deep Learning with Keras year: 2017 ident: ref34/cit34 contributor: fullname: Gulli A. – ident: ref39/cit39 doi: 10.1016/j.compchemeng.2022.107900 – ident: ref40/cit40 doi: 10.23919/ACC.2017.7963782 – ident: ref36/cit36 – ident: ref22/cit22 doi: 10.1016/j.compchemeng.2020.106801 – ident: ref29/cit29 doi: 10.1002/aic.17436 – ident: ref12/cit12 doi: 10.1021/ie502271r – volume-title: Industrial Process Identification and Control Design: Step-Test and Relay-Experiment-Based Methods year: 2012 ident: ref42/cit42 doi: 10.1007/978-0-85729-977-2 contributor: fullname: Liu T. – ident: ref33/cit33 – ident: ref38/cit38 doi: 10.1073/pnas.1900654116 – ident: ref24/cit24 doi: 10.1021/acs.iecr.1c04251 – ident: ref13/cit13 doi: 10.1021/ie200743c – ident: ref47/cit47 doi: 10.1016/j.compchemeng.2020.106834 – ident: ref15/cit15 doi: 10.1016/S0967-0661(02)00186-7 – ident: ref9/cit9 doi: 10.1016/S0255-2701(02)00017-X – ident: ref46/cit46 doi: 10.1109/JSAC.2020.3036950 – ident: ref28/cit28 doi: 10.1021/acs.iecr.1c04339 – ident: ref35/cit35 doi: 10.1007/978-1-4842-4470-8_7 – ident: ref1/cit1 doi: 10.1016/j.compchemeng.2014.09.002 – ident: ref41/cit41 doi: 10.1021/acs.iecr.2c02715 – ident: ref7/cit7 doi: 10.1016/0098-1354(95)00030-5 – ident: ref30/cit30 doi: 10.1016/S1570-7946(00)80041-3 – ident: ref32/cit32 doi: 10.1016/j.cep.2004.08.008 – ident: ref17/cit17 doi: 10.1016/j.compchemeng.2019.04.003 – ident: ref18/cit18 doi: 10.1186/s40537-014-0007-7 – ident: ref2/cit2 doi: 10.1016/j.compchemeng.2019.106627 – ident: ref20/cit20 doi: 10.3390/math6110242 – ident: ref25/cit25 doi: 10.1016/j.ifacol.2018.11.038 – ident: ref37/cit37 doi: 10.1016/j.jprocont.2020.03.013 – ident: ref3/cit3 doi: 10.1016/j.compchemeng.2021.107360 – ident: ref16/cit16 doi: 10.1016/j.compchemeng.2017.10.008 – ident: ref8/cit8 doi: 10.1016/S0255-2701(02)00055-7 – ident: ref10/cit10 doi: 10.1016/j.compchemeng.2008.08.007 – ident: ref26/cit26 doi: 10.15607/RSS.2020.XVI.087 – ident: ref45/cit45 – ident: ref5/cit5 doi: 10.1016/j.jprocont.2014.03.010 – ident: ref11/cit11 doi: 10.1021/ie9603575 – ident: ref31/cit31 doi: 10.1016/S0098-1354(01)00756-6 – ident: ref19/cit19 doi: 10.1109/ICCUBEA.2018.8697857 – ident: ref43/cit43 doi: 10.1016/j.neucom.2020.07.061 – ident: ref44/cit44 doi: 10.1016/0005-1098(94)90230-5 – ident: ref27/cit27 doi: 10.1016/j.ifacol.2018.09.373 – ident: ref4/cit4 doi: 10.1016/j.compchemeng.2009.06.007 – ident: ref23/cit23 doi: 10.1109/TNNLS.2020.3015869 – ident: ref21/cit21 doi: 10.1002/aic.16734 – ident: ref49/cit49 doi: 10.1002/aic.690490213 – ident: ref6/cit6 doi: 10.1021/ie00036a022 |
| SSID | ssj0005544 |
| Score | 2.496079 |
| Snippet | The present study proposes two model predictive control (MPC) frameworks that incorporate deep learning models: (i) deep learning MPC (implements only deep... |
| SourceID | crossref acs |
| SourceType | Aggregation Database Publisher |
| StartPage | 10587 |
| SubjectTerms | Process Systems Engineering |
| Title | Deep Learning Model Predictive Control Frameworks: Application to a Fluid Catalytic Cracker–Fractionator Process |
| URI | http://dx.doi.org/10.1021/acs.iecr.3c01110 |
| Volume | 62 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NS8MwGA4yL3rwW5xf5KAHD61Lsq6Jt1EtQ1AEHexWkjSR4dhG2x305H_wH_pLzNt2bPgBXnooJS1pkvfreZ8HobNUSOEsm_JsKrjXtkR5ggHIkTtjKTqGcQv5jrv7Tq_fvh0EgwVNzvcKPiWXUuf-0LlQPtOgi-7C81UKAEJwg6LHBZwjKIVb3aaBTiIe1CXJ30YAQ6TzJUO0ZFHizUqaKC-JCAFI8uLPCuXrt580jf_42C20UTuWuFuthG20YsY7aH2JbnAXZdfGTHHNqPqMQQZthB8yKNXAoYejCraO4zlgK7_C3UWBGxcTLHE8mg1THEHW59W9CkeZBGTG5_tHnFVNEhDG47oBYQ_145unqOfVmguepLxVeEAnb0Op2qEk2qRaOw-jVCkLgGzKRdIho6G7qDCUzLrYLiW8ZRkJuEmFIpbto8Z4MjYHCIfUEKkVHCocWNykUIpyLZWljIlUNNG5m66k3jN5UpbDKUngJsxhUs9hE13Mf1QyrSg4_nz28J9jHqE10I2HJC2hx6hRZDNz4ryLQp2Wy-oLtMzKqg |
| link.rule.ids | 315,786,790,2782,27109,27957,27958,57093,57143 |
| linkProvider | American Chemical Society |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFG8IHtSD30b87EEPHoZ0Zaz1RqYLKhCjkHBb2q01RAJkGwc9-T_4H_qX2DeGEKOJXnZolreXt7bv-_cQOo244EazSUtHnFlVTaTFKRQ5MqMseU1RpiHe0WrXGt3qbc_pFRCZ9cIYJhJDKcmS-HN0AXIBa31jSZVpCOPRjZe-5LjGHQdryHucV3U42fxWc3agoYg5eWbyJwqgj8JkQR8tKBZ_HT18sZTVkzyXJ6ksh6_f0Br_xfMGWsvNTFyf7otNVFDDLbS6AD64jeIrpcY4x1d9wjAUbYDvY0jcwBWIvWkRO_Zn5VvJJa7P0904HWGB_cGkH2EPYkAv5lPYiwXUaXy8vfvxtGUCnHqctyPsoK5_3fEaVj6BwRI2q6QWgMtrV8iqK0ioojA09kY2s8wB6CnjV7vUds1Duq6g2nh6EWEVTYnDVMQl0XQXFYejodpD2LUVEaGEK4YBppvgUtosFFLblPKIl9CZEVeQn6AkyJLjNglgEWQY5DIsofPZ_wrGU0COX9_d_yPNE7Tc6LSaQfOmfXeAVmCiPIRviX2Iimk8UUfG7kjlcbbTPgHYcNMV |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA5jgujBb3F-5qAHD52mWdfE2-gs82sMdLJbSdpEhmMbbXfQk__Bf-gvMW_buSEKeukhlPQlTfJ-Pw9CxxEX3Gg2aemIM6umibQ4hSJHZpQlryvKNMQ77tr1Vrd23XN6JeRMe2GMEImZKcmS-HCqx5EuEAbIGYz3jTVVpSFQpBtPfcEB_m6wiLz7WWWHk3G4mvMDTUXMKbKTP80AOilM5nTSnHLxV9Hjl1hZTclzdZLKavj6DbHx33KvoZXC3MSNfH-so5IabqDlORDCTRQ3lRrjAmf1CQM52gB3YkjgwFWIvbyYHfvTMq7kAjdmaW-cjrDA_mDSj7AHsaAX8ynsxQLqNT7e3v04b50A5x4XbQlbqOtfPngtq2BisITNzlMLQOa1K2TNFSRUURgauyPjLnMAgsr41y61XfOQriuoNh5fRNi5psRhKuKSaLqNysPRUO0g7NqKiFDCVcMA201wKW0WCqltSnnEK-jELFdQnKQkyJLkNglgENYwKNawgk6n_ywY58Acv767-8c5j9Bip-kHt1ftmz20BMTyEMUl9j4qp_FEHRjzI5WH2Wb7BLQK1Y8 |
| 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=Deep+Learning+Model+Predictive+Control+Frameworks%3A+Application+to+a+Fluid+Catalytic+Cracker%E2%80%93Fractionator+Process&rft.jtitle=Industrial+%26+engineering+chemistry+research&rft.au=Santander%2C+Omar&rft.au=Kuppuraj%2C+Vidyashankar&rft.au=Harrison%2C+Christopher+A.&rft.au=Baldea%2C+Michael&rft.date=2023-07-12&rft.issn=0888-5885&rft.eissn=1520-5045&rft.volume=62&rft.issue=27&rft.spage=10587&rft.epage=10600&rft_id=info:doi/10.1021%2Facs.iecr.3c01110&rft.externalDBID=n%2Fa&rft.externalDocID=10_1021_acs_iecr_3c01110 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0888-5885&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0888-5885&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0888-5885&client=summon |