Comparing generative process synthesis approaches with superstructure optimization for the conception of supercritical CO2 Brayton cycles
In process synthesis, while heuristic-based approaches are most often used for proposing relevant alternatives (that must then be thoroughly analyzed), this strategy may not be the most efficient. When it comes to the search for innovative processes, prior domain knowledge may be scarce or may not e...
Uloženo v:
| Vydáno v: | Computers & chemical engineering Ročník 201; s. 109255 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.10.2025
|
| Témata: | |
| ISSN: | 0098-1354 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | In process synthesis, while heuristic-based approaches are most often used for proposing relevant alternatives (that must then be thoroughly analyzed), this strategy may not be the most efficient. When it comes to the search for innovative processes, prior domain knowledge may be scarce or may not effectively exploit the properties contributing to the process novelty. Generative synthesis approaches that can freely explore the search space and that do not rely on any previous knowledge, have been proposed in the literature. Yet, a lack of benchmarks on complex problems strongly hinders their use. In this work, we address this gap by comparing two generative approaches, based on Evolutionary Programming and Machine Learning, to a superstructure optimization (which serves as a baseline). They are applied to the synthesis of supercritical CO2 Brayton cycles. Despite starting with no field of expertise, the generative approaches not only manage to identify multiple known heuristics of the domain, but also a counter-intuitive and new way of increasing the efficiency of sCO2 cycles — by expanding the fluid at lower temperatures. The approaches’ use-cases are discussed, based on the amount of computational resources necessary, implementation difficulties and quality of the results.
[Display omitted]
•Two generative synthesis approaches are benchmarked for a complex problem.•Both approaches discover a new heuristic for increasing efficiency of sCO2 cycles.•Large volumes of data are generated, which can be useful for data mining and ML.•The evolutionary method found good cycles despite starting from an empty flowsheet.•A better fine-tuning strategy is developed for training the ML-based approach. |
|---|---|
| AbstractList | In process synthesis, while heuristic-based approaches are most often used for proposing relevant alternatives (that must then be thoroughly analyzed), this strategy may not be the most efficient. When it comes to the search for innovative processes, prior domain knowledge may be scarce or may not effectively exploit the properties contributing to the process novelty. Generative synthesis approaches that can freely explore the search space and that do not rely on any previous knowledge, have been proposed in the literature. Yet, a lack of benchmarks on complex problems strongly hinders their use. In this work, we address this gap by comparing two generative approaches, based on Evolutionary Programming and Machine Learning, to a superstructure optimization (which serves as a baseline). They are applied to the synthesis of supercritical CO2 Brayton cycles. Despite starting with no field of expertise, the generative approaches not only manage to identify multiple known heuristics of the domain, but also a counter-intuitive and new way of increasing the efficiency of sCO2 cycles — by expanding the fluid at lower temperatures. The approaches’ use-cases are discussed, based on the amount of computational resources necessary, implementation difficulties and quality of the results.
[Display omitted]
•Two generative synthesis approaches are benchmarked for a complex problem.•Both approaches discover a new heuristic for increasing efficiency of sCO2 cycles.•Large volumes of data are generated, which can be useful for data mining and ML.•The evolutionary method found good cycles despite starting from an empty flowsheet.•A better fine-tuning strategy is developed for training the ML-based approach. |
| ArticleNumber | 109255 |
| Author | Privat, Romain Neveux, Thibaut Loubière, Valentin Commenge, Jean-Marc Rocha Azevedo, Antonio Nabil, Tahar |
| Author_xml | – sequence: 1 givenname: Antonio orcidid: 0000-0002-0633-1252 surname: Rocha Azevedo fullname: Rocha Azevedo, Antonio email: antonio.rocha-azevedo@univ-lorraine.fr organization: Université de Lorraine, CNRS, LRGP, F-54000, Nancy, France – sequence: 2 givenname: Tahar orcidid: 0009-0004-3400-0997 surname: Nabil fullname: Nabil, Tahar organization: EDF R&D, Boulevard Gaspard Monge, F-91120, Palaiseau, France – sequence: 3 givenname: Valentin surname: Loubière fullname: Loubière, Valentin organization: EDF R&D Chatou, 6 quai Watier, 78400, Chatou, France – sequence: 4 givenname: Romain orcidid: 0000-0001-6174-9160 surname: Privat fullname: Privat, Romain organization: Université de Lorraine, CNRS, LRGP, F-54000, Nancy, France – sequence: 5 givenname: Thibaut orcidid: 0000-0002-7460-702X surname: Neveux fullname: Neveux, Thibaut organization: EDF R&D Chatou, 6 quai Watier, 78400, Chatou, France – sequence: 6 givenname: Jean-Marc orcidid: 0000-0003-2792-9357 surname: Commenge fullname: Commenge, Jean-Marc organization: Université de Lorraine, CNRS, LRGP, F-54000, Nancy, France |
| BookMark | eNqNkMtOwzAQRb0oEm3hH8wHpDjOg2QJES-pUjewtpzxpHXV2JHtFoU_4K9xCQuWrEa6o3M1cxZkZqxBQm5StkpZWt7uV2D7AXbYo9muOONFzGteFDMyZ6yukjQr8kuy8H7PGON5Vc3JVxMR6bTZ0i0adDLoE9LBWUDvqR9N2KHXnsohZjJ2e_qhw47644DOB3eEcHRI7RB0rz8jbQ3trKMRo2AN4PAT2W4iwOmgQR5os-H0wckxxCWMcEB_RS46efB4_TuX5P3p8a15Sdab59fmfp1AllYhkWWWAa-ykiuopMJSpZApJlXRFW1e10VZVkzxsmVdnWZ5Cwy5ZAq7umwrlHfZktRTLzjrvcNODE730o0iZeLsUezFH4_i7FFMHiPbTCzGA08anfCgMX6ptEMIQln9j5ZvRpGLeQ |
| Cites_doi | 10.1016/S0098-1354(03)00152-2 10.1016/j.coche.2024.101012 10.1016/j.applthermaleng.2020.116447 10.1016/B978-0-323-95879-0.50115-6 10.1016/j.compchemeng.2022.107676 10.1016/j.energy.2016.10.007 10.1016/j.apenergy.2017.02.048 10.1002/cite.201800091 10.1016/j.swevo.2018.03.011 10.1016/j.energy.2012.01.041 10.1007/s11705-021-2055-9 10.1007/s11081-023-09798-9 10.1002/aic.16443 10.1016/j.memsci.2018.08.024 10.1002/aic.11228 10.3390/en17051129 10.3389/fceng.2023.1144115 10.1002/aic.690310302 10.1016/j.ces.2018.04.015 10.1002/aic.17938 10.1016/j.compchemeng.2005.07.007 10.1016/j.compchemeng.2020.106808 10.1016/j.cep.2022.108885 10.1016/B978-0-323-85159-6.50048-8 10.3390/en16145470 10.1016/0098-1354(95)00219-7 10.1021/acssuschemeng.1c03362 10.1016/j.asr.2012.11.006 10.1021/acscentsci.7b00572 |
| ContentType | Journal Article |
| Copyright | 2025 The Authors |
| Copyright_xml | – notice: 2025 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.compchemeng.2025.109255 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| ExternalDocumentID | 10_1016_j_compchemeng_2025_109255 S0098135425002595 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6I. 7-5 71M 8P~ 9JN AABNK AAEDT AAEDW AAFTH AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYWO ABFNM ABJNI ABMAC ABNUV ABWVN ABXDB ACDAQ ACGFS ACNNM ACRLP ACRPL ACVFH ADBBV ADCNI ADEWK ADEZE ADMUD ADNMO ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFFNX AFJKZ AFPUW AFTJW AGCQF AGHFR AGQPQ AGUBO AGYEJ AHHHB AHJVU AHPOS AI. AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKURH AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP ASPBG AVWKF AXJTR AZFZN BBWZM BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS EJD ENUVR EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA HLY HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LX7 M41 MO0 N9A NDZJH O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCE SDF SDG SDP SES SEW SPC SPCBC SSG SST SSZ T5K VH1 WUQ ZY4 ~G- 9DU AAYXX ACLOT CITATION EFLBG ~HD |
| ID | FETCH-LOGICAL-c318t-a633c28362dc8ade6d1c3d0ad5f5b49956680d26b0f9134bc0e2a0def96b8ea73 |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001529471800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0098-1354 |
| IngestDate | Sat Nov 29 07:40:26 EST 2025 Sat Aug 16 17:02:12 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Process synthesis Evolutionary programming Artificial intelligence Superstructure |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c318t-a633c28362dc8ade6d1c3d0ad5f5b49956680d26b0f9134bc0e2a0def96b8ea73 |
| ORCID | 0000-0002-7460-702X 0000-0003-2792-9357 0000-0001-6174-9160 0009-0004-3400-0997 0000-0002-0633-1252 |
| OpenAccessLink | https://dx.doi.org/10.1016/j.compchemeng.2025.109255 |
| ParticipantIDs | crossref_primary_10_1016_j_compchemeng_2025_109255 elsevier_sciencedirect_doi_10_1016_j_compchemeng_2025_109255 |
| PublicationCentury | 2000 |
| PublicationDate | October 2025 2025-10-00 |
| PublicationDateYYYYMMDD | 2025-10-01 |
| PublicationDate_xml | – month: 10 year: 2025 text: October 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Computers & chemical engineering |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Stops, Leenhouts, Gao, Schweidtmann (b30) 2023; 69 Nabil, T., Le Moullec, Y., Le Coz, A., 2019. Machine Learning Based Design of a Supercritical CO2 Concentrating Solar Power Plant. In: 3rd European Supercritical CO2 Conference. Paris, France, pp. 148–157. Ahn, Bae, Kim, Cho, Baik, Lee, Cha (b1) 2014 Drugan (b5) 2019; 44 Ramírez-Santos, Bozorg, Addis, Piccialli, Castel, Favre (b26) 2018; 566 Davis, Ierapetritou (b3) 2007; 53 Nabil, Commenge, Neveux (b19) 2022; vol. 49 Wang, Lampe, Voll, Yang, Bardow (b34) 2016; 116 Crespi, Gavagnin, Sánchez, Martínez (b2) 2017; 195 Zheng, Chen, Zhang, Sahinidis, Siirola (b39) 2022; 159 URL Zhang, Sahinidis, Siirola (b36) 2019; 65 White, Bianchi, Chai, Tassou, Sayma (b35) 2021; 185 Khan, Lapkin (b11) 2022; 180 McBride, Sundmacher (b15) 2019; 91 Martinez-Hernandez (b14) 2022 Schlueter, Erb, Gerdts, Kemble, Ruckmann (b28) 2013; 51 Gao, Schweidtmann (b7) 2024; 44 Mencarelli, Chen, Pagot, Grossmann (b16) 2020; 136 Nabil, Noaman, Morosuk (b21) 2023; 5 Midgley (b17) 2020 Kraft (b12) 1988 Zhao, Mecheri, Neveux, Privat, Jaubert, Le Moullec (b38) 2023; 16 Göttl, Grimm, Burger (b10) 2022; 16 Neveux (b22) 2018; 185 Vogel, Hirtreiter, Schulze Balhorn, Schweidtmann (b32) 2023; 24 Molière, Privat, Jaubert, Geiger (b18) 2024; 17 Lemmon, Bell, Huber, McLinden (b13) 2018 Neveux, Addis, Castel, Piccialli, Favre (b23) 2022; vol. 51 Türkay, Grossmann (b31) 1996; 20 . Powell (b25) 1994 Zhao (b37) 2018 Douglas (b4) 1985; 31 Piña-Martinez, Lasala, Privat, Falk, Jaubert (b24) 2021; 9 Rocha Azevedo, Nabil, Loubière, Valentin, Privat, Neveux, Commenge (b27) 2024 Farkas, Rev, Lelkes (b6) 2005; 29 Voll, Lampe, Wrobel, Bardow (b33) 2012; 45 Gómez-Bombarelli, Wei, Duvenaud, Hernández-Lobato, Sánchez-Lengeling, Sheberla, Aguilera-Iparraguirre, Hirzel, Adams, Aspuru-Guzik (b9) 2018; 4 Gao, Yang, Shanbhag, Schweidtmann (b8) 2023 Siirola, Hauan, Westerberg (b29) 2003; 27 Khan (10.1016/j.compchemeng.2025.109255_b11) 2022; 180 Powell (10.1016/j.compchemeng.2025.109255_b25) 1994 Midgley (10.1016/j.compchemeng.2025.109255_b17) 2020 Nabil (10.1016/j.compchemeng.2025.109255_b19) 2022; vol. 49 Molière (10.1016/j.compchemeng.2025.109255_b18) 2024; 17 White (10.1016/j.compchemeng.2025.109255_b35) 2021; 185 Neveux (10.1016/j.compchemeng.2025.109255_b22) 2018; 185 Zhao (10.1016/j.compchemeng.2025.109255_b37) 2018 Zheng (10.1016/j.compchemeng.2025.109255_b39) 2022; 159 Kraft (10.1016/j.compchemeng.2025.109255_b12) 1988 Neveux (10.1016/j.compchemeng.2025.109255_b23) 2022; vol. 51 Nabil (10.1016/j.compchemeng.2025.109255_b21) 2023; 5 Gao (10.1016/j.compchemeng.2025.109255_b8) 2023 Siirola (10.1016/j.compchemeng.2025.109255_b29) 2003; 27 Vogel (10.1016/j.compchemeng.2025.109255_b32) 2023; 24 Göttl (10.1016/j.compchemeng.2025.109255_b10) 2022; 16 Türkay (10.1016/j.compchemeng.2025.109255_b31) 1996; 20 Zhang (10.1016/j.compchemeng.2025.109255_b36) 2019; 65 Lemmon (10.1016/j.compchemeng.2025.109255_b13) 2018 Gao (10.1016/j.compchemeng.2025.109255_b7) 2024; 44 Davis (10.1016/j.compchemeng.2025.109255_b3) 2007; 53 10.1016/j.compchemeng.2025.109255_b20 Mencarelli (10.1016/j.compchemeng.2025.109255_b16) 2020; 136 Ahn (10.1016/j.compchemeng.2025.109255_b1) 2014 Stops (10.1016/j.compchemeng.2025.109255_b30) 2023; 69 Gómez-Bombarelli (10.1016/j.compchemeng.2025.109255_b9) 2018; 4 Farkas (10.1016/j.compchemeng.2025.109255_b6) 2005; 29 Ramírez-Santos (10.1016/j.compchemeng.2025.109255_b26) 2018; 566 Schlueter (10.1016/j.compchemeng.2025.109255_b28) 2013; 51 Douglas (10.1016/j.compchemeng.2025.109255_b4) 1985; 31 Drugan (10.1016/j.compchemeng.2025.109255_b5) 2019; 44 Martinez-Hernandez (10.1016/j.compchemeng.2025.109255_b14) 2022 Voll (10.1016/j.compchemeng.2025.109255_b33) 2012; 45 Wang (10.1016/j.compchemeng.2025.109255_b34) 2016; 116 Piña-Martinez (10.1016/j.compchemeng.2025.109255_b24) 2021; 9 Rocha Azevedo (10.1016/j.compchemeng.2025.109255_b27) 2024 Crespi (10.1016/j.compchemeng.2025.109255_b2) 2017; 195 McBride (10.1016/j.compchemeng.2025.109255_b15) 2019; 91 Zhao (10.1016/j.compchemeng.2025.109255_b38) 2023; 16 |
| References_xml | – year: 1988 ident: b12 article-title: A Software Package for Sequential Quadratic Programming publication-title: Deutsche Forschungs- und Versuchsanstalt für Luft- und Raumfahrt Köln: Forschungsbericht – volume: 31 start-page: 353 year: 1985 end-page: 362 ident: b4 article-title: A hierarchical decision procedure for process synthesis publication-title: AIChE J. – year: 2023 ident: b8 article-title: Transfer learning for process design with reinforcement learning – volume: 51 start-page: 1116 year: 2013 end-page: 1131 ident: b28 article-title: MIDACO on MINLP space applications publication-title: Adv. Space Res. – volume: 185 year: 2021 ident: b35 article-title: Review of supercritical CO2 technologies and systems for power generation publication-title: Appl. Therm. Eng. – volume: 136 year: 2020 ident: b16 article-title: A review on superstructure optimization approaches in process system engineering publication-title: Comput. Chem. Eng. – year: 2022 ident: b14 article-title: Digitalisation of chemical processes as graphs and applications of modular decomposition to process design and analysis publication-title: Digit. Chem. Eng. – year: 2018 ident: b13 article-title: NIST standard reference database 23: Reference fluid thermodynamic and transport properties-REFPROP, version 10.0, national institute of standards and technology – volume: 91 start-page: 228 year: 2019 end-page: 239 ident: b15 article-title: Overview of surrogate modeling in chemical process engineering publication-title: Chem. Ing. Tech. – volume: 53 start-page: 2001 year: 2007 end-page: 2012 ident: b3 article-title: A kriging method for the solution of nonlinear programs with black-box functions publication-title: AIChE J. – volume: 69 year: 2023 ident: b30 article-title: Flowsheet generation through hierarchical reinforcement learning and graph neural networks publication-title: AIChE J. – volume: 24 start-page: 2911 year: 2023 end-page: 2933 ident: b32 article-title: SFILES 2.0: An extended text-based flowsheet representation publication-title: Optim. Eng. – volume: 29 start-page: 2180 year: 2005 end-page: 2197 ident: b6 article-title: Process flowsheet superstructures: Structural multiplicity and redundancy: Part I: Basic GDP and MINLP representations publication-title: Comput. Chem. Eng. – volume: 44 start-page: 228 year: 2019 end-page: 246 ident: b5 article-title: Reinforcement learning versus evolutionary computation: A survey on hybrid algorithms publication-title: Swarm Evol. Comput. – volume: 9 start-page: 11807 year: 2021 end-page: 11824 ident: b24 article-title: Design of promising working fluids for emergent combined cooling, heating, and power (CCHP) systems publication-title: ACS Sustain. Chem. Eng. – volume: 116 start-page: 1104 year: 2016 end-page: 1116 ident: b34 article-title: Multi-objective superstructure-free synthesis and optimization of thermal power plants publication-title: Energy – volume: 195 start-page: 152 year: 2017 end-page: 183 ident: b2 article-title: Supercritical carbon dioxide cycles for power generation: A review publication-title: Appl. Energy – volume: 180 year: 2022 ident: b11 article-title: Designing the process designer: Hierarchical reinforcement learning for optimisation-based process design publication-title: Chem. Eng. Process. - Process. Intensif. – volume: 17 start-page: 1129 year: 2024 ident: b18 article-title: Supercritical CO2 power technology: Strengths but challenges publication-title: Energies – volume: 5 year: 2023 ident: b21 article-title: Data-driven structural synthesis of supercritical CO2 power cycles publication-title: Front. Chem. Eng. – reference: , URL: – year: 2018 ident: b37 article-title: Conception and Optimization of Supercritical CO2 Brayton Cycles for Coal-Fired Power Plant Application – volume: 20 start-page: 959 year: 1996 end-page: 978 ident: b31 article-title: Logic-based MINLP algorithms for the optimal synthesis of process networks publication-title: Comput. Chem. Eng. – volume: 185 start-page: 209 year: 2018 end-page: 221 ident: b22 article-title: Ab-initio process synthesis using evolutionary programming publication-title: Chem. Eng. Sci. – volume: 27 start-page: 1801 year: 2003 end-page: 1811 ident: b29 article-title: Toward agent-based process systems engineering: Proposed framework and application to non-convex optimization publication-title: Comput. Chem. Eng. – reference: . – start-page: 372 year: 2024 end-page: 377 ident: b27 article-title: Representation learning for flowsheets: Generating structures for process synthesis publication-title: Book of Abstracts – volume: vol. 49 start-page: 289 year: 2022 end-page: 294 ident: b19 article-title: Generative approaches for the synthesis of process structures publication-title: Computer Aided Chemical Engineering – start-page: 51 year: 1994 end-page: 67 ident: b25 article-title: A direct search optimization method that models the objective and constraint functions by linear interpolation publication-title: Advances in Optimization and Numerical Analysis – volume: 16 start-page: 288 year: 2022 end-page: 302 ident: b10 article-title: Automated synthesis of steady-state continuous processes using reinforcement learning publication-title: Front. Chem. Sci. Eng. – volume: 159 year: 2022 ident: b39 article-title: Learning process patterns via multiple sequence alignment publication-title: Comput. Chem. Eng. – year: 2014 ident: b1 article-title: Cycle layout studies of S-CO2 cycle for the next generation nuclear system application publication-title: The Korean Nuclear Society Autumn Meeting (2014) – volume: 45 start-page: 424 year: 2012 end-page: 435 ident: b33 article-title: Superstructure-free synthesis and optimization of distributed industrial energy supply systems publication-title: Energy – volume: vol. 51 start-page: 685 year: 2022 end-page: 690 ident: b23 article-title: A comparison of process synthesis approaches for multistage separation processes by gas permeation publication-title: Computer Aided Chemical Engineering – volume: 44 year: 2024 ident: b7 article-title: Deep reinforcement learning for process design: Review and perspective publication-title: Curr. Opin. Chem. Eng. – volume: 566 start-page: 346 year: 2018 end-page: 366 ident: b26 article-title: Optimization of multistage membrane gas separation processes. Example of application to CO2 capture from blast furnace gas publication-title: J. Membr. Sci. – year: 2020 ident: b17 article-title: Deep reinforcement learning for process synthesis – reference: Nabil, T., Le Moullec, Y., Le Coz, A., 2019. Machine Learning Based Design of a Supercritical CO2 Concentrating Solar Power Plant. In: 3rd European Supercritical CO2 Conference. Paris, France, pp. 148–157. – volume: 65 start-page: 592 year: 2019 end-page: 603 ident: b36 article-title: Pattern recognition in chemical process flowsheets publication-title: AIChE J. – volume: 16 start-page: 5470 year: 2023 ident: b38 article-title: Search for the optimal design of a supercritical-CO2 brayton power cycle from a superstructure-based approach implemented in a commercial simulation software publication-title: Energies – volume: 4 start-page: 268 year: 2018 end-page: 276 ident: b9 article-title: Automatic chemical design using a data-driven continuous representation of molecules publication-title: ACS Central Sci. – volume: 27 start-page: 1801 issue: 12 year: 2003 ident: 10.1016/j.compchemeng.2025.109255_b29 article-title: Toward agent-based process systems engineering: Proposed framework and application to non-convex optimization publication-title: Comput. Chem. Eng. doi: 10.1016/S0098-1354(03)00152-2 – volume: 44 year: 2024 ident: 10.1016/j.compchemeng.2025.109255_b7 article-title: Deep reinforcement learning for process design: Review and perspective publication-title: Curr. Opin. Chem. Eng. doi: 10.1016/j.coche.2024.101012 – year: 2014 ident: 10.1016/j.compchemeng.2025.109255_b1 article-title: Cycle layout studies of S-CO2 cycle for the next generation nuclear system application – volume: 185 year: 2021 ident: 10.1016/j.compchemeng.2025.109255_b35 article-title: Review of supercritical CO2 technologies and systems for power generation publication-title: Appl. Therm. Eng. doi: 10.1016/j.applthermaleng.2020.116447 – ident: 10.1016/j.compchemeng.2025.109255_b20 – volume: vol. 51 start-page: 685 year: 2022 ident: 10.1016/j.compchemeng.2025.109255_b23 article-title: A comparison of process synthesis approaches for multistage separation processes by gas permeation doi: 10.1016/B978-0-323-95879-0.50115-6 – volume: 159 year: 2022 ident: 10.1016/j.compchemeng.2025.109255_b39 article-title: Learning process patterns via multiple sequence alignment publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2022.107676 – volume: 116 start-page: 1104 year: 2016 ident: 10.1016/j.compchemeng.2025.109255_b34 article-title: Multi-objective superstructure-free synthesis and optimization of thermal power plants publication-title: Energy doi: 10.1016/j.energy.2016.10.007 – volume: 195 start-page: 152 year: 2017 ident: 10.1016/j.compchemeng.2025.109255_b2 article-title: Supercritical carbon dioxide cycles for power generation: A review publication-title: Appl. Energy doi: 10.1016/j.apenergy.2017.02.048 – volume: 91 start-page: 228 issue: 3 year: 2019 ident: 10.1016/j.compchemeng.2025.109255_b15 article-title: Overview of surrogate modeling in chemical process engineering publication-title: Chem. Ing. Tech. doi: 10.1002/cite.201800091 – volume: 44 start-page: 228 year: 2019 ident: 10.1016/j.compchemeng.2025.109255_b5 article-title: Reinforcement learning versus evolutionary computation: A survey on hybrid algorithms publication-title: Swarm Evol. Comput. doi: 10.1016/j.swevo.2018.03.011 – volume: 45 start-page: 424 issue: 1 year: 2012 ident: 10.1016/j.compchemeng.2025.109255_b33 article-title: Superstructure-free synthesis and optimization of distributed industrial energy supply systems publication-title: Energy doi: 10.1016/j.energy.2012.01.041 – year: 2018 ident: 10.1016/j.compchemeng.2025.109255_b13 – volume: 16 start-page: 288 issue: 2 year: 2022 ident: 10.1016/j.compchemeng.2025.109255_b10 article-title: Automated synthesis of steady-state continuous processes using reinforcement learning publication-title: Front. Chem. Sci. Eng. doi: 10.1007/s11705-021-2055-9 – volume: 24 start-page: 2911 issue: 4 year: 2023 ident: 10.1016/j.compchemeng.2025.109255_b32 article-title: SFILES 2.0: An extended text-based flowsheet representation publication-title: Optim. Eng. doi: 10.1007/s11081-023-09798-9 – volume: 65 start-page: 592 issue: 2 year: 2019 ident: 10.1016/j.compchemeng.2025.109255_b36 article-title: Pattern recognition in chemical process flowsheets publication-title: AIChE J. doi: 10.1002/aic.16443 – year: 2022 ident: 10.1016/j.compchemeng.2025.109255_b14 article-title: Digitalisation of chemical processes as graphs and applications of modular decomposition to process design and analysis publication-title: Digit. Chem. Eng. – volume: 566 start-page: 346 year: 2018 ident: 10.1016/j.compchemeng.2025.109255_b26 article-title: Optimization of multistage membrane gas separation processes. Example of application to CO2 capture from blast furnace gas publication-title: J. Membr. Sci. doi: 10.1016/j.memsci.2018.08.024 – volume: 53 start-page: 2001 issue: 8 year: 2007 ident: 10.1016/j.compchemeng.2025.109255_b3 article-title: A kriging method for the solution of nonlinear programs with black-box functions publication-title: AIChE J. doi: 10.1002/aic.11228 – volume: 17 start-page: 1129 issue: 5 year: 2024 ident: 10.1016/j.compchemeng.2025.109255_b18 article-title: Supercritical CO2 power technology: Strengths but challenges publication-title: Energies doi: 10.3390/en17051129 – volume: 5 year: 2023 ident: 10.1016/j.compchemeng.2025.109255_b21 article-title: Data-driven structural synthesis of supercritical CO2 power cycles publication-title: Front. Chem. Eng. doi: 10.3389/fceng.2023.1144115 – volume: 31 start-page: 353 issue: 3 year: 1985 ident: 10.1016/j.compchemeng.2025.109255_b4 article-title: A hierarchical decision procedure for process synthesis publication-title: AIChE J. doi: 10.1002/aic.690310302 – volume: 185 start-page: 209 year: 2018 ident: 10.1016/j.compchemeng.2025.109255_b22 article-title: Ab-initio process synthesis using evolutionary programming publication-title: Chem. Eng. Sci. doi: 10.1016/j.ces.2018.04.015 – volume: 69 issue: 1 year: 2023 ident: 10.1016/j.compchemeng.2025.109255_b30 article-title: Flowsheet generation through hierarchical reinforcement learning and graph neural networks publication-title: AIChE J. doi: 10.1002/aic.17938 – volume: 29 start-page: 2180 issue: 10 year: 2005 ident: 10.1016/j.compchemeng.2025.109255_b6 article-title: Process flowsheet superstructures: Structural multiplicity and redundancy: Part I: Basic GDP and MINLP representations publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2005.07.007 – volume: 136 year: 2020 ident: 10.1016/j.compchemeng.2025.109255_b16 article-title: A review on superstructure optimization approaches in process system engineering publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2020.106808 – volume: 180 year: 2022 ident: 10.1016/j.compchemeng.2025.109255_b11 article-title: Designing the process designer: Hierarchical reinforcement learning for optimisation-based process design publication-title: Chem. Eng. Process. - Process. Intensif. doi: 10.1016/j.cep.2022.108885 – volume: vol. 49 start-page: 289 year: 2022 ident: 10.1016/j.compchemeng.2025.109255_b19 article-title: Generative approaches for the synthesis of process structures doi: 10.1016/B978-0-323-85159-6.50048-8 – start-page: 51 year: 1994 ident: 10.1016/j.compchemeng.2025.109255_b25 article-title: A direct search optimization method that models the objective and constraint functions by linear interpolation – year: 1988 ident: 10.1016/j.compchemeng.2025.109255_b12 article-title: A Software Package for Sequential Quadratic Programming – year: 2018 ident: 10.1016/j.compchemeng.2025.109255_b37 – volume: 16 start-page: 5470 issue: 14 year: 2023 ident: 10.1016/j.compchemeng.2025.109255_b38 article-title: Search for the optimal design of a supercritical-CO2 brayton power cycle from a superstructure-based approach implemented in a commercial simulation software publication-title: Energies doi: 10.3390/en16145470 – start-page: 372 year: 2024 ident: 10.1016/j.compchemeng.2025.109255_b27 article-title: Representation learning for flowsheets: Generating structures for process synthesis – volume: 20 start-page: 959 issue: 8 year: 1996 ident: 10.1016/j.compchemeng.2025.109255_b31 article-title: Logic-based MINLP algorithms for the optimal synthesis of process networks publication-title: Comput. Chem. Eng. doi: 10.1016/0098-1354(95)00219-7 – year: 2023 ident: 10.1016/j.compchemeng.2025.109255_b8 – volume: 9 start-page: 11807 issue: 35 year: 2021 ident: 10.1016/j.compchemeng.2025.109255_b24 article-title: Design of promising working fluids for emergent combined cooling, heating, and power (CCHP) systems publication-title: ACS Sustain. Chem. Eng. doi: 10.1021/acssuschemeng.1c03362 – volume: 51 start-page: 1116 issue: 7 year: 2013 ident: 10.1016/j.compchemeng.2025.109255_b28 article-title: MIDACO on MINLP space applications publication-title: Adv. Space Res. doi: 10.1016/j.asr.2012.11.006 – volume: 4 start-page: 268 issue: 2 year: 2018 ident: 10.1016/j.compchemeng.2025.109255_b9 article-title: Automatic chemical design using a data-driven continuous representation of molecules publication-title: ACS Central Sci. doi: 10.1021/acscentsci.7b00572 – year: 2020 ident: 10.1016/j.compchemeng.2025.109255_b17 |
| SSID | ssj0002488 |
| Score | 2.4715385 |
| Snippet | In process synthesis, while heuristic-based approaches are most often used for proposing relevant alternatives (that must then be thoroughly analyzed), this... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 109255 |
| SubjectTerms | Artificial intelligence Evolutionary programming Process synthesis Superstructure |
| Title | Comparing generative process synthesis approaches with superstructure optimization for the conception of supercritical CO2 Brayton cycles |
| URI | https://dx.doi.org/10.1016/j.compchemeng.2025.109255 |
| Volume | 201 |
| WOSCitedRecordID | wos001529471800001&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0098-1354 databaseCode: AIEXJ dateStart: 19950611 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0002488 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ta9RAEF7OVqR-KL5itcoKfpNIbnPZbMAvx1FRkVqwyn0L-xZ7xSah1x5t_0F_jP_RmexukvqCivglHMvNhuw8zM7szjxDyDOlxgo2ag2xiYEAxcQqkrGJo5znejIWUuSlaJtNZLu7Yj7P90ajr6EWZvUlqypxdpY3_1XVMAbKxtLZv1B3NykMwG9QOjxB7fD8I8XPXGfB6jN2R7ae2Ltx9QBIUAAeH5KQBDJxuwxp6g16gsgmi3cKNZiSI1-j2aUialfj6H3MVkKHVgmz9wyAIs-RpkOfY67d0O8NzSOWLdR0YCmwPRtif_OjD-Tz6YVdWVN7egOwO3V3ao2UwC3K5IHsMovf1adq0V76C3eo_knidrrooL93jG3cXC75kfTj_rSDpV3enD-CC2U4fc5Ta9ZzCIUTx0YdzDpzYj9sEe604hA13ODnwpe-wDchsRZzlMHfMXB_wPlxenAX4Y95eo2ssyzNwYiuT9_szN92Wz-bCBFIWlHgBnnaJxT-4oU_d4gGTs7-LbLpoxM6dai6TUa2ukNuDjgr75LLDl-0xxf1-KIdvmiPL4r4olfxRYf4ooAvCmK0xxetS3oFXxTwRT2-qMPXPfLx1c7-7HXk-3lEGnaOk0jyJNHgznJmtJDGcjPWiYmlSctUTbDEmovYMK7iEvNBlI4tA8Nhy5wrYWWW3CdrVV3ZB4TakpcQPFgMECdWZ8poqw2suOBGcqa2CAuLWjSOtqUI-YyHxUATBWqicJrYIi_D8hfe_3R-ZQHY-b34w38Tf0Q2esBvkzVQiH1MruvVyWJ5_MQj7RuYg7y0 |
| linkProvider | Elsevier |
| 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=Comparing+generative+process+synthesis+approaches+with+superstructure+optimization+for+the+conception+of+supercritical+CO2+Brayton+cycles&rft.jtitle=Computers+%26+chemical+engineering&rft.au=Rocha+Azevedo%2C+Antonio&rft.au=Nabil%2C+Tahar&rft.au=Loubi%C3%A8re%2C+Valentin&rft.au=Privat%2C+Romain&rft.date=2025-10-01&rft.pub=Elsevier+Ltd&rft.issn=0098-1354&rft.volume=201&rft_id=info:doi/10.1016%2Fj.compchemeng.2025.109255&rft.externalDocID=S0098135425002595 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0098-1354&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0098-1354&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0098-1354&client=summon |