Deep reinforcement learning enables conceptual design of processes for separating azeotropic mixtures without prior knowledge

Process synthesis in chemical engineering is a complex planning problem due to vast search spaces, continuous parameters and the need for generalization. Deep reinforcement learning agents, trained without prior knowledge, have shown to outperform humans in various complex planning problems in recen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers & chemical engineering Ročník 194; s. 108975
Hlavní autoři: Göttl, Quirin, Pirnay, Jonathan, Burger, Jakob, Grimm, Dominik G.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.03.2025
Témata:
ISSN:0098-1354
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Process synthesis in chemical engineering is a complex planning problem due to vast search spaces, continuous parameters and the need for generalization. Deep reinforcement learning agents, trained without prior knowledge, have shown to outperform humans in various complex planning problems in recent years. Existing work on reinforcement learning for flowsheet synthesis shows promising concepts. We further develop those concepts and present a general deep reinforcement learning approach for flowsheet synthesis. We demonstrate the adaptability of an agent to the general task of separating binary azeotropic mixtures. The agent is trained to set up the discrete process topology alongside choosing continuous specifications for the individual flowsheet elements (e.g., distillation columns and recycles). Without prior knowledge, it learns within one training cycle to craft flowsheets for multiple chemical systems, considering different feed compositions and conceptual approaches. The agent discovers autonomously fundamental process engineering paradigms as heteroazeotropic distillation or curved-boundary distillation. [Display omitted] •Reinforcement learning based automated process synthesis.•An agent that discovers classical process engineering schemes.•An agent that handles various flowsheet problems without retraining.
AbstractList Process synthesis in chemical engineering is a complex planning problem due to vast search spaces, continuous parameters and the need for generalization. Deep reinforcement learning agents, trained without prior knowledge, have shown to outperform humans in various complex planning problems in recent years. Existing work on reinforcement learning for flowsheet synthesis shows promising concepts. We further develop those concepts and present a general deep reinforcement learning approach for flowsheet synthesis. We demonstrate the adaptability of an agent to the general task of separating binary azeotropic mixtures. The agent is trained to set up the discrete process topology alongside choosing continuous specifications for the individual flowsheet elements (e.g., distillation columns and recycles). Without prior knowledge, it learns within one training cycle to craft flowsheets for multiple chemical systems, considering different feed compositions and conceptual approaches. The agent discovers autonomously fundamental process engineering paradigms as heteroazeotropic distillation or curved-boundary distillation. [Display omitted] •Reinforcement learning based automated process synthesis.•An agent that discovers classical process engineering schemes.•An agent that handles various flowsheet problems without retraining.
ArticleNumber 108975
Author Burger, Jakob
Grimm, Dominik G.
Göttl, Quirin
Pirnay, Jonathan
Author_xml – sequence: 1
  givenname: Quirin
  surname: Göttl
  fullname: Göttl, Quirin
  organization: Technical University of Munich, TUM Campus Straubing for Biotechnology and Sustainability, Laboratory of Chemical Process Engineering, Uferstraße 53, 94315 Straubing, Germany
– sequence: 2
  givenname: Jonathan
  surname: Pirnay
  fullname: Pirnay, Jonathan
  organization: Technical University of Munich, TUM Campus Straubing for Biotechnology and Sustainability, Bioinformatics, Petersgasse 18, 94315 Straubing, Germany
– sequence: 3
  givenname: Jakob
  surname: Burger
  fullname: Burger, Jakob
  email: burger@tum.de
  organization: Technical University of Munich, TUM Campus Straubing for Biotechnology and Sustainability, Laboratory of Chemical Process Engineering, Uferstraße 53, 94315 Straubing, Germany
– sequence: 4
  givenname: Dominik G.
  orcidid: 0000-0003-2085-4591
  surname: Grimm
  fullname: Grimm, Dominik G.
  email: dominik.grimm@hswt.de
  organization: Technical University of Munich, TUM Campus Straubing for Biotechnology and Sustainability, Bioinformatics, Petersgasse 18, 94315 Straubing, Germany
BookMark eNqNkMtKQzEQhrNQ0KrvEB-gNTnXZCVSr1Bwo-uQzJnTpp4mhyT1Br67KXUhrlwNzMz3M_NNyIHzDgk552zGGW8u1jPwmxFWuEG3nBWsqHJfyLY-IMeMSTHlZV0dkUmMa8byVIhj8nWNONKA1vU-wI5MdEAdnHVLik6bASMF7wDHtNUD7TDapaO-p2PwgDHmcSZpxFEHnXaU_kSfgh8t0I19T9uQV95sWvltypDNyy_Ovw3YLfGUHPZ6iHj2U0_I8-3N0_x-uni8e5hfLaZQiLaeGtlUUpccSlk1GgvTgqwkE03T1IUWom7BiLrsSqP7xnDJDTdtV6LUYGQBojwhcp8LwccYsFf5kI0OH4oztXOn1uqXO7Vzp_buMnv5hwWb8qfepaDt8K-E-T4B84uvFoOKYDEr7WxASKrz9h8p34Lhm8M
CitedBy_id crossref_primary_10_1016_j_cjche_2025_05_014
crossref_primary_10_1016_j_compchemeng_2025_109399
crossref_primary_10_1016_j_compchemeng_2025_109192
Cites_doi 10.1038/s41592-019-0686-2
10.1016/0098-1354(88)85045-2
10.1016/j.renene.2012.09.055
10.1016/j.cherd.2024.07.045
10.1016/B978-0-323-85159-6.50259-1
10.1007/BF02698263
10.1021/acs.iecr.3c01269
10.1016/j.cep.2022.108885
10.1146/annurev-chembioeng-080615-033546
10.1002/cite.201800091
10.1021/acs.jcim.9b00237
10.1038/s41586-022-05172-4
10.1002/cite.202100083
10.1002/cite.202100086
10.1016/j.ces.2012.08.018
10.1021/acs.iecr.0c04555
10.1038/s41586-023-06004-9
10.1016/j.compchemeng.2003.09.029
10.1016/j.compchemeng.2020.107027
10.1021/acscentsci.7b00492
10.1016/j.fluid.2012.04.002
10.1021/acs.iecr.3c03575
10.1016/j.compchemeng.2017.10.008
10.1021/ie950450d
10.1038/s42256-020-00284-w
10.1021/ef8004064
10.1038/s42256-022-00580-7
10.1016/j.eng.2021.03.019
10.1021/i160039a003
10.1021/acs.iecr.8b03125
10.1016/j.compchemeng.2023.108321
10.1016/S0098-1354(99)00003-4
10.1002/aic.17938
10.1021/acs.iecr.5b01671
10.1016/B978-0-323-88506-5.50034-6
10.1038/nature24270
10.1016/j.compchemeng.2021.107252
10.1016/j.ces.2011.05.049
10.1126/science.aar6404
10.1039/C8SC04228D
10.1016/0098-1354(89)85019-7
10.1002/aic.12677
10.1016/j.compchemeng.2022.108097
10.1002/1521-4125(20020910)25:9<869::AID-CEAT869>3.0.CO;2-9
10.1007/s11705-021-2055-9
10.1016/0098-1354(83)80013-1
10.1016/j.compchemeng.2019.04.028
10.1016/B978-0-443-15274-0.50319-X
10.1002/aic.690440616
ContentType Journal Article
Copyright 2024 The Authors
Copyright_xml – notice: 2024 The Authors
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.compchemeng.2024.108975
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_compchemeng_2024_108975
S0098135424003934
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6I.
7-5
71M
8P~
9DU
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
ACLOT
ACNNM
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEWK
ADEZE
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFFNX
AFJKZ
AFPUW
AFTJW
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
EFLBG
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-
ROL
RPZ
SBC
SCE
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSG
SST
SSZ
T5K
VH1
WUQ
ZY4
~G-
~HD
AAYXX
CITATION
ID FETCH-LOGICAL-c2875-b9649a31c3946ae2b7c9490866652a8857cb853d3baf6b191b1b7d3e9acb92c83
ISSN 0098-1354
IngestDate Sat Nov 29 06:56:44 EST 2025
Tue Nov 18 21:08:22 EST 2025
Sat Nov 29 17:08:52 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Automated process synthesis
Conceptual design
Process simulation
Reinforcement learning
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c2875-b9649a31c3946ae2b7c9490866652a8857cb853d3baf6b191b1b7d3e9acb92c83
ORCID 0000-0003-2085-4591
OpenAccessLink https://dx.doi.org/10.1016/j.compchemeng.2024.108975
ParticipantIDs crossref_primary_10_1016_j_compchemeng_2024_108975
crossref_citationtrail_10_1016_j_compchemeng_2024_108975
elsevier_sciencedirect_doi_10_1016_j_compchemeng_2024_108975
PublicationCentury 2000
PublicationDate March 2025
2025-03-00
PublicationDateYYYYMMDD 2025-03-01
PublicationDate_xml – month: 03
  year: 2025
  text: March 2025
PublicationDecade 2020
PublicationTitle Computers & chemical engineering
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Danihelka, I., Guez, A., Schrittwieser, J., Silver, D., 2022. Policy improvement by planning with gumbel. In: ICLR.
Kunnakorn, Rirksomboon, Siemanond, Aungkavattana, Kuanchertchoo, Chuntanalerg, Hemra, Kulprathipanja, James, Wongkasemjit (b26) 2013; 51
Ryll, Blagov, Hasse (b44) 2012; 84
Venkatasubramanian (b63) 2018; 65
Chen, Li, Chen, Chien (b5) 2015; 54
Stephanopoulos, Reklaitis (b55) 2011; 66
Rooks, Julka, Doherty, Malone (b40) 1998; 44
Biegler, Grossmann, Westerberg (b3) 1997
Mankowitz, Michi, Zhernov, Gelmi, Selvi, Paduraru, Leurent, Iqbal, Lespiau, Ahern, Köppe, Millikin, Gaffney, Elster, Broshear, Gamble, Milan, Tung, Hwang, Cemgil, Barekatain, Li, Mandhane, Hubert, Schrittwieser, Hassabis, Kohli, Riedmiller, Vinyals, Silver (b30) 2023; 618
Bekiaris, Morari (b2) 1996; 35
Seidenberg, Khan, Lapkin (b51) 2023; 169
Gani, O’Connell (b11) 1989; 13
Sargent (b45) 1983; 7
Ryll, Blagov, Hasse (b43) 2012; 324
Silver, Schrittwieser, Simonyan, Antonoglou, Huang, Guez, Hubert, Baker, Lai, Bolton, Chen, Lillicrap, Hui, Sifre, Driessche, Graepel, Hassabis (b54) 2017; 550
Van Hasselt, Guez, Hessel, Mnih, Silver (b61) 2016
Mencarelli, Chen, Pagot, Grossmann (b32) 2020; 136
Sasi, Kruber, Ascani, Skiborowski (b46) 2020; vol. 48
He, Hooi, Laurent, Perold, LeCun, Bresson (b20) 2023
Schwaller, Probst, Vaucher, Nair, Kreutter, Laino, Reymond (b49) 2021; 3
Grossmann, Caballero, Yeomans (b18) 1999; 16
Petlyuk (b35) 2004
Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b62) 2017
Ross, Belgodere, Chenthamarakshan, Padhi, Mroueh, Das (b41) 2022; 4
Schulman, Wolski, Dhariwal, Radford, Klimov (b48) 2017
Sasi, Skiborowski (b47) 2020; 59
Pohlen, Piot, Hester, Azar, Horgan, Budden, Barth-Maron, Van Hasselt, Quan, Večerík, Hessel, Munos, Pietquin (b38) 2018
Aspen, ., Aspen Plus 8.8, Aspen Technology Inc.
Virtanen, Gommers, Oliphant, Haberland, Reddy, Cournapeau, Burovski, Peterson, Weckesser, Bright, Walt, Brett, Wilson, Millman, Mayorov, Nelson, Jones, Kern, Larson, Carey, Polat, Feng, Moore, Plas, Laxalde, Perktold, Cimrman, Henriksen, Quintero, Harris, Archibald, Ribeiro, Pedregosa, Mulbregt, SciPy 1.0 Contributors (b64) 2020; 17
Yang, Dong, Grossmann (b69) 2012; 58
Ryll (b42) 2009
Towler, Sinnott (b60) 2022
Lee, Shin, Realff (b27) 2018; 114
Göttl, Grimm, Burger (b13) 2021; 50
Meng, Wang, Bai, Dong, Du (b33) 2024; 63
Hubert, T., Schrittwieser, J., Antonoglou, I., Barekatain, M., Schmitt, S., Silver, D., 2021. Learning and planning in complex action spaces. In: ICML.
Silver, Hubert, Schrittwieser, Antonoglou, Lai, Guez, Lanctot, Sifre, Kumaran, Graepel, Lillicrap, Simonyan, Hassabis (b53) 2018; 362
Stops, Leenhouts, Gao, Schweidtmann (b56) 2023; 69
Pirnay, J., Göttl, Q., Burger, J., Grimm, D., 2023. Policy-Based Self-Competition for Planning Problems. In: International Conference on Learning Representations.
Fawzi, Balog, Huang, Hubert, Romera-Paredes, Barekatain, Novikov, Ruiz, Schrittwieser, Swirszcz, Silver, Hassabis, Kohli (b10) 2022; 610
Khan, Lapkin (b23) 2022; 180
Dobbelaere, Plehiers, Van de Vijver, Stevens, Van Geem (b9) 2021; 7
Khan, Lapkin (b22) 2020; 141
DDBST (b8) 2023
Sutton, Barto (b57) 2018
Pistikopoulos, Barbosa-Povoa, Misener, Mitsos, Reklaitis, Venkatasubramanian, You, Gani (b37) 2021; 147
Westerberg (b68) 2004; 28
Krey, Owen (b25) 2007
Wang, Guzman-Urbina, Wu, Ohno, Fukushima (b67) 2024; 209
Midgley (b34) 2020
McBride, Sundmacher (b31) 2019; 91
Taifan, Maravelias (b58) 2023; 62
Luyben (b29) 2008; 22
Coley, Jin, Rogers, Jamison, Jaakkola, Green, Barzilay, Jensen (b6) 2019; 10
Linstrom, Mallard (b28) 2023
Yang, Swanson, Jin, Coley, Eiden, Gao, Guzman-Perez, Hopper, Kelley, Mathea, Palmer, Settels, Jaakkola, Jensen, Barzilay (b70) 2019; 59
Yeomans, Grossmann (b71) 1999; 23
Chen, Grossmann (b4) 2017; 7
Gao, Yang, Shanbhag, Schweidtmann (b12) 2023; 52
Schweidtmann, Esche, Fischer, Kloft, Repke, Sager, Mitsos (b50) 2021; 93
Tolstikhin, Houlsby, Kolesnikov, Beyer, Zhai, Unterthiner, Yung, Steiner, Keysers, Uszkoreit, Lucic, Dosovitskiy (b59) 2021; vol. 34
Prausnitz, Lichtenthaler, Azevedo (b39) 1999
Göttl, Tönges, Grimm, Burger (b17) 2021; 93
Göttl, Grimm, Burger (b14) 2022; 16
Grossmann, Harjunkoski (b19) 2019; 126
Wang, Chien (b66) 2018; 57
Zhou, Li, Zare (b72) 2017; 3
Göttl, Pirnay, Grimm, Burger (b16) 2023; 177
Kirkwood, Locke, Douglas (b24) 1988; 12
Vogelpohl (b65) 2002; 25
Siirola, Rudd (b52) 1971; 10
Göttl, Grimm, Burger (b15) 2022; 49
Schwaller (10.1016/j.compchemeng.2024.108975_b49) 2021; 3
Meng (10.1016/j.compchemeng.2024.108975_b33) 2024; 63
Schulman (10.1016/j.compchemeng.2024.108975_b48) 2017
Petlyuk (10.1016/j.compchemeng.2024.108975_b35) 2004
Göttl (10.1016/j.compchemeng.2024.108975_b13) 2021; 50
Chen (10.1016/j.compchemeng.2024.108975_b5) 2015; 54
Grossmann (10.1016/j.compchemeng.2024.108975_b18) 1999; 16
Stops (10.1016/j.compchemeng.2024.108975_b56) 2023; 69
Wang (10.1016/j.compchemeng.2024.108975_b66) 2018; 57
Yeomans (10.1016/j.compchemeng.2024.108975_b71) 1999; 23
Ryll (10.1016/j.compchemeng.2024.108975_b42) 2009
Chen (10.1016/j.compchemeng.2024.108975_b4) 2017; 7
Ross (10.1016/j.compchemeng.2024.108975_b41) 2022; 4
Westerberg (10.1016/j.compchemeng.2024.108975_b68) 2004; 28
Yang (10.1016/j.compchemeng.2024.108975_b70) 2019; 59
Biegler (10.1016/j.compchemeng.2024.108975_b3) 1997
DDBST (10.1016/j.compchemeng.2024.108975_b8) 2023
Tolstikhin (10.1016/j.compchemeng.2024.108975_b59) 2021; vol. 34
Linstrom (10.1016/j.compchemeng.2024.108975_b28) 2023
Kirkwood (10.1016/j.compchemeng.2024.108975_b24) 1988; 12
Kunnakorn (10.1016/j.compchemeng.2024.108975_b26) 2013; 51
Vaswani (10.1016/j.compchemeng.2024.108975_b62) 2017
Sargent (10.1016/j.compchemeng.2024.108975_b45) 1983; 7
Schweidtmann (10.1016/j.compchemeng.2024.108975_b50) 2021; 93
Van Hasselt (10.1016/j.compchemeng.2024.108975_b61) 2016
Rooks (10.1016/j.compchemeng.2024.108975_b40) 1998; 44
Göttl (10.1016/j.compchemeng.2024.108975_b14) 2022; 16
Luyben (10.1016/j.compchemeng.2024.108975_b29) 2008; 22
Towler (10.1016/j.compchemeng.2024.108975_b60) 2022
Göttl (10.1016/j.compchemeng.2024.108975_b15) 2022; 49
Mencarelli (10.1016/j.compchemeng.2024.108975_b32) 2020; 136
Fawzi (10.1016/j.compchemeng.2024.108975_b10) 2022; 610
Gao (10.1016/j.compchemeng.2024.108975_b12) 2023; 52
Khan (10.1016/j.compchemeng.2024.108975_b23) 2022; 180
Yang (10.1016/j.compchemeng.2024.108975_b69) 2012; 58
Silver (10.1016/j.compchemeng.2024.108975_b54) 2017; 550
Khan (10.1016/j.compchemeng.2024.108975_b22) 2020; 141
Siirola (10.1016/j.compchemeng.2024.108975_b52) 1971; 10
Zhou (10.1016/j.compchemeng.2024.108975_b72) 2017; 3
Ryll (10.1016/j.compchemeng.2024.108975_b43) 2012; 324
10.1016/j.compchemeng.2024.108975_b7
Virtanen (10.1016/j.compchemeng.2024.108975_b64) 2020; 17
Sasi (10.1016/j.compchemeng.2024.108975_b47) 2020; 59
Pistikopoulos (10.1016/j.compchemeng.2024.108975_b37) 2021; 147
10.1016/j.compchemeng.2024.108975_b1
Grossmann (10.1016/j.compchemeng.2024.108975_b19) 2019; 126
Mankowitz (10.1016/j.compchemeng.2024.108975_b30) 2023; 618
Venkatasubramanian (10.1016/j.compchemeng.2024.108975_b63) 2018; 65
10.1016/j.compchemeng.2024.108975_b36
Vogelpohl (10.1016/j.compchemeng.2024.108975_b65) 2002; 25
Wang (10.1016/j.compchemeng.2024.108975_b67) 2024; 209
Bekiaris (10.1016/j.compchemeng.2024.108975_b2) 1996; 35
Seidenberg (10.1016/j.compchemeng.2024.108975_b51) 2023; 169
Ryll (10.1016/j.compchemeng.2024.108975_b44) 2012; 84
Krey (10.1016/j.compchemeng.2024.108975_b25) 2007
Taifan (10.1016/j.compchemeng.2024.108975_b58) 2023; 62
Prausnitz (10.1016/j.compchemeng.2024.108975_b39) 1999
Silver (10.1016/j.compchemeng.2024.108975_b53) 2018; 362
Coley (10.1016/j.compchemeng.2024.108975_b6) 2019; 10
Gani (10.1016/j.compchemeng.2024.108975_b11) 1989; 13
Midgley (10.1016/j.compchemeng.2024.108975_b34) 2020
Sutton (10.1016/j.compchemeng.2024.108975_b57) 2018
Stephanopoulos (10.1016/j.compchemeng.2024.108975_b55) 2011; 66
Göttl (10.1016/j.compchemeng.2024.108975_b16) 2023; 177
He (10.1016/j.compchemeng.2024.108975_b20) 2023
Sasi (10.1016/j.compchemeng.2024.108975_b46) 2020; vol. 48
Göttl (10.1016/j.compchemeng.2024.108975_b17) 2021; 93
Lee (10.1016/j.compchemeng.2024.108975_b27) 2018; 114
McBride (10.1016/j.compchemeng.2024.108975_b31) 2019; 91
10.1016/j.compchemeng.2024.108975_b21
Dobbelaere (10.1016/j.compchemeng.2024.108975_b9) 2021; 7
Pohlen (10.1016/j.compchemeng.2024.108975_b38) 2018
References_xml – volume: 91
  start-page: 1
  year: 2019
  end-page: 13
  ident: b31
  article-title: Overview of surrogate modeling in chemical process engineering
  publication-title: Chem. Ing. Tech.
– volume: 362
  start-page: 1140
  year: 2018
  end-page: 1144
  ident: b53
  article-title: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play
  publication-title: Science
– volume: 59
  start-page: 20816
  year: 2020
  end-page: 20835
  ident: b47
  article-title: Automatic synthesis of distillation processes for the separation of homogeneous azeotropic multicomponent systems
  publication-title: Ind. Eng. Chem. Res.
– reference: Danihelka, I., Guez, A., Schrittwieser, J., Silver, D., 2022. Policy improvement by planning with gumbel. In: ICLR.
– volume: 147
  year: 2021
  ident: b37
  article-title: Process systems engineering - The generation next?
  publication-title: Comput. Chem. Eng.
– volume: 50
  start-page: 209
  year: 2021
  end-page: 214
  ident: b13
  article-title: Automated process synthesis using reinforcement learning
  publication-title: Comput. Aided Chem. Eng.
– year: 2020
  ident: b34
  article-title: Deep reinforcement learning for process synthesis
– volume: 65
  year: 2018
  ident: b63
  article-title: The promise of artificial intelligence in chemical engineering: Is it here, finally?
  publication-title: AIChE J.
– volume: 16
  start-page: 288
  year: 2022
  end-page: 302
  ident: b14
  article-title: Automated synthesis of steady-state continuous processes using reinforcement learning
  publication-title: Front. Chem. Sci. Eng.
– year: 2007
  ident: b25
  article-title: Basic Theoretical Physics
– year: 2018
  ident: b57
  article-title: Reinforcement Learning: An Introduction
– volume: 126
  start-page: 474
  year: 2019
  end-page: 484
  ident: b19
  article-title: Process systems engineering: Academic and industrial perspectives
  publication-title: Comput. Chem. Eng.
– year: 2018
  ident: b38
  article-title: Observe and look further: Achieving consistent performance on atari
– volume: 10
  start-page: 370
  year: 2019
  end-page: 377
  ident: b6
  article-title: A graph-convolutional neural network model for the prediction of chemical reactivity
  publication-title: Chem. Sci.
– volume: 10
  start-page: 353
  year: 1971
  end-page: 362
  ident: b52
  article-title: Computer-aided synthesis of chemical process designs. From reaction path data to the process task network
  publication-title: Ind. Eng. Chem. Fundamen.
– volume: 69
  start-page: 17938
  year: 2023
  ident: b56
  article-title: Flowsheet generation through hierarchical reinforcement learning and graph neural networks
  publication-title: AIChE J.
– volume: 3
  start-page: 1337
  year: 2017
  end-page: 1344
  ident: b72
  article-title: Optimizing chemical reactions with deep reinforcement learning
  publication-title: ACS Cent. Sci.
– year: 2004
  ident: b35
  article-title: Distillation Theory and Its Application to Optimal Design of Separation Units
– volume: 136
  year: 2020
  ident: b32
  article-title: A review on superstructure optimization approaches in process system engineering
  publication-title: Comput. Chem. Eng.
– reference: Hubert, T., Schrittwieser, J., Antonoglou, I., Barekatain, M., Schmitt, S., Silver, D., 2021. Learning and planning in complex action spaces. In: ICML.
– volume: 93
  start-page: 2029
  year: 2021
  end-page: 2039
  ident: b50
  article-title: Machine learning in chemical engineering: A perspective
  publication-title: Chem. Ing. Tech.
– volume: 25
  start-page: 869
  year: 2002
  end-page: 872
  ident: b65
  article-title: On the relation between ideal and real mixtures in multicomponent distillation
  publication-title: Chem. Eng. Technol.: Ind. Chem.–Plant Equip.–Process Eng.–Biotechnol.
– volume: 114
  start-page: 111
  year: 2018
  end-page: 121
  ident: b27
  article-title: Machine learning: Overview of the recent progresses and implications for the process systems engineering field
  publication-title: Comput. Chem. Eng.
– year: 2022
  ident: b60
  article-title: Chemical Engineering Design: Principles, Practice and Economics of Plant and Process Design
– volume: 7
  start-page: 219
  year: 1983
  end-page: 237
  ident: b45
  article-title: Advances in modelling and analysis of chemical process systems
  publication-title: Comput. Chem. Eng.
– volume: 13
  start-page: 397
  year: 1989
  end-page: 404
  ident: b11
  article-title: A knowledge based system for the selection of thermodynamic models
  publication-title: Comput. Chem. Eng.
– volume: 44
  start-page: 1382
  year: 1998
  end-page: 1391
  ident: b40
  article-title: Structure of distillation regions for multicomponent azeotropic mixtures
  publication-title: AIChE J.
– year: 2009
  ident: b42
  article-title: Thermodynamische Analyse gekoppelter Reaktions-Destillations-Prozesse: konzeptioneller Entwurf, Modellierung, Simulation und experimentelle Validierung (in German)
– volume: 66
  start-page: 4272
  year: 2011
  end-page: 4306
  ident: b55
  article-title: Process systems engineering: from solvay to modern bio- and nanotechnology. a history of development, successes and prospects for the future
  publication-title: Chem. Eng. Sci.
– volume: 49
  start-page: 1555
  year: 2022
  end-page: 1560
  ident: b15
  article-title: Using reinforcement learning in a game-like setup for automated process synthesis without prior process knowledge
  publication-title: Comput. Aided Chem. Eng.
– volume: 62
  start-page: 12220
  year: 2023
  end-page: 12234
  ident: b58
  article-title: Optimization-based azeotropic distillation system synthesis using geometric insights
  publication-title: Ind. Eng. Chem. Res.
– volume: 3
  start-page: 144
  year: 2021
  end-page: 152
  ident: b49
  article-title: Mapping the space of chemical reactions using attention-based neural networks
  publication-title: Nat. Mach. Intell.
– volume: 12
  start-page: 329
  year: 1988
  end-page: 343
  ident: b24
  article-title: A prototype expert system for synthesizing chemical process flowsheets
  publication-title: Comput. Chem. Eng.
– year: 2023
  ident: b8
  article-title: Dortmund data bank
– reference: Pirnay, J., Göttl, Q., Burger, J., Grimm, D., 2023. Policy-Based Self-Competition for Planning Problems. In: International Conference on Learning Representations.
– volume: 4
  start-page: 1256
  year: 2022
  end-page: 1264
  ident: b41
  article-title: Large-scale chemical language representations capture molecular structure and properties
  publication-title: Nat. Mach. Intell.
– volume: 169
  year: 2023
  ident: b51
  article-title: Boosting autonomous process design and intensification with formalized domain knowledge
  publication-title: Comput. Chem. Eng.
– volume: 22
  start-page: 4249
  year: 2008
  end-page: 4258
  ident: b29
  article-title: Control of the heterogeneous azeotropic n-butanol/water distillation system
  publication-title: Energy Fuel
– volume: 324
  start-page: 108
  year: 2012
  end-page: 116
  ident: b43
  article-title: Convex envelope method for the determination of fluid phase diagrams
  publication-title: Fluid Ph. Equilibria
– volume: vol. 34
  start-page: 24261
  year: 2021
  end-page: 24272
  ident: b59
  article-title: MLP-mixer: An all-MLP architecture for vision
  publication-title: NeurIPS
– volume: 28
  start-page: 447
  year: 2004
  end-page: 458
  ident: b68
  article-title: A retrospective on design and process synthesis
  publication-title: Comput. Chem. Eng.
– volume: 59
  start-page: 3370
  year: 2019
  end-page: 3388
  ident: b70
  article-title: Analyzing learned molecular representations for property prediction
  publication-title: J. Chem. Inf. Model.
– volume: 57
  start-page: 12884
  year: 2018
  end-page: 12894
  ident: b66
  article-title: Unique design considerations for maximum-boiling azeotropic systems via extractive distillation: Acetone/chloroform separation
  publication-title: Ind. Eng. Chem. Res.
– volume: 58
  start-page: 1487
  year: 2012
  end-page: 1502
  ident: b69
  article-title: A framework for synthesizing the optimal separation process of azeotropic mixtures
  publication-title: AIChE J.
– start-page: 5998
  year: 2017
  end-page: 6008
  ident: b62
  article-title: Attention is all you need
– volume: 177
  year: 2023
  ident: b16
  article-title: Convex envelope method for determining liquid multi-phase equilibria in systems with arbitrary number of components
  publication-title: Comput. Chem. Eng.
– volume: 141
  year: 2020
  ident: b22
  article-title: Searching for optimal process routes: A reinforcement learning approach
  publication-title: Comput. Chem. Eng.
– year: 2017
  ident: b48
  article-title: Proximal policy optimization algorithms
– year: 2023
  ident: b28
  article-title: NIST Chemistry WebBook
– volume: 550
  start-page: 354
  year: 2017
  end-page: 359
  ident: b54
  article-title: Mastering the game of go without human knowledge
  publication-title: Nature
– volume: 7
  start-page: 1201
  year: 2021
  end-page: 1211
  ident: b9
  article-title: Machine learning in chemical engineering: Strengths, weaknesses, opportunities, and threats
  publication-title: Engineering
– volume: 23
  start-page: 709
  year: 1999
  end-page: 731
  ident: b71
  article-title: A systematic modeling framework of superstructure optimization in process synthesis
  publication-title: Comput. Chem. Eng.
– volume: 52
  start-page: 2005
  year: 2023
  end-page: 2010
  ident: b12
  article-title: Transfer learning for process design with reinforcement learning
  publication-title: Comput. Aided Chem. Eng.
– volume: 63
  start-page: 2294
  year: 2024
  end-page: 2306
  ident: b33
  article-title: Automatic design of extractive distillation sequence for a multicomponent azeotropic system
  publication-title: Ind. Eng. Chem. Res.
– year: 1997
  ident: b3
  article-title: Systematic Methods of Chemical Process Design
– start-page: 12724
  year: 2023
  end-page: 12745
  ident: b20
  article-title: A generalization of vit/mlp-mixer to graphs
  publication-title: International Conference on Machine Learning
– volume: 84
  start-page: 315
  year: 2012
  end-page: 332
  ident: b44
  article-title: Inf/inf analysis of homogeneous distillation processes
  publication-title: Chem. Eng. Sci.
– volume: 17
  start-page: 261
  year: 2020
  end-page: 272
  ident: b64
  article-title: Scipy 1.0: Fundamental algorithms for scientific computing in python
  publication-title: Nature Methods
– volume: 610
  start-page: 47
  year: 2022
  end-page: 53
  ident: b10
  article-title: Discovering faster matrix multiplication algorithms with reinforcement learning
  publication-title: Nature
– volume: 35
  start-page: 4264
  year: 1996
  end-page: 4280
  ident: b2
  article-title: Multiple steady states in distillation: Inf/inf predictions, extensions, and implications for design, synthesis, and simulation
  publication-title: Ind. Eng. Chem. Res.
– year: 1999
  ident: b39
  article-title: Molecular Thermodynamics of Fluid-Phase Equilibria
– volume: 209
  start-page: 26
  year: 2024
  end-page: 36
  ident: b67
  article-title: Automated hybrid distillation sequence synthesis framework of mixed azeotropes and nonazeotropes
  publication-title: Chem. Eng. Res. Des.
– year: 2016
  ident: b61
  article-title: Learning values across many orders of magnitude
– volume: vol. 48
  start-page: 1009
  year: 2020
  end-page: 1014
  ident: b46
  article-title: Automatic synthesis of distillation processes for the separation of heterogeneous azeotropic multi-component mixtures
  publication-title: Computer Aided Chemical Engineering
– reference: Aspen, ., Aspen Plus 8.8, Aspen Technology Inc.
– volume: 16
  start-page: 407
  year: 1999
  end-page: 426
  ident: b18
  article-title: Mathematical programming approaches to the synthesis of chemical process systems
  publication-title: Korean J. Chem. Eng.
– volume: 618
  start-page: 257
  year: 2023
  end-page: 263
  ident: b30
  article-title: Faster sorting algorithms discovered using deep reinforcement learning
  publication-title: Nature
– volume: 7
  start-page: 249
  year: 2017
  end-page: 283
  ident: b4
  article-title: Recent developments and challenges in optimization-based process synthesis
  publication-title: Annu. Rev. Chem. Biomol. Eng.
– volume: 54
  start-page: 7715
  year: 2015
  end-page: 7727
  ident: b5
  article-title: Design and control of a hybrid extraction/distillation system for the separation of pyridine and water
  publication-title: Ind. Eng. Chem.
– volume: 51
  start-page: 310
  year: 2013
  end-page: 316
  ident: b26
  article-title: Techno-economic comparison of energy usage between azeotropic distillation and hybrid system for water-ethanol separation
  publication-title: Renew. Energy
– volume: 180
  year: 2022
  ident: b23
  article-title: Designing the process designer: Hierarchical reinforcement learning for optimisation-based process design
  publication-title: Chem. Eng. Process.
– volume: 93
  start-page: 2010
  year: 2021
  end-page: 2018
  ident: b17
  article-title: Automated flowsheet synthesis using hierarchical reinforcement learning: Proof of concept
  publication-title: Chem. Ing. Tech.
– volume: 17
  start-page: 261
  year: 2020
  ident: 10.1016/j.compchemeng.2024.108975_b64
  article-title: Scipy 1.0: Fundamental algorithms for scientific computing in python
  publication-title: Nature Methods
  doi: 10.1038/s41592-019-0686-2
– volume: 12
  start-page: 329
  issue: 4
  year: 1988
  ident: 10.1016/j.compchemeng.2024.108975_b24
  article-title: A prototype expert system for synthesizing chemical process flowsheets
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/0098-1354(88)85045-2
– volume: 51
  start-page: 310
  year: 2013
  ident: 10.1016/j.compchemeng.2024.108975_b26
  article-title: Techno-economic comparison of energy usage between azeotropic distillation and hybrid system for water-ethanol separation
  publication-title: Renew. Energy
  doi: 10.1016/j.renene.2012.09.055
– volume: 209
  start-page: 26
  year: 2024
  ident: 10.1016/j.compchemeng.2024.108975_b67
  article-title: Automated hybrid distillation sequence synthesis framework of mixed azeotropes and nonazeotropes
  publication-title: Chem. Eng. Res. Des.
  doi: 10.1016/j.cherd.2024.07.045
– volume: 49
  start-page: 1555
  year: 2022
  ident: 10.1016/j.compchemeng.2024.108975_b15
  article-title: Using reinforcement learning in a game-like setup for automated process synthesis without prior process knowledge
  publication-title: Comput. Aided Chem. Eng.
  doi: 10.1016/B978-0-323-85159-6.50259-1
– volume: 16
  start-page: 407
  issue: 4
  year: 1999
  ident: 10.1016/j.compchemeng.2024.108975_b18
  article-title: Mathematical programming approaches to the synthesis of chemical process systems
  publication-title: Korean J. Chem. Eng.
  doi: 10.1007/BF02698263
– ident: 10.1016/j.compchemeng.2024.108975_b21
– volume: 62
  start-page: 12220
  issue: 31
  year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b58
  article-title: Optimization-based azeotropic distillation system synthesis using geometric insights
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/acs.iecr.3c01269
– volume: 180
  year: 2022
  ident: 10.1016/j.compchemeng.2024.108975_b23
  article-title: Designing the process designer: Hierarchical reinforcement learning for optimisation-based process design
  publication-title: Chem. Eng. Process.
  doi: 10.1016/j.cep.2022.108885
– volume: vol. 34
  start-page: 24261
  year: 2021
  ident: 10.1016/j.compchemeng.2024.108975_b59
  article-title: MLP-mixer: An all-MLP architecture for vision
– year: 2022
  ident: 10.1016/j.compchemeng.2024.108975_b60
– volume: 7
  start-page: 249
  issue: 8
  year: 2017
  ident: 10.1016/j.compchemeng.2024.108975_b4
  article-title: Recent developments and challenges in optimization-based process synthesis
  publication-title: Annu. Rev. Chem. Biomol. Eng.
  doi: 10.1146/annurev-chembioeng-080615-033546
– volume: 91
  start-page: 1
  issue: 3
  year: 2019
  ident: 10.1016/j.compchemeng.2024.108975_b31
  article-title: Overview of surrogate modeling in chemical process engineering
  publication-title: Chem. Ing. Tech.
  doi: 10.1002/cite.201800091
– volume: 59
  start-page: 3370
  issue: 8
  year: 2019
  ident: 10.1016/j.compchemeng.2024.108975_b70
  article-title: Analyzing learned molecular representations for property prediction
  publication-title: J. Chem. Inf. Model.
  doi: 10.1021/acs.jcim.9b00237
– volume: 610
  start-page: 47
  issue: 7930
  year: 2022
  ident: 10.1016/j.compchemeng.2024.108975_b10
  article-title: Discovering faster matrix multiplication algorithms with reinforcement learning
  publication-title: Nature
  doi: 10.1038/s41586-022-05172-4
– volume: 93
  start-page: 2029
  year: 2021
  ident: 10.1016/j.compchemeng.2024.108975_b50
  article-title: Machine learning in chemical engineering: A perspective
  publication-title: Chem. Ing. Tech.
  doi: 10.1002/cite.202100083
– volume: 93
  start-page: 2010
  issue: 12
  year: 2021
  ident: 10.1016/j.compchemeng.2024.108975_b17
  article-title: Automated flowsheet synthesis using hierarchical reinforcement learning: Proof of concept
  publication-title: Chem. Ing. Tech.
  doi: 10.1002/cite.202100086
– ident: 10.1016/j.compchemeng.2024.108975_b7
– volume: 84
  start-page: 315
  year: 2012
  ident: 10.1016/j.compchemeng.2024.108975_b44
  article-title: Inf/inf analysis of homogeneous distillation processes
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2012.08.018
– year: 2018
  ident: 10.1016/j.compchemeng.2024.108975_b57
– volume: 59
  start-page: 20816
  issue: 47
  year: 2020
  ident: 10.1016/j.compchemeng.2024.108975_b47
  article-title: Automatic synthesis of distillation processes for the separation of homogeneous azeotropic multicomponent systems
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/acs.iecr.0c04555
– year: 2016
  ident: 10.1016/j.compchemeng.2024.108975_b61
  article-title: Learning values across many orders of magnitude
– year: 2017
  ident: 10.1016/j.compchemeng.2024.108975_b48
– volume: 618
  start-page: 257
  issue: 7964
  year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b30
  article-title: Faster sorting algorithms discovered using deep reinforcement learning
  publication-title: Nature
  doi: 10.1038/s41586-023-06004-9
– volume: 28
  start-page: 447
  issue: 4
  year: 2004
  ident: 10.1016/j.compchemeng.2024.108975_b68
  article-title: A retrospective on design and process synthesis
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2003.09.029
– volume: 141
  year: 2020
  ident: 10.1016/j.compchemeng.2024.108975_b22
  article-title: Searching for optimal process routes: A reinforcement learning approach
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2020.107027
– volume: 3
  start-page: 1337
  issue: 12
  year: 2017
  ident: 10.1016/j.compchemeng.2024.108975_b72
  article-title: Optimizing chemical reactions with deep reinforcement learning
  publication-title: ACS Cent. Sci.
  doi: 10.1021/acscentsci.7b00492
– volume: 324
  start-page: 108
  year: 2012
  ident: 10.1016/j.compchemeng.2024.108975_b43
  article-title: Convex envelope method for the determination of fluid phase diagrams
  publication-title: Fluid Ph. Equilibria
  doi: 10.1016/j.fluid.2012.04.002
– volume: 63
  start-page: 2294
  issue: 5
  year: 2024
  ident: 10.1016/j.compchemeng.2024.108975_b33
  article-title: Automatic design of extractive distillation sequence for a multicomponent azeotropic system
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/acs.iecr.3c03575
– year: 2020
  ident: 10.1016/j.compchemeng.2024.108975_b34
– year: 1999
  ident: 10.1016/j.compchemeng.2024.108975_b39
– volume: 114
  start-page: 111
  year: 2018
  ident: 10.1016/j.compchemeng.2024.108975_b27
  article-title: Machine learning: Overview of the recent progresses and implications for the process systems engineering field
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2017.10.008
– volume: 35
  start-page: 4264
  year: 1996
  ident: 10.1016/j.compchemeng.2024.108975_b2
  article-title: Multiple steady states in distillation: Inf/inf predictions, extensions, and implications for design, synthesis, and simulation
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/ie950450d
– year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b28
– volume: 3
  start-page: 144
  year: 2021
  ident: 10.1016/j.compchemeng.2024.108975_b49
  article-title: Mapping the space of chemical reactions using attention-based neural networks
  publication-title: Nat. Mach. Intell.
  doi: 10.1038/s42256-020-00284-w
– volume: 22
  start-page: 4249
  year: 2008
  ident: 10.1016/j.compchemeng.2024.108975_b29
  article-title: Control of the heterogeneous azeotropic n-butanol/water distillation system
  publication-title: Energy Fuel
  doi: 10.1021/ef8004064
– volume: 4
  start-page: 1256
  year: 2022
  ident: 10.1016/j.compchemeng.2024.108975_b41
  article-title: Large-scale chemical language representations capture molecular structure and properties
  publication-title: Nat. Mach. Intell.
  doi: 10.1038/s42256-022-00580-7
– volume: 7
  start-page: 1201
  issue: 9
  year: 2021
  ident: 10.1016/j.compchemeng.2024.108975_b9
  article-title: Machine learning in chemical engineering: Strengths, weaknesses, opportunities, and threats
  publication-title: Engineering
  doi: 10.1016/j.eng.2021.03.019
– ident: 10.1016/j.compchemeng.2024.108975_b36
– volume: 10
  start-page: 353
  issue: 3
  year: 1971
  ident: 10.1016/j.compchemeng.2024.108975_b52
  article-title: Computer-aided synthesis of chemical process designs. From reaction path data to the process task network
  publication-title: Ind. Eng. Chem. Fundamen.
  doi: 10.1021/i160039a003
– volume: 57
  start-page: 12884
  issue: 38
  year: 2018
  ident: 10.1016/j.compchemeng.2024.108975_b66
  article-title: Unique design considerations for maximum-boiling azeotropic systems via extractive distillation: Acetone/chloroform separation
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/acs.iecr.8b03125
– volume: 136
  issue: 106808
  year: 2020
  ident: 10.1016/j.compchemeng.2024.108975_b32
  article-title: A review on superstructure optimization approaches in process system engineering
  publication-title: Comput. Chem. Eng.
– volume: 177
  year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b16
  article-title: Convex envelope method for determining liquid multi-phase equilibria in systems with arbitrary number of components
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2023.108321
– volume: 23
  start-page: 709
  issue: 6
  year: 1999
  ident: 10.1016/j.compchemeng.2024.108975_b71
  article-title: A systematic modeling framework of superstructure optimization in process synthesis
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/S0098-1354(99)00003-4
– volume: 69
  start-page: 17938
  issue: 1
  year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b56
  article-title: Flowsheet generation through hierarchical reinforcement learning and graph neural networks
  publication-title: AIChE J.
  doi: 10.1002/aic.17938
– volume: 54
  start-page: 7715
  year: 2015
  ident: 10.1016/j.compchemeng.2024.108975_b5
  article-title: Design and control of a hybrid extraction/distillation system for the separation of pyridine and water
  publication-title: Ind. Eng. Chem.
  doi: 10.1021/acs.iecr.5b01671
– year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b8
– volume: 50
  start-page: 209
  year: 2021
  ident: 10.1016/j.compchemeng.2024.108975_b13
  article-title: Automated process synthesis using reinforcement learning
  publication-title: Comput. Aided Chem. Eng.
  doi: 10.1016/B978-0-323-88506-5.50034-6
– volume: 550
  start-page: 354
  year: 2017
  ident: 10.1016/j.compchemeng.2024.108975_b54
  article-title: Mastering the game of go without human knowledge
  publication-title: Nature
  doi: 10.1038/nature24270
– year: 1997
  ident: 10.1016/j.compchemeng.2024.108975_b3
– volume: vol. 48
  start-page: 1009
  year: 2020
  ident: 10.1016/j.compchemeng.2024.108975_b46
  article-title: Automatic synthesis of distillation processes for the separation of heterogeneous azeotropic multi-component mixtures
– start-page: 12724
  year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b20
  article-title: A generalization of vit/mlp-mixer to graphs
– volume: 147
  year: 2021
  ident: 10.1016/j.compchemeng.2024.108975_b37
  article-title: Process systems engineering - The generation next?
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2021.107252
– year: 2018
  ident: 10.1016/j.compchemeng.2024.108975_b38
– year: 2009
  ident: 10.1016/j.compchemeng.2024.108975_b42
– volume: 66
  start-page: 4272
  issue: 19
  year: 2011
  ident: 10.1016/j.compchemeng.2024.108975_b55
  article-title: Process systems engineering: from solvay to modern bio- and nanotechnology. a history of development, successes and prospects for the future
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2011.05.049
– volume: 362
  start-page: 1140
  year: 2018
  ident: 10.1016/j.compchemeng.2024.108975_b53
  article-title: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play
  publication-title: Science
  doi: 10.1126/science.aar6404
– year: 2007
  ident: 10.1016/j.compchemeng.2024.108975_b25
– ident: 10.1016/j.compchemeng.2024.108975_b1
– volume: 10
  start-page: 370
  year: 2019
  ident: 10.1016/j.compchemeng.2024.108975_b6
  article-title: A graph-convolutional neural network model for the prediction of chemical reactivity
  publication-title: Chem. Sci.
  doi: 10.1039/C8SC04228D
– volume: 13
  start-page: 397
  issue: 4–5
  year: 1989
  ident: 10.1016/j.compchemeng.2024.108975_b11
  article-title: A knowledge based system for the selection of thermodynamic models
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/0098-1354(89)85019-7
– volume: 65
  year: 2018
  ident: 10.1016/j.compchemeng.2024.108975_b63
  article-title: The promise of artificial intelligence in chemical engineering: Is it here, finally?
  publication-title: AIChE J.
– volume: 58
  start-page: 1487
  issue: 5
  year: 2012
  ident: 10.1016/j.compchemeng.2024.108975_b69
  article-title: A framework for synthesizing the optimal separation process of azeotropic mixtures
  publication-title: AIChE J.
  doi: 10.1002/aic.12677
– volume: 169
  year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b51
  article-title: Boosting autonomous process design and intensification with formalized domain knowledge
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2022.108097
– volume: 25
  start-page: 869
  issue: 9
  year: 2002
  ident: 10.1016/j.compchemeng.2024.108975_b65
  article-title: On the relation between ideal and real mixtures in multicomponent distillation
  publication-title: Chem. Eng. Technol.: Ind. Chem.–Plant Equip.–Process Eng.–Biotechnol.
  doi: 10.1002/1521-4125(20020910)25:9<869::AID-CEAT869>3.0.CO;2-9
– volume: 16
  start-page: 288
  year: 2022
  ident: 10.1016/j.compchemeng.2024.108975_b14
  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
– year: 2004
  ident: 10.1016/j.compchemeng.2024.108975_b35
– volume: 7
  start-page: 219
  year: 1983
  ident: 10.1016/j.compchemeng.2024.108975_b45
  article-title: Advances in modelling and analysis of chemical process systems
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/0098-1354(83)80013-1
– volume: 126
  start-page: 474
  year: 2019
  ident: 10.1016/j.compchemeng.2024.108975_b19
  article-title: Process systems engineering: Academic and industrial perspectives
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2019.04.028
– volume: 52
  start-page: 2005
  year: 2023
  ident: 10.1016/j.compchemeng.2024.108975_b12
  article-title: Transfer learning for process design with reinforcement learning
  publication-title: Comput. Aided Chem. Eng.
  doi: 10.1016/B978-0-443-15274-0.50319-X
– volume: 44
  start-page: 1382
  issue: 6
  year: 1998
  ident: 10.1016/j.compchemeng.2024.108975_b40
  article-title: Structure of distillation regions for multicomponent azeotropic mixtures
  publication-title: AIChE J.
  doi: 10.1002/aic.690440616
– start-page: 5998
  year: 2017
  ident: 10.1016/j.compchemeng.2024.108975_b62
  article-title: Attention is all you need
SSID ssj0002488
Score 2.4493165
Snippet Process synthesis in chemical engineering is a complex planning problem due to vast search spaces, continuous parameters and the need for generalization. Deep...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 108975
SubjectTerms Automated process synthesis
Conceptual design
Process simulation
Reinforcement learning
Title Deep reinforcement learning enables conceptual design of processes for separating azeotropic mixtures without prior knowledge
URI https://dx.doi.org/10.1016/j.compchemeng.2024.108975
Volume 194
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/eLvHCXMwtV1Lb9QwELaWFiE4IJ6ivGQkblGqJk42tsSlQHkdqiKKtLcodpwqbTeJsmm1IPFH-LXM2HESXqIIcYlW0Y4j73zreMbffEPIU11AZKxV5PM4i_1IhcqXheJ-EYSF2smKIs53TLOJZH-fLxbiYDb76mphzk-TquLrtWj-q6vhHjgbS2f_wt3DoHADPoPT4Qpuh-uFHP9S68ZrtVFEVSb551pDHHnaVEqtkGuOdBYsHckNhcMQn23NgDYKDd5KW1VwrGH8rOuurZtSectyjUcOtiYOKc1NW8KXh8zcdK_rGkasDLyUUybQowLiQP7B4_rn864z-ej3Z2VbDpg9KGHKn6aJ_iGDYCq6LdX3pJYjk6hcLm1sgLopJ97r7WlqI4xHbpfNt7mam5HgZNZwAXEvs9LTwxpuOyX_9D6wqYljdGeD84QpbsOTIqRWCtuy5Qe57Q84Pg6P5FomWHSJbIZJLGDF3Nx9u7d4N7znw4hzp8iKBlfIk5E9-JsH_nr3M9nRHN4g1_tQhO5aCN0kM13dItcmApW3yRcEE_0OTNSBifZgoiOYqAUTrQs6gImCJR3BREcwUQcm2oOJGjDRAUx3yMdXe4cv3vh9ww5fQeAd-1LMI5GxQDERzTMdykQJPFiGEDkOM87jREnYHuZMZsVcBiKQgUxypkWmpAgVZ3fJRlVX-h6hImZSCs5ZISUWb0OYIVmuk1xhxJDFW4S7HzJVvZo9NlU5TR1t8Tid-CBFH6TWB1skHEwbK-lyEaNnzltpvze1e84UoPZn8_v_Zv6AXB3_Hw_JRtee6UfksjrvylX7uAfmN36Iw9g
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=Deep+reinforcement+learning+enables+conceptual+design+of+processes+for+separating+azeotropic+mixtures+without+prior+knowledge&rft.jtitle=Computers+%26+chemical+engineering&rft.au=G%C3%B6ttl%2C+Quirin&rft.au=Pirnay%2C+Jonathan&rft.au=Burger%2C+Jakob&rft.au=Grimm%2C+Dominik+G.&rft.date=2025-03-01&rft.pub=Elsevier+Ltd&rft.issn=0098-1354&rft.volume=194&rft_id=info:doi/10.1016%2Fj.compchemeng.2024.108975&rft.externalDocID=S0098135424003934
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