Machine learning in process systems engineering: Challenges and opportunities

Prodromos Daoutidis; Jay H. Lee; Srinivas Rangarajan; Leo Chiang; Bhushan Gopaluni; Artur M. Schweidtmann; Iiro Harjunkoski; Mehmet Mercangöz; Ali Mesbah; Fani Boukouvala; Fernando V. Lima; Antonio del Rio Chanona; Christos Georgakis

doi:10.1016/j.compchemeng.2023.108523

Machine learning in process systems engineering: Challenges and opportunities

Prodromos Daoutidis^*, Jay H. Lee^*, Srinivas Rangarajan, Leo Chiang, Bhushan Gopaluni, Artur M. Schweidtmann, Iiro Harjunkoski, Mehmet Mercangöz, Ali Mesbah, Fani Boukouvala, Fernando V. Lima, Antonio del Rio Chanona, Christos Georgakis

^*Corresponding author for this work

Research output: Contribution to journal › Review Article

27 Citations (Scopus)

Abstract

This “white paper” is a concise perspective of the potential of machine learning in the process systems engineering (PSE) domain, based on a session during FIPSE 5, held in Crete, Greece, June 27–29, 2022. The session included two invited talks and three short contributed presentations followed by extensive discussions. This paper does not intend to provide a comprehensive review on the subject or a detailed exposition of the discussions; instead its aim is to distill the main points of the discussions and talks, and in doing so, highlight open problems and directions for future research. The general conclusion from the session was that machine learning can have a transformational impact on the PSE domain enabling new discoveries and innovations, but research is needed to develop domain-specific techniques for problems in molecular/material design, data analytics, optimization, and control.

Original language	English
Article number	108523
Journal	Computers and Chemical Engineering
Volume	181
Early online date	23 Nov 2023
DOIs	https://doi.org/10.1016/j.compchemeng.2023.108523
Publication status	Published - Feb 2024
MoE publication type	B1 Non-refereed journal articles
Event	Future Innovation in Process System Engineering - Aldemar Knossos Royal Hotel, Hersonissos, Greece Duration: 27 Jun 2022 → 29 Jun 2022 Conference number: 5 https://www.fi-in-pse.org/

Keywords

Control
Machine learning
Modeling
Molecule discovery
Optimization
Process monitoring

Access to Document

10.1016/j.compchemeng.2023.108523

Cite this

Daoutidis, P., Lee, J. H., Rangarajan, S., Chiang, L., Gopaluni, B., Schweidtmann, A. M., Harjunkoski, I., Mercangöz, M., Mesbah, A., Boukouvala, F., Lima, F. V., del Rio Chanona, A., & Georgakis, C. (2024). Machine learning in process systems engineering: Challenges and opportunities. Computers and Chemical Engineering, 181, Article 108523. https://doi.org/10.1016/j.compchemeng.2023.108523

@article{4f892afe7320494986a8bef352c02d3e,

title = "Machine learning in process systems engineering: Challenges and opportunities",

abstract = "This “white paper” is a concise perspective of the potential of machine learning in the process systems engineering (PSE) domain, based on a session during FIPSE 5, held in Crete, Greece, June 27–29, 2022. The session included two invited talks and three short contributed presentations followed by extensive discussions. This paper does not intend to provide a comprehensive review on the subject or a detailed exposition of the discussions; instead its aim is to distill the main points of the discussions and talks, and in doing so, highlight open problems and directions for future research. The general conclusion from the session was that machine learning can have a transformational impact on the PSE domain enabling new discoveries and innovations, but research is needed to develop domain-specific techniques for problems in molecular/material design, data analytics, optimization, and control.",

keywords = "Control, Machine learning, Modeling, Molecule discovery, Optimization, Process monitoring",

author = "Prodromos Daoutidis and Lee, {Jay H.} and Srinivas Rangarajan and Leo Chiang and Bhushan Gopaluni and Schweidtmann, {Artur M.} and Iiro Harjunkoski and Mehmet Mercang{\"o}z and Ali Mesbah and Fani Boukouvala and Lima, {Fernando V.} and {del Rio Chanona}, Antonio and Christos Georgakis",

note = "Funding Information: PD would like to acknowledge financial support by NSF-CBET . Publisher Copyright: {\textcopyright} 2023 Elsevier Ltd; Future Innovation in Process System Engineering, FIPSE ; Conference date: 27-06-2022 Through 29-06-2022",

year = "2024",

month = feb,

doi = "10.1016/j.compchemeng.2023.108523",

language = "English",

volume = "181",

journal = "Computers and Chemical Engineering",

issn = "0098-1354",

publisher = "Elsevier",

url = "https://www.fi-in-pse.org/",

}

Daoutidis, P, Lee, JH, Rangarajan, S, Chiang, L, Gopaluni, B, Schweidtmann, AM, Harjunkoski, I, Mercangöz, M, Mesbah, A, Boukouvala, F, Lima, FV, del Rio Chanona, A & Georgakis, C 2024, 'Machine learning in process systems engineering: Challenges and opportunities', Computers and Chemical Engineering, vol. 181, 108523. https://doi.org/10.1016/j.compchemeng.2023.108523

TY - JOUR

T1 - Machine learning in process systems engineering: Challenges and opportunities

AU - Daoutidis, Prodromos

AU - Lee, Jay H.

AU - Rangarajan, Srinivas

AU - Chiang, Leo

AU - Gopaluni, Bhushan

AU - Schweidtmann, Artur M.

AU - Harjunkoski, Iiro

AU - Mercangöz, Mehmet

AU - Mesbah, Ali

AU - Boukouvala, Fani

AU - Lima, Fernando V.

AU - del Rio Chanona, Antonio

AU - Georgakis, Christos

N1 - Conference code: 5

PY - 2024/2

Y1 - 2024/2

N2 - This “white paper” is a concise perspective of the potential of machine learning in the process systems engineering (PSE) domain, based on a session during FIPSE 5, held in Crete, Greece, June 27–29, 2022. The session included two invited talks and three short contributed presentations followed by extensive discussions. This paper does not intend to provide a comprehensive review on the subject or a detailed exposition of the discussions; instead its aim is to distill the main points of the discussions and talks, and in doing so, highlight open problems and directions for future research. The general conclusion from the session was that machine learning can have a transformational impact on the PSE domain enabling new discoveries and innovations, but research is needed to develop domain-specific techniques for problems in molecular/material design, data analytics, optimization, and control.

AB - This “white paper” is a concise perspective of the potential of machine learning in the process systems engineering (PSE) domain, based on a session during FIPSE 5, held in Crete, Greece, June 27–29, 2022. The session included two invited talks and three short contributed presentations followed by extensive discussions. This paper does not intend to provide a comprehensive review on the subject or a detailed exposition of the discussions; instead its aim is to distill the main points of the discussions and talks, and in doing so, highlight open problems and directions for future research. The general conclusion from the session was that machine learning can have a transformational impact on the PSE domain enabling new discoveries and innovations, but research is needed to develop domain-specific techniques for problems in molecular/material design, data analytics, optimization, and control.

KW - Control

KW - Machine learning

KW - Modeling

KW - Molecule discovery

KW - Optimization

KW - Process monitoring

UR - http://www.scopus.com/inward/record.url?scp=85177795287&partnerID=8YFLogxK

U2 - 10.1016/j.compchemeng.2023.108523

DO - 10.1016/j.compchemeng.2023.108523

M3 - Review Article

AN - SCOPUS:85177795287

SN - 0098-1354

VL - 181

JO - Computers and Chemical Engineering

JF - Computers and Chemical Engineering

M1 - 108523

T2 - Future Innovation in Process System Engineering

Y2 - 27 June 2022 through 29 June 2022

ER -

Machine learning in process systems engineering: Challenges and opportunities

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this