document

A review and perspective on hybrid modeling methodologies

Schweidtmann, A.M. (author), Zhang, Dongda (author), von Stosch, Moritz (author)

The term hybrid modeling refers to the combination of parametric models (typically derived from knowledge about the system) and nonparametric models (typically deduced from data). Despite more than 20 years of research, over 150 scientific publications (Agharafeie et al., 2023), and some recent industrial applications on this topic, the...

review 2024

document

Data-driven product-process optimization of N-isopropylacrylamide microgel flow-synthesis

Kaven, Luise F. (author), Schweidtmann, A.M. (author), Keil, Jan (author), Israel, Jana (author), Wolter, Nadja (author), Mitsos, Alexander (author)

Microgels are cross-linked, colloidal polymer networks with great potential for stimuli-response release in drug-delivery applications, as their small size allows them to pass human cell boundaries. For applications with specified requirements regarding size, producing tailored microgels in a continuous flow reactor is advantageous because...

journal article 2024

document

Empirical assessment of ChatGPT’s answering capabilities in natural science and engineering

Schulze Balhorn, L. (author), Weber, J.M. (author), Buijsman, S.N.R. (author), Hildebrandt, Julian R. (author), Ziefle, Martina (author), Schweidtmann, A.M. (author)

ChatGPT is a powerful language model from OpenAI that is arguably able to comprehend and generate text. ChatGPT is expected to greatly impact society, research, and education. An essential step to understand ChatGPT’s expected impact is to study its domain-specific answering capabilities. Here, we perform a systematic empirical assessment of...

journal article 2024

document

Deep reinforcement learning for process design: Review and perspective

Gao, Q. (author), Schweidtmann, A.M. (author)

The transformation toward renewable energy and feedstock supply in the chemical industry requires new conceptual process design approaches. Recently, deep reinforcement learning (RL), a subclass of machine learning, has shown the potential to solve complex decision-making problems and aid sustainable process design. However, its suitability...

review 2024

document

Mixed-integer optimisation of graph neural networks for computer-aided molecular design

McDonald, Tom (author), Tsay, Calvin (author), Schweidtmann, A.M. (author), Yorke-Smith, N. (author)

ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP), enabling surrogate-based optimisation in various domains and efficient solution of machine learning certification problems. However, previous works are mostly limited to MLPs. Graph neural networks (GNNs) can learn from non-euclidean data...

journal article 2024

document

Machine learning in process systems engineering: Challenges and opportunities

Daoutidis, Prodromos (author), Lee, Jay H. (author), Rangarajan, Srinivas (author), Chiang, Leo (author), Gopaluni, Bhushan (author), Schweidtmann, A.M. (author), Harjunkoski, Iiro (author), Mercangöz, Mehmet (author), Mesbah, Ali (author)

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...

journal article 2024

document

SFILES 2.0: an extended text-based flowsheet representation

Vogel, G.C. (author), Hirtreiter, E.J. (author), Schulze Balhorn, L. (author), Schweidtmann, A.M. (author)

SFILES are a text-based notation for chemical process flowsheets. They were originally proposed by d’Anterroches (Process flow sheet generation & design through a group contribution approach) who was inspired by the text-based SMILES notation for molecules. The text-based format has several advantages compared to flowsheet images...

journal article 2023

document

An Educational Workshop for Effective PSE Course Development

Lewin, Daniel R. (author), Zondervan, Edwin (author), Franke, Meik (author), Kiss, A.A. (author), Pérez-Fortes, Mar (author), Schweidtmann, A.M. (author), (Ellen) Slegers, Petronella M. (author), Somoza Tornos, A. (author), Swinkels, P.L.J. (author)

An educational workshop for developing Process Systems Engineering (PSE) courses will be held during ESCAPE-33, following the model workshop that was run during the CAPE Forum 2022 held at the University of Twente, in the Netherlands. This 3-hour workshop distributes the participants into four teams working together to develop the outline of...

book chapter 2023

document

Data augmentation for machine learning of chemical process flowsheets

Schulze Balhorn, L. (author), Hirtreiter, E.J. (author), Luderer, Lynn (author), Schweidtmann, A.M. (author)

Artificial intelligence has great potential for accelerating the design and engineering of chemical processes. Recently, we have shown that transformer-based language models can learn to auto-complete chemical process flowsheets using the SFILES 2.0 string notation. Also, we showed that language translation models can be used to translate...

book chapter 2023

document

Transfer learning for process design with reinforcement learning

Gao, Q. (author), Yang, Haoyu (author), Shanbhag, S.M. (author), Schweidtmann, A.M. (author)

Process design is a creative task that is currently performed manually by engineers. Artificial intelligence provides new potential to facilitate process design. Specifically, reinforcement learning (RL) has shown some success in automating process design by integrating data-driven models that learn to build process flowsheets with process...

book chapter 2023

document

Toward automatic generation of control structures for process flow diagrams with large language models

Hirtreiter, E.J. (author), Schulze Balhorn, L. (author), Schweidtmann, A.M. (author)

Developing Piping and Instrumentation Diagrams (P&IDs) is a crucial step during process development. We propose a data-driven method for the prediction of control structures. Our methodology is inspired by end-to-end transformer-based human language translation models. We cast the control structure prediction as a translation task where...

journal article 2023

document

Graph neural networks for temperature-dependent activity coefficient prediction of solutes in ionic liquids

Rittig, J. (author), Ben Hicham, Karim (author), Schweidtmann, A.M. (author), Dahmen, Manuel (author), Mitsos, Alexander (author)

Ionic liquids (ILs) are important solvents for sustainable processes and predicting activity coefficients (ACs) of solutes in ILs is needed. Recently, matrix completion methods (MCMs), transformers, and graph neural networks (GNNs) have shown high accuracy in predicting ACs of binary mixtures, superior to well-established models, e.g., COSMO...

journal article 2023

document

Geometry optimization of a continuous millireactor via CFD and Bayesian optimization

Begall, Moritz J. (author), Schweidtmann, A.M. (author), Mhamdi, Adel (author), Mitsos, Alexander (author)

Computational Fluid Dynamics (CFD) is a powerful tool which can help with the geometry optimization of continuous milli-scale reactors, which often are highly complex devices. Attempting to perform this optimization by manually modifying and testing geometry configurations can however be tedious and computationally inefficient. Addressing...

journal article 2023

document

Learning from flowsheets: A generative transformer model for autocompletion of flowsheets

Vogel, G.C. (author), Schulze Balhorn, L. (author), Schweidtmann, A.M. (author)

We propose a novel method enabling autocompletion of chemical flowsheets. This idea is inspired by the autocompletion of text. We represent flowsheets as strings using the text-based SFILES 2.0 notation and learn the grammatical structure of the SFILES 2.0 language and common patterns in flowsheets using a transformer-based language model. We...

journal article 2023

document

Molecular Design of Fuels for Maximum Spark-Ignition Engine Efficiency by Combining Predictive Thermodynamics and Machine Learning

Fleitmann, Lorenz (author), Ackermann, Philipp (author), Schilling, Johannes (author), Kleinekorte, Johanna (author), Rittig, J. (author), vom Lehn, Florian (author), Schweidtmann, A.M. (author), Pitsch, Heinz (author), Leonhard, Kai (author)

Co-design of alternative fuels and future spark-ignition (SI) engines allows very high engine efficiencies to be achieved. To tailor the fuel’s molecular structure to the needs of SI engines with very high compression ratios, computer-aided molecular design (CAMD) of renewable fuels has received considerable attention over the past decade. To...

journal article 2023

document

Physical pooling functions in graph neural networks for molecular property prediction

Schweidtmann, A.M. (author), Rittig, J. (author), Weber, J.M. (author), Grohe, Martin (author), Dahmen, Manuel (author), Leonhard, Kai (author), Mitsos, Alexander (author)

Graph neural networks (GNNs) are emerging in chemical engineering for the end-to-end learning of physicochemical properties based on molecular graphs. A key element of GNNs is the pooling function which combines atom feature vectors into molecular fingerprints. Most previous works use a standard pooling function to predict a variety of...

journal article 2023

document

Digitization of chemical process flow diagrams using deep convolutional neural networks

Theisen, M.F. (author), Nishizaki Flores, K.F. (author), Schulze Balhorn, L. (author), Schweidtmann, A.M. (author)

Advances in deep convolutional neural networks led to breakthroughs in many computer vision applications. In chemical engineering, a number of tools have been developed for the digitization of Process and Instrumentation Diagrams. However, there is no framework for the digitization of process flow diagrams (PFDs). PFDs are difficult to...

journal article 2023

document

Multi-objective Bayesian optimisation of a two-step synthesis of p-cymene from crude sulphate turpentine

Jorayev, Perman (author), Russo, Danilo (author), Tibbetts, Joshua D. (author), Schweidtmann, A.M. (author), Deutsch, Paul (author), Bull, Steven D. (author), Lapkin, Alexei A. (author)

Production of functional molecules from renewable bio-feedstocks and bio-waste has the potential to significantly reduce the greenhouse gas emissions. However, the development of such processes commonly requires invention and scale-up of highly selective and robust chemistry for complex reaction networks in bio-waste mixtures. We demonstrate...

journal article 2022

document

Graph machine learning for design of high-octane fuels

Rittig, J. (author), Ritzert, Martin (author), Schweidtmann, A.M. (author), Winkler, Stefanie (author), Weber, J.M. (author), Morsch, Philipp (author), Heufer, Karl Alexander (author), Grohe, Martin (author), Mitsos, Alexander (author), Dahmen, Manuel (author)

Fuels with high-knock resistance enable modern spark-ignition engines to achieve high efficiency and thus low CO₂ emissions. Identification of molecules with desired autoignition properties indicated by a high research octane number and a high octane sensitivity is therefore of great practical relevance and can be supported by...

journal article 2022

document

Flowsheet Recognition using Deep Convolutional Neural Networks

Schulze Balhorn, L. (author), Gao, Q. (author), Goldstein, Dominik (author), Schweidtmann, A.M. (author)

Flowsheets are the most important building blocks to define and communicate the structure of chemical processes. Gaining access to large data sets of machine-readable chemical flowsheets could significantly enhance process synthesis through artificial intelligence. A large number of these flowsheets are publicly available in the scientific...

book chapter 2022