Publications

Toward autocorrection of chemical process flowsheets using large language models
The process engineering domain widely uses Process Flow Diagrams (PFDs) and Process and Instrumentation Diagrams (P&IDs) to …
PDF Cite DOI
Toward autocorrection of chemical process flowsheets using large language models
Physics-informed neural networks and time-series transformer for modeling of chemical reactors
Multiscale modeling of catalytical chemical reactors typically results in solving a system of partial differential equations (PDEs) or …
PDF Cite DOI
Physics-informed neural networks and time-series transformer for modeling of chemical reactors
Generative artificial intelligence in chemical engineering
Generative artificial intelligence
Cite DOI
Generative artificial intelligence in chemical engineering
Machine learning in process systems engineering: Challenges and opportunities
Machine learning in process systems engineering
PDF Cite DOI
Machine learning in process systems engineering: Challenges and opportunities
Data-driven Product-Process Optimization of N-isopropylacrylamide Microgel Flow-Synthesis
Data-driven Product-Process Optimization
PDF Cite DOI
Data-driven Product-Process Optimization of N-isopropylacrylamide Microgel Flow-Synthesis
A review and perspective on hybrid modeling methodologies
Hybrid modeling
PDF Cite DOI
A review and perspective on hybrid modeling methodologies
Empirical assessment of ChatGPT’s answering capabilities in natural science and engineering
ChatGPT
PDF Cite DOI
Empirical assessment of ChatGPT’s answering capabilities in natural science and engineering
Deep reinforcement learning for process design: Review and perspective
Deep reinforcement learning
PDF Cite DOI
Deep reinforcement learning for process design: Review and perspective
An Educational Workshop for Effective PSE Course Development
An educational workshop for developing Process Systems Engineering (PSE) courses will be held during ESCAPE-33, following the model …
PDF Cite DOI
An Educational Workshop for Effective PSE Course Development
Transfer learning for process design with reinforcement learning
Process design is a creative task that is currently performed manually by engineers. Artificial intelligence provides new potential to …
PDF Cite DOI
Transfer learning for process design with reinforcement learning
Data augmentation for machine learning of chemical process flowsheets
Flowsheets are the most important building blocks to define and communicate the structure of chemical processes. Gaining access to …
PDF Cite DOI
Data augmentation for machine learning of chemical process flowsheets
Molecular Design of Fuels for Maximum Spark-Ignition Engine Efficiency by Combining Predictive Thermodynamics and Machine Learning
Molecular design
PDF Cite DOI
Molecular Design of Fuels for Maximum Spark-Ignition Engine Efficiency by Combining Predictive Thermodynamics and Machine Learning
Graph machine learning for design of high-octane fuels
Molecular design
PDF Cite DOI
Graph machine learning for design of high-octane fuels
Toward automatic generation of control structures for process flow diagrams with large language models
Piping and Instrumentation Diagrams (P&IDs)
PDF Cite DOI
Toward automatic generation of control structures for process flow diagrams with large language models
Digitization of chemical process flow diagrams using deep convolutional neural networks
Flowsheet digitization
PDF Cite DOI
Digitization of chemical process flow diagrams using deep convolutional neural networks
Geometry optimization of a continuous millireactor via CFD and Bayesian optimization
Geometry optimization
PDF Cite DOI
Geometry optimization of a continuous millireactor via CFD and Bayesian optimization
Learning from flowsheets: A generative transformer model for autocompletion of flowsheets
Flowsheets autocompletion
PDF Cite DOI
Learning from flowsheets: A generative transformer model for autocompletion of flowsheets
SFILES 2.0: an extended text-based flowsheet representation
SFILES 2.0
PDF Cite DOI
SFILES 2.0: an extended text-based flowsheet representation
Flowsheet generation through hierarchical reinforcement learning and graph neural networks
Reinforcement learning for process design
PDF Cite DOI
Flowsheet generation through hierarchical reinforcement learning and graph neural networks
Graph neural networks for temperature-dependent activity coefficient prediction of solutes in ionic liquids
Porperty prediction
PDF Cite DOI
Graph neural networks for temperature-dependent activity coefficient prediction of solutes in ionic liquids
Efficient Bayesian Uncertainty Estimation for nnU-Net
The self-configuring nnU-Net has achieved leading performance in a large range of medical image segmentation challenges. It is widely …
PDF Cite DOI
Efficient Bayesian Uncertainty Estimation for nnU-Net
Flowsheet Recognition using Deep Convolutional Neural Networks
Flowsheets are the most important building blocks to define and communicate the structure of chemical processes. Gaining access to …
PDF Cite DOI
Flowsheet Recognition using Deep Convolutional Neural Networks
HybridML: Open source platform for hybrid modeling
A tool for hybrid modeling.
Cite
HybridML: Open source platform for hybrid modeling
Physical pooling functions in graph neural networks for molecular property prediction
Physical pooling functions
PDF Cite DOI
Physical pooling functions in graph neural networks for molecular property prediction
Multi-objective Bayesian optimisation of a two-step synthesis of p-cymene from crude sulphate turpentine
Production of functional molecules from renewable bio-feedstocks and bio-waste has the potential to significantly reduce the greenhouse …
PDF Cite DOI
Multi-objective Bayesian optimisation of a two-step synthesis of p-cymene from crude sulphate turpentine
Pushing nanomaterials up to the kilogram scale – An accelerated approach for synthesizing antimicrobial ZnO with high shear reactors, machine learning and high-throughput analysis
Novel materials are the backbone of major technological advances. However, the development and wide-scale introduction of new …
PDF Cite DOI
Pushing nanomaterials up to the kilogram scale – An accelerated approach for synthesizing antimicrobial ZnO with high shear reactors, machine learning and high-throughput analysis
Efficient hybrid multiobjective optimization of pressure swing adsorption
Pressure swing adsorption (PSA) is an energy-efficient technology for gas separation, while the multiobjective optimization of PSA is a …
PDF Cite DOI
Efficient hybrid multiobjective optimization of pressure swing adsorption
Machine learning in chemical engineering: A perspective
Discussion of perspecitves for future interdisciplinary research and transformation of chemical engineering by identifying challenges and formulation problems for machine learning.
PDF Cite DOI
Machine learning in chemical engineering: A perspective
Insight to gene expression from promoter libraries with the machine learning workflow Exp2Ipynb
Metabolic engineering relies on modifying gene expression to regulate protein concentrations and reaction activities. The gene …
PDF Cite DOI
Insight to gene expression from promoter libraries with the machine learning workflow Exp2Ipynb
Chemical data intelligence for sustainable chemistry
This study highlights new opportunities for optimal reaction route selection from large chemical databases brought about by the rapid …
PDF Cite DOI
Chemical data intelligence for sustainable chemistry
Designing production-optimal alternative fuels for conventional, flexible-fuel, and ultra-high efficiency engines
Road transportation needs to abandon fossil fuels. One promising alternative are renewable fuels for internal combustion engines. We …
PDF Cite DOI
Designing production-optimal alternative fuels for conventional, flexible-fuel, and ultra-high efficiency engines
Deterministic global optimization with Gaussian processes embedded
Gaussian processes (Kriging) are interpolating data-driven models that are frequently applied in various disciplines. Often, Gaussian …
PDF Cite Code DOI
Deterministic global optimization with Gaussian processes embedded
Obey validity limits of data-driven models through topological data analysis and one-class classification
Data-driven models are becoming increasingly popular in engineering, on their own or in combination with mechanistic models. Commonly, …
PDF Cite DOI
Obey validity limits of data-driven models through topological data analysis and one-class classification
Globally optimal working fluid mixture composition for geothermal power cycles
Numerical optimization is very useful for design and operation of energy processes. As the design has a major impact on the economics …
PDF Cite DOI
Globally optimal working fluid mixture composition for geothermal power cycles
The potential of hybrid mechanistic/data‐driven approaches for reduced dynamic modeling: application to distillation columns
Extensive literature has considered reduced, but still highly accurate, nonlinear dynamic process models, particularly for distillation …
PDF Cite DOI
The potential of hybrid mechanistic/data‐driven approaches for reduced dynamic modeling: application to distillation columns
Deterministic global superstructure-based optimization of an organic Rankine cycle
Organic Rankine cycles (ORCs) offer a high structural design flexibility. The best process structure can be identified via the …
PDF Cite DOI
Deterministic global superstructure-based optimization of an organic Rankine cycle
Modelling circular structures in reaction networks: Petri nets and reaction network flux analysis
Optimal reaction pathways for the conversion of renewable feedstocks are often examined by reaction network flux analysis. An …
PDF Cite DOI
Modelling circular structures in reaction networks: Petri nets and reaction network flux analysis
Hybrid mechanistic data-driven modeling for the deterministic global optimization of a transcritical organic Rankine cycle
Global optimization is desirable for the design of chemical and energy processes as design decisions have a significant influence on …
PDF Cite DOI
Hybrid mechanistic data-driven modeling for the deterministic global optimization of a transcritical organic Rankine cycle
Graph neural networks for prediction of fuel ignition quality
Prediction of combustion-related properties of (oxygenated) hydrocarbons is an important and challenging task for which quantitative …
PDF Cite DOI Software
Graph neural networks for prediction of fuel ignition quality
Multi-scale membrane process optimization with high-fidelity ion transport models through machine learning
Innovative membrane technologies optimally integrated into large separation process plants are essential for economical water treatment …
PDF Cite DOI
Multi-scale membrane process optimization with high-fidelity ion transport models through machine learning
Nonlinear scheduling with time‐variable electricity prices using sensitivity‐based truncations of wavelet transforms
We propose an algorithm for scheduling subject to time-variable electricity prices using nonlinear process models that enables long …
PDF Cite DOI
Nonlinear scheduling with time‐variable electricity prices using sensitivity‐based truncations of wavelet transforms
Deterministic global nonlinear model predictive control with neural networks embedded
Nonlinear model predictive control requires the solution of nonlinear programs with potentially multiple local solutions. Here, …
PDF Cite DOI
Deterministic global nonlinear model predictive control with neural networks embedded
Working fluid selection for organic rankine cycles via deterministic global optimization of design and operation
The performance of an organic Rankine cycle (ORC) relies on process design and operation. Simultaneous optimization of design and …
PDF Cite DOI
Working fluid selection for organic rankine cycles via deterministic global optimization of design and operation
Simultaneous rational design of ion separation membranes and processes
Economically viable water treatment process plants for drinking water purification are a prerequisite for sustainable supply of safe …
PDF Cite DOI
Simultaneous rational design of ion separation membranes and processes
Automated self-optimisation of multi-step reaction and separation processes using machine learning
There has been an increasing interest in the use of automated self-optimising continuous flow platforms for the development and …
PDF Cite DOI
Automated self-optimisation of multi-step reaction and separation processes using machine learning
Wavelet-based grid-adaptation for nonlinear scheduling subject to time-variable electricity prices
Using nonlinear process models in discrete-time scheduling typically prohibits long planning horizons with fine temporal …
PDF Cite DOI
Wavelet-based grid-adaptation for nonlinear scheduling subject to time-variable electricity prices
Impact of accurate working fluid properties on the globally optimal design of an organic Rankine cycle
Deterministic global optimization of process flowsheets has so far mostly been limited to simplified thermodynamic models. Herein, we …
PDF Cite DOI
Impact of accurate working fluid properties on the globally optimal design of an organic Rankine cycle
Deterministic global process optimization: Flash calculations via artificial neural networks
We recently demonstrated the potential of deterministic global optimization in a reduced-space formulation for flowsheet optimization. …
PDF Cite DOI
Deterministic global process optimization: Flash calculations via artificial neural networks
Machine learning and molecular descriptors enable rational solvent selection in asymmetric catalysis
Rational solvent selection remains a significant challenge in process development. Here we describe a hybrid mechanistic-machine …
PDF Cite DOI
Machine learning and molecular descriptors enable rational solvent selection in asymmetric catalysis
Deterministic global optimization with artificial neural networks embedded
Artificial neural networks are used in various applications for data-driven black-box modeling and subsequent optimization. Herein, we …
PDF Cite DOI
Deterministic global optimization with artificial neural networks embedded
Deterministic global process optimization: Accurate (single-species) properties via artificial neural networks
Global deterministic process optimization problems have recently been solved efficiently in a reduced-space by automatic propagation of …
PDF Cite DOI
Deterministic global process optimization: Accurate (single-species) properties via artificial neural networks
Model-based bidding strategies on the primary balancing market for energy-intense processes
Energy-intense enterprises that flexibilize their electricity consumption can market this either at electricity spot markets or by …
PDF Cite DOI
Model-based bidding strategies on the primary balancing market for energy-intense processes
Rational design of ion separation membranes
Synthetic membranes for desalination and ion separation processes are a prerequisite for the supply of safe and sufficient drinking …
PDF Cite DOI
Rational design of ion separation membranes
Machine learning meets continuous flow chemistry: Automated optimization towards the Pareto front of multiple objectives
Automated development of chemical processes requires access to sophisticated algorithms for multi-objective optimization, since …
PDF Cite DOI
Machine learning meets continuous flow chemistry: Automated optimization towards the Pareto front of multiple objectives
Dynamic modeling and optimization of sustainable algal production with uncertainty using multivariate Gaussian processes
Dynamic modeling is an important tool to gain better understanding of complex bioprocesses and to determine optimal operating …
PDF Cite DOI
Dynamic modeling and optimization of sustainable algal production with uncertainty using multivariate Gaussian processes
Correction to: Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm
PDF Cite DOI
Correction to: Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm
Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm
Many engineering problems require the optimization of expensive, black-box functions involving multiple conflicting criteria, such that …
PDF Cite DOI
Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm
The concept of selectivity control by simultaneous distribution of the oxygen feed and wall temperature in a microstructured reactor
This paper explores the feasibility of controlling the selectivity of a partial oxidation reaction by simultaneous modulation of local …
PDF Cite DOI
The concept of selectivity control by simultaneous distribution of the oxygen feed and wall temperature in a microstructured reactor
A multiobjective optimization including results of life cycle assessment in developing biorenewables-based processes
A decision support tool has been developed that uses global multiobjective optimization based on 1) the environmental impacts, …
PDF Cite DOI
A multiobjective optimization including results of life cycle assessment in developing biorenewables-based processes
Techno-economic optimization of a green-field post-combustion CO2 capture process using superstructure and rate-based models
A techno-economic optimization of a commercial-scale, amine-based, post-combustion CO2 capture process is carried out. The most …
PDF Cite DOI
Techno-economic optimization of a green-field post-combustion CO2 capture process using superstructure and rate-based models