News
Our PhD candidate Max Theisen won the Best Presentation Award at the symposium of the Nederlandse Werkgroep Drogen (NWGD, Dutch Working Group on Drying) for his talk on AI for multistage spray drying.
PhD students Qinghe Gao and Lukas Schulze Balhorn have completed their PhD research. Both will defend their dissertations publicly on Friday, 20 November 2026, in the TU Delft Aula.
Our MSCA Postdoctoral Fellow Ulderico Di Caprio is spending a research secondment as a guest researcher in the Energy and Process Systems Engineering group of Prof. André Bardow at ETH Zürich, as part of his Marie Skłodowska-Curie project CoAUTHOR.
In 2026, three researchers joined the Process Intelligence Research group: Ulderico Di Caprio as a Marie Skłodowska-Curie Postdoctoral Fellow, Tolga Dinc as an associated PhD student from KU Leuven, and Taeyong Woo as a visiting PhD student from Kyung Hee University.
Our paper GraphRAG for engineering diagrams: ChatP ID enables LLM interaction with P IDs by Achmad Anggawirya Alimin and Artur M. Schweidtmann was published in the AIChE Journal .
Our paper A Graph-Based Generative Artificial Intelligence Methodology for Autocorrection of Utility-System P IDs by Lukas Schulze Balhorn, Dominik P. Goldstein, Niels Seijsener, Kevin Dao, Ge H. M. Driessen and Artur M. Schweidtmann was published in Chemie Ingenieur Technik .
Version 1.2.0 of pyDEXPI , our open-source Python package for DEXPI P IDs, was released on PyPI on 14 April 2026.
Our review Multi-agent systems for chemical engineering: a review and perspective by Sophia Rupprecht, Qinghe Gao, Tanuj Karia and Artur M. Schweidtmann was published in Current Opinion in Chemical Engineering .
Last week, our entire PI research group packed up and headed to Zeeland for something a bit different – a week-long hackathon focused on AI for process systems engineering and design.
Anggawirya Alimin, Lukas Schulze Balhorn and Dominik Goldstein won the 2025 Faculty Open Science Award of the Faculty of Applied Sciences at TU Delft for their work on pyDEXPI.
We released version 1.0.0 of pyDEXPI , our open-source Python package for the DEXPI standard for Piping and Instrumentation Diagrams (P IDs). It can now be installed directly from PyPI with pip install pydexpi .
Our paper Accelerating process synthesis with reinforcement learning: Transfer learning from multi-fidelity simulations and variational autoencoders by Qinghe Gao, Haoyu Yang, Maximilian F. Theisen and Artur M. Schweidtmann was published in Computers Chemical Engineering .
Our paper Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligence by Lukas Schulze Balhorn, Kevin Degens and Artur M. Schweidtmann was published in Computers Chemical Engineering .
In November 2024, we introduced DigiCo - Digitization Companion , our AI-based software for the digitization of engineering documents such as Piping and Instrumentation Diagrams (P IDs) and Process Flow Diagrams (PFDs).
On 19 November 2024, Artur gave the IChemE webinar Digitisation of Piping and Instrumentation Diagrams using Computer Vision , hosted by the IChemE Computer Aided Process Engineering (CAPE) Special Interest Group.
Artur received the 2024 W. David Smith, Jr. Graduate Publication Award of the Computing and Systems Technology (CAST) Division of the American Institute of Chemical Engineers (AIChE).
We are thrilled to share the launch of an innovative collaboration in the field of process systems engineering. The Process Intelligence Research Group at Delft University of Technology, in partnership with Siemens and Linde, is embarking on a new project: the development of the P ID Co-Pilot, a Generative AI...
Max, Lukas, Kenji and Artur are awarded the Senior Moulton Medal by Institution of Chemical Engineers IChemE
We are happy to share that Artur receives a Veni grant from NWO (Dutch Research Council) to work on reinforcement learning for chemical process design. As global chemical industries adapt to become greener there is a substantial need to transform the way that chemical processes are designed. Digitization and artificial...
We are glad to share that our master student Maximilian F.Theisen has just published his first Journal paper on Digitization of chemical process flow diagrams using deep convolutional neural networks at Digitial Chemical Engineering Journal . Advances in deep convolutional neural networks led to breakthroughs in many computer vision applications....
I am proud to share the first Dutch article about my scientific work. It was written by Arjen Dijkgraaf for C2W | Mens Molecule . And here is the news link . Initially Artur Schweidtmann studied mechanical engineering. But during a stay at Carnegie Mellon University (USA), he was captivated...
With his presentation on Process synthesis through reinforcement learning, Qinghe Gao won the Best Presentation Award at the CAPE Forum 2022 .
We are glad to share that our PhD student Lukas Schulze Balhorn has just published his first conference paper on Flowsheet Recognition using Deep Convolutional Neural Networks at PSE 2021+ .
We are glad to share that our PhD student Qinghe Gao has just published his first conference paper on Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders at the NeurIPS 2021 workshop Shared Visual Representations in Human and Machine Intelligence (SVRHM) .
Artur Schweidtmann has won a FAIR Data Fund 2021 granted by the the 4TU.ResearchData Community . His proposal is about FAIR scientific publications. The project obtained 73 out of 81 points from three reviewers.
Artur Schweidtmann has won a NWO Open Science Fund with his proposal for an open-source knowledge graph database for chemical engineering. His project is one of the 26 projects that were honored by this call for the first time this year (and the only one from TU Delft). The ChemEng...
I am happy to present our new open-source tool for the MILP optimization of ReLU artificial neural networks. We directly interface #Pyomo and Gurobi Optimization for optimization and #tensorflow for training. Thus, combining state-of-the-art optimization and machine-learning algorithms.
