CHEME AI Lab

Master Projects

Openings

• M.Sc. Thesis for Artificial Intelligence in Chemical Engineering Research
  This thesis is about the application and development of machine-learning and artificial intelligence algorithms within chemical engineering. We offer a variety of master projects related to deep learning, computer vision, data mining, process modelling. We apply our methods for the optimal design and operation of more sustainable processes. For more information contact: a.schweidtmann@tudelft.nl
• M.Sc. Thesis for Artificial Intelligence in Chemical Engineering Industry
  This thesis is about the industrial application and development of machine-learning and artificial intelligence algorithms within chemical engineering. We offer a variety of master projects in close collaboration with industry. The topics are related to deep learning, computer vision, data mining, process modelling. We apply our methods for the optimal design and operation of more sustainable processes. For more information contact: a.schweidtmann@tudelft.nl
• M.Sc. Thesis for Artificial Intelligence in Medical Image Analysis
  We offer a variety of interesting master projects on AI for medical image analysis, covering medical image segmentation, registration, and interpretation, towards high-performance, generalisable, and interpretable AI for medical imaging. For more information contact: q.tao@tudelft.nl 

Finished

• Digitization of P&IDs using machine learning, Artur Schweidtmann, Winston Oudshoorn (2023/2024) 
• Web application for the digitization of engineering diagrams with machine learning, Artur Schweidtmann, Nils Polarek (2023/2024) 
• Automating life cycle assessment from simulations for circular economy, Artur Schweidtmann, Daniel Bakker (2023/2024) 
• gegevens opgevraagd, Artur Schweidtmann, Tim Faruss (2023/2024) 
• Web application for the digitization of engineering diagrams with machine learning, Artur Schweidtmann, Tobias Gies (2023/2024) 
• Digitization of P&IDs using machine learning, Artur Schweidtmann, Linus Hartz (2023/2024) 
• Automatic Life-Cycle Assessment, Artur Schweidtmann, Sophie Rupprecht (2023/2024) 
• Knowledge graphs and model implementation, Artur Schweidtmann, Jeroen Rood (2023/2024) 
• RL for process design, Artur Schweidtmann, Ernst Uijthof (2023/2024) 
• Development of soft sensors for auto-quality of spray dryer powders, Artur Schweidtmann, Lynn Luderer (2023/2024) 
• Rule-based error detection in chemical processes using the DEXPI format, Artur Schweidtmann, Minji Kim (2023/2024) 
• Cost approximation of P&IDs, Artur Schweidtmann, Rianne van Zanen (2023/2024) 
• Routing of lines in P&IDs, Artur Schweidtmann, Manuel Albach (2023/2024) 
• Natural Language Processing for Information Extraction in Chemical Engineering, Artur Schweidtmann, Philipus Putra (2023/2024) 
• Automatic generation of piping and instrumentation diagrams (P&IDs) with artificial intelligence, Artur Schweidtmann, Edwin Hirtreiter (2022/2023) 
• Early-stage investigation of the techno-economic and environmental feasibility of using perhydro-dibenzyltoluene as a hydrogen carrier to facilitate the Africa-EU renewable energy transition, Artur Schweidtmann, Pascalle Drijver (2022/2023) 
• Images in chemical engineering, Artur Schweidtmann, Abdessamad Boumaiz (2022/2023) 
• The Materials Knowledge Graph, Artur Schweidtmann, Clara van Hall (2022/2023) 
• Mixed Integer (Non-) Linear Programming Formulations of Graph Neural Networks, Artur Schweidtmann, Tom McDonald (2022/2023) 
• Pretraining reinforcement learning agents for process synthesis with variational autoencoders, Artur Schweidtmann, Maximilian Theisen (2022/2023) 
• Autocorrection of process diagrams using Natural Language Processing, Artur Schweidtmann, Marc Caballero Meqia (2022/2023) 
• Environmental impact prediction of chemical processes using graph neural networks, Artur Schweidtmann, Alessandro Laera (2022/2023) 
• Transfer learning for reinforcement learning in process synthesis, Artur Schweidtmann, Haoyu Yang (2022/2023) 
• Automated Control Structure Prediction, Artur Schweidtmann, Kevin Degens (2022/2023) 
• Prospects towards automatic conceptual life cycle assessment from chemical process simulations, Artur Schweidtmann, Anna Ossollinska (2022/2023) 
• Multi-objective RL for process synthesis, Artur Schweidtmann, Ralph Sulit Velasquez (2022/2023) 
• Automatic digitization of Piping and Instrumentation Diagrams through deep learning: A novel ontology-informed hierarchical object detection algorithm, Artur Schweidtmann, Giacomo Lastrucci (2022/2023) 
• Line detection evaluation in flowsheet digitization, Artur Schweidtmann, Bart van Slooten (2022/2023) 
• Flowsheet digitization - An extensible architecture for text recognition in process diagrams, Artur Schweidtmann, Yaoxin Zhang (2022/2023) 
• Data Mining and Image Classification for Chemical Engineering Patents, Artur Schweidtmann, Max Corvers (2022/2023) 
• Development of a Knowledge Graph for Chemical Engineering Literature, Artur Schweidtmann, Kevin Dao (2022/2023) 
• Enhancing photovoltaic cell research with large-scale scholarly data mining and figure classification, Artur Schweidtmann, Maurits van der Tol (2022/2023) 
• Creating a Dataset for Several Classes of Chemistry-related Images, Artur Schweidtmann, Johand Karl Lindvall (2022/2023) 
• Self-Supervised Graph Neural Networks for Polymer Property Prediction, Artur Schweidtmann, Tammo Dukker (2022/2023) 
• Quantifying the carbon neutrality of upcycling technologies and assessing supply chains, Artur Schweidtmann, Ozkan Tutar (2022/2023) 
• Flowsheet digitization: Connectivity recognition based on L-CNN model, Artur Schweidtmann, Jiahang Xi (2022/2023) 
• Standardizing Unstructured Chemical Process Data for Effective AI and ML Applications in the Chemical Industry, Artur Schweidtmann, Constantin Lichnog (2022/2023) 
• Metadata Extraction from Process and Instrumentation Diagram Title Blocks, Artur Schweidtmann, Stijn Scholten (2022/2023) 
• Template matching algorithms - An approach for digitization of Piping and Instrumentation Diagrams, Artur Schweidtmann, Robin Stassen (2022/2023) 
• Data augmentation with the task to automatically generate new training data for developing P&IDs from simpler PFDs., Artur Schweidtmann, Giovanni Iorio (2022/2023) 
• A Neo4j Knowledge Graph for Chemical Process Engineering, Artur Schweidtmann, Daniel Miedema (2020/2021)
• Digitization of chemical process flow diagrams using deep convolutional neural networks, Artur Schweidtmann, Kenji Nishizaki Flores (2021/2022) 
• Data mining in chemical flow-sheet mining, Artur Schweidtmann, Shijia Kanq (2021/2022) 
• Flowsheet generation through hierarchical reinforcement learning and graph neural networks, Artur Schweidtmann, Laura Stops (2021/2022) 
• Learning from flowsheets: A generative transformer model for autocompletion of flowsheets, Artur Schweidtmann, Gabriel Vogel (2021/2022) 
• Automatic superstructure optimization of chemical processes, Artur Schweidtmann, Lukas Wille (2021/2022) 
• Learning from flowsheets: A generative transformer model for autocompletion of flowsheets, Artur Schweidtmann, Roel Leenhouts (2021/2022) 
• Connecting chemical process design to knowledge representation, Artur Schweidtmann, Marios Vasileiadis (2021/2022) 
• Reinforcement learning for process synthesis, Artur Schweidtmann, Shachi Marthu Shanbhaq (2021/2022) 
• Digitization of Process Flowsheets Image Recognition Using Mask R-CNN, Artur Schweidtmann, Alex Ruinen (2021/2022) 
• Towards a figure database - Data mining from chemical engineering literature with deep learning, Artur Schweidtmann, Niels van Welzen (2021/2022) 
• Navigating the process space, Artur Schweidtmann, Nicolas Oye (2021/2022) 
• Auto-comletion of flowsheets, Artur Schweidtmann, Lynn Luderer (2021/2022)