Print Email Facebook Twitter Data augmentation for machine learning of chemical process flowsheets Title Data augmentation for machine learning of chemical process flowsheets Author Schulze Balhorn, L. (TU Delft ChemE/Product and Process Engineering) Hirtreiter, E.J. (TU Delft ChemE/Product and Process Engineering) Luderer, Lynn (Student TU Delft) Schweidtmann, A.M. (TU Delft ChemE/Product and Process Engineering) Contributor Kokossis, Antonis (editor) Georgiadis, Michael C. (editor) Pistikopoulos, Efstratios N. (editor) Date 2023 Abstract 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 Process Flow Diagrams (PFDs) into Process and Instrumentation Diagrams (P&IDs). However, artificial intelligence methods require big data and flowsheet data is currently limited. To mitigate this challenge of limited data, we propose a new data augmentation methodology for flowsheet data that is represented in the SFILES 2.0 notation. We show that the proposed data augmentation improves the performance of artificial intelligence-based process design models. In our case study flowsheet data augmentation improved the prediction uncertainty of the flowsheet autocompletion model by 14.7%. In the future, our flowsheet data augmentation can be used for other machine learning algorithms on chemical process flowsheets that are based on SFILES notation. Subject Data AugmentationFlowsheet AutocompletionSFILESTransformers To reference this document use: http://resolver.tudelft.nl/uuid:3835c799-c6b7-441a-a873-5b461c204a74 DOI https://doi.org/10.1016/B978-0-443-15274-0.50320-6 Publisher Elsevier Embargo date 2023-12-30 ISBN 978-0-443-15274-0 Source Computer Aided Chemical Engineering Series Computer Aided Chemical Engineering, 1570-7946, 52 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type book chapter Rights © 2023 L. Schulze Balhorn, E.J. Hirtreiter, Lynn Luderer, A.M. Schweidtmann Files PDF 1_s2.0_B97804431527405032 ... 6_main.pdf 776.3 KB Close viewer /islandora/object/uuid:3835c799-c6b7-441a-a873-5b461c204a74/datastream/OBJ/view