Print Email Facebook Twitter Flowsheet generation through hierarchical reinforcement learning and graph neural networks Title Flowsheet generation through hierarchical reinforcement learning and graph neural networks Author Stops, L. (TU Delft ChemE/Product and Process Engineering) Leenhouts, Roel (Student TU Delft) Gao, Q. (TU Delft ChemE/Product and Process Engineering) Schweidtmann, A.M. (TU Delft ChemE/Product and Process Engineering) Date 2022 Abstract Process synthesis experiences a disruptive transformation accelerated by artificial intelligence. We propose a reinforcement learning algorithm for chemical process design based on a state-of-the-art actor-critic logic. Our proposed algorithm represents chemical processes as graphs and uses graph convolutional neural networks to learn from process graphs. In particular, the graph neural networks are implemented within the agent architecture to process the states and make decisions. We implement a hierarchical and hybrid decision-making process to generate flowsheets, where unit operations are placed iteratively as discrete decisions and corresponding design variables are selected as continuous decisions. We demonstrate the potential of our method to design economically viable flowsheets in an illustrative case study comprising equilibrium reactions, azeotropic separation, and recycles. The results show quick learning in discrete, continuous, and hybrid action spaces. The method is predestined to include large action-state spaces and an interface to process simulators in future research. Subject artificial intelligencegraph convolutional neural networksgraph generationprocess synthesisreinforcement learning To reference this document use: http://resolver.tudelft.nl/uuid:457e1062-732d-4574-9197-1cf8c4439365 DOI https://doi.org/10.1002/aic.17938 ISSN 0001-1541 Source AIChE Journal, 69 (1), 14 Part of collection Institutional Repository Document type journal article Rights © 2022 L. Stops, Roel Leenhouts, Q. Gao, A.M. Schweidtmann Files PDF AIChE_Journal_2022_Stops_ ... tworks.pdf 2.46 MB Close viewer /islandora/object/uuid:457e1062-732d-4574-9197-1cf8c4439365/datastream/OBJ/view