Reinforcement learning for the design of chemical processes using graph neural networks скачать в хорошем качестве

Reinforcement learning for the design of chemical processes using graph neural networks

Qinghe Gao is a PhD student in the Process Intelligence Research group of Dr. Artur Schweidtmann at Delft University of Technology. He is presenting his research on the development of reinforcement learning (RL) for the design of chemical processes. We propose a reinforcement learning algorithm for chemical process design based on 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. References Gao, Qinghe, and Artur M. Schweidtmann. "Deep reinforcement learning for process design: Review and perspective." Current Opinion in Chemical Engineering 44 (2024): 101012. https://doi.org/10.1016/j.coche.2024.... Qinghe Gao et al. “Transfer learning for process design with reinforcement learning”. In: Computer Aided Chemical Engineering. Elsevier, 2023, pp. 2005–2010. https://doi.org/10.1016/B978-0-443-15... Stops, L., Leenhouts, R., Gao, Q., & Schweidtmann, A. M. (2023). Flowsheet generation through hierarchical reinforcement learning and graph neural networks. AIChE Journal, 69(1), e17938. https://doi.org/10.1002/aic.17938