Automated Synthesis of Steady-State Continuous Processes using Reinforcement Learning
This addresses the problem of automating process design in chemical engineering without relying on heuristics, though it appears incremental as it adapts reinforcement learning to a specific domain.
The paper tackled automated flowsheet synthesis for chemical processes by developing a reinforcement learning method called SynGameZero, which models synthesis as a game between competing players and successfully applied it to a reaction-distillation process in a quaternary system.
Automated flowsheet synthesis is an important field in computer-aided process engineering. The present work demonstrates how reinforcement learning can be used for automated flowsheet synthesis without any heuristics of prior knowledge of conceptual design. The environment consists of a steady-state flowsheet simulator that contains all physical knowledge. An agent is trained to take discrete actions and sequentially built up flowsheets that solve a given process problem. A novel method named SynGameZero is developed to ensure good exploration schemes in the complex problem. Therein, flowsheet synthesis is modelled as a game of two competing players. The agent plays this game against itself during training and consists of an artificial neural network and a tree search for forward planning. The method is applied successfully to a reaction-distillation process in a quaternary system.