Synthesis of separation processes with reinforcement learning
This work addresses process synthesis for chemical engineering, but it is incremental as it applies an existing RL method to a new domain with noted limitations.
The paper tackled the design and optimization of a distillation sequence for separating a hydrocarbon mixture using reinforcement learning integrated with commercial simulator Aspen Plus, achieving learning behavior and increased profit, though the simulation was slow (190 hours) and unsuitable for parallelization.
This paper shows the implementation of reinforcement learning (RL) in commercial flowsheet simulator software (Aspen Plus V12) for designing and optimising a distillation sequence. The aim of the SAC agent was to separate a hydrocarbon mixture in its individual components by utilising distillation. While doing so it tries to maximise the profit produced by the distillation sequence. All actions of the agent were set by the SAC agent in Python and communicated in Aspen Plus via an API. Here the distillation column was simulated by use of the build-in RADFRAC column. With this a connection was established for data transfer between Python and Aspen and the agent succeeded to show learning behaviour, while increasing profit. Although results were generated, the use of Aspen was slow (190 hours) and Aspen was found unsuitable for parallelisation. This makes that Aspen is incompatible for solving RL problems. Code and thesis are available at https://github.com/lollcat/Aspen-RL