Automated Flowsheet Synthesis Using Hierarchical Reinforcement Learning: Proof of Concept

Quirin Göttl, Yannic Tönges, Dominik G. Grimm, Jakob Burger

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

Recently we showed that reinforcement learning can be used to automatically generate process flowsheets without heuristics or prior knowledge. For this purpose, SynGameZero, a novel two-player game has been developed. In this work we extend SynGameZero by structuring the agent's actions in several hierarchy levels, which improves the approach in terms of scalability and allows the consideration of more sophisticated flowsheet problems. We successfully demonstrate the usability of our novel framework for the fully automated synthesis of an ethyl tert-butyl ether process.

Original languageEnglish
Pages (from-to)2010-2018
Number of pages9
JournalChemie-Ingenieur-Technik
Volume93
Issue number12
DOIs
StatePublished - 1 Dec 2021

Keywords

  • Artificial intelligence
  • Automated process synthesis
  • Flowsheet synthesis
  • Machine learning
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Automated Flowsheet Synthesis Using Hierarchical Reinforcement Learning: Proof of Concept'. Together they form a unique fingerprint.

Cite this