Boosting autonomous process design and intensification with formalized domain knowledge

Conceptual process design deals with searching for optimal process flowsheets in a large design space. Effective approaches benefit from sensible search space restrictions, commonly carried out by a knowledgeable expert in the form of a superstructure optimization or heuristic rules. To achieve the goal of autonomous process design, knowledge has to be formalized in a machine-readable format.This contribution aims to incorporate an ontological representation of fundamental process knowledge to empower general-purpose design procedures while respecting problem-specific variability. Specifically, the presented framework leverages an ontology to express declarative knowledge (what-is) of processes, phenomena and design tasks to set up the search space and boost a hierarchical reinforcement learning agent which learns the required procedural knowledge (how-to) in order to find an optimal solution. The work is applied in a case study of an intensified steam methane reforming process. Results show that the automated treatment of domain knowledge allows for dynamic search space reduction and achieves better computational efficiency and solution quality, highlighting its potential in autonomous process design approaches.

Automated summary

Conceptual process design involves finding optimal process flowsheets in a large design space. Effective approaches often rely on restricting the search space, which can be done through superstructure optimization or heuristic rules. To enable autonomous process design, it is necessary to formalize knowledge in a machine-readable format. This study proposes incorporating ontological representation of fundamental process knowledge to enhance general-purpose design procedures, while considering problem-specific variability. The framework leverages an ontology to express declarative knowledge and uses a hierarchical reinforcement learning agent to learn procedural knowledge, leading to more efficient and high-quality solutions. The case study on intensified steam methane reforming process demonstrates the benefits of automating domain knowledge in reducing search space and improving computational efficiency and solution quality, highlighting its potential in autonomous process design approaches.