ESFILES: Intelligent process flowsheet synthesis using process knowledge, symbolic AI, and machine learning

Abstract

Process flowsheet synthesis, design, and simulation require integrated approaches that combine domain knowledge and data-driven methods for fast, efficient, and reliable solutions. However, due to the recent surge in data and machine learning capabilities, there has been a shift towards building purely data-driven systems for process flowsheet synthesis and related problems. Such approaches have certain drawbacks. Here, we present a hybrid method that combines data-driven approaches with domain knowledge to represent process flowsheets and solve problems related to process synthesis, design, and simulation. We present an extended SFILES (or eSFILES) representation, a multi-level hierarchical flowsheet representation with varying degrees of process knowledge. At level 0, flow diagrams are represented as purely text-based SFILES strings. At level 1, the SFILES grammar, along with inferencing algorithms, is used to construct a flowsheet hypergraph explicitly representing flow diagram connectivity. At level 2, specifications needed for material and energy balance calculations are introduced, and, after simulation, the results are also added using annotated flowsheet hypergraphs. Finally, at level 3, a process ontology is connected with the annotated flowsheet hypergraph to include design and operation parameters as well as the detailed simulation results. We discuss this hierarchical framework using several case studies.