Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligence

TL;DR

This paper introduces Graph-to-SFILES, a generative AI model that predicts control structures from process topologies represented as graphs, showing promising accuracy improvements especially with limited data.

Contribution

The study proposes a novel graph-based AI approach for control structure prediction, including a new GNN architecture, outperforming sequence-based methods on small datasets.

Findings

Achieves 73.2% top-5 accuracy on 10,000 topologies.

GNN encoder outperforms other architectures.

Significant accuracy gain over sequence methods in small-data scenarios.

Abstract

Control structure design is an important but tedious step in P&ID development. Generative artificial intelligence (AI) promises to reduce P&ID development time by supporting engineers. Previous research on generative AI in chemical process design mainly represented processes by sequences. However, graphs offer a promising alternative because of their permutation invariance. We propose the Graph-to-SFILES model, a generative AI method to predict control structures from flowsheet topologies. The Graph-to-SFILES model takes the flowsheet topology as a graph input and returns a control-extended flowsheet as a sequence in the SFILES 2.0 notation. We compare four different graph encoder architectures, one of them being a graph neural network (GNN) proposed in this work. The Graph-to-SFILES model achieves a top-5 accuracy of 73.2% when trained on 10,000 flowsheet topologies. In addition, the proposed GNN performs best among the encoder architectures. Compared to a purely sequence-based approach, the Graph-to-SFILES model improves the top-5 accuracy for a relatively small training dataset of 1,000 flowsheets from 0.9% to 28.4%. However, the sequence-based approach performs better on a large-scale dataset of 100,000 flowsheets. These results highlight the potential of graph-based AI models to accelerate P&ID development in small-data regimes but their effectiveness on industry relevant case studies still needs to be investigated.