Data augmentation for machine learning of chemical process flowsheets

TL;DR

This paper introduces a data augmentation method for chemical process flowsheet data represented in SFILES 2.0 notation, significantly enhancing AI model performance in flowsheet prediction tasks.

Contribution

The paper presents a novel data augmentation technique for SFILES 2.0 flowsheet data, improving AI model accuracy and uncertainty in chemical process design.

Findings

Flowsheet data augmentation reduced prediction uncertainty by 14.7%.

Augmentation enhances AI model performance on limited data.

Applicable to various machine learning models for chemical flowsheets.

Abstract

Artificial intelligence has great potential for accelerating the design and engineering of chemical processes. Recently, we have shown that transformer-based language models can learn to auto-complete chemical process flowsheets using the SFILES 2.0 string notation. Also, we showed that language translation models can be used to translate Process Flow Diagrams (PFDs) into Process and Instrumentation Diagrams (P&IDs). However, artificial intelligence methods require big data and flowsheet data is currently limited. To mitigate this challenge of limited data, we propose a new data augmentation methodology for flowsheet data that is represented in the SFILES 2.0 notation. We show that the proposed data augmentation improves the performance of artificial intelligence-based process design models. In our case study flowsheet data augmentation improved the prediction uncertainty of the flowsheet autocompletion model by 14.7%. In the future, our flowsheet data augmentation can be used for other machine learning algorithms on chemical process flowsheets that are based on SFILES notation.