Physics-informed neural networks for dynamic process operations with limited physical knowledge and data

Mehmet Velioglu, Song Zhai, Sophia Rupprecht, Alexander Mitsos, Andreas Jupke, Manuel Dahmen*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

1 Downloads (Pure)

Abstract

In chemical engineering, process data are expensive to acquire, and complex phenomena are difficult to fully model. We explore the use of physics-informed neural networks (PINNs) for modeling dynamic processes with incomplete mechanistic semi-explicit differential–algebraic equation systems and scarce process data. In particular, we focus on estimating states for which neither direct observational data nor constitutive equations are available. We propose an easy-to-apply heuristic to assess whether estimation of such states may be possible. As numerical examples, we consider a continuously stirred tank reactor and a liquid–liquid separator. We find that PINNs can infer immeasurable states with reasonable accuracy, even if respective constitutive equations are unknown. We thus show that PINNs are capable of modeling processes when relatively few experimental data and only partially known mechanistic descriptions are available, and conclude that they constitute a promising avenue that warrants further investigation.
Original languageEnglish
Article number108899
Number of pages13
JournalComputers and Chemical Engineering
Volume192
DOIs
Publication statusPublished - 2024

Keywords

  • Chemical engineering
  • Dynamic process modeling
  • Liquid–liquid separator
  • Physics-informed neural networks
  • State estimation
  • Van de Vusse reaction

Fingerprint

Dive into the research topics of 'Physics-informed neural networks for dynamic process operations with limited physical knowledge and data'. Together they form a unique fingerprint.

Cite this