Digitization of chemical process flow diagrams using deep convolutional neural networks

Maximilian F. Theisen, Kenji Nishizaki Flores, Lukas Schulze Balhorn, Artur M. Schweidtmann*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

5 Citations (Scopus)
372 Downloads (Pure)

Abstract

Advances in deep convolutional neural networks led to breakthroughs in many computer vision applications. In chemical engineering, a number of tools have been developed for the digitization of Process and Instrumentation Diagrams. However, there is no framework for the digitization of process flow diagrams (PFDs). PFDs are difficult to digitize because of the large variability in the data, e.g., there are multiple ways to depict unit operations in PFDs. We propose a two-step framework for digitizing PFDs: (i) unit operations are detected using a deep learning powered object detection model, (ii) the connectivities between unit operations are detected using a pixel-based search algorithm. To ensure robustness, we collect and label over 1000 PFDs from diversified sources including various scientific journals and books. To cope with the high intra-class variability in the data, we define 47 distinct classes that account for different drawing styles of unit operations. Our algorithm delivers accurate and robust results on an independent test set. We report promising results for line and unit operation detection with an Average Precision at 50 percent (AP50) of 88% and an Average Precision (AP) of 68% for the detection of unit operations.

Original languageEnglish
Article number100072
Pages (from-to)11
JournalDigital Chemical Engineering
Volume6
DOIs
Publication statusPublished - 2023

Keywords

  • Deep convolutional neural network
  • Digitalization
  • Flowsheet digitization
  • Machine learning
  • Object detection
  • Process flow diagrams (PFD)

Fingerprint

Dive into the research topics of 'Digitization of chemical process flow diagrams using deep convolutional neural networks'. Together they form a unique fingerprint.

Cite this