Flowsheet Recognition using Deep Convolutional Neural Networks

Book chapter (2022)

Authors

L. Schulze Balhorn ChemE/Product and Process Engineering - AS
Q. Gao ChemE/Product and Process Engineering - AS
Dominik Goldstein Rheinisch-Westfälische Technische Hochschule
A.M. Schweidtmann ChemE/Product and Process Engineering - AS
Research Group
ChemE/Product and Process Engineering (AS) (TU Delft)
Copyright: © 2022 L. Schulze Balhorn, Q. Gao, Dominik Goldstein, A.M. Schweidtmann
DOI: https://doi.org/10.1016/B978-0-323-85159-6.50261-X
Image Classification Deep Learning Data Mining Transfer Learning Flowsheet
More Info
expand_more

Published Date

2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Applied Sciences

Department

ChemE/Chemical Engineering

Research Group

ChemE/Product and Process Engineering

Abstract

Flowsheets are the most important building blocks to define and communicate the structure of chemical processes. Gaining access to large data sets of machine-readable chemical flowsheets could significantly enhance process synthesis through artificial intelligence. A large number of these flowsheets are publicly available in the scientific literature and patents but hidden among innumerable other figures. Therefore, an automatic program is needed to recognize flowsheets. In this paper, we present a deep convolutional neural network (CNN) that can identify flowsheets within images from literature. We use a transfer learning approach to initialize the CNN's parameter. The CNN reaches an accuracy of 97.9% on an independent test set. The presented algorithm can be combined with publication mining algorithms to enable an autonomous flowsheet mining. This will eventually result in big chemical process databases.