Proceedings of ESCAPE 35ISSN: 2818-4734
Volume: 4 (2025)
Table of Contents
LAPSE:2025.0418
Published Article
LAPSE:2025.0418
Rule-Based Autocorrection of Piping and Instrumentation Diagrams (P&IDs) on Graphs
Lukas Schulze Balhorn, Niels Seijsener, Kevin Dao, Minji Kim, Dominik P. Goldstein, Ge H. M. Driessen, Artur M. Schweidtmann
June 27, 2025
Abstract
A piping and instrumentation diagram (P&ID) is a central reference document in chemical process engineering. Currently, chemical engineers manually review P&IDs through visual inspection to find and rectify errors. However, engineering projects can involve hundreds to thousands of P&ID pages, creating a significant revision workload. This study proposes a rule-based method to support engineers with error detection and correction in P&IDs. The method is based on a graph representation of P&IDs, enabling automated error detection and correction, i.e., autocorrection, through rule graphs. We use our pyDEXPI Python package to generate P&ID graphs from DEXPI-standard P&IDs. In this study, we developed 33 rules based on chemical engineering knowledge and heuristics, with five selected rules demonstrated as examples. A case study on an illustrative P&ID validates the reliability and effectiveness of the rule-based autocorrection method in revising P&IDs.
Record ID
LAPSE:2025.0418
Keywords
Autocorrection, P&ID graphs, pyDEXPI
Subject
Energy Systems
Suggested Citation
Balhorn LS, Seijsener N, Dao K, Kim M, Goldstein DP, Driessen GHM, Schweidtmann AM. Rule-Based Autocorrection of Piping and Instrumentation Diagrams (P&IDs) on Graphs. Systems and Control Transactions 4:1656-1661 (2025) https://doi.org/10.69997/sct.150968
Author Affiliations
Balhorn LS: Process Intelligence Research Group, Department of Chemical Engineering, Delft University of Technology, The Netherlands
Seijsener N: Fluor BV, Amsterdam, The Netherlands
Dao K: Fluor BV, Amsterdam, The Netherlands
Kim M: Process Intelligence Research Group, Department of Chemical Engineering, Delft University of Technology, The Netherlands
Goldstein DP: Process Intelligence Research Group, Department of Chemical Engineering, Delft University of Technology, The Netherlands
Driessen GHM: Fluor BV, Amsterdam, The Netherlands
Schweidtmann AM: Process Intelligence Research Group, Department of Chemical Engineering, Delft University of Technology, The Netherlands
Journal Name
Systems and Control Transactions
Volume
4
First Page
1656
Last Page
1661
Year
2025
Publication Date
2025-07-01
DOI:
https://doi.org/10.69997/sct.150968
Version Comments
Original Submission
Other Meta
PII: 1656-1661-1123-SCT-4-2025, Publication Type: Journal Article
Record Map
Published Article

LAPSE:2025.0418
This Record
External Link

https://doi.org/10.69997/sct.150968
Article DOI
Download
Files
Download 1v1.pdf (1.1 MB)
Jun 27, 2025
Main Article
[Full Details]
License
CC BY-SA 4.0
[details]
Meta
Record Statistics
Record Views
880
Version History
[v1] (Original Submission)
Jun 27, 2025
 
Verified by curator on
Jun 27, 2025
This Version Number
v1
Citations
LAPSE:2025.0418
Most Recent
LAPSE:2025.0418v1
This Version
URL Here
http://psecommunity.org/LAPSE:2025.0418
 
Record Owner
PSE Press
Links to Related Works
Directly Related to This Work
https://doi.org/10.69997/sct.150968
Article DOI
References Cited
  1. Theisen MF, Flores KN, Schulze Balhorn L, Schweidtmann AM. Digitization of chemical process flow diagrams using deep convolutional neural networks. Digital Chemical Engineering 6:100072 (2023) https://doi.org/10.1016/j.dche.2022.100072
  2. Theißen M, Wiedau M. DEXPI P&ID specification. DEXPI Initiative, version 1.3 (2021)
  3. Schweidtmann AM. Generative artificial intelligence in chemical engineering. Nature Chemical Engineering 1:193-193 (2024) https://doi.org/10.1038/s44286-024-00041-5
  4. Bayer J, Sinha A. Graph-based manipulation rules for piping and instrumentation diagrams. LEVIA'19 (2019) https://doi.org/10.31219/osf.io/dynqj
  5. Dzhusupova R, Banotra R, Bosch J, Olsson HH. Using artificial intelligence to find design errors in engineering drawings. Journal of Software: Evolution and Process 35(12) (2023) https://doi.org/10.1002/smr.2543
  6. Oeing J, Brandt K, Wiedau M, Tolksdorf G, Welscher W, Kockmann N. Graph learning in machine-readable plant topology data. Chemie Ingenieur Technik 95(7):1049-1060 (2023) https://doi.org/10.1002/cite.202200223
  7. Mizanur Rahman S, Bayer J, Dengel A. Graph-based object detection enhancement for symbolic engineering drawings. Document Analysis and Recognition - ICDAR 2021 Workshops. 74-90 (2021) https://doi.org/10.1007/978-3-030-86198-8_6
  8. Schulze Balhorn L, Caballero M, Schweidtmann AM. Toward autocorrection of chemical process flowsheets using large language models. Computer Aided Chemical Engineering. 53:3109-3114 (2024) https://doi.org/10.1016/B978-0-443-28824-1.50519-6
  9. Goldstein DP, Schulze Balhorn L, Schweidtmann AM. pyDEXPI: A Python implementation and toolkit for the DEXPI information model. Unpublished manuscript (2024)
  10. Cordella LP, Foggia P, Sansone C, Vento M. A (sub) graph isomorphism algorithm for matching large graphs. IEEE transactions on pattern analysis and machine intelligence 26(10):1367-1372 (2004) https://doi.org/10.1109/TPAMI.2004.75
  11. Toghraei, M. Piping and instrumentation diagram development. John Wiley & Sons (2019) https://doi.org/10.1002/9781119329503
  12. Woolf P. Chemical Process Dynamics and Controls. Open Textbook Library. University of Michigan Engineering Controls Group (2009) https://books.google.nl/books?id=Op87vwEACAAJ
  13. Schweidtmann AM, Esche E, Fischer A, Kloft M, Repke JU, Sager S, & Mitsos A. Machine learning in chemical engineering: A perspective. Chemie Ingenieur Technik 93(12), 2029-2039 (2021) https://doi.org/10.1002/cite.202100083