TR112: Computer Interpretation of Process and Instrumentation Diagrams

Placeholder Show Content

Abstract/Contents

Abstract

This report describes a prototype system that interprets Process and Instrumentation Diagrams (P&IDs). The system takes a P&ID in a vector CAD file in DXF format and produces an intelligent P&ID model that has symbolic interpretations for system components (e.g., check valve, pumps, etc.) and symbolic attributions (cold water, propane, etc.).

The system finds structure among vectors, recognizes graphic symbols as physical components from a database of components (e.g., valves), interprets annotations that assign text to graphic symbols. Representation of diagrams is a hierarchy of classes based on cellular topology and geometry (the Area-Curve-Vertex graph (ACV)) at the symbol level. Presently, there are about 100 graphic symbols in the database.

The system has recognized 95% of covered graphic symbol instances for a full page of an industrial drawing, with 89% of graphic symbol instances covered (in the database). A drawing with 5,000 vectors required 20 minutes on an SGI Indy 4400SC (approximately 10% faster than a P 5 100MHz on SPECint92). For symbols that are not yet in the database, a "learning" mechanism and a GUI is being developed to construct the ACV data structure of the unknown symbol.

Description

Type of resource text
Date created August 1997

Creators/Contributors

Author Binford, Thomas
Author Chen, T.
Author Kunz, John
Author Law, Kincho

Subjects

Subject CIFE
Subject Center for Integrated Facility Engineering
Subject Stanford University
Subject Process and Instrumentation Diagrams
Subject Symbolic Interpretation
Genre Technical report

Bibliographic information

Access conditions

Use and reproduction
User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.

Preferred citation

Preferred Citation
Binford, Thomas and Chen, T. and Kunz, John and Law, Kincho. (1997). TR112: Computer Interpretation of Process and Instrumentation Diagrams. Stanford Digital Repository. Available at: http://purl.stanford.edu/dg595yz4168

Collection

CIFE Publications

Contact information

Loading usage metrics...