Abstract
In the piping layout design process, it takes a lot of hours to read the piping and instrumentation diagram (P&ID) and find the connection information. P&IDs are often delivered as images or non-digital drawings for various reasons. In this study, to extract connection information automatically from drawing images, we recognize text, symbols, and lines, and organize connection relation based on the objects’ location. Tesseract OCR, an optical character recognition engine, was used for text recognition, and an Object Detection model and OpenCV were used in combination for symbol and line, and those are implemented in Python. Connection between the objects detected was evaluated based on the coordinates of them and some pixel distance considering the drawing resolution. To verify the proposed method, the possibility of extracting drawing information was reviewed by testing 9 P&ID drawings provided by a shipyard. The overall recognition rate was 74.8% for text and more than 97% for symbols. A digital file which includes the connection relation between the pipes and the instruments generated after the recognition stage, and it shows that the method finds the connection between pipe-pipe and pipe-instrument in the accuracy of 76.2% and 89.7% respectively.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Korean Journal of Computational Design and Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
