Helping the Energy Industry Achieve Digital Transformation Through AI
In this 8-weeks challenge, 50 AI changemakers collaborator to help to automatize site schemas in the energy industry building through Computer Vision.
Large Industrial facilities in the Energy industry use different information systems to store technical information about their facilities. These documents capture information about the design, inspection, maintenance, and operations of energy plants.
One of such documents is called the Piping and instrumentation diagram (P&ID), which is a diagram to graphically display a complete system. It includes all connectivity between piping, instruments, valves, and equipment that are present in the system. This document plays a key role in carrying out the daily operations of the facility.
As most of these P&ID documents are currently present only in paper format, they are not interpretable by computers. Hence in this challenge, we will work on building computer vision models for automating the conversion of the P&ID documents to their digital format. This will include detection of different symbols, texts, lines, and their export into computer-readable XML-based format (DEXPI standard derived from ISO 15926).
In this challenge, we will work on building Digital Twins for Large Industrial Facilities. The solution will be integrated into their product for automatic generation of Smart P&IDs from Images and/or PDFs.
The Project Goals
1. Detection and localization of different symbols present in a P&ID.
List of symbols which majorly fall in these categories:
– Line symbols
– Valve symbols
– Piping symbols (tees, flanges, reducers, etc)
– Pumps symbols
– Vessels symbols
– Tanks symbols
– Instrumentation symbols
2. Use of OCR for detection of Tag numbers and then associating them with their respective symbols.
3. Detection of lines that correspond to Pipes and Cables. Mapping them with their LineID number.
Figure: Example P&ID diagram
Reference for reading Symbols, Lines, and TagNumber encoding:
A collaborative experience you never had in your working life! For the next eight weeks, you will not only build AI solutions to make a real-world impact but also go through an entire data science project lifecycle. This covers problem scoping, data collection, and preparation, as well as modeling for deployment.
And the best part is that you will join a global and collaborative team of changemakers. Omdena AI Challenges are not a competition or hackathon but a real-world project that will take your experience of what is possible through collaboration to a new level.