Overview

Learn about exporting intelligent P&IDs to the DEXPI standard and making graph models of them for AI use cases.

Hexagon SPID2GRAPH tool can read Smart P&ID drawings and convert them into unweighted directed multigraphs, which we will call PIDGraph from now on. For example you can then create a P&ID chat function using an LLM under the hood. It is a simple approach but you can already see the value it could provide. Using the P&ID graph as foundation, the LLM is able to provide useful insights. For example it can do these three use cases:

• counting, highlighting and returning elements and their data; explain the process to engineers
• supporting tasks like HAZOP by using the P&ID topology
• using agentic AI to check the quality of a P&ID, if it complies with engineering rules.

And are you also looking to export your Smart P&ID drawings to the industry standard DEXPI 2.0 XML format? The upcoming Hexagon SPID2DEXPI Postprocessor will make it possible.

Mapping is now much easier to configure and customise compared to previous versions of the Postprocessor. The new approach streamlines the setup process, making it more intuitive and flexible for users to define and adjust mapping rules according to project-specific needs.

The conversion procedure is structured into three distinct phases, each designed to address specific technical and semantic challenges. This ensures a robust and accurate transformation of engineering data into a fully compliant DEXPI 2.0 XML document.

Speakers

Jaime Thos Martin, Implementation Consultant & DEXPI Lead, Hexagon Asset Lifecycle Intelligence

Jaime is an implementation consultant and DEXPI lead at Hexagon Asset Lifecycle Intelligence. Prior to this he has worked as an IT Manager for Creative Communications Engineering, an applications engineer for MyAlert and a software developer for UFACEX. Jamie loves solving challenges and he has a BSc in computer science from the University Polytechnic of Madrid.

Martin Bergmann, Principal Strategy Enablement Consulting AI, Hexagon Asset Lifecycle Intelligence

Martin joined Hexagon’s Asset Lifecycle Intelligence division in 2022 as Lead Strategist for AI and Enabling Technologies. Previously, he led product management at Bilfinger Digital Next, part of Bilfinger group. He has an educational background in chemical engineering, business administration and data science.

The material presented has not been peer-reviewed. Any opinions are the presenters' own and do not necessarily represent those of IChemE or the Process Management and Control Special Interest Group. The information is given in good faith but without any liability on the part of IChemE.

Time

09:00–10:00 GMT.

Software

The presentation will be delivered via Microsoft Teams. We recommend downloading the app from the Microsoft website, rather than using the web portal.