Green Digital

AI-enabled RDS coding

Green Digital is developing AI-driven technology that can propose IEC/ISO 81346 Reference Designation Structure (RDS) codes and related metadata by interpreting common engineering information sources such as P&ID drawings, reports and PDFs. The use case demonstrates how automated RDS coding can accelerate consistent structuring of asset information and make it easier to connect documents, data and 3D/digital twin environments.

What we are piloting

  • Extract relevant asset and system identifiers from heterogeneous inputs (e.g., P&ID drawings, technical reports, specifications and PDFs).
  • Generate or propose RDS codes aligned to agreed RDS aspects, including relationships between objects where possible.
  • Enable human review and correction so that suggested codes become trusted, reusable reference designations.
  • Publish the resulting RDS-coded structures so they can be reused in downstream workflows (e.g., digital twin population, costing, requirements/verification, and handover).

Why it matters for RDS4X

  • Addresses a key adoption barrier: the effort required to establish consistent RDS codes across documentation and tools.
  • Creates a scalable path from document-centric engineering to structured, interoperable asset information.
  • Supports “show & share” by making RDS-coded objects discoverable and linkable across disciplines and lifecycle phases.
  • Provides a foundation for knowledge graphs and digital twins by turning unstructured sources into structured RDS-based entities.

Use case outline

Starting from selected engineering sources, the workflow applies AI-assisted interpretation to identify candidate objects and propose RDS codes. These are reviewed and curated to form a high-quality RDS-coded structure that can be exported or synchronized to other environments (e.g., a knowledge graph store, a 3D viewer, or a digital twin platform). The primary measure of success is increased speed and consistency of RDS coding while maintaining traceability back to source material.


Timeline & status

The use case is being validated iteratively with selected source material and target workflows. Updates and learnings will be shared through RDS4X as results mature.

Partners

Green Digital leads the AI-driven coding technology; the use case is shared via RDS4X to demonstrate how RDS can be established efficiently from existing engineering information sources.

Expected outcomes

  • A practical approach for proposing RDS codes from unstructured and semi-structured engineering sources.
  • Improved speed and consistency of RDS establishment, with traceability back to original drawings/documents.
  • Reusable RDS-coded structures that can populate knowledge graphs and digital twins and support downstream use cases.
  • Lessons learned that can inform RDS4X guidance for scalable RDS adoption.