Process Control Narrative Miner

Knowledge-Enhanced LLMs for Extracting PCN Information

Authors

  • Mohamed Elsheikh ABB AG Corporate Research Center Germany
  • Nicolai Schoch ABB AG Corporate Research Center Germany
  • Marion Hoernicke ABB AG Corporate Research Center Germany
  • Katharina Stark ABB AG Corporate Research Center Germany
  • Thilo Braun ABB AG Corporate Research Center Germany
  • Sebastian Palacio ABB AG Corporate Research Center Germany
  • Nika Strem ABB AG Corporate Research Center Germany

DOI:

https://doi.org/10.17560/atp.v68i5.2831

Keywords:

AI-supported Engineering, Digitalization of Technical Design Specifications, LLM

Abstract

In automation engineering, converting unstructured specifications into machine readable formats remains a key challenge. The “Engineering Data Funnel” (EDF) addresses this by combining neuro-symbolic AI and domain knowledge to process multimodal data. This paper presents an EDF component that extracts structured information from process control narratives (PCNs) using a domain‑knowledge‑augmented, schema‑guided LLM workflow with automated validation, improving reliability
and accuracy over unconstrained LLM prompting.

Published

2026-05-12

Issue

Section

Article / Peer Review

Most read articles by the same author(s)

1 2 3 > >>