English

From Documents to Database: Failure Modes for Industrial Assets

Databases 2025-09-23 v1 Artificial Intelligence Computation and Language

Abstract

We propose an interactive system using foundation models and user-provided technical documents to generate Failure Mode and Effects Analyses (FMEA) for industrial equipment. Our system aggregates unstructured content across documents to generate an FMEA and stores it in a relational database. Leveraging this tool, the time required for creation of this knowledge-intensive content is reduced, outperforming traditional manual approaches. This demonstration showcases the potential of foundation models to facilitate the creation of specialized structured content for enterprise asset management systems.

Cite

@article{arxiv.2509.17834,
  title  = {From Documents to Database: Failure Modes for Industrial Assets},
  author = {Duygu Kabakci-Zorlu and Fabio Lorenzi and John Sheehan and Karol Lynch and Bradley Eck},
  journal= {arXiv preprint arXiv:2509.17834},
  year   = {2025}
}

Comments

7 pages, 4 figures. Artificial Intelligence for Knowledge Acquisition & Management (AI4KAM) Workshop @ IJCAI 2025

R2 v1 2026-07-01T05:49:41.596Z