From Documents to Database: Failure Modes for Industrial Assets
Duygu Kabakci-Zorlu, Fabio Lorenzi, John Sheehan, Karol Lynch, Bradley Eck
公開日: 2025/9/22
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.