Summary
Industrial plants keep lots of notes about equipment failures, but these notes are often hard to understand because they use shorthand, misspellings, and inconsistent terms. The authors created Plant Memory, a system that reads these messy maintenance records and turns them into a clean, organized collection of facts with confidence scores and verifications by technicians. This organized knowledge can then be searched by people or AI tools to help diagnose problems more accurately. They show their system works well using real data from a rice plant, improving the accuracy of identifying failure causes compared to raw records.
What this means in practice
- •For industrial maintenance teams: Use Plant Memory to extract and verify failure knowledge from maintenance logs improving diagnostic accuracy and preserving expertise.
- •For ai application developers: Access the verified maintenance ontology through a standard protocol to build AI tools that provide trustworthy failure diagnoses with cited evidence.
Abstract
Maintenance work orders are the largest written record of how industrial equipment fails, yet in most plants they are close to unusable for analysis. Short texts are abbreviated and misspelt, asset identity is buried in free text, work-type labels contradict the work described, and the fields that matter most for reliability (symptom, root cause, action taken) are usually empty. As a result, diagnostic knowledge stays with senior technicians and leaves when they do. We present Plant Memory, a system that applies technical language processing (TLP) to SAP Plant Maintenance (PM) exports and builds an ISO 14224-aligned maintenance ontology in which every extracted statement is a reified fact carrying a confidence score, the evidence it was read from, and a verification state. Extraction is rule-first, with an optional large language model (LLM) acting as a second reader whose disagreements raise a fact's review priority rather than overwrite it. Technicians verify facts through a review queue, answer targeted knowledge-gap questions where failures repeat without a recorded cause, and approve or reject ontology drift proposals when new terms appear. The resulting graph is served to people through a web application and to AI agents through a Model Context Protocol (MCP) server, so both query the same verified knowledge and every answer cites the work orders behind it. On a synthetic 12-month export of 400 work orders from a parboiled-rice plant, rule-based extraction reaches 96.2% component accuracy, 88.9% failure-mode accuracy and 100% root-cause precision at 62% coverage; on 28 diagnostic questions, ranked root causes from the ontology are correct at top-1 in 82.1% of cases against 53.6% for the raw SAP root-cause column.