Evidence‑Driven Reasoning for Industrial Maintenance Using Heterogeneous Data

Fearghal O'Donncha, Nianjun Zhou, Natalia Martinez, James T Rayfield, Fenno F. Heath III, Abigail Langbridge, Roman Vaculin

Keywords: Large Language Models, Explainable AI, Decision Support Systems, Industrial AI, Predictive Maintenance, AI Governance, Human-in-the-Loop Systems

TL;DR: A deployed framework that uses deterministic evidence construction and constrained LLM reasoning to generate auditable maintenance insights from heterogeneous industrial data.

Abstract:

Industrial maintenance platforms contain rich but fragmented evidence, including free-text work orders, heterogeneous operational sensors or indicators, and structured failure knowledge. These sources are often analyzed in isolation, producing alerts or forecasts that do not support conditional decision-making: given this asset history and behavior, what is happening and what action is warranted?

We present Condition Insight Agent, a deployed decision-support framework that integrates maintenance language, behavioral abstractions of operational data, and engineering failure semantics to produce evidence-grounded explanations and advisory actions. The system constrains reasoning through deterministic evidence construction and structured failure knowledge, and applies a rule-based verification loop to suppress unsupported conclusions.

Case studies from production CMMS deployments show that this verification-first design operates reliably under heterogeneous and incomplete data while preserving human oversight. Our results demonstrate how constrained LLM-based reasoning can function as a governed decision-support layer for industrial maintenance.

Submission Type: Deployed

Submission Number: 159