Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data

TL;DR

This paper introduces Condition Insight Agent, a decision-support system that integrates diverse industrial maintenance data sources to provide evidence-based explanations and actions, enhancing reliability and oversight in maintenance decision-making.

Contribution

The paper presents a novel framework that combines heterogeneous data, structured failure knowledge, and rule-based verification to improve industrial maintenance reasoning.

Findings

Reliable operation under incomplete data

Effective suppression of unsupported conclusions

Enhanced human oversight in maintenance decisions

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.