IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance

2026-04-25

AI Summary

This work addresses a critical limitation in existing industrial maintenance AI assistants, which often produce overly generalized explanations lacking telemetry grounding, verifiability, and support for counterfactual or actionable reasoning—thereby undermining trust in safety-critical contexts. To bridge this gap, the study introduces, for the first time, a neuro-symbolic approach to industrial asset maintenance question answering, proposing an embodied question answering (EQA) framework that integrates event-based telemetry representations with a Failure Mode and Effects Analysis knowledge graph (FMEA-KG). The resulting system generates explanations tightly aligned with telemetry data, enabling verification and logical inference. Evaluated across four industrial asset datasets, the approach demonstrates substantial performance gains: up to 0.51 improvement in structural validity, 0.47 higher counterfactual accuracy, a 0.64 increase in explanation entailment scores, and approximately 93% reduction in severe over-assertiveness.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web question answering
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Industrial maintenance environments increasingly rely on AI systems to assist operators in understanding asset behavior, diagnosing failures, and evaluating interventions. Although large language models (LLMs) enable fluent natural-language interaction, deployed maintenance assistants routinely produce generic explanations that are weakly grounded in telemetry, omit verifiable provenance, and offer no testable support for counterfactual or action-oriented reasoning that undermine trust in safety-critical settings. We present IndustryAssetEQA, a neurosymbolic operational intelligence system that combines episodic telemetry representations with a Failure Mode Effects Analysis Knowledge Graph (FMEA-KG) to enable Embodied Question Answering (EQA) over industrial assets. We evaluate on four datasets covering four industrial asset types, including rotating machinery, turbofan engines, hydraulic systems, and cyber-physical production systems. Compared to LLM-only baselines, IndustryAssetEQA improves structural validity by up to 0.51, counterfactual accuracy by up to 0.47, and explanation entailment by 0.64, while reducing severe expert-rated overclaims from 28% to 2% (approximately 93% reduction). Code, datasets, and the FMEA-KG are available at https://github.com/IBM/AssetOpsBench/tree/IndustryAssetEQA/IndustryAssetEQA.

Problem

• Embodied Question Answering
• Industrial Asset Maintenance
• Neurosymbolic AI
• Failure Mode Effects Analysis
• Operational Intelligence

Innovation

• Neurosymbolic AI
• Embodied Question Answering
• FMEA Knowledge Graph
• Industrial Asset Maintenance
• Operational Intelligence