IndustryAssetEQA: 一种用于工业资产维护中具身体验问答的神经符号操作智能系统
IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance
- Artificial Intelligence Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）
- University of South Carolina（南卡罗来纳大学）
- IBM Yorktown（IBM约克镇分公司）
- Indian AI Research Organization（印度人工智能研究组织）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出IndustryAssetEQA系统，结合事件 telemetry 表示与FMEA-KG知识图谱，提升工业资产问答的结构有效性、反事实准确性及解释蕴含性，减少专家评估的过度声称。
AI中文摘要：
工业维护环境日益依赖AI系统帮助操作员理解资产行为、诊断故障并评估干预措施。尽管大语言模型（LLMs）能提供流畅的自然语言交互，但部署的维护助手通常生成通用解释，缺乏 telemetry 支持，无法提供可验证的溯源或可测试的反事实或行动导向推理，从而损害安全关键场景的信任。本文提出IndustryAssetEQA，一种结合事件 telemetry 表示与故障模式影响分析知识图谱（FMEA-KG）的神经符号操作智能系统，以实现工业资产的具身体验问答（EQA）。我们评估了四个涵盖四种工业资产类型的数据集，包括旋转机械、涡轮风扇发动机、液压系统和网络物理生产系统。与仅依赖LLM的基线相比，IndustryAssetEQA在结构有效性上提高0.51，在反事实准确性上提高0.47，在解释蕴含性上提高0.64，同时将严重专家评估的过度声称从28%降至2%（约减少93%）。代码、数据集和FMEA-KG可在https://github.com/IBM/AssetOpsBench/tree/IndustryAssetEQA/IndustryAssetEQA获取。
英文摘要：
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.
