用图模型提升建筑系统故障诊断效率与准确率
GRID: Graph-based Reasoning for Intervention and Discovery in Built Environments
- 融合约束搜索、神经结构方程与语言模型先验，构建因果发现流程
- 在真实数据上达F1=0.89，控制环境下实现完全正确恢复（F1=1.00）
- 适合建筑运维、智能楼宇系统研发人员参考
商业建筑中手动暖通空调故障诊断耗时8-12小时，准确率仅60%，因分析止于相关性而非因果性。为弥补此差距，我们提出GRID（基于图的干预与发现框架），一个三阶段因果发现流程，结合约束搜索、神经结构方程建模和语言模型先验，从建筑传感器数据中恢复有向无环图。在六个基准上测试：合成房间、EnergyPlus模拟、ASHRAE Great Energy Predictor III数据集及真实办公环境测试平台，GRID的F1分数在0.65至1.00之间，三个受控环境（基础、隐藏、物理）实现完全恢复（F1=1.00），真实数据表现优异（F1=0.89于ASHRAE，0.86于噪声条件）。该方法在所有评估场景中均优于十种基线模型。干预调度在多数情况下操作影响低（成本≤0.026），同时降低风险指标。框架整合约束方法、神经架构与领域语言模型提示，解决建筑分析中的观测-因果鸿沟。
原文摘要 · Abstract (English)
Manual HVAC fault diagnosis in commercial buildings takes 8-12 hours per incident and achieves only 60 percent diagnostic accuracy, reflecting analytics that stop at correlation instead of causation. To close this gap, we present GRID (Graph-based Reasoning for Intervention and Discovery), a three-stage causal discovery pipeline that combines constraint-based search, neural structural equation modeling, and language model priors to recover directed acyclic graphs from building sensor data. Across six benchmarks: synthetic rooms, EnergyPlus simulation, the ASHRAE Great Energy Predictor III dataset, and a live office testbed, GRID achieves F1 scores ranging from 0.65 to 1.00, with exact recovery (F1 = 1.00) in three controlled environments (Base, Hidden, Physical) and strong performance on real-world data (F1 = 0.89 on ASHRAE, 0.86 in noisy conditions). The method outperforms ten baseline approaches across all evaluation scenarios. Intervention scheduling achieves low operational impact in most scenarios (cost <= 0.026) while reducing risk metrics compared to baseline approaches. The framework integrates constraint-based methods, neural architectures, and domain-specific language model prompts to address the observational-causal gap in building analytics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。