Water distribution systems (WDSs) face increasing cyber-physical risks, which make reliable anomaly detection essential. Many data-driven models ignore network topology and are hard to interpret, while model-based ones depend strongly on parameter accuracy. This work proposes a hydraulic-aware graph attention network using normalized conservation law violations as features. It combines mass and energy balance residuals with graph attention and bidirectional LSTM to learn spatio-temporal patterns. A multi-scale module aggregates detection scores from node to network level. On the BATADAL dataset, it reaches $F1=0.979$, showing $3.3$pp gain and high robustness under $15\%$ parameter noise.

翻译：供水系统面临日益增长的物理-网络风险，这使得可靠的异常检测变得至关重要。许多数据驱动模型忽略了网络拓扑结构且难以解释，而基于模型的方法则高度依赖参数准确性。本研究提出一种水力感知图注意力网络，以归一化守恒律违例值作为特征。该方法将质量与能量平衡残差同图注意力机制及双向长短期记忆网络相结合，以学习时空模式。多尺度模块将检测分数从节点级聚合至网络级。在BATADAL数据集上，该模型达到$F1=0.979$，显示出$3.3$个百分点的性能提升，并在$15\%$参数噪声下保持高度鲁棒性。