Wang Jian, Liu Li, Savic Dragan, Fu Guangtao
Centre for Water Systems, University of Exeter, Exeter EX4 4QF, United Kingdom.
School of Civil Engineering, Hefei University of Technology, Hefei 230009, China.
Water Res. 2025 Sep 1;283:123843. doi: 10.1016/j.watres.2025.123843. Epub 2025 May 16.
Pressure estimation is crucial for efficient operation and management of water distribution networks (WDNs). However, it is often challenged by limited sensor observations. While graph neural networks (GNNs) have been used to improve hydraulic and water quality predictions of WDNs, their reliance on homogeneous graphs oversimplifies the diverse roles and interactions of hydraulic components, resulting in lower performance under dynamic system states. This research introduces a novel heterogeneous graph neural network (HGNN) framework, which models control units such as pumps and valves as distinct nodes while preserving their interactions through additional edge types. Experimental results using C-Town as a benchmark demonstrate that HGNN outperforms GNN in terms of accuracy, robustness, and adaptability, achieving a mean absolute percentage error (MAPE) of 1.88 % and a mean absolute error (MAE) of 1.70 m under a 95 % masking rate. Additionally, this study shows that optimal sensor placement reduces MAE by up to 15 %, and the proposed HGNN framework achieves high computational efficiency, highlighting its effectiveness in WDN analysis and management. This research offers an advanced and transferable approach for WDN pressure estimation, serving as a superior alternative to traditional pressure evaluation models.
压力估计对于供水管网（WDN）的高效运行和管理至关重要。然而，它常常受到传感器观测数据有限的挑战。虽然图神经网络（GNN）已被用于改进供水管网的水力和水质预测，但其对同构图的依赖过度简化了水力组件的不同作用和相互作用，导致在动态系统状态下性能较低。本研究引入了一种新颖的异构图神经网络（HGNN）框架，该框架将泵和阀门等控制单元建模为不同的节点，同时通过额外的边类型保留它们之间的相互作用。以C-Town为基准的实验结果表明，HGNN在准确性、鲁棒性和适应性方面优于GNN，在95%的掩码率下，平均绝对百分比误差（MAPE）为1.88%，平均绝对误差（MAE）为1.70米。此外，本研究表明，最优传感器布置可将MAE降低多达15%，并且所提出的HGNN框架具有较高的计算效率，突出了其在供水管网分析和管理中的有效性。本研究为供水管网压力估计提供了一种先进且可转移的方法，是传统压力评估模型的优质替代方案。
