基于特征聚类的给水管网压力监测点优化布置

为了及时发现城市给水管网中的漏损、爆管等问题,需要在管网中布置压力监测点.现阶段通常依据各节点压力值的相似程度实现压力监测点的布置.针对上述方法未考虑管网节点空间属性的问题,作者提出一种给水管网压力监测点的优化布置方法.该方法通过选取节点的坐标、影响度和压力的标准差3个特征属性构建节点特征矩阵,再利用DBSCAN(density-based spatial clustering of applications with noise)算法对节点特征矩阵进行聚类分析,依据聚类结果最终确定压力监测点的位置和数量.仿真实验结果表明:该方法有效地保证聚类后归属同一类的节点在管网中是连通的,选取的压力监测点空间分布均匀,为实际管网中压力监测点的布置奠定了良好基础.

Optimal location of the pressure monitoring points in water distribution networks based on feature clustering

In order to find problems like leakage and burst which are commonly seen in urban water distribution networks,pressure monitoring points need to be disposed.The pressure monitoring point placement is often based on similar degree of the node pressure data in the current stage.A method of optimal pressure monitoring point location was proposed in this paper because of the above method did not consider spatial properties of network node.The node coordinate,influence and the standard deviation of pressure were selected to establish the node characteristic matrix.The node characteristic matrix was clustered by using DBSCAN (density-based spatial clustering of applications with noise) and the number and location of pressure monitoring point was determined according to clustering result.The experimental results showed that the method ensured that the nodes belonging to the same cluster were connected effectively and the selected pressure monitoring points were uniform in water distribution networks,laying a solid foundation for the pressure monitoring point placement in the actual pipe network.