Research On Water Supply Network Monitoring And Leakage Location Method

Urban water supply systems are the basic guarantee of residents’ lives.In the management process of the water supply pipe network system,water loss caused by leakage needs to be solved urgently,because it will not only lead to the consumption of water resources but also increase the energy consumption of system management and bring water safety risks such as bacteria and pollutant pollution.At present,China’s annual average water shortage is about 40 billion cubic meters,and more than 400 cities have varying degrees of water shortage,136 of which are seriously short of water.In addition,with the improvement of living standards and economic and social development,people’s requirements for water quality are also increasing,so it is necessary to constantly improve and perfect the urban water supply system.In addition to the loss of water resources and water safety issues,the social impact caused by leakage,such as water supply and return interruptions and traffic delays in the case of pipe bursts,are also issues that need to be addressed.Based on the above situation,it is essential to effectively locate the leak and restore the water supply as soon as possible.This paper presents a pressure sensor layout method based on a graph cluster embedded autoencoder(EGAE).Firstly,the EGAE deep clustering algorithm is used to cluster the network nodes based on the topology,structure,and hydraulic characteristics of the network.According to the clustering results,the network nodes are divided into different regions.Then,by calculating the correlation of each node,the representative nodes of each region are selected and set as sensor layout nodes.In the experimental pipe network,the performance of other schemes is compared and analyzed.The experimental results show that the EGAE deep clustering network can effectively integrate the topological structure characteristics and hydraulic characteristics of the pipe network.The sensor nodes laid out in the scheme proposed in this paper can effectively carry out accurate leakage positioning in subsequent positioning models and have higher leakage pipe segment identification accuracy and smaller precise positioning errors compared with other schemes.In the current research,there is a lack of research on the specific location of the leakage point.Combined with the hydraulic data of sensor layout nodes,this paper proposes a precise leakage location framework for a double-branch based on a residual neural network(Res Net).This study proposes a new idea of leakage location in parallel with classification and regression processes.A double-branch structure is used to construct classification and regression modules so that the framework can accurately locate the exact location of leakage points in pipelines.In addition,multiple monitoring mechanisms are designed during the regression process to accelerate the convergence of the model.The results of the two cases show that the framework can accurately identify the location of the leakage point under different experimental conditions,which provides a possibility for accurate positioning.