Identification of the Contamination Source Location in the Drinking Water Distribution System Based on the Neural Network Classifier

摘要

The contamination ingression to the Water Distribution System (WDS) may have a major impact on the drinking water consumers health. In the case of the WDS contamination the data from the water quality sensors may be efficiently used for the appropriate disaster management. In this paper the methodology based on the Learning Vector Quantization (LVQ) neural network classifier for the identification of the contamination source location in the WDS is proposed. For that purpose, two algorithms for the simplified representation of the WDS in the form of separate subzones, and the water quality monitoring stations locations in the WDS are proposed. As the result of identification, the appropriate subzone of the WDS is identified as the location of the contamination ingression. Within that identified subzone, the node which is the contamination source node is located. To obtain the all required water contamination data for the proposed classifier synthesis the computer simulations have been performed with the mathematical model of the WDS in Chojnice city in the northern Poland. The promising results of that experiment have been obtained.