Water quality comprehensive evaluation method for large water distribution network based on clustering analysis

In order to evaluate water quality for large water distribution network comprehensively, two clustering methods, self-organizing map (SOM) and fuzzy c-mean (FCM), were represented. With these two clustering methods, the nodes of a large real water distribution network were divided into some groups considering one or more water quality indicators synchronously. According to the clustering results, the status of water quality of the water network was analyzed. The result showed that the classification of SOM was more coincidental to the real water quality distribution than that of FCM. Some water quality monitors had been installed according to the clustering result of SOM. According to the study, water quality comprehensive evaluation was of significance for water quality monitors location, water network rehabilitation and expansion.