With the advance of new technologies and emergence of the concept of the smart city, there has been a dramatic increase in available information. Water distribution systems (WDSs) in which databases can be updated every few minutes are no exception. Suitable techniques to evaluate available information and produce optimized responses are necessary for planning, operation, and management. This can help identify critical characteristics, such as leakage patterns, pipes to be replaced, and other features. This paper presents a clustering method based on self-organizing maps coupled with k-means algorithms to achieve groups that can be easily labeled and used for WDS decision-making. Three case-studies are presented, namely a classification of Brazilian cities in terms of their water utilities; district metered area creation to improve pressure control; and transient pressure signal analysis to identify burst pipes. In the three cases, this hybrid technique produces excellent results.

随着新技术的进步和智能城市概念的出现，可用信息已大大增加。水分配系统（WDS）可以每隔几分钟更新一次数据库，这也不例外。评估可用信息并产生优化响应的合适技术对于计划，操作和管理是必需的。这可以帮助确定关键特征，例如泄漏模式，要更换的管道和其他特征。本文提出了一种基于自组织映射和k-means算法的聚类方法，以实现可以轻松标记并用于WDS决策的组。提出了三个案例研究，即按照供水设施对巴西城市进行分类；创建区域计量区域以改善压力控制；以及瞬态压力信号分析以识别爆裂的管道。在这三种情况下，这种混合技术会产生出色的结果。