论文部分内容阅读
作为现代都市的生命线,供水管网在人们的日常生活和城市的发展中占据不可替代的地位,然而爆管问题一直困扰着整个供水行业。针对供水管网爆管事故,该文以流量监测数据为基础,通过分析计量分区(district metering area,DMA)各个出入口流量计的数据关联性,使用聚类算法检测各种事件引起的异常流量数据,然后依据其出入口流量的变化特征识别管线爆管事故。结果表明:该方法应用在多出入口DMA时,识别效果会受到DMA出入口的数量与位置的影响,在出入口数量较少且位置适宜的前提下,能够准确识别爆管事故,并具有较低误报率。
As the lifeline of modern city, the water supply network plays an irreplaceable role in people’s daily life and urban development. However, the problem of squirting has always plagued the entire water supply industry. Aiming at the pipe burst accident in water supply network, based on the traffic monitoring data, this paper analyzes the data relevance of each meter at the entrance and exit of the district metering area (DMA), and uses the clustering algorithm to detect the abnormal traffic data caused by various events , And then identify the pipeline squib according to the change characteristics of its entrance and exit flow. The results show that the proposed method can effectively identify the number and location of DMA ports when using DMA, and accurately identify the squib accident with a lower number of inlets and exits and lower false positives rate.