集中供热管网泄漏的分类识别
Classification and identification of leakage in central heating networks
摘要：
提出了一种集中供热管网泄漏位置的分类识别方法。该方法首先利用管网的非稳态水力仿真对集中供热管网某管道发生泄漏的工况进行数值模拟，并记录各换热站的供水压力变化；其次，基于压力信号的经验模态分解（EMD），得到本征模态函数（IMF），利用特征分解构建集中供热管网的泄漏工况数据集；最后，基于K-means算法进行管网分区，并利用K最邻近（KNN）算法进行管网泄漏的分类识别。结果表明，该方法具有较好的性能。
Abstract：
In this paper, a classification and identification method for the leakage location of central heating networks is proposed. Firstly, the unsteady hydraulic simulation of the pipe network is used to simulate the leakage of a pipe in the central heating network, and the change of water supply pressure of each heat exchange station is recorded. Secondly, based on the empirical mode decomposition (EMD) of pressure signal, the intrinsic mode function (IMF) is obtained, and the leakage condition data set of central heating network is constructed by using the eigen decomposition. Finally, the K-means algorithm is used to partition the pipe network, and the K-nearest neighbor (KNN) algorithm is used to classify and identify the leakage of the pipe network. The results show that the method has good performance.
Keywords:heating network; unsteady hydraulic model; numerical simulation; leakage identification; classification and identification