Classification and identification of leakage in central heating networks

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.