Assessment of leakage degree of underground heating primary pipe network based on chaotic simulated annealing neural network

Abstract

The research shows that primary pipe network leak will cause the fluctuations of temperature and conductance around the leak point. There is a complex non-linear relationship between the pipeline leakage and physical quantity, and the leakage of the pipeline can not be assessed by the change of the single physical quantity. In this paper, the assessment model of the leakage degree of the pipe network based on the chaotic simulated annealing neural network is established by on-line monitoring the changes of the physical quantities around the pipe network nodes. The model takes the temperature and conductivity as the input parameters and the leakage degree of the pipe network as the output parameters, which realizes the accurate assessment of the leakage degree of pipe network. Simulation and field experiments show that the assessment model based on chaotic simulated annealing competition neural network has higher accuracy compared with the traditional BP network, which identifies the foundation for the on-line monitoring and accurate assessment of the underground heating primary pipe network leakage.