Application of neural network in heating network leakage fault diagnosis  

神经网络在供热管网泄漏故障诊断中的应用(英文)

作　　者：雷翠红[1] 邹平华[1] 

机构地区：[1]哈尔滨工业大学市政环境工程学院,哈尔滨150090

出　　处：《Journal of Southeast University(English Edition)》2010年第2期173-176,共4页东南大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No.50378029)

摘　　要：In order to investigate the leak detection strategy of a heating network,a space-based simulation mathematical model for the heating network under leakage conditions is built by graph theory.The pressure changes of all the nodes in the heating network are obtained from node leak and pipe leak conditions.Then,a leakage diagnosis system based on the back propagation（BP）neural network is established.This diagnosis system can predict the leakage pipe by collecting the pressure change data of the monitoring points,which can preliminary estimate the leak location.The usefulness of this system is proved by an example.The experimental results show that the forecast accuracy by this diagnosis system can reach 100%.为了研究供热管网泄漏检测策略,利用图论理论构建了一个基于空间管网的泄漏工况水力计算数学模型,得出节点泄漏和管段泄漏工况下管网各点的压力变化情况.然后,采用人工神经网络方法建立了一个基于BP神经网络的供热管网泄漏诊断系统.该诊断系统可根据管网中压力监测点的压力变化定位泄漏管段,实现对泄漏点位置的初步估计.最后,通过实例验证了该方法的有效性.实验结果表明,这种诊断系统对泄漏管段的预测准确率达到100%.

关 键 词：heating network FAULT DIAGNOSIS artificial neural network 

分 类 号：TU995[建筑科学—供热、供燃气、通风及空调工程]