[1] Lei Cuihong, Zou Pinghua,. Application of neural networkin heating network leakage fault diagnosis [J]. Journal of Southeast University (English Edition), 2010, 26 (2): 173-176. [doi:10.3969/j.issn.1003-7985.2010.02.006]
Copy
Application of neural networkin heating network leakage fault diagnosis(
)
神经网络在供热管网泄漏故障诊断中的应用
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 26
- Issue:
- 2010 2
- Page:
- 173-176
- Research Field:
- Civil Engineering
- Publishing date:
- 2010-06-30
Info
- Title:
- Application of neural networkin heating network leakage fault diagnosis
- 神经网络在供热管网泄漏故障诊断中的应用
- Author(s):
- Lei Cuihong; Zou Pinghua
- School of Municipal and Environmental Engineering, Harbin Institute of Technology, Harbin 150090, China
- Keywords:
- heating network; fault; diagnosis; artificial neural network
- PACS:
- TU995
- DOI:
- 10.3969/j.issn.1003-7985.2010.02.006
- Abstract:
- 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%.
References:
[1] Zhou J H, Qu S L, Zhao H B.A model for pressure-dependent leakage in water distribution network[J].Water & Wastewater Engineering, 2005, 31(8):94-97.(in Chinese)
[2] Lei C H, Zou P H.Investigation and analysis for failure of heat-supply networks in Heilongjiang province[J].District Heating, 2008(5):15-20.(in Chinese)
[3] Belsito S, Lombardi P, Andreussi P, et al.Leak detection in liquefied gas pipelines by artificial neural networks [J].AICHE Journal, 1998, 44(12):2675-2688.
[4] Zhou Z J, Hu C H, Yang J B, et al.Online updating belief rule based system for pipeline leak detection under expert intervention [J].Expert Systems with Applications, 2009, 36(4):7700-7709.
[5] Li L H.The study and analysis of makeup water constant press and leakage condition on hot water pipe network[D].Harbin:School of Municipal and Environmental Engineering of Harbin Institute of Technology, 2008.(in Chinese)
[6] Ministry of Construction.CJJ34—2002 design code of district heating network[S].Beijing:China Architecture & Building Press, 2002.(in Chinese)
[7] Xu J M.Graph theory and application[M].Beijing:University of Science and Technology of China, 1998.(in Chinese)
[8] Хасилева В Я, Меленкова А П. Методы и алгоритмы расчёта тепловых сетей[M]. Масква: Энергия, 1978.
[9] Wang X X, Liu M J, Zou P H.Effect of failure scheduling scheme to reliability of complicated heat-supply network[C]//Proceedings of the 2nd International Conference on Built Environment and Public Health.Shantou, China, 2004:455-461.
Memo
- Memo:
-
Biographies: Lei Cuihong(1981—), female, graduate;Zou Pinghua(corresponding author), female, professor, zph@hit.edu.cn.
Foundation item: The National Natural Science Foundation of China(No.50378029).
Citation: Lei Cuihong, Zou Pinghua.Application of neural network in heating network leakage fault diagnosis[J].Journal of Southeast University(English Edition), 2010, 26(2):173-176.