基于贝叶斯理论的城市供水管网泄漏在线检测与定位

Bayesian theorem based on-line leakage detection and localization of municipal water supply network

许多城市的供水管网都安装了SCADA(Supervisory Control And Data Acquisition)系统,基于SCADA系统监测到的数据可对管网泄漏进行检测。通过引进统计学概率论中一基本定理——贝叶斯定理来建立管网泄漏的在线检测与定位模型,一定程度上解决了水力模拟误差、测量误差、测点配置等因素导致的不确定性问题。模型通过实例考核取得较为满意的诊断结果。

Supervisory Control And Data Acquisition （SCADA） system has been installed in many municipal water supply networks. Now the Bayesian system identification methodology is proposed to identify the location and the severity of damage in a water supply network by on-line water pressures monitoring at some selected positions of the network, which can treat explicitly the uncertainties arising from the hydraulic model error, measurement error and sensor configuration. This model has been examined by an actual water network, and the result is satisfying.