基于BP神经网络的城市供水系统管网预测

针对城市供水系统的复杂性、非线性、时变化性以及多因素影响的特点，探讨了建立基于BP神经网络城市供水管网预测的原理，阐述了建立基于BP网络的城市供水时序预测模型方法．根据管网的节点压力历史数据纪录，建立基于神经网络的管网压力时序预测模型，对未来某一时段的节点压力进行预测．从预测过程和结果分析，基于BP神经网络城市供水管网预测方法操作简单，运行速度快，误差修正方便，精度高．图2，表1，参12．

The pipe networks prediction for water distribution systems based on BP networks

Aiming at characteristics of city water distribution systems such as multi -parameters, nonlinear, transitional, complex, as the foundation of establishing model, BP neural networks was selected to research and discussed the principles and mechanisms of neural networks water supply pipe network prediction, and the method was presented how to establish water supply time serial prediction model based on BP neural networks. On the ground of the history datum of node pressure of water distribution systems, water supply pipe network prediction model based on BP neural networks was established, and node pressure in next period of time were predicted by BP neural networks model. Simulation result show the prediction method based on BP neural networks have simplicity of operation, speed rapidness, convenience of modifying errors, high precision. 2figs. , 1 tab. , 12refs.