人工神经网络模型在应对城市内涝中的应用

现在城市排水系统的规划和运营管理一般不考虑城市下游受纳水体变化的影响,这也是国内城市内涝频发的原因之一。目前,越来越多的城市应用模型来应对城市内涝,模型中受纳水体的水位一直以来都是利用经验设定一个恒定值。本文利用ANN(人工神经网络)技术,以城市上游观测站的实测水位为输入,以城市未来某时段的水位为目标选择合理的参数,建立了预测河流水位模型。利用更准确的动态预测值代替恒定值,可以提高城市排水系统水力模型的精度。选择某地区水位站的资料,对预报模型进行了检验,结果表明,在合理选择输入层数据和预测时间段的条件下,可以取得很好的预报结果。

Artificial Neural Network Model's Application in Urban Water-logging

Nowdays, the water level of downstream isn＇t considered in urban drainage management system. It is one of the reasons to cause urban waterlogged. The hydro model are more and more used in urban flood control, and one of the boundary conditions- river＇s water level is always a invariable data according experience. The ANN artificial neural network can be used to establish the hydro model to forecast the river water level base on the data of upstream hydrological and local station. So the more accurate dynamic forecasting can replace that invariable data. One drainage area is used to verify the accuracy of the ANN model, and the forecasting result prove that the ANN model can be used in urban flood control well, base on reasonable enter data and forecasting time.