基于径向基函数的多闸门控制河流的洪水模拟  

Flood simulations using radial basis functions for complex river flows controlled by sluices

作　　者：郑毅[1] 方红卫[1] 何国建[1] 赵慧明[1] 

机构地区：[1]清华大学水利水电工程系、水沙科学与水利水电工程国家重点实验室,北京100084

出　　处：《清华大学学报（自然科学版）》2008年第12期2061-2064,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金杰出青年基金项目(50325929);国家重点基础研究发展计划项目(2003CB415206)

摘　　要：为了快速而准确地制定联合调度的复杂闸门水利枢纽处的洪水过程的防洪决策,开发了一种快速洪水模拟方法。以位于北京市北运河流域的北关分洪枢纽为例,采用二维水动力学模型计算了由上游来流量、闸门开度和相应下游水位等因素确定的800组工况;把模拟结果作为径向基函数神经网络的训练样本。这样,只用上游来流量、闸门开度、闸下水位就能快速地模拟出该区域的水位和流量。结果表明,模拟一组工况,用该方法只需不到1m in,而用二维模型需3h。Complex river flows controlled by sluices were simulated to enable rapidly accurate flood defense decisions. A 2-D hydrodynamic model was used to simulate for 800 modes for the Beiguan diversion project in Beiyun River in Beijing considering several factors such as upper reach total inflow, each sluice opening height and water level downstream. The simulation results were used to train a radial basis function （RBF） neural network. The water levels and flow rates in the diversion can then he determined quickly using only the upper reach flow rate, each sluice opening height and each sluice water level down stream. Simulations of one mode take less than 1 rain using this method instead of almost 3 h by the 2-D model.

关 键 词：洪水模拟 水动力学模型 径向基函数 实时 

分 类 号：P338.9[天文地球—水文科学]