汤河水库实时洪水预报技术研究  

Research of Real-time Flood Forecast Technology in Tanghe Reservoir

作　　者：郑春成[1] 

机构地区：[1]辽宁省汤河水库管理局,辽宁辽阳111000

出　　处：《水利信息化》2012年第3期37-39,43,共4页Water Resources Informatization

摘　　要：汤河水库洪水预报对汤河水库及其下游的防洪安全极其重要,需要研究实时洪水预报技术,以提高洪水预报精度。根据汤河水库自然地理和水文特性,汤河水库实时洪水预报采用汤河水库洪水预报,考虑到各场次洪水预报误差之间存在一定的相依性,故采用人工神经网络方法构建实时校正系统,模型用实际洪水资料进行校准,并用2场较大洪水予以检验。2个场次的校验表明,实时校正能明显地提高洪水预报的精度。The flood forecast of Tanghe reservoir is very important for downstream flood protection. It needs to research the real-time flood forecast technology for improving flood forecasting precision. Based on the physical geography and hydrological features, the real-time flood forecast of Tanghe reservoir uses its flood forecast. In view of the dependence between each flood forecast＇ s error, real-time calibration system is builded with artificial neural networks. The model is calibrated by Real flood data and tested by two big floods. The tests indicate that real-time correction could improve the precision of flood forecast obviously.

关 键 词：洪水预报 实时校正 模型 人工神经网络 汤河水库 

分 类 号：TV697[水利工程—水利水电工程]