模糊优选神经网络BP模型在黄河内蒙段封开河预报中的应用

Application of fuzzy optimization neural network BP approach in forecasting freeze-up and break-up date in the Inner Mongolia reach of the Yellow River

黄河内蒙段地处黄河流域最北端,由于它特殊的地理位置、水文气象条件、河道特性,几乎年年发生凌汛。在分析凌汛成因影响因素的基础上,选取合适的预报因子,基于模糊优选神经网络BP模型,对黄河内蒙段封河、开河日期进行样本训练和预报方案验证。预报结果表明,模糊优选神经网络冰凌预报模型计算简便,精度良好。

The Inner Mongolia reach lies in the top north of the Yellow River. Every year, ice flood occurs in this district because of its special geographical position, hydro-meteorological conditions and river c araeteristics. Based on analysis of all kinds of factors influencing ice flood, some forecasting indicators are selected, and a new fuzzy optimization neural network BP approach is proposed. The application of this new approach in forecasting the freeze-up and break-up date of the Inner Mongolia reach of the Yellow River shows that this new approach is of high accuracy and the calculation procedure is simple.