| 基于误差修正的BP神经网络模型在河道洪水预报中的应用 |
| |
| 引用本文： | 戴会超,何文社,曹叔尤. 基于误差修正的BP神经网络模型在河道洪水预报中的应用[J]. 水电能源科学, 2006, 24(1): 69-71 |
| |
| 作者姓名： | 戴会超 何文社 曹叔尤 |
| |
| 作者单位： | 1. 中国长江三峡工程开发总公司,湖北,宜昌,443002;四川大学,高速水力学国家重点实验室,四川,成都,610065
2. 四川大学,高速水力学国家重点实验室,四川,成都,610065 |
| |
| 摘 要： | 针对经典BP神经网络模型,增设误差修正系数,实现网络误差修正权重倾向于输出样本的较大值,据此提出了一种计算输入输出向量的归一化公式,并建立了具有洪峰识别的洪水预报BP网络预报模型。采用新模型对宜昌水文站典型年实测流量过程进行了预测检验,其结果与实测值较吻合,对流量过程及洪峰流量过程的预报精度较经典BP模型高。
|
| 关 键 词： | 洪水预报 预测模型 BP神经网络 识别洪峰方法 |
| 文章编号： | 1000-7709（2006）01-0069-03 |
| 收稿时间： | 2006-01-09 |
| 修稿时间： | 2006-01-09 |
Flood Process Forecasting Model Based on Back Propagation in BP Neural Network Theory |
| |
| DAI Huichao,HE Wenshe,CAO Shuyou. Flood Process Forecasting Model Based on Back Propagation in BP Neural Network Theory[J]. International Journal Hydroelectric Energy, 2006, 24(1): 69-71 |
| |
| Authors: | DAI Huichao HE Wenshe CAO Shuyou |
| |
| Abstract: | In this paper,the BP neural network model for flood forecasting is improved by adding the correct coefficient,and error weights for bigger output examplevalues are introduced into BP model to meet the peak flood.This model can simulate and forecast different characters of discharge process and its peak flood.The standardized formulas are proposed for calculating the vector of input and output.Finally,two years result of measured and forecasting discharge process at Yichang Station have been obtained,it can be found that forecast result agrees well with the measured data. |
| |
| Keywords: | flood forecasting forecast model BP artificial neural network flood peak recognization method |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
