基于BP网络的洪灾风险评价算法

Flood Risk Evaluation Algorithm on BP Net

为了解决洪灾风险评价问题,文中在分析传统洪灾风险评价算法不足的基础上,结合BP网络特点,提出了基于BP网络的洪灾风险评价算法(Flood Risk Evaluation algorithm on BP Net,FRE-BPN),同时为了解决BP算法对复杂高维样本数据建模效率差、精度低的缺陷,利用粗糙集对BP网络进行约简。仿真实验表明,粗糙集约简使得BP网络大大降低了洪灾风险评价模型建立的复杂度,同时FRE-BPN算法对洪灾数据集进行风险评价时的平均耗时大大下降。

To solve flood risk evaluation,presents Flood Risk Evaluation algorithm on BP Net （FRE- BPN）, which combines BP net to solve problems of traditional flood risk evaluation algorithm. Meanwhile, in order to solve the defect of BP net for inefficiency and low accuracy of data modeling,BP net is reducted by rough set. By experiments, it＇s showed that the complexity which BP created flood risk evaluation model is reduced greatly by reduction with rough set, and the average consumptive time of FRE - BPN decreases apparently.