摘要
鉴于边坡系统是一个复杂的多因素影响的非线性系统,综合考虑边坡的物理状态和环境因素,采用了一种基于果蝇优化算法(FOA)的广义回归神经网络(GRNN)模型(FOAGRNN)预测边坡的稳定状态,并与BP神经网络预测模型结果进行比较。结果表明,FOAGRNN预测的精度较高,基本反映了边坡稳定的真实状态。
A slope system is a complicated nonlinear system which is affected by lots of factors.General regression neural network method improved by fruit fly optimization algorithm（FOAGRNN）is used to predict slope stability by comprehensively considering physical status of slope and environmental factor.Compared with BP neural network method,the results show that the FOAGRNN has higher prediction accuracy,which basically reflects the true state of slope stability.
出处
《水电能源科学》
北大核心
2015年第1期124-126,144,共4页
Water Resources and Power
基金
国家自然科学基金青年基金项目(50909072)
国家自然科学基金创新研究群体科学基金项目(51321065)
中央高校基本科研项目(3122014C012)
关键词
边坡稳定
果蝇优化算法
广义回归神经网络
预测
slope stability
fruit fly optimization algorithm
general regression neural network
prediction
