改进补偿模糊神经网络在坡面产沙模拟预报中的应用  

CFNN Modification and Its Application in Predicting Soil Erosion on Slope Land

作　　者：代华龙[1] 曹叔尤[1] 耿新宇[2] 

机构地区：[1]四川大学水力学与山区河流开发国家重点实验室,四川成都610065 [2]西南石油大学计算机科学学院,四川成都610500

出　　处：《四川大学学报（工程科学版）》2008年第5期45-50,共6页Journal of Sichuan University (Engineering Science Edition)

基　　金：国家自然科学基金资助项目(50739002)

摘　　要：土壤侵蚀产沙是一个极其复杂的物理过程,其物理机理十分复杂,往往难以用数学方式来描述。根据土壤侵蚀过程内在特点,采用一种改进的补偿模糊神经网络(CFNN)方法,对坡面侵蚀产沙过程进行了预测研究。利用四川某水土保持实验站观测数据,通过MATLAB语言编制程序进行了仿真试验,全局误差为0.0517,预测值与实测值吻合良好,误差小于10%。结果表明,该方法预报精度较好,为坡面产沙模拟模型的建立提供了重要的参考方法。Soil erosion is a very complicated physical process and its physical mechanism is very complex so that it is difficult to describe by mathematical expression.Compensatory fuzzy neural network(CFNN) is a complex system of compensatory fuzzy logic(CFL) and artificial neural network(ANN).It has higher systematic stability and error tolerance.Base on the dynamic and physical behavior of soil erosion,the present paper modified the CFNN to predict soil erosion on slope land.MATLAB computer program had emulated us...

关 键 词：补偿模糊神经网络 侵蚀产沙 坡面 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]