摘要
采用改进的BP神经网络算法和多元线性回归模型分别建立目标函数,并以油田产量预测为例计算验证。通过比较分析,BP网络模型克服了多元线性回归模型的局限性,检验误差为0.0162,同时表明神经网络的非线性映射能力能够更好地反应多个自变量和因变量之间的复杂关系,具有较好的精确性和可行性。
With application of improved BP neural network and multi-variable linear regression,operation functions are established respectively and verified by case study of rate prediction.Through comparison and analysis,the verification error of BP neural network model which overcame the localization of multi-variable linear regression model is 0.016 2,and it is shown that the neural network has a better nonlinear reflection ability,and can describe the complex relationship between the independent variable and the dependent variable with better precision,and has well feasibility.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第23期203-204,共2页
Computer Engineering and Applications
基金
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60172061)
关键词
BP神经网络
非线性映射
算法
多元线性回归
BP neural network
nonlinear mapping
algorithm
multi-linear regression
