摘要
利用神经网络所具有的输入-输出之间的高度非线性映射关系,给出一种利用BP神经网络模型预测木材径向导热系数的方法。为了提高网络模型的泛化能力,采用规则化调整的方法。仿真结果表明:利用文中所提出的神经网络模型能够较准确、快速地预测木材径向导热系数的变化,其精度高于推导出的木材径向导热系数的理论公式。
A method to predict the wood radial thermal conductivity based on back propagation (BP) neural network model which has non-linear relation highly was proposed. The generalization ability of the network was improved by regularization. The simulation results showed that the neural network model given in this paper is capable of forecasting the behavior of the wood radial thermal conductivity exactly and rapidly. Experiments presented that the model was of accuracy and was higher in respect of precision than the formula derived.
出处
《林业科学》
EI
CAS
CSCD
北大核心
2006年第3期25-28,共4页
Scientia Silvae Sinicae
基金
国家自然基金资助项目(30371134)
关键词
神经网络
网络泛化
预测
导热系数
规则化调整
neural network
generalization ability of network
predict
thermal conductivity
regularization