关键词: 杉木, 微观结构, 物理力学特性, 广义回归神经网络, 建模方法

Abstract:

This paper presented a kind of NN modeling method named Generalized Regression Neural Network (GRNN), through which the physical, mechanical properties of Chinese Fir could be obtained from its internal structure parameters. The implementation of this method could help find out the inherent relationship of Chinese Fir microstructure and physical, mechanical properties with desired approximation precision (above 96.3%).The result worked out here will provide strong scientific foundation and effective research approach when it comes to the research of wood quality and it’s forming mechanism, wood transgene and directive breeding.

Key words: Chinese Fir, microstructure, physical and mechanical properties, Generalized Regression Neural Network (GRNN), modeling method