当前位置: 首页 > 文章 > 杉木微观结构与其品质特性关系模型的一类神经网络建模方法 林业科学 2005,41 (4) 133-139
Position: Home > Articles > A Kind of NN Modeling Method of Relational Model of Chinese Fir Microstructure and Its Material Characteristic Scientia Silvae Sinicae 2005,41 (4) 133-139

杉木微观结构与其品质特性关系模型的一类神经网络建模方法

作  者:
江泽慧;姜笑梅;周玉成;安源;赵亮;井元伟
单  位:
中国林业科学研究院木材工业研究所;东北大学
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
摘  要:
给出由木材内部结构参数确定其物理力学特征的神经网络设计与实现的方法———广义回归神经网络(GRNN)模型。该方法的实现,全面、准确地揭示出杉木微观结构参数与其物理力学特性的内在联系,并且达到理想的逼近精度(96.3%以上)。这一结果将为木材性质研究、木材性质形成机理、树木优质种质资源培育、树木转基因工程、定向培育材质改良的树木新品种提供强有力的科学依据及研究方法。
译  名:
A Kind of NN Modeling Method of Relational Model of Chinese Fir Microstructure and Its Material Characteristic
作  者:
Jiang Zehui~(1) Jiang Xiaomei~(1) Zhou Yucheng~(1) An Yuan~(1) Zhao Liang~(2) Jing Yuanwei~(2)(1. Research Institute of Wood Industry, CAF Beijing100091; 2. Northeastern University Shenyang110004)
关键词:
Chinese Fir;microstructure;physical and mechanical properties;Generalized Regression Neural Network (GRNN);modeling method
摘  要:
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.

相似文章

计量
文章访问数: 10
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊