摘要
根据主成分分析的结论,选取86种商品材的气干密度、差异干缩、体积干缩系数、顺纹抗压强度、抗弯强度、抗弯弹性模量、顺纹抗拉强度、冲击韧性、端面硬度等9个变量,利用离差平方和法进行聚类分析,然后利用多组判别分析法进行判别分析,并且利用判别分析的结果,判定了31种待判木材的所属类别。结果表明,可以5.5为阈值,将其分为6类。经过判别分析证明,利用9个变量分为6类,这种分类方法效果明显,由此而求得的判别函数可以用于判定类别不明的树种。
The nine variables (air dry density, differential shrinkage, Volumetric shrinkage coefficient, tensile strength along the grain, shock toughness, hardness and so on) of eighty six kinds of commercial wood species were clustered by the method of the sum of deviation squares according to the conclusion of principal component analysis. Then the discriminant analysis was done and the categories of thirty one kinds of wood species were decided according to above results. Wood species in China can be divided into six parts by the threshold value 5.5. After discriminant analysis, it is proved that the method of using nine variables to divide species into six parts is very effective.
出处
《东北林业大学学报》
CAS
CSCD
北大核心
1989年第6期63-69,共7页
Journal of Northeast Forestry University
关键词
木材
物理性质
力学性质
聚类分析
Physical properties of wood
Mechnical properties of wood
Cluster analysis
Discriminant analysis