陶瓷原料分类的Bayes判别分析法

Classification of Ceramic Raw Materials by Bayes Discriminant Analysis Method

将Bayes判别分析法应用于陶瓷原料分类中,建立了陶瓷原料分类识别的Bayes判别分析模型。模型选用陶瓷原料的9种化学成分作为分类识别的判别因子;将陶瓷原料分为4个类别并作为Bayes判别分析的4个正态总体;以陶瓷原料样本实测数据作为训练样本,建立Bayes线性判别函数;以Bayes线性判别函数计算待判样品的Bayes判别函数值,以最大值对应的总体作为样品所归属的总体;最后以回代法对判别准则进行评价以检验模型的优良性。实例研究表明,Bayes判别分析模型回判估计误判率为0,因而是陶瓷原料分类识别的一种有效方法,可在生产实际中应用和推广。

Based on the principle of Bayes discriminant analysis, Bayes discriminant model for the classification of ceramic raw materials is established. Nine chemical compositions are selected as the factors for synthetic evaluation of samples of ceramic raw materials. The grades of ceramic raw materials are divided into four grades that are considered as four normal populations in Bayes discriminant analysis. Bayes discriminant functions obtained through training a series of samples of ceramic raw materials are employed to compute the Bayes function values of the evaluating samples, and the maximal function value is used to judge which population the evaluating sample belongs to. The optimality of the proposed model is verified by back substitution method. The study shows that the ratio of mistake-distinguish is zero and the proposed model could be used widely in practical.