陶瓷原料分类的距离判别分析法

CLASSIFICATION OF CERAMIC RAW MATERIALS BY DISTANCE DISCRIMINATION ANALYSIS

将距离判别分析法应用于陶瓷原料分类中,建立陶瓷原料分类的距离判别分析模型。模型选用陶瓷原料的9种化学成分作为距离判别分析模型的判别因子。将陶瓷原料分为4个类别并作为距离判别分析的4个正态总体,以陶瓷原料样本实测数据作为训练样本,建立相应线性判别函数对待判样本进行分类。研究结果表明,距离判别分析模型分类性能良好,回判估计的误判率为0,可以在生产实际中推广应用。

Based on the principle of Mahalanobis distance discrimination analysis, a classification model of ceramic raw materials is established. Nine chemical compositions are selected as the factors for the classification model based on distance discrimination analysis. Ceramic raw materials are divided into four grades, which are considered as four normal populations in distance discrimination analysis. Linear discrimination functions are obtained through the tests of a series of ceramic raw material samples. Then a series of new samples are classified by using the model. The results show that the classification model based on distance discrimination analysis has excellent performance and the ratio of wrong-distinguishing is zero. The proposed model could be used widely in practice.