HU Yi, ZHOU Jingwei ,HU Zhen

(School of Information Engineering, Jingdezhen Ceramic Institute, Jingdezhen Jiangxi 333403, China）

Abstract: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.

Keywords:ceramic raw materials, classification, distance discrimination analysis