距离判别分析法在产品质量控制中的应用  

Application of distance discriminant analysis method in product quality control

作　　者：欧阳娜[1] 黄利文[2] OU Yangna;HUANG Liwen(School of New Materials and Shoes&Clothing Engineering,Liming Vocational University,Quanzhou 362000,China;College of Mathematics and Computer Science,Quanzhou Normal University,Quanzhou 362000,China)

机构地区：[1]黎明职业大学新材料与鞋服工程学院 [2]泉州师范学院数学与计算机科学学院,福建泉州362000

出　　处：《延边大学学报（自然科学版）》2021年第4期334-339,共6页Journal of Yanbian University（Natural Science Edition）

基　　金：福建省先进高分子材料应用技术协同创新中心专项(GFZ202009);福建省中青年教师教育科研项目(JAT210884)。

摘　　要：为提高多个观测变量的质量监控,在统计过程控制(SPC)方法的基础上提出了一种距离判别分析方法.该方法首先对SPC的过程监控图进行改进,并建立产品质量分类模型;然后对影响产品质量的因素进行分析,并通过仿真实验测试该方法的效果.仿真实验显示,该方法能较好地将产品质量分为4个等级,且分类正确率优于常见分类方法,因此此方法在产品质量控制中具有良好的应用价值.A distance discriminant analysis method was proposed based on statistical process control(SPC)in order to improve the quality control of multiple observation variables.The method firstly improves the SPC process monitoring chart,then establishes the product quality classification model,analyzes the influencing factors of product quality,and tests the effect of this method through simulation experiments.The results of simulation experiments and comparison with the common classification methods show that the proposed method can divide the product quality into four grades,and the classification accuracy is better than the common classification methods.Therefore,the proposed method has good application value in product quality control.

关 键 词：距离判别 判别准则 统计过程控制 产品质量 质量控制 蒙特卡罗方法 

分 类 号：O212.4[理学—概率论与数理统计]