基于主成分分析的半导体封装质量控制系统  

Quality Controlling of Semiconductor Assembly Based on Principal Components Analysis

作　　者：郑轶松[1] 王谦[1] 何曙光[2] 

机构地区：[1]南开大学泰达学院工业工程系,天津300457 [2]天津大学管理学院,天津300072

出　　处：《系统工程》2009年第1期108-112,共5页Systems Engineering

摘　　要：半导体封装某工序具有5个需要进行控制的关键质量特性,而且这些关键质量特性之间存在相关关系,为此,对抽样检测到的数据进行主成分分析,并对前几个主成分应用Hotelling T2控制图进行控制。应用开发的分析工具,对某工序的抽样数据进行了研究,对主成分的控制与对采样数据直接采用Hotelling T2控制图得到了相同的结果,而维度从5降到了2。There are 5 critical quality characteristics in the bolding process in semiconductor assembly line, and these characteristics are correlated, so the principal components analysis is used to analyze the sampling data and the former several components are controlled with Hotelling T^2 controlling chart. Furthermore, the sampling data are analyzed by the developed analysis tool. It is proven that the results remain the same when Hotelling T^2 control chart is directly used, except for the transformation from high-dimension to lower dimension, i.e. from 5 to 2 or three in this example.

关 键 词：半导体封装 主成分分析 质量控制 

分 类 号：F273[经济管理—企业管理]