摘要
离群点检测是一种专项检测步骤,检测出潜在的不可靠芯片以进一步提升质量。然而,在实际应用中,往往难以确定哪些测试应该进行离群点检测以及如何设置参数才能检测出离群点并降低产量损失。提出了一种离群点测试选择问题的总体框架,当目标设备已知时,可以为离群点选择测试并设置每种离群点方法的参数。基于真实数据展开实验,实验结果表明,方法只用29个离群点屏障即可检测出89%的目标设备,且额外产量损失只有0.6%。
As an additional step,outlier detection is used to detect potential unreliable chips such that quality can be improved further.However,when in practical applications,it is often unclear to which tests outlier detection should be applied and how the parameters must be set,such that outliers are detected and yield loss remains limited.This paper introduces a general framework for the outlier test selection problem,that gives a set of target devices,can select tests for outlier detection and set the parameters for each outlier detection method.
出处
《工业控制计算机》
2014年第11期49-52,共4页
Industrial Control Computer
关键词
集成电路
离群点检测
框架
目标设备
产量损失
Integrated circuits,outlier detection,framework,target devices,yield loss
