Ultrasonic Wire Bond Outlier Classification

H. Seppänen, Siang Tat Chua, Joel Elizondo Martinez, Pedro Villa
{"title":"Ultrasonic Wire Bond Outlier Classification","authors":"H. Seppänen, Siang Tat Chua, Joel Elizondo Martinez, Pedro Villa","doi":"10.4071/1085-8024-2021.1.000256","DOIUrl":null,"url":null,"abstract":"K&S developed and tested the Advanced Process Diagnostics (APD) algorithm to classify bonding outliers in ultrasonic wire bond production. APD is a software feature, part of Kulicke & Soffa wedge bonders to measure and analyze process signals and detect and classify bond outliers. APD helps bonder operators, production supervisors and process engineers to detect process deviations and fix the underlying root causes. APD measures bond signals, such as deformation, ultrasonic current and ultrasonic frequency. Bonds are automatically divided into subgroups based on bond order and process parameters and the signals within a subgroup are then normalized. For outlier classification, the features are extracted from the normalized signals and combined into failure class values. The failure classes, such as contamination, misaligned wire and unstable substrate, are calculated independently. Within the APD feature, a user can define limits for the failure class values and define bonder actions based on the severity of the detected outlier. We measured the detection rates for large wire Al bond failure classes and demonstrate how APD calculates failure class values from the signals. Additionally, we show how new signal features and failure classes can be defined to detect production specific or rare failure classes. Finally, we present outlier classification performance metrics against large production data sets.","PeriodicalId":14363,"journal":{"name":"International Symposium on Microelectronics","volume":"51 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Symposium on Microelectronics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4071/1085-8024-2021.1.000256","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

K&S developed and tested the Advanced Process Diagnostics (APD) algorithm to classify bonding outliers in ultrasonic wire bond production. APD is a software feature, part of Kulicke & Soffa wedge bonders to measure and analyze process signals and detect and classify bond outliers. APD helps bonder operators, production supervisors and process engineers to detect process deviations and fix the underlying root causes. APD measures bond signals, such as deformation, ultrasonic current and ultrasonic frequency. Bonds are automatically divided into subgroups based on bond order and process parameters and the signals within a subgroup are then normalized. For outlier classification, the features are extracted from the normalized signals and combined into failure class values. The failure classes, such as contamination, misaligned wire and unstable substrate, are calculated independently. Within the APD feature, a user can define limits for the failure class values and define bonder actions based on the severity of the detected outlier. We measured the detection rates for large wire Al bond failure classes and demonstrate how APD calculates failure class values from the signals. Additionally, we show how new signal features and failure classes can be defined to detect production specific or rare failure classes. Finally, we present outlier classification performance metrics against large production data sets.
超声线键异常值分类
K&S开发并测试了先进的过程诊断(APD)算法,用于对超声波线键合生产中的异常值进行分类。APD是Kulicke & Soffa楔形粘结机的一个软件功能,用于测量和分析过程信号,检测和分类粘结异常值。APD帮助粘合剂操作员、生产主管和工艺工程师检测工艺偏差并解决潜在的根本原因。APD测量键合信号,如变形、超声电流和超声频率。根据键的顺序和过程参数自动将键划分为子组,然后将子组内的信号规范化。对于异常点分类,从归一化信号中提取特征并组合成故障类别值。故障类别,如污染、导线错位和衬底不稳定,是独立计算的。在APD功能中,用户可以定义故障类别值的限制,并根据检测到的异常值的严重程度定义绑定操作。我们测量了大型铝键合故障类别的检测率,并演示了APD如何从信号中计算故障类别值。此外,我们还展示了如何定义新的信号特征和故障类别来检测生产特定的或罕见的故障类别。最后,我们提出了针对大型生产数据集的异常值分类性能指标。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信