Understanding overlay signatures using machine learning on non-lithography context information

被引：5

作者：

Overcast, Marshall ^{[1
]}

Mellegaard, Corey ^{[1
]}

Daniel, David ^{[1
]}

Habets, Boris ^{[2
]}

Erley, Georg ^{[2
]}

Guhlemann, Steffen ^{[2
]}

Thrun, Xaver ^{[2
]}

Buhl, Stefan ^{[2
]}

Tottewitz, Steven ^{[2
]}

机构：

[1] IM Flash, 4000 N Flash Dr, Lehi, UT 84043 USA

[2] Qoniac GmbH, Koenigsbruecker Str 34, D-01099 Dresden, Germany

来源：

METROLOGY, INSPECTION, AND PROCESS CONTROL FOR MICROLITHOGRAPHY XXXII | 2018年 / 10585卷

关键词：

Run-to-run; machine learning; non-litho contribution; non-linear overlay; simulation; mass context data; process signatures;

D O I：

10.1117/12.2303487

中图分类号：

TB3 [工程材料学];

学科分类号：

0805 ; 080502 ;

摘要：

Overlay errors between two layers can be caused by non-lithography processes. While these errors can be compensated by the run-to-run system, such process and tool signatures are not always stable. In order to monitor the impact of non-lithography context on overlay at regular intervals, a systematic approach is needed. Using various machine learning techniques, significant context parameters that relate to deviating overlay signatures are automatically identified. Once the most influential context parameters are found, a run-to-run simulation is performed to see how much improvement can be obtained. The resulting analysis shows good potential for reducing the influence of hidden context parameters on overlay performance. Non-lithographic contexts are significant contributors, and their automatic detection and classification will enable the overlay roadmap, given the corresponding control capabilities.

引用

页数：15