公开(公告)号：US09087176B1

公开(公告)日：2015-07-21

申请号：US14220665

申请日：2014-03-20

Applicant: KLA-Tencor Corporation

Inventor： Wei Chang ,  Krishna Rao ,  Joseph Gutierrez ,  Ramon Olavarria ,  Craig Macnaughton ,  Amir Azordegan ,  Prasanna Dighe ,  Jaydeep Sinha

IPC: G06F17/50 ,  G03F7/20 ,  G03F1/36 ,  G03F1/00

CPC classification number: G03F7/705 ,  G03F1/144 ,  G03F1/36 ,  G03F7/70633 ,  G06F17/5068 ,  G06F17/5081 ,  G06F2217/12 ,  G06N5/04 ,  G06N99/005 ,  Y02P90/265

Abstract: A method to collect data and train, validate and deploy statistical models to predict overlay errors using patterned wafer geometry data and other relevant information includes selecting a training wafer set, measuring at multiple lithography steps and calculating geometry differences, applying a plurality of predictive models to the training wafer geometry differences and comparing predicted overlay to the measured overlay on the training wafer set. The most accurate predictive model is identified and the results fed-forward to the lithography scanner tool which can correct for these effects and reduce overlay errors during the wafer scan-and-expose processes.

Abstract translation: 收集数据和训练，验证和部署统计模型以使用图案化晶片几何数据和其他相关信息来预测覆盖误差的方法包括选择训练晶片组，在多个光刻步骤测量并计算几何差异，将多个预测模型应用于 训练晶片几何差异并将预测覆盖与训练晶片组上测量的覆盖层进行比较。 识别最准确的预测模型，并将结果反馈到光刻扫描仪工具，可以校正这些影响并减少晶片扫描和曝光过程中的重叠误差。

公开(公告)号：US11456194B2

公开(公告)日：2022-09-27

申请号：US16449400

申请日：2019-06-23

Applicant: KLA-TENCOR CORPORATION

Inventor： Wei Chang ,  Joseph Gutierrez ,  Krishna Rao

IPC: H01L21/67 ,  G05B19/418 ,  G06N7/00

Abstract: A high-dimensional variable selection unit determines a list of critical parameters from sensor data and parametric tool measurements from a semiconductor manufacturing tool, such as a semiconductor inspection tool or other types of semiconductor manufacturing tools. The high-dimensional variable selection model can be, for example, elastic net, forward-stagewise regression, or least angle regression. The list of critical parameters may be used to design a next generation semiconductor manufacturing tool, to bring the semiconductor manufacturing tool back to a normal status, to match a semiconductor manufacturing tool's results with that of another semiconductor manufacturing tool, or to develop a specification for the semiconductor manufacturing tool.

公开(公告)号：US10545412B2

公开(公告)日：2020-01-28

申请号：US15123980

申请日：2015-03-05

Applicant: KLA-Tencor Corporation

Inventor： Wei Chang ,  Krishna Rao ,  Joseph Gutierrez ,  Ramon Olavarria ,  Craig MacNaughton ,  Amir Azordegan ,  Prasanna Dighe

IPC: G06F17/50 ,  G03F7/20 ,  G03F1/36 ,  G03F1/00 ,  G06N20/00 ,  G06N5/04

Abstract: A method to collect data and train, validate and deploy statistical models to predict overlay errors using patterned wafer geometry data and other relevant information includes selecting a training wafer set, measuring at multiple lithography steps and calculating geometry differences, applying a plurality of predictive models to the training wafer geometry differences and comparing predicted overlay to the measured overlay on the training wafer set. The most accurate predictive model is identified and the results fed-forward to the lithography scanner tool which can correct for these effects and reduce overlay errors during the wafer scan-and-expose processes.

公开(公告)号：US10361105B2

公开(公告)日：2019-07-23

申请号：US14955752

申请日：2015-12-01

Applicant: KLA-TENCOR CORPORATION

Inventor： Wei Chang ,  Joseph Gutierrez ,  Krishna Rao

IPC: H01L21/67 ,  G06N7/00 ,  G05B19/418

Abstract: A high-dimensional variable selection unit determines a list of critical parameters from sensor data and parametric tool measurements from a semiconductor manufacturing tool, such as a semiconductor inspection tool or other types of semiconductor manufacturing tools. The high-dimensional variable selection model can be, for example, elastic net, forward-stagewise regression, or least angle regression. The list of critical parameters may be used to design a next generation semiconductor manufacturing tool, to bring the semiconductor manufacturing tool back to a normal status, to match a semiconductor manufacturing tool's results with that of another semiconductor manufacturing tool, or to develop a specification for the semiconductor manufacturing tool.

公开(公告)号：US20170017162A1

公开(公告)日：2017-01-19

申请号：US15123980

申请日：2015-03-05

Applicant: KLA-Tencor Corporation

Inventor： Wei Chang ,  Krishna Rao ,  Joseph Gutierrez ,  Ramon Olavarria ,  Craig MacNaughton ,  Amir Azordegan ,  Prasanna Dighe

IPC: G03F7/20 ,  G03F1/36 ,  G06F17/50 ,  G06N99/00 ,  G06N5/04

CPC classification number: G03F7/705 ,  G03F1/144 ,  G03F1/36 ,  G03F7/70633 ,  G06F17/5068 ,  G06F17/5081 ,  G06F2217/12 ,  G06N5/04 ,  G06N20/00 ,  Y02P90/265

Abstract: A method to collect data and train, validate and deploy statistical models to predict overlay errors using patterned wafer geometry data and other relevant information includes selecting a training wafer set, measuring at multiple lithography steps and calculating geometry differences, applying a plurality of predictive models to the training wafer geometry differences and comparing predicted overlay to the measured overlay on the training wafer set. The most accurate predictive model is identified and the results fed-forward to the lithography scanner tool which can correct for these effects and reduce overlay errors during the wafer scan-and-expose processes.

Abstract translation: 收集数据和训练，验证和部署统计模型以使用图案化晶片几何数据和其他相关信息来预测覆盖误差的方法包括选择训练晶片组，在多个光刻步骤测量并计算几何差异，将多个预测模型应用于 训练晶片几何差异并将预测覆盖与训练晶片组上测量的覆盖层进行比较。 识别最准确的预测模型，并将结果反馈到光刻扫描仪工具，可以校正这些影响并减少晶片扫描和曝光过程中的重叠误差。