-
公开(公告)号：US20150302312A1
公开(公告)日：2015-10-22
申请号：US14457706
申请日：2014-08-12
Applicant: KLA-Tencor Corporation
Inventor： Pradeep Vukkadala , Jaydeep Sinha , Wei Chang , Krishna Rao
CPC classification number: B24B37/005 , B24B49/00 , G01B21/00 , G01B2210/48 , G03F7/705 , G03F9/7026 , G06N7/00 , G06N99/005
Abstract: Predictive modeling based focus error prediction method and system are disclosed. The method includes obtaining wafer geometry measurements of a plurality of training wafers and grouping the plurality of training wafers to provide at least one training group based on relative homogeneity of wafer geometry measurements among the plurality of training wafers. For each particular training group of the at least one training group, a predictive model is develop utilizing non-linear predictive modeling. The predictive model establishes correlations between wafer geometry parameters and focus error measurements obtained for each wafer within that particular training group, and the predictive model can be utilized to provide focus error prediction for an incoming wafer belonging to that particular training group.
Abstract translation: 公开了基于预测建模的聚焦误差预测方法和系统。 该方法包括获得多个训练晶片的晶片几何测量，并且基于多个训练晶片之间的晶片几何测量的相对均匀性，分组多个训练晶片以提供至少一个训练组。 对于至少一个训练组的每个特定训练组，利用非线性预测建模来开发预测模型。 该预测模型建立晶片几何参数和该特定训练组内的每个晶片获得的聚焦误差测量值之间的相关性，并且该预测模型可用于为属于该特定训练组的输入晶片提供聚焦误差预测。
-
公开(公告)号：US20160163035A1
公开(公告)日：2016-06-09
申请号：US14956326
申请日：2015-12-01
Applicant: KLA-TENCOR CORPORATION
Inventor： Wei Chang , Ramon Olavarria , Krishna Rao
CPC classification number: G06T7/0004 , G06K9/4628 , G06K9/6255 , G06K9/6274 , G06K9/66 , G06K2209/19 , G06T2207/20081 , G06T2207/20084 , G06T2207/30148
Abstract: Systems and methods for defection classification in a semiconductor process are provided. The system includes a communication line configured to receive a defect image of a wafer from the semiconductor process and a deep-architecture neural network in electronic communication with the communication line. The neural network has a first convolution layer of neurons configured to convolve pixels from the defect image with a filter to generate a first feature map. The neural network also includes a first subsampling layer configured to reduce the size and variation of the first feature map. A classifier is provided for determining a defect classification based on the feature map. The system may include more than one convolution layers and/or subsampling layers. A method includes extracting one or more features from a defect image using a deep-architecture neural network, for example a convolutional neural network.
Abstract translation: 提供半导体工艺中的缺陷分类的系统和方法。 该系统包括被配置为从半导体处理接收晶片的缺陷图像的通信线路和与通信线路进行电子通信的深层架构神经网络。 神经网络具有第一卷积层的神经元，其被构造成用来过滤来自缺陷图像的像素来卷积第一特征图。 神经网络还包括被配置为减小第一特征图的大小和变化的第一子采样层。 提供了一种基于特征图来确定缺陷分类的分类器。 系统可以包括多于一个卷积层和/或子采样层。 一种方法包括使用深层架构神经网络（例如卷积神经网络）从缺陷图像中提取一个或多个特征。
-
公开(公告)号：US09707660B2
公开(公告)日：2017-07-18
申请号：US14457706
申请日：2014-08-12
Applicant: KLA-Tencor Corporation
Inventor： Pradeep Vukkadala , Jaydeep Sinha , Wei Chang , Krishna Rao
CPC classification number: B24B37/005 , B24B49/00 , G01B21/00 , G01B2210/48 , G03F7/705 , G03F9/7026 , G06N7/00 , G06N99/005
Abstract: Predictive modeling based focus error prediction method and system are disclosed. The method includes obtaining wafer geometry measurements of a plurality of training wafers and grouping the plurality of training wafers to provide at least one training group based on relative homogeneity of wafer geometry measurements among the plurality of training wafers. For each particular training group of the at least one training group, a predictive model is develop utilizing non-linear predictive modeling. The predictive model establishes correlations between wafer geometry parameters and focus error measurements obtained for each wafer within that particular training group, and the predictive model can be utilized to provide focus error prediction for an incoming wafer belonging to that particular training group.
-
4.发明授权Statistical overlay error prediction for feed forward and feedback correction of overlay errors, root cause analysis and process control 有权反馈前馈和反馈校正的统计叠加误差预测，根本原因分析和过程控制公开(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
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。
-
Patent Agency Ranking
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：US10650508B2
公开(公告)日：2020-05-12
申请号：US14956326
申请日：2015-12-01
Applicant: KLA-TENCOR CORPORATION
Inventor： Wei Chang , Ramon Olavarria , Krishna Rao
Abstract: Systems and methods for defection classification in a semiconductor process are provided. The system includes a communication line configured to receive a defect image of a wafer from the semiconductor process and a deep-architecture neural network in electronic communication with the communication line. The neural network has a first convolution layer of neurons configured to convolve pixels from the defect image with a filter to generate a first feature map. The neural network also includes a first subsampling layer configured to reduce the size and variation of the first feature map. A classifier is provided for determining a defect classification based on the feature map. The system may include more than one convolution layers and/or subsampling layers. A method includes extracting one or more features from a defect image using a deep-architecture neural network, for example a convolutional neural network.
-
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
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.
-
9.发明申请Statistical Overlay Error Prediction for Feed Forward and Feedback Correction of Overlay Errors, Root Cause Analysis and Process Control 审中-公开统计叠加误差预测的前馈和反馈校正重叠错误，根本原因分析和过程控制公开(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
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。
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.016 seconds)
