公开(公告)号：US20160371826A1

公开(公告)日：2016-12-22

申请号：US14746820

申请日：2015-06-22

Applicant: KLA-TENCOR CORPORATION

Inventor： Himanshu VAJARIA ,  Shabnam Ghadar ,  Tommaso Torelli ,  Bradley RIES ,  Mohan MAHADEVAN ,  Stilian Pandev

IPC: G06T7/00

CPC classification number: G06T7/11 ,  G06T7/001 ,  G06T2207/30148

Abstract: Methods and devices are disclosed for automated detection of a status of wafer fabrication process based on images. The methods advantageously use segment masks to enhance the signal-to-noise ratio of the images. Metrics are then calculated for the segment mask variations in order to determine one or more combinations of segment masks and metrics that are predictive of a process non-compliance. A model can be generated as a result of the process. In another embodiment, a method uses a model to monitor a process for compliance.

Abstract translation: 公开了用于基于图像自动检测晶片制造过程的状态的方法和装置。 这些方法有利地使用段掩模来增强图像的信噪比。 然后针对段掩码变化计算度量，以便确定预测过程不符合性的段掩码和度量的一个或多个组合。 作为过程的结果可以生成模型。 在另一个实施例中，一种方法使用模型来监视合规性的过程。

公开(公告)号：US10365639B2

公开(公告)日：2019-07-30

申请号：US15248523

申请日：2016-08-26

Applicant: KLA-Tencor Corporation

Inventor： Shabnam Ghadar ,  Sina Jahanbin ,  Himanshu Vajaria ,  Bradley Ries

IPC: G05B19/408 ,  G06N5/02 ,  G05B19/418 ,  H01L21/66 ,  G06N20/00

Abstract: Feature extraction and classification is used for process window monitoring. A classifier, based on combinations of metrics of masked die images and including a set of significant combinations of one or more segment masks, metrics, and wafer images, is capable of detecting a process non-compliance. A process status can be determined using a classifier based on calculated metrics. The classifier may learn from nominal data.

公开(公告)号：US20170192411A1

公开(公告)日：2017-07-06

申请号：US15248523

申请日：2016-08-26

Applicant: KLA-Tencor Corporation

Inventor： Shabnam Ghadar ,  Sina Jahanbin ,  Himanshu Vajaria ,  Bradley Ries

IPC: G05B19/408 ,  G06N5/02

CPC classification number: G05B19/41875 ,  G05B2219/37224 ,  G06N20/00 ,  H01L22/12 ,  H01L22/20 ,  Y02P90/22

Abstract: Feature extraction and classification is used for process window monitoring. A classifier, based on combinations of metrics of masked die images and including a set of significant combinations of one or more segment masks, metrics, and wafer images, is capable of detecting a process non-compliance. A process status can be determined using a classifier based on calculated metrics. The classifier may learn from nominal data.

公开(公告)号：US09569834B2

公开(公告)日：2017-02-14

申请号：US14746820

申请日：2015-06-22

Applicant: KLA-TENCOR CORPORATION

Inventor： Himanshu Vajaria ,  Shabnam Ghadar ,  Tommaso Torelli ,  Bradley Ries ,  Mohan Mahadevan ,  Stilian Pandev

IPC: G06K9/00 ,  G06T7/00

CPC classification number: G06T7/11 ,  G06T7/001 ,  G06T2207/30148

Abstract: Methods and devices are disclosed for automated detection of a status of wafer fabrication process based on images. The methods advantageously use segment masks to enhance the signal-to-noise ratio of the images. Metrics are then calculated for the segment mask variations in order to determine one or more combinations of segment masks and metrics that are predictive of a process non-compliance. A model can be generated as a result of the process. In another embodiment, a method uses a model to monitor a process for compliance.

Abstract translation: 公开了用于基于图像自动检测晶片制造过程的状态的方法和装置。 这些方法有利地使用段掩模来增强图像的信噪比。 然后针对段掩码变化计算度量，以便确定预测过程不合规性的段掩码和度量的一个或多个组合。 作为过程的结果可以生成模型。 在另一个实施例中，一种方法使用模型来监视合规性的过程。