-
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:US09734568B2
公开(公告)日:2017-08-15
申请号:US14630252
申请日:2015-02-24
Applicant: KLA-TENCOR CORPORATION
Inventor: Himanshu Vajaria , Sina Jahanbin , Bradley Ries , Mohan Mahadevan
CPC classification number: G06T7/0004 , G01N21/9503 , G06K9/481 , G06K9/6204 , G06K2209/19 , G06T7/0006 , G06T7/13 , G06T7/62 , G06T2207/10024 , G06T2207/30148
Abstract: Shadow-grams are used for edge inspection and metrology of a stacked wafer. The system includes a light source that directs collimated light at an edge of the stacked wafer, a detector opposite the light source, and a controller connected to the detector. The stacked wafer can rotate with respect to the light source. The controller analyzes a shadow-gram image of the edge of the stacked wafer. Measurements of a silhouette of the stacked wafer in the shadow-gram image are compared to predetermined measurements. Multiple shadow-gram images at different points along the edge of the stacked wafer can be aggregated and analyzed.
-
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.
-
-