Feature selection and automated process window monitoring through outlier detection
US10365639B2 · kind B2 · utility
1Cited by
4References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Aug 26, 2016 |
| Grant date | Jul 30, 2019 |
| Priority date | — |
| Expiry date | Aug 10, 2037 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY02P90/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
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.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.