Die level predictive modeling to reduce latent reliability defect escapes

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F23%3A00372855" target="_blank" >RIV/68407700:21240/23:00372855 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1016/j.microrel.2023.115139" target="_blank" >https://doi.org/10.1016/j.microrel.2023.115139</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.microrel.2023.115139" target="_blank" >10.1016/j.microrel.2023.115139</a>

Result language
angličtina
Original language name
Die level predictive modeling to reduce latent reliability defect escapes
Original language description
This paper presents a die-level screening method based on inline defect inspection that uses advanced predictive engines to generate die-level failure probabilities to filter dice with high-reliability risk if the predicted probability is higher than a selected limit. The method uses the relationship between ’killer’ and latent defects to identify potentially unreliable dice that have passed the Wafer Sort. A novel approach of saliency map clustering algorithms is applied to increase the level of granularity in latent defect detection beyond supervised defect classification.
Czech name
—
Czech description
—

Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
20205 - Automation and control systems

Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)