Abstract
Advanced data analysis tools and techniques are important for semiconductor companies to gain competitive advantage. In particular, yield prediction tools, which fully utilize production data, help to improve operational efficiency and reduce production costs. This paper introduces a novel and scalable framework for semiconductor manufacturing Final Test (FT) yield prediction leveraging machine learning techniques. This framework is able to predict FT yield at wafer fabrication stage, so that FT low yield problems can be caught at an earlier production stage compared to past studies. Our work presents a robust solution to automatically handle both numerical and categorical production related data without prior knowledge of the low yield root cause. Gaussian Mixture Models, One Hot Encoder and Label Encoder techniques are adopted for data pre-processing. To improve model performance for both binary and multi-class classification, model selection and model ensemble using the F1-macro method is demonstrated. The framework has been applied to three mass production products with different wafer technologies and manufacturing flows. All of them achieved high F1-macro test score indicative of the robustness of our framework.
Highlights
The semiconductor manufacturing process flow involves hundreds of processes and the production life-cycle from raw material to packaged chips can take 8-16 weeks in all
We propose a holistic framework for Final Test (FT) yield prediction using a suite of machine learning techniques
The framework is able to predict FT yield at the Wafer Fabrication (WF) stage itself, which implies that FT low yield problems can be identified two months earlier when compared to current practice
Summary
The semiconductor manufacturing process flow involves hundreds of processes and the production life-cycle from raw material to packaged chips can take 8-16 weeks in all. During WF stage, Wafer Acceptance Test (WAT) is conducted to monitor important WF process related parameters. If there is any low yield problem, engineers need to manually review all related production data and identify the root cause. The second one is backend manufacturing flow problems, involving package types, product configurations, test facilities, human interference, etc. The framework is able to predict FT yield at the WF stage itself, which implies that FT low yield problems can be identified two months earlier when compared to current practice. Using the WAT measurements and backend manufacturing flow parameters, our proposed model is able to classify wafer material into different yield sub-populations. Based on the binning or multi-modal classification of the yield, wafer process adjustment or backend related manufacturing flow adjustment can be selectively carried out. Our data-driven decision-making process is able to overcome the limitations of manual work for low yield materials’ data review and disposition
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
