Early Diagnosis And Prediction Of Wafer Quality Using Machine Learning On Sub-10nm Logic Technology

This paper proposes to use machine learning (ML) methods to predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at wafer sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used in this study. We believe this method can be further fine-tuned to help enable ICs at the high level expected for automotive systems. By assigning predictive rankings, the method also helps enable best tooling system for higher quality