AI-guided reliability diagnosis for 5,7nm automotive process

Abstract

Automotive semiconductor products demand high reliability. The current process of performing electrical test after fab-out may not be sufficient for efficient reliability management. This paper proposes an AI solution for improving the reliability of automotive semiconductor products. The solution includes two unique concepts: fab-data augmentation (FDA) to estimate missing values using partially available measurement data during the fabrication process and real-time prediction of reliability using machine learning (ML) models. The ML model is also used to identify and rank critical process steps that impact reliability, and to predict the reliability of wafers in real time. This allows low reliability wafers to be screened out early during the chip fabrication process, improving the overall reliability of the final product.

Advanced process control by machine learning-based virtual metrology for high product mix manufacturing

“…Incorporating these design features into FDC data at the chamber level is achieved through the utilization of Calibre® Fab Insights [6][7][8][9][10]. This methodology employs sophisticated ML techniques, including a modified gradient boosted tree algorithm, to construct the extended VM model, as illustrated in Figure 5.…”