The semiconductor foundry industry faces challenges in high-product-mix manufacturing, requiring increased flexibility in managing diverse customer demands. Coordinating multiple chambers and process steps with different designs and technology nodes is complex resulting in reduced yields and increased costs. The Chemical Vapor Deposition (CVD) process in semiconductor manufacturing experiences thickness variations due to device layout design and chamber condition drift. A lack of control across layouts affects transistor parameters and yield. Managing chamber-by-chamber variations is crucial for high-volume manufacturing, but traditional solutions are not sufficient for fab line management, causing throughput loss. Traditional virtual metrology (VM) addresses the trade-off between metrology activities and cost by utilizing data from the process chamber (FDC) to predict metrology results. In addition, design features are extracted and used for prediction across layouts and technologies for high-product-mix manufacturing. Siemens' Calibre Fab Insights is employed for feature extraction, and machine learning (ML) methodologies construct the VM model. Results demonstrate the superiority of the VM model with design features and FDC. An advanced process control (APC) system using the VM model for R2R control is proposed. It incorporates design features, FDC, and measurements to achieve the desired thickness target. The system triggers updates to the VM model based on prediction errors. The APC system significantly improves process capability and reduces film thickness variations through control simulation, confirming the effectiveness of integrating the APC system with the VM model in a high-mix product foundry fab. The growing demand for custom-designed products from diverse customers requires increased manufacturing flexibility. Integrating an ML-based VM model with design features and FDC into the APC system is proposed as an effective process control solution for high-product-mix manufacturing. Simulation results confirm the remarkable effectiveness of this solution in the CVD process, particularly within a high-product-mix foundry fab.
