Big Data Capabilities Applied to Semiconductor Manufacturing Advanced Process Control

Abstract

As requirements on data volumes, rates, quality, merging, and analytics increase exponentially in the digital universe, semiconductor manufacturers are faced with a need for new approaches to data management and use across the Fab. These are often termed “big data” challenges. In our industry big data solutions will be key to scaling advanced process control (APC) solutions to finer levels of control and diagnostics. However the main impact will be to better enable more effective predictive technologies such as predictive maintenance (PdM), virtual metrology and yield prediction, all of which utilize data from traditional APC capabilities that include fault detection and classification and run-to-run control. PdM represents one area where big data solutions are generating significant benefits across a variety of process types. Moving to big data solutions involves addressing the aforementioned requirements either with enhancements of existing systems or moving to more big data friendly platforms. Big data friendly platforms applied to APC systems provide quantifiable cost-of-ownership and speed improvements, thereby better enabling high quality prediction solutions. Initially, big data solutions will largely be delegated to off-line and on-time critical tasks; over the longer term these big data solutions will increasingly be leveraged for time critical and real-time capabilities.