Artificial Intelligence for Real Time Cluster Tool Scheduling : EO: Equipment Optimization

Abstract

Semiconductor cluster tools add an integral component to the modern semiconductor manufacturing process. These complex tools provide a flexible deployment option to group multiple processing steps into a single piece of equipment, allowing for more efficient processing. They also contribute to a reduction in the number of times a wafer must go through the atmospheric-vacuum-atmospheric cycle. These highly automated tools present a complex scheduling challenge where process-specific requirements are balanced against a need to achieve maximum wafer throughput in a fault tolerant manner. Due to the global chip shortage, many semiconductor fabs have started to demand increased throughput from the equipment on their manufacturing floors. While process timing is often constrained by physics, opportunities do exist to reduce wait time waste by leveraging machine learning to optimize the manner in which substrates are scheduled within complex semiconductor cluster tools.Previous work demonstrated that a reinforcement learning algorithm is suitable for automated generation of efficient planners for both simple and complex tools [2]. This investigation looked at techniques that could be used to move scheduler optimization away from offline cloud analysis and into real time, on-tool production planning.