Machine Learning for Optimized Scheduling in Complex Semiconductor Equipment

Abstract

Semiconductor cluster equipment adds 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. Such 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. Software engineers typically build schedulers using a set of manually- configured heuristics but this can be a labor-intensive process where small changes to the cluster configuration or process requirements can require large changes to the scheduler. Our motivation for this work was to investigate whether a machine learning approach to complex cluster scheduling could be developed more efficiently and at a lower cost than existing methods.