Expertise / Resources / Presentations / Machine Learning for cluster tool throughput optimization
Machine Learning for cluster tool throughput optimization
These slides were presented at the virtual APC|M conference, 2021.
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 efficient processing. Cluster tools also contribute to a reduction in the number of times a wafer must go through the atmospheric-vacuum-atmospheric cycle, resulting in faster processing and reduced risk of excursions. These highly automated tools present a complex scheduling challenge where process-specific requirements must be balanced against the 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 often require large changes to the scheduler. We investigated whether a Machine Learning approach to complex scheduling could be developed efficiently and at a lower cost than existing methods.