Model-based scheduling for substrate processing systems

A tool for processing semiconductor substrates comprising:

• a first robot configured to input the semiconductor substrates into the tool for processing the semiconductor substrates in the tool;
• a plurality of processing chambers configured to process the semiconductor substrates in the tool according to a recipe;
• a second robot configured to transfer the semiconductor substrates between the plurality of processing chambers according to the recipe;
• and
• a controller configured to predict, using a model trained by simulating the tool and the recipe, one or more of:
• processing times for processing the semiconductor substrates in the plurality of processing chambers;
• transfer times for the second robot for transferring the semiconductor substrates between the plurality of processing chambers;
• a route to transfer the semiconductor substrates between the plurality of processing chambers based on the processing times and the transfer times;
• and
• a time when the first robot is to schedule additional semiconductor substrates for processing in the tool based on the processing times and the transfer times.

A system for optimizing throughput and wait times during processing semiconductor substrates in a semiconductor processing tool, the system comprising:

• a processor;
• and
• non-transitory memory storing instructions for execution by the processor, wherein the instructions are configured to:
• simulate, based on a configuration of the semiconductor processing tool and a recipe to be performed on the semiconductor substrates in the semiconductor processing tool, a plurality of routes for routing the semiconductor substrates between a plurality of processing chambers of the semiconductor processing tool;
• simulate processing of the semiconductor substrates in the semiconductor processing tool according to the recipe along the plurality of routes;
• simulate, based on the processing of the semiconductor substrates, a plurality of timing schedules for subsequently processing additional semiconductor substrates in the semiconductor processing tool;
• simulate processing of the additional semiconductor substrates according to the plurality of timing schedules;
• and
• train a model based on data generated by the simulations.