Predictive wafer scheduling for multi-chamber semiconductor equipment

A system comprising:

• a memory;
• and
• a processing device communicably coupled to the memory, the processing device to:
• identify a machine learning model, updated based on a first duration to perform a first manufacturing task using a wafer modification chamber and a second duration to perform a second manufacturing task using a wafer movement chamber, to perform a computer simulation forecasting processing of a set of wafers using the wafer modification chamber and the wafer movement chamber based on a set of start times, wherein each wafer of the set of wafers is associated with a respective start time of the set of start times;
• initiate the computer simulation using the machine learning model based on the set of start times for the set of wafers to obtain a first simulation result;
• determine whether the set of wafers includes an idle wafer that is idle for a duration that exceeds a predefined threshold value;
• in response to determining that the set of wafers includes the idle wafer, generate a modified set of start times by modifying at least the start time for the idle wafer;
• initiate, using the machine learning model, a second computer simulation forecasting processing of the set of wafers using the wafer modification chamber and the wafer movement chamber based on the modified set of start times to obtain a second simulation result;
• and
• store, in a data store, a simulation result selected from a set of simulation results comprising the first simulation result and the second simulation result, wherein the simulation result is represented by a set of vectors comprising time series data.

A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations comprising:

• identifying a machine learning model, updated based on a first duration to perform a first manufacturing task using a wafer modification chamber and a second duration to perform a second manufacturing task using a wafer movement chamber, to perform a computer simulation forecasting processing of a set of wafers using the wafer modification chamber and the wafer movement chamber based on a set of start times, wherein each wafer of the set of wafers is associated with a respective start time of the set of start times;
• initiating the computer simulation using the machine learning model based on the set of start times for the set of wafers to obtain a first simulation result;
• determining whether the set of wafers includes an idle wafer that is idle for a duration that exceeds a predefined threshold value;
• in response to determining that the set of wafers includes the idle wafer, generating a modified set of start times by modifying at least the start time for the idle wafer;
• initiating, using the machine learning model, a second computer simulation forecasting processing of the set of wafers using the wafer modification chamber and the wafer movement chamber based on the modified set of start times to obtain a second simulation result;
• and
• storing, in a data store, a simulation result selected from a set of simulation results comprising the first simulation result and the second simulation result, wherein the simulation result is represented by a set of vectors comprising time series data.