Plasma processing system, assistance device, assistance method, and assistance program

An assistance device comprising:

• a processor;
• memory including a computer readable program stored executable by the processor;
• an input unit configured to acquire a first input related to a structure of a pre-processing substrate, a second input related to a required shape of a post-processing substrate, a third input related to a specification of a plasma processing device, and a fourth input related to a state of the plasma processing device;
• a first determination unit configured to determine, based on the first input, the second input, the third input, and the fourth input, a plurality of control parameters for processing the pre-processing substrate so that a predicted shape of the post-processing substrate conforms the required shape of the post-processing substrate, using a first machine learning model, each of the plurality of control parameters having a plurality of states that change over time, the first machine learning model being trained in advance based on a plurality of experimental results and a plurality of simulation results;
• a second determination unit configured to determine, based on the determined control parameters, the third input, and the fourth input, an operating condition of the plasma processing device using a second machine learning model, the operating condition including a cleaning condition and/or a coating condition for a chamber included in the plasma processing device, the second machine learning model being trained in advance based on a plurality of experimental results and a plurality of simulation results;
• and
• an output unit configured to output the determined control parameters and the determined operating condition.

An assistance method causing a computer to execute:

• acquiring a first input related to a structure of a pre-processing substrate, a second input related to a required shape of a post-processing substrate, a third input related to a specification of a plasma processing device, and a fourth input related to a state of the plasma processing device;
• determining, based on the first input, the second input, the third input, and the fourth input, a plurality of control parameters for processing the pre-processing substrate so that a predicted shape of the post-processing substrate conforms the required shape of the post-processing substrate, using a first machine learning model, each of the plurality of control parameters having a plurality of states that change over time, the first machine learning model being trained in advance based on a plurality of experimental results and a plurality of simulation results;
• determining, based on the determined control parameters, the third input, and the fourth input, an operating condition of the plasma processing device using a second machine learning model, the operating condition including a cleaning condition and/or a coating condition for a chamber included in the plasma processing device, the second machine learning model being trained in advance based on a plurality of experimental results and a plurality of simulation results;
• and
• outputting the determined control parameters and the determined operating condition.

A non-transitory computer readable medium comprising computer executable program code configured to instruct at least one computer to perform the following process:

• acquiring a first input related to a structure of a pre-processing substrate, a second input related to a required shape of a post-processing substrate, a third input related to a specification of a plasma processing device, and a fourth input related to a state of the plasma processing device;
• determining, based on the first input, the second input, the third input, and the fourth input, a plurality of control parameters for processing the pre-processing substrate so that a predicted shape of the post-processing substrate conforms the required shape of the post-processing substrate, using a first machine learning model, each of the plurality of control parameters having a plurality of states that change over time, the first machine learning model being trained in advance based on a plurality of experimental results and a plurality of simulation results;
• determining, based on the determined control parameters, the third input, and the fourth input, an operating condition of the plasma processing device using a second machine learning model, the operating condition including a cleaning condition and/or a coating condition for a chamber included in the plasma processing device, the second machine learning model being trained in advance based on a plurality of experimental results and a plurality of simulation results;
• and
• outputting the determined control parameters and the determined operating condition.