Chamber matching and calibration
A method includes receiving a plurality of sets of sensor data associated with a processing chamber of a substrate processing system. Each of the plurality of sets of sensor data comprises a corresponding sensor value of the processing chamber mapped to a corresponding spacing value of the processing chamber. The method further includes providing the plurality of sets of sensor data as input to a trained machine learning model. The method further includes obtaining, from the trained machine learning model, one or more outputs indicative of a health of the processing chamber. The method further includes causing, based on the one or more outputs, performance of one or more corrective actions associated with the processing chamber.
1. A method comprising:
receiving a plurality of sets of sensor data associated with a processing chamber of a substrate processing system, wherein each of the plurality of sets of sensor data comprises a corresponding sensor value of the processing chamber mapped to a corresponding spacing value of the processing chamber, wherein the corresponding spacing value corresponds to a respective distance between an upper surface of an edge ring of the processing chamber and a lower surface of a ceramic isolator of the processing chamber;
providing the plurality of sets of sensor data as input to a trained machine learning model;
obtaining, from the trained machine learning model, one or more outputs indicative of a health of the processing chamber; and
causing, based on the one or more outputs, performance of one or more corrective actions associated with adjusting the respective distance between the edge ring and the ceramic isolator.
2. The method of claim 1 , wherein the corresponding sensor value is:
a corresponding pressure value of the processing chamber; or
a corresponding pumping efficiency value associated with the processing chamber.
3. The method of claim 1 , wherein the corresponding sensor value is a corresponding pressure value associated with exhaust pressure of gas leaving the processing chamber via an opening between the upper surface of the edge ring and the lower surface of the ceramic isolator.
4. The method of claim 1 , wherein the receiving of the plurality of sets of sensor data is after one or more of performing preventative maintenance on the processing chamber or installation of the processing chamber.
5. The method of claim 1 , wherein the one or more outputs are indicative of an error in calibration of heater spacing of the processing chamber, and wherein the performance of the one or more corrective actions comprises one or more of providing an alert or causing recalibration of the heater spacing of the processing chamber.
6. The method of claim 5 , and wherein the heater spacing comprises a plurality of distances between the upper surface of the edge ring and the lower surface of the ceramic isolator.
7. The method of claim 1 , wherein the one or more outputs are indicative of an error in installation of a process kit ring in the processing chamber, and wherein the performance of the one or more corrective actions comprises one or more of providing an alert or causing re-installation of the process kit ring in the processing chamber.
8. The method of claim 1 further comprising:
receiving performance data associated with the processing chamber; and
causing the trained machine learning model to be further trained with data input comprising the plurality of sets of sensor data and target output comprising the performance data.
9. A method comprising:
receiving a plurality of sets of historical sensor data associated with one or more processing chambers of one or more substrate processing systems, wherein each of the plurality of sets of historical sensor data comprises a corresponding historical sensor value mapped to a corresponding historical spacing value, wherein the corresponding historical spacing value corresponds to a respective distance between an upper surface of an edge ring of a corresponding processing chamber and a lower surface of a cermaic isolator of the corresponding processing chamber;
receiving a plurality of sets of historical performance data associated with the one or more processing chambers, wherein each of the plurality of sets of historical performance data corresponds to a respective set of historical sensor data of the plurality of sets of historical sensor data; and
training a machine learning model with data input comprising the plurality of sets of historical sensor data and target output comprising the plurality of sets of historical performance data to generate a trained machine learning model, the trained machine learning model being capable of generating one or more outputs indicative of a health of a processing chamber to cause performance of one or more corrective actions associated with adjusting the respective distance between the edge ring and the ceramic isolator.
10. The method of claim 9 , wherein the corresponding historical sensor value is a corresponding historical pressure value associated with exhaust pressure of gas leaving the corresponding processing chamber via an opening between the upper surface of the edge ring and the lower surface of the ceramic isolator.
11. The method of claim 9 , wherein:
the one or more outputs are indicative of an error in calibration of heater spacing of the processing chamber;
the performance of the one or more corrective actions comprises one or more of providing an alert or causing recalibration of the heater spacing of the processing chamber; and
the heater spacing comprises a plurality of distances between the upper surface of the edge ring and the lower surface of the ceramic isolator.
12. The method of claim 9 , wherein the one or more outputs are indicative of an error in installation of a process kit ring in the processing chamber, and wherein the performance of the one or more corrective actions comprises one or more of providing an alert or causing re-installation of the process kit ring in the processing chamber.
13. A non-transitory machine-readable storage medium storing instructions which, when executed cause a processing device to perform operations comprising:
receiving a plurality of sets of sensor data associated with a processing chamber of a substrate processing system, wherein each of the plurality of sets of sensor data comprises a corresponding sensor value of the processing chamber mapped to a corresponding spacing value of the processing chamber, wherein the corresponding spacing value corresponds to a respective distance between an upper surface of an edge ring of the processing chamber and a lower surface of a ceramic isolator of the processing chamber;
providing the plurality of sets of sensor data as input to a trained machine learning model;
obtaining, from the trained machine learning model, one or more outputs indicative of a health of the processing chamber; and
causing, based on the one or more outputs, performance of one or more corrective actions associated with adjusting the respective distance between the edge ring and the ceramic isolator.
14. The non-transitory machine-readable storage medium of claim 13 , wherein:
the respective distance is between the upper surface of the edge ring and the lower surface of the ceramic isolator; and
the corresponding sensor value is a corresponding pressure value associated with exhaust pressure of gas leaving the processing chamber via an opening between the upper surface of the edge ring and the lower surface of the ceramic isolator.
15. The non-transitory machine-readable storage medium of claim 13 , wherein the receiving of the plurality of sets of sensor data is after one or more of performing preventative maintenance on the processing chamber or installation of the processing chamber.
16. The non-transitory machine-readable storage medium of claim 13 , wherein:
the one or more outputs are indicative of an error in calibration of heater spacing of the processing chamber;
the performance of the one or more corrective actions comprises one or more of providing an alert or causing recalibration of the heater spacing of the processing chamber; and
the heater spacing comprises a plurality of distances between the upper surface of the edge ring and the lower surface of the ceramic isolator.
17. The non-transitory machine-readable storage medium of claim 13 , wherein the one or more outputs are indicative of an error in installation of a process kit ring in the processing chamber, and wherein the performance of the one or more corrective actions comprises one or more of providing an alert or causing re-installation of the process kit ring in the processing chamber.
18. The non-transitory machine-readable storage medium of claim 13 , the operations further comprising:
receiving performance data associated with the processing chamber; and
causing the trained machine learning model to be further trained with data input comprising the plurality of sets of sensor data and target output comprising the performance data.