Process characterization and correction using optical wall process sensor (OWPS)
A method includes receiving, by a processing device, first data from an optical sensor of a processing chamber. The method further includes processing the first data to obtain second data. The second data includes an indication of a condition of a coating on an interior surface of the processing chamber. The method further includes generating an indication of performance of a processing operation of the processing chamber in view of the second data. The method further includes causing performance of a corrective action in view of the indication of performance of the processing chamber.
1 . A method, comprising:
receiving, by a processing device, first data from an optical sensor of a processing chamber, wherein the first data is collected while the processing chamber is under operating conditions;
obtaining reference state data from the optical sensor, collected while the processing chamber is in a reference state which is different from the operating conditions;
determining a reference sensor response of the optical sensor based on the reference state data;
correcting the first data to generate corrected first data based on the reference sensor response of the optical sensor;
processing the corrected first data to obtain second data, wherein the second data comprises an indication of a condition of a coating on an interior surface of the processing chamber;
generating an indication of performance of a first processing operation of the processing chamber in view of the second data; and
causing performance of a corrective action in response to the indication of performance of the first processing operation of the processing chamber, the corrective action comprising providing a signal to cause the processing chamber to end a second processing operation in accordance with an updated chamber endpoint condition based on the indication of performance.
2 . The method of claim 1 , wherein the first processing operation comprises at least one of:
a chamber cleaning operation;
a chamber conditioning operation;
a chamber coating operation, or
a chamber seasoning operation.
3 . The method of claim 1 , wherein the first processing operation comprises an operation wherein material is deposited on or removed from the coating on the interior surface of the processing chamber, and wherein the corrective action comprises adjusting an endpoint of a process recipe associated with the first processing operation.
4 . The method of claim 1 , further comprising receiving third data from the optical sensor, wherein the first data is collected while a light source optically coupled to the optical sensor is active, and the second data is collected while the light source is inactive.
5 . The method of claim 1 , wherein the first data comprises spectral data.
6 . The method of claim 1 , wherein the corrective action further comprises one or more of: providing an alert to a user;
updating a processing operation recipe;
scheduling preventative maintenance;
scheduling corrective maintenance; or
scheduling chamber conditioning or seasoning.
7 . The method of claim 1 , wherein the condition of the coating comprises a thickness of the coating.
8 . The method of claim 1 , wherein generating an indication of performance of the first processing operation comprises:
providing the second data to a trained machine learning model; and
receiving output indicative of performance of the first processing operation from the trained machine learning model.
9 . The method of claim 8 , further comprising:
receiving third data associated with historical optical sensor data;
receiving fourth data comprising historical anomaly label data associated with the third data; and
training the trained machine learning model by providing the third data as training input and the fourth data as target output.
10 . A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations comprising:
receiving first data from an optical sensor of a processing chamber, wherein the first data is associated with a first operation of the processing chamber;
receiving second data from the optical sensor of the processing chamber, wherein the second data is associated with a second operation of the processing chamber;
generating a first and second indication of performance of the processing chamber based on the first and second data;
obtaining reference data from the optical sensor, the reference data collected while the processing chamber is in a reference state, different than operating conditions of the first operation and operating conditions of the second operation;
determining one or more differences in performance between the first operation and the second operation; and
causing performance of a corrective action based on the one or more differences and the reference data, the corrective action comprising providing a signal to cause the processing chamber to end a third operation of the processing chamber in accordance with an updated endpoint condition based on the one or more differences and the reference data.
11 . The non-transitory machine-readable storage medium of claim 10 , wherein the first data is one among a plurality of historical data received from the optical sensor, wherein each of the plurality of historical data is associated with one of a plurality of historical operations of the processing chamber.
12 . The non-transitory machine-readable storage medium of claim 10 , the operations further comprising:
providing the second data to a trained machine learning model, wherein the trained machine learning model is configured to detect at least one of outliers or anomalies based on optical sensor data.
13 . The non-transitory machine-readable storage medium of claim 10 , wherein the second data is indicative of an evolution of optical sensor data over a duration of the second operation of the processing chamber.
14 . The non-transitory machine-readable storage medium of claim 10 , the operations further comprising:
receiving third data, wherein the third data comprises at least one of sensor data or metrology data associated with the first operation;
receiving fourth data, wherein the fourth data comprises at least one of sensor data or metrology data associated with the second operation; and
determining a third and fourth indication of performance of the processing chamber, wherein the third indication is determined in view of the first data and the third data, and the fourth indication of performance is determined in view of the second data and the fourth data.
15 . A method, comprising:
receiving, by a processing device, first data from an optical sensor of a first processing chamber;
receiving second data from an optical sensor of a second processing chamber;
obtaining third data from the optical sensor of the first processing chamber, collected while the first processing chamber is in a reference state;
obtaining fourth data from the optical sensor of the second processing chamber, collected with the second processing chamber is in the reference state;
generating a first indication of performance of the first processing chamber based on the first data and the third data and a second indication of performance of the second processing chamber based on the second data and the fourth data;
determining one or more differences in performance between the first processing chamber and the second processing chamber; and
causing performance of a corrective action based on the one or more differences, the corrective action comprising providing a signal to cause the second processing chamber to end an operation of the second processing chamber in accordance with an updated endpoint condition based on the one or more differences.
16 . The method of claim 15 , wherein the corrective action is to alter performance of the second processing chamber, wherein the altered performance of the second processing chamber is associated with a first performance metric, and wherein a value of the first performance metric is closer to a value of a second performance metric associated with the first process chamber after the corrective action is performed.
17 . The method of claim 15 , further comprising receiving third data comprising data indicative of performance of a plurality of processing chambers, wherein causing performance of a corrective action is responsive to one or more differences between the second data and the third data.
18 . The method of claim 15 , further comprising providing the second data to a trained machine learning model, wherein the trained machine learning model is configured to determine the one or more differences in performance between the first and second processing chambers.
19 . The method of claim 15 , wherein the first and second indications of performance comprise a dimensionless index associated with an optical thickness of a coating on an interior surface of the first processing chamber and the second processing chamber or a chemical composition of a coating on an interior surface of the first processing chamber and the second processing chamber.