Methods and apparatuses for utilizing adaptive predictive algorithms and determining when to use the adaptive predictive algorithms for virtual metrology

Patent metadata

Field	Value
Publication number	US-9886009-B2
Application number	US-201514673228-A
Country	US
Kind code	B2
Filing date	Mar 30, 2015
Priority date	Feb 16, 2010
Publication date	Feb 6, 2018
Grant date	Feb 6, 2018

Abstract

Described herein are methods, apparatuses, and systems for determining adaptive predictive algorithms for virtual metrology. In some embodiments, a computer implemented method identifies a plurality of predictive algorithms. The method determines when to use one or more of the plurality of predictive algorithms to predict one or more virtual metrology variables in a manufacturing facility.

First claim

What is claimed is:

1. A computer implemented method comprising:
identifying, with a multi-algorithm predictive subsystem that is designed to facilitate switching between predictive algorithms, a plurality of predictive algorithms including first and second adaptive predictive algorithms to predict one or more virtual metrology variables in a manufacturing facility;
identifying a quality threshold that is based on predictions of data and actual measurement data to determine when to switch between the first and second adaptive predictive algorithms;
comparing a quality for prediction with the quality threshold when actual measurement data for a current prediction cycle is not available; and
invoking, when the actual measurement data for a current prediction cycle is not available, the first adaptive predictive algorithm if the quality for prediction is less than or approximately equal to the quality threshold to update a prediction equation to adapt to dynamics of the manufacturing facility.

2. The computer implemented method of claim 1 , further comprising:
invoking, when the actual measurement data for a current prediction cycle is not available, the second adaptive predictive algorithm if the quality for prediction is greater than the quality threshold.

3. The computer implemented method of claim 1 , further comprising:
identifying a quality for prediction for each predictive algorithm;
identifying a quality for prediction for each prediction of data; and
performing a normalized weighted calculation of the predictions where weights are a function of the quality for prediction for each predictive algorithm if the actual measurement data is not available.

4. The computer implemented method of claim 1 , further comprising:
identifying an error switching threshold that is based on a comparison of predictions of data and actual data.

5. The computer implemented method of claim 4 , further comprising:
determining whether an error, which is a difference between predictions of data and actual measurement data, is greater than the error switching threshold.

6. The computer implemented method of claim 5 , further comprising:
invoking, when actual measurement data for the current prediction cycle is available, the first adaptive predictive algorithm for updating the prediction equation if an error is greater than the error switching threshold; and
subsequently invoking the second adaptive predictive algorithm for updating the prediction equation.

7. The computer implemented method of claim 5 , further comprising:
invoking, when actual measurement data for the current prediction cycle is available, the first adaptive predictive algorithm if the error is less than or approximately equal to the error switching threshold.

8. A computer-readable non-transitory storage medium comprising executable instructions to cause a processor to perform operations, the instructions comprising:
identifying, with a multi-algorithm predictive subsystem that is designed to facilitate switching between predictive algorithms, a plurality of predictive algorithms including first and second adaptive predictive algorithms to predict one or more virtual metrology variables in a manufacturing facility;
identifying a quality threshold that is based on predictions of data and actual measurement data to determine when to switch between the first and second adaptive predictive algorithms;
comparing a quality for prediction with the quality threshold when actual measurement data for a current prediction cycle is not available; and
invoking, when the actual measurement data for a current prediction cycle is not available, the first adaptive predictive algorithm if the quality for prediction is less than or approximately equal to the quality threshold to update a prediction equation to adapt to dynamics of the manufacturing facility.

9. The computer implemented method of claim 8 , further comprising:
invoking, when the actual measurement data for a current prediction cycle is not available, the second adaptive predictive algorithm if the quality for prediction is greater than the quality threshold.

10. The computer implemented method of claim 8 , further comprising:
identifying a quality for prediction for each predictive algorithm;
identifying a quality for prediction for each prediction of data; and
performing a normalized weighted calculation of the predictions where weights are a function of the quality for prediction for each predictive algorithm if the actual measurement data is not available.

11. The computer implemented method of claim 8 , further comprising:
identifying an error switching threshold that is based on a comparison of predictions of data and actual data.

12. The computer implemented method of claim 8 , further comprising:
determining whether an error, which is a difference between predictions of data and actual measurement data, is greater than the error switching threshold.

13. The computer implemented method of claim 12 , further comprising:
invoking, when actual measurement data for the current prediction cycle is available, the first adaptive predictive algorithm for updating the prediction equation if an error is greater than the error switching threshold; and
subsequently invoking the second adaptive predictive algorithm for updating the prediction equation.

14. The computer implemented method of claim 12 , further comprising:
invoking, when actual measurement data for the current prediction cycle is available, the first adaptive predictive algorithm if the error is less than or approximately equal to the error switching threshold.

15. A computer system comprising:
a memory to store a plurality of predictive algorithms; and
and at least one processing device, coupled to the memory, that is configured to execute processing logic to:
identify the plurality of predictive algorithms including first and second adaptive predictive algorithms to predict one or more virtual metrology variables in a manufacturing facility;
identify a quality threshold that is based on predictions of data and actual measurement data to determine when to switch between the first and second adaptive predictive algorithms;
compare a quality for prediction with the quality threshold when actual measurement data for a current prediction cycle is not available; and
invoking, when the actual measurement data for a current prediction cycle is not available, the first adaptive predictive algorithm if the quality for prediction is less than or approximately equal to the quality threshold to update a prediction equation to adapt to dynamics of the manufacturing facility.

16. The computer system of claim 15 , wherein the at least one processing device is further configured to execute processing logic to:
invoke, when the actual measurement data for a current prediction cycle is not available, the second adaptive predictive algorithm if the quality for prediction is greater than the quality threshold.

17. The computer system of claim 16 , wherein the at least one processing device is further configured to execute processing logic to:
identify a quality for prediction for each predictive algorithm;
identify a quality for prediction for each prediction of data; and
perform a normalized weighted calculation of the predictions where weights are a function of the quality for prediction for each predictive algorithm if the actual measurement data is not available.

18. The computer system of claim 15 , wherein the at least one processing device is further config

Assignees

• Moyne James
• Applied Materials Inc

Inventors

• Moyne James

Classifications

• G05B13/026 Primary

  using a predictor · CPC title

• G05B23/0297 Primary

  Reconfiguration of monitoring system, e.g. use of virtual sensors; change monitoring method as a response to monitoring results · CPC title

• G05B2219/31483

  Verify monitored data if valid or not by comparing with reference value · CPC title

• G06Q50/04

  Manufacturing · CPC title

• G05B2219/31459

  Library with metrology plan for different type of workpieces · CPC title