Method and apparatus for evaluating processing apparatus status and predicting processing result

• US 7,689,028 B2
• Filed: 11/10/2004
• Issued: 03/30/2010
• Est. Priority Date: 05/16/2002
• Status: Active Grant

• Current Assignee: Tokyo Electron Limited
• Original Assignee: Tokyo Electron Limited
• Inventors: Sakano, Shinji, Harada, Satoshi
• Primary Examiner(s): Mariam; Daniel G
• Assistant Examiner(s): Woldemariam; Aklilu k
• Application Number:
  US10/984,932
• Publication Number:
  US 20050125090A1
• Time in Patent Office: 1,966 Days
• Field of Search: 382/145, 382/155, 700/108, 700/121, 702/18, 702/182, 216/61, 340/604
• US Class Current: 382/145
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
• CPC Class Codes: H01J 37/32862 In situ cleaning of vessels and/or internal parts

Abstract

A method for predicting a processing result includes a process of performing a principal component analysis on a plurality of detected data obtained during a first standard processing, to construct a principal component analysis model; a process of obtaining residuals of the principal component analysis model as first residuals; a process of performing a second standard processing; and a process of obtaining a plurality of detected data from a plurality of detectors during the second standard processing. And, the detected data obtained during the second standard processing are applied to the principal component analysis model, to obtain second residuals. The method further includes a process of weighting the second residuals based on weighting references, and constructing a new multivariate analysis model with use of the weighted second residuals; and a process of predicting a processing result of the second standard processing with use of the multivariate analysis model.

Claims

1. A method for predicting a processing result, comprising:

a process of performing a predetermined first standard processing on a plurality of objects to be processed with use of a first processing apparatus set in a certain condition;

a process of obtaining a plurality of detected data from a plurality of detectors provided at the first processing apparatus during the first standard processing;

a process of performing a principal component analysis on the plurality of detected data obtained during the first standard processing, to construct a principal component analysis model;

a process of obtaining residuals of the principal component analysis model as first residuals;

a process of performing a second standard processing, which is similar to the first standard processing, on a plurality of objects to be processed, which are similar to said the plurality of objects to be processed, with use of the first processing apparatus in another condition or another second processing apparatus of the same kind;

a process of obtaining a plurality of detected data from the plurality of detectors provided at the first processing apparatus or from a plurality of detectors provided at the second processing apparatus during the second standard processing;

a process of applying the plurality of detected data obtained during the second standard processing to the principal component analysis model, to obtain second residuals;

a process of selecting from the obtained second residuals those of the second residuals within a maximum and a minimum of the first residuals;

a process of weighting the selected second residuals, and constructing a new multivariate analysis model with use of the selected second residuals; and

a process of predicting a processing result of the second standard processing with use of the multivariate analysis model.

2. The processing result prediction method of claim 1, wherein the process of weighting applies weighting references which are binary references indicating whether or not each of the second residuals should be adopted.

3. The processing result prediction method of claim 2, wherein the process of weighting applies weighting references which are references to adopt second residuals with small variations.

4. The processing result prediction method of claim 3, wherein the process of weighting applies weighting references which are references to determine second residuals with small variations based on the maximum value and the minimum value of the first residuals.

5. The processing result prediction method of claim 1, wherein the process of performing the principal component analysis on the plurality of detected data obtained during the first standard processing, to construct the principal component analysis model includes a process of obtaining a degree of principal components with use of a cross-validation method.

6. The processing result prediction method of claim 1, wherein the process of obtaining the residuals of the principal component analysis model as the first residuals includes:

a process of dividing a result of the principal component analysis into principal components with high contribution rates and principal components with low contribution rates; and

a process of merging residuals of the principal components with low contribution rates into a residual matrix.

7. The processing result prediction method of claim 1, wherein the multivariate analysis model is a multiple regression analysis model.

8. The processing result prediction method of claim 1, wherein said a certain condition is a condition before a maintenance, and said another condition is a condition after the apparatus is changed due to the maintenance.

9. The processing result prediction method of claim 8, wherein said a condition in the apparatus includes attachment statuses of the respective detectors.

10. The processing result prediction method of claim 8, wherein said a condition in the apparatus includes a surface condition in the apparatus.

11. The processing result prediction method of claim 8, wherein the maintenance includes a cleaning of the apparatus.

12. The processing result prediction method of claim 1, wherein the processing apparatus is a plasma processing apparatus.

13. The processing result prediction method of claim 12, wherein both the detected data include data for plasma emission intensities.

21. The processing result prediction method of claim 4, wherein the selected second residuals which are greater than the minimum value of the first residuals and smaller than the maximum value of the first residuals are adopted.

14. An apparatus for predicting a processing result, comprising:

a unit for, while performing a predetermined first standard processing on a plurality of objects to be processed with use of a first processing apparatus set in a certain condition, performing a principal component analysis on a plurality of detected data obtained from a plurality of detectors provided at the first processing apparatus, to construct a principal component analysis model;

a unit for obtaining residuals of the principal component analysis model as first residuals;

a unit for, while performing a second standard processing, which is similar to the first standard processing, on a plurality of objects to be processed, which are similar to said the plurality of objects to be processed, with use of the first processing apparatus in another condition or another second processing apparatus of the same kind, applying a plurality of detected data, obtained from the plurality of detectors provided at the first processing apparatus or from a plurality of detectors provided at the second processing apparatus, to the principal component analysis model, to obtain second residuals;

a unit for selecting from the obtained second residuals those of the second residuals within a maximum and a minimum of the first residuals;

a unit for weighting the second residuals, and constructing a new multivariate analysis model with use of the selected second residuals; and

a unit for predicting a processing result of the second standard processing with use of the multivariate analysis model.

15. The processing result prediction apparatus of claim 14, wherein the unit for weighting applies weighting references which are binary references indicating whether or not each of the second residuals should be adopted.

16. The processing result prediction apparatus of claim 15, wherein the unit for weighting applies weighting references which are references to adopt second residuals with small variations.

17. The processing result prediction apparatus of claim 16, wherein the unit for weighting applies weighting references which are references to determine second residuals with small variations based on the maximum value and the minimum value of the first residuals.

18. The processing result prediction apparatus of claim 14, wherein the unit to construct the principal component analysis model includes a unit for obtaining a degree of principal components with use of a cross-validation method.

19. The processing result prediction apparatus of claim 14, wherein the unit for obtaining the residuals of the principal component analysis model as the first residuals includes:

a unit for dividing a result of the principal component analysis into principal components with high contribution rates and principal components with low contribution rates; and

a unit for merging residuals of the principal components with low contribution rates into a residual matrix.

20. The processing result prediction apparatus of claim 14, wherein the multivariate analysis model is a multiple regression analysis model.

22. The processing result prediction apparatus of claim 17, wherein the selected second residuals which are greater than the minimum value of the first residuals and smaller than the maximum value of the first residuals are adopted.