Classifying faults associated with a manufacturing process

• US 20080010531A1
• Filed: 06/12/2006
• Published: 01/10/2008
• Est. Priority Date: 06/12/2006
• Status: Abandoned Application

• Current Assignee: MKS Instruments Incorporated
• Original Assignee: MKS Instruments Incorporated
• Inventors: Hendler, Lawrence, Lev-Ami, Uzi Josef
• Application Number:
  US11/451,223
• Publication Number:
  US 20080010531A1
• Time in Patent Office: Days
• US Class Current: 714/33
• CPC Class Codes: G05B 23/0281 Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis

Abstract

Faults that are associated with a set of variables that are each associated with a manufacturing parameter are classified. A fault vector is defined according to a multivariate analysis based on a contribution to a metric of a subset of the variables. The fault vector is compared to a plurality of previously-defined fault vectors to determine a comparison value indicative of a correlation between the fault vector and the plurality of previously-defined fault vectors. The fault vector is associated with at least one of a first set of fault vectors indicative of a known fault or a second set of fault vectors indicative of an unknown fault based in part on the comparison value.

Claims

1. A method for classifying faults associated with a manufacturing process, the method comprising:

determining that a fault exists when at least one of a

(a) T² score, calculated based on a Hotelling-type calculation performed on a first subset of a plurality of manufacturing process-related variables, exceeds a predetermined T² critical value or,

(b) DModX score, calculated based on a DModX-type calculation performed on a second subset of the plurality of manufacturing process-related variables, exceeds a predetermined DModX critical value;

generating fault vectors for each of the calculation types performed in which the corresponding score exceeds the corresponding critical value;

comparing the generated fault vectors to a plurality of corresponding, previously-defined fault vectors to determine a comparison value indicative of a correlation between the generated fault vectors and the plurality of corresponding, previously-defined fault vectors; and

associating each of the generated fault vectors with at least one of a first class of vectors indicative of a known fault or a second class of vectors indicative of an unknown fault based in part on the comparison value.

2. A method for classifying a fault associated with a set of variables each associated with a manufacturing parameter, the method comprising:

defining a fault vector according to a multivariate analysis based on a contribution of a subset of the set of variables to a metric;

comparing the fault vector to a plurality of previously-defined vectors to determine a comparison value indicative of a correlation between the fault vector and the plurality of previously-defined vectors; and

associating the fault vector with at least one of a first set of fault vectors indicative of a known fault or a second set of fault vectors indicative of an unknown fault based in part on the comparison value.

3. The method of claim 2, wherein the step of associating comprises determining if a subset of values of the fault vector satisfies a predetermined criterion.

4. The method of claim 3, wherein the subset of values of the fault vector comprises values that contribute to the comparison value and the predetermined criterion comprises whether a calculation based on the subset of values of the fault vector is above a predetermined threshold.

5. The method of claim 3, wherein the subset of values of the fault vector comprises values that do not contribute to the comparison value and the predetermined criterion comprises whether a calculation based on the subset of values of the fault vector is below a predetermined threshold.

6. The method of claim 3, wherein the predetermined criterion is determined by a user.

7. The method of claim 2, wherein the manufacturing parameters are measured in a semiconductor wafer processing facility.

8. The method of claim 2, further comprising:

prior to defining the fault vector, determining the fault exists when a value, calculated based on a mathematical expression performed on the set of variables, exceeds a critical value.

9. The method of claim 2, further comprising:

prior to defining the fault vector, determining the fault exists when at least one of

(a) a first value, calculated based on a Hotelling-type calculation performed on the set of variables, exceeds a first critical value or

(b) a second value, calculated based on a DModX-type calculation performed on the set of variables, exceeds a second value.

10. The method of claim 9, wherein the metric comprises at least one of the first value, the second value or both.

11. The method of claim 2, wherein the comparison value is determined according to Pearson'"'"'s correlation equation.

12. The method of claim 2, wherein the fault vector is associated with the first set of fault vectors when the comparison value exceeds a predetermined value.

13. The method of claim 12, wherein the predetermined value is determined by a user.

14. The method of claim 2, wherein the fault vector is associated with the second set of fault vectors when the comparison value does not exceed a predetermined value.

15. The method of claim 2, wherein the second set of fault vectors comprises an empty set before the fault vector is associated with the second set of fault vectors.

16. The method of claim 2, wherein associating the fault vector with the second set of fault vectors comprises establishing the second set of fault vectors.

17. The method of claim 2, further comprising assigning a statistical weight to the contribution to the metric of each member of the subset of the set of variables.

18. The method of claim 2, further comprising generating a model set of variables based on contributions from each member of a second set of variables used to define one or more previously-defined vectors selected from the plurality of previously-defined vectors.

19. The method of claim 2, further comprising determining an action to correct the fault based in part on whether the fault vector is associated with the first set of fault vectors or the second set of fault vectors.

20. The method of claim 2, further comprising associating a type of fault with the second set of fault vectors.

21. The method of claim 2, further comprising associating the fault vector with the plurality of previously-defined vectors.

22. A system for classifying a fault associated with a set of variables each associated with a manufacturing parameter, the system comprising:

a means for defining a fault vector according to a multivariate analysis based on a contribution of a subset of the set of variables to a metric;

a means for comparing the fault vector to a plurality of previously-defined vectors to determine a comparison value indicative of a correlation between the fault vector and the plurality of previously-defined vectors; and

a means for associating the fault vector with at least one of a first set of fault vectors indicative of a known fault or a second set of fault vectors indicative of an unknown fault based in part on the comparison value.

23. The system of claim 22, further comprising:

a means for determining the fault exists when at least one of a

(a) first value, calculated based on a Hotelling-type calculation performed on the set of variables, exceeds a first critical value or

(b) a second value, calculated based on a DModX-type calculation performed on the set of variables, exceeds a second critical value.

24. A computer program product, tangibly embodied in an information carrier, the computer program product including instructions being operable to cause data processing apparatus to:

define a fault vector according to a multivariate analysis based on a contribution to a metric of a subset of a set of variables each associated with a manufacturing parameter;

compare the fault vector to a plurality of previously-defined vectors to determine a comparison value indicative of a correlation between the fault vector and the plurality of previously-defined vectors; and

associate the fault vector with at least one of a first set of fault vectors indicative of a known fault or a second set of fault vectors indicative of an unknown fault based in part on the comparison value.

25. The computer program product of claim 24, further comprising instructions being operable to cause data processing apparatus to:

determine the fault exists when at least one of a

(a) first value, calculated based on a Hotelling-type calculation performed on the set of variables, exceeds a first critical value or

(b) a second value, calculated based on a DModX-type calculation performed on the set of variables, exceeds a second critical value.