Fault detection through feedback

• US 20060095232A1
• Filed: 11/02/2004
• Published: 05/04/2006
• Est. Priority Date: 11/02/2004
• Status: Active Grant

• Current Assignee: Ocean Semiconductor LLC (Fullbrite Capital Partners, LLC)
• Original Assignee: Advanced Micro Devices, Inc.
• Inventors: Purdy, Matthew A.
• Granted Patent: US 8,676,538 B2
• Time in Patent Office: Days
• US Class Current: 702/185
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods

Abstract

A method, apparatus and a system, for provided for performing a dynamic weighting technique for performing fault detection. The method comprises processing a workpiece and performing a fault detection analysis relating to the processing of the workpiece. The method further comprises determining a relationship of a parameter relating to the fault detection analysis to a detected fault and adjusting a weighting associated with the parameter based upon the relationship of the parameter to the detected fault.

Claims

1. A method, comprising:

processing a workpiece;

performing a fault detection analysis relating to said processing of said workpiece;

determining a relationship of a parameter relating to said fault detection analysis to a detected fault; and

adjusting a weighting associated with said parameter based upon said relationship of said parameter to said detected fault.

2. The method of claim 1, wherein performing said processing said workpiece further comprises processing a semiconductor wafer.

3. The method of claim 1, further comprising processing at least one subsequent workpiece.

4. The method of claim 1, further comprising determining a relationship of a parameter relating to said fault detection analysis to a detected fault further comprises determining a causation of a parameter relating to said fault detection analysis to a detected fault.

5. The method of claim 1, further comprising determining a relationship of a parameter relating to said fault detection analysis to a detected fault further comprises determining an importance of a parameter relating to said fault detection analysis to a detected fault.

6. The method of claim 1, further comprising:

determining whether said detected fault is a significant fault; and

adjusting said weighting associated with said parameter based upon determining that said detected fault is a significant fault.

7. The method of claim 1, further comprising:

acquiring metrology data relating to processing said workpiece;

acquiring tool state data relating to processing said workpiece; and

correlating said metrology data and said tool state data with said fault data to characterize a fault.

8. The method of claim 7, wherein acquiring said tool state data relating to processing said workpiece further comprises acquiring at least one of a pressure data, a temperature data, humidity data, and a gas flow rate data associated with said processing of said workpiece.

9. The method of claim 1, wherein performing said fault detection analysis further comprises utilizing a fault detection model to perform said fault detection, wherein said parameter is an input parameter to said fault detection model.

10. The method of claim 1, wherein performing said fault detection analysis further comprises performing a principal component analysis (PCA) relating to said processing of said workpiece.

11. The method of claim 10, wherein performing said principal component analysis further comprises utilizing a PCA model to perform said PCA, wherein said parameter is an input parameter to said PCA model.

12. The method of claim 1, wherein determining said relationship of a parameter relating to said fault detection analysis to a detected fault further comprises determining whether said parameter is a significant factor associated with said fault.

13. The method of claim 1, wherein adjusting said weighting associated with said parameter based upon said relationship of said parameter to said detected fault further comprises increasing said weighting associated with said parameter based upon said relationship.

14. The method of claim 13, wherein increasing said weighting associated with said parameter based upon said relationship further comprises requiring a smaller fluctuation of said parameter during said fault detection analysis to determine that a fault associated with said processing of said workpiece has occurred.

15. The method of claim 1, wherein adjusting said weighting associated with said parameter based upon said relationship of said parameter to said detected fault further comprises decreasing said weighting associated with said parameter based upon said relationship.

16. The method of claim 15, wherein increasing said weighting associated with said parameter based upon said relationship further comprises requiring a larger fluctuation of said parameter during said fault detection analysis to determine that a fault associated with said processing of said workpiece has occurred.

17. The method of claim 1, wherein determining said relationship of a parameter relating to said fault detection analysis to said detected fault further comprises determining a relationship between at least one of a pressure data, a temperature data, a humidity data, and a gas flow rate data associated with said processing of said workpiece, to said detected fault.

18. A method, comprising:

processing a workpiece;

performing a fault detection analysis relating to said processing of said workpiece based upon a tool state parameter being input into a fault detection model associated with said fault detection analysis;

determining whether said parameter is associated with a detected fault as a result of performing said fault detection analysis; and

modifying a weighting of said parameter in said fault detection model based upon a determination that said parameter is associated with said detected fault.

19. The method of claim 18, wherein modifying said weighting of said parameter in said fault detection model further comprises increasing said weighting of said parameter.

20. The method of claim 18, wherein modifying said weighting of said parameter in said fault detection model further comprises decreasing said weighting of said parameter.

21. The method of claim 18, further comprising performing a principal component analysis.

22. The method of claim 18, further comprising processing at least one subsequent workpiece.

23. A method, comprising:

processing a workpiece;

performing a principal component analysis (PCA) relating to said processing of said workpiece based upon a tool state parameter being input into a PCA model associated with said PCA analysis;

determining whether said parameter is associated with a detected fault as a result of performing said PCA; and

modifying a weighting of said parameter in said PCA model based upon a determination that said parameter is associated with said detected fault.

24. The method of claim 23, further comprising performing a principal component analysis.

25. An apparatus, comprising:

means for processing a workpiece;

means for performing a fault detection analysis relating to said processing of said workpiece;

means for determining a relationship of a parameter relating to said fault detection analysis to a detected fault; and

means for adjusting a weighting associated with said parameter based upon said relationship of said parameter to said detected fault.

26. A system, comprising:

a processing tool to perform a process upon a workpiece;

a metrology tool to acquire metrology data relating to said process performed on said workpiece to provide metrology data;

a tool state data sensor unit to acquire tool state data;

a controller operatively coupled to said processing tool, metrology tool and to said tool state data sensor unit, said controller to perform a fault detection analysis relating to said processing of said workpiece to determine a relationship between a parameter relating to said fault detection analysis and a detected fault, said controller to also adjust a weighting associated with said parameter based upon said relationship of said parameter to said detected fault.

27. The system of claim 26, wherein said workpiece is a semiconductor wafer.

28. The system of claim 26, further comprising a fault detection model for performing said fault detection analysis, said parameter being an input into said fault detection model.

29. The system of claim 26, further comprising a principal component analysis (PCA) model for performing principal component analysis, said parameter being an input into said PCA model.

30. The system of claim 29, wherein said controller further comprising a dynamic PCA-weighting module, said dynamic PCA-weighting module comprising:

a fault data analysis module for determining whether said parameter was a significant factor in said detected fault;

a fault data input interface to receive an external data indicating whether said parameter was a significant factor in said detected fault; and

a dynamic PCA weight calculation module to dynamically modify said weighting of said parameter based upon at least one of said determination and said indication whether said parameter was a significant factor in said detected fault.

31. The system of claim 30, wherein said controller to increase a weighting of said parameter in response to at least said indication and said determination that said parameter is a significant factor in said detected fault.

32. The system of claim 30, wherein said controller to decrease a weighting of said parameter in response to at least said indication and said determination that said parameter is a significant factor in said detected fault.

33. The system of claim 26, further comprising a database unit to store at least one of said metrology data, said tool state data, and data relating to said fault detection analysis.

34. An apparatus, comprising:

a controller operatively to perform a fault detection analysis relating to a processing of a workpiece to determine a relationship between a parameter relating to said fault detection analysis and a detected fault, said controller to also adjust a weighting associated with said parameter based upon said relationship of said parameter to said detected fault.

35. The apparatus of claim 34, wherein said workpiece is a semiconductor wafer.

36. The apparatus of claim 34, wherein said controller further comprising a fault detection model for performing said fault detection analysis, said parameter being an input into said fault detection model.

37. The apparatus of claim 34, wherein said controller further comprising a principal component analysis (PCA) model for performing principal component analysis, said parameter being an input into said PCA model.

38. The apparatus of claim 34, said controller further comprising a dynamic PCA-weighting unit, said dynamic PCA-weighting unit comprising:

a fault data analysis module for determining whether said parameter was a significant factor in said detected fault;

a fault data input interface to receive an external data indicating whether said parameter was a significant factor in said detected fault; and

a dynamic PCA-weighting calculation module to dynamically modify said weighting of said parameter based upon at least one of said determination and said indication whether said parameter was a significant factor in said detected fault.

39. The apparatus of claim 38, wherein said controller to increase a weighting of said parameter in response to at least said indication and said determination that said parameter is a significant factor in said detected fault.

40. The apparatus of claim 38, wherein said controller to decrease a weighting of said parameter in response to at least said indication and said determination that said parameter is a significant factor in said detected fault.

41. A computer readable program storage device encoded with instructions that, when executed by a computer, performs a method, comprising:

processing a workpiece;

performing a fault detection analysis relating to said processing of said workpiece;

determining a relationship of a parameter relating to said fault detection analysis to a detected fault; and

adjusting a weighting associated with said parameter based upon said relationship of said parameter to said detected fault.

42. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 41, further comprising:

acquiring metrology data relating to processing said workpiece;

acquiring tool state data relating to processing said workpiece; and

correlating said metrology data and said tool state data with said fault data to characterize a fault.

43. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 42, wherein acquiring said tool state data relating to processing said workpiece further comprises acquiring at least one of a pressure data, a temperature data, humidity data, and a gas flow rate data associated with said processing of said workpiece.

44. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 41, wherein performing said fault detection analysis further comprises utilizing a fault detection model to perform said fault detection, wherein said parameter is an input parameter to said fault detection model.

45. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 42, further comprising determining a relationship of a parameter relating to said fault detection analysis to a detected fault further comprises determining a causation of a parameter relating to said fault detection analysis to a detected fault.

46. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 42, further comprising determining a relationship of a parameter relating to said fault detection analysis to a detected fault further comprises determining an importance of a parameter relating to said fault detection analysis to a detected fault.

47. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 41, wherein performing said fault detection analysis further comprises performing a principal component analysis (PCA) relating to said processing of said workpiece.

48. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 47, wherein performing said principal component analysis further comprises utilizing a PCA model to perform said PCA, wherein said parameter is an input parameter to said PCA model.

49. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 41, wherein determining said relationship of a parameter relating to said fault detection analysis to a detected fault further comprises determining whether said parameter is a significant factor associated with said fault.

50. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 41, wherein adjusting said weighting associated with said parameter based upon said relationship of said parameter to said detected fault further comprises increasing said weighting associated with said parameter based upon said relationship.

51. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 50, wherein increasing said weighting associated with said parameter based upon said relationship further comprises requiring a smaller fluctuation of said parameter during said fault detection analysis to determine that a fault associated with said processing of said workpiece has occurred.

52. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 41, wherein adjusting said weighting associated with said parameter based upon said relationship of said parameter to said detected fault further comprises decreasing said weighting associated with said parameter based upon said relationship.

53. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 52, wherein increasing said weighting associated with said parameter based upon said relationship further comprises requiring a larger fluctuation of said parameter during said fault detection analysis to determine that a fault associated with said processing of said workpiece has occurred.

54. The computer readable program storage device encoded with instructions that, when executed by a computer, performs the method of claim 41, wherein determining said relationship of a parameter relating to said fault detection analysis to said detected fault further comprises determining a relationship between at least one of a pressure data, a temperature data, a humidity data, and a gas flow rate data associated with said processing of said workpiece, to said detected fault.