Method and apparatus for monitoring tool health

• US 6,594,589 B1
• Filed: 05/23/2001
• Issued: 07/15/2003
• Est. Priority Date: 05/23/2001
• Status: Active Grant

• Current Assignee: Advanced Micro Devices, Inc.
• Original Assignee: Advanced Micro Devices, Inc.
• Inventors: Cowan, Patrick M., Coss, Jr., Elfido, Markle, Richard J.
• Primary Examiner(s): Bui, Bryan
• Assistant Examiner(s): BHAT, ADITYA S
• Application Number:
  US09/863,822
• Time in Patent Office: 783 Days
• Field of Search: 702/34, 702/36, 702/134, 702/179, 738/659, 340/680, 700/173, 318/565
• US Class Current: 702/34
• CPC Class Codes: G05B 19/4184 characterised by fault tolerance, reliability of production system
• CPC Class Codes: G05B 2219/31357 Observer based fault detection, use model
• CPC Class Codes: G05B 2219/45031 Manufacturing semiconductor wafers
• CPC Class Codes: Y02P 80/15 On-site combined power, heat or cool generation or distribution, e.g. combined heat and power [CHP] supply
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A method for monitoring health of a tool includes receiving at least one tool parameter related to the processing of a workpiece in a tool; receiving a model selection trigger; selecting a tool health model based on the model selection trigger; generating at least one predicted tool parameter based on the selected tool health model; and generating a tool health rating for the tool based on a comparison between the measured tool parameter and the predicted tool parameter. A tool health monitor includes a library of tool health models, a model selector, and a fault detection and classification unit. The model selector is adapted to receive a model selection trigger and select a tool health model based on the model selection trigger. The fault detection and classification unit is adapted to receive at least one tool parameter related to the processing of a workpiece in a tool, generate at least one predicted tool parameter based on the selected tool health model, and generate a tool health rating for the tool based on a comparison between the received tool parameter and the predicted tool parameter.

Claims

1. A method for monitoring health of a tool, comprising:

receiving at least one measured tool parameter related to the processing of a workpiece in a tool;

receiving a model selection trigger;

selecting a tool health model based on the model selection trigger;

generating at least one predicted tool parameter based on the selected tool health model and the measured tool parameter; and

generating a tool health rating for the tool based on a comparison between the measured tool parameter and the predicted tool parameter.

2. The method of claim 1, wherein receiving the model selection trigger further comprises receiving an external model selection trigger.

3. The method of claim 2, wherein receiving the external model selection trigger further comprises receiving a maintenance event trigger associated with the performance of a maintenance event on the tool.

4. The method of claim 2, wherein receiving the external model selection trigger further comprises receiving a control event trigger associated with an automatic change to an operating recipe parameter of the tool.

5. The method of claim 2, wherein receiving the external model selection trigger further comprises receiving an operator trigger.

6. The method of claim 2, wherein the tool includes an external sensor, and receiving the external model selection trigger further comprises receiving an external sensor trigger based on a measurement recorded by the external sensor.

7. The method of claim 1, wherein receiving the model selection trigger further comprises receiving an internal model selection trigger.

8. The method of claim 7, wherein receiving the internal model selection trigger further comprises receiving a model age trigger.

9. The method of claim 7, wherein receiving the internal model selection trigger further comprises receiving a workpiece count trigger associated with the number of workpieces processed in the tool.

10. The method of claim 7, wherein receiving the internal model selection trigger further comprises receiving a tool parameter trigger based on the value of the tool parameter.

11. The method of claim 7, wherein receiving the internal model selection trigger further comprises receiving a tool setup trigger.

12. The method of claim 1, further comprising identifying a degraded tool condition in response to the tool health rating being less than a predetermined threshold.

13. The method of claim 11, wherein the tool health model comprises a first tool health model, the tool health rating comprises a first tool health rating, and the method further comprises:

selecting a second tool health model in response to identifying the degraded tool condition; and

generating a second tool health rating based on the second tool health model and the measured tool parameter.

14. The method of claim 13, wherein selecting the second tool health model further comprises selecting the second tool health model having a higher precision than the first tool health model.

15. The method of claim 1, wherein selecting the tool health model further comprises selecting the tool health model from a library of tool health models.

16. The method of claim 15, wherein the tool is adapted to process the workpiece in accordance with a base operating recipe, and the library of tool health models is associated with the base operating recipe.

17. The method of claim 15, wherein the tool is adapted to process the workpiece in accordance with one of a plurality of base operating recipes, and the library of tool health models includes subsets of tool health models, each subset being associated with a particular one of the base operating recipes.

18. A manufacturing system, comprising:

a tool adapted to process a workpiece; and

a tool health monitor adapted to receive at least one tool parameter related to the processing of a workpiece in the tool, receive a model selection trigger, select a tool health model based on the model selection trigger, generate at least one predicted tool parameter based on the selected tool health model and the measured tool parameter, and generate a tool health rating for the tool based on a comparison between the received tool parameter and the predicted tool parameter.

19. The system of claim 18, wherein the model selection trigger comprises an external model selection trigger.

20. The system of claim 19, wherein the external model selection trigger comprises a maintenance event trigger associated with the performance of a maintenance event on the tool.

21. The system of claim 19, wherein the external model selection trigger comprises control event trigger associated with an automatic change to an operating recipe parameter of the tool.

22. The system of claim 19, wherein the external model selection trigger comprises an operator trigger.

23. The system of claim 19, wherein the tool includes an external sensor, and the external model selection trigger comprises an external sensor trigger based on a measurement recorded by the external sensor.

24. The system of claim 18, wherein the model selection trigger comprises an internal model selection trigger.

25. The system of claim 24, wherein the internal model selection trigger comprises a model age trigger.

26. The system of claim 24, wherein the internal model selection trigger comprises a workpiece count trigger associated with the number of workpieces processed in the tool.

27. The system of claim 24, wherein the internal model selection trigger comprises a tool parameter trigger based on the value of the tool parameter.

28. The system of claim 24, wherein the internal model selection trigger comprises a tool setup trigger.

29. The system of claim 18, wherein the tool health monitor is further adapted to identify a degraded tool condition in response to the tool health rating being less than a predetermined threshold.

30. The system of claim 28, wherein the tool health model comprises a first tool health model, the tool health rating comprises a first tool health rating, and the tool health monitor is further adapted to select a second tool health model in response to identifying the degraded tool condition and generate a second tool health rating based on the second tool health model and the measured tool parameter.

31. The system of claim 30, wherein the second tool health model has a higher precision than the first tool health model.

32. The system of claim 28, further comprising a library of tool health models, wherein the tool health monitor is adapted to select the tool health model from the library.

33. The system of claim 32, wherein the tool is adapted to process the workpiece in accordance with a base operating recipe, and the library of tool health models is associated with the base operating recipe.

34. The system of claim 32, wherein the tool is adapted to process the workpiece in accordance with one of a plurality of base operating recipes, and the library of tool health models includes subsets of tool health models, each subset being associated with a particular one of the base operating recipes.

35. A tool health monitor, comprising:

a library of tool health models;

a model selector adapted to receive a model selection trigger and select at least one of the tool health models based on the model selection trigger; and

a fault detection and classification unit adapted to receive at least one tool parameter related to the processing of a workpiece in a tool, generate at least one predicted tool parameter based on the selected tool health model and the received tool parameter, and generate a tool health rating for the tool based on a comparison between the received tool parameter and the predicted tool parameter.

36. The tool health monitor of claim 35, wherein the model selection trigger comprises an external model selection trigger.

37. The tool health monitor of claim 36, wherein the external model selection trigger comprises a maintenance event trigger associated with the performance of a maintenance event on the tool.

38. The tool health monitor of claim 36, wherein the external model selection trigger comprises control event trigger associated with an automatic change to an operating recipe parameter of the tool.

39. The tool health monitor of claim 36, wherein the external model selection trigger comprises an operator trigger.

40. The tool health monitor of claim 36, wherein the tool includes an external sensor, and the external model selection trigger comprises an external sensor trigger based on a measurement recorded by the external sensor.

41. The tool health monitor of claim 35, wherein the model selection trigger comprises an internal model selection trigger.

42. The tool health monitor of claim 41, wherein the internal model selection trigger comprises a model age trigger.

43. The tool health monitor of claim 41, wherein the internal model selection trigger comprises a workpiece count trigger associated with the number of workpieces processed in the tool.

44. The tool health monitor of claim 41, wherein the internal model selection trigger comprises a tool parameter trigger based on the value of the tool parameter.

45. The tool health monitor of claim 41, wherein the internal model selection trigger comprises a tool setup trigger.

46. The tool health monitor of claim 35, wherein the fault detection and classification unit is further adapted to identify a degraded tool condition in response to the tool health rating being less than a predetermined threshold.

47. The tool health monitor of claim 35, wherein the tool health model comprises a first tool health model, the tool health rating comprises a first tool health rating, the model selector is further adapted to select a second tool health model in response to identifying the degraded tool condition, and the fault detection and classification unit is further adapted to generate a second tool health rating based on the second tool health model and the received tool parameter.

48. The tool health monitor of claim 47, wherein the second tool health model has a higher precision than the first tool health model.

49. The tool health monitor of claim 35, wherein the tool is adapted to process the workpiece in accordance with a base operating recipe, and the library of tool health models is associated with the base operating recipe.

50. The tool health monitor of claim 35, wherein the tool is adapted to process the workpiece in accordance with one of a plurality of base operating recipes, and the library of tool health models includes subsets of tool health models, each subset being associated with a particular one of the base operating recipes.

51. A manufacturing system, comprising:

means for receiving at least one tool parameter related to the processing of a workpiece in a tool;

means for receiving a model selection trigger;

means for selecting a tool health model based on the model selection trigger and the received tool parameter;

means for generating at least one predicted tool parameter based on the selected tool health model; and

means for generating a tool health rating for the tool based on a comparison between the measured tool parameter and the predicted tool parameter.