Autonomous adaptive system and method for improving semiconductor manufacturing quality

• US 8,078,552 B2
• Filed: 03/08/2008
• Issued: 12/13/2011
• Est. Priority Date: 03/08/2008
• Status: Active Grant

• Current Assignee: Tokyo Electron Limited
• Original Assignee: Tokyo Electron Limited
• Inventors: Kaushal, Sanjeev, Patel, Sukesh Janubhai, Sugishima, Kenji
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): CHANG, LI WU
• Application Number:
  US12/044,959
• Publication Number:
  US 20090228408A1
• Time in Patent Office: 1,375 Days
• Field of Search: 706/12
• US Class Current: 706/12
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

An autonomous biologically based learning tool system and a method that the tool system employs for learning and analysis are provided. The autonomous biologically based learning tool system includes (a) one or more tool systems that perform a set of specific tasks or processes and generate assets and data related to the assets that characterize the various processes and associated tool performance; (b) an interaction manager that receives and formats the data, and (c) an autonomous learning system based on biological principles of learning. The autonomous learning system comprises a memory platform and a processing platform that communicate through a network. The network receives data from the tool system and from an external actor through the interaction manager. Both the memory platform and the processing platform include functional components and memories that can be defined recursively. Similarly, the one or more tools can be deployed recursively, in a bottom-up manner in which an individual autonomous tools is assembled in conjunction with other (disparate or alike) autonomous tools to form an autonomous group tool, which in turn can be assembled with other group tools to form a conglomerated autonomous tool system. Knowledge generated and accumulated in the autonomous learning system(s) associated with individual, group and conglomerated tools can be cast into semantic networks that can be employed for learning and driving tool goals based on context.

Claims

1. A semiconductor tool system, comprising:

a processor;

a computer-readable storage medium communicatively coupled to the processor and storing computer executable components comprising;

a learning system configured to;

receive data that pertains to a set of tools utilized to fabricate a product; and

backward chain through the data to rank at least one tool in the set of tools in accord with degradation of the product to generate knowledge to facilitate an increase in product yield.

2. The system of claim 1, wherein the knowledge generated comprises a mean time between failures of the at least one tool in the set of tools.

3. The system of claim 1, wherein the knowledge generated comprises a mean time to repair the at least one tool in the set of tools.

4. The system of claim 1, wherein the knowledge further comprises a prediction of failure of at least one part comprising the at least one tool.

5. The system of claim 4, wherein the learning system is further configured to utilize an expected time to failure of the at least one part comprising the at least one tool to optimize a parts inventory pertaining to the at least one part comprising the at least one tool.

6. The system of claim 1, wherein the optimized fabrication of the product the knowledge further comprises learning to predict a prediction of a set of factors for ramp up associated with an increase in rate of performance which affect product fabrication.

7. The system of claim 6, further comprising optimizing wherein the prediction facilitates selection of the set of factors associated with an increase in rate of performance.

8. The system of claim 1, wherein the set of tools are associated with a product asset, the product asset comprises a recipe for at least a portion of a process associated with fabrication of the product.

9. The system of claim 1, wherein the set of tools are associated with a product asset, the product asset comprises a set of observed data associated with measurements conducted on the product.

10. The system of claim 9, wherein the observed data includes at least one of an index of refraction, an absorption coefficient, or a critical dimension.

11. The system of claim 9, wherein the product asset further comprises a set of metrics computed from the observed data.

12. The system of claim 11, wherein the set of computed metrics includes at least one of a mean value, a standard deviation value, or a uniformity value.

13. The system of claim 1, wherein the set of tools are associated with a product asset, the product asset comprises at least a partially processed solid state semiconductor material.

19. The system of claim 1, further comprising an autonomous learning system associated with the at least one tool in the set of tools.

20. The system of claim 19, wherein the autonomous learning system comprises a memory platform configured to store operation knowledge pertaining to operation of the at least one tool, wherein the memory platform includes a hierarchy of memories.

21. The system of claim 20, wherein the hierarchy of memories includes at least one of a long term memory, a short term memory, or an episodic memory.

22. The system of claim 20, wherein the autonomous learning system further comprises a platform configured to process the data, wherein the platform includes a set of functional units configured to operate on the data.

23. The system of claim 22, further comprising a knowledge network configured to facilitate communication among the hierarchy of memories in the memory platform, the set of functional units in the platform that, or a combination thereof.

24. The system of claim 22, wherein the set of functional units includes a memory platform and a platform that processes data.

25. The system of claim 22, wherein the set of functional units includes at least one unit configured to identify a degradation condition for the at least one tool in the set of tools.

26. The system of claim 25, wherein the degradation condition pertains to at least one difference between a set of features in a first fabrication process and a second fabrication process.

27. The system of claim 25, wherein the degradation condition includes a numeric value, the numeric value assesses a distance amongst two vectors of N tuples, wherein the N tuples are computed metrics of observed data and N is a positive integer.

28. The system of claim 27, wherein the numeric value is a Euclidean distance.

29. The system of claim 27, wherein the numeric value includes a cosine similarity metric.

14. A method comprising:

receiving data pertaining to quality of a product, wherein the data is further associated with a plurality of tools involved in fabricating the product;

identifying, by backward chaining through the data, degradation in the quality of the product; and

ranking at least one tool, in the plurality of tools, regarding an effect of the at least one tool on the quality of the product.

15. The method of claim 14, further comprising monitoring the data facilitating determining of the effect of the at least one tool on a future quality of the product.

16. The method of claim 14, further comprising encrypting the data.

17. The method of claim 14, further comprising scheduling a distribution time for the data.

18. A computer-readable storage medium having computer executable instructions stored thereon that, in response to execution by a processor, cause the processor to perform operations for semiconductor processing, the operations comprising:

receiving data pertaining to quality of a product, wherein the data is further associated with a plurality of tools involved in fabricating the product; and

generating a knowledge facilitating an increase in product yield, wherein the generating further comprises;

identifying, by backward chaining through the data, degradation in quality of the product; and

ranking at least one tool, in the plurality of tools, regarding an effect of the at least one tool on the quality of the product.

30. A semiconductor tool system, comprising:

a processor;

a computer-readable storage medium communicatively coupled to the processor and storing computer executable components comprising;

a learning system configured to;

receive data that pertains to a set of tools utilized to fabricate a product; and

backward chain, in the event of degradation in the quality of the product, through the data to rank at least one tool in the set of tools to generate knowledge to facilitate an increase in efficiency of the semiconductor tool system.