Method and apparatus for self-learning and self-improving a semiconductor manufacturing tool

• US 8,744,607 B2
• Filed: 02/11/2013
• Issued: 06/03/2014
• 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): KASENGE, CHARLES R
• Application Number:
  US13/763,797
• Publication Number:
  US 20130151447A1
• Time in Patent Office: 477 Days
• Field of Search: 700/28, 700/47, 700/52, 700/100, 700/103, 700/104, 700/105, 700/108, 700/109, 700/110, 700/121, 702/81, 702/82, 702/83, 702/84, 702/182, 702/183, 702/184, 438/5, 438/14, 438/16, 438/17, 706/12, 706/13, 706/16, 706/23
• US Class Current: 700/104
• 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

Performance of a manufacturing tool is optimized. Optimization relies on recipe drifting and generation of knowledge that capture relationships among product output metrics and input material measurement(s) and recipe parameters. Optimized recipe parameters are extracted from a basis of learned functions that predict output metrics for a current state of the manufacturing tool and measurements of input material(s). Drifting and learning are related and lead to dynamic optimization of tool performance, which enables optimized output from the manufacturing tool as the operation conditions of the tool changes. Features of recipe drifting and associated learning can be autonomously or externally configured through suitable user interfaces, which also can be drifted to optimize end-user interaction.

Claims

1. A system, comprising:

a processor, coupled to a memory, comprising computer-executable components, comprising;

a drift component that modifies a manufacturing recipe processed by a manufacturing tool that produces an asset based at least in part on a set of driving variables and a defined probability distribution function to generate a modified manufacturing recipe for the asset, wherein the set of driving variables determine a sequence in which to modify a set of recipe parameters associated with the manufacturing recipe, and wherein a magnitude of change between the manufacturing recipe and the modified manufacturing recipe is determined based at least in part on the defined probability distribution function.

2. The system of claim 1, further comprising an objective autonomous learning engine that infers one or more functions for the manufacturing tool based on the modified manufacturing recipe processed by the manufacturing tool, wherein the one or more functions predict asset output metrics for the produced asset.

3. The system of claim 2, further comprising an autonomous optimization engine that extracts a set of updated recipe parameters from a set of input measurements and the one or more functions to generate an adjusted recipe within a predefined tolerance of a target value for the asset output metrics.

4. The system of claim 3, wherein, to infer the one or more functions, the objective autonomous learning engine relaxes one or more constraints for the asset output metrics.

5. The system of claim 4, wherein the relaxation of the one or more constraints is dictated at least in part by a ranking of weights for the asset output metrics.

6. A method, comprising:

determining, by a device comprising a processor, a sequence for modifying one or more parameters associated with an initial recipe; and

modifying the initial recipe to fabricate a product that is predicted to fulfill a target product output based at least in part on the sequence and a defined probability distribution function that determines a magnitude of the modifying of the initial recipe.

7. The method of claim 6, further comprising learning a set of relationships associated with product output based on the modifying of the initial recipe.

8. The method of claim 7, further comprising generating an adjusted recipe to accomplish the target product output based at least in part on the set of relationships.

9. The method of claim 8, further comprising evaluating whether the target product output is fulfilled in response to determining that generation of the adjusted recipe is successful.

10. The method of claim 9, further comprising continuing the modifying in response to determining that the evaluating indicates an unsuccessful outcome.

11. The method of claim 9, wherein the modifying includes:

setting the initial recipe as a current recipe;

randomizing the one or more parameters of the current recipe to generate an adjusted recipe;

initiating processing, via a manufacturing tool, of the adjusted recipe obtained in response to the randomizing;

in response to determining that the adjusted recipe is to be drifted, adding the adjusted recipe to a genealogy of recipes and setting the adjusted recipe as the current recipe; and

in response to determining that the adjusted recipe is not to be drifted, sending the genealogy of recipes and data associated with the genealogy of recipes to a database.

12. The method of claim 9, wherein the generating includes:

receiving the set of relationships that define predicted product outputs for a set of recipes;

receiving input material measurements;

extracting recipe parameters for the adjusted recipe based at least in part on a set of functions or the input material measurements; and

sending the adjusted recipe at least in part with the recipe parameters to a database in response to determining that the predicted product outputs of the set of relationships satisfy respective output constraints.

13. The method of claim 12, in response to determining that the predicted product outputs do not satisfy the respective output constraints, further comprising:

relaxing a set of the respective output constraints; and

extracting recipe parameters for the adjusted recipe based at least in part on the set of functions or the input material measurements in response to determining that a current number of relaxed constraints is below a defined threshold.

14. The method of claim 13, further comprising configuring a maintenance repair procedure in response to determining that the current number of relaxed constraints is below the defined threshold.

15. The method of claim 11, wherein the learning includes:

receiving production data generated through execution of one or more modified recipes;

learning a functional relationship among a product output metric, material input measurements, and recipe parameters of the manufacturing tool based on the production data; and

accepting the functional relationship in response to determining that predictions of the product output are within a specified quality.

16. The method of claim 12, wherein the extracting includes solving an inverse problem through at least one of genetic algorithm, Monte Carlo simulation, simulated annealing, or Tabu search.

17. The method of claim 15, wherein the accepting includes at least one of delivering the functional relationship or storing the functional relationship.

18. A non-transitory computer-readable medium comprising a set of code instruction retained therein that, in response to execution, cause a computing system including at least one processor to perform operations, comprising:

determining a sequence for modifying one or more parameters associated with an initial recipe; and

modifying the initial recipe to fabricate a product that fulfills a target product output based at least in part on the sequence and a defined probability distribution function that determines a degree of the modifying of the initial recipe.

19. The non-transitory computer-readable medium of claim 18, further comprising learning a set of relationships associated with product output through the modifying of the initial recipe.

20. The non-transitory computer-readable medium of claim 19, further comprising generating an adjusted recipe to accomplish the target product output based at least in part on the set of relationships.