ADAPTIVE AND AUTOMATIC DETERMINATION OF SYSTEM PARAMETERS

• US 20140074258A1
• Filed: 11/15/2013
• Published: 03/13/2014
• Est. Priority Date: 11/18/2010
• Status: Active Grant

• Current Assignee: Taiwan Semiconductor Manufacturing Company Limited
• Original Assignee: Taiwan Semiconductor Manufacturing Company Limited
• Inventors: TSAI, Po-Feng, HO, Chia-Tong, WU, Sunny, WANG, Jo Fei, MOU, Jong-I
• Granted Patent: US 9,141,097 B2
• Time in Patent Office: Days
• US Class Current: 700/47
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 2219/32188 Teaching relation between controlling parameters and quality parameters
• CPC Class Codes: G05B 2219/32189 Compare between original solid model and measured manufactured object
• CPC Class Codes: G05B 2219/45031 Manufacturing semiconductor wafers
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
• CPC Class Codes: Y02P 90/80 Management or planning

Abstract

A method of automatically determining process parameters for processing equipment includes processing at least one first substrate in the processing equipment at a first time; and processing at least one second substrate in the processing equipment at a second time. The method includes collecting data on process monitors for the at least one first substrate; and the at least one second substrate. The method includes receiving the data by a multiple-input-multiple-output (MIMO) optimization system. The method includes revising a sensitivity matrix, by a MIMO optimizer, using the data and an adaptive-learning algorithm, wherein the adaptive-learning algorithm revises the sensitivity matrix based on a learning parameter which is related to a rate of change of the processing equipment over time. The method includes determining a set of process parameters for the processing equipment by the MIMO optimizer, wherein the MIMO optimizer uses the revised sensitivity matrix to determine the process parameters.

Claims

1. A method of automatically determining process parameters for processing equipment, said method comprising:

processing at least one first substrate in the processing equipment at a first time;

processing at least one second substrate in the processing equipment at a second time different from the first time;

collecting data on process monitors for the at least one first substrate after processing is completed;

collecting data on process monitors for the at least one second substrate after processing is completed;

receiving the collected data by a multiple-input-multiple-output (MIMO) optimization system;

revising a sensitivity matrix used, by a MIMO optimizer of the MIMO optimization system, using the collected data and an adaptive-learning algorithm, wherein the adaptive-learning algorithm revises the sensitivity matrix based on a learning parameter which is related to a rate of change of the processing equipment over time; and

determining a set of process parameters for the processing equipment by the MIMO optimizer, wherein the MIMO optimizer uses the revised sensitivity matrix to determine the process parameters.

2. The method of claim 1, wherein determining the set of process parameters further comprises accounting for user defined constraints.

3. The method of claim 2, wherein accounting for the user defined constraints comprises accounting for hard constraints, wherein the set of process parameters do not exceed the hard constraints.

4. The method of claim 2, wherein accounting for the user defined constraints comprises accounting for soft constraints, wherein the soft constraints comprise weighting coefficients for at least one process parameter of the set of process parameters.

5. The method of claim 2, further comprising relaxing the user defined constraints if the determined set of process parameter fail to satisfy process monitoring criteria.

6. The method of claim 1, further comprising determining a number of additional sets of process parameters different from the set of process parameters, wherein determining the number of additional process parameters is performed using the MIMO optimizer.

7. The method of claim 6, further comprising displaying the set of process parameters and at least one of the additional sets of process parameters.

8. The method of claim 6, further comprising:

selecting the set of process parameters or one of the at least one additional process parameters; and

releasing the processing equipment for production based on the selected process parameters.

9. A non-transitory computer-readable storage medium embodying instructions for causing, when executed by a processor, the processor to perform a method of automatically determining process parameters for processing equipment, said medium configured to store instructions for:

collecting data on process monitors for at least one first substrate processed in a processing equipment at a first time;

collecting data on process monitors for at least one second substrate processed in a processing equipment at a second time different from the first time;

receiving the collected data by a multiple-input-multiple-output (MIMO) optimization system;

revising a sensitivity matrix used by a MIMO optimizer of the MIMO optimization system using the collected data and an adaptive-learning algorithm, wherein the adaptive-learning algorithm revises the sensitivity matrix based on a learning parameter which is related to a rate of change of the processing equipment over time; and

determining a set of process parameters for the processing equipment by the MIMO optimizer, wherein the MIMO optimizer uses the revised sensitivity matrix to determine the process parameters.

10. The non-transitory computer-readable storage medium of claim 9, wherein determining the set of process parameters further comprises accounting for user defined constraints.

11. The non-transitory computer-readable storage medium of claim 10, wherein accounting for the user defined constraints comprises accounting for hard constraints, wherein the set of process parameters do not exceed the hard constraints.

12. The non-transitory computer-readable storage medium of claim 10, wherein accounting for the user defined constraints comprises accounting for soft constraints, wherein the soft constraints comprise weighting coefficients for at least one process parameter of the set of process parameters.

13. The non-transitory computer-readable storage medium of claim 10, wherein the non-transitory computer-readable storage medium further comprising instructions for relaxing the user defined constraints if the determined set of process parameter fail to satisfy process monitoring criteria.

14. The non-transitory computer-readable storage medium of claim 9, wherein the non-transitory computer-readable storage medium further comprising instructions for determining a number of additional sets of process parameters different from the set of process parameters, wherein determining the number of additional process parameters is performed using the MIMO optimizer.

15. The non-transitory computer-readable storage medium of claim 14, wherein the non-transitory computer-readable storage medium further comprising instructions for displaying the set of process parameters and at least one of the additional sets of process parameters.

16. The non-transitory computer-readable storage medium of claim 14, wherein the non-transitory computer-readable storage medium further comprising instructions for:

selecting the set of process parameters or one of the at least one additional process parameters; and

releasing the processing equipment for production based on the selected process parameters.

17. A system for determining process parameters for processing equipment, the system comprising:

a processor; and

a non-transitory computer-readable storage medium connected to the processor, the non-transitory computer-readable storage medium embodying instructions for;

collecting data on process monitors for at least one first substrate processed in a processing equipment at a first time;

collecting data on process monitors for at least one second substrate processed in a processing equipment at a second time different from the first time;

receiving the collected data by a multiple-input-multiple-output (MIMO) optimization system;

revising a sensitivity matrix used by a MIMO optimizer of the MIMO optimization system using the collected data and an adaptive-learning algorithm, wherein the adaptive-learning algorithm revises the sensitivity matrix based on a learning parameter which is related to a rate of change of the processing equipment over time; and

determining a set of process parameters for the processing equipment by the MIMO optimizer, wherein the MIMO optimizer uses the revised sensitivity matrix to determine the process parameters.

18. The system of claim 17, wherein the non-transitory computer-readable storage medium further comprising instructions for:

determining a number of additional sets of process parameters different from the set of process parameters, wherein determining the number of additional process parameters is performed using the MIMO optimizer;

selecting the set of process parameters or one of the at least one additional process parameters; and

releasing the processing equipment for production based on the selected process parameters.

19. The system of claim 17, wherein determining the set of process parameters further comprises accounting for user defined constraints.

20. The system of claim 19, wherein the non-transitory computer-readable storage medium further comprising instructions for relaxing the user defined constraints if the determined set of process parameter fail to satisfy process monitoring criteria.