IP Library Granted Patent US 12675085
Granted Patent B2
US 12675085 · App. 17/910,086 · Granted Jul 7, 2026

Method and apparatus for predicting a process metric associated with a process

Inventor: Arnaud Hubaux (Erpent, BE)
Assignee: ASML NETHERLANDS B.V.
G05B13/048G05B13/0265H10P74/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12675085
App. No.
17/910,086
Granted
Jul 7, 2026
Kind
B2
Abstract

A method including: obtaining one or more models configured for predicting a process metric of a manufacturing process based on inputting process data; and using a reinforcement learning framework to evaluate the one or more models and/or model configurations of the one more models based on inputting new process data to the one or more models and determining a performance indication of the one or more models and/or model configurations in predicting the process metric based on inputting the new process data.

Claims (25)

1 . A method comprising:

obtaining one or more models configured for predicting a process metric of a manufacturing process based on inputting process data, the process data comprising one or more Key Performance Indicators (KPIs) associated with a plurality of functional modules involved in the manufacturing process; and

using, by a hardware computer system, a reinforcement learning framework to evaluate the one or more models and/or model configurations of the one more models based on inputting new process data to the one or more models and determining an indication of a performance of the one or more models and/or model configurations in predicting the process metric based on inputting the new process data.

2 . The method of claim 1 , wherein the process metric is associated with a yield or quality parameter of the manufacturing process.

3 . The method of claim 1 , wherein the configuration comprises one or more selected from: a model type, model parameters and/or model hyperparameters.

4 . The method of claim 1 , wherein the process data and new process data comprise features of the manufacturing process.

5 . The method of claim 1 , wherein the manufacturing process is a process of patterning semiconductor wafers.

6 . The method of claim 1 , wherein the performance in predicting the process metric is based on comparing the predicted process metric and an otherwise obtained value of the process metric.

7 . The method of claim 1 , further comprising selecting a model and/or model configuration based on the evaluation.

8 . The method of claim 7 , wherein the process metric is indicative of the quality of a substrate being subject to a patterning process.

9 . The method of claim 1 , wherein the one or more models comprise at least two machine learning based models, each model being of a different architecture.

10 . The method of claim 9 , wherein the one or more models comprise at least a first model based on supervised learning and a second model based on unsupervised learning.

11 . A semiconductor manufacturing apparatus comprising a computer processor and a storage medium comprising instructions operable to execute the method of claim 1 .

12 . A computer program product comprising a non-transitory computer-readable storage medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:

obtain one or more models configured for predicting a process metric of a manufacturing process based on inputting process data, the process data comprising one or more Key Performance Indicators (KPIs) associated with a plurality of functional modules involved in the manufacturing process; and

use a reinforcement learning framework to evaluate the one or more models and/or model configurations of the one more models based on inputting new process data to the one or more models and determine an indication of a performance of the one or more models and/or model configurations in predicting the process metric based on inputting the new process data.

13 . The computer program product of claim 12 , wherein the process metric is associated with a yield or quality parameter of the manufacturing process.

14 . The computer program product of claim 12 , wherein the configuration comprises one or more selected from: a model type, model parameters and/or model hyperparameters.

15 . The computer program product of claim 12 , wherein the process data and new process data comprise features of the manufacturing process.

16 . The computer program product of claim 12 , wherein the performance in predicting the process metric is based on comparison of the predicted process metric and an otherwise obtained value of the process metric.

17 . The computer program product of claim 12 , wherein the one or more models comprise at least two machine learning based models, each model being of a different architecture.

18 . A computer program product comprising a non-transitory computer-readable storage medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:

obtain one or more models configured for predicting a process metric of a manufacturing process based on inputting process data, wherein the process metric is indicative of the quality of a substrate being subject to a patterning process;

use a reinforcement learning framework to evaluate the one or more models and/or model configurations of the one more models based on inputting new process data to the one or more models and determine an indication of a performance of the one or more models and/or model configurations in predicting the process metric based on inputting the new process data;

select a model and/or model configuration based on the evaluation.