Training method for machine learning-assisted optical proximity error correction
CN113614638BActive Publication Date: 2025-04-01ASML NETHERLANDS BV
Patent Information
- Application Number
- CN202080023323.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2019-03-21
- Filing Date
- 2020-03-05
- Publication Date
- 2025-04-01
- Estimated Expiration
- 2040-03-05
AI Technical Summary
Technical Problem
It is difficult for existing lithography devices to effectively correct the optical proximity effect, resulting in a reduced transfer accuracy of the pattern on the substrate and affecting the manufacturing quality of the device.
Method used
By determining the representative pattern, the optical proximity effect correction process is simulated, reference data is obtained, and machine learning models are trained to predict optical proximity effect corrections for the design layout.
Benefits of technology
The accuracy and efficiency of lithography equipment in optical proximity effect correction are improved, and the pattern transfer accuracy in device manufacturing is enhanced.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN113614638B_ABST
Abstract
Described herein is a method of determining representative patterns for training a machine learning model to predict optical proximity correction. The method includes: obtaining a design layout including a set of pattern groups, each pattern group including one or more subgroups; determining a set of representative patterns in the set of pattern groups, the representative patterns being subgroups whose instances appear in the set of pattern groups; obtaining reference optical proximity correction data associated with the set of representative patterns by simulating an optical proximity correction process using the set of representative patterns; and training a machine learning model to predict optical proximity correction for the design layout based on the set of representative patterns and the set of reference optical proximity correction data.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
System and method for creating a focus-exposure model of a lithography process
US20070031745A1
Method for identifying and using process window signature patterns for lithography process control
US20070050749A1
System and method for model-based sub-resolution assist feature generation
US20080301620A1
Multivariable solver for optical proximity correction
US20080309897A1
Method and system for lithography process-window-maximixing optical proximity correction
US20100162197A1