Double Patterning Mask Correction Using ML Stitch Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The photolithography process in semiconductor manufacturing often results in defects such as disconnection, short-circuiting, and bridging due to the complexity of circuit patterns, which existing optical proximity correction (OPC) methods struggle to address effectively, especially as tracing density increases.
Innovation Solution
A mask correction method and device for double patterning that employs a layout machine learning model trained on target layouts and three-dimensional etching information to decompose patterns into sub-layouts, analyze stitch regions, and perform OPC procedures to ensure accurate etching quality, incorporating a device with an input unit, decomposition unit, layout machine learning model, and OPC unit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional optical proximity correction (OPC) methods are used, then the process is simple and easy to implement, but the etching quality deteriorates with increasing tracing density, resulting in defects such as disconnection, short-circuiting, and bridging
Solution Approach 1:
The patent divides the target layout into multiple sub-layouts that are processed separately through different masks and etching steps. This segmentation allows each sub-layout to be corrected and etched independently, improving overall etching quality while managing complexity through systematic division of the correction process
Solution Approach 2:
The patent transitions from traditional 2D OPC methods to 3D-aware correction by incorporating depth information and vertical profile considerations. The machine learning model analyzes three-dimensional etching results to determine stitch region sizes, adding a dimensional perspective that improves etching precision for high-density patterns
2Productivity
If the tracing density is increased to improve circuit integration, then the circuit functionality is enhanced, but the etching quality deteriorates due to defects such as disconnection, short-circuiting, and bridging
Solution Approach 1:
The patent performs preliminary analysis of the target layout to identify and define stitch regions before the actual etching process. The machine learning model predicts optimal stitch region sizes based on the layout characteristics, allowing preventive correction of potential etching defects before they occur in high-density circuits
Solution Approach 2:
The patent implements a feedback mechanism where the machine learning model is trained on three-dimensional etching results and uses this learned information to optimize stitch region settings for subsequent corrections. The system continuously improves etching quality by incorporating feedback from previous etching outcomes into the correction process
3Manufacturing precision
If the stitch region size is not accurately controlled, then the layout processing is simple, but the etching quality deteriorates with connection defects and metallic material thickness variations
Solution Approach 1:
The machine learning model performs self-service by automatically analyzing layout characteristics and determining optimal stitch region sizes without requiring manual intervention. The model uses the target layout as input and autonomously outputs corrected layouts with appropriately sized stitch regions, improving accuracy while managing complexity through automation
Data Source
AI summary
A mask correction method, a mask correction device for double patterning, and a training method for a layout machine learning model are provided. The mask correction method for double patterning includes the following steps. A target layout is obtained. The target layout is decomposed into two sub-layouts, which overlap at a stitch region. A size of the stitch region is analyzed by the layout machine learning model according to the target layout. The layout machine learning model is established according to a three-dimensional information after etching. An optical proximity correction (OPC) procedure is performed on the sub-layouts.