Automated Semiconductor Recipe Generation via Periodic Stitch Aggregation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional manual or semi-manual recipe generation processes in semiconductor manufacturing are inefficient and prone to errors due to the complexity of measurements and recipes, particularly in inspection, metrology, and review processes, which require increased precision and effectiveness.

Innovation Solution

A method and system for automated recipe creation using design data to identify repetitive areas in the design data, enabling decision-making for die-to-die or cell-to-cell inspection without relying on data from a produced wafer, by generating candidate stitches and aggregating them into periodical arrays for automated recipe creation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual or semi-manual recipe generation processes are used, then flexibility and adaptability are maintained, but processing time and resource consumption increase significantly

Engineering Contradiction:

Improverecipe generation speedVSAvoidprocessing time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of design data to identify repetitive areas and generate candidate stitches before actual recipe creation. By pre-processing design data and identifying periodic patterns in advance, the system eliminates the need for time-consuming manual analysis during recipe generation, thus resolving the contradiction between maintaining flexibility and reducing processing time

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of repetitive areas identified in design data and uses these copies to generate standardized recipe patterns. By copying and reusing identified patterns across repetitive regions, the system automatically generates recipes much faster than manual processes while maintaining consistency and accuracy

Inventive Principle:

Principle #26Copying

2Productivity

If automated recipe generation is implemented, then processing time is reduced, but reliability may be compromised due to complexity of algorithms

Engineering Contradiction:

Improverecipe generation efficiencyVSAvoidrecipe accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms where generated recipes are validated against design data criteria and periodicity requirements. The algorithm continuously refines candidate stitches based on feedback from periodicity analysis, ensuring that generated recipes meet specified accuracy standards while maintaining automated efficiency

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The automated recipe generation process is segmented into distinct modules: design data analysis, repetitive area identification, candidate stitch generation, periodicity verification, and recipe compilation. This segmentation allows each module to be independently validated and tested, improving overall system reliability while maintaining automation benefits

Inventive Principle:

Principle #1Segmentation

3Reliability

If design data analysis is used instead of produced wafer data, then processing time is reduced and reliability is enhanced, but the complexity of data processing increases

Engineering Contradiction:

Improverecipe creation reliabilityVSAvoiddata processing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system extracts only the essential periodicity information and repetitive pattern characteristics from design data, separating these critical features from the complete design dataset. By extracting and focusing only on relevant periodicity attributes, the system reduces processing complexity while maintaining high reliability in recipe generation

Inventive Principle:

Principle #2Taking out (Extraction)

4Loss of time

If manual recipe generation is used, then error chances are reduced due to human oversight, but production time and development time increase

Engineering Contradiction:

Improvedevelopment timeVSAvoidoperational simplicity

Core Design Contradiction:

Loss of timeVSEase of operation

Solution Approach 1:

The system performs self-validation of generated recipes against design data criteria and periodicity requirements without requiring manual oversight. The automated system independently verifies recipe accuracy and makes necessary adjustments, eliminating the need for time-consuming manual review while maintaining high operational simplicity through standardized processes

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS8640060B2Method of generating a recipe for a manufacturing tool and system thereof

Publication Date: 2014.01.28 APPL MATERIALS ISRAEL LTD

AI summary

There is provided a computer-implemented method of creating a recipe for a manufacturing tool and a system thereof. The method comprises: upon obtaining data characterizing periodical sub-arrays in one or more dies, generating candidate stitches; identifying one or more candidate stitches characterized by periodicity characteristics satisfying, at least, a periodicity criterion, thereby identifying periodical stitches among the candidate stitches; and aggregating the identified periodical stitches and the periodical sub-arrays into periodical arrays, said periodical arrays to be used for automated recipe creation.