AI End-Pointing for Charged Particle Sample Preparation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current automated processes for preparing samples for charged particle microscopy, such as lamella formation, are hindered by variations in circuit structure shapes and layouts, making it difficult to reliably determine processing end points, thus requiring skilled technicians and limiting automation.

Innovation Solution

The implementation of artificial intelligence-enabled systems, specifically using trained artificial neural networks, to analyze images and provide feedback for controlling charged particle microscopes, allowing for the determination of processing end points and automation of lamella preparation processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If conventional pattern recognition is used for automated sample preparation, then automation is achieved, but reliability deteriorates due to variations in circuit structure shapes and layouts

Engineering Contradiction:

Improveautomation of sample preparationVSAvoidreliability of end point determination

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The patent transforms the image analysis approach from conventional pattern recognition to artificial intelligence-based analysis. This parameter change in the analytical method enables the system to handle variations in circuit structure shapes and layouts effectively, achieving both high automation and reliability in end point determination during sample preparation

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces conventional pattern recognition mechanisms with artificial intelligence-based image analysis. This substitution enables more robust automated control of sample preparation processes, particularly in determining when to stop material removal to preserve features of interest while achieving complete removal of unwanted portions

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If highly skilled technicians are used for manual sample preparation, then reliability is improved, but productivity deteriorates due to time-consuming manual operations

Engineering Contradiction:

Improveaccuracy of end point determinationVSAvoidspeed of sample preparation

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent implements an automated system that performs sample preparation end point determination independently without requiring highly skilled technicians. The artificial intelligence-based image analysis system autonomously analyzes images, determines when features of interest are exposed, and controls the material removal process, thereby maintaining high accuracy while dramatically increasing throughput and productivity

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent incorporates real-time feedback through continuous image acquisition and AI-based analysis during the sample preparation process. The system monitors the exposure of features of interest and automatically adjusts or terminates material removal based on the analyzed images, enabling accurate end point detection without manual intervention and maintaining high productivity

Inventive Principle:

Principle #23Feedback

3Measurement precision

If additional processing steps are added to ensure feature visibility, then measurement precision is improved, but device complexity worsens

Engineering Contradiction:

Improvevisibility of circuit structuresVSAvoidcomplexity of sample preparation process

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a multi-functional system where the charged particle microscope performs both material removal (via focused ion beam) and image analysis (via imaging column) within a single integrated platform. The artificial intelligence-based control system coordinates these functions, enabling the system to automatically determine end points and adjust processing parameters, thereby achieving high measurement precision without proportionally increasing device complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enables full automation of lamella preparation, reduces the need for highly skilled technicians, and increases the speed and accuracy of evaluating features in samples, improving the efficiency of industries that rely on charged particle microscopy.

Implementation Method 1

a focused ion beam to mill the surface of the sample

Methodology Applied

Scientific EffectFocused ion beam: Ion Beam

Implementation Method 2

milling, by the focused ion beam, the surface of the sample to remove a layer of material

Methodology Applied

Scientific EffectSputtering: Sputtering

Data Source

PatentUS11847813B2Artificial intelligence-enabled preparation end-pointing

Publication Date: 2023.12.19 FEI CO

AI summary

Methods and systems for implementing artificial intelligence enabled preparation end-pointing are disclosed. An example method at least includes obtaining an image of a surface of a sample, the sample including a plurality of features, analyzing the image to determine whether an end point has been reached, the end point based on a feature of interest out of the plurality of features observable in the image, and based on the end point not being reached, removing a layer of material from the surface of the sample.