Substrate Chemical Processing Using ML for Hardened Resist Removal

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for removing hardened layers in resist layers during substrate processing are inefficient, leading to either incomplete removal or increased costs due to excessive chemical liquid usage.

Innovation Solution

A substrate processing apparatus and method that utilizes a trained model to determine optimal chemical liquid processing conditions based on substrate information, including hardened layer thickness and ion implantation conditions, to accurately remove hardened layers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of substance

If an excessively small amount of chemical liquid is used for removing the hardened layer, then the cost is reduced, but the removal effectiveness becomes insufficient

Engineering Contradiction:
Improvechemical liquid consumptionVSAvoidhardened layer removal effectiveness
Core Design Contradiction:
Loss of substanceVSReliability

Solution Approach 1:

The patent applies parameter changes by adjusting the chemical liquid supply amount based on the hardened layer thickness. The control unit calculates the optimal supply amount using the formula: supply amount = hardened layer thickness × supply area × removal rate coefficient. This dynamic parameter adjustment ensures sufficient removal effectiveness while minimizing chemical liquid consumption, resolving the contradiction between cost reduction and removal effectiveness.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent implements feedback control by measuring the actual hardened layer thickness after ion implantation and using this information to adjust the chemical liquid supply amount. The system continuously monitors the relationship between ion implantation conditions, hardened layer formation, and chemical liquid consumption, creating a closed-loop control system that optimizes both removal effectiveness and chemical liquid usage efficiency.

Inventive Principle:
Principle #23Feedback

2Reliability

If an excessively large amount of chemical liquid is used for removing the hardened layer, then the removal effectiveness is improved, but the cost increases

Engineering Contradiction:
Improvehardened layer removal effectivenessVSAvoidchemical liquid consumption
Core Design Contradiction:
ReliabilityVSLoss of substance

Solution Approach 1:

The patent dynamically changes the chemical liquid supply parameter based on the actual hardened layer thickness measured after ion implantation. By calculating the precise supply amount needed (supply amount = hardened layer thickness × supply area × removal rate coefficient), the system achieves optimal removal effectiveness without excessive chemical liquid consumption, directly resolving the contradiction between improved removal and reduced cost.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent applies partial action by supplying only the necessary amount of chemical liquid required for effective hardened layer removal, rather than using an excessively large amount. The system calculates and supplies precisely the partial amount needed based on hardened layer characteristics, achieving sufficient removal effectiveness while minimizing chemical liquid consumption and cost.

Inventive Principle:
Principle #16Partial or excessive action

3Ease of operation

If a fixed amount of chemical liquid is used for all substrates, then the process is simple to operate, but the removal effectiveness varies with different substrate conditions

Engineering Contradiction:
Improveprocess operation simplicityVSAvoidhardened layer removal effectiveness
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent transforms the static fixed supply amount into a dynamic supply amount that automatically adjusts according to substrate conditions. The control unit calculates the chemical liquid supply amount based on real-time hardened layer thickness measurements and ion implantation parameters, enabling the system to adapt to different substrate conditions while maintaining consistent removal effectiveness. This dynamic adjustment is automated, preserving ease of operation.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the chemical liquid supply parameter from a fixed value to a variable value that depends on substrate-specific conditions such as hardened layer thickness and ion implantation dose. The control system automatically calculates and adjusts the supply amount for each substrate, ensuring optimal removal effectiveness across varying conditions while maintaining simple automated operation through formula-based calculation.

Inventive Principle:
Principle #35Parameter changes

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

The solution allows for precise and efficient removal of hardened layers, optimizing chemical liquid usage and reducing costs by adapting processing conditions based on substrate characteristics.

Implementation Method 1

a trained model determining chemical liquid processing condition information indicating a chemical liquid processing condition for the processing target substrate based on the substrate information of the processing target substrate

Methodology Applied
Scientific EffectMachine learning:

Implementation Method 2

a chemical liquid supply section configured to supply a chemical liquid to the processing target substrate; a controller configured to control the substrate holding section and the chemical liquid supply section to perform processing with a chemical liquid on the processing target substrate

Methodology Applied
Scientific EffectChemical etching:

Data Source

PatentEP4145492B1Substrate treatment device, substrate treatment method, method for generating learning data, learning method, learning device, method for generating learned model, and learned model
Publication Date: 2025.07.02 SCREEN HOLDINGS CO LTD
  • EP4145492B1 patent drawingFigure 1
  • EP4145492B1 patent drawingFigure 2
  • EP4145492B1 patent drawingFigure 3

AI summary

A substrate processing apparatus (100) includes a substrate holding section (120), a chemical liquid supply section (130), a substrate information acquiring section (22a), a chemical liquid processing condition information acquiring section (22b), and a controller (22). The substrate information acquiring section (22a) acquires substrate information including hardened layer thickness information indicating a thickness of a hardened layer in a resist layer of a processing target substrate or ion implantation condition information indicating a condition for ion implantation by which the hardened layer has been formed in the resist layer. The chemical liquid processing condition information acquiring section (22b) acquires based on the substrate information chemical liquid processing condition information indicating a chemical liquid processing condition for the processing target substrate from a trained model. The controller (22) controls the substrate holding section (120) and the chemical liquid supply section (130) to perform processing with a chemical liquid on the processing target substrate based on the chemical liquid processing condition information.