Substrate Processing EMI Prediction From AC Current Signals

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing substrate processing devices face challenges in accurately predicting the effect of electromagnetic waves generated from AC power lines during substrate processing, which can interfere with normal operations.

Innovation Solution

An information processing device that includes a current value information generation unit and an electromagnetic effect information generation unit to predict the impact of electromagnetic waves based on current values, using machine learning models to analyze data from substrate processing devices connected to AC power sources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If AC current is supplied to AC devices during substrate processing, then the devices can operate normally, but electromagnetic waves are generated that may interfere with substrate processing operations

Engineering Contradiction:

Improvedevice operationVSAvoidelectromagnetic wave interference

Core Design Contradiction:

Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary actions by generating current value information and electromagnetic effect information before substrate processing begins. Machine learning models predict electromagnetic wave effects in advance, allowing the system to prepare mitigation strategies or warnings before the actual processing starts, thus preventing interference issues rather than reacting to them.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an information processing device as an intermediary between the AC power supply system and the substrate processing system. This intermediary generates and provides electromagnetic effect information based on current values, serving as a mediator that translates electrical parameters into predictive information about potential interference, enabling better coordination and mitigation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If electromagnetic wave effects are predicted using traditional measurement methods, then the prediction can be obtained, but the accuracy and appropriateness of the prediction is insufficient

Engineering Contradiction:

Improveelectromagnetic effect prediction accuracyVSAvoidprediction reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent replaces traditional mechanical or empirical measurement methods with machine learning-based prediction systems. By using trained models that analyze current value information and generate electromagnetic effect information, the system achieves higher accuracy and reliability without relying on physical measurements or simplified assumptions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the approach from direct measurement to predictive modeling by transforming current value parameters into electromagnetic effect parameters through machine learning. This parameter transformation enables more accurate predictions by capturing complex relationships that traditional measurement methods cannot detect.

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

Enables accurate prediction of electromagnetic wave effects, allowing for better management and minimization of interference in substrate processing systems.

Implementation Method 1

electromagnetic waves are generated from the AC power line through which the AC current flows

Methodology Applied

Scientific EffectElectromagnetic wave generation: Electromagnetic Induction

Data Source

PatentUS20260093304A1Information processing device, machine learning device, information processing method, and machine learning method

Publication Date: 2026.04.02 EBARA CORP

AI summary

Provided is an information processing device 5 including a current value information generation unit that generates current value information of an AC current supplied to an AC device when substrate processing is performed by a substrate processing device including the AC device connected to an AC power source via an AC power line, and a control panel that controls the AC device to perform the substrate processing by supplying a processing fluid to a substrate or a processing member while bringing the processing member into contact with the substrate, and an electromagnetic effect information generation unit that generates electromagnetic effect information indicating an effect of electromagnetic waves generated from the AC power line based on the current value information generated by the current value information generation unit.