Substrate Furnace Temperature Prediction With Responsiveness Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing temperature prediction models for substrate processing apparatuses suffer from decreased accuracy due to differences among individual apparatuses and changes over time, requiring high setup costs and difficulty in model reconstruction, especially with complex process recipes.

Innovation Solution

A prediction apparatus that optimizes correction parameters based on a trained model and sensor data to account for the difference in temperature responsiveness between reference and target apparatuses, using Bayesian optimization to improve prediction accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a temperature prediction model is created for each individual substrate processing apparatus, then prediction accuracy is improved, but setup costs and device complexity increase

Engineering Contradiction:

Improvetemperature prediction accuracyVSAvoidmodel setup complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the temperature prediction problem into two parts: a base model that captures common thermal characteristics across all apparatuses, and apparatus-specific correction parameters that account for individual differences. This segmentation allows the system to maintain high prediction accuracy for each individual apparatus while avoiding the need to create entirely separate models, thereby reducing setup complexity and costs.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent uses parameter optimization to adjust correction parameters for each individual apparatus based on its specific thermal responsiveness characteristics. By changing only the correction parameters rather than the entire model structure, the system achieves apparatus-specific prediction accuracy while maintaining a unified base model framework, thus reducing overall system complexity.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If a temperature prediction model is recreated when apparatus characteristics change over time, then prediction accuracy is maintained, but time loss and operational disruption increase

Engineering Contradiction:

Improvetemperature prediction accuracyVSAvoidmodel reconstruction time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements a feedback mechanism where the system continuously monitors actual temperature measurements and compares them with predicted values. Based on this feedback, the correction parameters are automatically optimized and updated to reflect changes in apparatus characteristics over time. This allows the system to maintain prediction accuracy without requiring manual model recreation, thereby eliminating time loss and operational disruption.

Inventive Principle:

Principle #23Feedback

3Device complexity

If a universal temperature prediction model is used for all apparatuses, then device complexity is reduced, but prediction accuracy deteriorates due to apparatus-specific differences

Engineering Contradiction:

Improvemodel setup simplicityVSAvoidtemperature prediction accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent creates a universal base model that can be applied across all substrate processing apparatuses, capturing common thermal behavior patterns. This base model serves multiple apparatuses simultaneously, reducing overall system complexity. The model is enhanced with apparatus-specific correction parameters that can be optimized for each individual apparatus, allowing the universal model to adapt to apparatus-specific differences and maintain high prediction accuracy.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250329562A1Information processing apparatus, information processing method, and storage medium

Publication Date: 2025.10.23 TOKYO ELECTRON LTD

AI summary

An information processing apparatus includes: a model acquisition unit that acquires a trained model that predicts temperature inside a processing container included in a first substrate processing apparatus; a data acquisition unit that acquires sensor data indicating a sensor value obtained by measuring temperature inside a processing container included in a second substrate processing apparatus; an optimization unit that optimizes a parameter indicating a difference in temperature responsiveness between the first substrate processing apparatus and the second substrate processing apparatus based on the trained model and the sensor data; and a prediction unit that predicts the temperature inside the processing container included in the second substrate processing apparatus based on the trained model and the parameter.