Machine-Learning Control of Polishing Pad Temperature in CMP

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing substrate polishing devices face challenges in accurately determining the control amount for temperature adjustment of the polishing pad during chemical mechanical polishing due to complex variations in device states, affecting processing quality.

Innovation Solution

An information processing device that utilizes a learning model trained through machine learning to generate polishing surface temperature control information based on measured temperature distribution and device state information, enabling precise adjustment of the polishing pad's temperature distribution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Temperature

If a temperature adjustment device is used to control the polishing pad temperature, then the temperature distribution can be maintained at target levels, but it becomes difficult to accurately determine the control amount due to complex variations in device states

Engineering Contradiction:

Improvepolishing pad temperature distributionVSAvoidcomplexity of control amount determination

Core Design Contradiction:

TemperatureVSDevice complexity

Solution Approach 1:

The system implements feedback control by measuring the actual temperature distribution on the polishing pad surface during polishing and using this information to adjust the heating/cooling device control amounts. The control section continuously monitors temperature changes and modifies control amounts based on the difference between actual and target temperature distributions, enabling accurate temperature control despite complex device state variations.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary analysis of the relationship between device states and temperature distributions before actual polishing operations. By pre-establishing the complex relationships between various device parameters and temperature outcomes, the system can quickly determine appropriate control amounts during polishing without needing to analyze all behaviors and factors in real-time, thus simplifying the control process.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If all device state behaviors and factors are analyzed to determine control amount, then accurate temperature control may be achieved, but the analysis complexity and time required increase significantly

Engineering Contradiction:

Improveaccuracy of control amount determinationVSAvoidtime for analyzing device states

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system extracts and utilizes only the essential device state information that has the most significant impact on temperature distribution, rather than analyzing all possible device behaviors and factors. By identifying and focusing on the key parameters that directly influence polishing pad temperature, the system achieves accurate control amount determination without the time-consuming analysis of every device state variable.

Inventive Principle:

Principle #2Taking out (Extraction)

3Manufacturing precision

If the polishing pad temperature distribution is not accurately controlled, then processing quality of substrates deteriorates, but implementing complex control mechanisms increases device complexity

Engineering Contradiction:

Improveprocessing quality of substrateVSAvoidcomplexity of temperature control system

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system enables the temperature control process to self-adjust by automatically measuring temperature distribution and determining appropriate control amounts based on the measured data and pre-established relationships. The control section autonomously modifies heating/cooling device settings without requiring complex external intervention or manual adjustment, achieving high processing quality through automated feedback control while keeping the overall system relatively simple.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20250303514A1Information processing device, substrate polishing device, inference device, machine learning device, information processing method, inference method, and machine learning method

Publication Date: 2025.10.02 EBARA CORP

AI summary

Provided is an information processing device including an information acquisition section that acquires substrate polishing information including measured temperature distribution information indicating a measured value of a temperature distribution of a polishing surface when a polishing process for polishing a substrate with the polishing surface of a polishing pad is performed by a substrate polishing device and device state information indicating a device state of the substrate polishing device, and an information generation section that inputs the substrate polishing information acquired by the information acquisition section into a learning model to generate polishing surface temperature control information indicating a control amount of a polishing surface temperature adjustment section when a polishing process is performed by the substrate polishing device. The learning model is a trained model that has learned a correlation between the substrate polishing information and the polishing surface temperature control information by machine learning.