Semiconductor Process Recipe Control With Dynamic Feedback Tuning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current semiconductor manufacturing processes face inefficiencies in process recipe optimization due to time-consuming manual adjustments, high resource intensity, and discrepancies between model predictions and actual outcomes, leading to increased costs and variability in feature scale results.

Innovation Solution

A dynamic controller, such as a MIMO controller, is employed to refine process parameters based on real-time performance data, reducing the need for extensive manual tuning and iterative adjustments by using minimal training data to achieve target performance criteria.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual monitoring and adjusting of process parameters is performed, then process control quality is maintained, but time consumption and resource intensity increase

Engineering Contradiction:

Improveprocess control qualityVSAvoidtime consumption

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The dynamic controller automatically monitors process parameters and adjusts them based on real-time performance data without requiring manual intervention. The system self-regulates by comparing actual performance against target performance and autonomously modifying process parameters to maintain optimal conditions, thereby eliminating time-consuming manual adjustments while preserving control quality.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements continuous feedback loops where performance data from process runs is fed back to the dynamic controller, which then adjusts process parameters accordingly. This automated feedback mechanism replaces manual monitoring by continuously comparing actual performance with target performance and making real-time adjustments, reducing time consumption while maintaining precision.

Inventive Principle:

Principle #23Feedback

2Manufacturing precision

If extensive manual tuning and iterative adjustments are performed, then optimal process parameters are achieved, but resource consumption and time requirements increase

Engineering Contradiction:

Improveprocess parameter optimizationVSAvoidresource consumption

Core Design Contradiction:

Manufacturing precisionVSLoss of energy

Solution Approach 1:

The dynamic controller is pre-trained using minimal training data to learn the relationship between process parameters and performance outcomes. This preliminary training phase enables the controller to make accurate predictions and adjustments during actual production without requiring extensive iterative tuning, thereby reducing resource consumption while achieving optimal parameter settings.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual mechanical tuning processes with an automated dynamic control system that uses computational algorithms to adjust process parameters. This substitution eliminates the need for extensive human intervention and iterative adjustments, reducing resource consumption while maintaining or improving optimization quality.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If model predictions are used for process control, then initial setup time is reduced, but discrepancies between predictions and actual outcomes increase variability

Engineering Contradiction:

Improveprocess setup speedVSAvoidfeature scale accuracy

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The system transitions from static model predictions to dynamic adaptive control. The dynamic controller continuously adapts to actual process conditions by learning from real-time performance data and adjusting parameters dynamically. This dynamic approach maintains the speed advantage of model-based control while reducing variability through continuous adaptation to actual outcomes.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the nature of parameter control from fixed model-based predictions to adaptive parameter adjustments. The dynamic controller modifies process parameters based on real-time performance feedback, allowing the system to maintain rapid setup speeds while improving accuracy by continuously adjusting parameters to match actual process behavior rather than relying solely on predetermined models.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260016812A1Dynamic process control in electronic device manufacturing

Publication Date: 2026.01.15 APPLIED MATERIALS INC

AI summary

A method includes receiving a first data set for a first process run of a process recipe, the first data set comprising first process parameter values, first performance data and target performance data of the process recipe. The method further includes process the first data set using a dynamic controller to determine second process parameter values that differ from the first process parameter values for at least one process parameter. The method further includes receiving a second data set for a second process run of the process recipe, the second data set comprising the second process parameter values, second performance, and the target performance data of the process recipe. The method further includes, responsive to determining that the second performance data satisfies one or more criteria with respect to the target performance data, saving the second process parameter values as final process parameter values for the process recipe.