Run-to-Run Tool Control for Faster Equipment Requalification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current manufacturing processes face inefficiencies in equipment recovery time, particularly in mean-time-to-repair (MTTR), due to iterative and often manual tuning processes that are univariate and time-consuming, leading to prolonged downtime and reduced productivity.

Innovation Solution

Implementing multivariate run-to-run (R2R) control modeling and virtual metrology (VM) predictive algorithms to analyze tool parameter settings and metrology data, enabling precise adjustments and reducing the number of tuning iterations required to return equipment to a production-ready state.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If iterative manual tuning processes are used to requalify equipment after maintenance, then equipment can be returned to production, but the process is time-consuming and increases mean-time-to-repair (MTTR)

Engineering Contradiction:

Improveequipment requalificationVSAvoidmean-time-to-repair (MTTR)

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by collecting and analyzing process data during normal operation to build predictive models. Before maintenance occurs, the system has already gathered relevant data patterns and relationships, enabling faster post-maintenance requalification without requiring extensive iterative tuning.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual mechanical tuning processes with automated computational systems. Multivariate statistical models and machine learning algorithms automatically analyze process data and determine optimal parameter settings, substituting the manual iterative adjustment process with an automated computational approach that reduces time and labor.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of manufacture

If univariate adhoc parameter tuning is performed during equipment requalification, then some parameters can be adjusted, but the approach is inefficient and does not optimize all parameters simultaneously

Engineering Contradiction:

Improveparameter adjustment processVSAvoidequipment recovery speed

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent merges multiple univariate parameter adjustments into a single multivariate optimization process. By analyzing correlations between multiple parameters simultaneously and applying coordinated adjustments across all parameters based on comprehensive data analysis, the system achieves faster convergence to optimal settings compared to sequential single-parameter tuning.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system employs multivariate statistical models that analyze relationships between multiple process parameters simultaneously. This enables coordinated parameter changes that account for interdependencies between variables, allowing the system to optimize multiple parameters in a unified manner rather than adjusting them independently and sequentially.

Inventive Principle:

Principle #35Parameter changes

3Manufacturing precision

If multiple tuning iterations are conducted to achieve production-ready state, then equipment quality criteria can be met, but the number of iterations increases downtime

Engineering Contradiction:

Improvequality criteria complianceVSAvoidgreen-to-green (G2G) time

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system implements feedback mechanisms that continuously monitor process data during and after maintenance. By comparing actual process outcomes against predicted outcomes from multivariate models, the system can make real-time adjustments and determine when quality criteria are met, reducing the number of iterative cycles needed compared to methods without systematic feedback.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary data collection and model building during normal operation before maintenance occurs. This preliminary preparation includes gathering process data, establishing parameter relationships, and training predictive models, so that when maintenance is completed, the system can quickly determine optimal parameters with fewer iterations rather than starting from scratch.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11022968B2Methods and systems for applying run-to-run control and virtual metrology to reduce equipment recovery time

Publication Date: 2021.06.01 APPLIED MATERIALS INC

AI summary

Described herein are methods, apparatuses, and systems for reducing equipment repair time. Disclosed methods include collecting data including test substrate data or other metrology data and fault detection data for maintenance recovery of at least one manufacturing tool in a manufacturing facility. Disclosed methods include determining a relationship between tool parameter settings for the at least one manufacturing tool and at least some collected data including the test substrate data. The disclosure includes utilizing virtual metrology predictive algorithms and at least some collected data to obtain a metrology prediction and applying multivariate run-to-run (R2R) control modeling to obtain a tool parameter adjustment for at least one target parameter for the at least one manufacturing tool. The disclosure further includes applying the R2R control modeling to obtain tool parameter adjustments for at least one manufacturing tool.