Run-to-Run Control and Virtual Metrology for Faster Tool Requalification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current manufacturing processes face lengthy and iterative equipment requalification procedures after maintenance, contributing to high mean-time-to-repair (MTTR) and green-to-green (G2G) time, which are often manual and univariate in nature, leading to inefficiencies and increased downtime.
Innovation Solution
Implementing multivariate run-to-run (R2R) control modeling and virtual metrology (VM) predictive algorithms to collect and analyze data from manufacturing tools, determining relationships between tool parameter settings and substrate data, and applying adjustments to reduce the number of tuning iterations and improve equipment recovery times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual univariate tuning iterations are used for equipment requalification, then equipment can be requalified to a certain state, but the process is lengthy and increases mean-time-to-repair (MTTR)
Solution Approach 1:
The patent replaces manual mechanical tuning processes with automated multivariate control systems. The multivariate R2R control system automatically adjusts multiple process parameters simultaneously based on statistical models, eliminating the need for manual iterative tuning and significantly reducing requalification time while maintaining equipment reliability.
Solution Approach 2:
The system changes from univariate to multivariate parameter control. Instead of adjusting one parameter at a time through manual iteration, the system simultaneously optimizes multiple parameters using statistical models and automated algorithms, fundamentally changing the approach to equipment requalification and reducing MTTR.
2Manufacturing precision
If iterative tuning processes are used for equipment requalification, then equipment parameters can be adjusted to meet criteria, but the process requires multiple test substrate productions and measurements
Solution Approach 1:
The system performs preliminary statistical analysis and parameter optimization before actual production. By using multivariate R2R control and virtual metrology to predict optimal parameter settings in advance, the system eliminates the need for multiple iterative test substrate productions, thereby improving equipment utilization while maintaining manufacturing precision.
Solution Approach 2:
The system uses virtual metrology to create virtual copies of physical measurements and predictions of process outcomes. This allows parameter validation and optimization to occur in the virtual domain before physical implementation, reducing the need for actual test substrate productions and improving equipment productivity.
3Loss of time
If automated multivariate R2R control and virtual metrology are implemented, then requalification time is reduced, but system complexity increases
Solution Approach 1:
The system integrates multiple functions into a unified multivariate control platform that combines R2R control, virtual metrology, statistical process control, and automated parameter optimization. This multi-functional approach reduces overall system complexity by eliminating the need for separate manual processes while achieving significant requalification time reduction.
Data Source
AI summary
Described herein are methods, apparatuses, and systems for reducing equipment repair time. In one embodiment, a computer implemented method includes collecting test substrate data or other metrology data and fault detection data for maintenance recovery of at least one manufacturing tool in a manufacturing facility and determining a relationship between tool parameter settings for the manufacturing tool and the test substrate data. The method further 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 state estimation including a current operating region of the at least one manufacturing tool. Applying multivariate run-to-run (R2R) control modeling to obtain tool parameter adjustments for at least one manufacturing tool to reduce maintenance recovery time and to reduce requalification time.