ML Equipment Parameter Control for Process Tool Drift
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining and optimizing equipment parameters for substrate manufacturing systems is time-consuming and prone to human bias, especially as equipment parameters vary and drift over time, affecting process consistency and efficiency.
Innovation Solution
Utilizing machine learning techniques to monitor, update, and assign default values and criticality to equipment parameters, reducing the need for human intervention and improving parameter management efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to determine and optimize equipment parameters, then human expertise and judgment can be applied, but the process becomes time-consuming and prone to human bias
Solution Approach 1:
The patent replaces manual human analysis and optimization of equipment parameters with an automated machine learning system. The ML model processes equipment data and automatically determines optimal parameters, eliminating the time-consuming manual process while maintaining or improving optimization accuracy through data-driven insights.
Solution Approach 2:
The system enables equipment parameters to be automatically optimized through self-learning machine learning models that continuously improve by processing equipment data. The system serves itself by automatically detecting parameter drift, predicting optimal values, and implementing corrections without human intervention, reducing both time loss and human bias.
2Stability of the object's composition
If equipment parameters are frequently monitored and adjusted to maintain process consistency, then manufacturing quality improves, but the complexity of parameter management increases
Solution Approach 1:
The patent implements a feedback mechanism where machine learning models continuously monitor equipment parameters, compare actual values against predicted optimal values, and automatically trigger adjustments when drift is detected. This closed-loop feedback system maintains process consistency while simplifying management by automating the monitoring and adjustment process.
Solution Approach 2:
The machine learning model acts as an intermediary between equipment data and parameter adjustments. It processes complex equipment data, identifies drift patterns, and determines optimal correction actions, thereby maintaining process consistency while reducing the complexity of direct parameter management through intelligent mediation.
3Productivity
If multiple equipment parameters are optimized simultaneously across multiple process tools, then overall manufacturing efficiency improves, but the difficulty of determining the correct parameter settings increases
Solution Approach 1:
The patent employs a universal machine learning platform that can simultaneously optimize multiple equipment parameters across multiple process tools. The ML system handles diverse parameter types and equipment variations through a unified approach, improving manufacturing throughput while reducing optimization difficulty by consolidating multiple optimization tasks into a single multi-functional system.
Solution Approach 2:
The system segments the complex optimization problem into manageable components by training separate ML models or using ensemble methods for different parameter groups and equipment types. This segmentation allows simultaneous optimization of multiple parameters while reducing overall complexity by breaking down the large-scale optimization into smaller, more tractable sub-problems.
Data Source
AI summary
A method includes receiving first data associated with an equipment parameter. The first data is indicative of an equipment setting of a process tool of a plurality of process tools at a first manufacturing system. The method further includes providing the first data as input to a trained machine learning model. The trained machine learning model is trained using historical data pertaining to equipment parameters of the plurality of process tools at the first manufacturing system. The method further includes obtaining, as output of the trained machine learning model, a predicted value of a metric corresponding to the equipment parameter. The method further includes comparing the predicted value of the metric with the first data, and performing a corrective action based on the comparing.