Virtual Knobs for Process Chamber Recipe Tuning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing manufacturing systems face challenges in efficiently adjusting process chamber parameters to compensate for hardware variations and deteriorating conditions, leading to defects in substrates such as uneven layer thickness and incomplete etching.
Innovation Solution
The implementation of an electronic device manufacturing system that uses machine-learning models to generate virtual knobs, allowing for the adjustment of process parameters without changing the physical settings, thereby optimizing manufacturing processes and reducing defects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If process chamber hardware settings are adjusted to compensate for deviations, then manufacturing precision is improved, but time consumption and operational complexity increase
Solution Approach 1:
The patent creates virtual copies of physical hardware knobs as software-based virtual knobs that replicate the functional effects of physical adjustments. These virtual knobs allow operators to compensate for chamber variations and recipe deviations through software adjustments rather than time-consuming physical hardware modifications, thereby maintaining manufacturing precision while significantly reducing adjustment time.
Solution Approach 2:
The patent replaces the mechanical system of physical hardware adjustments with an electronic/software-based system. Virtual knobs substitute for physical chamber setting adjustments, allowing rapid parameter modifications through software interfaces. This substitution eliminates the time-consuming nature of physical hardware adjustments while maintaining the ability to achieve precise manufacturing outcomes.
2Manufacturing precision
If process chamber hardware settings are adjusted to compensate for deviations, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The patent creates virtual copies of complex physical hardware adjustment systems as simplified software interfaces. The virtual knobs provide a user-friendly interface that abstracts away the complexity of physical chamber adjustments while maintaining the ability to achieve precise manufacturing outcomes. This copying approach reduces operational complexity without sacrificing manufacturing precision.
Solution Approach 2:
The patent introduces virtual knobs as an intermediary layer between the operator and the physical chamber hardware. This intermediary software interface simplifies the interaction by providing intuitive controls that automatically translate user inputs into appropriate chamber parameter adjustments, thereby reducing the perceived complexity of recipe adjustments while maintaining manufacturing precision.
3Measurement precision
If machine-learning models are trained with extensive data, then model accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by pre-training machine learning models with extensive historical manufacturing data before actual production use. The models are trained in advance to learn the complex relationships between chamber parameters, hardware variations, and manufacturing outcomes. Once trained, these models can rapidly predict optimal parameter adjustments without requiring extensive real-time data processing, thus achieving high accuracy while minimizing adjustment time during production.
Solution Approach 2:
The patent applies partial action by using the trained machine learning models to predict only the specific parameter adjustments needed based on current chamber conditions, rather than reprocessing all historical data during production. The models leverage previously learned patterns to quickly determine optimal adjustments, achieving high predictive accuracy without the computational overhead of processing complete datasets in real-time.
Data Source
AI summary
An electronic device manufacturing system configured to receive, by a processor, input data reflecting a feature related to a manufacturing process of a substrate. The manufacturing system is further configured to train a machine-learning model based on the input data reflecting the feature. The manufacturing system is further configured to modify the machine-learning model in view of the virtual knob for the feature.