Chamber Control Knob Estimation for Faster Post-Maintenance Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for chamber control knob tuning after preventive maintenance, such as chamber seasoning, require multiple iterations and test samples, leading to delays and downtime in semiconductor fabrication facilities, as they rely on inspection results and do not provide in-situ monitoring.
Innovation Solution
A method and system using machine learning models to estimate chamber control knob settings by processing sensor data and substrate process data, allowing for real-time updates and reducing the need for test samples, thereby accelerating the return to production mode.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional iterative methods with test samples are used for chamber control knob tuning, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent replaces the mechanical/physical iterative testing system with a data processing and machine learning system. Instead of physically processing test samples and inspecting results, the system uses sensor data and substrate process data fed into machine learning models to predict optimal control knob settings, thereby eliminating the time-consuming iterative physical testing while maintaining assessment accuracy
Solution Approach 2:
The system performs preliminary data collection and model training in advance. Sensor data and substrate process data are collected and used to train machine learning models before actual chamber recovery is needed. This preliminary preparation enables rapid prediction of optimal control knob settings without requiring time-consuming iterative testing during the recovery process
2Manufacturing precision
If iterative test sample evaluations are performed, then manufacturing precision is improved, but productivity deteriorates
Solution Approach 1:
The patent replaces the mechanical iterative testing process with a computational machine learning system that processes sensor and process data to predict optimal chamber settings. This substitution eliminates the need to remove wafers for inspection and re-processing, maintaining substrate processing quality while preventing productivity loss from iterative testing cycles
Solution Approach 2:
The system creates a virtual model of the chamber environment using sensor data and substrate process data. Machine learning models process this data to generate predictions about optimal control knob settings, effectively creating a digital copy or representation of the physical chamber state without requiring physical test samples, thereby maintaining precision while preserving productivity
Data Source
AI summary
The subject matter of this specification can be implemented in, among other things, methods, systems, computer-readable storage medium. A method can include receiving (i) sensor data indicating a first state of an environment of a processing chamber processing a substrate subsequent to a chamber recovery procedure, and (ii) substrate process data indicating a set of process parameter values associated with performing a substrate processing procedure by the processing chamber having the environment in a second state prior to the chamber recovery procedure. The method further includes processing the sensor data and the substrate process data using one or more machine learning models to determine one or more outputs. The one or more outputs include an update to at least one of the set of process parameter values. The update is associated with performing the substrate processing procedure by the processing chamber having the environment in the first state.