Run-to-Run Control Modeling with Digital Twin Recipe Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional control systems in manufacturing processes lack agility and adaptability, relying on infrequent and costly external metrology, leading to inefficiencies and inaccuracies in process adjustments.
Innovation Solution
An enhanced process control platform utilizing on-board sensing and machine learning models, including a virtual metrology model, run-to-run controller, and digital twin feedback model, enables frequent and precise adjustments based on real-time metrology data, integrating input/output models and constrained optimizers to optimize process conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional control systems use external metrology for process monitoring, then measurement capability is provided, but the system lacks agility and adaptability due to infrequent and costly measurements
Solution Approach 1:
The patent creates a digital twin model that is a virtual copy of the physical process chamber and substrate processing. This digital twin replicates the physical metrology measurements without requiring actual physical measurements, enabling continuous monitoring and frequent adjustments without the constraints of external metrology equipment. The digital twin allows the system to adapt rapidly to process changes while maintaining measurement accuracy.
2Loss of information
If external metrology is used for substrate measurement, then measurement data is obtained, but the process adjustments are infrequent and costly
Solution Approach 1:
The system uses on-board sensors integrated within the process chamber to continuously monitor process parameters such as temperature, pressure, and gas flow. These sensors enable the system to self-monitor and self-adjust without requiring external metrology equipment. The run-to-run controller processes this continuous data to make frequent, real-time adjustments to process parameters, dramatically increasing productivity while reducing costs associated with external metrology services.
3Reliability
If conventional control systems are used, then basic process control is maintained, but the system lacks the flexibility and robustness needed for optimized manufacturing
Solution Approach 1:
The patent implements a dynamic control system where the run-to-run controller continuously adjusts process parameters based on real-time data from on-board sensors and the digital twin model. This dynamic adjustment capability allows the system to adapt to changing process conditions, equipment drift, and substrate variations, providing both high reliability through continuous monitoring and high flexibility through real-time optimization. The system evolves from static conventional control to dynamic adaptive control.
Data Source
AI summary
A method includes a run-to-run controller to obtain metrology data. The run-to-run controller is associated with a process chamber. The metrology data is of a first substrate. The first substrate has been processed in the process chamber in accordance with a processing operation. The run-to-run controller includes a first model, configured to determine a relationship between substrate metrology and one or more process knob inputs. The run-to-run controller includes a second model, which is configured to recommend one or more corrective actions based on output generated by the first model. The method further includes processing the metrology data by the first model to determine a relationship between the metrology data of the substrate and process knobs of the first processing operation. The method further includes determining, by the second model, a recommended one or more process recipe updates. The method further includes updating a recipe of the processing operation.