Substrate Processing Control Using Model Data for Faster Setup
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Substrate processing systems face challenges in efficiently controlling film formation processes due to numerous adjustable parameters, leading to prolonged setup times and inability to identify optimal parameter combinations for desired processing results.
Innovation Solution
A substrate processing apparatus and method that utilizes a model data generation system to store and control processing conditions and movable part attitudes based on training data, including machine learning to derive optimal settings for film formation, thereby streamlining the control of substrate processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If multiple processing parameters are adjusted to achieve desired processing results, then manufacturing precision is improved, but loss of time increases due to prolonged setup times
Solution Approach 1:
The system performs preliminary actions by generating model data in advance that predicts processing results based on various processing conditions. This pre-computed model data allows the processing controller to determine optimal processing conditions without time-consuming trial-and-error adjustments during actual setup, thus reducing setup time while maintaining manufacturing precision
Solution Approach 2:
The system implements feedback by using the model data to predict processing results and adjust processing conditions accordingly. The processing controller refers to the model data generated from training data that includes processing conditions and their corresponding results, enabling precise control of substrate processing while minimizing the time needed to achieve desired outcomes
2Manufacturing precision
If numerous processing parameters are manually adjusted to find optimal combinations, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The system introduces an intermediary element - the model data generated by the model data generation apparatus - that mediates between the complex processing parameters and the desired processing results. This model data serves as a reference that simplifies the control task for the processing controller, reducing the apparent complexity of controlling multiple parameters while maintaining manufacturing precision
Solution Approach 2:
The system creates a copy or representation of the complex processing system in the form of model data generated from training data. This model data captures the relationships between processing conditions and results, allowing the processing controller to reference this simplified representation rather than directly managing the complexity of numerous processing parameters
Data Source
AI summary
The storage is configured to store model data generated based on data including, in patterns, a processing condition for substrate processing, an attitude of a movable part that affects a processing result of the substrate processing, and the processing result of the substrate processing. The processing controller is configured to use the model data stored in the storage to control the substrate processing, including control of the processing condition for the substrate processing and control of the attitude of the movable part, according to a condition to be satisfied by the processing result of the substrate processing.