Lithography Control Using Switched Neural Networks for Real-Time Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional control apparatuses using neural networks face long calculation times, which degrade real-time control performance.
Innovation Solution
A control apparatus comprising a plurality of neural networks and a selector that chooses the appropriate neural network for each control pattern, reducing the scale of each network and enabling rapid calculation by switching between them.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single large-scale neural network is used for control, then control accuracy is improved, but calculation time increases and real-time performance degrades
Solution Approach 1:
The patent divides a single large-scale neural network into multiple smaller neural networks, each specialized for specific control patterns. This segmentation reduces the calculation burden of each individual network while maintaining overall control accuracy through selective deployment of appropriate networks for different operating conditions.
Solution Approach 2:
The system dynamically selects which neural network to use based on the current control pattern or operating conditions. This dynamic adaptation allows the system to use simpler, faster networks when appropriate while maintaining accuracy when needed, thereby improving real-time performance without sacrificing control precision.
2Measurement precision
If a single large-scale neural network is used for control, then control accuracy is improved, but real-time control performance degrades
Solution Approach 1:
The patent segments the control system into multiple specialized neural networks, each optimized for specific control patterns. This allows the system to achieve high accuracy for each pattern while maintaining fast response times by selecting the appropriate pre-trained network, thereby improving real-time control performance.
Solution Approach 2:
Multiple neural networks are pre-trained offline for different control patterns before deployment. This preliminary action allows the system to have ready-to-use, optimized networks for various scenarios, eliminating the need for real-time training or complex computations during actual control operations, thus enhancing real-time performance.
3Loss of time
If the scale of each neural network is reduced, then calculation time is shortened, but individual network capability is reduced
Solution Approach 1:
Instead of one large network, the system uses multiple smaller networks, each specialized for specific control patterns. Each small network has reduced calculation time, but collectively they cover the full range of control scenarios, maintaining overall system capability while improving speed.
Solution Approach 2:
Each neural network is specialized for specific local control patterns or operating conditions rather than being a general-purpose network. This local optimization allows each small network to achieve high accuracy for its designated function, compensating for the reduced scale through targeted expertise.
Data Source
AI summary
A control apparatus for generating a control signal for controlling a control target includes a plurality of neural networks, and a selector configured to select, from the plurality of neural networks, a neural network to be used to generate the control signal, wherein each of the plurality of neural networks is selected by the selector to be used in execution of one corresponding control pattern among a plurality of control patterns for controlling the control target.