Adaptive Neural Network Control for Lithography Drive Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Control accuracy deteriorates over time due to changes in the state of a controlled object, even when optimized neural networks are used for control, as they do not account for changing driving and environmental conditions.
Innovation Solution
A processing apparatus with a controller that includes a first compensator and a second compensator, where the second compensator is a neural network that learns parameter values by incorporating driving and environmental conditions in addition to control errors, to generate command values for the driver, thereby maintaining control accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a neural network optimized for a controlled object is used, then control accuracy is improved, but control accuracy deteriorates over time due to changes in the state of the controlled object
Solution Approach 1:
The neural network parameters are made dynamic through continuous learning and updating mechanisms. The control apparatus learns new parameter values over time to adapt to changing states of the controlled object, transforming the static optimized network into a dynamic adaptive system that maintains control accuracy despite state changes.
Solution Approach 2:
A feedback mechanism is implemented where the control apparatus continuously monitors the state of the controlled object and uses this information to update the neural network parameters. The learning process incorporates feedback from actual control performance and state changes, enabling the system to adjust and maintain optimal control accuracy over time.
2Measurement precision
If neural network parameters are updated by iterative learning, then control accuracy is improved, but the system complexity increases
Solution Approach 1:
The control apparatus performs self-learning and self-updating of neural network parameters through iterative learning processes. The system automatically adjusts its own parameters based on observed state changes and control performance, eliminating the need for external manual re-optimization and reducing operational complexity despite the sophisticated learning mechanisms.
Data Source
AI summary
A processing apparatus includes a driver configured to drive a controlled object, and a controller configured to control the driver by generating a command value to the driver based on a control error. The controller includes a first compensator configured to generate a first command value based on the control error, a second compensator configured to generate a second command value based on the control error, and an adder configured to obtain the command value by adding the first command value and the second command value. The second compensator includes a neural network for which a parameter value is decided by learning, and input parameters input to the neural network include at least one of a driving condition of the driver and an environment condition in a periphery of the controlled object in addition to the control error.