Control apparatus, lithography apparatus, and article manufacturing method
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.
1. A control apparatus for generating a control signal for controlling a control target, which is included in a lithography apparatus for performing processing of transferring a pattern of an original to a substrate, the control apparatus comprising:
a selector configured to select, from a plurality of neural networks, one neural network to be used to generate the control signal, for each one of a plurality of sequences,
wherein the selector is configured to select a first neural network from the plurality of neural networks for first sequence, and select a second neural network from the plurality of neural networks for an exposure sequence of exposing the substrate such that the pattern of the original is transferred to the substrate, the second neural network being different from the first neural network, and
wherein the first sequence is one of a measurement sequence for alignment of the substrate and the original, a load sequence of conveying the substrate to a substrate stage, or an unload sequence of conveying the substrate on the substrate stage to a location different from the substrate stage.
2. The control apparatus according to claim 1 , wherein the second neural network is selected by the selector to be used in execution of at least part of an exposure control pattern.
3. The control apparatus according to claim 1 , wherein the selector selects, based on information provided from a higher level apparatus, the one neural network to be used.
4. The control apparatus according to claim 1 , further comprising:
a subtractor configured to calculate a difference between a target value and a state signal indicating a state of the control target;
a compensator configured to calculate a manipulated variable based on the difference; and
an adder,
wherein the difference is supplied to the one neural network to be used, and the adder adds the manipulated variable and an output from the one neural network to be used, thereby generating the control signal.
5. The control apparatus according to claim 1 , wherein the control apparatus is configured to control a position of the control target.
6. The control apparatus according to claim 1 , wherein the control apparatus is configured to control a temperature of the control target.
7. A control apparatus for generating a control signal for controlling a control target, the control apparatus comprising:
a selector configured to select, from a plurality of neural networks, a neural network to be used to generate the control signal,
wherein an acceleration profile of the control target includes a plurality of time sections, and the plurality of time sections include a jerk section during which an acceleration increases within a positive range, a uniform acceleration section during which the acceleration is maintained at a positive constant value, a jerk section during which the acceleration decreases within the positive range, a uniform velocity section during which the acceleration is maintained at zero, a jerk section during which an absolute value of the acceleration increases within a negative range, a uniform acceleration section during which the acceleration is maintained at a negative constant value, and a jerk section during which the absolute value of the acceleration decreases within the negative range, and
wherein in accordance with a current time section among the plurality of time sections, the selector selects, from the plurality of neural networks, the neural network to be used.
8. A lithography apparatus for performing processing of transferring a pattern of an original to a substrate, the lithography apparatus comprising:
an operation unit configured to operate for the processing; and
a control unit configured to generate a control signal for controlling the operation unit,
wherein the control unit includes a selector configured to select, from a plurality of neural networks, one neural network to be used to generate the control signal, for each one of a plurality of sequences,
wherein the selector is configured to select a first neural network from the plurality of neural networks for a first sequence, and select a second neural network from the plurality of neural networks for an exposure sequence of exposing the substrate such that the pattern of the original is transferred to the substrate, the second neural network being different from the first neural network, and
wherein the first sequence is one of a measurement sequence for alignment of the substrate and the original, a load sequence of conveying the substrate to a substrate stage, or an unload sequence of conveying the substrate on the substrate stage to a location different from the substrate stage.
9. The lithography apparatus according to claim 8 , wherein each of the plurality of neural networks is selected by the selector to be used in execution of at least part of at least one of the plurality of control patterns for controlling the operation unit.
10. The lithography apparatus according to claim 8 , wherein:
the operation unit includes a scanning mechanism configured to scan the original and the substrate so as to transfer the pattern of the original to the substrate, and
the exposure sequence includes exposing the substrate while scanning the substrate and the original by the scanning mechanism.
11. The lithography apparatus according to claim 8 , further comprising:
a sensor configured to detect a state of the operation unit;
a subtractor configured to calculate a difference between a target value and an output from the sensor;
a compensator configured to calculate a manipulated variable based on the difference; and
an adder,
wherein the difference is supplied to the one neural network to be used, and the adder adds the manipulated variable and an output from the one neural network to be used, thereby generating the control signal.
12. An article manufacturing method comprising:
a transfer step of transferring a pattern of an original to a substrate using a lithography apparatus defined in claim 8 ; and
a processing step of processing the substrate having undergone the transfer step,
wherein an article is obtained from the substrate having undergone the processing step.
13. A lithography apparatus for performing processing of transferring a pattern of an original to a substrate, the lithography apparatus comprising:
an operation unit configured to operate for the processing; and
a control unit configured to generate a control signal for controlling the operation unit,
wherein the control unit includes a selector configured to select, from a plurality of neural networks, one neural network to be used to generate the control signal, for each one of a plurality of sequences,
wherein an acceleration profile of the operation unit includes a plurality of time sections, and the plurality of time sections include a jerk section during which an acceleration increases within a positive range, a uniform acceleration section during which the acceleration is maintained at a constant value, a jerk section during which the acceleration decreases within the positive range, a uniform velocity section during which the acceleration is maintained at zero, a jerk section during which an absolute value of the acceleration increases within a negative range, a uniform acceleration section during which the acceleration is maintained at a constant value, and a jerk section during which the absolute value of the acceleration decreases within the negative range, and
wherein in accordance with a current time section among the plurality of time sections, the selector selects, from the plurality of neural networks, the one neural network to be used.
14. A control method of controlling a control target, which is included in a lithography apparatus for performing processing of transferring a pattern of an original to a substrate, the control method comprising:
selecting, from a plurality of neural networks, one neural network to be used to generate a control signal for controlling the control target, for each one of a plurality of sequences; and
controlling the control target using the control signal generated by the selected neural network,
wherein in the selecting, a first neural network is selected from the plurality of neural networks for a first sequence, and a second neural network is selected from the plurality of neural networks for an exposure sequence of exposing the substrate such that the pattern of the original is transferred to the substrate, the second neural network being different from the first neural network, and
wherein the first sequence is one of a measurement sequence for alignment of the substrate and the original, a load sequence of conveying the substrate to a substrate stage, or an unload sequence of conveying the substrate on the substrate stage to a location different from the substrate stage.
15. A control method of controlling a control target, which is included in a lithography apparatus for performing processing of transferring a pattern of an original to a substrate, the control method comprising:
selecting, from a plurality of neural networks, a neural network to be used to generate a control signal for controlling the control target; and
controlling the control target using the control signal generated by the selected neural network,
wherein an acceleration profile of the control target includes a plurality of time sections, and the plurality of time sections include a jerk section during which an acceleration increases within a positive range, a uniform acceleration section during which the acceleration is maintained at a positive constant value, a jerk section during which the acceleration decreases within the positive range, a uniform velocity section during which the acceleration is maintained at zero, a jerk section during which an absolute value of the acceleration increases within a negative range, a uniform acceleration section during which the acceleration is maintained at a negative constant value, and a jerk section during which the absolute value of the acceleration decreases within the negative range, and
wherein in the selecting, the neural network to be used is selected from the plurality of neural networks in accordance with a current time section among the plurality of time sections.