KR20230118130A - Control devices, adjustment methods, lithographic devices and methods of manufacturing articles - Google Patents

Abstract

A control device that generates a control signal for controlling an object to be controlled, and corrects the control deviation by correcting the control deviation according to a first compensator that generates a first signal based on a control deviation of the control object and an arithmetic expression capable of adjusting coefficients. A compensator for correcting the control deviation using one of a plurality of adjusters for generating a signal; a second compensator for generating a second signal by a neural network based on the correction signal; and an operator for generating the control signal based on the second signal.

Description

Control devices, adjustment methods, lithographic devices and methods of manufacturing articles

The present invention relates to control devices, adjustment methods, lithographic devices and methods of manufacturing articles.

BACKGROUND OF THE INVENTION In a photolithography process for manufacturing devices such as semiconductor devices and flat panel displays (FPDs), an exposure apparatus that transfers a pattern of a mask to a substrate is used. Exposure apparatuses are required to perform positional and synchronizing control of a mask stage holding a mask and a substrate stage holding a substrate with high accuracy, for example, in order to align the position of a mask and a substrate.

The demand for precision required for position control or synchronous control of the stage, etc. as described above is becoming stricter as devices become more precise, and the required precision may not be reached only with conventional feedback control. Therefore, in addition to the conventional controller, efforts have been made to construct a neural network controller in parallel (Patent Document 1). In addition, a method of performing compensation suitable for the control target by switching the neural network controller according to the state of the control target has been devised (Patent Document 2).

Japanese Patent Publication No. 7-503563 Japanese Unexamined Patent Publication No. 7-277286

However, although accuracy can be improved by configuring a plurality of neural network controllers, the control calculation time increases. Further, the parameters of the neural network controller are adjusted by machine learning, but it takes a lot of time to learn the parameters of a plurality of neural networks. In addition, when a change in the state of a control object or a change in a disturbance environment occurs, since the parameters of the neural network determined in advance are not optimal, it takes a lot of time to readjust the parameters.

Accordingly, an object of the present invention is to provide a control device that is advantageous for adjusting appropriate control characteristics in a short time in a control device using a neural network.

In order to achieve the above object, a control device as one aspect of the present invention is a control device that generates a control signal for controlling a control object, and a first compensator that generates a first signal based on a control deviation of the control object. and a corrector for correcting the control deviation using one of a plurality of adjusting units generating a correction signal by correcting the control deviation according to an arithmetic expression capable of adjusting coefficients; and a neural network based on the correction signal. It is characterized in that it comprises a second compensator for generating a second signal, and an operator for generating the control signal based on the first signal and the second signal.

According to the present invention, in a control device using a neural network, it is possible to provide a control device that is advantageous for adjusting appropriate control characteristics in a short time.

1 is a diagram showing a configuration example of a system in a first embodiment.
Fig. 2 is a diagram showing an example of the configuration of the system in the first embodiment.
Fig. 3 is a diagram showing an example of the configuration of a controller in the system of the first embodiment.
Fig. 4 is a diagram showing an example of the configuration of a controller in the sixth embodiment.
Fig. 5 is a diagram showing an example of the configuration of a controller in the seventh embodiment.
6 is a diagram showing a configuration example of a controller in the eighth embodiment.
7 is a diagram showing a configuration example of the system in the first embodiment.
8 is a flowchart showing an example of operation when the system of the first embodiment is applied to production equipment.
9 is a diagram showing an example of measurement results of disturbance suppression characteristics.
10 is a diagram showing a configuration example of a stage control device in the second embodiment.
Fig. 11 is a diagram showing a configuration example of a control board in the system according to the second embodiment.
12 is a flow chart showing the adjustment of the compensator.
13 is a diagram illustrating a position control deviation.
14 is a diagram showing an example of a result of frequency analysis.
15 is a diagram showing a configuration example of an exposure apparatus.

EMBODIMENT OF THE INVENTION Below, preferred embodiment of this invention is described in detail based on attached drawing. In addition, in each figure, the same reference number is attached|subjected about the same member, and overlapping description is abbreviate|omitted.

<First Embodiment>

Fig. 1 shows the configuration of the system SS in this embodiment. System SS is applied, for example, to manufacturing equipment for manufacturing articles. The manufacturing apparatus includes, for example, a processing apparatus that processes an article or a member constituting a part of the article. The processing device may be, for example, any of a lithography device for transferring a pattern to a material or member, a film forming device for forming a film on the material or member, an device for etching the material or member, and a heating device for heating the material or member. there is.

The system SS includes, for example, a sequence unit 101, a control device 100, and a control target 103. The control device 100 includes a controller 102 . The control device 100 or the controller 102 generates a control signal MV for controlling the control object 103 . When the system SS is applied to the production system, the sequence unit 101 is provided with a production sequence. A production sequence defines a sequence for production. The sequence unit 101 generates a target value R for controlling the control object 103 based on the production sequence, and provides the target value R to the control device 100 or the controller 102 .

The control device 100 or the controller 102 performs feedback control on the control target 103 . Specifically, the control device 100 calculates the control amount CV of the control object 103 based on the control deviation, which is the difference between the target value R provided from the sequence unit 101 and the control amount CV provided from the control object 103. The control target 103 is controlled so as to follow the target value R. The control target 103 may have a sensor that detects the control amount CV, and the control amount CV detected by the sensor may be provided to the controller 102 . The target value R, the control signal MV, and the control amount CV may be time-series data whose values change with the lapse of time.

As illustrated in FIG. 2 , a learning unit 201 may be included in the system SS. The learning unit 201 may be configured as a part of the control device 100 or may be configured as an external device of the control device 100 . When the learning unit 201 is configured as an external device of the control device 100, the learning unit 201 may be separated from the control device 100 after completion of learning. The learning unit 201 is configured to send a previously prepared learning sequence to the sequence unit 101. The sequence unit 101 generates a target value R according to the learning sequence and provides it to the controller 102.

The controller 102 generates the control signal MV based on the control deviation, which is the difference between the target value R generated and provided from the sequence unit 101 according to the learning sequence and the control amount CV provided from the control object 103. Here, the controller 102 has a neural network and uses the neural network to generate the control signal MV. The control signal MV generated by the controller 102 is provided to the control target 103, and the control target 103 operates according to the control signal MV. The control amount CV as a result of this operation is provided to the controller 102. The controller 102 provides the learning unit 201 with an operation history indicating a history of the operation of the controller 102 based on the target value R. The learning unit 201 determines parameter values of the neural network of the controller 102 based on the corresponding motion history, and sets the corresponding parameter values to the corresponding neural network. The corresponding parameter value is determined by machine learning such as reinforcement learning, for example.

3 is a diagram showing one example of the configuration of the controller 102. As shown in FIG. The controller 102 includes a first compensator 301 generating a first signal S1 based on the control deviation E and a compensator 303 generating a correction signal CS by calculating the control deviation E according to an arithmetic expression capable of adjusting coefficients. includes In addition, the controller 102 includes a second compensator 302 generating a second signal S2 by a neural network based on the correction signal CS, and a control signal MV based on the first signal S1 and the second signal S2. It includes an arithmetic unit 306.

The compensator 303 has a plurality of compensators including a first adjuster 303a and a second adjuster 303b, and an adjuster to be used (connected adjuster) can be selected according to the control state. The control signal MV is the sum of the first signal S1 and the second signal S2, and the operator 306 may be configured as an adder. In addition, the control signal MV is a signal obtained by correcting the first signal S1 based on the second signal S2. The controller 102 includes a subtractor 305 that generates a control deviation E, which is the difference between the target value R and the control amount CV. The control amount CV is acquired by measuring with a sensor or the like not shown provided in the control target 103 . In addition, compared to the difference between the control amount and the target value R, which is the result of controlling the control target 103 based on the first signal S1, the control amount and target value R, which is the result of controlling the control target 103 based on the control signal MV The side of the car of is small.

The controller 102 further includes an operation history recording unit 304 . The learning unit 201 in FIG. 2 is configured to perform learning for determining neural network parameter values of the second compensator 302 in FIG. 3 . For learning by the learning unit 201, the motion history recording unit 304 records motion history required for learning by the learning unit 201 and provides the recorded motion history to the learning unit 201. The operation history is, for example, a correction signal CS that is input data to the second compensator 302 and a second signal S2 that is output data of the second compensator 302, but the control deviation and the output of the second compensator 302 The second signal S2 as data may be used, or other data may be used. The first adjustment unit 303a and the second adjustment unit 303b can perform learning with an arbitrary parameter as an initial value.

In Embodiments 1 to 5 below, configuration examples of the compensator 303 will be described. In Embodiments 1 to 5, examples of arithmetic expressions used by the compensator 303 to generate the correction signal CS based on the control deviation E are shown. The arithmetic expression may be, for example, a mononomial expression or a polynomial expression.

(Example 1)

In Example 1, the 1st adjustment part 303a and the 2nd adjustment part 303b have the control characteristic represented by the following formula (1). Here, the input (E) to the compensator 303 is x, the output (CS) of the compensator 303 is y, and an arbitrary coefficient (constant) is Kp.

(Example 2)

In Example 2, the 1st adjustment part 303a and the 2nd adjustment part 303b have the control characteristic represented by the following formula (2). Here, the input (E) to the compensator 303 is x, the output (CS) of the compensator 303 is y, the time is t, and an arbitrary coefficient (constant) is Ki. In addition, integration may be performed a plurality of times. The integral may be a definite integral or an inverse integral of a certain time interval.

(Example 3)

In Example 3, the 1st adjustment part 303a and the 2nd adjustment part 303b have the control characteristic represented by the following formula (3). Here, the input (E) to the compensator 303 is x, the output (CS) of the compensator 303 is y, the time is t, and an arbitrary coefficient (constant) Kd. In addition, you may perform differentiation several times.

(Example 4)

In Example 4, the 1st adjustment part 303a and the 2nd adjustment part 303b have the control characteristic represented by the following formula (4). Here, the input (E) to the compensator 303 is x, the output (CS) of the compensator 303 is y, and arbitrary coefficients (constants) are referred to as Kp, Ki, and Kd. In addition, integration and differentiation may be performed a plurality of times.

(Example 5)

In Example 5, the 1st adjustment part 303a and the 2nd adjustment part 303b have the control characteristic represented by the following formula (5). where x is the input (E) to the compensator 303, y is the output (CS) of the compensator 303, n is the integral coefficient of the multiple integral, m is the differential coefficient, and Kp is the random coefficient (constant), n An arbitrary coefficient (constant) in the case of double integration is called Ki_n, and an arbitrary constant in the case of m-order differentiation is called Kd_m.

Embodiments 1 to 5 are examples in which the arithmetic expression used by the compensator 303 to generate the correction signal CS includes at least one of a term proportional to the control deviation E, a term for performing integration, and a term for performing differentiation. can be understood

Coefficients (constants) Kp, Ki, Kd, Ki_n, and Kd_m of the arithmetic expressions given as examples in Examples 1 to 5 are examples of adjustable parameters of the corrector 303. The 1st adjustment part 303a and the 2nd adjustment part 303b determine the optimal parameter using any one of Embodiments 1-5 according to the change of the control state assumed beforehand. The control state is, for example, switching of synchronous control, switching of controllers, switching of operation patterns, changes in environment or disturbances such as temperature, noise, floor vibration, and the like. Optimum control characteristics can be obtained by selecting the first adjusting unit 303a and the second adjusting unit 303b according to the control state. Since the adjustment time by configuring a plurality of correctors is shorter than the adjustment time by configuring a plurality of neural networks, it is advantageous from the viewpoint of time reduction.

In addition, when the state of the control object 103 or the disturbance environment changes during the operation of the system SS, by adjusting the values (parameter values) of (coefficients of) the arithmetic expressions exemplified as the first to fifth embodiments, the change can respond The time required for adjusting the values of (coefficients of) the arithmetic expression of the corrector 303 is shorter than the time required for relearning the neural network. Therefore, the control precision can be maintained without reducing the productivity of the system SS. That is, by introducing the compensator 303, tolerance for a change in the state of the control object 103 or a change in a disturbance environment can be improved.

(Example 6)

Embodiments 6 to 8 explain the relationship between the change in the control state and the switching of the adjustment unit used in the corrector 303.

4 is a diagram showing a configuration example of the controller 102 in the sixth embodiment. In the sixth embodiment, as shown in FIG. 4 , it is possible to switch whether control is performed individually or synchronously with respect to a plurality of control objects including the control object 103a and the control object 103b. there is. The control state in Example 6 is a state determined depending on whether a plurality of control targets are individually controlled or synchronized, and an appropriate adjustment unit is switched depending on whether the plurality of control targets are synchronously controlled. Further, in the sixth embodiment, the compensator 303 is switched depending on the state of the synchronous control switching unit 402, and whether the first adjustment unit 303a or the second adjustment unit 303b is used is determined. You can choose. Further, in the sixth embodiment, a synchronization called master-slave system in which the controlled axis of the control target 103a is set as a master axis and the controlled axis of the control target 103b is set as a slave axis, and the slave axis follows the master axis. Control is explained.

The controller 102 obtains the control amounts CVa and CVb of each of the control objects 103a and 103b measured by a sensor (not shown) of the control object 103, and controls the difference between the respective target values Ra and Rb, respectively. Calculate as deviations Ea, Eb.

The control deviation Ea is input to the controller 301a. An input to the controller 301b and the compensator 303 provided at the front end of the neural network 302 configured in parallel with the controller 301b determines whether to control the control target 103a and the control target 103b synchronously. can be converted to whether The input to the compensator 303 is the control deviation Eb switched by the synchronous control switching unit 402 for switching the synchronous control of the control target 103a and the control target 103b, or the difference between the control deviation Eb and the control deviation Ea. The synchronous deviation Ec can be selected. The output of the compensator 303 can select whether to use the first adjustment unit 303a or the second adjustment unit 303b according to the state of the synchronization control switching unit 402 .

As a specific example of Example 6, for example, when applying to an exposure apparatus, when synchronizing a plate stage and a mask stage, and when performing other operations, you may select another adjusting unit. At this time, the parameters of the first adjusting unit 303a and the second adjusting unit 303b are optimized when the plate stage and the mask stage are synchronized and when performing other operations. Outputs of the first adjustment unit 303a and the second adjustment unit 303b selected according to the state of the synchronization control switching unit 402 are input to the neural network 302 (second compensator). The output of the compensator 301a is referred to as the control signal MVA. The output of the compensator 301b and the output of the neural network 302 are added together and referred to as a control signal MVb. The controller 102 outputs the control signals MVA and MVb to the control targets 103a and 103b, respectively.

The first adjusting unit 303a and the second adjusting unit 303b determine the optimum parameters using any one of the first to fifth embodiments according to the state of the synchronous control switching unit 402 . Optimum control characteristics can be obtained by selecting the first adjusting unit 303a and the second adjusting unit 303b according to the state of the synchronous control switching unit 402 .

The increase in the adjustment time due to the configuration in which the corrector 303 selects the optimal adjustment unit from the plurality of adjustment units is shorter than the increase in the adjustment time due to the configuration of a plurality of neural networks. In addition, when the state of the control object 103 or the disturbance environment changes during operation using any of the first to fifth embodiments, the change can be responded to by adjusting the parameters of the first to fifth embodiments. The time required for adjustment of the first adjustment unit 303a and the second adjustment unit 303b is shorter than the time required for relearning the neural network. In the sixth embodiment, even in the case of performing a plurality of compensations suitable for the state of the control target or the disturbance environment, the increase in the calculation time and the learning time can be suppressed, and a change in the state of the control target or a change in the disturbance environment occurs. Also, appropriate control characteristics can be adjusted in a short time.

(Example 7)

5 is a diagram showing a configuration example of the controller 102 in the seventh embodiment. In the seventh embodiment, the compensator 301 is switched according to the state or operation of the control object 103, and it is possible to select whether to use the compensator 301a or the compensator 301b. The control state in Example 7 is a state determined depending on which of the plurality of compensators is to be used, and switching of the adjustment unit is performed depending on whether the compensator 301a or the compensator 301b is to be used. In the seventh embodiment, the compensator 303 is switched according to the state of the compensator 301, and it is possible to select whether to use the first adjusting unit 303a or the second adjusting unit 303b. .

As a specific example of Example 7, when applied to an exposure apparatus, for example, when a change in gain occurs by using the compensator 301a during the exposure operation of the plate stage and the compensator 301b during the plate conveyance operation. You can do it. That is, the adjustment unit used for correcting the control deviation E may be selected from a plurality of adjustment units based on whether or not the gain switching of the control object 103 is occurring. At this time, the first adjusting unit 303a and the second adjusting unit 303b determine optimum parameters for the compensator 301a and the compensator 301b using any one of Examples 1 to 5. Optimum control characteristics can be obtained by selecting the first adjusting unit 303a and the second adjusting unit 303b according to the state of the compensator 301 .

The increase in the adjustment time due to the configuration in which the corrector 303 selects the optimal adjustment unit from the plurality of adjustment units is shorter than the increase in the adjustment time due to the configuration of a plurality of neural networks. In addition, when the state of the control object 103 or the disturbance environment changes during operation using any of the first to fifth embodiments, the change can be responded to by adjusting the parameters of the first to fifth embodiments. The time required for adjustment of the first adjustment unit 303a and the second adjustment unit 303b is shorter than the time required for relearning the neural network. In the seventh embodiment, even in the case of performing a plurality of compensations suitable for the state of the control object or disturbance environment, the increase in calculation time and learning time can be suppressed, even if a change in the state of the control object or a change in the disturbance environment occurs. , the appropriate control characteristics can be adjusted in a short time.

(Example 8)

6 is a diagram showing a configuration example of the controller 102 in the eighth embodiment. The control state in the eighth embodiment is a state determined by whether or not the operation pattern 403 of the control target is changing. A specific example of the operation pattern 403 will be described later. In the eighth embodiment, the adjustment unit is switched according to the state of the operation pattern 403, and it is possible to select whether to use the first adjustment unit 303a or the second adjustment unit 303b.

As a specific example of Example 7, for example, when applying to a stage apparatus used for an exposure apparatus or the like, it may be applied by switching between an acceleration section during driving of the stage and an operation pattern other than that. At this time, the first adjusting unit 303a and the second adjusting unit 303b determine the optimum parameter using any one of the first to fifth embodiments according to the state of the operation pattern 403 of the control target 103. Optimal control characteristics can be obtained by selecting the first adjusting unit 303a and the second adjusting unit 303b according to the state of the operation pattern 403 .

The increase in the adjustment time due to the configuration in which the corrector 303 selects the optimal adjustment unit from the plurality of adjustment units is shorter than the increase in the adjustment time due to the configuration of a plurality of neural networks. In addition, when the state of the control object 103 or the disturbance environment changes during operation using any of the first to fifth embodiments, the change can be responded to by adjusting the parameters of the first to fifth embodiments. The time required for adjustment of the first adjustment unit 303a and the second adjustment unit 303b is shorter than the time required for relearning the neural network. In the eighth embodiment, even in the case of performing a plurality of compensations suitable for the state of the control object or the disturbance environment, the increase in the calculation time and the learning time can be suppressed, and a change in the state change of the control object or the disturbance environment occurs, Also, appropriate control characteristics can be adjusted in a short time.

As illustrated in FIG. 7 , the control device 100 may include a setting unit 202 that selects whether to use the first adjustment unit 303a or the second adjustment unit. In addition, the setting unit 202 may have a role of setting parameter values of the corrector 303.

The setting unit 202 may perform switching of the adjustment unit or adjustment processing for adjusting parameter values, and may determine and set the switching of the adjustment unit or parameter values by this adjustment processing, or switch the adjustment unit based on a command from the user. or parameter values can be set. In the former, the setting unit 202 may send a confirmation sequence for confirming the operation of the controller 102 to the sequence unit 101, and generate the target value R in the sequence unit 101 based on the confirmation sequence. there is. Then, the setting unit 202 obtains an operation history (eg, control deviation) from the controller 102 operating based on the target value R, and needs to switch the corrector 303 based on the operation history. It is possible to determine the presence or absence of a parameter value. The setting unit 202 having such a function can be understood as an adjustment unit for switching the corrector 303 or adjusting parameter values.

The setting unit 202 acquires an operation history (e.g., control deviation) from the controller 102 at the time of production when the sequence unit 101 generates the target value R based on the production sequence, and records the operation history. Based on this, it may be determined whether or not to perform adjustment of the parameter value of the corrector 303. Alternatively, the determination unit for determining whether or not to adjust the parameter value of the corrector 303 by the setting unit 202 during production in which the sequence unit 101 generates the target value R based on the production sequence is the setting unit. It may be provided separately from 202.

Next, an example in which production is performed by the system in the present embodiment will be described. 8 is an example of operation of the system SS when the system SS of the present embodiment is applied to production equipment.

In step S501, the sequence unit 101 generates a target value R based on the given production sequence, and provides it to the control device 100 or controller 102. The control device 100 or controller 102 controls the control object 103 based on the target value R.

In step S502, the setting unit 202 acquires the operation history (eg, control deviation) of the controller 102 in step S501.

In step S503, the setting unit 202 can determine whether to perform adjustment of the compensator 303, such as switching the adjustment unit or adjusting (or readjusting) parameter values, based on the operation history obtained in step S502. . The setting unit 202 may determine that, for example, when the operation history satisfies a predetermined condition, adjustment (or readjustment) of the switching parameter value of the adjustment unit is executed. The predetermined condition is a condition for stopping production, and it is determined that adjustment of the compensator 303 is necessary when, for example, a control deviation obtained as an operation history exceeds a prescribed value. Then, if the adjustment of the compensator 303 by the setting unit 202 is to be performed, the process proceeds to step S504, otherwise, the process proceeds to step S505.

In step S504, the setting unit 202 adjusts the corrector 303. This adjustment is performed in a state where the parameter values of the second compensator 302 are maintained in the previous state, and by this adjustment, the parameter values (coefficients) of the compensator 303 are reset, for example.

In step S505, the sequence unit 101 judges whether to end production according to the production sequence, returns to step S501 if not, and ends production in the case of ending. According to the above processing, even when production is in a state where it is necessary to stop, it is possible to quickly adjust the parameter value of the compensator 303 and resume production while minimizing production interruption.

In step S504, the setting unit 202 sends the confirmation sequence to the sequence unit 101, and causes the sequence unit 101 to execute the confirmation sequence, and the operation history (e.g., control deviation) in the confirmation sequence is stored in the controller ( 102) can be obtained from Then, the setting unit 202 performs frequency analysis of the operation history, determines a frequency to be improved based on the result, and adjusts the parameters of the corrector 303 so that the control deviation at that frequency is within the specified value. value can be determined. A more specific example of step S504 will be described in the second embodiment.

9 is a diagram illustrating measurement results of disturbance suppression characteristics. The result of measuring the frequency response when the control deviation when a sine wave is input as the control signal MV in FIG. 2 is output is referred to as a disturbance suppression characteristic. In Fig. 9, the horizontal axis represents the frequency, and the vertical axis represents the gain of the disturbance suppression characteristic. Since the disturbance suppression characteristic shows the frequency response of the control deviation E when a disturbance is added to the control signal MV, a large gain indicates a low disturbance suppression effect. On the other hand, when the gain is small, the effect of suppressing disturbance is high. In Fig. 9, the broken line represents the disturbance suppression characteristic before adjustment, and the solid line represents the disturbance suppression characteristic after adjustment.

If the frequency indicated by the dashed-dotted line in Fig. 9 is determined as the frequency at which the disturbance suppression characteristic should be improved and step S504 is executed, the disturbance suppression characteristic indicated by the solid line can be obtained, for example. It can be seen that the gain of the disturbance suppression characteristic is reduced at the frequency to be improved, and the disturbance suppression characteristic is improved. In Embodiments 1 to 8, when adjusting the parameters of the compensator 303 provided at the front end of the neural network, the parameters may be adjusted using the disturbance suppression characteristic shown in Fig. 9 as an index.

<Second Embodiment>

In this embodiment, an example in which the control system SS described in the first embodiment is applied to the stage control device 800 will be described. Matters not mentioned in the present embodiment follow the first embodiment. Fig. 10 is a diagram showing a hardware configuration when the control system SS shown in Fig. 1 is applied to the stage control device 800.

The stage control device 800 is configured to control the stage 804 while holding the object on the stage 804 in order to control the position of an object such as a substrate. The stage control device 800 includes a control board 801, a current driver 802, a motor 803, a stage 804 and a sensor 805. The control board 801 corresponds to the control device 100 or the controller 102 in the system SS of the first embodiment. The current driver 802, motor 803, stage 804, and sensor 805 correspond to the control object 103 in the system SS of the first embodiment. However, the current driver 802 may be included in the control board 801. Although not shown in FIG. 10 , the stage control device 800 may include a sequence unit 101 , a learning unit 201 , and a setting unit 202 .

A position target value as a target value may be supplied to the control board 801 from the sequence unit 101 . The control board 801 may generate a current command as a control signal based on the position target value supplied from the sequence unit 101 and the position information supplied from the sensor 805 and supply the current command to the current driver 802 . Also, the control board 801 may supply the operation history to the sequence unit 101 .

The current driver 802 may supply current according to a current command to the motor 803 . The motor 803 may be an actuator that converts current supplied from the current driver 802 into thrust and drives the stage 804 with the thrust. The stage 804 can hold an object such as a plate or a mask, for example. The sensor 805 can detect the position of the stage 804 and supply positional information obtained thereby to the control board 801 .

11, an example of the configuration of the control board 801 is shown as a block diagram. The control board 801 corrects the control deviation E according to the first compensator 301 that generates the first signal S1 based on the position control deviation E of the stage 804 as a control target and an arithmetic expression capable of adjusting the coefficient. It may include a compensator 303 that generates a correction signal CS. In addition, the control board 801 includes a second compensator 302 generating a second signal S2 by a neural network based on the correction signal CS, and a current command as a control signal based on the first signal S1 and the second signal S2. It may include an operator 306 that generates. In addition, the control board 801 may include a subtractor 305 that generates a control deviation E, which is a difference between the position target value PR and the position information.

The stage control device 100 of the second embodiment may also include a learning unit 201 as in the first embodiment described with reference to FIG. 7 . The learning unit 201 may be configured to perform learning to determine the neural network parameter value of the second compensator 302 . For learning by the learning unit 201, the motion history recording unit 304 may record a motion history required for learning by the learning unit 201 and provide the recorded motion history to the learning unit 201. The operation history may be, for example, the correction signal CS, which is input data to the second compensator 302, and the second signal S2, which is output data of the second compensator 302, but may be other data.

The stage control device 100 of the second embodiment may include a setting unit 202 . The setting unit 202 may execute an adjustment process for adjusting the parameter values of the corrector 303, and may determine and set the parameter values of the corrector 303 by this adjustment process, or adjust the corrector based on a command from the user. You may set the parameter value of (303).

Referring to FIG. 8 , the operation of the stage device 800 when the stage control device 800 according to the second embodiment is applied to production equipment will be exemplarily described. In step S501, the sequence unit 101 can generate a position target value PR based on the given production sequence and provide it to the stage control device 800. The stage control device 800 controls the position of the stage 804 based on the position target value PR.

In step S502, the setting unit 202 acquires the operation history (eg, control deviation) of the control board 801 in step S501.

In step S503, the setting unit 202 can determine whether to perform adjustment of the compensator 303, such as switching the adjustment unit or adjusting (or readjusting) parameter values, based on the operation history obtained in step S502. . The setting unit 202 may determine that the adjustment of the corrector 303 is executed, for example, when the operation history satisfies a predetermined condition. The predetermined condition is a condition for stopping production, and for example, when the maximum value of the position control deviation during constant speed driving of the stage 804 exceeds a predetermined specified value, it is determined that adjustment of the compensator 303 is necessary. Then, if the adjustment of the compensator 303 by the setting unit 202 is to be performed, the process proceeds to step S504, otherwise, the process proceeds to step S505.

In step 504, the setting unit 202 can adjust the corrector 303. In step S505, the sequence unit 101 judges whether to end production according to the production sequence, returns to step S501 if not, and ends production if it has ended.

Fig. 12 shows a specific example of processing in adjusting parameter values (or re-adjusting parameter values) during the adjustment of the corrector 303 in step S504. In step S601, the setting unit 202 sends a confirmation sequence for confirming the operation of the stage control device 800 to the sequence unit 101, and the position target value PR is sent to the sequence unit 101 based on this confirmation sequence. can create In step S602, the setting unit 202 can acquire the position control deviation E as an operation history from the controller 102 operating based on the position target value PR.

Here, with reference to Fig. 13, the change in position control deviation E before and after parameter adjustment will be described. 13 is a diagram illustrating position control deviations before and after parameter adjustment. In Fig. 13, the horizontal axis represents time, and the vertical axis represents position control deviation E. Here, the curve indicated by the dotted line is the position control deviation E before adjusting the parameter values of the compensator 303, indicating that the position control accuracy has deteriorated. By adjusting the parameter value, the variation of the position control deviation E can be reduced.

In step S603, the setting unit 202 can perform frequency analysis of the position control deviation E obtained in step S602. Here, with reference to FIG. 14, the result of the frequency analysis before and after parameter adjustment is demonstrated. 14 is a diagram illustrating results of frequency analysis before and after parameter adjustment. In Fig. 14, the horizontal axis is the frequency, and the vertical axis is the power spectrum. The dotted line represents the frequency showing the maximum spectrum before adjustment. In step S604, the setting unit 202 can determine, for example, a frequency that exhibits the maximum spectrum in the power spectrum as the frequency to be improved.

Steps S605 to S610 are specific examples of adjustment processing for adjusting the parameter values of the corrector 303. Here, an example is described employing the steepest descent method as a method of adjusting parameter values, but other methods may be used. In step S605, the setting unit 202 initializes n to 1. For example, when the arithmetic expression of the compensator 303 is composed of three terms of a first-order integral term, a proportional term, and a first-order derivative term, three parameters whose parameter values are to be adjusted are Ki, Kp, and Kd. The parameter value pn in the n-th adjustment is represented by the following formula (6).

In step S606, the setting unit 202 can set an arbitrary initial value for the parameter value p1 in the first adjustment of the parameter value pn. In the nth adjustment, the parameter value pn represented by Formula (8) mentioned later can be set.

The objective function J(pn) for adjusting the parameter value pn can be, for example, the gain of the disturbance suppression characteristic at the frequency determined in step S604. In step S607, the setting unit 202 can measure the gradient vector grad J(pn) of the objective function J(pn). The gradient vector grad J(pn) can be given by the following equation (7). The gradient vector grad J(pn) can be measured by changing each element Ki-n, Kp-n and Kd-n constituting the parameter value pn by a small amount.

In step S608, the setting unit 202 can determine whether or not the value of each element of the gradient vector grad J(pn) is equal to or less than a specified value as a convergence determination of the steepest descent method. When the value of each element of the gradient vector grad J(pn) is less than or equal to the specified value, the setting unit 202 may terminate the adjustment of the parameter value of the corrector 303. On the other hand, if the value of each element of the gradient vector grad J(pn) exceeds the prescribed value, in step S609, the setting unit 202 can calculate the parameter value pn+1. Here, the parameter value pn+1 can be calculated according to the following equation (8) using, for example, an arbitrary constant α greater than 0. In step S610, the setting unit 202 adds 1 to the value of n, and returns to step S606.

In step S611, the setting unit 202 sends a confirmation sequence for confirming the operation of the stage control device 800 to the sequence unit 101, and the position target value PR is sent to the sequence unit 101 based on this confirmation sequence. can create In step S612, the setting unit 202 can acquire the position control deviation E as an operation history from the controller 102 operating based on the position target value PR.

In step S613, the setting unit 202 judges whether or not the position control deviation E obtained in step S612 is equal to or less than the prescribed value, and if the position control deviation E exceeds the prescribed value, the setting unit 202 returns to step S601 to re-execute the adjustment. If the control deviation E is less than the specified value, the adjustment can be terminated.

According to the present embodiment, when the state or disturbance of the control target including the stage 804 changes, it is possible to respond to the change by adjusting the parameter value of the compensator 303. For example, in the example of FIG. 13 , the position control deviation indicated by a dotted line is reduced to the position control deviation indicated by a solid line, and the control accuracy is improved.

In the example of Equation (6), the number of parameters of the compensator 303 is only three, which is far less than that of general neural networks. For example, in the case of using a deep neural network, if the number of dimensions of the input layer is 5, the number of dimensions of the hidden layer is 2 of 32, and the number of dimensions of the output layer is 8, the number of parameters is 1545. Rather than determining the values of these 1545 parameters by relearning, adjusting the parameter values of the corrector 303 can complete the adjustment in a shorter time. Accordingly, the control precision can be maintained without reducing the productivity of the stage control device 800 .

<Third Embodiment>

In this embodiment, an example in which the control system SS described in the first embodiment is applied to the exposure apparatus EXP will be described. Matters not mentioned in the present embodiment follow the first embodiment. 15 schematically shows an example of the configuration of the exposure apparatus EXP of the present embodiment. The exposure device EXP can be configured as a scanning exposure device.

The exposure apparatus EXP may include, for example, an illumination light source 1000, an illumination optical system 1001, a mask stage 1003, a projection optical system 1004, and a plate stage 1006. The illumination light source 1000 may include, but is not limited to, a mercury lamp, an excimer laser light source, or an EUV light source. The exposure light 1010 from the illumination light source 1000 is shaped by the illumination optical system 1001 into the form of an irradiation area of the projection optical system 1004 with uniform illumination. In one example, the exposure light 1010 may be formed into a long rectangle in the X direction, which is an axis perpendicular to the plane by the Y axis and the Z axis. Depending on the type of the projection optical system 1004, the exposure light 1010 may be shaped into an arc shape. The molded exposure light 1010 is irradiated onto a pattern of a mask (original plate) 1002, and the exposure light 1010 passing through the pattern of the mask 1002 passes through the projection optical system 1004 to the plate 1005 (substrate). An image of the pattern of the mask 1002 is formed on the surface of ).

The mask 1002 is held by the mask stage 1003 by vacuum suction, etc., and the plate 1005 is held by the chuck 1007 of the plate stage 1006 by vacuum suction or the like. The positions of the mask stage 1003 and the plate stage 1006 are controlled by a multi-axis position control device including a position sensor 1030 such as a laser interferometer or a laser scale, a drive system 1031 such as a linear motor, and a controller 1032. can be controlled by A position measurement value output from the position sensor 1030 may be provided to the controller 1032 . The controller 1032 drives the mask stage 1003 and the plate stage 1006 by generating a control signal based on the position control deviation, which is the difference between the position target value and the position measurement value, and providing the control signal to the drive system 1031. do. The pattern of the mask 1002 is transferred to the plate 1005 (the photosensitive material above) by scanning and exposing the plate 1005 while synchronously driving the mask stage 1003 and the plate stage 1006 in the Y direction.

A case where the second embodiment is applied to the control of the plate stage 1006 will be described. The control board 801 in FIG. 11 is the controller 1032, the current driver 802 and the motor 803 are the driving system 1031, the stage 804 is the plate stage 1006, and the sensor 805 is the position sensor. Corresponds to (1030). By applying a controller having a neural network to the control of the plate stage 1006, positional control deviation of the plate stage 1006 can be reduced. In this way, the overlapping accuracy and the like can be improved. Parameter values of the neural network may be determined by a predetermined learning sequence. However, the control accuracy of the plate stage 1006 deteriorates when the state of the control object changes from the time of learning or the disturbance environment changes. Even in such a case, by adjusting the parameter value of the corrector, the adjustment can be completed in a shorter time than relearning the neural network. As a result, the control precision can be maintained without reducing the productivity of the exposure apparatus.

A case where the second embodiment is applied to the control of the mask stage 1003 will be described. The control board 801 in FIG. 11 is the controller 1032, the current driver 802 and the motor 803 are the driving system 1031, the stage 804 is the mask stage 1003, and the sensor 805 is the position sensor. Corresponds to (1030).

Even when the second embodiment is applied to the control of the mask stage 1003, the positional control deviation of the mask stage 1003 can be reduced. In this way, the overlapping accuracy and the like can be improved. Parameter values of the neural network may be determined by a predetermined learning sequence. However, the control accuracy of the mask stage 1003 deteriorates when the state of the control object changes from the time of learning or the disturbance environment changes. Even in such a case, by adjusting the parameter value of the corrector, the adjustment can be completed in a shorter time than relearning the neural network. As a result, the control precision can be maintained without reducing the productivity of the exposure apparatus.

The second embodiment can be applied not only to stage control in an exposure apparatus, but also to stage control in other lithography apparatuses such as an imprint apparatus and an electron beam drawing apparatus. Further, the first embodiment or the second embodiment can also be applied to control of a movable part in a conveyance mechanism that conveys an article, for example, a hand that holds an article.

<Embodiment of the manufacturing method of an article>

The method for manufacturing an article according to an embodiment of the present invention is suitable for manufacturing a flat panel display (FPD), for example. The article manufacturing method of the present embodiment includes a step of forming a latent image pattern on a photosensitive agent applied on a substrate using the exposure device (step of exposing the substrate), and a step of developing the substrate on which the latent image pattern is formed in this step. do. In addition, this manufacturing method includes other well-known processes (oxidation, film formation, vapor deposition, doping, planarization, etching, resist removal, dicing, bonding, packaging, etc.). The article manufacturing method of the present embodiment is advantageous in terms of at least one of article performance, quality, productivity, and production cost, compared to conventional methods.

As mentioned above, although the preferable embodiment of this invention was described, this invention is not limited to these embodiment, and various modifications and changes are possible within the scope of the summary.

The present invention is not limited to the above embodiments, and various changes and modifications are possible without departing from the spirit and scope of the present invention. Accordingly, the following claims are appended to clarify the scope of the present invention.

This application claims priority based on Japanese Patent Application No. 2020-205546 filed on December 11, 2020, and all of the contents of the description are incorporated herein.

Claims (23)

A control device that generates a control signal for controlling a control target,
A first compensator for generating a first signal based on the control deviation of the control target;
a compensator for correcting the control deviation using one of a plurality of adjusting units generating a correction signal by correcting the control deviation according to an arithmetic expression capable of adjusting coefficients;
a second compensator for generating a second signal by a neural network based on the correction signal;
An operator for generating the control signal based on the first signal and the second signal
A control device comprising a. According to claim 1,
In the compensator, an adjusting unit used for correcting the control deviation is selected from the plurality of adjusting units based on a control state of the control object. According to claim 1 or 2,
An adjustment unit used for correcting the control deviation is selected from the plurality of adjustment units based on whether or not the control target and a control target different from the control target are synchronized and controlled. According to claim 1 or 2,
An adjustment unit used for correcting the control deviation is selected from the plurality of adjustment units based on whether or not the gain switching of the control target is occurring. According to claim 1 or 2,
The controller according to claim 1 , wherein an adjusting unit to be used for correcting the control deviation is selected from the plurality of adjusting units based on a state of the first compensator. According to claim 1 or 2,
The controller according to claim 1 , wherein an adjustment unit used for correcting the control deviation is selected from the plurality of adjustment units based on whether or not the operation pattern of the control object is changing. According to any one of claims 1 to 6,
The control device according to claim 1, wherein the arithmetic expression includes a term proportional to the control deviation. According to any one of claims 1 to 7,
The control device characterized in that the arithmetic expression includes a term for performing an integral on the control deviation. According to any one of claims 1 to 8,
The control device according to claim 1, wherein the arithmetic expression includes a term for differentiating the control deviation. According to any one of claims 1 to 6,
The control device characterized in that the arithmetic expression includes at least one of a term proportional to the control deviation, a term for performing integration, and a term for performing differentiation. According to any one of claims 1 to 10,
Further comprising a setting unit for adjusting the compensator,
The control device according to claim 1 , wherein the setting unit selects an adjusting unit to be used for correcting the control deviation from the plurality of adjusting units. According to claim 11,
The control device according to claim 1 , wherein the setting unit sets the arithmetic expression. According to claim 11 or 12,
The control device according to claim 1 , wherein the setting unit resets the coefficient of the arithmetic expression when the control deviation satisfies a predetermined condition. According to claim 13,
The control device according to claim 1, wherein the predetermined condition includes that the control deviation exceeds a predetermined value. According to any one of claims 1 to 14,
and a learning unit that determines parameter values of the neural network by machine learning. According to any one of claims 1 to 15,
The control signal is a signal obtained by correcting the first signal based on the second signal,
Compared to the difference between the control amount resulting from controlling the control object based on the first signal and the target value for controlling the control object, the control amount resulting from controlling the control object based on the control signal and the control object are controlled. A control device characterized in that the difference between target values for A control device that generates a control signal for controlling a control target,
A first compensator for generating a first signal based on the control deviation of the control target;
a compensator for correcting the control deviation by using one of a plurality of adjusting units generating a correction signal by correcting the control deviation according to an arithmetic expression;
a second compensator for generating a second signal by a neural network based on the correction signal;
An operator for generating the control signal based on the first signal and the second signal
A control device comprising a. According to claim 17,
In the compensator, an adjustment unit to be used for correcting the control deviation is selected from the plurality of adjustment units based on a control state of the control object. The method of claim 17 or 18,
The control device characterized in that the arithmetic expression includes at least one of a term proportional to the control deviation, a term for performing integration, and a term for performing differentiation. A stage control device for controlling a stage that holds and supports the object in order to control the position of the object,
A stage control device comprising the control device according to any one of claims 1 to 19. A lithography apparatus for transferring a pattern of an original plate onto a substrate,
A lithographic apparatus comprising a control device according to any one of claims 1 to 19 configured to control the position of said substrate or said original plate. a transfer step of transferring a pattern of the original plate onto a substrate using the lithography apparatus according to claim 21;
A treatment process of treating the substrate that has gone through the transfer process
including,
A method for manufacturing an article, characterized in that an article is obtained from the substrate subjected to the treatment step. a first compensator generating a first signal based on a control deviation of a control target; a compensator correcting the control deviation using one of a plurality of adjusting units generating a correction signal by correcting the control deviation; An adjustment method for adjusting a control device comprising a second compensator for generating a second signal by a neural network based on a correction signal, and an calculator for generating a control signal based on the first signal and the second signal. ,
In the compensator, an adjustment step of selecting an adjustment unit to be used for correcting the control deviation from the plurality of adjustment units based on a control state of the control object.
characterized in that the adjustment method.

Images