JP2021051200A - Determination device - Google Patents

Abstract

To provide a determination device that can determine the necessity of maintenance of a substrate treatment device.SOLUTION: A determination device performs classification on alignment failure factors with respect to image data of a mark on a substrate captured in a substrate treatment device, using a learning model obtained by machine learning and determines the necessity of maintenance of the substrate treatment device on the basis of the results of classification.SELECTED DRAWING: Figure 3

Description

The present invention relates to a determination device, a substrate processing apparatus, a substrate processing system, and a method for manufacturing an article.

In recent years, with the miniaturization of electronic devices and the expansion of demand, it is necessary to achieve both miniaturization and productivity of semiconductor elements represented by memories and MPUs.
Therefore, in a substrate processing apparatus for processing a substrate used for manufacturing a semiconductor element, it is necessary to improve the accuracy of alignment for aligning the positions of the substrates.

In the alignment of the substrate, a method of obtaining the position of the substrate by taking an image of a mark formed on the substrate and performing a pattern matching process on the obtained image data is often used.
Patent Document 1 discloses an exposure apparatus that accurately detects a mark by simultaneously extracting the edge of the mark and the direction of the edge and performing pattern matching processing focusing on the edge for each direction of the edge. ..

Japanese Unexamined Patent Publication No. 2000-260669

Conventionally, when a substrate alignment fails in a substrate processing apparatus, the user determines whether it is necessary to maintain the apparatus by referring to image data or related data related to the image data.
Therefore, in some cases, the processing of the device is interrupted or it takes time to make a judgment, which causes a decrease in throughput.
Therefore, an object of the present invention is to provide a determination device capable of determining whether or not it is necessary to maintain the substrate processing apparatus.

The determination device according to the present invention classifies the image data of the marks on the substrate imaged by the substrate processing apparatus with respect to the alignment failure factors using the learning model acquired by machine learning, and is based on the classification result. It is characterized in that it is determined whether or not it is necessary to maintain the substrate processing apparatus.

According to the present invention, it is possible to provide a determination device capable of determining whether or not it is necessary to maintain the substrate processing apparatus.

The block diagram which shows the structure of the substrate processing system which concerns on 1st Embodiment. The schematic diagram which shows the structure of the exposure apparatus provided in the substrate processing system which concerns on 1st Embodiment. The figure which shows the structure for determining whether maintenance is necessary in the substrate processing system which concerns on 1st Embodiment. The figure which shows typically the screen displayed on the display device in the substrate processing system which concerns on 1st Embodiment. The figure which shows exemplary the screen of creating the learning data in the substrate processing system which concerns on 1st Embodiment. The flowchart which shows the process of creating the learning data in the substrate processing system which concerns on 1st Embodiment. The figure which shows exemplary the button which displays the learning data creation screen in the substrate processing system which concerns on 1st Embodiment. The figure which shows the structure for determining whether maintenance is necessary in the substrate processing system which concerns on 2nd Embodiment.

Hereinafter, the determination device according to the present embodiment will be described in detail with reference to the drawings. It should be noted that the embodiments shown below are merely specific examples of the embodiments, and the present embodiments are not limited to the following embodiments.
In addition, not all combinations of features described in the following embodiments are essential for solving the problems of the present embodiment.
In addition, the drawings shown below may be drawn at a scale different from the actual one so that the present embodiment can be easily understood.

[First Embodiment]
When manufacturing devices such as semiconductor elements, liquid crystal display elements, and thin film magnetic heads using photolithography technology, exposure that projects the pattern of the original plate such as a reticle onto a substrate such as a wafer by a projection optical system and transfers the pattern. The device is in use.

In exposure equipment, it is necessary to achieve both miniaturization and productivity of semiconductor elements such as memories and MPUs as electronic devices become smaller and demand increases.
Therefore, the exposure apparatus is required to improve basic performance such as resolution, overlay accuracy, and throughput.

Since the resolution of the exposure device is inversely proportional to the numerical aperture (NA) of the projection optical system and proportional to the wavelength of the light (exposure light) used for exposure, the numerical aperture of the projection optical system can be increased and the wavelength of the exposure light can be shortened. It is progressing.
Further, as the semiconductor element becomes finer, it is necessary to improve the overlay accuracy, so that the alignment for aligning the relative positions of the original plate and the substrate also needs to be improved.

Further, as a technique for further improving the overlay accuracy, a technique for controlling variations in the semiconductor manufacturing process, changes over time, etc. by feedforward or the like is known. As such a technique, specifically, AEC (Advanced Equipment Control), APC (Advanced Process Control) and the like are known. Further, there is known a technique of learning the result measured by an inspection device by machine learning and feeding it back to a lithography device or a coating / developing device (coater / developer).

The reason why the alignment measurement fails in the exposure device is that the mark is located in the measurement field of view but is not clear due to the process failure of the substrate or the influence of the aberration of the scope, or the mark formation position is significantly deviated. Various things can be considered, such as not being within the measurement field of view.
If the position of the mark is significantly deviated in the measurement field of view, the mark depends on factors derived from the exposure device such as misalignment when the exposure device receives the substrate, or the processing process of the substrate in a device other than the exposure device. Factors other than those derived from the exposure device, such as position fluctuations, are considered.
Therefore, when there are multiple possible causes for failing the alignment measurement, the coping method including maintenance differs depending on each failure factor.
Therefore, when performing maintenance of the exposure apparatus, it is necessary to accurately classify the failure factors and make an accurate judgment based on them.

FIG. 1 is a block diagram showing a configuration of a substrate processing system 50 provided with a determination device according to the first embodiment.

The substrate processing system 50 includes at least one semiconductor manufacturing line 1.
Each semiconductor manufacturing line 1 includes a plurality of substrate processing devices 10 (semiconductor manufacturing devices) that process substrates, and a host computer 11 (host control device) that controls the operation of the plurality of substrate processing devices 10. ..
Examples of the substrate processing apparatus 10 include a lithography apparatus (exposure apparatus, imprint apparatus, charged particle beam drawing apparatus, etc.), a film forming apparatus (CVD apparatus, etc.), a processing apparatus (laser processing apparatus, etc.), and an inspection apparatus (overlay inspection). Equipment, etc.).
The substrate processing apparatus 10 also includes a coating developer (coater / developer) that applies a resist material (adhesive material) to the substrate as a pretreatment for the lithography process and also performs a developing process as a post-processing for the lithography process. It can be.

In the exposure apparatus, by exposing the photoresist supplied on the substrate through the original plate (reticle, mask), a latent image corresponding to the pattern of the original plate is formed on the photoresist on the substrate.
In the imprinting apparatus, a pattern is formed on the substrate by curing the imprinting material in a state where the original plate (mold, template) is in contact with the imprinting material supplied on the substrate.
In the charged particle beam drawing apparatus, a latent image is formed on the photoresist on the substrate by drawing a pattern on the photoresist supplied on the substrate by the charged particle beam.

As shown in FIG. 1, each of the plurality of substrate processing devices 10 provided in each semiconductor manufacturing line 1 is connected to a management device 12 that manages maintenance.
As a result, the management device 12 can manage a plurality of substrate processing devices 10 provided in each semiconductor manufacturing line 1.
The determination device according to the present embodiment is provided in any of the substrate processing device 10, the host computer 11, and the management device 12.

In the board processing system 50, the connection between the plurality of board processing devices 10 and the host computer 11 and the connection between the plurality of board processing devices 10 and the management device 12 can be either a wired connection or a wireless connection. I do not care.

Next, a specific example in which each substrate processing apparatus 10 is configured as an exposure apparatus in the substrate processing system 50 will be described.

FIG. 2A is a block diagram showing the configuration of the exposure apparatus 10 provided in the substrate processing system 50. Further, FIG. 2B is a schematic view showing the configuration of the substrate alignment optical system 190 included in the exposure apparatus 10.

The exposure apparatus 10 is a lithography apparatus used for manufacturing devices such as semiconductor elements, liquid crystal display elements, and thin film magnetic heads as articles, and performing pattern formation on a substrate.
Further, the exposure apparatus 10 exposes the substrate by a step-and-scan method or a step-and-repeat method.

As shown in FIG. 2A, the exposure apparatus 10 includes a main control unit 100, a light source control unit 110, a light source 120, an image processing unit 130, a stage control unit 140, and an interferometer 150.
Further, the exposure apparatus 10 includes an original plate alignment optical system 160, an original plate stage 171 and a projection optical system 180, a substrate alignment optical system 190, and a substrate stage 200.

The original plate stage 171 holds and moves the original plate 170 illuminated by the illumination optical system (not shown). On the original plate 170, a pattern to be transferred to the substrate 210 is drawn.
The projection optical system 180 projects the pattern of the original plate 170 onto the substrate 210. The board stage 200 can hold and move the board 210.

The original plate alignment optical system 160 is used for alignment of the original plate 170. For example, the original plate alignment optical system 160 includes an image pickup element 161 composed of a storage type photoelectric conversion element, and an optical system 162 that guides light from a mark provided on the original plate 170 to the image pickup element 161.
The substrate alignment optical system 190 is used for alignment of the substrate 210. In the present embodiment, the substrate alignment optical system 190 is an off-axis optical system that detects the mark 211 provided on the substrate 210.

The main control unit 100 includes a CPU, a memory, and the like, and controls each part of the exposure apparatus 10 to perform an exposure process for exposing the substrate 210 and a process related thereto.
In the substrate processing system 50, the main control unit 100 controls the position of the substrate stage 200 based on the position of the mark formed on the original plate 170 and the position of the mark 211 formed on the substrate 210. In other words, the main control unit 100 performs alignment between the original plate 170 and the substrate 210, for example, global alignment.

The light source 120 includes a halogen lamp and the like, and illuminates the mark 211 formed on the substrate 210.
The light source control unit 110 controls the illumination intensity of the light from the light source 120, that is, the light for illuminating the mark 211.

The image processing unit 130 performs image processing on image signals (detection signals) from the image sensor 161 in the original plate alignment optical system 160 and the image sensors 191A and 191B in the substrate alignment optical system 190 to acquire the mark position, that is, the mark image. ..
In the substrate processing system 50, the image processing unit 130 and the substrate alignment optical system 190 function as measuring devices for measuring the position of the mark 211 formed on the substrate 210.

The interferometer 150 measures the position of the substrate stage 200 by irradiating the mirror 212 provided on the substrate stage 200 with light and detecting the light reflected by the mirror 212.
The stage control unit 140 moves (drives and controls) the substrate stage 200 to an arbitrary position based on the position of the substrate stage 200 measured by the interferometer 150.

In the exposure apparatus 10, light (exposure light) from an illumination optical system (not shown) passes through the original plate 170 held by the original plate stage 171 and is incident on the projection optical system 180.
Since the original plate 170 and the substrate 210 are arranged in an optically conjugate positional relationship with each other, the pattern of the original plate 170 is placed on the substrate 210 held by the substrate stage 200 via the projection optical system 180. It is imaged and transferred.

The substrate alignment optical system 190 functions as a detection unit that detects the mark 211 formed on the substrate 210 and generates a detection signal (image signal in this embodiment).
As shown in FIG. 2B, the substrate alignment optical system 190 includes image pickup devices 191A and 191B, imaging optical systems 192A and 192B, and a half mirror 193. Further, the substrate alignment optical system 190 includes an illumination optical system 194, a polarization beam splitter 195, a relay lens 196, a λ / 4 plate 197, and an objective lens 198.

In the exposure apparatus 10, the light from the light source 120 is guided to the substrate alignment optical system 190 via an optical fiber (not shown) or the like.
Then, the light guided to the substrate alignment optical system 190 is incident on the polarization beam splitter 195 via the illumination optical system 194 as shown in FIG. 2 (b).
Then, the light reflected by the polarizing beam splitter 195 passes through the relay lens 196, the λ / 4 plate 197, and the objective lens 198, and illuminates the mark 211 formed on the substrate 210.

The light reflected by the mark 211 passes through the objective lens 198, the λ / 4 plate 197, the relay lens 196, and the polarization beam splitter 195, and enters the half mirror 193.
Then, the light incident on the half mirror 193 is divided into two lights by an appropriate intensity ratio by the half mirror 193, and then guided to the imaging optical systems 192A and 192B having different imaging magnifications, respectively.

The imaging optical systems 192A and 192B form an image of the mark 211 on the image pickup surface of the image pickup devices 191A and 191B, respectively.
Each of the image pickup devices 191A and 191B includes an image pickup surface that images a region including the mark 211, and generates an image signal corresponding to the region imaged by the image pickup surface.

Then, the image signals generated by the image sensors 191A and 191B are read out by the image processing unit 130.
In the present embodiment, the image processing unit 130 acquires the position of the mark 211 on the image pickup surface of the image pickup devices 191A and 191B by performing pattern matching processing as image processing on the read image signal.

The pattern matching process is generally classified into the following two types.
One is a method in which an image (shade image) is binarized and matched with a template prepared in advance, and the position having the highest correlation is set as the position of mark 211.
The other is a method of obtaining the position of the mark 211 by performing a correlation calculation with a template including the shading information while keeping the shading image.

The image processing by the image processing unit 130 is not limited to the pattern matching processing, and may be other processing such as edge detection processing as long as it is possible to acquire the position information of the mark 211.

Further, as the alignment method, there are a movement measurement method and an image processing method.
In the movement measurement method, the mark 211 provided on the substrate 210 is irradiated with light (laser) while the substrate stage 200 is moved. Then, the position of the mark 211 is obtained by measuring the change in the intensity of the light reflected from the mark 211 and the position of the substrate stage 200 in parallel.
In the image processing method, the mark 211 provided on the substrate 210 is irradiated with white light while the substrate stage 200 is stationary. Then, the position of the mark 211 is obtained by detecting the light reflected from the mark 211 with the storage type photoelectric conversion element and performing image processing.

Further, examples of the alignment optical system used in such an alignment method include a TTL (through the lens) optical system, a TTR (through the reticle) optical system, and an off-axis optical system.
The TTL optical system detects marks provided on the substrate via the projection optical system. The TTR optical system simultaneously detects the mark provided on the reticle and the mark provided on the substrate via the projection optical system. The off-axis optical system is a dedicated optical system having an optical axis at a position separated from the optical axis of the projection optical system by a predetermined distance without going through the projection optical system, and irradiates a substrate with white light from a dedicated light source. Detects the provided mark.
As described above, the substrate alignment optical system 190 provided in the substrate processing system 50 according to the present embodiment is an off-axis optical system.

In the exposure apparatus 10, two types of alignment, pre-alignment and fine alignment, are performed using the acquired position information of the mark 211.
The term "pre-alignment" as used herein means that the substrate 210 is roughly aligned (so that fine alignment can be started by detecting the amount of misalignment of the substrate 210 sent to the substrate stage 200 from a substrate transport system (not shown)). Positioning).
Further, the fine alignment referred to here means that the position of the substrate 210 held by the substrate stage 200 is measured with high accuracy, and the substrate 210 is precisely aligned so that the alignment error of the substrate 210 is within an allowable range. (Positioning).

In the prealignment, as described above, the amount of misalignment of the substrate 210 sent to the substrate stage 200 from the substrate transfer system (not shown) must be detected.
Therefore, the substrate alignment optical system 190 that detects the mark 211 has a wide detection range (field of view) with respect to the size of the mark 211.

In order to obtain the position (XY coordinates) of the mark 211 from such a wide detection range, the pattern matching (template matching) process as described above is often used.
In the pattern matching process, it becomes difficult to detect the mark 211 for a low-contrast image, a noise image, or an image including a mark in which an abnormality has occurred when processing the substrate 210.

The measurement of the mark 211 may fail due to any factor. That is, the mark 211 may not be detected by fine alignment. Further, even if the mark 211 can be detected, the position may not be acquired for some reason in the image processing and may fail.
For example, the mark 211 may not be clear due to the influence of the processing process of the substrate 210, or the mark 211 may not be clearly visible due to the influence of the aberration of the substrate alignment optical system 190.
It is also conceivable that the position of the mark 211 deviates from the field of view of the image pickup surface of the image pickup elements 191A and 191B.

When a clear image of the mark 211 can be obtained in the field of view of the image pickup surface of the image pickup device 191A or 191B, the position of the mark 211 can be correctly measured by image processing.
However, if the contrast of the image is low or the image is distorted due to the influence of aberration, the position of the mark 211 may not be measured correctly.

Further, it is considered that the cause of the mark 211 shifting from the field of view of the image pickup surface of the image pickup devices 191A and 191B is due to the device such as erroneous measurement in prealignment and misalignment in the transfer process before measurement.
Further, it is considered that the factor of the mark 211 shifting from the field of view of the image pickup surface of the image pickup device 191A or 191B is due to the processing process of the substrate 210 such as the transfer position of the mark 211 fluctuating.

If the measurement of the mark 211 fails, the alignment of the substrate 210 cannot be performed normally.
Then, when the alignment of the substrate 210 cannot be performed normally, a maintenance process (maintenance process) for enabling the alignment to be performed normally is executed.

The maintenance process includes, for example, changing the mark to be used among the plurality of marks 211, expanding the search range of the mark image, changing the imaging conditions, and the like.

If the alignment process fails on the substrate 210, sufficient alignment accuracy cannot be achieved even if the substrate 210 is subsequently exposed.
At that time, an error is usually issued to stop the processing of the substrate 210, and work for investigating and eliminating the cause of the failure is performed.

On the other hand, if the alignment process is successful on the substrate 210, the exposure process on the substrate 210 is continuously performed, but even if the alignment process is successful, there is a possibility that sufficient alignment accuracy cannot be achieved in the exposure process.
One of the causes in such a possibility is that the calculation result for alignment with respect to the substrate 210 becomes inaccurate due to erroneous measurement of the position of the mark 211.

The erroneous measurement of the position of the mark 211 is caused by, for example, an erroneous image signal being generated due to the influence of dust adhesion or other conditions at the time of imaging in the mark image obtained by imaging the area including the mark 211. Occur.
If the position of the mark 211 is erroneously measured, an erroneous value will be used when calculating the alignment of the substrate 210.
Therefore, as a result of the calculation, even if the alignment error of the substrate 210 is within the permissible range and the alignment process is successful, the alignment accuracy is lowered during the exposure process.

3A and 3B are a block diagram and a processing flow diagram showing a configuration for determining whether the exposure apparatus 10 needs maintenance, respectively.

First, the image processing means 300 provided in the exposure apparatus 10 performs image processing on the substrate 210 to acquire a mark image (image data) (step S401).

Then, when the image processing means 300 determines that the alignment error of the substrate 210 is within the permissible range from the mark image and the alignment is successful, the exposure processing is executed by the exposure processing means 350 provided in the exposure apparatus 10. To.
Further, by adding the related data to the mark image at the same time as the exposure processing is executed, the image processing means 300 acquires the alignment data 301 and then passes it to the image classification means 400 (step S402).
Further, even when the image processing means 300 determines from the mark image that the alignment error of the substrate 210 is not within the permissible range and the alignment fails, the alignment data 301 is similarly acquired and then passed to the image classification means 400. (Step S402).

Even if the image processing means 300 determines that the alignment is successful, it may actually fail due to erroneous measurement.
In such a case, the alignment data 301 determined to be successful due to erroneous measurement may be redetermined as failed based on the overlay measurement result of the substrate 210 by an external measuring instrument (not shown).

Here, the related data is data including information related to the acquired mark image. For example, the related data may include information that identifies a configuration such as a model, a unit, a hardware configuration, a software configuration, and an installation line of the exposure apparatus 10.
In addition, the related data may include information that identifies the configuration such as lot, substrate 210, original plate 170, recipe, environmental conditions, processing date and time.
Further, the related data may include information for specifying various offset settings of the exposure apparatus 10 at the time of mark measurement, and illumination conditions such as the amount of light of the light source 120 that illuminates the mark 211 and the amount of focus of the optical system.
Further, the related data may include information for specifying the configuration such as the operating conditions at the time of alignment of the exposure apparatus 10 such as the type of the mark 211 and the position information of the stage.
Further, the related data may include information for specifying the configuration such as the immediately preceding alignment measurement result and the operating state at the time of alignment such as the pressure at which the substrate stage 200 adsorbs the substrate 210.

Further, the alignment data 301 passed to the image classification means 400 is not limited to the above, and may be the result of classifying the mark image by an image classification means (not shown) using machine learning or the like.

As described above, the alignment data 301 passed to the image classification means 400 includes any alignment data 301 determined to be successful or unsuccessful by the image processing means 300, but is limited to this. I can't.
In order to improve the throughput, only the alignment data 301 determined by the image processing means 300 that the alignment has failed may be passed to the image classification means 400.

Further, the number of marks 211 measured in step S401 may be one or more, and the number of alignment data 301 passed to the image classification means 400 may be one or more.
Further, the alignment data 301 may be delivered to the image classification means 400 in sequence each time the image processing for one mark 211 is completed. Further, the present invention is not limited to this, and all the marks 211 on the substrate 210 may be collectively performed after the image processing is completed.

Next, the image classification means 400 classifies the received alignment data 301 into one of a plurality of types related to the alignment failure factor (step S403).
The image classification means 400 can be realized by a software program executed by at least one of the main control unit 100, the management device 12, and the host computer 11 of the exposure device 10.

In the determination device according to the present embodiment, the following machine learning is used as a specific classification method of the alignment data 301 in the substrate processing system 50.

As a method for making a judgment using machine learning, there is supervised learning in which learning data is created and machine learning is performed.
Then, in supervised learning, it is necessary to create learning data (supervised data) including input data and output data which is correct data corresponding to the input data.

In the determination device according to the present embodiment, the image classification means 400 uses a learning model obtained by machine learning using a plurality of alignment data 301 in which classification type numbers are input as learning data 305.
Here, machine learning can be performed using, for example, a neural network. A neural network is a model having a multi-layered network structure such as an input layer, an intermediate layer, and an output layer.
Then, the learning model can be acquired by optimizing the random variables inside the network by an algorithm such as the error back propagation method using the learning data showing the relationship between the input data and the output data.

Here, an example of acquiring a learning model using a neural network has been described, but the present invention is not limited to this, and a learning model may be acquired using another model or algorithm such as a support vector machine or a decision tree.
Then, the image classification means 400 outputs the classification information 302 including the type number corresponding to the alignment data 301 as output data by inputting the alignment data 301 into the acquired learning model.

Next, the specific creation of the learning data in the determination device according to the present embodiment will be shown.
First, using the result of the alignment process previously performed on the substrate 210, the learning data 305 is obtained by using the alignment data 301 as input data and the classification information 302 corresponding to the classification into various different numbers as output data. create.

As the classification information 302, for example, type numbers 0 to 5 as shown in Table 1 below can be set.

It should be noted that various different numbers as shown in Table 1 may be manually provided based on the alignment data 301 when the alignment process has failed in the past, the result of the automatic recovery operation of the exposure device 10, and the like. Alternatively, various different numbers as shown in Table 1 may be automatically provided by using machine learning or the like.

As shown in Table 1, in the determination device according to the present embodiment, as the classification information 302, a factor of failure of the alignment process and a maintenance method for improving the factor are provided for each type number.
In Table 1, one factor is specified for one type number and one maintenance method is presented, but the present invention is not limited to this, and a plurality of factors are specified for one type number and a plurality of factors are specified. Conservation methods may be presented.

Specifically, the type number 0 is normal alignment data 301 that does not include the alignment failure factor, and corresponds to the classification when maintenance is not required.
Further, the type number 1 corresponds to the classification when the cause of the alignment failure cannot be identified and the maintenance method is unknown.
Further, the type number 2 corresponds to the classification when the cause of the alignment failure is the positional deviation when the substrate 210 is delivered and the maintenance method is the adjustment of the delivery position of the substrate 210.
Further, the type number 3 corresponds to the classification when the cause of the alignment failure is the setting error of the light source 120 at the time of alignment measurement and the maintenance method is the adjustment of the light source 120 at the time of alignment measurement.
Further, the type number 4 corresponds to the classification when the cause of the alignment failure is the vibration of the substrate stage 200 at the time of alignment measurement and the maintenance method is the adjustment for the vibration of the substrate stage 200 at the time of alignment measurement.
Further, the type number 5 corresponds to the classification when the cause of the alignment failure is the deterioration of the light source 120 and the maintenance method is the replacement of the light source 120.

For these classifications, the related data added in the alignment data 301 is effectively used.
The above type is an example, and other types of classification may be set.

Then, in order to create the classification information 302 as the output data, the alignment data 301 which is the input data can be classified into the type numbers 0 to 5 by the image classification means 400, and the classification information 302 can be acquired.

When the alignment data 301 is applied to the above types in a complex manner, it may be classified into the data having the highest degree of application.
Further, the present invention is not limited to this, and when the alignment data 301 is applied to the above types in a complex manner, weighting may be performed according to the degree to which the alignment data 301 is applied to each type.

In the above procedure, the learning data 305 can be created by using the alignment data 301 as input data and the classification information 302 corresponding to the classification into various different numbers as output data.
Then, the inference logic can be created by learning a plurality of alignment data 301 with type numbers.

In the above, the image classification means 400 is used to classify the alignment data 301 for creating the learning data 305, but the present invention is not limited to this.
For example, in order to create the learning data 305 required to obtain the learning model, the user can check a plurality of alignment data 301 and manually input the type number.
Further, in order to increase the correct answer rate of the classification information 302 output from the learning model, it is necessary to create the learning data 305 for a large amount of alignment data 301.

As shown in FIG. 3A, the display device 206 displays information necessary for operating the exposure device 10, information related to the operation of the exposure device 10, and the like.
FIG. 4 is a diagram schematically showing a screen 900 displayed on the display device 206.

Further, in the input device 205, information necessary for operating the exposure device 10 and information necessary for displaying the screen on the display device 206 are input by the user.
Further, by displaying the information necessary for inputting the classification type number on the display device 206, the user can input the information of the classification type number via the input device 205.

Further, in a CPU (not shown), processing by the display means 800 for displaying information on the display device 206 and the input means 810 for inputting information to the input device 205 is executed.
Further, in the CPU (not shown), the display on the display device 206 and the processing by the determination means 820 for determining whether or not the input on the input device 205 is valid are executed.

Further, the storage device 204 stores the uncreated data 801 in which the type number has not been input and the created data 802 in which the type number has been input.
The uncreated data 801 is the alignment data 301 acquired in the alignment process, and is the data for creating the learning data.
Further, the created data 802 is data to which a type number is added to the uncreated data 801 and becomes the learning data 305 input to the image classification means 400.

Here, the display device 206, the input device 205, and the storage device 204 may be provided in the exposure device 10, and are not limited to this, and may be provided in an external information processing device such as the host computer 11 and the management device 12. Absent.
Further, the display means 800 and the input means 810 can be realized by a software program executed by at least one of the main control unit 100, the management device 12, and the host computer 11 of the exposure device 10.
Further, the determination means 820 can be realized by a software program executed by at least one of the main control unit 100, the management device 12, and the host computer 11 of the exposure device 10.

The display means 800 causes the display device 206 to display the information necessary for creating the learning data 305.
FIG. 5 is a diagram illustrating an example of a screen for creating the learning data 305.

As shown in FIG. 5, the screen 910 displays information related to the data included in the uncreated data 801.
For example, the mark image 911 of the mark 211 imaged by the substrate alignment optical system 190 is displayed on the screen 910.
Further, on the screen 910, for example, the model of the exposure device 10, the installation line of the exposure device 10, the lighting conditions of the exposure device 10, the position information of the substrate stage 200, and other related data 912 when the mark 211 is imaged are displayed. ..

Further, on the screen 910, the classification information 913 indicating the classification options and the selection state indicating whether or not the classification is selected is displayed.
The selected state of the classification information 913 can be selected or not selected by using the input device 205.
When the confirmation button 914 is pressed while a certain classification is selected, the information of the selected classification for the displayed uncreated data 801 is input.
When the stop button 915 is pressed, the creation of the learning data 305 is stopped.

The display means 800 may display a plurality of uncreated data 801s, a plurality of related data 912s, and a plurality of classification information 913s on the screen 910 to select a classification for the plurality of uncreated data 801s. ..

The input means 810 acquires the selection information of the classification input from the input device 205. Then, the input means 810 associates the selection information of the classification with the uncreated data 801 stored in the storage device 204 and stores it in the storage device 204 as the created data 802.
The determination means 820 determines the start or end of the creation of the learning data 305 based on a predetermined condition. That is, the determination means 820 determines whether to start the process of causing the display means 800 to display the information for selecting the classification in the display device 206 and causing the input means 810 to input the classification selection information.
Further, the determination means 820 determines whether to end the process of displaying the information for selecting the classification in the display device 206 by the display means 800 and inputting the selection information of the classification by the input means 810.

When the created data 802 reaches a predetermined number, the image classification means 400 may additionally learn the created data 802 as the training data 305 and delete the created data 802 from the storage device 204. ..
Further, the storage device 204 may store the number of uncreated data 801 and the created data 802, and the input means 810 or the image classification means 400 may update the number of such data.

Further, the storage device 204 stores the number of each of the trained data (data added to the training data 305) and the unlearned data (data not added to the training data 305) of the created data 802. May be good. Then, the number of such data may be updated by the input means 810 or the image classification means 400.
Further, the display means 800 may display the number of such data on the display device 206.

Next, the process of creating the training data 305 will be described.
FIG. 6 is a flowchart showing a process of creating the learning data 305.

In S110, the determination means 820 determines whether to start the creation of the learning data 305 based on a predetermined condition for starting the creation of the learning data 305.
If the determination means 820 determines that the creation of the learning data 305 is not started, the process returns to S110 after a predetermined period of time has elapsed, and it is determined whether to start the creation of the learning data 305 again.

On the other hand, when the determination means 820 determines that the creation of the learning data 305 is started, the process proceeds to S111 and the creation of the learning data 305 is started.
Then, in S111, the information of the classification type number is added to the alignment data 301 included in the uncreated data 801 according to the above procedure.

Then, in S112, the alignment data 301 to which the type number is added is deleted from the uncreated data 801 and added to the created data 802.

Then, in S113, the determination means 820 determines whether to end the creation of the learning data 305 based on a predetermined condition for ending the creation of the learning data 305.
When the determination means 820 determines that the creation of the learning data 305 is not completed, the process returns to S111 and the next uncreated data 801 is displayed on the display device 206.

On the other hand, when the determination means 820 determines that the creation of the learning data 305 is finished, the display of the screen 910 is finished and the process of creating the learning data 305 is finished.

Further, the display means 800 may allow the user to determine whether to display the screen for classifying the uncreated data 801 on the display device 206.
FIG. 7 is an exemplary diagram showing a button for displaying the creation screen of the learning data 305.

The button 901 is a button for causing the user to determine whether to display the screen for classifying the uncreated data 801 on the display device 206.
The display means 800 displays the button 901 on the screen 900, and when the button is pressed by the user, the display device 206 displays a screen for classifying the uncreated data 801.

Further, the display means 800 may display a message 902 indicating the number of uncreated data 801 together with the button 901.
By displaying the message 902, the user can determine whether to start creating the learning data 305 based on the number of uncreated data 801.

Further, by providing the image classification means 400 in a device provided outside the exposure device 10 such as the management device 12, it is possible to receive the alignment data 301 from the plurality of exposure devices 10 and create the learning data 305.

Further, the image classification means 400 may store all or a part of the received alignment data 301 for a preset period or up to the upper limit of the number of cases.

Further, an arbitrary type may be selected from the plurality of types displayed in the list, and the alignment data 301 classified into the selected type and stored may be called and displayed on the screen.
Further, the number of alignment data 301 included in the selected type may be aggregated and the result may be displayed.
Further, the alignment data 301 included in the selected type may be classified by the attached related data, aggregated, and the result may be displayed.

Then, when the alignment data 301 is classified by the image classification means 400 in step S403, the classification result is displayed by the exposure device 10 or the management device 12 (step S404).

Then, based on the displayed classification result, the user or the determination device determines whether or not the maintenance process 303 is possible (determines the necessity of maintenance) (step S405).
When it is determined that the maintenance process is possible (Yes in step S405), the maintenance process 303 is executed manually or automatically (step S406). On the other hand, when it is determined that the maintenance process 303 is not possible (No in step S405), the execution determination of the maintenance process ends.
The maintenance process 303 referred to here is shown in Table 1, for example, and may be automatically executed by the device, or a warning may be displayed by the device so that the user can manually perform the maintenance process 303.

Next, it is monitored whether or not the alignment data 301 is classified again into the type number in which the maintenance process 303 has been performed, that is, whether or not the same alignment failure has occurred again even though the maintenance process 303 has been performed. (Step S407).

Then, when the alignment data 301 is classified again into the type number in which the maintenance process 303 is performed, that is, when the problem is not solved (No in step S407), the alignment data 301 is classified into another type number. Perform additional learning (step S408).
Note that this additional learning (changing the classification criteria) may be manually executed by the user or automatically executed by the device.
On the other hand, when the alignment data 301 is not classified again into the type number in which the maintenance process 303 has been performed at a predetermined time (Yes in step S407), the execution determination of the maintenance process ends.

As described above, the determination device according to the present embodiment classifies the alignment failure factor with respect to the alignment data 301 acquired by the exposure device 10 using the learning model acquired by machine learning. Then, it is determined whether or not it is necessary to maintain the exposure apparatus 10 based on the classified alignment failure factors.
As a result, it is possible to obtain a determination device capable of determining whether or not the exposure apparatus 10 needs to be maintained.

[Second Embodiment]
8 (a) and 8 (b) are a block diagram and a processing flow diagram showing a configuration for determining whether the exposure device 10 needs maintenance in the determination device according to the second embodiment, respectively.
Since the determination device according to the present embodiment has the same configuration as the determination device according to the first embodiment except that the failure determination means 430 is newly provided, the same member has the same code number. Is added, and the description is omitted.

First, the image processing means 300 provided in the exposure apparatus 10 performs image processing on the substrate 210 to acquire a mark image (image data) (step S601).

Then, when the image processing means 300 determines that the alignment error of the substrate 210 is within the permissible range from the mark image and the alignment is successful, the exposure processing is executed by the exposure processing means 350 provided in the exposure apparatus 10. To.
Further, at the same time as the exposure processing is executed, the related data is added to the mark image, so that the image processing means 300 acquires the alignment data 301 and then passes it to the image classification means 400 (step S602).
Further, even when the image processing means 300 determines from the mark image that the alignment error of the substrate 210 is not within the permissible range and the alignment fails, the alignment data 301 is similarly acquired and then passed to the image classification means 400. (Step S602).

Even if the image processing means 300 determines that the alignment is successful, it may actually fail due to erroneous measurement.
In such a case, the alignment data 301 determined to be successful due to erroneous measurement may be redetermined as failed based on the overlay measurement result of the substrate 210 by an external measuring instrument (not shown).

Here, the related data is data including information related to the acquired mark image. For example, the related data may include information that identifies a configuration such as a model, a unit, a hardware configuration, a software configuration, and an installation line of the exposure apparatus 10.
The related data may also include information specifying the configuration such as lot, substrate 210, original plate 170, recipe, environmental conditions, processing date and time.
Further, the related data may include information for specifying configurations such as various offset settings of the exposure apparatus 10 at the time of mark measurement, lighting conditions such as the amount of light of the light source 120 that illuminates the mark 211 and the focus amount of the optical system.
Further, the related data may include information for specifying the configuration such as the operating conditions at the time of alignment of the exposure apparatus 10 such as the type of the mark 211 and the position information of the stage.
Further, the related data may include information for specifying the configuration such as the immediately preceding alignment measurement result and the operating state at the time of alignment such as the pressure at which the substrate stage 200 adsorbs the substrate 210.

Further, the alignment data 301 passed to the image classification means 400 is not limited to the above, and may be the result of classifying the mark image by an image classification means (not shown) using machine learning or the like.

As described above, the alignment data 301 passed to the image classification means 400 includes, but is not limited to, any alignment data 301 determined by the image processing means 300 to be successful or unsuccessful. ..
In order to improve the throughput, only the alignment data 301 determined by the image processing means 300 that the alignment has failed may be passed to the image classification means 400.

Further, the number of marks 211 measured in step S601 may be one or more, and the number of alignment data 301 passed to the image classification means 400 may be one or more.
Further, the alignment data 301 may be delivered to the image classification means 400 in sequence each time the image processing for one mark 211 is completed. Further, the present invention is not limited to this, and all the marks 211 on the substrate 210 may be collectively performed after the image processing is completed.

Next, the image classification means 400 acquires the classification information 302 by classifying the received alignment data 301 into one of a plurality of types related to the alignment failure factor (step S603).
The image classification means 400 can be realized by a software program executed by at least one of the main control unit 100, the management device 12, and the host computer 11 of the exposure device 10.

As the classification information 302, for example, type numbers 0 to 5 as shown in Table 2 below can be set.

It should be noted that various different numbers as shown in Table 2 may be manually provided based on the alignment data 301 when the alignment process has failed in the past, the result of the automatic recovery operation of the exposure device 10, and the like. Alternatively, various different numbers as shown in Table 2 may be automatically provided by using machine learning or the like.

As shown in Table 2, in the determination device according to the present embodiment, as the classification information 302, a factor of failure of the alignment process and a maintenance method for improving the factor are provided for each type number.

Specifically, the type number 0 is normal alignment data 301 that does not include the alignment failure factor, and corresponds to the classification when maintenance is not required.

Further, the type number 1 corresponds to the classification when the cause of the alignment failure cannot be identified and the maintenance method is unknown.
Further, the type number 2 is a misalignment when the substrate 210 is delivered as an alignment failure factor, or a position change of the mark 211 depending on the processing process of the substrate 210. In the former case, the maintenance method is the delivery of the substrate 210. It corresponds to the classification when the position is adjusted.
Further, the type number 3 corresponds to the classification when the cause of the alignment failure is the setting error of the light source 120 at the time of alignment measurement and the maintenance method is the adjustment of the light source 120 at the time of alignment measurement.
Further, the type number 4 corresponds to the classification when the cause of the alignment failure is the vibration of the substrate stage 200 at the time of alignment measurement or the decrease in contrast depending on the processing process of the substrate 210. Then, when the alignment failure factor is the former, it corresponds to the classification when the maintenance method is the adjustment for the vibration of the substrate stage 200 at the time of alignment measurement.
Further, the type number 5 corresponds to the classification when the cause of the alignment failure is the deterioration of the light source 120 and the maintenance method is the replacement of the light source 120.

For these classifications, the related data added in the alignment data 301 is effectively used.
The above type is an example, and other types of classification may be set.

When the alignment data 301 is applied to the above types in a complex manner, it may be classified into the data having the highest degree of application.
Further, the present invention is not limited to this, and when the alignment data 301 is applied to the above types in a complex manner, weighting may be performed according to the degree to which the alignment data 301 is applied to each type.

In the determination device according to the first embodiment, as shown in Table 1, one factor was specified for one type number, and one maintenance method was presented.
However, in the determination device according to the present embodiment, as shown in Table 2, there are cases where a plurality of factors are specified for one type number and a maintenance method is presented for each factor. is there.

For example, in the type number 2 shown in Table 2, the cause of the alignment failure is "misalignment when delivering the substrate 210" which is a factor derived from the exposure apparatus 10, or "processing process of the substrate 210" which is a factor derived from the substrate processing process. The position variation of the mark 211 depending on the above is specified.
This means that the existing alignment data 301 alone cannot narrow down the alignment failure factor to one.

For example, consider a case where the position of the mark 211 is greatly deviated in the mark image included in the alignment data 301.

At this time, alignment failure occurs because the position of the mark 211 is so large that it cannot be measured by the pattern matching process of the exposure apparatus 10.
Then, it is assumed that the alignment data 301 is classified into the type number 2 based on the fact that the position of the mark 211 is largely deviated by the classification by the image classification means 400.

At this time, depending on the factors specified in the type number 2, restoration can be performed by maintaining the exposure apparatus 10.
That is, when this alignment failure is caused by the receiving position of the substrate 210 in the exposure apparatus 10 being displaced, the recovery can be performed by adjusting the receiving position of the substrate 210 in the exposure apparatus 10.
However, when the position of the mark 211 varies depending on the processing process of the substrate 210, that is, when the mark 211 is formed at a displaced position on the substrate 210, the substrate processing process in an apparatus other than the exposure apparatus 10 is taken into consideration. Adjustment is required. Therefore, it cannot be restored by the maintenance process of the exposure apparatus 10.

In the determination device according to the present embodiment, when the alignment data 301 is classified into the type numbers in which a plurality of factors are suspected by the image classification means 400 as described above, the failure determination means 430 is used.
That is, the image classification means 400 passes the classification information 302 so classified to the failure determination means 430, and determines whether the factor is derived from the exposure apparatus (step S604).
Here, the failure determination means 430 can be realized by, for example, a software program executed in the management device 12.

Table 3 exemplifies the number of times a plurality of mark images acquired in the past predetermined number of failures of alignment processing are classified into various different numbers for each exposure device.

As described above, the alignment failure factor may be different depending on the exposure device, that is, the alignment operation conditions such as the type of the light source 120 used at the time of alignment measurement and the shape of the mark 211 may depend on the device.
Therefore, the failure determination means 430 makes a determination by comparing the classification information 302 acquired by the same number of alignment processes in the past between the exposure devices as shown in Table 3.

For example, paying attention to the type number 2 in Table 3, it can be seen that the number of times classified by the exposure apparatus EQ2 is significantly larger than that of other exposure apparatus.
Therefore, when the alignment data 301 classified in the type number 2 is acquired by the exposure apparatus EQ2, the failure determination means 430 identifies the above comparison result, that is, the factor derived from the exposure apparatus. The determination result 431 is returned to the image classification means 400.

Then, the image classification means 400 selects an appropriate alignment failure factor from the specified plurality of alignment failure factors based on the determination result 431, that is, further classifies, and outputs the classification information 302 (step S605). ..
That is, when the image classification means 400 classifies the alignment data 301 acquired by the exposure apparatus EQ2 into the type number 2, the image classification means 400 classifies that the alignment failure factor is the misalignment when the substrate 210 is delivered. Then, it can be classified that the maintenance method is the adjustment of the delivery position of the substrate 210.

The determination by the failure determination means 430 is based on the fact that the median value or the average value of the number of times classified by each exposure device is calculated, and the difference from the number of times classified by the predetermined exposure device exceeds the threshold value. You may go.
Further, in the determination by the failure determination means 430, assuming that the number of times classified by a predetermined device is x and the average value and standard deviation of the number of times classified by each exposure device are μ and σ, respectively, the test statistic | x−μ This may be done because | / σ exceeds the threshold.
Further, the determination method in the failure determination means 430 is not limited to the above, and it is also possible to adopt a method of statistically selecting outliers.

Further, in the determination device according to the present embodiment, the determination in the failure determination means 430 is performed by comparing the classifications of the same number of mark images acquired by each exposure apparatus, but the determination is not limited to this. For example, the determination by the failure determination means 430 may be performed by comparing the classifications of the mark images acquired within the same period in each exposure apparatus.
Further, the determination by the failure determination means 430 may be limited to the mark image acquired by the alignment process performed under specific operating conditions such as a predetermined alignment mode or recipe. That is, the determination in the failure determination means 430 may be performed by comparing the classifications of the mark images acquired under the same operating conditions in each substrate processing apparatus.

Then, when the classification information 302 is output by the image classification means 400 in step S605, the classification result is displayed by the apparatus (step S606).

Then, based on the displayed classification result, the user or the device determines whether or not the maintenance process 303 is possible (step S607).
When it is determined that the maintenance process 303 is possible (Yes in step S607), the maintenance process 303 is manually or automatically executed (step S608). On the other hand, when it is determined that the maintenance process 303 is not possible (No in step S607), the execution determination of the maintenance process ends.
The maintenance process 303 referred to here is shown in Table 2, for example, and may be automatically executed by the device, or a warning may be displayed by the device so that the user can manually perform the maintenance process 303.

Next, it is monitored whether or not the alignment data 301 is classified again into the type number in which the maintenance process 303 has been performed, that is, whether or not the same alignment failure has occurred again even though the maintenance process 303 has been performed. (Step S609).

Then, when the alignment data 301 is classified again into the type number in which the maintenance process 303 has been performed, that is, when it is determined that the problem has not been solved (No in step S609), one of the following two is executed. ..
That is, the image classification means 400 performs additional learning so as to classify the alignment data 301 into another type number (changes the classification criteria), or changes the threshold value in the determination in step S604 (changes the determination criteria). ) (Step S610).
The additional learning in step S610 may be manually executed by the user or automatically executed by the device. Further, the change of the threshold value in step S610 may be manually executed by the user, or may be automatically executed by the device using machine learning or the like.

On the other hand, when the alignment data 301 is not classified again into the type number in which the maintenance process 303 has been performed at the predetermined time (Yes in step S609), the execution determination of the maintenance process ends.

As described above, in the determination device according to the present embodiment, the alignment data 301 acquired by the exposure device 10 is classified according to the alignment failure factor using the learning model acquired by machine learning, and each exposure device is used. The classifications in 10 are compared with each other.
As a result, it is determined whether the classified alignment failure factor is derived from the exposure apparatus 10, and it is determined whether it is necessary to maintain the exposure apparatus 10 based on the determination.

As a result, it is possible to obtain a determination device capable of determining whether or not the exposure apparatus 10 needs to be maintained with higher accuracy.

[Manufacturing method of goods]
The method for manufacturing an article using the determination device according to the present embodiment is suitable for manufacturing an article such as a device (semiconductor element, magnetic storage medium, liquid crystal display element, etc.), for example.
Further, the method for manufacturing an article according to the present embodiment includes a step of exposing a substrate coated with a photosensitizer (forming a pattern on the substrate) using an exposure apparatus 10, and developing the exposed substrate (not shown). It includes a step of developing (processing a substrate) using an apparatus.

In addition, the production method according to the present embodiment may include other well-known steps (oxidation, film formation, vapor deposition, doping, flattening, etching, resist peeling, dicing, bonding, packaging, etc.).
The method for producing an article according to the present embodiment is advantageous in at least one of the performance, quality, productivity and production cost of the article as compared with the conventional method.

Although the preferred embodiments have been described above, it goes without saying that the embodiments are not limited to these embodiments, and various modifications and changes can be made within the scope of the gist thereof.
Further, although the exposure apparatus has been described as an example of the substrate processing apparatus 10, the present invention is not limited to this.
For example, as an example of the substrate processing apparatus 10, an imprint apparatus that forms a pattern of an imprint material on a substrate using a mold may be used.

Further, as an example of the substrate processing apparatus 10, a drawing apparatus may be used in which a pattern is formed on the substrate by drawing on the substrate with a charged particle beam (electron beam, ion beam, etc.) via a charged particle optical system.
Further, the substrate processing apparatus 10 is an imprint apparatus or the like as described above in the manufacture of articles such as devices such as a coating apparatus for applying a photosensitive medium on the surface of a substrate, a developing apparatus for developing a substrate on which a pattern is formed, and the like. It may also include manufacturing equipment that performs steps other than those performed by the equipment.

The scope of the present embodiment also includes a method and a program for carrying out the embodiment shown above, and a computer-readable recording medium on which the program is recorded.

10 Board processing device 12 Management device (judgment device)
210 Board 211 Mark 301 Alignment data (image data)

Claims (19)

The image data of the marks on the substrate captured by the substrate processing apparatus are classified regarding the causes of alignment failure using a learning model acquired by machine learning, and the substrate processing apparatus is maintained based on the result of the classification. A judgment device characterized in determining whether or not it is necessary to do so. The determination device according to claim 1, wherein the determination device classifies the alignment data obtained by adding related data including information related to the image data to the image data. The determination device according to claim 1 or 2, wherein the determination device performs the classification by comparing the classifications among a plurality of the substrate processing devices. The determination device according to claim 3, wherein the determination device determines whether or not the alignment failure factor is derived from the substrate processing apparatus by the comparison. The determination device is characterized in that it determines whether or not the alignment failure factor is derived from the substrate processing apparatus by comparing the classifications of the same number of image data acquired in each substrate processing apparatus. The determination device according to 4. The determination device is characterized in that it determines whether or not the alignment failure factor is derived from the substrate processing apparatus by comparing the classifications of the image data acquired within the same period in each substrate processing apparatus. Item 4. The determination device according to item 4. The determination device is characterized in that it determines whether the alignment failure factor is derived from the substrate processing apparatus by comparing the classification of the image data acquired under the same operating conditions in each substrate processing apparatus. The determination device according to any one of claims 4 to 6. The invention according to any one of claims 4 to 7, wherein the determination device executes maintenance processing on the substrate processing apparatus when it is determined that the alignment failure factor is derived from the substrate processing apparatus. Judgment device. The determination device determines whether or not the alignment failure factor has been eliminated after executing the maintenance process, and if not, a reference for determining whether or not the alignment failure factor is derived from the substrate processing apparatus. The determination device according to claim 8, wherein the determination device is changed. Any of claims 1 to 9, wherein the determination device classifies the image data and then executes maintenance processing on the substrate processing device based on a maintenance method corresponding to the classified alignment failure factors. The judgment device according to one item. The tenth aspect of the present invention, wherein the determination device determines whether or not the alignment failure factor has been eliminated after executing the maintenance process, and if not eliminated, changes the criteria for the classification. Judgment device. The determination device according to any one of claims 1 to 11, wherein the determination device displays at least one of the result of the classification and the maintenance method corresponding to the result. The determination device according to any one of claims 1 to 12, wherein the determination device performs the classification only on image data in which alignment processing has failed among the image data. Any one of claims 1 to 13, wherein the substrate processing apparatus is an exposure apparatus that exposes the substrate so that a pattern formed on the original plate is transferred onto the substrate using exposure light. Judgment device described in. A substrate processing apparatus for processing a substrate, the substrate processing apparatus comprising the determination apparatus according to any one of claims 1 to 14. A step of processing a substrate using the substrate processing apparatus according to claim 15.
A method for producing an article, which comprises producing the article from the processed substrate. Multiple board processing devices that process boards,
A host computer that controls the operation of the plurality of board processing devices, and
A management device that manages the maintenance of the plurality of board processing devices, and
With
The substrate processing system, wherein the management device includes the determination device according to any one of claims 1 to 14. A process of classifying alignment failure factors using a learning model acquired by machine learning for image data of marks on a substrate captured by a substrate processing apparatus.
A step of determining whether the substrate processing apparatus needs to be maintained based on the result of the step of performing the classification, and a step of determining whether or not the substrate processing apparatus needs to be maintained.
A judgment method characterized by having. A computer-readable recording medium on which a program that causes a computer to determine the need for maintenance is recorded.
A process of classifying alignment failure factors using a learning model acquired by machine learning for image data of marks on a substrate captured by a substrate processing apparatus.
A step of determining whether the substrate processing apparatus needs to be maintained based on the result of the step of performing the classification, and a step of determining whether or not the substrate processing apparatus needs to be maintained.
A computer-readable recording medium on which a program is recorded, characterized in that the program is executed by a computer.

Images