TWI829962B - Judgment device, substrate processing device, article manufacturing method, substrate processing system, judgment method, and computer-readable recording medium - Google Patents

Abstract

In order to provide a judgment device that can judge whether it is necessary to maintain the substrate processing apparatus, the judgment device according to the present invention performs comparison with the image data of the mark on the substrate captured by the substrate processing apparatus using a learning model obtained through machine learning. The quasi-failure factors are classified, and based on the classification results, it is judged whether it is necessary to maintain the substrate processing equipment.

Description

Judgment device, substrate processing device, article manufacturing method, substrate processing system, judgment method, and computer-readable recording medium

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

In recent years, as electronic equipment has been miniaturized and demand has expanded, it has been necessary to achieve both miniaturization and productivity of semiconductor elements represented by memories and MPUs.

Therefore, in a substrate processing apparatus that processes a substrate used in manufacturing semiconductor elements, it is also necessary to achieve high accuracy in alignment for positioning the substrate.

In the alignment of substrates, a technique of taking an image of a mark formed on the substrate and performing pattern matching processing on the obtained image data to determine the position of the substrate is widely used.

Japanese Patent Application Publication No. 2000-260699 discloses an exposure device that simultaneously extracts the edge of a mark and the direction of the edge, and performs pattern matching processing focusing on the edge for each edge direction, thereby detecting the mark with high accuracy.

Conventionally, when alignment of a substrate in a substrate processing apparatus fails, the user determines whether a security device is required by referring to image data and related data associated with the image data.

Therefore, depending on the situation, the processing of the device is interrupted or time is required for the judgment, resulting in a reduction in the throughput.

Therefore, an object of the present invention is to provide a determination device capable of determining whether maintenance of a substrate processing apparatus is necessary.

The judgment device according to the present invention uses a learning model obtained through machine learning to classify the image data of the mark on the substrate captured in the substrate processing apparatus, and performs classification on the alignment failure factors, and determines whether or not based on the classification result. The substrate processing equipment needs to be preserved.

Hereinafter, the determination device according to this embodiment will be described in detail with reference to the drawings. In addition, the embodiment shown below only shows the specific example of implementation, and this embodiment is not limited to the following embodiment. In addition, not all combinations of features described in the embodiments shown below are necessary to solve the problems of this embodiment. In addition, in the drawings shown below, in order to make this embodiment easy to understand, they may be drawn on a scale different from the actual scale.

[First Embodiment] When using photolithography technology to manufacture devices such as semiconductor elements, liquid crystal display elements, and thin-film magnetic heads, an exposure device is used that projects a pattern of a master such as a reticle through a projection optical system onto a substrate such as a wafer to transfer the pattern.

In exposure equipment, along with the miniaturization and expansion of demand for electronic equipment, it is necessary to simultaneously improve the miniaturization and productivity of semiconductor elements represented by memories and MPUs. Therefore, in the exposure apparatus, it is required to improve basic performance such as resolution, overlay accuracy, and throughput.

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 used for exposure (exposure light). Therefore, the numerical aperture of the projection optical system is expanded and the wavelength of the exposure light is shortened. is developing. In addition, as semiconductor elements become miniaturized, coverage accuracy also needs to be improved, so alignment to align the relative positions of the original plate and the substrate also needs to be highly accurate.

In addition, as a technique for further improving the coverage accuracy, a technique for controlling deviation fluctuations, temporal changes, etc. in the semiconductor process through feedforward and the like is known. As such technology, specifically, AEC (Advanced Equipment Control, advanced equipment control), APC (Advanced Process Control, advanced process control), etc. are known. In addition, there is known a technology in which the results measured in the inspection device are learned through machine learning and fed forward to the photolithography device and the coating and developing device (coater/developer).

Factors that may cause alignment measurement failure in the exposure device include poor processing of the substrate, aberration of the range display, whereby the mark is not clear even though it is within the measurement field of view, or the formation position of the mark is significantly shifted and is not within the measurement field. Various factors such as within the field of view. When the position of the mark within the measurement field of view is significantly shifted, consider factors such as positional shift when the exposure apparatus receives the substrate, factors caused by the exposure apparatus, and positional changes of the mark that depend on the processing procedures of the substrate in devices other than the exposure apparatus. etc. due to factors other than the exposure device. Therefore, when a plurality of factors are considered as the causes of alignment measurement failure, the handling method including maintenance will be different according to each failure factor. Therefore, when maintaining the exposure apparatus, it is necessary to correctly classify failure factors and make correct judgments based on these.

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

The substrate processing system 50 includes at least one semiconductor production line 1 . Furthermore, each semiconductor production line 1 includes a plurality of substrate processing apparatuses 10 (semiconductor manufacturing apparatuses) that process substrates, and a host computer 11 (main control apparatus) that controls the operations of the plurality of substrate processing apparatuses 10 . Examples of the substrate processing apparatus 10 include photolithography apparatuses (exposure apparatuses, imprinting apparatuses, charged particle beam drawing apparatuses, etc.), film forming apparatuses (CVD apparatuses, etc.), processing apparatuses (laser processing apparatuses, etc.), and inspection apparatuses. Devices (coverage inspection devices, etc.). In addition, the substrate processing apparatus 10 may further include a coating and developing device (coater/developer) for applying a resist material (adhesive material) to the substrate as a pre-processing process for the photolithography process, and as a photolithography process. Develop after the engraving process.

In addition, in the exposure device, the photoresist supplied to the substrate is exposed through the original plate (reduction mask, mask), and a pattern corresponding to the original plate is formed in the photoresist on the substrate. latent image. In the imprint device, a pattern is formed on the substrate by hardening the imprint material while the original plate (mold, template) is in contact with the imprint material supplied on the substrate. In a charged particle beam drawing apparatus, a charged particle beam is used to draw a pattern on the photoresist supplied on the substrate, thereby forming a latent image on the photoresist on the substrate.

As shown in FIG. 1 , a plurality of substrate processing devices 10 installed in each semiconductor production line 1 are respectively connected to a management device 12 for management and maintenance. Thereby, the management device 12 can separately manage the plurality of substrate processing devices 10 installed in each semiconductor production line 1 . The judgment device according to this embodiment is provided in any one of the substrate processing device 10 , the host computer 11 , and the management device 12 .

In addition, in the substrate processing system 50 , the connection between the plurality of substrate processing apparatuses 10 and the host computer 11 and the connection between the plurality of substrate processing apparatuses 10 and the management apparatus 12 may be any of wired connections and wireless connections.

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

FIG. 2A is a block diagram showing the structure of the exposure device 10 provided in the substrate processing system 50 . In addition, FIG. 2B is a schematic diagram showing the structure of the substrate alignment optical system 190 provided in the exposure apparatus 10 .

The exposure apparatus 10 is a photolithography apparatus used in the manufacture of devices such as semiconductor elements, liquid crystal display elements, and thin film magnetic heads as articles, and forms patterns on substrates. In addition, the exposure device 10 exposes the substrate in a step scanning method or a step and repeat method.

As shown in FIG. 2A , the exposure device 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 . In addition, the exposure apparatus 10 has a master alignment optical system 160, a master stage 171, a projection optical system 180, a substrate alignment optical system 190, and a substrate stage 200.

The master stage 171 moves while holding the master 170 illuminated by an illumination optical system (not shown). In the master 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 substrate stage 200 can move while holding the substrate 210 .

The master alignment optical system 160 is used for the alignment of the master 170 . For example, the master alignment optical system 160 includes an imaging element 161 composed of an accumulation-type photoelectric conversion element, and an optical system 162 that guides light from a mark provided on the master 170 to the imaging element 161 . Substrate alignment optical system 190 is used for alignment of substrate 210 . In this 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, etc., controls each unit of the exposure device 10, and performs exposure processing for exposing the substrate 210 and processing 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 master plate 170 and the position of the mark 211 formed on the substrate 210 . In other words, the main control unit 100 performs alignment, such as overall alignment, between the original plate 170 and the substrate 210 .

The light source 120 includes a halogen lamp or 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 used to illuminate the mark 211 .

The image processing unit 130 performs image processing on image signals (detection signals) from the imaging element 161 in the master alignment optical system 160 and the imaging elements 191A and 191B in the substrate alignment optical system 190, and obtains the position of the mark, i.e. label the image. In the substrate processing system 50 , the image processing unit 130 and the substrate alignment optical system 190 function as a measurement device that measures the position of the mark 211 formed on the substrate 210 .

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

In the exposure device 10 , light (exposure light) from an illumination optical system (not shown) passes through the original plate 170 held on the original plate stage 171 and enters the projection optical system 180 . Furthermore, since the original plate 170 and the substrate 210 are arranged in an optically conjugated positional relationship with each other, the pattern of the original plate 170 is imaged on the substrate 210 held on the substrate stage 200 via the projection optical system 180 and transferred.

The substrate alignment optical system 190 functions as a detection unit that detects the marks 211 formed on the substrate 210 and generates a detection signal (an image signal in this embodiment). As shown in FIG. 2B , the substrate alignment optical system 190 includes imaging elements 191A and 191B, imaging optical systems 192A and 192B, and a half mirror 193 . In addition, 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 device 10 , light from the light source 120 is introduced into the substrate alignment optical system 190 via an optical fiber (not shown) or the like. Then, as shown in FIG. 2B , the light introduced into the substrate alignment optical system 190 enters the polarization beam splitter 195 via the illumination optical system 194 . 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 split into two lights at an appropriate intensity ratio through the half mirror 193 and then introduced into the imaging optical systems 192A and 192B having mutually different imaging magnifications.

The imaging optical systems 192A and 192B form images of the mark 211 on the imaging surfaces of the imaging elements 191A and 191B, respectively. The imaging elements 191A and 191B each include an imaging surface for imaging an area including the mark 211, and generate an image signal corresponding to the area captured on the imaging surface.

Then, the image signals generated by the imaging elements 191A and 191B are read by the image processing unit 130 . In the present embodiment, the image processing unit 130 performs pattern matching processing as image processing on the read image signal to obtain the position of the mark 211 on the imaging surfaces of the imaging elements 191A and 191B.

Pattern matching processing is generally roughly divided into the following two types. One method is to binarize an image (a shading image), match it with a template prepared in advance, and use the most relevant position as the position of the mark 211 . The other method is to keep the shading image as it is and perform a correlation operation with a template containing shading information to find the position of the mark 211.

In addition, the image processing performed by the image processing unit 130 is not limited to pattern matching processing. As long as the position information of the mark 211 can be obtained, other processing such as edge detection processing may be used.

In addition, as alignment methods, there are movement measurement methods and image processing methods. In the moving 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 kept stationary. Then, the light reflected from the mark 211 is detected through an accumulation-type photoelectric conversion element and image processing is performed to determine the position of the mark 211 .

In addition, as alignment optical systems used in such alignment methods, there are TTL (through the lens) optical system, TTR (through the reticle) optical system, off-axis ( off axis) optical system. The TTL optical system detects the mark provided on the substrate via the projection optical system. The TTR optical system simultaneously detects the mark provided on the magnification mask and the mark provided on the substrate via the projection optical system. The off-axis optical system is a dedicated optical system that has an optical axis at a position a predetermined distance away from the optical axis of the projection optical system without passing through the projection optical system. It irradiates white light from a dedicated light source to detect the mark provided on the substrate. As described above, the substrate alignment optical system 190 provided in the substrate processing system 50 according to this embodiment is an off-axis optical system.

In the exposure device 10, two types of alignment, pre-alignment and precision alignment, are performed using the acquired position information of the mark 211. The pre-alignment here refers to detecting the positional deviation amount of the substrate 210 sent to the substrate stage 200 from the substrate transport system (not shown), and performing rough alignment (positioning) of the substrate 210 so that precision can be started. Align. In addition, the precision alignment referred to here refers to measuring the position of the substrate 210 held by the substrate stage 200 with high accuracy, and accurately positioning the substrate 210 so that the positioning error of the substrate 210 is within an allowable range. (position).

In the pre-alignment, as described above, it is necessary to detect the positional deviation amount of the substrate 210 sent to the substrate stage 200 from the substrate transport system (not shown). Therefore, the substrate alignment optical system 190 that detects the mark 211 has a wide detection range (field of view) for the size of the mark 211 .

In order to obtain the position (XY coordinate) of the mark 211 based on such a wide detection range, the above-mentioned pattern matching (template matching) process is often used. In the pattern matching process, it is difficult to detect the mark 211 for a low-contrast image, a noisy image, or an image including a mark that is abnormal when processing the substrate 210 .

The measurement of mark 211 sometimes fails due to some reasons. That is, the mark 211 may not be detected during precision alignment. In addition, even if the mark 211 can be detected, the image processing may fail to obtain the position due to some factors. For example, the mark 211 may be unclear due to the influence of the processing procedure of the substrate 210 , or the mark 211 may be unclear due to the influence of aberration of the substrate alignment optical system 190 . In addition, it is also considered that the position of the mark 211 deviates from the field of view of the imaging surfaces of the imaging elements 191A and 191B.

When a clear image of the mark 211 is obtained within the field of view of the imaging surface of the imaging element 191A or 191B, the position of the mark 211 can be accurately measured through image processing. However, when the contrast of the image becomes low or the image is distorted due to the influence of aberration, the position of the mark 211 may not be accurately measured.

In addition, as factors causing the mark 211 to deviate from the field of view of the imaging surfaces of the imaging elements 191A and 191B, factors caused by the device such as mismeasurement during pre-alignment and positional deviation during the transportation process before measurement may be considered. In addition, factors causing the mark 211 to deviate from the field of view of the imaging surface of the imaging element 191A or 191B may also be caused by changes in the transfer position of the mark 211 and other factors caused by the processing procedure of the substrate 210 .

If the measurement of the mark 211 fails, the substrate 210 cannot be positioned normally. Furthermore, when the substrate 210 cannot be positioned normally, a maintenance process (maintenance process) is performed to enable the alignment to be performed normally.

The preservation processing includes, for example, changing the mark 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 this time, usually, an error occurs, processing of the substrate 210 is stopped, and work is performed to investigate and eliminate the cause of the failure.

On the other hand, if the alignment process on the substrate 210 is successful, the exposure process on the substrate 210 is subsequently performed. However, even if the alignment process is successful, sufficient alignment accuracy may not be achieved in the exposure process. possibility. One possible reason for this is that the calculation result for positioning the substrate 210 becomes incorrect due to an erroneous measurement of the position of the mark 211 .

For example, in a mark image obtained by imaging an area including the mark 211 , an erroneous image signal is generated due to the adhesion of dust or the influence of other conditions during imaging, resulting in an erroneous measurement of the position of the mark 211 . If an erroneous measurement of the position of the mark 211 occurs, an erroneous value may be used in the calculation of the alignment of the substrate 210 . Therefore, as a result of calculation, even if the alignment error of the substrate 210 is within the allowable range and the alignment process is successful, the alignment accuracy is still reduced during the exposure process.

3A and 3B are respectively a block diagram and a process flowchart showing a structure for determining whether maintenance is required in the exposure device 10 .

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

Then, when the image processing means 300 determines based on the mark image that the alignment error of the substrate 210 is within the allowable range and the alignment is successful, the exposure process is executed by the exposure processing means 350 provided in the exposure device 10 . In addition, the image processing means 300 acquires the alignment data 301 by adding the related data to the mark image simultaneously with the execution of the exposure process, and then transfers the alignment data 301 to the image classification means 400 (step S402). In addition, even if the image processing means 300 determines from the mark image that the alignment error of the substrate 210 is not within the allowable range and the alignment fails, the alignment data 301 is similarly acquired and handed over to the image classification means 400 (Step S402).

Furthermore, even if the image processing means 300 determines that 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 re-determined to have failed based on the coverage measurement result of the substrate 210 measured by an external measuring instrument (not shown).

Here, the related data is data including information related to the acquired mark image. For example, the associated data may include information that determines the model, model, hardware structure, software structure, installation line, etc. of the exposure device 10 . In addition, the associated data may include information that determines the composition of the batch, substrate 210, original master 170, recipe, environmental conditions, processing date and time, etc. In addition, the related data may include information that determines the settings of various offsets of the exposure device 10 during mark measurement, the amount of light from the light source 120 that illuminates the mark 211, the focus amount of the optical system, and other lighting conditions. In addition, the related data may include information such as operating conditions for aligning the exposure device 10 such as the type of the mark 211, position information of the stage, and the like. In addition, the related data may include information that determines the immediately preceding alignment measurement result, the operating state during alignment, such as the pressure of the substrate stage 200 to absorb the substrate 210, and the like.

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

As described above, the alignment data 301 handed over to the image classification means 400 also includes any alignment data 301 that the image processing means 300 determines as alignment success or failure, but is not limited to this. In order to increase the throughput, only the alignment data 301 judged as alignment failure by the image processing means 300 may be transferred to the image classification means 400 .

In addition, the number of markers 211 measured in step S401 may be one or a plurality of them, and the number of alignment data 301 transferred to the image classification means 400 may be one or a plurality of them. In addition, each time the image processing for one mark 211 is completed, the alignment data 301 may be sequentially transferred to the image classification means 400. In addition, the present invention is not limited to this, and may be performed collectively after the image processing is completed for all the marks 211 on the substrate 210 .

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

In the determination device according to this embodiment, machine learning as shown below is used as a specific method of classifying the alignment data 301 in the substrate processing system 50 .

As a method for judgment using machine learning, there is supervised learning that creates learning data and performs machine learning. Furthermore, in supervised learning, it is necessary to create learning data (teacher data) including input data and output data that is correct answer data corresponding to the input data.

In the judgment device according to this embodiment, the image classification means 400 uses a learning model obtained by machine learning using a plurality of alignment data 301 to which classification category numbers are input as the learning data 305 . In this case, machine learning can be performed using neural networks, for example. A neural network refers to a model having a multi-layered network structure such as an input layer, an intermediate layer, and an output layer. Furthermore, by using learning data that represents the relationship between input data and output data, a learning model can be obtained by optimizing random variables within the network using algorithms such as the backpropagation algorithm.

Here, an example of using a neural network to obtain a learning model is described. However, the present invention is not limited to this, and other models and algorithms such as support vector machines and decision trees may also be used to obtain the learning model. Then, the image classification means 400 inputs the alignment data 301 to the acquired learning model, and outputs the classification information 302 including the category number corresponding to the alignment data 301 as output data.

Next, specific creation of learning data in the judgment device according to this embodiment will be described. First, learning data 305 is created by using the results of the previous alignment processing performed on the substrate 210, using the alignment data 301 as input data, and using the classification information 302 corresponding to the classification into each category number as output data.

As the classification information 302, for example, category numbers 0 to 5 shown in Table 1 below can be set. [Table 1] Category number Classified information 302 Reasons for failure Preservation method 0 None (alignment successful) without 1 Undetermined reasons without 2 Positional shift during board handover Adjustment of substrate handover position 3 The measurement light intensity is set incorrectly Adjustment of light intensity during measurement 4 Vibration of the substrate stage Adjustment of substrate stage vibration 5 Deterioration of aiming light source Alignment light source replacement : : :

In addition, each category number shown in Table 1 can be manually set based on the alignment data 301 when the alignment process failed in the past, the result of the automatic recovery operation of the exposure device 10, and the like. Alternatively, each category number shown in Table 1 may be automatically set using machine learning or the like.

As shown in Table 1, in the judgment device according to this embodiment, as the classification information 302, factors for failure of the alignment process and a preservation method for improving the factors are set for each category number. In addition, in Table 1, for one category number, one factor is determined and one preservation method is suggested. However, it is not limited to this. For one category number, multiple factors can be determined and multiple preservation methods are prompted.

Specifically, category number 0 is normal alignment data 301 that does not include the cause of alignment failure, and corresponds to the classification of cases where maintenance is not required. In addition, category number 1 corresponds to the classification of cases where the cause of alignment failure cannot be determined and the preservation method is unknown. In addition, the alignment failure factor of category number 2 corresponds to the classification of the case where the alignment failure factor is positional deviation when the substrate 210 is transferred, and the maintenance method is adjustment of the transfer position of the substrate 210 . In addition, the alignment failure factor of category number 3 is a classification response to the case where the setting error of the light intensity of the light source 120 during alignment measurement is an error, and the maintenance method is adjustment of the light intensity of the light source 120 during alignment measurement. In addition, the alignment failure factor of category number 4 is the vibration of the substrate stage 200 during alignment measurement, and the maintenance method is a classification response to the case where the vibration of the substrate stage 200 is adjusted during alignment measurement. In addition, the alignment failure factor of category number 5 corresponds to the classification of the case where 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 .

In these classifications, the associated data appended to the alignment data 301 is effectively used. In addition, the above categories are examples, and categories other than the categories may be set.

Furthermore, in order to create the classification information 302 as the output data, the alignment data 301 as the input data can be classified into category numbers 0 to 5 through the image classification means 400, and the classification information 302 can be obtained.

In addition, when the alignment data 301 is compositely suitable for the above-mentioned categories, it may be classified into the category with the greatest degree of suitability. In addition, the present invention is not limited to this. When the alignment data 301 is compositely suitable for the above-mentioned categories, the alignment data 301 may be weighted and classified according to the degree of suitability for each category.

Based on the above points, the learning data 305 can be created by using the alignment data 301 as input data and using the classification information 302 corresponding to the classification into each category number as output data. Then, by learning a plurality of alignment data 301 with category numbers attached, inference logic can be created.

In addition, in the above description, the image classification means 400 performs classification of 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 necessary to obtain the learning model, the user can confirm a plurality of alignment data 301 and manually input the category number. In addition, in order to increase the correct answer rate of the classification information 302 output from the learning model, it is necessary to create learning data 305 for a large amount of alignment data 301 .

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

In addition, in the input device 205, the user inputs information required to operate the exposure device 10, information required to cause the display device 206 to display a screen, and the like. Furthermore, by causing the display device 206 to display the information required for inputting the category number for classification, the user can input the information for the category number for classification via the input device 205 .

In addition, the CPU (not shown) executes the processing of the display means 800 for causing the display device 206 to display information, and the input means 810 for causing the input device 205 to input information. In addition, the CPU (not shown) executes the processing of the determination means 820 for determining whether the display on the display device 206 and the input on the input device 205 are valid.

In addition, the storage device 204 stores uncreated data 801 for which a category number has not been input and created data 802 for which a category number has been input. The uncreated data 801 is the alignment data 301 acquired in the alignment process, and is data used to create learning data. In addition, the created data 802 is data in which a category 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 memory device 204 may be provided in the exposure device 10, but are not limited thereto and may also be provided in external information processing devices such as the host computer 11 and the management device 12. In addition, the display means 800 and the input means 810 can be realized by a software program executed in at least one of the main control unit 100 of the exposure device 10 , the management device 12 and the host computer 11 . In addition, the determination means 820 can be realized by a software program executed in at least one of the main control unit 100 of the exposure device 10 , the management device 12 , and the host computer 11 .

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

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

In addition, on the screen 910, options indicating classification and classification information 913 indicating a selection status indicating whether the classification is selected are displayed. Regarding the selection status of the classification information 913, selection or non-selection can be input using the input device 205. When the OK button 914 is pressed while a certain category is selected, information about the selected category is input to the displayed uncreated data 801 . In addition, when the stop button 915 is pressed, the creation of the learning data 305 is stopped.

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

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

When the number of created data 802 reaches a predetermined number, the image classification means 400 may additionally learn the created data 802 as learning data 305 and delete the created data 802 from the storage device 204 . In addition, the number of pieces of uncreated data 801 and created data 802 may be stored in the storage device 204, and the number of pieces of these data may be updated through the input means 810 and the image classification means 400.

In addition, the storage device 204 may store the respective numbers of learned data (data added to the learning data 305) and unlearned data (data not added to the learning data 305) in the created data 802. Furthermore, the number of pieces of these data can also be updated through the input means 810 and the image classification means 400. In addition, the display means 800 may display the number of pieces of these data on the display device 206 .

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

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

On the other hand, if the determination means 820 determines that the creation of the learning data 305 is to be started, the process proceeds to S111 to start the creation of the learning data 305 . Then, in S111, the information of the category number of the classification is added to the alignment data 301 included in the uncreated data 801 in accordance with the above-mentioned points.

Then, in S112, the alignment data 301 to which the category 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 completed, the display of the screen 910 is ended, and the process of creating the learning data 305 is completed.

In addition, the display means 800 may allow the user to determine whether to display a 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.

Button 901 is a button for causing the user to determine whether to display a screen for classifying uncreated data 801 on the display device 206 . When the display means 800 displays the button 901 on the screen 900 and the user presses the button, a screen for classifying the uncreated data 801 is displayed on the display device 206 .

In addition, the display means 800 may display a message 902 indicating the number of uncreated data 801 and a button 901 together. 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.

In addition, by providing the image classification means 400 in a device installed outside the exposure device 10 such as the management device 12, the alignment data 301 can be received from a plurality of exposure devices 10 and the learning data 305 can be created.

In addition, the image classification means 400 may store all or part of the received alignment data 301 for a preset period or until the upper limit of the number of items.

Furthermore, an arbitrary category may be selected from a plurality of categories displayed in a list, and the alignment data 301 stored in the selected category may be called and displayed on the screen. Alternatively, the number of alignment data 301 included in the selected category may be totaled and the results may be displayed. In addition, the alignment data 301 included in the selected category may be distinguished using assigned related data, and the results may be displayed in total.

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

Then, based on the displayed classification result, the user or the judgment device judges whether the preservation process 303 is possible (determines the necessity of preservation) (step S405). When it is determined that the preservation process is possible (Yes in step S405), the preservation process 303 is executed manually or automatically (step S406). On the other hand, if it is determined that the security process 303 is not possible (NO in step S405), the determination of execution of the security process is completed. In addition, the security process 303 referred to here may be automatically performed by the device as shown in Table 1, or a warning may be displayed through the device so that the user can perform it manually.

Next, it is monitored whether the alignment data 301 is classified again into the category number for which the security process 303 has been performed, that is, whether the same alignment failure occurs again despite the security process 303 being performed (step S407).

Then, when the alignment data 301 is classified again into the category number for which the preservation process 303 has been performed, that is, when the problem has not been eliminated ("No" in step S407), the alignment data 301 is classified into another category number. Additional learning is performed (step S408). In addition, the additional learning (changing the classification criteria) may be performed manually by the user or automatically by the device. On the other hand, if the alignment data 301 has not been reclassified into the category number for which the security process 303 has been performed within the predetermined time (YES in step S407), the execution judgment of the security process is ended.

As described above, in the judgment device according to this embodiment, the alignment data 301 obtained by the exposure device 10 is classified into alignment failure factors using a learning model obtained through machine learning. Then, based on the classified alignment failure factors, it is determined whether the exposure device 10 needs to be maintained. This makes it possible to obtain a determination device capable of determining whether it is necessary to maintain the exposure device 10 .

[Second Embodiment] 8A and 8B are respectively a block diagram and a process flowchart showing a structure for determining whether maintenance is required in the exposure device 10 in the determination device according to the second embodiment. In addition, the determination device according to the present embodiment has the same structure as the determination device according to the first embodiment except for newly installing the failure determination means 430. Therefore, the same components are assigned the same numbers and descriptions thereof are omitted.

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

Then, when the image processing means 300 determines based on the mark image that the alignment error of the substrate 210 is within the allowable range and the alignment is successful, the exposure process is executed by the exposure processing means 350 provided in the exposure device 10 . In addition, the image processing means 300 acquires the alignment data 301 by adding the related data to the mark image simultaneously with the execution of the exposure process, and then transfers the alignment data 301 to the image classification means 400 (step S602). In addition, even if the image processing means 300 determines from the mark image that the alignment error of the substrate 210 is not within the allowable range and the alignment fails, the alignment data 301 is similarly acquired and handed over to the image classification means. 400 (step S602).

Furthermore, even if the image processing means 300 determines that 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 re-determined to have failed based on the coverage measurement result of the substrate 210 measured by an external measuring instrument (not shown).

Here, the related data is data including information related to the acquired mark image. For example, the associated data may include information that determines the model, model, hardware structure, software structure, installation line, etc. of the exposure device 10 . In addition, the associated data may also include information that determines the composition of the batch, substrate 210, master 170, formula, environmental conditions, processing date and time, etc. Furthermore, the related data may include information that determines the settings of various offsets of the exposure device 10 during mark measurement, the amount of light from the light source 120 that illuminates the mark 211, the focus amount of the optical system, and other lighting conditions. In addition, the related data may include information such as operating conditions for aligning the exposure device 10 such as the type of the mark 211, position information of the stage, and the like. In addition, the related data may include information that determines the immediately preceding alignment measurement result, the operating state during alignment, such as the pressure of the substrate stage 200 to absorb the substrate 210, and the like.

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

As described above, the alignment data 301 handed over to the image classification means 400 also includes any alignment data 301 that the image processing means 300 determines as alignment success or failure, but is not limited to this. In order to increase the throughput, only the alignment data 301 judged as alignment failure by the image processing means 300 may be transferred to the image classification means 400 .

In addition, the number of markers 211 measured in step S601 may be one or a plurality of them, and the number of alignment data 301 transferred to the image classification means 400 may be one or a plurality of them. In addition, each time the image processing for one mark 211 is completed, the alignment data 301 may be sequentially transferred to the image classification means 400. In addition, the present invention is not limited to this, and may be performed together after the image processing is completed for all the marks 211 on the substrate 210 .

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

As the classification information 302, for example, category numbers 0 to 5 shown in Table 2 below can be set. [Table 2] Category number Classified information 302 Reasons for failure Preservation method 0 None (alignment successful) without 1 Undetermined reasons without 2 Positional shift during substrate handover or change in mark position depending on the substrate processing procedure Adjustment of substrate transfer position or no 3 The measurement light intensity is set incorrectly Adjustment of light intensity during measurement 4 Vibration of the substrate stage or reduction in contrast depending on the substrate handling procedure Adjustment or absence of substrate stage vibration 5 Deterioration of aiming light source Alignment light source replacement : : :

In addition, each category number shown in Table 2 can be manually set based on the alignment data 301 when the alignment process failed in the past, the result of the automatic recovery operation of the exposure device 10, and the like. Alternatively, each category number shown in Table 2 may be automatically set using machine learning or the like.

As shown in Table 2, in the judgment device according to this embodiment, as the classification information 302, factors for failure in the alignment process and a preservation method for improving the factors are set for each category number.

Specifically, category number 0 is normal alignment data 301 that does not include the cause of alignment failure, and corresponds to the classification of cases where maintenance is not required.

In addition, category number 1 corresponds to the classification of the case where the cause of the alignment failure cannot be determined and the preservation method is unknown. In addition, the category number 2 and the alignment failure factor are positional deviation when the substrate 210 is delivered, or the position change of the mark 211 depending on the processing procedure of the substrate 210, and in the case of the former, the preservation method is the delivery position of the substrate 210. Classification corresponding to the adjustment situation. In addition, category number 3 corresponds to a classification in which the alignment failure factor is an error in setting the light intensity of the light source 120 during alignment measurement, and the maintenance method is adjustment of the light intensity of the light source 120 during alignment measurement. In addition, category number 4 corresponds to a classification in which the alignment failure factor is vibration of the substrate stage 200 during alignment measurement or a decrease in contrast depending on the processing procedure of the substrate 210 . Furthermore, when the alignment failure factor is the former, it corresponds to the classification in which the maintenance method is adjustment for vibration of the substrate stage 200 during alignment measurement. In addition, category number 5 corresponds to a category in which the alignment failure factor is deterioration of the light source 120 and the maintenance method is replacement of the light source 120 .

In these classifications, the associated data appended to the alignment data 301 is effectively used. In addition, the above categories are examples, and categories other than the categories may be set.

In addition, when the alignment data 301 is compositely suitable for the above-mentioned categories, it may be classified into the category with the greatest degree of suitability. In addition, the present invention is not limited to this. When the alignment data 301 is compositely suitable for the above-mentioned categories, the alignment data 301 may be weighted and classified according to the degree of suitability for each category.

In the judgment device according to the first embodiment, as shown in Table 1, one factor is determined for one category number and a preservation method is suggested. However, in the judgment device according to this embodiment, as shown in Table 2, a plurality of factors are determined for one category number, and a preservation method is suggested for each factor.

For example, in Category No. 2 shown in Table 2, as the alignment failure factor, "positional deviation when transferring the substrate 210" which is a factor originating from the exposure device 10 or "positional deviation when transferring the substrate 210" which is a factor originating from the substrate processing program is determined. The position of the mark 211 changes depending on the processing procedure of the substrate 210." This means that the alignment failure factors cannot be converged into one based solely on the existing alignment data 301 .

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

At this time, during the pattern matching process of the exposure device 10 , the position of the mark 211 is greatly shifted to an unmeasurable level, causing an alignment failure. Furthermore, it is assumed that through classification by the image classification means 400, the alignment data 301 is classified into the category number 2 due to the large shift in the position of the mark 211.

At this time, based on the factor specified in category number 2, repair can be performed by maintaining the exposure device 10 . That is, when the alignment failure occurs due to the deviation of the receiving position of the substrate 210 in the exposure device 10 , it can be repaired by adjusting the receiving position of the substrate 210 in the exposure device 10 . However, when there is a change in the position of the mark 211 depending on the processing procedure of the substrate 210, that is, when the mark 211 is formed at a shifted position on the substrate 210, it is necessary to consider the substrate processing procedure in an apparatus other than the exposure apparatus 10. adjust. Therefore, repair cannot be performed during the maintenance process of the exposure device 10 .

In the judgment device according to the present embodiment, when the image classification means 400 classifies the alignment data 301 into the category numbers of suspected plural factors as described above, the failure judgment means 430 is used. That is, the image classification means 400 transfers the classification information 302 classified in this way to the failure determination means 430, and determines whether the cause is caused by the exposure device (step S604). Here, the failure determination means 430 can be implemented by, for example, a software program executed in the management device 12 .

Table 3 exemplarily shows the number of times that a plurality of mark images acquired in the past predetermined number of failed alignment processes are classified into each category number for each exposure device. [table 3]

As described above, the alignment failure factor may vary depending on the exposure device, that is, the alignment operation conditions such as the type of the light source 120 used in the 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 obtained through the same number of alignment processes in the past between exposure devices as shown in Table 3.

For example, when focusing on category number 2 in Table 3, it can be seen that the number of times of classification is significantly greater in the exposure device EQ2 than in other exposure devices. Therefore, when the alignment data 301 classified into the category number 2 is the alignment data acquired in the exposure device EQ2, the failure determination means 430 determines that the comparison result is the factor originating from the exposure device. 431 is sent back to the image classification means 400.

Then, the image classification means 400 selects an appropriate alignment failure factor from the determined alignment failure factors based on the determination result 431, that is, performs further classification and outputs classification information 302 (step S605). That is, when the image classification means 400 classifies the alignment data 301 acquired in the exposure device EQ2 into the category number 2, it classifies that the alignment failure factor is the positional shift when the substrate 210 is transferred. Then, the maintenance method can be classified as adjusting the transfer position of the substrate 210 .

In addition, the failure determination means 430 may determine based on calculating the median value or the average value of the number of times of classification in each exposure device, and if the difference between the number of times of classification in a predetermined exposure device exceeds a threshold value. In addition, if the number of times of classification in a predetermined device is x, and the average and standard deviation of the number of times of classification in each exposure device are μ and σ, respectively, then the test statistic |x-μ| /σ exceeds the threshold, and the determination in the failure determination means 430 is performed. In addition, the determination method in the failure determination means 430 is not limited to the above, and a method of selecting statistical outliers can also be used.

In addition, in the judgment device according to this embodiment, the judgment in the failure judgment means 430 is performed by comparing the classifications of the same number of mark images acquired in each exposure device, but it is not limited to this. For example, the determination in the failure determination means 430 may be made by comparing the classifications of the mark images acquired during the same period in each exposure device. In addition, the determination in the failure determination means 430 may be limited to the mark images acquired in the alignment process performed under specific operating conditions such as a predetermined alignment mode and recipe. That is, the determination in the failure determination means 430 may be made by comparing the classification of the mark images obtained under the same operating conditions in each substrate processing apparatus.

Then, after the classification information 302 is output through the image classification means 400 in step S605, the classification result is displayed through the device (step S606).

Then, based on the displayed classification result, the user or the device determines whether the preservation process 303 is possible (step S607). When it is determined that the preservation process 303 is possible (Yes in step S607), the preservation process 303 is executed manually or automatically (step S608). On the other hand, if it is determined that the security process 303 is not possible (NO in step S607), the execution determination of the security process is completed. In addition, the security process 303 referred to here is an example shown in Table 2, and may be automatically performed by the device, or a warning may be displayed through the device so that the user can perform it manually.

Next, it is monitored whether the alignment data 301 is classified again into the category number for which the security process 303 has been performed, that is, whether the same alignment failure occurs again despite the security process 303 being performed (step S609).

Then, when the alignment data 301 is reclassified into the category number for which the security process 303 has been performed, that is, when it is determined that the problem has not been eliminated (NO in step S609), either of the following two is performed. . That is, additional learning is performed so that the alignment data 301 is classified into other category numbers by the image classification means 400 (the criterion for classification is changed), or the threshold value in the judgment in step S604 is changed (the criterion for judgment is changed) (step S610 ). In addition, the additional learning in step S610 can be performed manually by the user or automatically by the device. In addition, the change of the threshold value in step S610 can be performed manually by the user, or can be performed automatically through the device using machine learning or the like.

On the other hand, if the alignment data 301 has not been reclassified into the category number for which the security process 303 has been performed within the predetermined time (YES in step S609), the execution judgment of the security process is ended.

As described above, in the judgment device according to this embodiment, the alignment data 301 obtained by the exposure device 10 is classified into alignment failure factors using a learning model obtained through machine learning, and compared with each other. Classification in each exposure device 10 . Thereby, it is determined whether the classified alignment failure factor is caused by the exposure device 10, and based on this, it is determined whether the exposure device 10 needs to be maintained.

This makes it possible to obtain a determination device that can determine with higher accuracy whether it is necessary to maintain the exposure device 10 .

[How to make items] The method of manufacturing an article using the judgment device according to this embodiment is suitable for manufacturing articles such as devices (semiconductor elements, magnetic memory media, liquid crystal display elements, etc.), for example. In addition, the manufacturing method of the article according to this embodiment includes: using the exposure device 10, a process of exposing a substrate coated with a photosensitive agent (forming a pattern on the substrate); and using a developing device (not shown) to expose the substrate. The process of developing the substrate (processing the substrate).

In addition, the manufacturing method according to this embodiment may include other well-known procedures (oxidation, film formation, evaporation, doping, planarization, etching, resist stripping, cutting, bonding, packaging, etc.). The method of manufacturing an article according to this embodiment is more advantageous than conventional methods in at least one of the performance, quality, productivity, and production cost of the article.

The preferred embodiments have been described above, but it is needless to say that the present invention is not limited to these embodiments, and various modifications and changes can be made within the scope of the gist thereof. Moreover, as an example of the substrate processing apparatus 10, the exposure apparatus was demonstrated, However, it is not limited to this. For example, an example of the substrate processing apparatus 10 may be an imprint apparatus that uses a mold to form a pattern of an imprint material on a substrate.

An example of the substrate processing apparatus 10 may be a drawing apparatus that draws a substrate with a charged particle beam (electron beam, ion beam, etc.) via a charged particle optical system to form a pattern on the substrate. In addition, the substrate processing apparatus 10 may further include a coating device that applies a photosensitive medium to the surface of the substrate, a developing device that develops the substrate on which a pattern is formed, and an imprinting device as described above when manufacturing articles such as devices. Manufacturing equipment for processes other than those implemented by the equipment.

In addition, methods and programs for implementing the above-described embodiments, and computer-readable recording media recording the programs are also included in the scope of this embodiment.

According to the present invention, it is possible to provide a determination device capable of determining whether maintenance of the substrate processing apparatus is necessary.

1:Semiconductor production line 10:Substrate processing device 11: Main computer 12:Management device 50:Substrate processing system 100: Main control department 110:Light source control department 120:Light source 130:Image processing department 140: Stage control department 150:Interferometer 160:Original alignment optical system 161:Camera component 162:Optical system 170:Original 171:Original carrier 180:Projection optical system 190: Substrate alignment optical system 193:Half mirror 194:Illumination optical system 195:Polarization beam splitter 196:Relay lens 197:λ/4 plate 198:Objective lens 200: Substrate carrier 204:Memory device 205:Input device 206:Display device 210:Substrate 211:mark 212:Reflector 300:Image processing methods 301: Align data 303: Preservation processing 305:Learning data 350: Exposure processing methods 400: Image classification means 401: Classification of action conditions and failure reasons 430: Failure determination method 431:Judgment result 800: Display means 801: Data not created 802: Data has been created 810:Input means 820: Judgment means 900:Screen 911: Tag image 912:Related data 913: Classified information 914: OK button 915: Abort button 191A:Camera element 191B:Camera component 192A: Imaging optical system 192B: Imaging optical system

[FIG. 1] is a block diagram showing the structure of the substrate processing system according to the first embodiment.

2A is a block diagram showing the structure of the exposure device included in the substrate processing system according to the first embodiment.

2B is a schematic diagram showing the structure of the substrate alignment optical system provided in the exposure device provided in the substrate processing system according to the first embodiment.

3A is a block diagram illustrating a structure for determining whether maintenance is required in the exposure apparatus, which is included in the substrate processing system according to the first embodiment.

3B is a flowchart illustrating the process of determining whether maintenance is required in the exposure device, which is included in the substrate processing system according to the first embodiment.

4 is a diagram schematically showing a screen displayed on the display device in the substrate processing system according to the first embodiment. FIG. 5 is a diagram schematically showing a screen for creating learning data in the substrate processing system according to the first embodiment. 6 is a flowchart showing a process of creating learning data in the substrate processing system according to the first embodiment. 7 is a diagram schematically showing a button for displaying a learning data creation screen in the substrate processing system according to the first embodiment. 8A is a block diagram illustrating a structure for determining whether maintenance is required in the exposure apparatus, which is included in the substrate processing system according to the second embodiment. [Fig. 8B] is a flowchart showing a process of determining whether maintenance is required in the exposure device included in the substrate processing system according to the second embodiment.

10:Exposure device

204:Memory device

205:Input device

206:Display device

300:Image processing methods

301: Align data

303: Preservation processing

305:Learning data

350: Exposure processing methods

400: Image classification means

800: Display means

801: Data not created

802: Data has been created

810:Input means

820: Judgment means

Claims (28)

A judgment device that uses a learning model obtained through machine learning for alignment data including image data of a mark on a substrate imaged by a substrate processing device and related data of information related to the image data, and performs The factors related to the alignment failure are classified, and based on the results of the classification, it is judged whether it is necessary to maintain the aforementioned substrate processing device. The judgment device of claim 1, wherein the judgment device performs the classification by comparing the classification among a plurality of the substrate processing devices. The determination device of claim 2, wherein the determination device determines whether the alignment failure factor is caused by the substrate processing device through the comparison. The judgment device of claim 3, wherein the judgment device judges whether the alignment failure factor is due to the substrate processing by comparing classifications of the same number of image data acquired in each substrate processing device. device. The judgment device of claim 3, wherein the judgment device judges whether the alignment failure factor is caused by the substrate by comparing classifications of the image data acquired during the same period in each substrate processing device. processing device. The judgment device of claim 3, wherein the judgment device compares classifications of the image data obtained using the same operating conditions in each substrate processing device, Thereby, it is determined whether the aforementioned alignment failure factor is caused by the aforementioned substrate processing device. The determination device of Claim 3, wherein the determination device executes a security process for the substrate processing device when it is determined that the alignment failure factor is caused by the substrate processing device. The judgment device of claim 7, wherein the judgment device judges whether the alignment failure factor is eliminated after the preservation process is performed, and if it is not eliminated, is modified to judge whether the alignment failure factor is caused by The benchmark for the aforementioned substrate processing equipment. The judgment device of Claim 1, wherein the judgment device, after classifying the alignment data, executes a preservation process for the substrate processing apparatus according to a preservation method corresponding to the classified alignment failure factor. The determination device of claim 9, wherein the determination device determines whether the alignment failure factor has been eliminated after executing the preservation process, and if it has not been eliminated, changes the classification criteria. The judgment device of claim 1, wherein the judgment device displays at least one of the result of the classification and the preservation method corresponding to the result. The judgment device of claim 1, wherein the judgment device is only for alignment processing failures in the alignment data. The alignment data is classified as described above. The determination device of claim 1, wherein the substrate processing device is an exposure device that exposes the substrate by using exposure light to transfer a pattern formed on the master plate to the substrate. A judgment device that uses a learning model obtained through machine learning with respect to image data of marks on a substrate imaged by a plurality of substrate processing apparatuses, and classifies the alignment failure factors by processing the plurality of substrates Comparisons are made between the devices, and based on the results of the classification, it is determined whether it is necessary to maintain the substrate processing device. A judgment device that uses a learning model obtained through machine learning to classify the image data of a mark on a substrate captured by a substrate processing device, and classifies the alignment failure factors, and judges whether it is necessary based on the result of the classification. To preserve the substrate processing device, a preservation process for the substrate processing device is performed according to the corresponding preservation method according to the classified alignment failure. A judgment device that uses a learning model obtained through machine learning to classify the image data of a mark on a substrate captured by a substrate processing device, and classifies the alignment failure factors, and judges whether it is necessary based on the result of the classification. The substrate processing apparatus is maintained, and at least one of a result of the classification and a maintenance method corresponding to the result is displayed. A judgment device that uses a learning model obtained through machine learning to determine the cause of the alignment failure only for the image data of the mark on the substrate imaged by the substrate processing device that has failed in the alignment process. Classification, and based on the results of the classification, it is judged whether it is necessary to maintain the aforementioned substrate processing device. A judgment device using transmission machine learning for image data of a mark on a substrate captured by an exposure device that exposes the substrate so that a pattern formed on a master plate is transferred to the substrate using exposure light. The obtained learning model is classified into categories related to the alignment failure factors, and based on the results of the classification, it is judged whether it is necessary to maintain the aforementioned exposure device. A substrate processing device for processing a substrate, having a judging device according to any one of claims 1 to 18. A method of manufacturing an article, which includes a program for processing a substrate using a substrate processing apparatus according to claim 19, and manufactures an article based on the processed substrate. A substrate processing system, including: a plurality of substrate processing devices that process substrates; a host computer that controls the operations of the plurality of substrate processing devices; and a management device that manages the maintenance of the plurality of substrate processing devices, and the management device includes the claim Judgment device for any one of 1 to 18. A judgment method including: markings on a substrate included in an image taken by a substrate processing device A program for classifying the alignment failure factors using a learning model obtained through machine learning using the alignment data of the associated data of the image data and the information related to the aforementioned image data; and a program based on the program for performing the classification As a result, it is determined whether it is necessary to maintain the program of the substrate processing apparatus. A judgment method includes: using a learning model obtained through machine learning with respect to image data of a mark on a substrate imaged by a plurality of substrate processing apparatuses, classifying the alignment failure factors on the plurality of substrates A program that performs comparisons between processing devices; and a program that determines whether it is necessary to maintain the substrate processing device based on the results of the classification program. A judgment method including: a program for classifying image data of marks on a substrate imaged by a substrate processing apparatus using a learning model obtained through machine learning, and classification related to alignment failure factors; As a result of the procedure, it is determined whether the aforementioned substrate processing device needs to be preserved; and according to the preservation method corresponding to the classified alignment failure factor, the procedure of executing the preservation process for the aforementioned substrate processing device is performed. A judgment method includes: a program for classifying image data of a mark on a substrate captured by a substrate processing device using a learning model obtained through machine learning and classifying factors related to alignment failure; A program for determining whether maintenance of the substrate processing apparatus is necessary based on the result of the classification program; and a program for displaying at least one of the result of the classification and a maintenance method corresponding to the result. A judgment method including: using a learning model obtained through machine learning to determine the alignment failure factors only for the image data of a mark on a substrate imaged by a substrate processing apparatus, which has failed in the alignment process. Relevant classification procedures; and a procedure for determining whether it is necessary to maintain the aforementioned substrate processing apparatus based on the results of the classification procedures. A judgment method comprising: using a transmission machine for image data of a mark on a substrate captured by an exposure device that exposes the substrate by transferring a pattern formed on a master plate to the substrate using exposure light. A program for classifying the alignment failure factors based on the acquired learning model; and a program for determining whether the exposure device needs to be preserved based on the results of the classification program. A computer-readable recording medium recorded with a program that causes the computer to determine the necessity of preservation, and the program causes the computer to execute the judgment method in any one of claims 22 to 27.

Images