Information processing system, information processing method, and information processing program

Abstract

The present invention provides an information processing system, an information processing method, and an information processing program that are capable of predicting the influence of a defect of a web in a predetermined manufacturing process, on the subsequent manufacturing process.　The information processing system comprises: an acquisition unit 511 that acquires first feature point information about a feature point present in a first web; an estimation unit 512 that, on the basis of the acquired first feature point information, estimates second feature point information about a feature point present in a second web obtained by performing predetermined processing on the first web; and an output unit 514 that outputs the estimated second feature point information in association with the first feature point information.

Description

Information processing system, information processing method, and information processing program

[0001] The present invention relates to an information processing system, an information processing method, and an information processing program.

[0002] Optical films are used on the display surfaces of liquid crystal display devices and the like. High quality is required for webs of such optical films. Therefore, strict control of defects occurring in the web is required in the web manufacturing process. For example, Patent Document 1 discloses a technique related to defects occurring in the web.

[0003] JP 2023-148609 A

[0004] In the case of a web such as an optical film that is manufactured through multiple processes, it is desirable to be able to predict the effect of a defect occurring in a given manufacturing process on subsequent manufacturing processes.

[0005] The present invention has been made in consideration of the above circumstances, and aims to provide an information processing system, an information processing method, and an information processing program that are capable of predicting the impact on subsequent manufacturing processes caused by a web defect that occurs in a specified manufacturing process.

[0006] The above object of the present invention can be achieved by the following means.

[0007] (1) An information processing system comprising: an acquisition unit that acquires first feature point information relating to feature points present on a first web; an estimation unit that estimates second feature point information relating to feature points present on a second web obtained by performing a predetermined process on the first web based on the acquired first feature point information; and an output unit that outputs the estimated second feature point information in association with the first feature point information.

[0008] (2) The information processing system according to (1) above, wherein the second feature point information includes information regarding the correspondence between feature points present on the first web and feature points present on the second web.

[0009] (3) The information processing system described in (1) above, wherein the second feature point information includes at least one of information regarding whether a specified feature point present on the first web remains on the second web and information regarding the probability that a specified feature point present on the first web will remain on the second web.

[0010] (4) The information processing system described in (1) above, wherein the output unit outputs the first feature point information and the second feature point information by displaying the second feature point information on a display unit in association with the first feature point information.

[0011] (5) The information processing system described in (4) above, wherein the first feature point information includes information regarding the position of a predetermined feature point present on the first web, and the display unit displays information representing the position of the predetermined feature point present on the first web.

[0012] (6) The information processing system described in (4) above, wherein the first feature point information includes information regarding the size of a specified feature point present on the first web, and the display unit displays information representing the size of the specified feature point present on the first web.

[0013] (7) The information processing system according to (4) above, wherein the display unit displays a screen showing each of a plurality of feature points present on the first web.

[0014] (8) An information processing system as described in (4) above, further comprising a reception unit that receives a selection of a portion of the feature points present on the first web, and the display unit displays the second feature point information associated with the portion of the feature points whose selection has been received.

[0015] (9) The information processing system according to (1), wherein the estimation unit estimates the second feature point information using a machine learning model.

[0016] (10) The information processing system according to (1), wherein the output unit further outputs output information generated based on the estimated second feature point information.

[0017] (11) An information processing method including: acquiring first feature point information relating to feature points present in a first web; estimating, based on the acquired first feature point information, second feature point information relating to feature points present in a second web obtained by performing a predetermined process on the first web; and outputting the estimated second feature point information in association with the first feature point information.

[0018] (12) An information processing program for causing a computer to execute a process including acquiring first feature point information regarding feature points present in a first web, estimating second feature point information regarding feature points present in a second web obtained by performing a predetermined process on the first web based on the acquired first feature point information, and outputting the estimated second feature point information in association with the first feature point information.

[0019] In the information processing system, information processing method, and information processing program according to the present invention, second feature point information regarding feature points present on a second web is estimated based on first feature point information regarding feature points present on a first web. This second feature point information is then output in association with the first feature point information. This allows, for example, a web manufacturing process manager to easily predict whether feature points present on a first web in a given manufacturing process will remain on a second web in a subsequent manufacturing process. This makes it possible to predict the impact of a web defect occurring in a given manufacturing process on subsequent manufacturing processes.

[0020] Advantages and features provided by one or more embodiments of the present invention will be more fully understood from the following detailed description and the accompanying drawings, which are intended for purposes of illustration only and are not intended to define limitations of the present invention.

[0023] FIG. 1 is a schematic diagram illustrating an application example of an information processing system according to a first embodiment.

[0024] FIG. 2 is a block diagram illustrating the general configuration of a terminal device shown in FIG. 1.

[0025] FIG. 3 is a table for explaining classification of feature points present on each of the first and second webs shown in FIG. 1.

[0026] FIG. 4 is a block diagram illustrating the general configuration of the information processing system shown in FIG. 1.

[0027] FIG. 5 is an example of a user list stored in the storage unit shown in FIG. 4.

[0028] FIG. 6 is another example of an inspection data DB stored in the storage unit shown in FIG. 4.

[0029] FIG. 7 is another example of an inspection data DB stored in the storage unit shown in FIG. 4.

[0030] FIG. 7 is another example of an inspection data DB stored in the storage unit shown in FIG. 4.

[0031] FIG. 7B is a schematic diagram illustrating feature points present on the first web shown in FIG. 1.

[0032] FIG. 7A is a schematic diagram illustrating an example of feature points on the second web corresponding to the feature points shown in FIG. 7A.

[0033] FIG. 7B is a schematic diagram illustrating another example of feature points shown in FIG. 7B.

[0034] FIG. 7B is a schematic diagram illustrating another example of feature points shown in FIG. 7B.

[0035] 11. It is a flowchart showing the generation process of the first inspection data shown in FIG. 6B. It is a schematic diagram showing an example of the configuration of the inspection device shown in FIG. 1. It is another schematic diagram showing the configuration of the inspection device shown in FIG. 9A. It is a schematic diagram showing another configuration of the inspection device shown in FIG. 9A. It is a flowchart showing the generation process of the second inspection data shown in FIG. 6C. It is a flowchart showing the generation process of the feature point classification data shown in FIG. 6D. It is a schematic diagram for explaining steps S32, S33 and S34 shown in FIG. 11. It is a subroutine flowchart of the process of step S34 shown in FIG. 11. It is a diagram showing an example of first feature point information and second feature point information displayed on the display unit shown in FIG. 2. It is a flowchart showing an example of the process executed by the information processing system shown in FIG. 1. It is a flowchart showing a machine learning method for a machine learning model used by the information processing system shown in FIG. 1. It is a flowchart showing an example of the process executed by an information processing system according to a modified example.21. It is a subroutine flowchart executed by the information processing system according to the second embodiment. It is a diagram showing an example of a probability density function calculated by the kernel density estimation shown in FIG. 18. It is a schematic diagram showing an application example of the information processing system according to the third embodiment. It is a table showing details of each of the plurality of inspection devices shown in FIG. 20. It is a table showing an example of first inspection data and second inspection data selected from the inspection data shown in FIG. 21. It is a schematic diagram showing an example of the first web manufacturing device shown in FIG. 1. It is an enlarged schematic diagram of the periphery of the winding device shown in FIG. 23. It is a schematic diagram showing an example of the second web manufacturing device shown in FIG.

[0021] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the scope of the present invention is not limited to the disclosed embodiments. In the description of the drawings, the same elements are denoted by the same reference numerals, and duplicate explanations will be omitted. Furthermore, the dimensional proportions in the drawings are exaggerated for the convenience of explanation and may differ from the actual proportions.

[0022] First Embodiment FIG. 1 is a schematic diagram illustrating an application example of an information processing system 50 according to a first embodiment. The information processing system 50 is configured with, for example, a server. The information processing system 50 is connected to a terminal device 70A in a factory A and a terminal device 70B in a factory B via a network. The network is a communication line such as a data communication network. Some networks may use a wired LAN or a wireless LAN. The wireless LAN is, for example, a LAN conforming to the IEEE 802.11 standard. The information processing system 50 may be connected to each of a plurality of factories via the network. The plurality of factories may be, for example, factories C and N. The plurality of factories including factories A and B may be operated or managed by a single manufacturer.

[0023] [Configuration of Terminal Devices 70A, 70B] The terminal devices 70A, 70B are computers such as PCs, smartphones, and tablet terminals. PC is an abbreviation for personal computer. The terminal devices 70A, 70B are configured to be connectable to the information processing system 50, and each of the terminal devices 70A, 70B transmits and receives various information to and from the information processing system 50. For example, the terminal device 70A is a PC used by an employee of a manufacturing company that operates Factory A, and the terminal device 70B is a PC used by an employee of a manufacturing company that operates Factory B.

[0024] 2 is a block diagram showing the schematic configuration of terminal devices 70A and 70B. Each of terminal devices 70A and 70B has a CPU 71, a ROM 72, a RAM 73, a storage 74, a communication interface 75, a display unit 76, and an operation reception unit 77. Each component is connected to each other via a bus 78 so that they can communicate with each other. CPU is an abbreviation for Central Processing Unit. ROM is an abbreviation for Read Only Memory. RAM is an abbreviation for Random Access Memory.

[0025] The CPU 71 controls the above components and performs various arithmetic processing in accordance with a program recorded in the ROM 72 or the storage 74 .

[0026] The ROM 72 stores various programs and various data.

[0027] The RAM 73 serves as a work area for temporarily storing programs and data.

[0028] The storage 74 stores various programs including an operating system and various data. For example, an application for displaying various information transmitted from the information processing system 50 is installed in the storage 74.

[0029] The communication interface 75 is an interface for communicating with other devices. A wired or wireless communication interface conforming to various standards is used as the communication interface 75. The communication interface 75 is used, for example, when transmitting first feature information (described below) to the information processing system 50 and when receiving second feature information (described below) from the information processing system 50.

[0030] The display unit 76 includes a liquid crystal display, an organic EL display, etc., and displays various information. The display unit 76 may be configured with viewer software, a printer, etc.

[0031] The operation reception unit 77 includes a touch sensor, a pointing device such as a mouse, a keyboard, etc., and receives various operations from the user. Note that the display unit 160 and the operation reception unit 77 may form a touch panel by superimposing a touch sensor serving as the operation reception unit 77 on the display surface serving as the display unit 76.

[0032] [Factory A, B] As shown in FIG. 1 , a first web manufacturing apparatus 1000 is installed in factory A. Factory A performs a first manufacturing process for manufacturing a first web 80A. The surface of the first web 80A is inspected by an inspection apparatus 90A. The inspection apparatus 90A includes, for example, a camera. The first web 80A is, for example, a raw film. The width of the first web 80A is, for example, in the range of 1000 mm to 3000 mm. The thickness of the first web 80A is set to a range of 15 μm to 200 μm, taking into consideration quality, handling, and the like. Factory A produces, for example, the first web 80A wound into a roll. The length of the first web 80A wound into a roll is, for example, in the range of 200 m to 10,000 m.

[0033] Factory B is equipped with a second web manufacturing apparatus 2000. Factory B manufactures a second web 80B using the first web 80A transported from Factory A. That is, a second manufacturing process for manufacturing the second web 80B is carried out in Factory B. Factory B manufactures the second web 80B by subjecting the first web 80A to a predetermined process. The predetermined process includes, for example, stretching, coating, and lamination. For example, Factory B manufactures the second web 80B by applying a coating process to the surface of the first web 80A, thereby providing a functional layer. The surface of the second web 80B is inspected by an inspection apparatus 90B. The inspection apparatus 90B includes, for example, a camera. The first web 80A may be transported to Factory B, Factory N, or other locations in addition to Factory B. The first web 80A and the second web 80B may each be a laminate including multiple webs.

[0034] In the first manufacturing process of factory A, first inspection data of first web 80A is generated by optical inspection using inspection device 90A. This first inspection data includes first feature point information for database use regarding feature points present in first web 80A.

[0035] In the second manufacturing process at factory B, second inspection data of second web 80B is generated by optical inspection using inspection device 90B. This second inspection data includes second feature point information for the database regarding feature points present in second web 80B.

[0036] Here, the feature points present on each of the first web 80A and the second web 80B are optical feature points present on the web, specifically, spots that are optically different from their surroundings. The feature points present on the webs are sometimes referred to as web defects, malfunctions, or faults. Feature points include, for example, defects caused by poor adhesion when bonding multiple webs together and defects caused by axial unevenness. For example, ultrasonic welding is used to bond multiple webs together. For example, tens to tens of thousands of feature points can be detected from image data captured of a single first web 80A or second web 80B. The total length of the first web 80A or second web 80B is, for example, several hundred meters to several kilometers.

[0037] For example, the terminal device 70A generates the first feature point information for the database by performing image analysis on the image data of the first web 80A captured by the inspection device 90A. The inspection device 90A may generate the first feature point information for the database.

[0038] For example, the terminal device 70B generates the second feature information for the database by performing image analysis on the image data of the second web 80B photographed by the inspection device 90B. The inspection device 90B may generate the second feature information for the database.

[0039] For example, a known technique is used for the image analysis. Specifically, pixels whose pixel values ​​in the image deviate from the average value of the surrounding pixels by a predetermined amount or more are extracted as feature points. Alternatively, feature points may be extracted using a method described below.

[0040] The first feature point information for database includes, for example, information regarding the position, size, etc. of each of the multiple feature points present on the first web 80A. The second feature point information for database includes, for example, information regarding the position, size, etc. of each of the multiple feature points present on the second web 80B. The position of the feature point can be expressed using, for example, XY coordinates. In the first feature point information for database and the second feature point information for database, multiple adjacent feature points may be clustered.

[0041] For example, terminal device 70A in factory A transmits first inspection data including this first feature point information for database to information processing system 50. Terminal device 70B in factory B transmits second inspection data including this second feature point information for database to information processing system 50.

[0042] The information processing system 50 classifies the feature points present on the first web 80A and the second web 80B into three types: first type feature points, second type feature points, and third type feature points, based on, for example, the first inspection data and the second inspection data received from the terminal devices 70A and 70B.

[0043] 3 is a table for explaining the first to third type characteristic points. The plurality of characteristic points present in the first web 80A can be classified, for example, into the first type characteristic points and the third type characteristic points. The plurality of characteristic points present in the second web 80B can be classified, for example, into the second type characteristic points and the third type characteristic points.

[0044] The first type characteristic points are characteristic points that are present only in the first web 80A and not in the second web 80B. That is, the first type characteristic points are characteristic points that disappear in the second manufacturing process. Even if the first type characteristic points are present in the first web 80A, they are relatively unlikely to affect the second manufacturing process and subsequent processes.

[0045] The second type feature points are feature points that are not present in the first web 80A but are present in the second web 80B. That is, the second type feature points are feature points that are newly generated in the second manufacturing process. These second type feature points are feature points that result from the second manufacturing process.

[0046] The third type feature points are feature points that exist in both the first web 80A and the second web 80B. That is, the third type feature points are feature points that are generated in the first manufacturing process and remain in the second manufacturing process. These third type feature points are feature points that are relatively likely to affect the second manufacturing process and subsequent processes.

[0047] The information processing system 50 classifies and stores the feature points present on each of the first web 80A and the second web 80B into first type feature points, second type feature points, and third type feature points.

[0048] 4 is a block diagram showing a schematic configuration of the information processing system 50. The information processing system 50 includes, for example, a control unit 51, a storage unit 52, and a communication unit 53.

[0049] The control unit 51 includes, for example, a CPU and memories such as RAM and ROM. The CPU is configured with a multi-core processor or the like that controls the above-mentioned units and executes various arithmetic processing in accordance with a program. Each function of the information processing system 50 is realized by the CPU executing the corresponding program. Specific functions of the control unit 51 will be described later.

[0050] The memory unit 52 is a large-capacity auxiliary storage device that stores various programs including an operating system and various data. For example, a hard disk, a solid-state drive, a flash memory, or a ROM is used as the storage. For example, the memory unit 52 stores a user list, a lot list, an inspection data DB, and the like. For example, the manager of factory A manages each of the user list and the lot list. For example, the manager of factory A is an employee of the manufacturer that operates factory A.

[0051] 5A shows an example of a user list. The user list includes information such as the user ID, user name, and contact information of each user. Each user may be assigned access rights to the inspection data DB. For example, each user may be able to access various data related to a specific first web 80A.

[0052] 5B shows an example of a lot list, which includes information such as the lot ID, product name, delivery destination user ID, manufacturing conditions, size, and manufacturing date for each lot.

[0053] 6A to 6D each show an example of the inspection data DB. The inspection data DB includes, for example, a process list for each of the processes in factories A and B, inspection data for each inspection performed in factories A and B, and feature point classification data.

[0054] 6A shows an example of a process list. The process list includes information such as the lot ID, the width and length of the web in each process, the process name, the stretch rate of the web, the number of layers of the web, the width direction and the length direction. The process list also includes information regarding each inspection performed in each of factories A and B, for example. The information regarding each inspection includes, for example, the inspection ID of each inspection, the inspection device ID of the inspection device used for each inspection, the inspection data, and the inspection date and time. The information regarding the width direction and the length direction of the web is expressed, for example, by whether the width direction and the length direction of the web in the previous process are the same as or reversed.

[0055] 6B and 6C each show an example of inspection data for each inspection included in the process list. FIG. 6B shows an example of inspection data with an inspection ID of i0101. This inspection data is, for example, first inspection data for the first web 80A and includes first feature point information for the database. FIG. 6C shows an example of inspection data with an inspection ID of i0102. This inspection data is, for example, second inspection data for the second web 80B and includes second feature point information for the database. Each of the first inspection data and second inspection data includes, for example, information regarding the feature point ID, position, area, length, width, maximum brightness, minimum brightness, classification, and presence or absence of concentrated dots for each of the multiple feature points present on the first web 80A or the second web 80B.

[0056] The positions of the characteristic points are expressed, for example, by X and Y coordinates based on a predetermined position on the first web 80A or the second web 80B. The X coordinate is, for example, the coordinate in the width direction of the first web 80A or the second web 80B and can range from 0 to 3,000 mm. The Y coordinate is, for example, the coordinate in the length direction of the first web 80A or the second web 80B and can range from 0 to 20,000 m.

[0057] The classification of feature points represents, for example, the shape and brightness distribution of each feature point. Each feature point is classified into, for example, about 5 to 20 classifications according to its shape and brightness distribution. The presence or absence of concentrated dots represents, for example, whether or not multiple feature points exist around the feature point.

[0058] 6D shows an example of feature point classification data. The feature point classification data includes, for example, information on an integrated comparison of feature points present on each of the first web 80A and the second web 80B. In the feature point classification data, for example, feature points present on each of the first web 80A and the second web 80B are assigned feature point IDs that are different from those in the first inspection data and the second inspection data. In the feature point classification data, the feature points are classified into first-type feature points, second-type feature points, or third-type feature points for each feature point ID. The feature point classification data may also include information on the accuracy of the classification of the first-type feature points, second-type feature points, and third-type feature points. The feature point classification data may be information on an integrated comparison of multiple inspection data, and may include, for example, information on an integrated comparison of the first inspection data with the third inspection data or the fourth inspection data.

[0059] Fig. 7A schematically shows a specific feature point present on the first web 80A. This feature point is, for example, the feature point with feature point ID: d0002. Figs. 7B to 7E each show an example of a feature point present on the second web 80B. This feature point is, for example, the feature point with feature point ID: e0002.

[0060] For example, when feature points on the first web 80A and the second web 80B are located at the same position, the information processing system 50 classifies these feature points as type 3 feature points. For example, as shown in FIG. 7B , the brightness ratio of the feature points on the first web 80A changes as a result of processing in the second manufacturing process. The change in brightness ratio is due to, for example, a change in the magnitude of the irregularities at the feature points. For example, as shown in FIG. 7C , the size of the feature points on the first web 80A changes as a result of processing in the second manufacturing process. For example, as shown in FIG. 7D , the shape of the feature points on the first web 80A, such as their aspect ratio, changes as a result of processing in the second manufacturing process. For example, as shown in FIG. 7E , the high-brightness and low-brightness regions of the feature points on the first web 80A are reversed as a result of processing in the second manufacturing process. For example, when the positions of feature points present on the first web 80A and the second web 80B are the same, the information processing system 50 may classify these feature points as first-type feature points or second-type feature points.

[0061] The communication unit 53 is an interface for connecting to external devices such as the terminal devices 70A and 70B via a network.

[0062] [Test Data DB Generation Process] Here, a description will be given of an example of a method for generating the test data DB by the information processing system 50. For example, the first test data is generated by the terminal device 70A and the test device 90A, and the second test data is generated by the terminal device 70B and the test device 90B.

[0063] FIG. 8 is a flowchart showing an example of a method for generating first test data.

[0064] (Step S11) The terminal device 70A instructs, for example, the first web manufacturing device 1000 to manufacture the first web 80A. At this time, for example, the first web 80A in roll form is manufactured according to the shipping standard z.

[0065] (Step S12) Next, terminal device 70A causes inspection device 90A to acquire image data.

[0066] The inspection device 90A is a transmission type or reflection type inspection device. The transmission type inspection device 90A irradiates the first web 80A with light and receives the light that has passed through the first web 80A. This allows for the detection of feature points present on the first web 80A. The reflection type inspection device 90A irradiates the first web 80A with light and receives the light that has been reflected by the first web 80A. This allows for the detection of feature points present on the first web 80A. The transmission type inspection device and the reflection type inspection device each include a bright-field type inspection device and a dark-field type inspection device.

[0067] 9A and 9B show an example of the configuration of a reflective inspection device 90A. Fig. 9A shows the configuration of this inspection device 90A as viewed from the width direction of the first web 80A. Fig. 9B shows the configuration of this inspection device 90A as viewed from the transport direction of the first web 80A. The inspection device 90A includes, for example, a light source 91, a camera 92, an analysis unit 93, and a memory unit 94.

[0068] In the inspection device 90A, cameras 92 capture images of the surface of the first web 80A and generate image data. The number of cameras 92, the angle of view, the distance to the surface of the first web 80A, etc. are appropriately set so that the entire width of the first web 80A is captured. Fig. 9B shows an inspection device 90A having two cameras 92 in the width direction.

[0069] The light source 91 irradiates the inspection area of ​​the first web 80 A with light. The light source 91 irradiates the light uniformly in the width direction of the roll-shaped first web 80 A. Here, irradiating the light uniformly means that the illuminance of the irradiated light is approximately the same.

[0070] The camera 92 is an optical sensor that optically reads the inspection area of ​​the first web 80A. The camera 92 includes an imaging element such as a CCD or CMOS, a lens, and the like. CCD is an abbreviation for Charge Coupled Device. CMOS is an abbreviation for Complementary Metal Oxide Semiconductor. The camera 92 generates two-dimensional image data from the output signals of each imaging element. The camera 92 detects diffused light among the light irradiated by the light source 91 and reflected by the surface of the first web 80A. The camera 92 may be a color camera or a monochrome camera. The camera 92 may detect light in the visible light range or infrared light range.

[0071] The camera 92 can read, for example, the entire widthwise range of the first web 80A at once. The contrast of the image data captured by the camera 92 is preferably equal to or greater than a predetermined value. In other words, it is desirable that the area of ​​the first web 80A irradiated with light from the light source 91 and the area not irradiated with light have a contrast equal to or greater than a predetermined value. In order to generate image data having a contrast equal to or greater than a predetermined value, it is desirable to use a light source 91 that is strong and has high linearity.

[0072] Here, "strong" means that, for example, when the illuminance at an irradiation distance of 50 mm is E50, the illuminance E50 is 50,000 lx or more. Also, "highly directional" means, for example, when the illuminance at an irradiation distance of 50 mm is E50 and the illuminance at an irradiation distance of 100 mm is E100, the relationship (E50-E100) / E50<0.5 is satisfied.

[0073] The camera 92 is disposed, for example, at a position where it receives specularly reflected light of the light emitted from the light source 91. The camera 92 may also be disposed at a position where it avoids specularly reflected light of the light emitted from the light source 91, that is, at a position where it receives diffused light from the first web 80A.

[0074] The analysis unit 93 is composed of a CPU, RAM, etc. The analysis unit 93 reads various processing programs stored in the storage unit 94, loads them into the RAM, and performs various processes in cooperation with the programs. The analysis unit 93 processes image data captured by the camera 92 to detect feature points present in the first web 80A. For example, the analysis unit 93 performs predetermined image processing on the image data, detects feature points, and quantitatively evaluates each of the detected feature points.

[0075] The analysis unit 93 may, for example, combine multiple images obtained by continuous shooting with one camera 92. The analysis unit 93 may, for example, generate one image data of the entire surface of the first web 80A and store it in the storage unit 94. Alternatively, the analysis unit 93 may generate multiple image data corresponding to the shooting time and store it in the storage unit 94. The analysis unit 93 may combine multiple image data obtained by multiple cameras 92 arranged in the width direction. The analysis unit 93 may determine the longitudinal position of the first web 80A based on the shooting time by, for example, referring to the stored transport speed. In the following description, it is assumed that the analysis unit 93 generates multiple image data corresponding to the shooting time and stores it in the storage unit 94.

[0076] The storage unit 94 is composed of an HDD, an SSD, etc. SSD is an abbreviation for Solid State Drive. The storage unit 94 stores various processing programs and data necessary for executing the programs. For example, the storage unit 94 stores image data captured by the camera 92, linking it to the time of capture. The storage unit 94 stores manufacturing conditions such as the winding speed of the first web manufacturing device 1000. The manufacturing conditions for the first manufacturing process may be included in the process list of the inspection DB.

[0077] 9C shows an example of a transmission type inspection device 90A. In this inspection device 90A, a light source 91 is disposed in a position facing a camera 92 with the first web 80A in between.

[0078] The inspection device 90A may have multiple inspection units. For example, the camera 92 may include a camera for detecting scratches on the surface of the first web 80A and a camera for detecting foreign matter inside the first web 80A. The first inspection data may use some of the data from the multiple inspection units, or may use a combination of the results from the multiple inspection units.

[0079] (Step S13) The terminal device 70A causes the inspection device 90A to detect a plurality of feature points from the image data and generate first inspection data. The inspection device 90A generates the first inspection data by, for example, the following process.

[0080] The analysis unit 93 of the inspection device 90A first acquires image data captured by the camera 92. Next, the analysis unit 93 divides the image data into a plurality of regions. For example, the analysis unit 93 divides the image data into n regions in the width direction. n may be, for example, several to several tens of regions. Hereinafter, the n regions will be referred to as region a1 to region an.

[0081] Next, the analysis unit 93 acquires image data of one region a1 and performs mathematical processing on the image data of the region a1. The mathematical processing includes, for example, preprocessing, enhancement processing, signal processing, and image feature extraction.

[0082] Preprocessing includes, for example, image cropping, low-pass filtering, high-pass filtering, Gaussian filtering, median filtering, bilateral filtering, morphological conversion, color conversion, contrast adjustment, noise removal, restoration of blurred or blurred images, mask processing, Hough transform, and projective transformation. Color conversion includes, for example, L*a*b*, sRGB, HSV, and HSL.

[0083] The enhancement process includes, for example, a Sobel filter, a Scharr filter, a Laplacian filter, a Gabor filter, and a Canny algorithm.

[0084] Signal processing includes, for example, basic statistics, square root of sum of squares, difference, sum, product, ratio, distance matrix calculation, differential and integral calculus, threshold processing, Fourier transform, wavelet transform, and peak detection. Basic statistics include, for example, maximum, minimum, mean, median, standard deviation, variance, and quartile. Threshold processing includes, for example, binarization and adaptive binarization. Peak detection includes, for example, detection of peak value, peak number, half-width, etc.

[0085] Image feature extraction includes template matching, SIFT features, and the like.

[0086] The analysis unit 93 performs mathematical processing on the image data of the region a1, and then performs threshold processing on the values ​​obtained by this processing. The threshold processing is a process of determining whether or not a point is a feature point based on a predetermined threshold, and determining the size of the feature point, etc.

[0087] The analysis unit 93 performs the same process on areas other than the area a1.

[0088] After processing each of the regions a1 to an, the analysis unit 93 integrates the results for each of the regions a1 to an, and data processing ends. Specifically, the analysis unit 93 generates data that associates the positions and sizes of the feature points detected for each region.

[0089] The analysis unit 93 then stores the results of the data processing in the storage unit 94. The analysis unit 93 performs this data processing on each of the multiple image data obtained by inspecting one first web 80A to obtain processing results. These processing results are aggregated to generate first inspection data.

[0090] (Step S14) Terminal device 70A transmits the first inspection data generated by inspection device 90A to information processing system 50, and stores the first inspection data in the inspection data DB of storage unit 52.

[0091] FIG. 10 is a flowchart showing an example of a method for generating second test data.

[0092] (Step S21) The terminal device 70B instructs, for example, the second web manufacturing apparatus 2000 to manufacture the second web 80B. At this time, for example, the second web manufacturing apparatus 2000 applies a predetermined material to the first web 80A, thereby manufacturing the roll-shaped second web 80B.

[0093] (Step S22) Next, the terminal device 70A causes the inspection device 90B to acquire image data. The inspection device 90B, like the inspection device 90A, includes, for example, a light source 91, a camera 92, an analysis unit 93, and a memory unit 94. For example, the inspection device 90B uses an inspection device with the same measurement system as the inspection device 90A. For example, when the inspection device 90A is a reflective inspection device, the inspection device 90B is also a reflective inspection device. It is preferable that the inspection device 90B inspects the second web 80B under the same measurement conditions as the inspection device 90A. Depending on differences in the performance, quality, product specifications, etc. required for the webs, the inspection devices 90A and 90B may use inspection devices with different measurement systems, and may inspect the first web 80A or the second web 80B under different measurement conditions.

[0094] (Step S23) The analysis unit 93 performs the same process as in step S13 to detect feature points from the image data and generate second inspection data.

[0095] (Step S24) Terminal device 70B transmits the second test data generated by test device 90B to information processing system 50, and stores the data in the test data DB of storage unit 52.

[0096] After receiving the first inspection data and the second inspection data, the information processing system 50 classifies the feature points of each of the first web 80A and the second web 80B into one of the first type feature points, the second type feature points, and the third type feature points.

[0097] 11 is a flowchart illustrating an example of a process for classifying the feature points of each of the first web 80A and the second web 80B into one of the first, second, and third type feature points. In other words, FIG. 11 illustrates a method for generating feature point classification data.

[0098] (Step S31) Information processing system 50 acquires first and second inspection data for the same lot, i.e., a pair of first and second inspection data, in response to an instruction from a user via terminal device 70A or 70B, for example. Information processing system 50 may acquire the pair of first and second inspection data when the pair of first and second inspection data is ready.

[0099] (Steps S32, S32, and S34) The information processing system 50 performs preprocessing on the first inspection data under first conditions and preprocessing on the second inspection data under second conditions to align the coordinate systems of the first web 80A and the second web 80B. For example, the information processing system 50 aligns the XY coordinate system of the second web 80B with the XY coordinate system of the first web 80A.

[0100] FIG. 12 is a schematic diagram illustrating an example of the processing of steps S32, S33, and S34. For example, the information processing system 50 inverts the Y coordinate of the second web 80B as preprocessing for the second inspection data. This aligns the difference in Y coordinate resulting from winding in the first manufacturing process and unwinding in the second manufacturing process. The information processing system 50 may invert the X coordinate of the second web 80B depending on, for example, the installation positions of the camera 92 in each of the first and second manufacturing processes. The information processing system 50 may convert the X and Y coordinates of the second web 80B depending on, for example, the elongation rate of the second web 80B. The information processing system 50 may align the X and Y coordinate system of the first web 80A with the X and Y coordinate system of the second web 80B.

[0101] The information processing system 50 further performs noise removal processing as preprocessing on each of the first inspection data and the second inspection data. The noise removal processing includes, for example, removal of low-intensity feature points, removal of extremely small feature points, and removal of continuous dots. The noise removal processing may also include removal of concentrated dots in the width direction. Concentrated dots in the width direction occur, for example, at the leading or trailing end of the first web 80A or the second web 80B.

[0102] The information processing system 50 performs preprocessing on each of the first inspection data and the second inspection data, and then performs a process of aligning the coordinate systems.

[0103] FIG. 13 is a subroutine flowchart showing the alignment process in step S34.

[0104] (Coarse Adjustment: Steps S401 to S403) The information processing system 50 first roughly adjusts the XY coordinates of the feature points of the first web 80A and the second web 80B as follows. For example, the information processing system 50 first shifts the coordinate position of a predetermined feature point of the second web 80B by a predetermined amount. Next, the information processing system 50 calculates distances L1 to Lm between the predetermined feature point of the second web 80B and the corresponding feature point of the first web 80A, and selects the shift amount (x1, y1) whose sum is the smallest. The information processing system 50 may use an average value instead of the sum. For example, the information processing system 50 determines the feature point of the first web 80A whose coordinate position is closest to the coordinate position of the predetermined feature point of the second web 80B as the feature point of the first web 80A that corresponds to the predetermined feature point of the second web 80B. If the information processing system 50 cannot determine a feature point of the first web 80A that corresponds to a specified feature point of the second web 80B, i.e., if the specified feature point is a second type feature point, it may exclude this feature point and calculate the sum of the distances L1 to Lm.

[0105] The information processing system 50 sequentially shifts the coordinate positions of predetermined feature points on the second web 80B from (-shift_x, -shift_y) to (+shift_x, +shift_y) around the central shift amount (0, 0) in increments of a fixed coarse adjustment shift amount a. The information processing system 50 calculates distances L1 to Lm from the coordinate positions of the predetermined feature points on the second web 80B to feature points 1 to m on the first web 80A. The information processing system 50 then selects the shift amount (x1, y1) from (-shift_x, -shift_y) to (+shift_x, +shift_y) that minimizes the sum of distances L1 to Lm.

[0106] For example, when the coarse adjustment shift amount a = 1.0 mm, (-shift_x, -shift_y) = (-10 mm, -10 mm), (-shift_x, +shift_y) = (+10 mm, +10 mm). The information processing system 50 may use different units for the X direction and the Y direction for the coarse adjustment shift amount a. For example, the X direction may be in millimeters and the Y direction in meters, so that (-shift_x, -shift_y) = (-10 mm, -10 m), (-shift_x, +shift_y) = (+10 mm, +10 m).

[0107] (Fine Adjustment: Steps S404 to S406) Next, the information processing system 50 fine-adjusts the X and Y coordinates of the feature points of each of the first web 80A and the second web 80B and selects a shift amount (x2, y2). The information processing system 50 selects the shift amount (x2, y2) in substantially the same manner as in steps S401 to S403 described above. Steps S404 to S406 differ from steps S401 to S403, for example, in the following respects. The fine adjustment shift amount b in step S404 is smaller than the coarse adjustment shift amount a. Furthermore, the shift amount (x1, y1) selected in step S403 is used as the center shift amount in step S405. For example, the fine adjustment shift amount b is sufficiently smaller than the coarse adjustment shift amount a, for example, 0.1 mm, which is one order of magnitude smaller.

[0108] (Step S407) The information processing system 50 performs coordinate conversion processing on all the feature points of the second web 80B using the shift amount (x2, y2) selected in step S406.

[0109] (Step S408) The information processing system 50 calculates the distances L1 to Lm after the coordinate transformation in step S407 and checks whether the sum of the distances L1 to Lm is less than a predetermined threshold. If the sum is equal to or greater than the predetermined threshold, the information processing system 50 may determine that the coordinate transformation process in step S407 is inappropriate.

[0110] (Step S409) If the alignment is inappropriate, i.e., if the answer is YES, the information processing system 50 ends the process. If the alignment is inappropriate, the information processing system 50 may display an error message on the display unit 76 or record a message in the test data DB indicating that calculation is not possible. On the other hand, if the alignment is appropriate, i.e., if the answer is NO, the information processing system 50 ends the process of FIG. 13, returns to the process of FIG. 11, and executes the processes from step S35 onwards.

[0111] (Steps S35 and S36) The information processing system 50 compares each of the feature points of the first web 80A with each of the feature points of the second web 80B. The coordinates of each of the feature points of the second web 80B have been transformed by the processing in step S34. Next, the information processing system 50 classifies each of the feature points of the first web 80A and the second web 80B into one of first-type feature points, second-type feature points, and third-type feature points. The information processing system 50 stores the classification results in the inspection data DB of the storage unit 52 and terminates the processing.

[0112] [Functions of Information Processing System 50] As shown in FIG. 4 , the information processing system 50 functions as an acquisition unit 511, an estimation unit 512, a reception unit 513, and an output unit 514 by the control unit 51 reading a program stored in the storage unit 52 and executing processing.

[0113] The acquisition unit 511 acquires first feature point information regarding feature points present on the first web 80A. The first feature point information includes, for example, information similar to the first feature point information for the database. Specifically, the first feature point information includes, for example, information regarding the feature point ID, position, area, length, width, maximum brightness, minimum brightness, division, and presence or absence of concentrated dots for each of the multiple feature points present on the first web 80A. The first feature point information may also include information regarding the process and cause of occurrence of the multiple feature points present on the first web 80A. Preferably, the first feature point information includes at least information regarding the position and size of each of the multiple feature points present on the first web 80A. The position of the feature point is expressed, for example, by XY coordinates based on a predetermined position on the first web 80A. The size of the feature point is expressed, for example, using at least one of the area, length, and width of the feature point. The first feature point information is generated, for example, using a method similar to the first feature point information for the database. For example, the first inspection data includes the first feature point information. The acquisition unit 511 acquires the first feature point information from, for example, the terminal device 70 A. The acquisition unit 511 may acquire the first feature point information from the storage unit 52.

[0114] The estimation unit 512 estimates second feature point information related to feature points present on the second web 80B based on the first feature point information acquired by the acquisition unit 511. The second feature point information includes, for example, information regarding the correspondence between feature points present on the first web 80A and feature points present on the second web 80B. Specifically, the second feature point information includes information regarding whether a specific feature point present on the first web 80A remains on the second web 80B. That is, the estimation unit 512 can estimate whether each feature point present on the first web 80A corresponds to a first-type feature point or a third-type feature point. The second feature point information may include information regarding the probability that a specific feature point present on the first web 80A will remain on the second web 80B. That is, the estimation unit 512 may estimate the likelihood that each feature point present on the first web 80A corresponds to a first-type feature point or a third-type feature point.

[0115] When the estimation unit 512 estimates that a specified feature point present on the first web 80A remains on the second web 80B, it may estimate at least one of the area, length, width, maximum brightness, minimum brightness, division, and presence or absence of a concentrated point of the feature point remaining on the second web 80B.

[0116] The estimation unit 512 estimates the second feature information by using, for example, a machine learning model. This machine learning model is created by using, for example, an inspection data DB, as will be described later.

[0117] The receiving unit 513 accepts a selection of some of the multiple feature points present on the first web 80A. For example, the manager of factory A selects some of the multiple feature points present on the first web 80A via the operation receiving unit 77 of the terminal device 70A. For example, the display unit 76 displays the multiple feature points present on the first web 80A, and the manager of factory A selects some of the displayed feature points using a mouse or the like. This causes the receiving unit 513 to accept the selection of some of the multiple feature points present on the first web 80A. The receiving unit 513 accepts, for example, the selection of one feature point.

[0118] The output unit 514 outputs the second feature point information estimated by the estimation unit 512 in association with the first feature point information. The output unit 514 outputs the first feature point information and the second feature point information, for example, by associating the second feature point information with the first feature point information and displaying the information on the display unit 76 of the terminal device 70A. The output unit 514 may also associate the second feature point information with the first feature point information and display it on the display unit 76 of the terminal device 70B or an external display device.

[0119] 14 shows an example of second feature point information displayed on the display unit 76. The output unit 514, for example, causes the display unit 76 to display a screen showing each of the multiple feature points present on the first web 80A. The screen showing each of the multiple feature points present on the first web 80A is, for example, an XY coordinate system showing each of the multiple feature points detected by the inspection device 90A. In the XY coordinate system, for example, each feature point is represented using a mark corresponding to its shape and size. As a result, information regarding the position and size of each of the multiple feature points present on the first web 80A is displayed on the display unit 76. For example, one screen may display 100 or more feature points.

[0120] The output unit 514 displays, for example, on this screen, second feature point information corresponding to some of the feature points selected by the receiving unit 513. For example, when the manager of factory A selects the feature point with feature point ID: d100 from among the multiple feature points on the first web 80A, the display unit 76 displays second feature point information corresponding to the feature point with feature point ID: d100. For example, the display unit 76 displays information indicating that the feature point with feature point ID: d100 has an 80% probability of remaining on the second web 80B. The display unit 76 may further display first feature point information related to the feature point with feature point ID: d100. For example, the display unit 76 displays the process in which the feature point with feature point ID: d100 occurred, the cause of occurrence, and an image of the feature point with feature point ID: d100.

[0121] Fig. 15 is a flowchart showing an example of the procedure for outputting second feature information executed in the information processing system 50. The processing of the information processing system 50 shown in the flowchart in Fig. 15 is stored as a program in the storage unit 52 of the information processing system 50, and is executed by the CPU controlling each unit.

[0122] (Step S101) The information processing system 50 first acquires first feature point information related to feature points present on the first web 80A. The information processing system 50 acquires the first feature point information by, for example, receiving first inspection data from the terminal device 70A. This first inspection data includes first feature point information related to each of the plurality of feature points present on the first web 80A.

[0123] (Step S102) The information processing system 50 estimates second feature point information related to feature points present on the second web 80B based on the first feature point information acquired in step S101. The information processing device 60, for example, inputs the first feature point information to a classifier that has been trained in advance through machine learning. This makes it possible to estimate, for example, whether each feature point present on the first web 80A is also present on the second web 80B and / or the probability that the feature point is present on the second web 80B. For example, the classifier is trained by machine learning using a learning method described below using teacher data that includes a large amount of previously prepared past first inspection data and second inspection data and corresponding feature point classification data. Specifically, the classifier is trained in machine learning using the first feature point information for database and the second feature point information for database as input data and information regarding the classification of feature points present on each of the first web 80A and the second web 80B as output data.

[0124] (Step S103) The information processing system 50 accepts a selection of some of the feature points present on the first web 80A. The information processing system 50 may accept the selection of some of the feature points before step S102. At this time, the information processing system 50 may estimate second feature point information corresponding to the selected part of the feature points.

[0125] (Step S104) The information processing system 50 outputs the second feature point information estimated in the processing of step S102 in association with the first feature point information. The information processing system 50 outputs the first feature point information and the second feature point information, for example, by displaying the second feature point information in association with the first feature point information on the display unit 76 of the terminal device 70A. The information processing system 50 outputs, for example, the second feature point information corresponding to the feature point selected in the processing of step S103.

[0126] Next, a machine learning method for a trained model used in a classifier will be described.

[0127] FIG. 16 is a flowchart showing a machine learning method for a trained model. In the process of FIG. 16 , machine learning is performed using multiple data sets as training sample data, with previously prepared first and second test data as input and feature point classification data as output. The multiple data sets may be, for example, i sets, where i is, for example, several thousand to several hundred thousand. The learning device that functions as a classifier may be, for example, a standalone high-performance computer using a CPU and GPU processor, or a cloud computer. Below, a learning method using a neural network configured by combining perceptrons such as deep learning in the learning device will be described, but this is not limiting, and various other techniques may be applied. For example, random forests, decision trees, support vector machines, logistic regression, k-nearest neighbors, topic models, etc. may be applied.

[0128] (Step S111) The learning device reads learning sample data, which is teacher data. If it is the first time, the first set of learning sample data is read, and if it is the i-th time, the i-th set of learning sample data is read.

[0129] (Step S112) The learning device inputs the input data from the read learning sample data to the neural network.

[0130] (Step S113) The learning device compares the estimation result of the neural network with the correct answer data.

[0131] (Step S114) The learning device adjusts the parameters based on the comparison result, for example, by performing a process based on backpropagation, so as to reduce the difference in the comparison result.

[0132] (Step S115) If the learning device has completed processing all data from the first to i-th sets, i.e., if the answer is YES, the process proceeds to step S116. If the learning device has not completed processing from the first to i-th sets, i.e., if the answer is NO, the process returns to step S111, reads the next learning sample data, and repeats the process from step S111 onwards.

[0133] (Step S116) The learning device determines whether to continue learning, and if it continues, that is, if the answer is YES, the process returns to step S111, and the processes from the first set to the i-th set are executed again in steps S111 to S115. If the learning device does not continue learning, that is, if the answer is NO, the process proceeds to step S117.

[0134] (Step S117) The learning device stores the trained model constructed in the processing up to this point, and then ends the processing. The storage destination includes the internal memory of the information processing system 50. In the processing of FIG. 15 described above, the second feature point information is estimated using the trained model generated in this manner.

[0135] [Effects of Information Processing System 50] In the information processing system 50 according to the present invention, second feature point information regarding feature points present in the second web 80B is estimated based on first feature point information regarding feature points present in the first web 80A. This second feature point information is then output in association with the first feature point information. This enables, for example, a manager of the first manufacturing process to easily predict whether feature points present in the first web 80A will remain in the second manufacturing process. This makes it possible to predict the impact on the second manufacturing process of defects in the first web 80A that occurred in the first manufacturing process. The effects of this are described below.

[0136] Strict quality control is required for webs such as optical films. For example, defects in the web are strictly controlled. Defects include, for example, foreign matter, scratches, and dents. Such webs are manufactured through multiple processes, and quality inspections are conducted at each process. When a web defect is detected in an upstream manufacturing process, it is difficult for managers at each manufacturing process to determine whether the defect will affect downstream manufacturing processes. Therefore, even if the defect does not actually affect downstream manufacturing processes, the defective web may not be smoothly transferred from upstream to downstream manufacturing processes. Under such circumstances, quality control at each manufacturing process, especially at upstream manufacturing processes, may become unnecessarily strict, resulting in a decrease in yield at each process. Furthermore, maintaining a predetermined production volume at each process requires extended factory operating hours and increased energy consumption. In addition, the amount of web and other waste at each process may increase, potentially increasing the burden on the environment.

[0137] In response to this, the information processing system 50 outputs the estimated second feature information in association with the first feature information, thereby enabling a manager of the first manufacturing process or the second manufacturing process to easily determine whether a predetermined defect in the first web 80A will affect the second manufacturing process before the second manufacturing process is carried out.

[0138] Furthermore, the manager of the first manufacturing process or the second manufacturing process can set the quality standard of the first web 80A to an appropriate value based on the estimated second feature information. This reduces excessive quality requirements for the first web 80A, improving the yield in each process. Furthermore, this information processing system 50 also reduces energy consumption and reduces the environmental impact.

[0139] Additionally, the information processing system 50 estimates second feature point information using an inspection data DB. In this inspection data DB, each feature point on the first web 80A is classified by aligning it with each feature point on the second web 80B. In this way, by classifying the feature points on the first web 80A and the second web 80B without marking the webs, it is possible to prevent new defects on the webs that would be caused by marking.

[0140] Furthermore, the information processing system 50 can accept the selection of some of the feature points present on the first web 80A and display second feature information corresponding to these feature points on the display unit 76. This makes it possible to easily display second feature information corresponding to a specific feature point, even when, for example, 100 or more feature points of the first web 80A are displayed on the display unit 76. In particular, for a long web of 100 m or more, a large number of feature points are displayed on the display unit 76. Therefore, the information processing system 50 is suitable for use in the manufacturing process of a long web of 100 m or more.

[0141] Below, we will explain modifications and other embodiments of the information processing system 50 described in the first embodiment. In order to avoid duplication of explanation, detailed explanations of components similar to those of the information processing system 50 described in the first embodiment will be omitted.

[0142] 17 is a flowchart illustrating an example of processing by the information processing system 50 according to a modified example. The information processing system 50 may generate output information based on the estimated second feature point information. The output unit 514 generates the generated output information.

[0143] (Step S51) The information processing system 50 estimates second feature information based on the acquired first feature information. This process corresponds to step S102 in FIG.

[0144] (Step S52) The information processing system 50 generates output information based on the second feature information estimated in step S51. The output information includes, for example, information related to the shipping standard z of the first web 80A. Based on this output information, managers of the first and second manufacturing processes can consider changing the shipping standard z of the first web 80A.

[0145] The output information includes, for example, information regarding the trend of the second feature information present throughout the entire first web 80A. The trend of the second feature information present throughout the entire first web 80A may be, for example, a trend over time. Based on this output information, a manager of the first manufacturing process and the second manufacturing process can, for example, determine how much time has passed since the start of manufacturing the first web 80A before feature points that are likely to remain in the second web 80B, i.e., third feature points, appear. The trend of the second feature information present throughout the entire first web 80A may be expected values ​​of the first feature points and the third feature points for each region of the first web 80A.

[0146] The output information includes, for example, information related to the analysis results of the feature points of the first web 80A. The information related to the analysis results of the feature points of the first web 80A is, for example, information related to whether the number of third-type feature points present in the first web 80A exceeds a predetermined threshold. The information related to the analysis results of the feature points of the first web 80A is, for example, information related to the cause of the occurrence of the third-type feature points present in the first web 80A. The information related to the analysis results of the feature points of the first web 80A is, for example, information related to changes in the manufacturing conditions of the first web 80A.

[0147] The output information includes, for example, information regarding the further processing of the first web 80A. The information regarding the further processing of the first web 80A is, for example, information regarding the delivery destination of the first web 80A, i.e., factories B, C, and N. For example, the delivery destination factory is changed depending on the number of first characteristic points and third characteristic points present on the first web 80A. The information regarding the further processing of the first web 80A may be information regarding whether or not the first web 80A will be delivered to a factory.

[0148] In the information processing system 50 according to the modified example, similarly to the embodiment described above, the second feature information is output in association with the first feature information, thereby enabling a manager of the first manufacturing process to predict the impact on the second manufacturing process of a defect in the first web 80A that occurs in one manufacturing process.

[0149] Furthermore, since output information is generated based on this second feature information, managers of the first manufacturing process and the second manufacturing process can more specifically consider changes to the shipping specifications of the first web 80A, changes to the manufacturing conditions of the first manufacturing process, and subsequent processing, etc.

[0150] Second Embodiment Fig. 18 is a subroutine flowchart showing the alignment process of an information processing system 50 according to a second embodiment. Fig. 18 corresponds to Fig. 13 described in the first embodiment. This information processing system 50 uses kernel density estimation to align the XY coordinates of the first web 80A and the second web 80B. In this respect, the information processing system 50 according to the second embodiment differs from the information processing system 50 according to the first embodiment. Except for this point, the information processing system 50 according to the second embodiment has the same configuration as the information processing system 50 according to the first embodiment and provides the same effects.

[0151] (Step S451) The information processing system 50 obtains a probability density function by performing kernel density estimation on the feature points of the first web 80A. The kernel density estimation is performed two-dimensionally, and a Gaussian kernel is used as the kernel function. For example, a predetermined value is used as the bandwidth. For example, a table correlating web product names with bandwidths is stored in the storage unit 52. The information processing system 50 may use a bandwidth value corresponding to the web product name, or may use different bandwidth values ​​depending on the number of feature points present on the first web 80A. When estimating the kernel density of a given feature point, the information processing system 50 takes into account data surrounding the feature point. Then, the information processing system 50 sums the densities of each feature point to obtain a probability density function.

[0152] Fig. 19 shows an example of a probability density function calculated by kernel density estimation, in which the vertical and horizontal axes represent X and Y coordinates, and the intensity of the color represents the density.

[0153] (Step S452) The information processing system 50 obtains a probability density function of each of the feature points of the second web 80B in the same manner as in step S451.

[0154] (Steps S453 to S455) The information processing system 50 compares the two obtained probability density functions and performs correspondence based on the density distribution. Then, the information processing system 50 calculates a transformation matrix based on the correspondence result and performs coordinate transformation of the X and Y coordinates for the feature points of the second web 80B.

[0155] (Steps S456 to S457) The information processing system 50 performs the processes of S456 to S457 in the same manner as steps S406 to S407 in FIG.

[0156] In the information processing system 50 according to the second embodiment, similarly to the first embodiment, the second feature information is output in association with the first feature information, thereby enabling a manager of the first manufacturing process to predict the impact on the second manufacturing process of a defect in the first web 80A that occurs in the first manufacturing process.

[0157] The information processing system 50 may align the positions of the feature points of the first web 80A and the second web 80B using other methods. For example, the information processing system 50 may perform kernel density estimation of the feature points of one of the first web 80A and the second web 80B. In this case, the information processing system 50 compares the obtained probability density function with the feature points of the other web. This allows the information processing system 50 to align the positions of the feature points of the first web 80A and the second web 80B.

[0158] Third Embodiment FIG. 20 is a schematic diagram illustrating an application example of an information processing system 50 according to a third embodiment. FIG. 20 corresponds to FIG. 1 of the first embodiment, but FIG. 20 omits the illustration of some components, such as terminal devices 70A and 70B. Here, the second manufacturing process includes a first sub-process, a second sub-process, and a third sub-process. In factory B where the second manufacturing process is performed, for example, web 80ba undergoes the first sub-process to become web 80bb. Web 80bb then undergoes the second sub-process to become web 80bc. Web 80bc then undergoes the third sub-process to become second web 80B. Web 80ba is, for example, the first web 80A transported from factory A. The first sub-process, second sub-process, and third sub-process are, for example, coating processes. That is, the second web 80B is a laminate including the first web 80A. The first sub-step, the second sub-step, and the third sub-step may each include an auxiliary step such as a drying step. The first sub-step, the second sub-step, and the third sub-step may each include an adhesion step such as a lamination step.

[0159] For example, multiple inspection devices are installed in factory B. The multiple inspection devices include inspection devices 90B0, 90B1, 90B2, and 90B3. For example, inspection device 90B0 is installed before the first sub-process. For example, inspection device 90B1 is installed between the first sub-process and the second sub-process. For example, inspection device 90B2 is installed between the second sub-process and the third sub-process. For example, inspection device 90B3 is installed after the third sub-process. The first manufacturing process may include multiple sub-processes, and multiple inspection devices may be installed in factory A. Multiple inspection devices may be installed in each of factories A and B.

[0160] 21 shows the details of each of the inspection devices 90A, 90B0, 90B1, 90B2, and 90B3. Data A is acquired from the inspection device 90A, data B0 from the inspection device 90B0, data B1 from the inspection device 90B1, data B2 from the inspection device 90B2, and data B3 from the inspection device 90B3.

[0161] 22 shows an example of a combination of the first inspection data and the second inspection data. For example, the first inspection data is data A and the second inspection data is data B0. In this case, the second feature point information estimated by the information processing system 50 allows a manager of the first manufacturing process or the second manufacturing process to easily determine whether a predetermined defect in the first web 80A will affect the storage and transportation processes of the first web 80A.

[0162] For example, the first inspection data is data B0 and the second inspection data is data B1. At this time, the second feature point information estimated by the information processing system 50 enables a manager of the first manufacturing process or the second manufacturing process to easily determine whether a predetermined defect in the web 80ba will affect the first sub-process.

[0163] For example, the first inspection data is data B1 and the second inspection data is data B2. At this time, the second feature point information estimated by the information processing system 50 enables a manager of the first manufacturing process or the second manufacturing process to easily determine whether a predetermined defect in the web 80bb will affect the second sub-process.

[0164] For example, the first inspection data is data B2, and the second inspection data is data B3. At this time, the second feature point information estimated by the information processing system 50 enables a manager of the first manufacturing process or the second manufacturing process to easily determine whether a predetermined defect in the web 80bc will affect the third sub-process.

[0165] For example, the first inspection data is data A and the second inspection data is data B3. In this case, the second feature information estimated by the information processing system 50 allows a manager of the first manufacturing process or the second manufacturing process to easily determine whether a predetermined defect in the first web 80A will affect the second manufacturing process.

[0166] The first inspection data and the second inspection data may be any combination other than those described above as long as they are combinations of inspection data acquired in different processes.

[0167] In the information processing system 50 of the third embodiment, similarly to the first embodiment, the second feature information is output in association with the first feature information, thereby enabling a manager of the first manufacturing process to predict the impact of a web defect occurring in the first manufacturing process on downstream manufacturing processes.

[0168] (First web manufacturing apparatus 1000) Fig. 23 shows an example of the schematic configuration of the first web manufacturing apparatus 1000. The first web manufacturing apparatus 1000 manufactures the first web 80A by, for example, a solution casting method. The first web manufacturing apparatus 1000 includes, for example, a casting section 01, a first drying section 02, a stretching section 03, a second drying section 04, a knurling section 05, and a winding and collecting section 06. For example, an inspection device 90A is disposed in the winding and collecting section 06.

[0169] The casting unit 01 includes, for example, a belt 01a, a die 01b, and a peeling roll 01d. In the casting unit 01, a dope, which is prepared by dissolving a resin in a solvent, is cast from the die 01b onto the belt 01a. A casting film 01c is formed on the belt 01a. The peeling roll 01d peels off the casting film 01c.

[0170] The first drying section 02 includes, for example, a drying box 02 a and a transport roll 02 d. The drying box 02 a is provided with a dry air intake 02 b and an exhaust 02 c. In the first drying section 02, the amount of the solvent contained in the casting film 01 c may be adjusted.

[0171] The stretching section 03 includes an MD stretching section 03a and a TD stretching section 03b. The stretching section 03 stretches the casting membrane 01c transported from the first drying section 02.

[0172] The second drying section 04 has, for example, almost the same configuration as the first drying section 02 .

[0173] The knurling unit 05 forms knurls on both ends of the casting membrane 01c conveyed from the second drying unit 04.

[0174] The winding and collecting section 06 includes a winder 06a and an entrained air amount control device 06b. The winding and collecting section 06 further includes a linear encoder 06c, a winding shaft rotation speed measuring device 06d, a tension control device 06e, and a thickness measuring device 06f. The linear encoder 06c may be of either a contact type or a non-contact type.

[0175] FIG. 24 shows an enlarged view of the knurling forming section 05 and the winding and collecting section 06 shown in FIG.

[0176] In the knurling device 05a, a knurling roll 501a and a backing roll 501b are paired. A pressing means 501c is connected to the knurling roll 501a. The knurling roll 501a has an uneven surface. The casting film 01c is sandwiched between the knurling roll 501a and the backing roll 501b, and knurling is formed. The knurling roll 501a is moved up and down by the pressing means 501c. The movement amount of the pressing means 501c is controlled by, for example, the control device 07.

[0177] The control device 07 has a memory, a CPU, and an input / output I / F. The control device 07 determines the amount of movement of the pressing means 501c, i.e., the amount of movement of the knurling forming roll 501a, using, for example, information input to the CPU and information previously input to the memory. As the amount of movement of the knurling forming roll 501a increases, the height of the knurls formed increases. As the amount of movement of the knurling forming roll 501a decreases, the height of the knurls formed decreases.

[0178] The knurling device 05a may be an inkjet type or laser type knurling device.

[0179] The entrained air amount control device 06b includes, for example, a touch roll 602a and a pressure amount control device 602b that controls the pressure amount of the touch roll 602a. The pressure amount control devices 602b are disposed on both ends of the touch roll 602a.

[0180] The relationship between the touch roll and tension control is described in, for example, J. K. Good, Modeling Nip Induced Tension in Wound Rolls, Proceedings of Forth International Conference on Web Handling, 1997.

[0181] The tension control device 06e includes a tension controller 605a and a moving means 605b for the tension controller 605a. The tension control device 06e moves the position of the tension controller 605a in accordance with the position of the first web 80A being wound around the winding shaft 82.

[0182] (Second web manufacturing apparatus 2000) Figure 25 shows an example of the schematic configuration of the second web manufacturing apparatus 2000. The second web manufacturing apparatus 2000 laminates, for example, a first protective film 12 and a second protective film 13 on both sides of a polarizer 1c. This produces a laminated polarizing film 1 having a layer structure of, for example, first protective film 12 / adhesive layer 31 / polarizer 11 / adhesive layer 32 / second protective film 13. This second protective film 13 is formed from the first web 80A manufactured by the first web manufacturing apparatus 1000.

[0183] The second web manufacturing apparatus 2000 includes, for example, a wet-treatment apparatus 204, a drying apparatus 205, and a laminating apparatus 206, in that order from the upstream side. The second web manufacturing apparatus 2000 further includes a payout unit 202. For example, the first web 80A is loaded onto the third roll unit 63 of the payout unit 202.

[0184] The wet-treatment device 204 has a first roll unit 41, a conveying unit 42, and a processing unit. A long strip of untreated hydrophilic polymer film 1a is wound around the first roll unit 41. The conveying unit 42 conveys the hydrophilic polymer film 1a. In the processing unit, the hydrophilic polymer film 1a is transformed into a polarizer 1b.

[0185] The transport unit 42 has a plurality of guide rolls, etc. The transport unit 42 unwinds the hydrophilic polymer film 1a wound around the first roll unit 41 and transports it to a processing unit.

[0186] The processing section includes, for example, a swelling processing tank 4A, a dyeing processing tank 4B, a crosslinking processing tank 4C, a stretching processing tank 4D, and a washing processing tank 4E in this order from the upstream side.

[0187] The swelling treatment tank 4A is a treatment tank containing a swelling treatment liquid. The swelling treatment liquid swells the hydrophilic polymer film 1a. The dyeing treatment tank 4B is a treatment tank containing a dyeing treatment liquid. The dyeing treatment liquid dyes the hydrophilic polymer film 1a. The crosslinking treatment tank 4C is a treatment tank containing a crosslinking treatment liquid. The crosslinking treatment liquid crosslinks the dyed hydrophilic polymer film 1a. The stretching treatment tank 4D is a treatment tank containing a stretching treatment liquid. The stretching treatment liquid is not particularly limited, but for example, a solution containing a boron compound as an active ingredient can be used. The cleaning treatment tank 4E is a treatment tank containing a cleaning treatment liquid. The cleaning treatment liquid cleans the hydrophilic polymer film 1a after stretching. The cleaning treatment liquid is a treatment liquid for cleaning treatment liquids such as the dyeing treatment liquid and the crosslinking treatment liquid that have adhered to the hydrophilic polymer film 1a. Typical cleaning treatment liquids used are water such as ion-exchanged water, distilled water, and pure water.

[0188] The drying device 205 has a conveying section 501 and a heating section. There may be one drying device 205, or two or more drying devices 205 may be provided side by side in the polarizer conveying direction. In the illustrated example, for example, one drying device 205 is provided on the polarizer conveying path. The conveying section 501 conveys the long strip-shaped polarizer 1b. The heating section applies heat to the polarizer 1b to dry it.

[0189] The heating section of the drying device 205 includes, for example, a chamber 502 and a heat source. The chamber 502 includes a space 503 therein that can transport a polarizer.

[0190] The laminating apparatus 206 includes a conveying unit 61, an adhesive coating unit 64, a bonding unit 67, and a chamber 69. The conveying unit 61 conveys the dried polarizer 1c and first protective film 12. The chamber 69 surrounds the adhesive coating unit 64 and the bonding unit 67.

[0191] The conveying unit 61 has a guide roll and the like. The conveying unit 61 conveys the long strip-shaped polarizer 1c dried by the drying device 205 to the bonding unit 67. The conveying unit 61 also conveys the long strip-shaped first protective film 12 and the like to the bonding unit 67.

[0192] The adhesive coating unit 64 has a gravure roll 641. The gravure roll 641 is a coating roll that coats an adhesive on a film. The adhesive coating unit 64 is arranged upstream of the laminating unit 67. For example, the adhesive coating unit 64 is arranged on one side of the first protective film 12 and one side of the second protective film 13. The adhesive coating unit 64 may also be arranged on one side of the polarizer 1c and the other side of the polarizer 1c.

[0193] The adhesive coating unit 64 includes, for example, a gravure roll 641 which is a coating roll, a container 642 in which an adhesive is stored, and a doctor blade 643. The adhesive coating unit 64 may also include a backup roll as necessary. The backup roll is disposed opposite the gravure roll 641 with the film sandwiched therebetween.

[0194] A plurality of cells are formed on the surface of the gravure roll 641. The plurality of cells are recesses into which adhesive is placed. The gravure roll 641 rotates so that its surface comes into contact with the adhesive 65 stored in a container 642. As the gravure roll 641 rotates, the adhesive 65 adheres to the surface of the gravure roll 641, including the cells. Excess adhesive 65 is scraped off into the container 642 by a doctor blade 643. When the gravure roll 641 comes into contact with the film, the adhesive 65 in the cells is transferred to one side of the first protective film 12 and the second protective film 13. In this way, the adhesive 65 is solidly coated from the gravure roll 641 onto one side of each of the first protective film 12 and the second protective film 13.

[0195] The adhesive for bonding the polarizer 1c to the first protective film 12 and the second protective film 13 is not particularly limited, but it is preferable to use an active energy ray-curable adhesive as described above. Any conventionally known active energy ray-curable adhesive can be used. The active energy ray-curable adhesive generally contains an active energy ray-curable component and a polymerization initiator, and optionally contains various additives.

[0196] The unwinding unit 202 has an easy-adhesion treatment tank 21, a cleaning treatment tank 22, and a heat treatment tank 23. The easy-adhesion treatment tank 21 performs easy-adhesion treatment on the surface of the second protective film 13 to which the polarizer 11 is bonded. For example, the easy-adhesion treatment tank 21 performs corona discharge treatment, plasma treatment, or the like. In corona discharge treatment, a high voltage is applied to a wire or sawtooth electrode inside a chamber. The cleaning treatment tank 22 has a configuration similar to the above-described cleaning treatment tank 4E. A cleaning treatment liquid is stored in the cleaning treatment tank 22. The second protective film 13 is cleaned by the cleaning treatment liquid. The heat treatment tank 23 has a configuration similar to the drying device 205. The heat treatment tank 23 heats and dries the second protective film 13. The drying temperature of the heat treatment tank 23 is changed, for example, by the manufacturing management system 3000.

[0197] The second web manufacturing apparatus 2000 further includes a second roll unit 62 and a third roll unit 63. The long strip-shaped first protective film 12 is wound around the second roll unit 62. The long strip-shaped second protective film 13 is wound around the third roll unit 63. The first protective film 12 and the second protective film 13 are transported from the second roll unit 62 and the third roll unit 63, respectively, to a bonding unit 67.

[0198] The configuration of the information processing system 50 described above is a main configuration used to explain the features of the above embodiment and modified examples. However, the present invention is not limited to the above configuration and can be modified in various ways within the scope of the claims. Furthermore, configurations included in general information processing devices or information processing systems are not excluded. For example, the information processing system 50 may include inspection devices 90A and 90B. Furthermore, the feature point generation function of the analysis unit 93 of the inspection device 90 may be performed by the control unit 51 of the information processing system 50.

[0199] For example, in the first embodiment and the like, an example has been described in which the information processing system 50 estimates the second feature information using a machine learning model, but the information processing system 50 may estimate the second feature information using other methods. For example, the information processing system 50 may estimate the second feature information by statistical processing using an inspection data DB.

[0200] Furthermore, the means and methods for performing various processes in the information processing system 50 according to the above-described embodiment can be realized by either a dedicated hardware circuit or a programmed computer. The above-described program may be provided, for example, by a computer-readable recording medium such as a USB memory or a DVD-ROM, or may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is typically transferred and stored in a storage unit such as a hard disk. The above-described program may also be provided as standalone application software, or may be incorporated into the software of a device as a function of the device.

[0201] While embodiments of the present invention have been described and illustrated in detail, the disclosed embodiments are made for purposes of illustration and example only and are not intended to be limiting, and the scope of the present invention should be construed by the language of the appended claims.

[0202] This application is based on a Japanese patent application (Patent Application No. 2024-44733) filed on March 21, 2024, the disclosure of which is incorporated herein by reference in its entirety.

[0203] 50 Information processing system 51 Control unit 511 Acquisition unit 512 Estimation unit 513 Reception unit 514 Output unit 52 Storage unit 90, 90A, 90B Inspection device 1000 First web manufacturing device 2000 Second web manufacturing device

Claims

1. An information processing system comprising: an acquisition unit that acquires first feature point information relating to feature points present on a first web; an estimation unit that, based on the acquired first feature point information, estimates second feature point information relating to feature points present on a second web obtained by performing a predetermined process on the first web; and an output unit that outputs the estimated second feature point information in association with the first feature point information.

2. An information processing system according to claim 1, wherein the second feature point information includes information relating to the correspondence between feature points present on the first web and feature points present on the second web.

3. An information processing system as described in claim 1, wherein the second feature point information includes at least one of information regarding whether a specified feature point present on the first web remains on the second web and information regarding the probability that a specified feature point present on the first web will remain on the second web.

4. An information processing system as described in claim 1, wherein the output unit outputs the first feature point information and the second feature point information by displaying the second feature point information on a display unit in association with the first feature point information.

5. An information processing system as described in claim 4, wherein the first feature point information includes information relating to the positions of predetermined feature points present on the first web, and the display unit displays information representing the positions of the predetermined feature points present on the first web.

6. An information processing system as described in claim 4, wherein the first feature point information includes information regarding the size of a predetermined feature point present on the first web, and the display unit displays information representing the size of the predetermined feature point present on the first web.

7. An information processing system according to claim 4, wherein said display unit displays a screen showing each of a plurality of feature points present on said first web.

8. An information processing system as described in claim 4, further comprising a reception unit that receives a selection of a portion of the plurality of feature points present on the first web, and the display unit displays the second feature point information associated with the portion of feature points whose selection has been received.

9. The information processing system according to claim 1, wherein the estimation unit estimates the second feature point information using a machine learning model.

10. The information processing system according to claim 1, wherein the output unit further outputs output information generated based on the estimated second feature point information.

11. An information processing method comprising: acquiring first feature point information relating to feature points present in a first web; estimating, based on the acquired first feature point information, second feature point information relating to feature points present in a second web obtained by performing a predetermined process on the first web; and outputting the estimated second feature point information in association with the first feature point information.

12. An information processing program for causing a computer to execute a process including: acquiring first feature point information relating to feature points present in a first web; estimating, based on the acquired first feature point information, second feature point information relating to feature points present in a second web obtained by performing a predetermined process on the first web; and outputting the estimated second feature point information in association with the first feature point information.

Images