Information processing system, information processing method, and information processing program
The information processing system aligns pre-processing and post-processing feature point maps to address the challenge of associating defects across web manufacturing steps, enhancing defect tracking and analysis in optical film production.
Patent Information
- Application Number
- PCT/JP2026/014962
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-13
- Filing Date
- 2026-04-13
- Publication Date
- 2026-11-19
AI Technical Summary
Existing web manufacturing processes for optical films face challenges in associating defects detected across multiple manufacturing steps due to stretching or contraction of the web, making it difficult to track and analyze defects by position.
An information processing system that generates and aligns pre-processing and post-processing feature point maps based on location information, allowing for the association of webs from different processes by position.
Enables the understanding of the approximate positional relationship between the long web and the processed web, facilitating the association of defects across manufacturing processes and improving defect tracking and analysis.
Smart Images

Figure JP2026014962_19112026_PF_FP_ABST
Abstract
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 such as these optical films. For this reason, strict control of defects and the like occurring in the web is required in the web manufacturing process. For example, Patent Document 1 discloses a technique for detecting defects that occur during the manufacture of optical films.
[0003] Japanese Unexamined Patent Application Publication No. 2013-024868
[0004] Such webs are manufactured through a plurality of processes. During the manufacture of such webs, inspections for detecting defects occurring in the web are often performed multiple times. By the way, in the process of going through a plurality of steps, the web is stretched or contracted, or only a part thereof is processed. Therefore, it is desirable that a plurality of inspection results can be associated with each other by position. This makes it possible, for example, to track and analyze defects that occur in each manufacturing process.
[0005] The present invention has been made in view of the above circumstances, and an object thereof is to provide an information processing system, an information processing method, and an information processing program capable of associating webs from respective processes with each other by position.
[0006] The above object of the present invention is achieved by the following means.
[0007] (1) An information processing system for processing information obtained from a long web and a processed web in which a predetermined process has been performed on at least a part of the long web, comprising: an acquisition unit that acquires pre-processing web information including location information of pre-processing feature points present in the long web and post-processing web information including location information of post-processing feature points present in the processed web; a map generation unit that generates a pre-processing compressed feature point map based on the pre-processing web information and generates a post-processing compressed feature point map based on the compression ratio of the pre-processing compressed feature point map and the post-processing web information; and a first alignment unit that aligns the generated pre-processing compressed feature point map and the post-processing compressed feature point map.
[0008] (2) The information processing system according to (1) above, wherein the map generation unit generates a feature point map corresponding to the position information of the pre-processing feature points assuming that the long web is compressed at a predetermined compression ratio, as the pre-processing compressed feature point map, and generates a feature point map corresponding to the position information of the post-processing feature points, as the post-processing compressed feature point map.
[0009] (3) The information processing system according to (1) or (2) above, further comprising an output unit that outputs the pre-processed compressed feature point map and the post-processed compressed feature point map, which have been aligned by the first alignment unit, to a display unit.
[0010] (4) The information processing system according to (3) above, wherein the output unit outputs the pre-processed compressed feature point map and the post-processed compressed feature point map generated by the map generation unit to the display unit.
[0011] (5) The information processing system according to (4) above, wherein the output unit displays the pre-processed compressed feature point map and the post-processed compressed feature point map on the display unit.
[0012] (6) The information processing system according to (4) or (5) above, wherein the first alignment unit aligns the pre-processed compressed feature point map and the post-processed compressed feature point map based on information input from the user.
[0013] (7) The information processing system according to (6) above, further comprising a first condition setting unit for setting first feature point conditions for the pre-processing feature points and the post-processing feature points, wherein the map generation unit generates the pre-processing compressed feature point map and the post-processing compressed feature point map with respect to the positional information of the pre-processing feature points and the post-processing feature points that conform to the first feature point conditions.
[0014] (8) The information processing system according to (6) above, wherein the processed web includes a first processed web in which a predetermined process has been performed on a first portion of the long web, and a second processed web in which a predetermined process has been performed on a second portion of the long web that is different from the first portion, and the post-processed compressed feature point map includes a first post-processed compressed feature point map corresponding to the position information of the post-processed feature points in the first processed web, and a second post-processed compressed feature point map corresponding to the position information of the post-processed feature points in the second processed web, and the output unit causes the display unit to display the pre-processed compressed feature point map, the first post-processed compressed feature point map, and the second post-processed compressed feature point map generated by the map generation unit.
[0015] (9) The information processing system according to (1) or (2) above, wherein the first alignment unit aligns the pre-processed compressed feature point map and the post-processed compressed feature point map using image processing technology.
[0016] (10) The information processing system according to (1) or (2) above, further comprising: a specification unit that identifies a specific region of a part of the long web based on the result of alignment by the first alignment unit; and a second alignment unit that associates predetermined pre-processing feature points and predetermined post-processing feature points present in the specified region based on their positions.
[0017] (11) The information processing system according to (9) above, further comprising a second condition setting unit for setting a second feature point condition for the pre-processing feature point and the post-processing feature point, wherein the second alignment unit associates a predetermined pre-processing feature point and a predetermined post-processing feature point that conform to the second feature point condition.
[0018] (12) The information processing system according to (1) or (2) above, wherein the long web has a width dimension and a length dimension intersecting the width dimension, and at the predetermined compression ratio, the compression ratio of the length dimension is higher than the compression ratio of the width dimension.
[0019] (13) The information processing system according to (12) above, wherein the length of the processing web is smaller than the length of the long web.
[0020] (14) An information processing method comprising: obtaining pre-processing web information including location information of pre-processing feature points present in a long web; and post-processing web information including location information of post-processing feature points present in a processed web in which a predetermined process has been performed on at least a portion of the long web; generating a pre-processing compressed feature point map based on the pre-processing web information; generating a post-processing compressed feature point map based on the compression ratio of the pre-processing compressed feature point map and the post-processing web information; and aligning the generated pre-processing compressed feature point map and the post-processing compressed feature point map.
[0021] (15) The information processing method according to (14) above, wherein the generation of the pre-processing compressed feature point map and the post-processing compressed feature point map is characterized in that a feature point map corresponding to the position information of the pre-processing feature points assuming that the long web is compressed at a predetermined compression ratio is generated as the pre-processing compressed feature point map, and a feature point map corresponding to the position information of the post-processing feature points is generated as the post-processing compressed feature point map.
[0022] (16) An information processing program that causes a computer to execute the information processing method described in (14) or (15) above.
[0023] In the information processing system, information processing method, and information processing program according to the present invention, a pre-processing compressed feature point map and a post-processing compressed feature point map are generated, and their positions are aligned. This allows the approximate positional relationship between the long web and the processed web to be understood. Therefore, it becomes possible to associate the webs of each process with each other based on their positions.
[0024] The advantages and features provided by one or more embodiments of the present invention will be better understood from the following detailed description and accompanying drawings, which are for illustrative purposes only and are not intended to define any limitations of the present invention. This is a schematic diagram showing an example of application of an information processing system according to the first embodiment. This is a block diagram showing the schematic configuration of a terminal device shown in Figure 1. This is a schematic diagram showing an example of the relationship between a long web and a processing web shown in Figure 1. This is a block diagram showing the schematic configuration of an information processing system shown in Figure 1. This is an example of a user list stored in the storage unit shown in Figure 4. This is an example of a lot list stored in the storage unit shown in Figure 4. This is an example of an inspection data DB stored in the storage unit shown in Figure 4. This is another example of an inspection data DB stored in the storage unit shown in Figure 4. This is another example of an inspection data DB stored in the storage unit shown in Figure 4. This is a flowchart showing the generation process of the first inspection data shown in Figure 6B. This is a schematic diagram showing an example of the configuration of an inspection device shown in Figure 1. This is another schematic diagram showing the configuration of an inspection device shown in Figure 8A. This is another schematic diagram showing the configuration of an inspection device shown in Figure 8A. This is a flowchart showing the generation process of the second inspection data shown in Figure 6C. This is a block diagram showing an example of the functions of an information processing system shown in Figure 4. This is a diagram showing an example of a screen output by the output unit shown in Figure 10 to the display unit. This figure shows another example of the screen shown in Figure 11. This figure shows another example of the screen shown in Figure 11. This figure shows an example of the screen after alignment by the first alignment unit shown in Figure 11. This is a schematic diagram for explaining a specific area of a long web identified by the identification unit shown in Figure 10. This is a flowchart of an example of processing performed by the information processing system shown in Figure 4. This is a schematic diagram for explaining step S32 shown in Figure 16. This is a subroutine flowchart of the processing in step S40 shown in Figure 16. This is a schematic diagram for explaining each step shown in Figure 18. This is a block diagram showing an example of the functions of an information processing system according to a modified example. This is a table for explaining the classification of feature points by the classification unit shown in Figure 20. This is a flowchart of an example of processing performed by the information processing system shown in Figure 21. This is a subroutine flowchart of the information processing system executed by the information processing system according to the second embodiment.This figure shows an example of a probability density function calculated by kernel density estimation shown in Figure 23. This is a schematic diagram showing an application example of the information processing system according to the third embodiment. This is a table showing the details of each of the multiple inspection devices shown in Figure 25. This is a table showing an example of first and second inspection data selected from the inspection data shown in Figure 26. This is a schematic diagram showing an example of a long web manufacturing device shown in Figure 1. This is an enlarged schematic diagram of the area around the winding device shown in Figure 28. This is a schematic diagram showing an example of a processed web manufacturing device shown in Figure 1.
[0025] Embodiments of the present invention will be described below with reference to the attached 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 redundant descriptions are omitted. Also, the dimensional ratios in the drawings are exaggerated for illustrative purposes and may differ from the actual ratios.
[0026] <First Embodiment> Figure 1 is a schematic diagram showing an application example of the information processing system 50 according to the first embodiment. The information processing system 50 is composed of, for example, a server. This information processing system 50 is mutually connected to terminal device 70A at factory A and terminal device 70B at factory B via a network. The network is a communication line such as a data communication network. In some networks, wired LANs or wireless LANs may be used. A wireless LAN is, for example, a LAN that conforms to the IEEE 802.11 standard. The information processing system 50 may be connected to each of multiple factories via the network. The multiple factories are, for example, factory C and factory N.
[0027] [Configuration of terminal devices 70A and 70B] Terminal devices 70A and 70B are computers such as PCs, smartphones, and tablet terminals. PC is an abbreviation for personal computer. Terminal devices 70A and 70B are configured to be connectable to the information processing system 50, and each terminal device 70A and 70B sends and receives various information to and from the information processing system 50. Terminal devices 70A and 70B are PCs used by employees of a manufacturing company operating factories A and B. Factories A and B are operated by, for example, one manufacturer.
[0028] Figure 2 is a block diagram showing the schematic configuration of terminal devices 70A and 70B. Terminal devices 70A and 70B each have a CPU 71, ROM 72, RAM 73, storage 74, communication interface 75, display unit 76, and operation reception unit 77. Each component is connected to the others via a bus 78 so as to be able to 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.
[0029] The CPU 71 controls each of the above configurations and performs various calculation processes according to the program recorded in the ROM 72 or storage 74.
[0030] ROM72 stores various programs and data.
[0031] RAM 73 temporarily stores programs and data as a working area.
[0032] The storage 74 stores various programs, including the operating system, and various data. For example, the storage 74 has an application installed for displaying various information transmitted from the information processing system 50.
[0033] The communication interface 75 is an interface for communicating with other devices. Various wired or wireless communication interfaces can be used as the communication interface 75. The communication interface 75 is used, for example, when transmitting pre-processing web information and post-processing web information (described later) to the information processing system 50, and when receiving screen data (described later) from the information processing system 50.
[0034] The display unit 76 includes, for example, a liquid crystal display or an organic EL display, and displays various information. The display unit 76 may also consist of viewer software or a printer.
[0035] The operation reception unit 77 includes a touch sensor, a pointing device such as a mouse, or a keyboard, and accepts various user operations. Alternatively, the display unit 160 and the operation reception unit 77 may be configured as a touch panel by superimposing a touch sensor (operation reception unit 77) onto the display surface (display unit 76).
[0036] [Factory A, B] As shown in Figure 1, Factory A is equipped with a long web manufacturing apparatus 1000. In Factory A, a first manufacturing process for manufacturing long webs 80A is carried out. The surface of the long web 80A is inspected by an inspection apparatus 90A. The inspection apparatus 90A includes, for example, a camera. The long web 80A is, for example, a roll of film. The width of the long web 80A is, for example, in the range of 1000 mm to 5000 mm. The thickness of the long web 80A is set in the range of 15 μm to 500 μm, taking into consideration quality and handling. When the long web 80A contains metal such as steel, the thickness of the long web 80A may be 1 mm or more. In Factory A, for example, long webs 80A are manufactured. The length of the long web 80A is, for example, in the range of 500 m to 10000 m. In Factory A, for example, a winding process of the long web 80A is carried out.
[0037] Factory B is equipped with a processed web manufacturing apparatus 2000. In Factory B, processed webs 80B are manufactured using long webs 80A transported from Factory A. That is, a second manufacturing process for manufacturing processed webs 80B is carried out in Factory B. In Factory B, processed webs 80B are manufactured by applying a predetermined process to at least a portion of the long web 80A. The predetermined process is, for example, winding, unwinding, stretching, slitting, surface treatment, coating, bonding, washing, and drying. The predetermined process is the process from when the long web 80A is inspected until the processed web 80B is inspected, and the predetermined process may be performed in Factory A. The predetermined process may include, for example, winding. The predetermined process includes, for example, at least a winding process and an unwinding process. For example, in Factory B, after unwinding the long web 80A in a wound state, a coating process is performed to impart a functional layer to the surface of the long web 80A. This allows a processed web 80B to be manufactured from a long web 80A. The long web 80A and the processed web 80B differ, for example, in at least one of their length and width.
[0038] Figure 3 schematically illustrates an example of the relationship between a long web 80A and a processed web 80B. For example, processed webs 80B-1, 80B-2, and 80B-3 from multiple different lots (lot IDs: b001, b002, b003) are manufactured from a long web 80A of one lot (lot ID: a001). Processed web 80B-1 (lot ID: b001) is a web in which a predetermined process has been applied to the first part 80A-1 of the long web 80A. Processed web 80B-2 (lot ID: b002) is a web in which a predetermined process has been applied to the second part 80A-2 of the long web 80A, which is different from the first part 80A-1. Processed web 80B-3 (lot ID: b003) is a web in which a predetermined process has been applied to the third part 80A-3 of the long web 80A, which is different from the first part 80A-1 and the second part 80A-2. For example, processing web 80B-1 corresponds to a specific example of the first processing web of the present invention, and processing web 80B-2 corresponds to a specific example of the second processing web of the present invention.
[0039] The width of the processed webs 80B-1, 80B-2, and 80B-3 is, for example, approximately the same as the width of the long web 80A, and is in the range of 1000 mm to 5000 mm. The length of the processed webs 80B-1, 80B-2, and 80B-3 is less than the length of the long web 80A, and is, for example, in the range of 100 m to 5000 m.
[0040] The long web 80A has, for example, several unused portions 80Z. The unused portions 80Z are, for example, portions used for feeding and processing adjustments during the manufacture of the processed web 80B. The processed web 80B is not formed on these unused portions 80Z. The length of the unused portions 80Z is, for example, in the range of 10m to 100m. The unused portions 80Z are located, for example, between the first portion 80A-1 and the second portion 80A-2, and between the second portion 80A-2 and the third portion 80A-3, etc.
[0041] Furthermore, the statement that at least one of the length and width of the long web 80A and the processed web 80B is different may include the case where, after a portion of the long web 80A is cut off and then stretched, the apparent length and width of the long web 80A and the processed web 80B become the same.
[0042] The long web 80A and the processed web 80B may have different thicknesses. The surface of the long web 80A is inspected by inspection device 90A, and the surface of the processed web 80B is inspected by inspection device 90B. Inspection devices 90A and 90B include, for example, cameras. The long web 80A may be transported to factories C and N, etc., in addition to factory B. At least one of the long web 80A and the processed web 80B is, for example, a resin film.
[0043] In the first manufacturing process of factory A, first inspection data of the long web 80A is generated by optical inspection using inspection device 90A. This first inspection data includes pre-processing web information about the long web 80A. The pre-processing web information includes positional information of pre-processing feature points present on the long web 80A.
[0044] In the second manufacturing process of Factory B, second inspection data of the processed web 80B is generated by optical inspection using the inspection device 90B. This second inspection data includes post-processing web information relating to the processed web 80B. The post-processing web information includes position information of post-processing feature points present on the processed web 80B.
[0045] Here, the pre-processing feature points and the post-processing feature points are optical feature points present on the web, specifically spots having an optical difference from the surroundings. In determining the optical difference from the surroundings, a predetermined threshold value may be set, and points exceeding the threshold value may be defined as feature points. The feature points present on the web may also be referred to as web defects, flaws, failures, and the like. The feature points include, for example, defects caused by poor adhesion occurring when bonding a plurality of webs, defects caused by shaft unevenness, and the like. For bonding a plurality of webs, for example, ultrasonic fusion or the like is used. For example, several tens to several hundreds of feature points are detected from image data obtained by photographing one long web 80A or processed web 80B. The feature points have a size such that, for example, the length in the longitudinal direction or the width direction is 0.05 mm to 5 mm. The total length of the long web 80A is, for example, several kilometers. Note that a plurality of defects, flaws, and failures within a predetermined region may be regarded as one feature point. The predetermined region is, for example, a 10 mm square region. In the following description, when the pre-processing feature points and the post-processing feature points are not distinguished, they may be simply referred to as feature points.
[0046] As described above, the predetermined processes performed on the long web 80A are winding, unwinding, stretching, slitting, surface processing, coating, bonding, cleaning, drying, and the like. For example, the density of post-processing feature points present on the processed web 80B is higher than the density of pre-processing feature points present on the long web 80A. That is, when compared by the number of feature points per unit area, the number of post-processing feature points present on the processed web 80B is greater than the number of pre-processing feature points present on the long web 80A. This becomes prominent when the long web 80A is subjected to coating or bonding. For example, when the long web 80A is subjected to coating or bonding, the density of post-processing feature points present on the processed web 80B can be approximately 10 times the density of pre-processing feature points present on the long web 80A.
[0047] Note that the post-processing feature points present on the processed web 80B may also include the same feature points as the pre-processing feature points present on the long web 80A. Here, an example in which coating or lamination is performed on the long web 80A will be described. When coating or lamination is performed on the long web 80A, the processed web 80B can be regarded as a laminate in which a processed layer is formed on the long web 80A. In the optical inspection by the inspection device 90B in the second manufacturing process at factory B, not only the feature points present in the processed layer are detected, but also the feature points that were present on the long web 80A, and the feature points generated at the boundary between the long web 80A and the processed layer in accordance with the processing can also be detected. That is, in the inspection by the inspection device 90B, not only the surface layer of the processed web 80B but also the feature points present in the lower layer can be detected. This is due to the small thickness of the long web 80A and the processed layer. In particular, when the long web 80A is an optical film, the processed layer also has translucency, so in the inspection by the inspection device 90B, not only the surface layer of the processed web 80B but also the feature points present in the lower layer can be detected.
[0048] For example, the terminal device 70A generates pre-processing web information by performing image analysis on the image data of the long web 80A captured by the inspection device 90A. The inspection device 90A may generate the pre-processing web information.
[0049] For example, the terminal device 70B generates post-processing web information by performing image analysis on the image data of the processed web 80B captured by the inspection device 90B. The inspection device 90B may generate the post-processing web information.
[0050] For the image analysis, for example, a known technique is used. Specifically, pixels whose pixel values in the image deviate from the surrounding average value by a predetermined value or more are extracted as pre-processing feature points or post-processing feature points.
[0051] The pre-processing web information includes, for example, information about the position, size, shape, brightness, and defect degree of each of the multiple pre-processing feature points present in the long web 80A. The post-processing web information includes, for example, information about the position, size, shape, brightness, and defect degree of each of the multiple post-processing feature points present in the processed web 80B. The positional information of each pre-processing and post-processing feature point can be represented, for example, using XY coordinates. In the pre-processing and post-processing web information, multiple adjacent pre-processing or post-processing feature points may be clustered.
[0052] Terminal device 70A at factory A transmits, for example, first inspection data including pre-processing web information to the information processing system 50. Terminal device 70B at factory B transmits, for example, second inspection data including post-processing web information to the information processing system 50.
[0053] [Configuration of Information Processing System 50] Figure 4 is a block diagram showing the 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.
[0054] The control unit 51 includes, for example, a CPU and memory such as RAM and ROM. The CPU is composed of a multi-core processor that controls the above-mentioned parts and performs various calculations according to a program. Each function of the information processing system 50 is performed by the CPU executing the corresponding program. The specific functions of the control unit 51 will be described later.
[0055] The memory unit 52 is a large-capacity auxiliary storage device that stores various programs, including the operating system, and various data. For example, a hard disk, solid-state drive, flash memory, or ROM can be used for storage. The memory unit 52 stores, for example, a user list, a lot list, and an inspection data database. For example, the manager of factory A manages the user list and the lot list, respectively. The manager of factory A is, for example, an employee of the manufacturer operating factory A.
[0056] Figure 5A shows an example of a user list. The user list includes information such as each user's user ID, username, and contact information. Each user may have access rights to the inspection data DB, and for example, each user can access various data related to a predetermined long web 80A.
[0057] Figure 5B shows an example of a lot list. The lot list includes information such as the lot ID, product name, customer user ID, manufacturing conditions, size, and manufacturing date for each lot.
[0058] Figures 6A to 6C each show an example of an inspection data database. The inspection data database includes, for example, process lists for each process at factories A and B, inspection data for each inspection performed at factories A and B, and feature point classification data.
[0059] Figure 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 at each process, the process name, the web stretching ratio, the number of web layers, the orientation of the width and length, etc. The process list also includes information about each inspection performed at, for example, factories A and B. Information about each inspection includes, for example, the inspection ID of each inspection, the inspection equipment ID of the inspection equipment used for each inspection, the inspection data, and the date and time of the inspection. Information about the orientation of the width and length of the web is represented, for example, by whether it is the same as or reversed from the orientation of the width and length of the web in the previous process.
[0060] Figures 6B and 6C each show an example of inspection data for each inspection included in the process list. Figure 6B shows an example of inspection data with inspection ID i0101. This inspection data is, for example, the first inspection data for a long web 80A and includes pre-processing web information. Figure 6C shows an example of inspection data with inspection ID i0102. This inspection data is, for example, the second inspection data for a processed web 80B and includes post-processing web information. The first inspection data includes information for each of multiple pre-processing feature points, and the second inspection data includes information for each of multiple post-processing feature points. The information for pre-processing and post-processing feature points includes, for example, information on each feature point such as the feature point ID, position, area, length, width, maximum brightness, minimum brightness, classification, and presence or absence of concentrated dots.
[0061] The position of the feature point is represented, for example, by XY coordinates relative to a predetermined position on the long web 80A or the processed web 80B. The X coordinate is, for example, the width coordinate of the long web 80A or the processed web 80B, and can take a range of, for example, 0 to 3000 mm. The Y coordinate is, for example, the length coordinate of the long web 80A or the processed web 80B, and can take a range of, for example, 0 to 10000 m.
[0062] The classification of feature points represents, for example, the shape and brightness distribution of each feature point. Each feature point is classified into approximately 5 to 20 categories according to, for example, its shape and brightness distribution. The presence or absence of concentrated points indicates, for example, whether or not multiple feature points exist around that feature point.
[0063] The communication unit 53 is an interface that connects to external devices such as terminal devices 70A and 70B via a network.
[0064] [Generation process of inspection data DB] Here, an example of how the information processing system 50 generates the inspection data DB will be described. For example, the first inspection data is generated by the terminal device 70A and the inspection device 90A, and the second inspection data is generated by the terminal device 70B and the inspection device 90B.
[0065] Figure 7 is a flowchart showing an example of a method for generating the first test data.
[0066] (Step S11) The terminal device 70A instructs the long web manufacturing device 1000 to manufacture the long web 80A. For example, at this time, a roll of long web 80A is manufactured according to the shipping standard z.
[0067] (Step S12) Next, the terminal device 70A causes the inspection device 90A to acquire image data.
[0068] The inspection device 90A is either a transmission-type or reflection-type inspection device. The transmission-type inspection device 90A irradiates light onto the long web 80A and receives the light that has passed through the long web 80A. This detects pre-processing feature points present on the long web 80A. The reflection-type inspection device 90A irradiates light onto the long web 80A and receives the light reflected by the long web 80A. This detects pre-processing feature points present on the long web 80A. The transmission-type inspection device and the reflection-type inspection device each include a bright-field inspection device and a dark-field inspection device, respectively.
[0069] Figures 8A and 8B show an example of the configuration of a reflective inspection device 90A. Figure 8A shows the configuration of the inspection device 90A viewed from the width direction of the long web 80A. Figure 8B shows the configuration of the inspection device 90A viewed from the transport direction of the long web 80A. The inspection device 90A includes, for example, a light source 91, a camera 92, an analysis unit 93, and a storage unit 94.
[0070] In the inspection device 90A, the camera 92 captures images of the surface of the long web 80A and generates image data. The number of cameras 92, the field of view, and the distance to the surface of the long web 80A are set appropriately so that the entire width of the long web 80A is captured. Figure 8B shows an inspection device 90A having two cameras 92 in the width direction.
[0071] The light source 91 irradiates light onto the inspection area of the long web 80A. The light source 91 irradiates light uniformly in the width direction of the roll-shaped long web 80A. Here, uniform irradiation means that the illuminance of the irradiated light is approximately the same.
[0072] Camera 92 is an optical sensor that optically reads the inspection area of the long web 80A. Camera 92 includes an image sensor such as a CCD and CMOS, and a lens, etc. CCD is an abbreviation for Charge Coupled Device. CMOS is an abbreviation for Completerity Metal Oxide Semiconductor. Camera 92 generates two-dimensional image data from the output signals of each image sensor. Camera 92 detects diffused light from the light reflected from the surface of the long web 80A after being irradiated by the light source 91. Camera 92 may be a color camera or a monochrome camera. Camera 92 may detect light in the visible light region or light in the infrared region.
[0073] The camera 92 can, for example, read the entire width of the long web 80A at once. It is desirable that the contrast of the image data captured by the camera 92 be above a predetermined value. In other words, it is desirable that the area of the long web 80A illuminated by light from the light source 91 and the unilluminated area have a contrast of above a predetermined value. To generate image data with a contrast of above a predetermined value, it is desirable to use a powerful and highly directional light source 91.
[0074] Here, "powerful" means, for example, that 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, that 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 condition (E50 - E100) / E50 < 0.5 is satisfied.
[0075] Camera 92 is positioned, for example, to receive specularly reflected light from light source 91. Camera 92 may also be positioned to avoid specularly reflected light from light source 91, that is, to receive diffused light from the long web 80A.
[0076] The analysis unit 93 consists of a CPU and RAM, etc. The analysis unit 93 reads various processing programs stored in the memory unit 94, loads them into RAM, and performs various processing in cooperation with the programs. The analysis unit 93 processes image data captured by the camera 92 to detect pre-processing feature points present in the long web 80A. For example, the analysis unit 93 applies predetermined image processing to the image data, then detects feature points and quantitatively evaluates each detected feature point.
[0077] 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 a single image data of the entire surface of the long web 80A and store it in the storage unit 94. Alternatively, the analysis unit 93 may generate multiple image data associated with the shooting time and store them 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 determines the position in the length direction of the long web 80A based on the shooting time by, for example, referring to the stored transport speed. In the following description, it will be assumed that the analysis unit 93 generates multiple image data associated with the shooting time and stores them in the storage unit 94.
[0078] The storage unit 94 is composed of an HDD and an SSD, etc. SSD is an abbreviation for Solid State Drive. The storage unit 94 stores various processing programs and data necessary for the execution of those programs. For example, the storage unit 94 stores image data captured by the camera 92, linked to the time of capture. The storage unit 94 also stores manufacturing conditions, such as the winding speed in the long web manufacturing apparatus 1000. The manufacturing conditions in the first manufacturing process may be included in the process list of the inspection DB.
[0079] Figure 8C shows an example of a transmissive inspection device 90A. In this inspection device 90A, the light source 91 is positioned opposite the camera 92, with a long web 80A in between.
[0080] 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 long web 80A and a camera for detecting foreign matter inside the long web 80A. The first inspection data may use data from some of the multiple inspection units, or a combination of the results from the multiple inspection units may be used.
[0081] (Step S13) The terminal device 70A causes the inspection device 90A to detect multiple pre-processing 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.
[0082] 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 multiple regions. For example, the analysis unit 93 divides the image data into n regions in the width direction. n regions can be, for example, several to several dozen. Hereinafter, the n regions will be referred to as region a1 to region an.
[0083] Next, the analysis unit 93 acquires image data of one region a1 and performs mathematical processing on the image data of region a1. Mathematical processing includes, for example, preprocessing, enhancement processing, signal processing, and image feature extraction.
[0084] Image preprocessing includes, for example, image cropping, low-pass filtering, high-pass filtering, Gaussian filtering, median filtering, bilateral filtering, morphological transformation, color transformation, contrast adjustment, noise reduction, blur / blur image restoration, masking, Hough transform, and projection transformation. Color transformations include, for example, L*a*b*, sRGB, HSV, and HSL.
[0085] Enhancement processes include, for example, the Sobel filter, Scharr filter, Laplacian filter, Gabor filter, and Canny method.
[0086] Signal processing includes, for example, calculating basic statistics, sums of squares and roots, differences, sums, products, ratios, and distance matrices, differential and integral calculus, thresholding, Fourier transforms, wavelet transforms, and peak detection. Basic statistics include, for example, maximum, minimum, mean, median, standard deviation, variance, and quartiles. Thresholding includes, for example, binarization and adaptive binarization. Peak detection includes, for example, detecting peak values, number of peaks, or full width at half maximum.
[0087] Image feature extraction includes template matching and SIFT feature extraction, among others.
[0088] The analysis unit 93 performs mathematical processing on the image data of region a1, and then performs thresholding on the values obtained from this processing. Thresholding is a process that determines whether or not a point is a pre-processing feature point based on a predetermined threshold, and also determines the size of the pre-processing feature point, etc.
[0089] The analysis unit 93 performs the same processing on regions other than region a1.
[0090] After processing each region a1 to an, the analysis unit 93 integrates the results for each region a1 to an, and the data processing is completed. Specifically, the analysis unit 93 generates data that associates the position and size of the pre-processing feature points detected for each region.
[0091] After this, the analysis unit 93 stores the processing 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 from the inspection of one long web 80A to obtain processing results. By aggregating these processing results, the first inspection data is generated.
[0092] (Step S14) The terminal device 70A transmits the first inspection data generated by the inspection device 90A to the information processing system 50, which stores it in the inspection data DB of the storage unit 52.
[0093] Figure 9 is a flowchart showing an example of a method for generating second-stage test data.
[0094] (Step S21) The terminal device 70B instructs the processed web manufacturing device 2000 to manufacture the processed web 80B. For example, at this time, the processed web manufacturing device 2000 applies a predetermined material to a part of the long web 80A, thereby manufacturing multiple lots of processed webs 80B.
[0095] (Step S22) Next, the terminal device 70B causes the inspection device 90B to acquire image data. The inspection device 90B has, for example, a light source 91, a camera 92, an analysis unit 93, and a storage unit 94, similar to the inspection device 90A. For example, the same measurement system inspection device as the inspection device 90A is used in the inspection device 90B. For example, if the inspection device 90A is a reflective type inspection device, the inspection device 90B is a reflective type inspection device. By making the inspection method of the inspection device 90B the same as the inspection method of the inspection device 90A, it becomes easy to compare the inspection results. Depending on the differences in the performance, quality and product specifications required for the web, the inspection devices 90A and 90B may use inspection devices with different measurement systems, and may inspect the long web 80A or the processed web 80B under different measurement conditions.
[0096] (Step S23) The analysis unit 93 generates second inspection data by detecting post-processing feature points from the image data using the same process as in step S13.
[0097] (Step S24) The terminal device 70B transmits the second inspection data generated by the inspection device 90B to the information processing system 50, which stores it in the inspection data DB of the storage unit 52.
[0098] [Functions of the Information Processing System 50] Figure 10 shows an example of the functions of the information processing system 50. The information processing system 50 functions as an acquisition unit 511, a map generation unit 512, an output unit 513, a first condition setting unit 514, a first alignment unit 515, a specific unit 516, a second condition setting unit 517, and a second alignment unit 518, by having the control unit 51 read a program stored in the storage unit 52 and execute processing.
[0099] The acquisition unit 511 acquires pre-processing web information and post-processing web information. For example, the first inspection data includes pre-processing web information. For example, the second inspection data includes post-processing web information. The acquisition unit 511 acquires pre-processing web information and post-processing web information by, for example, acquiring the first inspection data and the second inspection data stored in the storage unit 52. The acquisition unit 511 may also acquire pre-processing web information and post-processing web information from terminal devices 70A, 70B or inspection devices 90A, 90B. The pre-processing web information includes at least location information of pre-processing feature points, and the post-processing web information includes at least location information of post-processing feature points.
[0100] The map generation unit 512 generates a pre-processing compressed feature point map and a post-processing compressed feature point map. The pre-processing compressed feature point map is a map corresponding to the positional information of pre-processing feature points assuming that the long web 80A is compressed at a predetermined compression ratio. The map generation unit 512 generates the pre-processing compressed feature point map based on the pre-processing web information acquired by the acquisition unit 511. The map generation unit 512 virtually compresses the long web 80A to such an extent that the entire pre-processing compressed feature point map can be displayed on one screen of the display unit 76 of the terminal device 70A or terminal device 70B. At this time, the compression ratio in the length direction of the long web 80A is higher than the compression ratio in the width direction of the long web 80A. For example, when the length of the long web 80 is 3900 m and the width is 2000 mm, the length of the generated pre-processing compressed feature point map is 120 mm and the width is 50 mm. The map generation unit 512 generates such a pre-processing feature point map, making it easier for the user to grasp the overall trend of the pre-processing feature points present in the long web 80A.
[0101] The post-processed compressed feature point map is a map corresponding to the positional information of the post-processed feature points. The map generation unit 512 generates the post-processed compressed feature point map based on a predetermined compression ratio used when generating the pre-processed compressed feature point map and the post-processed web information acquired by the acquisition unit 511. For example, the map generation unit 512 virtually compresses the processed web 80B with the same compression ratio as the predetermined compression ratio used when generating the pre-processed compressed feature point map to generate the post-processed compressed feature point map. If a process that changes the size of the web is performed between the time the long web 80A is manufactured and the time the processed web 80B is manufactured, the map generation unit 512 adjusts the compression ratio of the processed web 80B taking this process into consideration. A process that changes the size of the web is, for example, web stretching.
[0102] The output unit 513 outputs, for example, the pre-processed compressed feature point map and the post-processed compressed feature point map generated by the map generation unit 512 to the display unit 76 of the terminal device 70A or terminal device 70B. As a result, the display unit 76 displays a screen including the pre-processed compressed feature point map and the post-processed compressed feature point map. The output unit 513 may also output the pre-processed compressed feature point map and the post-processed compressed feature point map to an external display device.
[0103] Figure 11 shows an example of the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM displayed on the display unit 76. In Figure 11, pre-processed feature points 81A present in the pre-processed compressed feature point map 80AM are represented by white circles, and post-processed feature points 81B present in the post-processed compressed feature point map 80BM are represented by black circles. The output unit 513, for example, overlays the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM on the display unit 76. This makes it easier for the user to compare the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM.
[0104] At least one of the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM is configured to be movable in the X and Y directions. For example, a user can move the cursor 761 displayed on the display unit 76 to the post-processed compressed feature point map 80BM and perform a drag operation. This moves the post-processed compressed feature point map 80BM.
[0105] Figure 12 shows an example of the post-compressed feature point maps 80BM-1, 80BM-2, and 80BM-3 displayed on the display unit 76. For example, post-compressed feature point map 80BM-1 is a map corresponding to the location information of post-compressed feature points present in the processed web 80B-1. Post-compressed feature point map 80BM-2 is a map corresponding to the location information of post-compressed feature points present in the processed web 80B-2. Post-compressed feature point map 80BM-3 is a map corresponding to the location information of post-compressed feature points present in the processed web 80B-3. For example, post-compressed feature point map 80BM-1 corresponds to a specific example of the first post-compressed feature point map of the present invention, and post-compressed feature point map 80BM-2 corresponds to a specific example of the second post-compressed feature point map of the present invention.
[0106] The output unit 513 may overlay the pre-processing compressed feature point map 80AM and the post-processing compressed feature point maps 80BM-1, 80BM-2, and 80BM-3 on the display unit 76. This makes it easier for the user to understand the positional relationship between the long web 80A and the processed webs 80B-1, 80B-2, and 80B-3 of multiple lots manufactured from this long web 80A. In Figure 12, the illustration of pre-processing feature points present in the pre-processing compressed feature point map 80AM and post-processing feature points present in the post-processing compressed feature point maps 80BM-1, 80BM-2, and 80BM-3 is omitted.
[0107] The first condition setting unit 514 sets first feature point conditions for feature points present in the long web 80A and the processing web 80B, respectively. The first feature point conditions are set for, for example, the area, length, width, brightness, or classification of the feature point. The first feature point conditions may also be set for the type of inspection device 90A, 90B. The first condition setting unit 514 sets the first feature point conditions based on, for example, information input by the user. The user inputs the first feature point conditions to the information processing system 50, for example, via the operation reception unit 77 of the terminal device 70A or terminal device 70B. The first condition setting unit 514 may also set the first feature point conditions based on information stored in the storage unit 52, etc.
[0108] The map generation unit 512 generates, for example, a pre-processing compressed feature point map 80AM and a post-processing compressed feature point map 80BM for feature points that meet the first feature point condition. This makes it possible to generate a pre-processing compressed feature point map 80AM and a post-processing compressed feature point map 80BM that focus on high-importance feature points, even when there are many feature points in the long web 80A and the processed web 80B.
[0109] Figure 13 shows an example of a pre-processed compressed feature point map 80AM and a post-processed compressed feature point map 80BM generated for feature points that meet a predetermined first feature point condition. For example, when the first feature point condition is an area less than or equal to a predetermined size, the map generation unit 512 deletes feature points with an area exceeding the predetermined size from the long web 80A and the processed web 80B, respectively, to generate a pre-processed compressed feature point map 80AM and a post-processed compressed feature point map 80BM. This allows the user to more easily compare the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM.
[0110] The first alignment unit 515 aligns the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM generated by the map generation unit 512. The first alignment unit 515 aligns the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM based on information input from the user, for example. The first alignment unit 515 roughly aligns the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM, for example.
[0111] Figure 14 shows an example of a pre-processed compressed feature point map 80AM and a post-processed compressed feature point map 80BM aligned by the first alignment unit 515. For example, the user moves the post-processed compressed feature point map 80BM using the cursor 761 while comparing the size and arrangement of the displayed pre-processed feature points 81A and post-processed feature points 81B. For example, when the post-processed compressed feature point map 80BM is placed in the region 80AMS of the pre-processed compressed feature point map 80AM, multiple post-processed feature points 81B overlap with multiple pre-processed feature points 81A. For example, at this time, the first alignment unit 515 determines that the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM have been aligned.
[0112] The first alignment unit 515 may align the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM using image processing technology. Examples of image processing technology include SIFT, SURF, ORB, HOG, LBP, deep learning, distance calculation, and image hashing. SIFT is an abbreviation for Scale-Invariant Feature Transform. SURF is an abbreviation for Speeded-Up Robust Features. ORB is an abbreviation for Oriented FAST and Rotated BRIEF. HOG is an abbreviation for Histogram of Oriented Gradients. LBP is an abbreviation for Local Binary Patterns.
[0113] The identification unit 516 identifies a specific region based on the alignment result by the first alignment unit 515. The specific region is a part of the long web 80A.
[0114] Figure 15 shows a specific region 80AS of the long web 80A together with the processing web 80B. The identification unit 516 identifies the specific region 80AS based, for example, on the region 80AMS (Figure 14) of the pre-processed compressed feature point map 80AM. The specific region 80AS includes, for example, the corresponding region of the long web 80A that corresponds to region 80AMS, and the marginal region surrounding this corresponding region. The size of the marginal region may be stored in the storage unit 52, etc., or it may be set by the user. By identifying the specific region 80AS of the long web 80A in this way, the processing load performed by the second alignment unit 518 is reduced. The identification unit 516 may also identify a part of the processing web 80B.
[0115] The output unit 513 may display the pre-processing feature points in the specific region 80AS and its vicinity, and the post-processing feature points in the processed web 80B, on the display unit 76 or the like.
[0116] The second condition setting unit 517 sets the second feature point conditions for the feature points. The second feature point conditions are set, for example, for the position of the feature point, the area, length, width, brightness, or classification of the feature point. The second feature point conditions may also be set for the type of inspection device 90A, 90B. The second condition setting unit 517 sets the second feature point conditions, for example, based on information input from the user. The user inputs the second feature point conditions to the information processing system 50, for example, via the operation reception unit 77 of terminal device 70A or terminal device 70B. The second condition setting unit 517 may also set the second feature point conditions based on information stored in the storage unit 52, etc.
[0117] The second alignment unit 518 aligns the XY coordinates of the long web 80A with the XY coordinates of the processed web 80B. Specifically, the second alignment unit 518 associates predetermined pre-processing feature points located in a specific region 80AS of the long web 80A with predetermined post-processing feature points located in the processed web 80B based on their relative positions. At this time, the second alignment unit 518 associates pre-processing and post-processing feature points that meet the second feature point condition. This more effectively reduces the processing load of the second alignment unit 518.
[0118] The second alignment unit 518 associates predetermined pre-processing feature points in a specific region 80AS with predetermined post-processing feature points in the processed web 80B, based on the pre-processing web information and post-processing web information acquired by the acquisition unit 511. The output unit 513 outputs the alignment result from the second alignment unit 518 to the display unit 76.
[0119] [Processing performed by the information processing system 50] Figure 16 is a flowchart showing an example of the procedure for processing performed by the information processing system 50. The processing of the information processing system 50 shown in the flowchart of Figure 16 is stored as a program in the storage unit 52 of the information processing system 50 and is executed by the CPU controlling each part.
[0120] (Step S31) The information processing system 50 acquires first inspection data and second inspection data for the same lot, for example, in response to instructions from a user via terminal device 70A or terminal device 70B. When multiple lots of processed webs 80B are manufactured from one lot of long webs 80A, the information processing system 50 may acquire multiple second inspection data. The information processing system 50 may acquire first inspection data and second inspection data when the first inspection data and second inspection data are available. For example, the first inspection data includes pre-processing web information, and the second inspection data includes post-processing web information.
[0121] (Step S32) The information processing system 50 performs preprocessing on the first inspection data and the second inspection data in order to generate the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM.
[0122] Figure 17 is a schematic diagram showing an example of the processing in step S32. The information processing system 50, for example, inverts the Y coordinate of the processing web 80B as preprocessing for the second inspection data. This aligns the difference in Y coordinates caused by winding in the first manufacturing process and unwinding in the second manufacturing process. The information processing system 50 may also invert the X coordinate of the processing web 80B depending on the installation position of the camera 92 in the first and second manufacturing processes, for example. The information processing system 50 may also transform the XY coordinates of the processing web 80B depending on the stretching rate of the processing web 80B. The information processing system 50 may also align the XY coordinate system of the long web 80A with the XY coordinate system of the processing web 80B.
[0123] The information processing system 50 further performs noise reduction processing as preprocessing for the first inspection data and the second inspection data, respectively. The noise reduction processing includes, for example, at least one of the following: removal of low-intensity feature points, removal of extremely small feature points, and removal of consecutive dots. The noise reduction 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 ends of the long web 80A or the processing web 80B.
[0124] (Step S33) After performing preprocessing on the first inspection data and the second inspection data, the information processing system 50 generates a pre-processed compressed feature point map 80AM based on the pre-processed web information contained in the first inspection data.
[0125] (Step S34) Next, the information processing system 50 generates a post-compressed feature point map 80BM based on the predetermined compression ratio used in step S33 and the post-processed web information included in the second inspection data.
[0126] (Step S35) Next, the information processing system 50 outputs the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM generated in steps S32 and S33 to, for example, the display unit 76. As a result, the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM are displayed on the display unit 76. For example, the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM are displayed superimposed on each other on the display unit 76.
[0127] (Step S36) Next, the information processing system 50 sets the first feature point conditions. The information processing system 50 sets the first feature point conditions based on information input from the user, for example. The information processing system 50 may perform the processing of step S36 before the processing of step S35. The information processing system 50 generates a pre-processed compressed feature point map 80AM and a post-processed compressed feature point map 80BM for feature points that meet the first feature point conditions, and displays these on the display unit 76.
[0128] (Step S37) Next, the information processing system 50 performs alignment of the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM generated in steps S32 and S33. The information processing system 50 performs alignment of the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM based on information input from the user, for example. The information processing system 50 may perform alignment for the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM that conform to the first feature point conditions set in step S36.
[0129] (Step S38) Next, the information processing system 50 identifies a portion of the long web 80A, i.e., a specific region 80AS, based on the alignment result of step S37.
[0130] (Step S39) Next, the information processing system 50 sets the second feature point conditions. The information processing system 50 sets the second feature point conditions based on information input from the user, for example. The information processing system 50 may perform the process of step S39 before the process of step S38.
[0131] (Step S40) Next, the information processing system 50 performs coordinate system alignment between the specific region 80AS of the long web 80A identified in step S38 and the processing web 80B, and terminates the processing. At this time, the information processing system 50 performs coordinate system alignment between the specific region 80AS and the processing web 80B using, for example, feature points that conform to the second feature point conditions set in step S39.
[0132] Figure 18 is a subroutine flowchart showing the alignment process in step S40. Figure 19 is a schematic diagram illustrating each process in step S40.
[0133] (Rough adjustment: Steps S401 to S403) First, the information processing system 50 roughly adjusts the XY coordinates of the feature points of the long web 80A and the processed web 80B as follows. For example, the information processing system 50 first shifts the coordinate position of a predetermined post-processed feature point of the processed web 80B by a predetermined amount. Next, the information processing system 50 calculates the distances L1 to Lm between this predetermined post-processed feature point of the processed web 80B and the pre-processed feature point of the long web 80A corresponding to this post-processed feature point, and selects the shift amount (x1, y1) whose sum is the smallest. The information processing system 50 may use the average value instead of the sum. For example, the information processing system 50 determines the pre-processed feature point of the long web 80A that has the coordinate position closest to the coordinate position of the predetermined post-processed feature point of the processed web 80B as the pre-processed feature point of the long web 80A corresponding to the predetermined post-processed feature point of the processed web 80B.
[0134] The information processing system 50, for example, shifts the coordinate positions of predetermined post-processed feature points of the processed web 80B sequentially from (-shift_x, -shift_y) to (+shift_x, +shift_y) around the central shift amount (0,0) using a fixed coarse adjustment shift amount a step size. From the coordinate positions of these predetermined post-processed feature points of the processed web 80B, it calculates the distances L1 to Lm to each of the pre-processed feature points 1 to m of the long web 80A. Then, from (-shift_x, -shift_y) to (+shift_x, +shift_y), it selects the shift amount (x1, y1) that minimizes the sum of distances L1 to Lm.
[0135] For example, if the coarse adjustment shift amount a = 1.0 mm, then (-shift_x, -shift_y) = (-10 mm, -10 mm) and (-shift_x, +shift_y) = (+10 mm, +10 mm). The information processing system 50 may also make the units for the X direction and the Y direction different for the coarse adjustment shift amount a. For example, the X direction may be in millimeters and the Y direction in meters, so (-shift_x, -shift_y) = (-10 mm, -10 m) and (-shift_x, +shift_y) = (+10 mm, +10 m).
[0136] (Fine-tuning: Steps S404-S406) Next, the information processing system 50 fine-tunes the XY coordinates of the feature points of the long web 80A and the processed web 80B, and selects a shift amount (x2, y2). The information processing system 50 selects a shift amount (x2, y2) in much the same manner as in steps S401-S403 above. Steps S404-S406 differ from steps S401-S403 in the following respects, for example: The fine-tuning shift amount b in step S404 is smaller than the coarse-tuning shift amount a. Also, the center shift amount in step S405 uses the shift amount (x1, y1) selected in step S403. For example, the fine-tuning shift amount b is sufficiently smaller than the coarse-tuning shift amount a, for example, 0.1 mm, which is one order of magnitude smaller.
[0137] (Step S407) The information processing system 50 uses the shift amount (x2, y2) selected in step S406 to perform a coordinate transformation process on all post-processed feature points of the processing web 80B.
[0138] (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 it is above the predetermined threshold, the information processing system 50 may determine that the coordinate transformation process in step S407 was inappropriate.
[0139] (Step S409) If the alignment is incorrect, i.e., YES, the information processing system 50 terminates the process. If it is incorrect, the information processing system 50 may display an error message on the display unit 76 or record in the inspection data DB that the calculation cannot be performed. On the other hand, if the alignment is correct, i.e., NO, the information processing system 50 returns to the process shown in Figure 16.
[0140] [Effects of the Information Processing System 50] In the information processing system 50 according to the present invention, a pre-processing compressed feature point map 80AM and a post-processing compressed feature point map 80BM are generated, and their positions are aligned. This allows the approximate positional relationship between the long web 80A and the processed web 80B to be understood. Therefore, it becomes possible to associate the webs of each process with each other based on their positions. The effects of this system will be explained below.
[0141] In the process of manufacturing webs such as optical films, it is preferable to align the webs at each stage of the process. For example, this alignment allows for tracking characteristic points of the web generated at each stage, making it possible to analyze which manufacturing stage is responsible for defects in the product. This helps to suppress the decrease in web manufacturing efficiency and yield caused by defects.
[0142] However, aligning the web at each stage of the process is not easy. This is because the size of the web's processing area, especially its length, changes during the manufacturing process. In recent years, raw webs have become longer, and the length of the web's processing area often changes significantly during the manufacturing process. This is because, for webs used in optical films and the like, strict specifications are required, leading to an increase in the portion of the raw web that is not used in the next process, i.e., the unused portion. In other words, it is due to an increase in the unused portion 80Z shown in Figure 3. In addition, inspection data is not obtained for this unused portion 80Z. This is because obtaining inspection data for the unused portion 80Z would result in a huge accumulation of unnecessary data. Under these circumstances, aligning the web at each stage of the process becomes difficult. In particular, when it is not possible to mark the web, aligning the web becomes difficult.
[0143] Furthermore, for example, in post-processing steps where the raw web is processed, when coating or lamination is applied intermittently to the raw web, the lengthwise size of the processed portion of the web changes from the lengthwise size of the raw web. In such cases, as described above, aligning the web at each step becomes difficult.
[0144] This will be explained using Figure 3. The processed web 80B-2 in Figure 3 is a web in which a predetermined process has been applied to the second part 80A-2 of the long web 80A. In web alignment, the pre-processing detection results, which detect pre-processing feature points present in the long web 80A, and the post-processing detection results, which detect post-processing feature points present in the processed web 80B-2, are compared and aligned. That is, the second part 80A-2 is identified using the pre-processing inspection results and the post-processing inspection results. At that time, as mentioned above, the long web 80A has multiple unused parts 80Z, and the length of each unused part 80Z is often not recorded. Therefore, in order to identify the position of the second part 80A-2, it is necessary to compare the pre-processing detection results and the post-processing detection results over a wide area of the long web 80A. As mentioned above, the length of the long web 80A is on the order of 1000m, and it was difficult to compare the detection results over that length.
[0145] In contrast, the information processing system 50 first generates a pre-processing compressed feature point map 80AM from the long web 80A, and then generates a post-processing compressed feature point map 80BM from the processed web 80B. The information processing system 50 then aligns the pre-processing compressed feature point map 80AM and the post-processing compressed feature point map 80BM. Therefore, the user can easily grasp the approximate area of the long web 80A that corresponds to the processed web 80B. The information processing system 50 can be used particularly well when it is not possible to mark the web.
[0146] Furthermore, the information processing system 50 may set a first feature point condition. This allows the information processing system 50 to generate a pre-processing compressed feature point map 80AM and a post-processing compressed feature point map 80BM for feature points that meet this first feature point condition. As described above, tens to hundreds of feature points are detected from the image data of the long web 80A and the processed web 80B. When the pre-processing compressed feature point map 80AM and the post-processing compressed feature point map 80BM are created based on this data, the density of feature points on the compressed feature point map becomes even higher. Therefore, when the pre-processing compressed feature point map 80AM and the post-processing compressed feature point map 80BM are generated for feature points that meet the first feature point condition, attention can be focused only on the feature points of high importance. Thus, the pre-processing compressed feature point map 80AM and the post-processing compressed feature point map 80BM can be aligned using only the feature points of high importance.
[0147] Furthermore, the information processing system 50 identifies a specific region 80AS of the long web 80A based on the alignment results of the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM. Then, coordinate system alignment is performed between this specific region 80AS and the processed web 80B. This allows the user to understand the position of the processed web 80B relative to the long web 80A with higher accuracy. In addition, since only a part of the long web 80A, i.e., the specific region 80AS, is identified, the processing load is reduced compared to performing coordinate system alignment between the entire long web 80A and the processed web 80B.
[0148] The effects of the information processing system 50 aligning the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM using image processing technology will be explained. When the information processing system 50 performs alignment using image processing technology, if the figures formed by adjacent feature points include characteristic shapes, the processing time is reduced and the accuracy of the alignment is improved. It is conceivable that the density of feature points increases when the information processing system 50 generates a compressed feature point map, and the number of combinations of feature points that form the characteristic shapes described above increases. Therefore, when the information processing system 50 aligns the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM using image processing technology, the processing time is reduced and the accuracy of the alignment is improved.
[0149] The following describes modifications and other embodiments of the information processing system 50 described in the first embodiment above. In order to avoid repetition of explanations, detailed explanations of configurations similar to those of the information processing system 50 described in the first embodiment above will be omitted below.
[0150] <Modified Example> Figure 20 shows an example of the functions of the modified information processing system 50. In addition to the acquisition unit 511, map generation unit 512, output unit 513, first condition setting unit 514, first alignment unit 515, identification unit 516, second condition setting unit 517, and second alignment unit 518, this information processing system 50 may also function as a classification unit 519.
[0151] The classification unit 519 uses the alignment results from the second alignment unit 518 to classify the pre-processing feature points present in the long web 80A and the post-processing feature points present in the processed web 80B into first-type feature points, second-type feature points, and third-type feature points. The XY coordinates of these pre-processing and post-processing feature points are aligned by the second alignment unit 518.
[0152] Figure 21 is a table for explaining each of the first to third type feature points. Multiple pre-processing feature points present in the long web 80A can be classified, for example, into first-type and third-type feature points. Multiple post-processing feature points present in the processed web 80B can be classified, for example, into second-type and third-type feature points.
[0153] Type 1 feature points are feature points that exist only in the long web 80A and not in the processed web 80B. In other words, Type 1 feature points are feature points that disappeared in the second manufacturing process. Even if these Type 1 feature points exist in the long web 80A, they are feature points that are relatively unlikely to affect processes after the second manufacturing process. In this specification, feature points that do not exist in the web or have disappeared do not necessarily have to be completely gone, and the concept also includes feature points that exist as feature points but are unlikely to be problematic as defects.
[0154] Type 2 feature points are feature points that are not present in the long web 80A but are present in the processed web 80B. In other words, Type 2 feature points are feature points newly generated in the second manufacturing process. These Type 2 feature points are feature points that originate from the second manufacturing process.
[0155] Type 3 feature points are feature points that exist in both the long web 80A and the processed web 80B. That is, Type 3 feature points are feature points that are generated in the first manufacturing process and remain in the second manufacturing process. These Type 3 feature points are feature points that have a relatively high probability of affecting processes from the second manufacturing process onward. Note that the shape and size of Type 3 feature points may change due to the second manufacturing process compared to when they were present in the long web 80A. Depending on the manufacturing process, additional failures may occur. For example, in the second manufacturing process, which stretches the long web 80A, small foreign matter from the first manufacturing process can cause bubbles called voids to form around it.
[0156] In the information processing system 50, for example, pre-processing feature points and post-processing feature points are classified into first-type feature points, second-type feature points, and third-type feature points and stored. The information processing system 50 may distinguish between the first-type feature points, second-type feature points, and third-type feature points and display them on a display unit 76 or the like.
[0157] Figure 22 is a flowchart showing an example of the processing procedure performed in this information processing system 50.
[0158] (Steps S31 to S40) First, the information processing system 50 executes the processes of steps S31 to S40, as described in the first embodiment above.
[0159] (Step S51) Next, the information processing system 50 compares each of the pre-processing feature points of the long web 80A with each of the post-processing feature points of the processed web 80B. The coordinates of each of these post-processing feature points have been transformed by the process in step S40. As a result, the pre-processing feature points and post-processing feature points are classified into one of three types: first-type feature points, second-type feature points, or third-type feature points. The information processing system 50 then, for example, saves the classification results of the feature points in the inspection data DB of the storage unit 52 and terminates the process.
[0160] In the modified information processing system 50, the aligned pre-processing and post-processing feature points are classified into Type 1 feature points, Type 2 feature points, and Type 3 feature points. Therefore, managers of each manufacturing process can easily grasp the remaining defect status between the first and second manufacturing processes by checking the Type 3 feature points. In other words, managers of each manufacturing process can easily analyze defects between manufacturing processes. Thus, it becomes possible to suppress the decrease in web manufacturing efficiency and yield caused by defects.
[0161] <Second Embodiment> Figure 23 is a subroutine flowchart representing the alignment process of the information processing system 50 according to the second embodiment. Figure 23 corresponds to Figure 18 described in the first embodiment above. This information processing system 50 uses kernel density estimation to align the XY coordinates of the long web 80A and the processing 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 produces the same effects.
[0162] (Step S451) The information processing system 50 obtains a probability density function by performing kernel density estimation on the pre-processing feature points of the long web 80A. The kernel density estimation is performed in two dimensions, and a Gaussian kernel is used as the kernel function. For example, a predetermined value is used for the bandwidth. For example, a table associating 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 it may use different bandwidth values depending on the number of pre-processing feature points present in the long web 80A. When the information processing system 50 estimates the kernel density of a predetermined feature point, it takes into account the data surrounding this feature point. Then, the information processing system 50 sums up the densities of each feature point and obtains a probability density function.
[0163] Figure 24 shows an example of a probability density function calculated by kernel density estimation. The vertical and horizontal axes in Figure 24 represent the X and Y coordinates, and the intensity of the color represents the density.
[0164] (Step S452) The information processing system 50 obtains the probability density function of each post-processed feature point of the processed web 80B in the same manner as the process in step S451.
[0165] (Steps S453 to S455) The information processing system 50 compares the two obtained probability density functions and makes a correspondence from the density distribution. Then, the information processing system 50 calculates a transformed row example based on the correspondence result and performs a coordinate transformation of the XY coordinates on the processed feature points of the processed web 80B.
[0166] (Steps S456 to S457) The information processing system 50 performs the processing in steps S456 to S457 in the same manner as in steps S406 to S407 in Figure 18.
[0167] In this second embodiment of the information processing system 50, similar to that described in the first embodiment, a pre-processing compressed feature point map 80AM and a post-processing compressed feature point map 80BM are generated and aligned. This allows the approximate positional relationship between the long web 80A and the processed web 80B to be understood. Therefore, it becomes possible to associate the positions of each web formed in each process with each other.
[0168] The information processing system 50 may align the feature points of the long web 80A and the processed web 80B by other means. For example, the information processing system 50 may perform kernel density estimation of the feature points of one of the long web 80A and the processed web 80B. In this case, the information processing system 50 compares the obtained probability density function with that of the other feature point. This allows the information processing system 50 to align the feature points of the long web 80A and the processed web 80B.
[0169] <Third Embodiment> Figure 25 is a schematic diagram showing an application example of the information processing system 50 according to the third embodiment. Figure 25 corresponds to Figure 1 of the first embodiment described above, but in Figure 25, some configurations such as terminal devices 70A and 70B are omitted. 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 carried out, for example, web 80ba becomes web 80bb through the first sub-process. This web 80bb becomes web 80bc through the second sub-process. This web 80bc becomes processed web 80B through the third sub-process. Web 80ba is, for example, a long web 80A transported from factory A. The first sub-process, the second sub-process and the third sub-process are, for example, coating processes. That is, processed web 80B is a laminate including the long web 80A. The first, second, and third sub-processes may include auxiliary processes such as drying processes. The first, second, and third sub-processes may also include bonding processes such as lamination processes, slitting processes to cut off the edges of the film, bonding processes for transport protective films, and peeling processes for transport protective films.
[0170] Factory B may have multiple inspection devices installed. 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 factory A may have multiple inspection devices installed. Factory A and factory B may each have multiple inspection devices installed.
[0171] Figure 26 shows the details of each of the inspection devices 90A, 90B0, 90B1, 90B2, and 90B3. Data A is acquired from inspection device 90A, data B0 from inspection device 90B0, data B1 from inspection device 90B1, data B2 from inspection device 90B2, and data B3 from inspection device 90B3.
[0172] Figure 27 shows an example of a combination of first and second inspection data. For example, the first inspection data is data A and the second inspection data is data B0. For example, the first inspection data is data B0 and the second inspection data is data B1. For example, the first inspection data is data B1 and the second inspection data is data B2. For example, the first inspection data is data B2 and the second inspection data is data B3. For example, the first inspection data is data A and the second inspection data is data B3. The first and second inspection data can be any combination of inspection data obtained in different processes, and combinations other than those shown above are also acceptable.
[0173] In this third embodiment, the information processing system 50 also generates a pre-processing compressed feature point map 80AM and a post-processing compressed feature point map 80BM, similar to those described in the first embodiment, and aligns them. This allows the approximate positional relationship between the long web 80A and the processed web 80B to be understood. Therefore, it becomes possible to associate the positions of each web formed in each process with each other.
[0174] (Long Web Manufacturing Apparatus 1000) Figure 28 shows an example of the schematic configuration of the long web manufacturing apparatus 1000. The long web manufacturing apparatus 1000 manufactures long webs 80A by, for example, a solution casting method. The long 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 forming section 05, and a winding and recovery section 06. For example, an inspection device 90A is located in the winding and recovery section 06.
[0175] The casting section 01 includes, for example, a belt 01a, a die 01b, and a peeling roll 01d. In the casting section 01, a dope, which is a resin dissolved in a solvent, is cast from the die 01b onto the belt 01a. A cast film 01c is formed on the belt 01a. The peeling roll 01d peels off this cast film 01c.
[0176] The first drying section 02 includes, for example, a drying box 02a and a conveying roll 02d. The drying box 02a is provided with a drying air intake 02b and an exhaust port 02c. In the first drying section 02, the amount of solvent contained in the cast film 01c may be adjusted.
[0177] The stretching section 03 includes an MD stretching section 03a and a TD stretching section 03b. The stretching section 03 stretches the flow-rolled film 01c that is transported from the first drying section 02.
[0178] The second drying section 04 has a configuration substantially similar to that of the first drying section 02, for example.
[0179] The knurling forming section 05 forms knurling on both ends of the cast film 01c that is transported from the second drying section 04.
[0180] The winding and retrieval unit 06 includes a winding machine 06a and an accompanying air volume control device 06b. The winding and retrieval unit 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 6f. The linear encoder 06c may be either a contact type or a non-contact type.
[0181] Figure 29 shows an enlarged view of the knurling forming section 05 and the winding and retrieval section 06 shown in Figure 28.
[0182] In the knurling forming apparatus 05a, a knurling forming roll 501a and a receiving roll 501b are paired. A pressing means 501c is connected to the knurling forming roll 501a. The knurling forming roll 501a has an uneven surface. A cast film 01c is sandwiched between the knurling forming roll 501a and the receiving roll 501b to form knurling. The knurling forming roll 501a moves vertically by the pressing means 501c. The amount of movement of the pressing means 501c is controlled, for example, by the control device 07.
[0183] The control device 07 has a memory, a CPU, and an input / output interface. The control device 07 uses, for example, information input to the CPU and information pre-input to the memory to determine the amount of movement of the pressing means 501c, that is, the amount of movement of the knurling forming roll 501a. When the amount of movement of the knurling forming roll 501a increases, the height of the formed knurling increases. When the amount of movement of the knurling forming roll 501a decreases, the height of the formed knurling decreases.
[0184] The knurling forming apparatus 05a may be an inkjet type or laser type knurling forming apparatus.
[0185] The accompanying air volume control device 06b includes, for example, a touch roll 602a and a pressure amount control device 602b that controls the amount of pressure applied to the touch roll 602a. The pressure amount control devices 602b are located at both ends of the touch roll 602a.
[0186] The relationship between touch rolls and tension control is described, for example, in the literature (J.K. Good, Modeling, Nip Induced Tension in Wound Rolls, Procedures of Forth International Conference on Web Handling, 1997).
[0187] The tension control device 06e includes a tension controller 605a and a means 605b for moving the tension controller 605a. The tension control device 06e moves the position of the tension controller 605a in accordance with the long web 80A being wound onto the winding shaft 82.
[0188] (Processed Web Manufacturing Apparatus 2000) Figure 30 shows an example of the schematic configuration of the processed web manufacturing apparatus 2000. The processed web manufacturing apparatus 2000 laminates a first protective film 12 and a second protective film 13 on both sides of a polarizer 1c, for example. This yields 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 made up of a long web 80A manufactured by the long web manufacturing apparatus 1000.
[0189] The processed web manufacturing apparatus 2000 includes, for example, a wet processing apparatus 204, a drying apparatus 205, and a laminating apparatus 206, in order from the upstream side. The processed web manufacturing apparatus 2000 further has a feeding section 202. For example, a long web 80A is loaded into the third roll section 63 of this feeding section 202.
[0190] The wet processing apparatus 204 includes a first roll section 41, a transport section 42, and a processing section. A long, untreated hydrophilic polymer film 1a is wound around the first roll section 41. The transport section 42 transports the hydrophilic polymer film 1a. In the processing section, the hydrophilic polymer film 1a is transformed into a polarizer 1b.
[0191] The conveying unit 42 has multiple guide rolls and the like. The conveying unit 42 pulls out the hydrophilic polymer film 1a wound around the first roll unit 41 and conveys it to the processing unit.
[0192] The processing unit includes, for example, a swelling treatment tank 4A, a dyeing treatment tank 4B, a crosslinking treatment tank 4C, a stretching treatment tank 4D, and a washing treatment tank 4E, in order from the upstream side.
[0193] The swelling treatment tank 4A is a treatment tank containing a swelling treatment solution. The swelling treatment solution swells the hydrophilic polymer film 1a. The dyeing treatment tank 4B is a treatment tank containing a dyeing treatment solution. The dyeing treatment solution dyes the hydrophilic polymer film 1a. The crosslinking treatment tank 4C is a treatment tank containing a crosslinking treatment solution. The crosslinking treatment solution crosslinks the dyed hydrophilic polymer film 1a. The stretching treatment tank 4D is a treatment tank containing a stretching treatment solution. The stretching treatment solution is not particularly limited, but for example, a solution containing a boron compound as an active ingredient can be used. The washing treatment tank 4E is a treatment tank containing a washing treatment solution. The washing treatment solution washes the stretched hydrophilic polymer film 1a. The washing treatment solution is a treatment solution for washing off treatment solutions such as the dyeing treatment solution and crosslinking treatment solution that have adhered to the hydrophilic polymer film 1a. Typically, water such as ion-exchanged water, distilled water, or pure water is used as the washing treatment solution.
[0194] The drying apparatus 205 has a conveying section 501 and a heating section. There may be one drying apparatus 205, or two or more may be provided side by side in the direction of polarizer transport. In the illustrated example, for example, one drying apparatus 205 is provided in the polarizer transport path. The conveying section 501 transports the long, strip-shaped polarizer 1b. The heating section applies heat to the polarizer 1b to dry it.
[0195] The heating section of the drying apparatus 205 includes, for example, a chamber 502 and a heat source. The chamber 502 has a space 503 inside which polarizers can be transported.
[0196] The laminating apparatus 206 includes a transport section 61, an adhesive coating section 64, a bonding section 67, and a chamber 69. The transport section 61 transports the polarizer 1c and the first protective film 12 after drying. The chamber 69 surrounds the adhesive coating section 64 and the bonding section 67.
[0197] The conveying unit 61 includes guide rolls and the like. The conveying unit 61 conveys the long, strip-shaped polarizer 1c, which has been 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.
[0198] The adhesive coating section 64 has a gravure roll 641. The gravure roll 641 is a coating roll that coats the film with adhesive. The adhesive coating section 64 is located upstream of the bonding section 67. The adhesive coating section 64 is located, for example, on one side of the first protective film 12 and on one side of the second protective film 13. The adhesive coating section 64 may also be located on one side of the polarizer 1c and on the other side of the polarizer 1c.
[0199] The adhesive coating section 64 includes, for example, a gravure roll 641 which is a coating roll, a container 642 in which adhesive is stored, and a doctor blade 643. The adhesive coating section 64 may also have a backup roll if necessary. The backup roll is positioned opposite the gravure roll 641 with the film in between.
[0200] Multiple cells are formed on the surface of the gravure roll 641. These cells are recesses into which the adhesive is contained. The gravure roll 641 rotates so that its surface comes into contact with the adhesive 65 stored in the container 642. As it 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 the doctor blade 643. As 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 applied in a solid layer from the gravure roll 641 to one side of the first protective film 12 and the second protective film 13, respectively.
[0201] The adhesive used to bond the polarizer 1c to the first protective film 12 and the second protective film 13 is not particularly limited, but as described above, it is preferable to use an active energy ray curable adhesive. Conventional active energy ray curable adhesives can be used. Active energy ray curable adhesives generally contain an active energy ray curable component and a polymerization initiator, and optionally contain various additives.
[0202] The dispensing unit 202 has an easy-adhesion treatment tank 21, a washing treatment tank 22, and a heat treatment tank 23. The easy-adhesion treatment tank 21 performs an easy-adhesion treatment on the surface of the second protective film 13 to which the polarizer 11 is adhered. For example, the easy-adhesion treatment tank 21 performs corona discharge treatment or plasma treatment. In corona discharge treatment, a high voltage is applied to a wire or sawtooth electrode in the chamber. The washing treatment tank 22 has the same configuration as the washing treatment tank 4E described above. The washing treatment tank 22 contains a washing treatment liquid. The second protective film 13 is washed with the washing treatment liquid. The heat treatment tank 23 has the same configuration as the drying apparatus 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.
[0203] The processed web manufacturing apparatus 2000 further includes a second roll section 62 and a third roll section 63. A long, strip-shaped first protective film 12 is wound around the second roll section 62. A long, strip-shaped second protective film 13 is wound around the third roll section 63. The first protective film 12 and the second protective film 13 are transported from the second roll section 62 and the third roll section 63, respectively, to the lamination section 67.
[0204] The configuration of the information processing system 50 described above is merely a description of the main configuration for explaining the features of the above embodiment, and is not limited to the above configuration; various modifications can be made within the scope of the claims. Furthermore, it does not exclude configurations that are generally found in information processing devices or information processing systems. For example, the information processing system 50 may include inspection devices 90A and 90B. Also, the feature point generation function of the analysis unit 93 of the inspection device 90 may be handled by the control unit 51 of the information processing system 50.
[0205] Furthermore, the information processing system 50 may perform alignment of the pre-processed compressed feature point map 80AM and the post-processed compressed feature point map 80BM using methods other than those described in the above embodiment.
[0206] Furthermore, the means and methods for performing various processing tasks in the information processing system 50 according to the above embodiment can be implemented by either a dedicated hardware circuit or a programmed computer. The program may be provided, for example, on a computer-readable recording medium such as a USB memory stick or DVD-ROM, or it may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is usually transferred to and stored in a storage unit such as a hard disk. The program may also be provided as a standalone application software, or it may be incorporated into the software of the device as a function of the device.
[0207] While embodiments of the present invention have been described and illustrated in detail, the disclosed embodiments are for illustrative purposes only and are not limiting. The scope of the present invention should be interpreted in accordance with the language of the appended claims.
[0208] This application is based on Japanese Patent Application No. 2025-080502, filed on 13 May 2025, and its disclosures are referenced and incorporated as a whole.
[0209] 50 Information processing system 51 Control unit 511 Acquisition unit 512 Map generation unit 513 Output unit 514 First condition setting unit 515 First alignment unit 516 Identification unit 517 Second condition setting unit 518 Second alignment unit 519 Classification unit 52 Storage unit 90, 90A, 90B Inspection device 1000 Long web manufacturing device 2000 Processing web manufacturing device
Claims
1. An information processing system for processing information obtained from a long web and a processed web in which a predetermined process has been performed on at least a portion of the long web, comprising: an acquisition unit that acquires pre-processing web information including location information of pre-processing feature points present in the long web and post-processing web information including location information of post-processing feature points present in the processed web; a map generation unit that generates a pre-processing compressed feature point map based on the pre-processing web information and generates a post-processing compressed feature point map based on the compression ratio of the pre-processing compressed feature point map and the post-processing web information; and a first alignment unit that aligns the generated pre-processing compressed feature point map and the post-processing compressed feature point map.
2. The information processing system according to claim 1, wherein the map generation unit generates a feature point map corresponding to the position information of the pre-processing feature points assuming that the long web is compressed at a predetermined compression ratio, as the pre-processing compressed feature point map, and generates a feature point map corresponding to the position information of the post-processing feature points, as the post-processing compressed feature point map.
3. The information processing system according to claim 1, further comprising an output unit that outputs the pre-processed compressed feature point map and the post-processed compressed feature point map, which have been aligned by the first alignment unit, to a display unit.
4. The information processing system according to claim 3, wherein the output unit outputs the pre-processed compressed feature point map and the post-processed compressed feature point map generated by the map generation unit to the display unit.
5. The information processing system according to claim 4, wherein the output unit displays the pre-processed compressed feature point map and the post-processed compressed feature point map superimposed on the display unit.
6. The information processing system according to claim 4 or 5, wherein the first alignment unit aligns the pre-processed compressed feature point map and the post-processed compressed feature point map based on information input from the user.
7. The information processing system according to claim 6, further comprising a first condition setting unit for setting first feature point conditions for the pre-processing feature points and the post-processing feature points, wherein the map generation unit generates the pre-processing compressed feature point map and the post-processing compressed feature point map with respect to the positional information of the pre-processing feature points and the post-processing feature points that conform to the first feature point conditions.
8. The information processing system according to claim 6, wherein the processed web includes a first processed web in which a predetermined process has been performed on a first portion of the long web, and a second processed web in which a predetermined process has been performed on a second portion of the long web that is different from the first portion, and the post-processed compressed feature point map includes a first post-processed compressed feature point map corresponding to the position information of the post-processed feature points in the first processed web, and a second post-processed compressed feature point map corresponding to the position information of the post-processed feature points in the second processed web, and the output unit causes the display unit to display the pre-processed compressed feature point map, the first post-processed compressed feature point map, and the second post-processed compressed feature point map generated by the map generation unit.
9. The information processing system according to claim 1 or 2, wherein the first alignment unit aligns the pre-processed compressed feature point map and the post-processed compressed feature point map using image processing technology.
10. The information processing system according to claim 1 or 2, further comprising: a specification unit that identifies a specific region of a part of the long web based on the result of the alignment by the first alignment unit; and a second alignment unit that associates predetermined pre-processing feature points and predetermined post-processing feature points present in the specified region based on their positions.
11. The information processing system according to claim 10, further comprising a second condition setting unit for setting a second feature point condition for the pre-processing feature point and the post-processing feature point, wherein the second alignment unit associates predetermined pre-processing feature points and predetermined post-processing feature points that conform to the second feature point condition.
12. The information processing system according to claim 1 or 2, wherein the long web has a size in the width direction and a size in the length direction intersecting the width direction, and at the predetermined compression ratio, the compression ratio of the size in the length direction is higher than the compression ratio of the size in the width direction.
13. The information processing system according to claim 11, wherein the length of the processing web is smaller than the length of the long web.
14. An information processing method comprising: obtaining pre-processing web information including location information of pre-processing feature points present in a long web, and post-processing web information including location information of post-processing feature points present in a processed web in which a predetermined process has been performed on at least a portion of the long web; generating a pre-processing compressed feature point map based on the pre-processing web information, and generating a post-processing compressed feature point map based on the compression ratio of the pre-processing compressed feature point map and the post-processing web information; and aligning the generated pre-processing compressed feature point map and the post-processing compressed feature point map.
15. The information processing method according to claim 14, wherein the generation of the pre-processing compressed feature point map and the post-processing compressed feature point map is characterized in that a feature point map corresponding to the position information of the pre-processing feature points assuming that the long web is compressed at a predetermined compression ratio is generated as the pre-processing compressed feature point map, and a feature point map corresponding to the position information of the post-processing feature points is generated as the post-processing compressed feature point map.
16. An information processing program that causes a computer to execute the information processing method described in claim 14 or 15.
