Information processing system, control method and control program

Abstract

[Problem] To understand the occurrence of defects during the manufacturing process of wire mesh and in the subsequent processing of the wire mesh. [Solution] An information processing system (50) is provided, comprising: an acquisition unit (511) that classifies the feature points contained in the first and second inspection data acquired in the process into a first type of feature point that exists in the first inspection data but not in the second inspection data, a second type of feature point that does not exist in the first inspection data but exists in the second inspection data, and a third type of feature point that exists in both the first and second inspection data, and acquires data from a recorded database; a selection unit (514) that accepts the selection of multiple batches of objects or the selection of multiple inspection intervals in the long side direction of the wire mesh in one batch; a display data generation unit (515) that generates display data from the data acquired by the acquisition unit (511) from the database and selected by the selection unit (514); and an output unit (516) that outputs the display data.

Description

[Technical Field]

[0001] This invention relates to an information processing system, a control method, and a control program. [Previous Technology]

[0002] Liquid crystal display devices are increasingly being used in large-screen televisions or large displays. Consequently, the thin films used on the display surfaces of liquid crystal display devices are also required to be wider. For example, films with a width of 2000mm or more are desired. Furthermore, in order to estimate substrate loss (film loss) in advance or to reduce transportation costs, it is required to manufacture film rolls with a length of 1000m or more, or even 3000m or more.

[0003] In the post-processing of products using webs such as films as substrates, when quality problems such as defects occur, it is necessary to clarify whether the defect originated in the preceding process (i.e., when manufacturing the web) or was originally present on the web, or originated in the post-processing. When it is not clearly determined whether the defect occurred in the post-processing, improvements to the preceding process are sometimes required. When expectations for improvement are met, the shipping standards of the preceding process become excessively stringent, resulting in overspecification. Furthermore, even if the impact on the post-processing is not clearly understood, there are situations where, in order to prevent quality problems from occurring, "overly stringent shipping standards are also estimated when manufacturing the web." In such cases, overspecification also occurs. Overspecification leads to decreased yield or increased costs, is environmentally unfriendly, and is detrimental to both the business operators performing the preceding and post-processing.

[0004] Patent Document 1 below discloses a technology in which first and second inspection units, configured at different stages of the manufacturing process, detect defects, are combined, and a predicted yield is determined based on the cutting position and dimensions, in an inspection system for optical thin films. [Prior Art Documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2013-024868 [Summary of the Invention]

[0006] [Problem to be solved by the present invention] However, the technology of Patent Document 1 integrates the defects generated among multiple processes, rather than grasping the generation status of defects in the process.

[0007] This invention was developed in view of the above-mentioned circumstances, with the aim of "understanding the occurrence of defects during the manufacture of webs such as thin films and in the manufacturing process of using them for subsequent processing." [Means for solving the problem]

[0008] The above-mentioned objective of the present invention is achieved by the following means.

[0009] (1) An information processing system, characterized by comprising: an acquisition unit that, based on first inspection data in a first manufacturing process of manufacturing a wire mesh or performing post-processing on the manufactured wire mesh, and second inspection data in a second manufacturing process performed after the first manufacturing process that uses the wire mesh for post-processing, classifies the feature points contained in each of the first and second inspection data into a first type of feature point that exists in the first inspection data but not in the second inspection data, a second type of feature point that does not exist in the first inspection data but exists in the second inspection data, and a third type of feature point that exists in both the first and second inspection data, and acquires data from a recorded database; a selection unit that selects a plurality of batches of the accepted object or a plurality of inspection intervals in the long side direction of the wire mesh in one batch; a display data generation unit that generates display data from the data acquired by the acquisition unit from the database and selected by the selection unit; and an output unit that outputs the display data.

[0010] (2) The information processing system as described in (1) above, wherein the aforementioned selection unit further accepts the selection of the type of the classified feature points, and the aforementioned display data generation unit generates the aforementioned display data based on the data of the type of feature points accepted.

[0011] (3) The information processing system as described in (1) above, wherein the aforementioned displayed data includes a chart comparing feature points generated in multiple batches of manufacturing processes.

[0012] (4) The information processing system as described in (3) above, wherein the aforementioned chart is a chart that “compares the second type of feature points generated in subsequent manufacturing processes among multiple batches”.

[0013] (5) The information processing system as described in (3) above, wherein the aforementioned chart contains at least one of bar chart, line chart, dot chart and stacked bar chart.

[0014] (6) A control method characterized by performing a process comprising the following steps: Step (a), based on first inspection data in a first manufacturing process of manufacturing a wire mesh or performing post-processing on the manufactured wire mesh and second inspection data in a second manufacturing process after the first manufacturing process of performing post-processing on the wire mesh, classifying the feature points contained in each of the first and second inspection data into a first type of feature point that exists in the first inspection data but does not exist in the second inspection data, a second type of feature point that does not exist in the first inspection data but exists in the second inspection data, and a third type of feature point that exists in both the first and second inspection data, and retrieving data from a recorded database; Step (b), selecting a plurality of batches of the accepted objects or selecting a plurality of inspection intervals in the long side direction of the wire mesh in one batch; Step (d) generates display data from the data obtained from the aforementioned database in step (a) and selected by step (a); and step (e) outputs the aforementioned display data.

[0015] (7) The control method as described in (6) above, wherein, in the aforementioned step (b), the selection of the type of the classified feature points is further accepted, and in the aforementioned step (d), the aforementioned display data is generated based on the data of the types of the accepted feature points.

[0016] (8) The control method as described in (6) above, wherein the aforementioned displayed data includes a chart comparing feature points generated in multiple batches of manufacturing processes.

[0017] (9) The control method as described in (8) above, wherein the aforementioned chart is a chart for “comparing the second type of feature points generated in subsequent manufacturing processes among multiple batches”.

[0018] (10) The control method as described in (8) above, wherein the aforementioned chart contains at least one of a bar chart, a line chart, a dot chart and a stacked bar chart.

[0019] (11) A control program for causing a computer to execute the control methods described in (6) to (10) above. [Effects of the Invention]

[0020] The information processing system of the present invention comprises: an acquisition unit that, based on first inspection data from a first manufacturing process in which the fabric is manufactured or in which the manufactured fabric is post-processed, and second inspection data from a second manufacturing process in which post-processing using the fabric is performed after the first manufacturing process, classifies the feature points contained in the first and second inspection data into a first type of feature point that exists in the first inspection data but not in the second inspection data, a second type of feature point that does not exist in the first inspection data but exists in the second inspection data, and a third type of feature point that exists in both the first and second inspection data, and acquires data from a recorded database; a selection unit that selects multiple batches of the accepted objects or multiple inspection intervals in the long side direction of the fabric in one batch; a display data generation unit that generates display data from the data acquired by the acquisition unit from the database and selected by the selection unit; and an output unit that outputs the display data. In this way, the occurrence of defects can be understood during the fabric manufacturing process and during the post-processing using the fabric.

Implementation Method

[0022] Hereinafter, embodiments of the present invention will be described with reference to the appended drawings. However, the scope of the present invention is not limited to the disclosed embodiments. Furthermore, in the description of the drawings, the same elements are given the same symbols, and repeated descriptions are omitted. Also, the scale ratios in the drawings are exaggerated for ease of explanation and may sometimes differ from the actual ratios.

[0023] (Net) In this embodiment, the net is a sheet-like material comprising a resin film and a metal film. Furthermore, the net contains a laminate. In the following description, the net is a strip of resin film, and the process thereof will be explained as a film roll. The processing also includes applying a coating liquid and laminating another film-like material to form a laminate.

[0024] (Batch) In this embodiment, "batch" is, in a typical example, assigned to a roll unit (film roll unit). As another example, "batch" simply refers to the method of ID division; it can also be chosen as a batch division of physical rolls, or a batch division based on time information of the manufacturing or post-processing stage. For example, it can be associated with the inspection time set in the process based on an inspection device. This can be done using another table that maps multiple inspection times to the film or film roll. Furthermore, as needed, any ID with a pre-assigned number (unique ID) can be used as the definition of a batch. In the following explanation, the batch number is defined as one that is automatically assigned a unique number.

[0025] Furthermore, the batch ID is sometimes assigned a sub-ID or a new batch ID in any process, and is not a one-to-one correspondence but rather a one-to-n or n-to-one correspondence. For example, in a previous process, a film may be 3000m long in one batch, but in a later process, it may be divided into three parts of 1000m each. In this case, in the later process, a sub-ID or a new batch ID is assigned to the batch ID. Conversely, in a previous process, two or three film rolls may be joined together as a single film for use in a later process. In this case, there are two or three batch IDs in the previous process and one batch ID in the later process. In any case, the correspondence between the batch IDs of each process is also recorded in the batch list (see Figure 4 described later).

[0026] (Feature Point Information) In this embodiment, a feature point is a defect on the thin film, generated by analyzing image data. Image analysis can be performed using conventional techniques, extracting pixels whose pixel values ​​deviate from the surrounding average by a predetermined margin (a difference of a predetermined margin) from the image data of the thin film surface as feature points, or it can be calculated using the "image processing for feature point generation" method described later. From capturing one or more image data of a single 80-kilometer roll of thin film (several km in length), in most cases, tens to thousands of feature points are generated. Defects include both defects that cause product defects and minor defects that do not cause product defects. Feature points include defects related to poor adhesion or axial misalignment when joining thin films together midway (e.g., ultrasonic fusion). Feature point information includes size and position (xy coordinates). Furthermore, as feature point information, it is also possible to use clustering (aggregating) multiple close feature points into one. The image processing for feature point generation is described later.

[0027] Figure 1 is a schematic diagram illustrating an applicable example of the information processing system 50 according to this embodiment. As shown in Figure 1, the information processing system 50 connects terminal devices 70 of factory A and factory B to each other via a network. The network is a communication line such as a data communication network. In some networks, wired LANs or wireless LANs (e.g., LANs according to the IEEE 802.11 standard) may also be used. Details regarding the information processing system 50 will be described below.

[0028] Terminal device 70 is, for example, a PC (personal computer). For example, terminal device 70 is a PC used by employees of manufacturing companies operating factory A and factory B.

[0029] Factory A is equipped with the aforementioned film roll manufacturing apparatus 1000. Factory A is operated or managed, for example, by a film manufacturer. In Factory A, a first manufacturing process for manufacturing film roll 80 is carried out. In the first manufacturing process, several types of sub-processes such as drying, stretching, and winding are carried out. Before and after the several sub-processes, inspection devices 90a1 and a2 (hereinafter, these are also collectively referred to as inspection devices 90) are arranged. The film surface of film roll 80 is inspected by the several inspection devices 90a1 and 90a2. Although two inspection devices 90a1 and 90a2 are shown in Figure 1, the number of inspection devices 90 is not limited to this, and may be one or more than three.

[0030] Factory B is equipped with a product manufacturing apparatus 2000. Factory B is operated or managed, for example, by a coating manufacturer (hereinafter also referred to as a user company or user). There are multiple user companies operating Factory B. In Factory B, products are manufactured using film rolls 80 shipped and transported from Factory A. Factory B includes multiple sub-processes, namely, post-processing such as "coating by feeding film (film F8 described below) from film roll 80, or overlapping or bonding with other films". Sub-processes are equivalent to the first or second manufacturing process. Before and after the multiple sub-processes, multiple inspection devices 90b1 to 90b4 (hereinafter also collectively referred to as inspection devices 90) are provided. In Figure 1, although four inspection devices 90b1, 90b2, 90b3, and 90b4 are shown, the number of inspection devices 90 is not limited to this, and may be three or less or five or more.

[0031] In this embodiment, in a typical example, the process of manufacturing the thin film (web) is referred to as the first manufacturing process, and the post-processing performed at factory B using the manufactured thin film is referred to as the second manufacturing process. For example, the post-processing process includes coating treatment to impart a functional layer to the surface, lamination process of overlapping webs of another thin film, etc. In the second manufacturing process, the film surface of the film roll 80 is also inspected by the inspection device 90.

[0032] While not particularly limited, the materials used for the film F8 manufactured as shown in Figure 1 generally include polycarbonate resin, polyurethane resin, acrylic resin, polyolefin resin, cyclic olefin resin, polyether resin, polyester resin, polyamide resin, polysulfide resin, unsaturated polyester resin, epoxy resin, melamine resin, phenolic resin, diallyl phthalate resin, polyimide resin, urethane resin, polyvinyl acetate resin, polyvinyl alcohol resin, styrene resin, cellulose acetate resin, and vinyl chloride resin. Furthermore, for example, the width of the film F8 is preferably 1000 mm to 3200 mm, considering factors such as productivity and quality. The thickness is preferably 15 μm to 500 μm, considering factors such as quality and operability.

[0033] As an example other than the typical embodiment, when the manufactured film undergoes multiple post-processing steps at factory B, the earlier post-processing step is sometimes referred to as the first manufacturing process, and the later post-processing step is sometimes referred to as the second manufacturing process. Also, sometimes in subsequent processes, the film roll 80 manufactured at factory A is sent out for post-processing. In a typical example, the sub-process performed at factory B includes a lamination process (also called an bonding process) that overlaps and bonds other films. A laminate 80B is formed by the lamination process (see the enlarged cross-sectional view of the white frame in FIG1). In the following, layers 1 to 3 are bonded or coated onto the original film (F8) through several sub-processes at factory B. Furthermore, in the enlarged cross-sectional view of the white frame, the markings of the bonding layers between each layer are omitted. For example, film F8 consists of a PVA (polyvinyl alcohol resin) layer, a TAC (triacetin cellulose) layer, a second layer that is an optical functional film layer such as a polarizer, and a third layer that is a protective layer. Furthermore, the third layer can also be a separating film or an anti-glare film, etc. The third layer is an opaque layer.

[0034] The inspection device 90 is used to photograph films, etc., and generate inspection data. As described above, in the example shown in FIG1, a plurality of inspection devices 90 are arranged before and after sub-processes such as extension processes and lamination processes in the film production line. Hereinafter, the inspection device 90 will be explained with reference to FIG2A to FIG2C.

[0035] (Inspection device 90) Using a transparent body such as film F8 as the object to be inspected, and using it as a device to detect irregularities on its surface or bubbles, cracks, deformations of the internal structure, etc., present inside the transparent body, the following methods (1) and (2) are used. Also, using a non-transparent body as the object to be inspected, and using it as a device to detect irregularities on its surface or bubbles, cracks, deformations of the internal structure, etc., present on the surface, the following methods (2) are used. (1) Transmissive inspection device: The object to be inspected is irradiated with light, and the light transmitted through the object to be inspected is received, thereby detecting defects in the object to be inspected. (2) Reflective inspection device: The object to be inspected is received after being reflected by the object to be inspected, thereby detecting defects in the object to be inspected.

[0036] Furthermore, in both transmittance and reflectance types, depending on the positional relationship between the camera's optical axis, the light source, and the inspected object, there are bright-field inspection devices that receive non-scattered light from the surface and dark-field inspection devices that receive scattered light. In a bright-field inspection device, since there is no light scattering when there are no defects, the light from the light source is not blocked and enters the light detection means. When there is a defect, the light is blocked by the defect and cannot enter the light detection means. Therefore, in a bright background, the defect is observed as a dark spot or stripe. In contrast, in a dark-field inspection device, although there is no light scattering when there are no defects and therefore the light cannot enter the light detection means, when there is a defect, the light is scattered by the defect and thus enters the light detection means. Therefore, in a dark background, the defect is observed as a bright spot or stripe. As the inspection device 90 in this embodiment, either type of inspection device can also be used. While it is preferable to obtain the first and second inspection data using the same inspection equipment, this is not a limitation.

[0037] (Reflective Inspection Device) Figure 2A is a schematic diagram showing the configuration of a reflective inspection device 90 as viewed from the width direction (X direction). Figure 2B is a schematic diagram showing the configuration of the inspection device 90 as viewed from the transport direction (Y direction). The inspection device 90 includes a light source 91, a camera 92 as an optical sensor, an image processing unit 93, and a memory unit 94 as a data processing unit. The inspection device 90 performs optical inspection on feature points (hereinafter also referred to as defects) generated on the thin film F8 during transport. The inspection device 90 uses the camera 92 to perform optical inspection on the thin film F8 of the thin film roll 80 and generate image data as inspection data. The image data includes not only still images but also animation data composed of continuous static images in a time series. Alternatively, as inspection data, feature points can be directly extracted from signal data without image data digitization. Camera 92 is configured to cover the entire width of the film F8 as the inspection area (photographic range) by setting the number of cameras, the viewing angle, and the distance to the film surface. The number of cameras is determined by arranging multiple cameras along the width direction when one camera cannot adequately capture the full width of the film. Figure 2B shows an example of two cameras 92 arranged in the width direction (X direction). The image analysis unit 93 can combine multiple images continuously captured by one camera 92 to generate a single image containing the entire film surface of the film roll 80, or it can store multiple image data corresponding to the photographing time in the memory unit 94. Furthermore, it can combine the same image data obtained by multiple cameras 92 arranged along the width direction. The image analysis unit 93, by referring to the stored transport speed (winding speed or feed speed), can determine the position of the film F8 along its long side based on the photographing time corresponding to the image data. In the following description, it is explained as "establishing a corresponding memory for multiple image data obtained by continuous shooting and the shooting time corresponding to one film roll 80". The image analysis unit 93 generates defect information by analyzing image data. The inspection device 90 takes defects generated in the manufacturing process, such as the winding of the long strip of film F8, as the inspection object.

[0038] Light source 91 is used to illuminate the inspection area of ​​film F8. Light source 91 is used to uniformly illuminate the roll-shaped film F8 in the width direction (a direction orthogonal to the long side of film F8 and parallel to the film surface). Here, "uniform" means that the illuminance in film F8 is approximately the same throughout the width direction of film F8 (the difference between the maximum and minimum values ​​is less than a predetermined value, etc.).

[0039] Camera 92 is an optical sensor that optically reads the inspection area of ​​the thin film F8. Camera 92 is equipped with an imaging element such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor), a lens, etc. Camera 92 is an area sensor that generates two-dimensional image data from the output signals of each imaging element. Camera 92 detects diffused light in the light illuminated by the light source 91 and reflected in the inspection area of ​​the thin film F8. Here, either a color camera or a black and white camera (monochrome camera) can also be used as camera 92.

[0040] One or more cameras 92 have a photographic range covering the entire width direction of the thin film F8, so as to simultaneously capture and read the entire width direction of the thin film F8 in one shot. The camera 92 can also be a light detector in the visible light region or a light detector in the infrared region.

[0041] Furthermore, in the output signal of the camera 92, it is desirable that the contrast between the signal value on the thin film F8 corresponding to the illuminated portion illuminated by the light source 91 and the signal value corresponding to the non-illuminated portion not illuminated by the light source 91 is a predetermined value or higher. That is, it is desirable that only the areas on the thin film F8 illuminated by the light from the light source 91 (illuminated portions) appear bright.

[0042] Contrast ratio is expressed as the difference or ratio of two values ​​of the processed object (here, the signal value corresponding to the irradiated part and the signal value corresponding to the non-irradiated part). The greater the difference between the two values, the greater the contrast ratio. In order to increase the contrast ratio between the irradiated part and the non-irradiated part, it is desirable to use a powerful light source 91 with high directivity.

[0043] Here, "powerful" means that when the illuminance at an illumination distance of 50 mm is set to E50, the illuminance E50 is 50,000 lx or more. Also, "high direct penetration" means that when the illuminance at an illumination distance of 50 mm is set to E50 and the illuminance at an illumination distance of 100 mm is set to E100, (E50-E100) / E50 < 0.5.

[0044] The image parsing unit 93 is composed of a CPU, RAM, etc. It reads out various processing programs stored in the memory unit 94 and expands them to RAM, and performs various processing through the cooperation of the program.

[0045] The memory unit 94 is composed of HDD, SSD (Solid State Drive), etc., and stores various processing programs and the data required to execute those programs. Furthermore, the memory unit 94 links the captured image data (inspection data) with the time of capture. The memory unit 94 stores the winding speed (e.g., 100 m / min) in the film roll manufacturing apparatus 1000 or the feed conditions (e.g., 30 m / min) of the film F8 in the product manufacturing apparatus 2000. These winding speeds and feed conditions can also be included in the inspection list of the inspection data DB (database) (see Table T3 in Figure 4).

[0046] The image analysis unit 93 processes the output signal of the camera 92 (optical sensor) to detect feature points (position and intensity) such as defects in the thin film F8. The data processing includes: image processing of image data obtained from the output signal of the camera 92, defect determination processing to determine defects based on the image-processed data, and quantitative evaluation processing to quantitatively evaluate defects based on the image-processed data.

[0047] (Relative position of camera 92 and light source 91) The camera 92 can also be positioned to receive the positively reflected light from the light source 91 (in the case of a bright field inspection mode that receives non-scattered light).

[0048] Furthermore, the camera 92 can also be positioned to avoid receiving reflected light from the light source 91 (in the case of dark-field inspection mode that receives diffused light). That is, it is preferable to position it to receive diffused light reflected from the object being inspected.

[0049] (Transparent Inspection Device) Figure 2C shows an example of a transparent inspection device 90. In this way, the light source 91 can also be a transparent inspection device 90 that is arranged opposite to the camera 92 through the thin film F8.

[0050] (Information Processing System 50) Hereinafter, referring to FIG3, the information processing system 50 will be explained. FIG3 is a block diagram showing the general structure of the information processing system 50. The information processing system 50 is, for example, a server. As shown in FIG3, the information processing system 50 includes a control unit 51, a memory unit 52, and a communication unit 53. The memory unit 52 stores the check data DB.

[0051] (Control Unit 51) The control unit 51 is a memory unit including a CPU, RAM, ROM, etc. The CPU is a control circuit composed of a multi-core processor that executes the control or various arithmetic operations of the above-mentioned units according to a program. The functions of the information processing system 50 are performed by the CPU executing its corresponding program.

[0052] The control unit 51 functions as an acquisition unit 511, a selection unit 514, and an output unit 516 in cooperation with the communication unit 53. Furthermore, the control unit 51 functions as a comparison unit 512, a capture unit 513, and a display data generation unit 515. The acquisition unit 511 acquires various data from the check data DB.

[0053] Furthermore, the acquisition unit 511 acquires the first and second inspection data obtained through inspections in the first and second manufacturing processes. The comparison unit 512 extracts feature points from the first and second inspection data respectively. The comparison unit 512 searches for corresponding feature points between the first and second inspection data through comparison processing. In the comparison processing, the comparison unit 512 generates descriptors (descriptor 2 described later) for feature points from the two inspection data (image data) and performs feature point matching processing between the inspection data using the descriptors of the feature points, outputting the comparison result (the corresponding point list shown in FIG12 described later). The extraction unit 513 uses the comparison result to extract (classify) the first to third types of feature points.

[0054] The selection unit 514 is for selecting from the user's batch or inspection range and the type of feature points, etc.

[0055] The display data generation unit 515 generates display data from the data selected by the selection unit 514. Display data refers to charts used to visually represent data. Charts include tabular data and line graphs. Line graphs include bar graphs, line graphs, dot graphs, and stacked bar graphs that represent the generation status of feature points. For example, they may include bar graphs, line graphs, dot graphs, and stacked bar graphs that represent the generation status of feature points for each process in a batch. The output unit 516 sends the display data to the terminal device 70 or displays it on the display unit (not shown) of the terminal device 70 in response to requests from the terminal device 70.

[0056] (Memory Unit 52) ​​The memory unit 52 is a large-capacity auxiliary memory device that stores various programs or data containing the operating system. The storage medium may be, for example, a hard drive, solid-state drive, flash memory, or ROM. The memory unit 52 stores user lists, batch lists, and a database (DB). The management and registration of the user lists and batch lists are performed by the administrator through access to the terminal device 70. For example, the administrator may be the head of the department responsible for operating factory A. The database (DB) of the memory unit 52 may also be a database independent of the information processing system 50.

[0057] (User List) Figure 4 shows an example of various data stored in the memory unit 52. Table T1 shown in Figure 4 is an example of a user list. The user list stores user ID, user name, contact information, etc. Furthermore, for each user, access permissions to the data database are set, and access permissions are granted to various data (data inspection, data retrieval, etc.) related to the film roll 80 (identified by batch ID) involved by the user.

[0058] (Batch List) Table T2 in Figure 4 is an example of a batch list. The batch list records the batch ID, product name (also known as variety), buyer user ID (orderer), and multiple manufacturing conditions, dimensions (width, length, thickness), manufacturing date, etc., assigned to each film roll.

[0059] (Inspection Data DB) Table T3 in Figure 4 is an example of an inspection list recorded in the Inspection Data DB. The inspection list contains information such as Inspection ID, Batch ID, Inspection Device ID, Inspection Data, and Inspection Date and Time. The Inspection Device ID refers to an example of the inspection data contained in the inspection list corresponding to the inspection device 90a1 shown in Figure 1, as described later.

[0060] (Communications Section 53) The communications section 53 is also an interface for network connection with external devices such as PCs.

[0061] (Generation Process of First and Second Inspection Data) Hereinafter, referring to Figures 5 to 7, the generation process of the first and second inspection data performed in the first and second manufacturing processes will be explained. Figure 5 is a flowchart showing the generation process of the first inspection data performed in the first manufacturing process. Figure 6 is a flowchart showing the generation process of the second inspection data performed in the second manufacturing process. Figure 7 is a diagram showing an example of the first and second inspection data obtained in the processes of Figures 5 and 6. The first inspection data is the inspection data generated by the generation process described below, in the example shown in Figure 1, using image data obtained by any one of the inspection devices 90a1 to 90b3. The second inspection data is the inspection data generated by the generation process described below using image data obtained by an inspection device 90, which is located further downstream than the inspection device 90 that obtained the first inspection data, in an inspection device 90a2 to 90b4.

[0062] (Generation and processing of first inspection data) Figure 5 is a flowchart showing the generation and processing of first inspection data in the first manufacturing process.

[0063] (Step S11) In the above typical example, in the first manufacturing process, the film roll 80 is manufactured by the film roll manufacturing apparatus 1000.

[0064] (Step S12) The inspection device 90 is used to photograph the film and save the image data. The inspection device 90 is as described in Figure 3A, etc.

[0065] (Step S13) The image analysis unit 93 performs the image processing described below on the image data to generate a plurality of feature points.

[0066] (Image processing for feature point generation) The image analysis unit 93 acquires two-dimensional image data generated by the camera 92 and stored in the memory unit 94.

[0067] The image analysis unit 93 processes the image data (inspection data) acquired from the camera 92.

[0068] The image analysis unit 93 divides the image data into a plurality of regions. For example, the image analysis unit 93 divides the image data into n (e.g., several to dozens) regions (hereinafter referred to as region a1 to region an) in the width direction.

[0069] Next, the image analysis unit 93 acquires image data of a region a1 and performs mathematical processing on the image data of region a1. Appropriate mathematical processing is prepared according to the type of defect in the object being inspected (strip-shaped protrusions, longitudinal wrinkles, oblique wrinkles, uneven bright spots, light leakage, etc.).

[0070] In mathematical processing, it includes preprocessing, emphasis processing, signal processing, image feature extraction, etc.

[0071] As preprocessing, the following can be listed: • Image trimming, • Low-pass filter, high-pass filter, Gaussian filter, medium-pass filter, bidirectional filter • Morphological transformation, color transformation (L*a*b*, sRGB, HSV, HSL), contrast adjustment, noise removal, blurring • Restoration of vibrating images, masking, Hough transform, projective transformation, etc.

[0072] As an example of emphasis processing, the following can be listed: Sobel filter, Scharr filter, Laplacian filter, Gabor filter, Canni method, etc.

[0073] As a signal processing method, the following can be listed: • Calculation of basic statistics (maximum, minimum, average, median, standard deviation, dispersion, quartiles), square and square root, difference, sum, product, ratio, distance matrix processing, differentiation and integration, thresholding (binarization, adaptive binarization, etc.), • Fourier transform, wavelet transform, peak detection (peak value, peak count, half width, etc.), etc.

[0074] As an example of image feature extraction, template matching, SIFT features, etc. can be listed.

[0075] Next, the image analysis unit 93 performs thresholding on the values ​​(feature quantities) obtained by mathematical processing of the image data for region a1. The thresholding is a process that determines whether a defect is a target for detection based on a predetermined defect determination threshold, and also determines the level (intensity) of the defect.

[0076] In threshold processing, determining the existence and type of a defect is equivalent to "defect determination processing". Also, in threshold processing, classifying defects into multiple levels according to thresholds is equivalent to "quantitative evaluation processing".

[0077] For example, for parameters (feature quantities) with values ​​from 1 to 100, defects are classified into multiple levels. For example, the levels can be classified according to the size (diameter or area) of the defect. Furthermore, the levels can also be further subdivided according to the size classification based on the parameter value.

[0078] The image analysis unit 93 processes regions other than region a1 in the same way.

[0079] After processing each region a1 to an, the image analysis unit 93 integrates the results for each region a1 to an, and the data processing ends. Specifically, the image analysis unit 93 generates data corresponding to the level of the detected defect and its location (xy coordinates) for each region (each position in the width direction of the thin film F8).

[0080] After data processing, the image analysis unit 93 stores the processing results in the memory unit 94. The image analysis unit 93 performs data processing on multiple image data obtained in the inspection of one film roll 80 to obtain processing results. By combining these processing results, first inspection data as shown in Table T11 of FIG7 is generated.

[0081] (Step S14) The terminal device 70, which is in the first manufacturing process, sends the inspection data containing information on a plurality of feature points obtained from the processing up to step S13 to the information processing system 50. The acquisition unit 511 of the information processing system 50 stores the acquired inspection data as the first inspection data in the inspection data DB of the memory unit 52.

[0082] Figure 7 shows an example of the contents of the inspection data in the inspection list. The first inspection data shown in Table T11 of Figure 7 records the feature point IDs that are automatically assigned sequentially to the feature points and the feature point descriptors 1 and 2 (hereinafter referred to as descriptor 1, etc.) for each feature point ID.

[0083] Descriptor 1 is individual information for a feature point, recording its XY coordinate position and intensity. Intensity refers to the level of the feature point, as described later. Furthermore, as intensity information, it may also contain information about the size (diameter, area) and brightness of the feature point. The XY coordinate position is the XY coordinate relative to the starting point of the film surface (e.g., the left end of the front end). X is the coordinate in the width direction of the film, taking a range of, for example, 0 to 3000 mm, depending on the film size (see Table T2). Y is the coordinate in the long side direction of the film, taking a range of, for example, 0 to 10000 μm, depending on the film size. The generation of descriptor 1 is performed by the image resolution unit 93 of the inspection device 90.

[0084] Descriptor 2 is surrounding information, representing vector or sequence information about the surrounding information, such as the relationship with other feature points. For example, SIFT feature values ​​can be used as descriptors, or the probability density function of feature points calculated by kernel density estimation can be used as descriptors. The generation of descriptor 2 is mainly performed by the comparison unit 512.

[0085] (Generation and processing of second inspection data) Figure 6 is a flowchart showing the generation and processing of second inspection data performed in the second manufacturing process.

[0086] (Step S21) In the second manufacturing process, after the first manufacturing process, the product manufacturing apparatus 2000 performs post-processing using film roll 80 to manufacture a product using film F8.

[0087] (Step S22) The inspection device 90 is used to photograph the surface of the film F8 before post-processing, during post-processing, or after post-processing, and save the image data.

[0088] (Step S23) The image analysis unit 93, through the same process as in step S13, stores the generated feature point information containing a plurality of feature points in the memory unit 94.

[0089] (Step S24) The terminal device 70, which is in the second manufacturing process, sends the inspection data containing information on a plurality of feature points obtained from the processing up to step S23 to the information processing system 50. The acquisition unit 511 of the information processing system 50 stores the acquired inspection data as the second inspection data in the inspection data DB of the memory unit 52. The second inspection data T12 shown in FIG7 is the same as the first inspection data shown in Table T11, described by feature point id and feature point descriptors 1 and 2.

[0090] (Feature point extraction and database entry processing) Referring to Figures 8 to 14, the feature point extraction and database entry processing performed in the information processing system 50 will be explained below. Figure 8 is a flowchart illustrating the feature point extraction process. Figure 9 is a schematic diagram illustrating the feature point extraction process.

[0091] The information processing system 50 starts the processing below step S31 in response to the start instruction received from the user through the operation screen of the terminal device 70, or at the time when the second check data is registered in the check data DB of the memory unit 52 and the first and second check data are complete.

[0092] (Step S31) The acquisition unit 511 acquires the same batch, that is, a pair of first and second inspection data, from the inspection data DB. The same batch is associated with the batch ID assigned to the inspection ID.

[0093] (Steps S32, S33) The comparison unit 512 performs preprocessing on the first inspection data according to the first condition and performs preprocessing on the second inspection data according to the second condition.

[0094] The comparison unit 512, as shown in FIG9, performs preprocessing before the second condition. If there is a difference between the winding (first manufacturing process) and the output (second manufacturing process) of the second inspection data, preprocessing is performed to reverse the Y coordinate (vertical) in order to make them consistent. Furthermore, in the second manufacturing process, depending on the information of whether the imaging area of ​​the camera 92 is set as the surface or back side of the film F8, the comparison unit 512 performs preprocessing to reverse the X coordinate (left-right) of the second inspection data (or the first inspection data).

[0095] Furthermore, the comparison unit 512 performs noise removal processing on the first inspection data and the second inspection data, including at least one of the following as part of the first and second conditions: (1) Removal of low-level feature points. (2) Removal of extremely small feature points. (3) Removal of continuous dots. (4) Removal of concentrated dots in the width direction. This is especially true at the front or rear end of the thin film F8.

[0096] (Step S34) The comparison unit 512 searches for feature points in the other party's inspection data that are the same as or correspond to the feature points in the inspection data of one party through comparison processing, and performs feature point correspondence (matching) between them. Figure 10 is a flowchart showing the routine process of step S34.

[0097] (Step S401) The comparison unit 512 generates descriptors 2 for each feature point of the first and second inspection data. The comparison unit 512 uses, for example, SIFT feature quantities as descriptors, or uses the probability density function of the feature points calculated by kernel density estimation as descriptors.

[0098] (Steps S402, S403) The comparison unit 512 compares the feature points of the first and second inspection data with each other and retrieves the most corresponding point. The comparison unit 512 evaluates the similarity between feature points using descriptor 1 and descriptor 2, and regards the most similar point as the corresponding feature point.

[0099] For example, in comparing the feature points of the first and second inspection data, the comparison unit 512 searches for feature points from the feature points of the first inspection data that correspond to the feature points of the object in the second inspection data. At this time, the comparison unit 512 determines the feature points of the first inspection data whose X and Y coordinates are consistent with or have the closest intensity to the feature points of the feature points of the second inspection data as the same point. Alternatively, it determines the points whose distance (Euclidean distance) between the X and Y coordinates of the descriptors 1 is closest to each other as the same point (corresponding points). The comparison unit 512 excludes feature points that are farther away than the set threshold from the determination of corresponding points. Furthermore, in this embodiment, the threshold is set to be 2 to 3 orders of magnitude larger in the Y direction than in the X direction. For example, the threshold in the X direction is several millimeters, and the threshold in the Y direction is several meters. The threshold in the Y direction is 2 to 3 orders of magnitude larger than that in the X direction because the amount of variation is larger.

[0100] Furthermore, the comparison unit 512 can also use descriptors 1 and 2 to extract the most similar feature points from each other by measuring the distance between vectors in the high-dimensional vector space. In this case, the comparison unit 512 can also use the probability density function calculated by kernel density estimation as described above as descriptor 2. Figure 11 shows an example of the probability density function of the position and intensity (density) of feature points calculated by kernel density estimation. In Figure 11, the horizontal and vertical axes are XY coordinates, and represents the higher the concentration, the higher the density.

[0101] The comparison unit 512 determines that one feature point corresponds to only one feature point. For example, for the feature points of the second inspection data, the feature points whose descriptor vectors in the first inspection data are closest to each other are recorded in the corresponding point list as the corresponding points.

[0102] Figure 12 shows an example of a corresponding point list stored in the memory unit 52. The corresponding point list establishes correspondences between feature points in the second inspection data and the most similar feature points in the first inspection data. Furthermore, the corresponding point list records the Euclidean distance between the XY coordinates of the feature points in the second inspection data and the corresponding feature points, the difference dx in the X coordinate, and the difference dy in the Y coordinate. The control unit 51 then terminates the processing shown in Figure 10 and returns to the processing shown in Figure 8, proceeding to step S35 and below.

[0103] (Step S35) The extraction unit 513 classifies feature points into type 1 to type 3 feature points from the correspondence list, the first inspection data, and the second inspection data. The type 1 to type 3 feature points will be described later. Specifically, the extraction unit 513, in the correspondence list, classifies feature points in the second inspection data that do not correspond to feature points in the first inspection data as type 2 feature points. Furthermore, the extraction unit 513 classifies feature points in the first inspection data that are not included in the correspondence list (feature points that do not correspond to feature points in the second inspection data) as type 1 feature points.

[0104] (Feature points 1 to 3) Figure 13 is a table used to illustrate feature points 1 to 3.

[0105] (Type 1 Feature Point) The Type 1 Feature Point is a feature point that exists in the first inspection data but not in the second inspection data. The Type 1 Feature Point is a feature point that disappears in the second manufacturing process (e.g., coating process or lamination process). This Type 1 Feature Point is a feature point that does not require management in the first manufacturing process. In this case, the manufacturing conditions that contribute to the generation of the Type 1 Feature Point are those that can be mitigated by standards in the first manufacturing process.

[0106] (Second type of feature point) The second type of feature point is a feature point that does not exist in the first inspection data but exists in the second inspection data. The second type of feature point is a feature point newly generated in the second manufacturing process. Since this second type of feature point is a feature point that originates from the second manufacturing process, it can be used to improve the second manufacturing process.

[0107] (Third Type of Feature Point) The third type of feature point exists in both the first inspection data and the second inspection data. This third type of feature point originates from the first manufacturing process and is a feature point that needs to be managed. Since this third type of feature point originates from the first manufacturing process, it can be applied to the improvement of the first manufacturing process.

[0108] (Step S36) The control unit 51 records the feature point capture information obtained from the processing up to step S35 into the inspection data DB (end).

[0109] Figure 14 shows an example of data extraction. The data extraction records the check IDs of the first and second check data as the basis, along with the extraction results for each feature point. The extraction results (types 1-3) are classified as shown in Figure 13. The integrated feature point ID is automatically assigned a consecutive number, generating integrated feature points corresponding to feature points in either or both of the first and second check data. The number of integrated feature point IDs is ≥ the number of feature point IDs in the first and second check data.

[0110] Additionally, for a single batch ID, multiple first and second inspection data may sometimes be generated based on multiple inspection devices. For example, in a second manufacturing process, the original wound film roll 80 is inspected (photographed), and inspections are performed in several downstream processes, thereby generating multiple second inspection data. In this case, the information processing system 50 can also generate multiple feature point extraction data (one-to-many) between one first inspection data and multiple second inspection data. For example, when there are three inspection data, feature point extraction data is generated between the first and second inspection data and between the second and third inspection data respectively. Furthermore, when there are more than three inspection data, the user can also select which inspection data to establish a correspondence with.

[0111] (Analysis and Processing of Defect Occurrence Status) Figure 15 is a flowchart showing the analysis and display process for analyzing and displaying the occurrence status of defects between batches or inspection intervals. Figures 16A and 16B are examples of operation screens displayed on terminal devices 70, etc.

[0112] (Step S51) The selection unit 514 is for selecting object data based on the user's selection. For example, in the operation screen 701 shown in FIG16A, after selecting the product listed in the batch list (see FIG4) in area b0, the selection of (1) multiple batches or (2) multiple inspection intervals within one batch is accepted in area b1. Regarding multiple batches, it will be described later. Multiple inspection intervals, for example, in the case of a 3000m film, multiple inspection intervals are selected in the long side direction for every 500m or every 1000m. Alternatively, multiple inspection intervals are selected in the width direction for every 500mm. Moreover, the feature points of each of the multiple divisions are compared. In this case, the full length can also be displayed for comparison. For example, in the long side direction, it can also be prompted to use the total number of feature points of the full length divided by the number of divisions (average value) as the comparison object.

[0113] The operation screen 702 shown in Figure 16B is the screen displayed in Figure 16A when multiple batches of buttons in area b1 are pressed. Area b11 of operation screen 702 displays a list of batches related to the selected product. The user activates the selection of each batch using button b12. In the example of operation screen 702, batches 1 through 5 are selected. The user responds to the selection by pressing the confirmation button b13. Furthermore, when there are multiple manufacturing processes, the selection of the target manufacturing process can also be performed within a batch.

[0114] (Step S52) The acquisition unit 511 acquires the capture data corresponding to the conditions selected in step S51 from the inspection data DB. Figure 17 shows an example of the capture data list acquired in step S52. In the following explanation, it is assumed that "batch 1 to batch 5 are processed and manufactured through three consecutive manufacturing processes 1 to 3, and capture data between each process is acquired". For example, in the example shown in Figure 17, for batch 1, two capture data are recorded: capture data 01 and capture data 02. Capture data 01 corresponds to the capture data shown in Figure 14.

[0115] (Step S53) The selection unit 514 is based on the user's selection of the type of feature point. Regarding this selection, the user can select the type of feature point by selecting several areas of area b2 on the operation screen 701. In the example of operation screen 701, this indicates the selection of the second and third type of feature points. Furthermore, this selection can also be performed automatically on the control unit 51 side. For example, in area b2, the user can also select the "Auto" button, thereby automatically performing the selection on the control unit 51 side.

[0116] (Steps S54, S55) The display data generation unit 515 analyzes the feature point data and generates display data according to the conditions selected in steps S52 and S53. Hereinafter, the analysis and processing of feature point data will be explained with reference to Figures 18A to 18C.

[0117] Figures 18A and 18B are tables showing the analysis results. Figure 18A shows the analysis results for batch 1, which is selected as a representative of batches 1 to 5. Figure 18B is a table explaining the extraction conditions of the feature points in Figure 18A. As shown in extraction condition 1 of Figure 18A, the feature points (defects) generated in process 1 use the third type of feature points, which are extracted data 01 generated using the inspection data of processes 1 and 2 (see Figure 17). Furthermore, the feature points generated in process 2 use the second type of feature points, which are extracted data 01 of the same extraction data. The feature points generated in process 3 use the second type of feature points, which are extracted data 02 generated using the inspection data of processes 2 and 3. Process Total uses all feature points extracted from the inspection data (inspection data i03) of a single process 3. In this case, the second feature point, which spans more than three projects, is for newly generated projects. Specifically, as shown in condition 1, the second feature point used in project 3 is a second feature point classified by comparing the inspection data of project 3 with the inspection data of the previous project 2.

[0118] As a variation, extraction condition 2 can also be applied instead of extraction condition 1 shown in FIG18B. In extraction condition 2, conditions a and b are applied using an AND condition. For example, the feature point generated in process 1 is a third type of feature point, and the first type of feature point is excluded. Also, the feature point generated in process 2 is a third type of feature point between processes 2 and 3, and a second type of feature point between processes 1 and 2. In the following examples, extraction condition 1 is applied.

[0119] Furthermore, in Figure 18A, the feature points are divided into five segments, namely size 1 to size 5, based on their size (area), and the number of feature points for each size is represented. Size 1 is the smallest segment, and size 5 is the largest segment. Hereinafter, although the total value of these sums, i.e., size Total, is used, the values ​​statistically derived for each size segment can also be used based on user input settings.

[0120] The table in Figure 18C displays a list of the number of feature points generated in each process of each batch. By performing such analysis, the display data generation unit 515 generates display data. Furthermore, the output unit 516 outputs the generated display data. For example, display data as shown in Figure 19A below is displayed in area b4 (see Figure 16A) of the operation screen 701 of the terminal device 70.

[0121] The displayed data can be tabular data in the form of a table as shown in Figure 18C, or it can be a bar chart, line chart, dot plot, or stacked bar chart generated from the tabular data shown in Figure 18B. It can also be a Venn diagram. For example, for each batch, it can also show how many of the changing feature points overlap between three or more processes. Figures 19A-19E are examples of such line graphs.

[0122] Figures 19A-19D are charts generated based on the tabular data in Figure 18C. Figures 19A-19C are dot plots, while Figures 19D and 19E are examples of stacked bar charts. In Figure 19A, the number of feature points in the Total of batches 1-5 is shown. In Figure 19B, the number of feature points generated in process 3 of batches 1-5 is shown. As shown in condition 1 of Figure 18B, the type of feature points shown here is the second type. In Figure 19C, the number of feature points generated in process 1 of batches 1-5 is shown. As shown in condition 1 of Figure 18B, the type of feature points shown here is the third type. In Figure 19D, the number of feature points in the Total of batches 1-5 is shown, and each bar represents the number of feature points generated in each process of process 1-3. As shown in condition 1 of Figure 18B, the types of feature points shown here are the third type and the second type. In Figure 19E, the number of feature points in the total of batches 1 to 5 is represented, and the number of feature points in each of dimensions 1 to 5 is represented in a stacked manner in each bar.

[0123] By means of the above method, the following effect can be obtained, for example. In Figure 19A, it can be observed that compared with batches 1 to 3, batches 4 and 5 have an increased number of feature points in process 3. By comparing with Figures 19B and 20C or by referring to Figure 19D, it can be understood that the increase in feature points in process 3 (Total) is not due to an increase in process 3 itself, but rather an increase in process 1.

[0124] Thus, the information processing system of this embodiment includes: an acquisition unit that, based on the first inspection data from the first manufacturing process of manufacturing each batch of mesh or performing post-processing on the manufactured mesh, and the second inspection data from the second manufacturing process of performing post-processing on the mesh after the first manufacturing process, classifies the feature points contained in the first and second inspection data into a first type of feature point that exists in the first inspection data but not in the second inspection data, a second type of feature point that does not exist in the first inspection data but exists in the second inspection data, and a third type of feature point that exists in both the first and second inspection data, and acquires data from a recorded database. Furthermore, it includes: a selection unit that selects multiple batches of the target object or multiple inspection intervals along the long side direction of the mesh in one batch; a display data generation unit that generates display data from the data acquired by the acquisition unit from the database and selected by the selection unit; and an output unit that outputs the display data. By means of the above methods, the occurrence of defects can be monitored during both the manufacturing of films and other meshes and the subsequent processing using them. In particular, in the information processing system of this embodiment, the selection unit further accepts the selection of the types of feature points being categorized, and the display data generation unit generates display data based on the received data on the types of feature points. This allows for individual monitoring of the occurrence of feature points in each process of a batch. When manufacturing products through multiple processes, it is possible to identify which process resulted in a change, thereby preventing or anticipating engineering problems.

[0125] The configuration of the information processing system 50 described above is a description of the main components when 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 patent application. Furthermore, the configuration possessed by general information processing devices / systems is not excluded.

[0126] (Modification 1) For example, in the above example of display data, it represents an example of displaying a state that can grasp the changes in condition between multiple batches. In the modification example, when the user selects an inspection interval within a batch instead of between batches (area b1 in FIG. 16A), display data is generated to grasp the state changes between intervals within a batch. For example, if the film length of a batch is 3000m, it is divided into three intervals: 0~1000m, 1000~2000m, and 2000~3000m. Moreover, the display data generation unit 515 generates the same display data as FIG. 19A~19E for each interval. In this case, the inspection data is divided according to the specified interval, and capture data is generated for each segmented inspection data. Moreover, the display data generation unit 515 parses the capture data corresponding to the acquired segmented intervals, thereby generating display data. In such variations, the same effect as the embodiment shown in Figures 1-17 is achieved. For example, the occurrence status of feature points (defects) corresponding to time changes can be grasped within one batch.

[0127] (Modification 2) In the example shown in Figure 16A, although it illustrates that "the user can select the type of feature quantity for each type," the type can also be selected for each project. For example, as in condition 1 of Figure 18B, the third or second type of selection can be accepted for each project. Furthermore, as in condition 2, multiple types of selection can be accepted for each project in relation to previous and subsequent projects. For example, as shown in the table of condition 2, in project 2, the user selects the second type of feature point in relation to previous projects (projects 1 and 2) and selects the third type of feature point in relation to subsequent projects (projects 2 and 3), and the selection is accepted using the AND condition. In addition, the user can also select the desired type of curve graph instead of selecting the type of feature point by the user, thereby automatically selecting the type of feature point on the control unit 51 side. For example, when visually representing the status of newly generated feature points in each process, the user selects "defects generated in each process," thereby automatically setting the type of feature point in condition 1 or condition 2 shown in Figure 18B on the control unit 51 side.

[0128] (Modification 3) Alternatively, the series of processes shown in Figure 15 can be performed in real time. For example, inspection data obtained from each process can be processed in real time and displayed according to preset conditions. Furthermore, an alarm can be output based on the number of newly generated second-type feature points. Specifically, if the number of newly generated second-type feature points exceeds a threshold, an alarm is issued to the target process (e.g., arbitrarily set such as the process that generated the feature point or processes before and after it). As a result, the improvement of the fault can be quickly determined and assistance provided.

[0129] (Modification 4) Furthermore, the information processing system 50 may also include an inspection device 90 disposed in the first manufacturing process and / or the second manufacturing process. Also, the control unit 51 of the information processing system 50 may also perform the function of generating feature points for the image analysis unit 93 of the inspection device 90. In this case, the inspection device 90 sends image data of the film surface captured and its photographic conditions (transfer speed, camera orientation, viewing angle, etc.) to the information processing system 50, and the feature point generation process is performed on the control unit 51 side.

[0130] Furthermore, the means and methods for performing various processes in the information processing system 50 of the above embodiment can be implemented by either dedicated hardware circuitry or a programmed computer. The aforementioned program can be provided, for example, via a computer-readable recording medium such as a USB memory or a DVD (Digital Versatile Disc)-ROM, or online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is usually transferred and stored in the memory of a hard drive or similar device. Furthermore, the aforementioned program can also be provided as standalone application software, or it can be integrated into the software of a device as a function of the device.

[0131] Although embodiments of the present invention have been described and illustrated in detail, the disclosed embodiments are for illustrative and exemplary purposes only and are not intended to be limiting. The scope of the present invention should be interpreted by the terminology used in the appended claims.

[0132] This application is based on Japanese Patent Application No. 2024-064474 filed on April 12, 2024, and its disclosure is incorporated in its entirety for reference. [Simplified Explanation of the Diagram]

[0021] The advantages and features provided by one or more embodiments of the present invention will be more fully understood from the following detailed description and accompanying drawings. However, these are intended for illustrative purposes only and are not intended to limit the invention. [Fig. 1] A schematic diagram showing an applicable example of the information processing system of this embodiment. [Fig. 2A] A schematic diagram showing the configuration of the inspection device. [Fig. 2B] A schematic diagram showing the configuration of the inspection device. [Fig. 2C] A schematic diagram showing the configuration of the inspection device. [Fig. 3] A block diagram showing the schematic configuration of the information processing system. [Fig. 4] Examples of various data stored in the memory unit. [Fig. 5] A flowchart showing the generation process of the first inspection data performed in the first manufacturing process. [Fig. 6] A flowchart showing the generation process of the second inspection data performed in the second manufacturing process. [Fig. 7] Examples of various data in the inspection data DB stored in the memory unit. [Fig. 8] A flowchart showing the feature point extraction process, etc., performed in the information processing system. [Fig. 9] A schematic diagram illustrating the feature point extraction process. [Figure 10] A flowchart showing the routine process of comparison processing in step S34. [Figure 11] An example of the probability density function of the position and intensity of feature points calculated by kernel density estimation. [Figure 12] An example of a list of corresponding points. [Figure 13] A table illustrating the first to third types of feature points. [Figure 14] An example of feature point data extraction. [Figure 15] A flowchart showing the analysis process of analyzing and displaying the generation status of defects. [Figure 16A] An example of an operation screen displayed on a terminal device. [Figure 16B] An example of an operation screen displayed on a terminal device. [Figure 17] An example of a data extraction list. [Figure 18A] A table showing the analysis results of feature points in batch 1. [Figure 18B] A table illustrating the extraction conditions 1 and 2 of feature points in Figure 18A. [Figure 18C] A table showing the generation status of feature points in each batch. [Figure 19A] An example of data display. [Figure 19B] An example of data display. [Figure 19C] An example of data display. [Figure 19D] shows an example of data. [Figure 19E] shows an example of data.

Claims

1. An information processing system, characterized by comprising: an acquisition unit that, based on first inspection data from a first manufacturing process in which a manufacturing wire is manufactured or the manufactured wire is post-processed, and second inspection data from a second manufacturing process in which the post-processing of the wire is performed after the first manufacturing process, classifies feature points contained in each of the first and second inspection data into a first type of feature point present in the first inspection data but absent in the second inspection data, a second type of feature point absent in the first inspection data but present in the second inspection data, and a third type of feature point present in both the first and second inspection data, and acquires data from a recorded database; a selection unit that selects multiple batches of objects or multiple inspection intervals along the long side direction of a single batch of wire; a display data generation unit that generates display data from the data acquired by the acquisition unit from the database and selected by the selection unit; and an output unit that outputs the display data.

2. As in request item 1, the information processing system, wherein, The aforementioned selection unit further accepts the selection of the types of feature points being classified, and the aforementioned display data generation unit generates the aforementioned display data based on the data of the types of feature points accepted.

3. As in request item 1, the information processing system, wherein, The aforementioned data includes charts that compare feature points generated in multiple batches of manufacturing processes.

4. As in request item 3, the information processing system, wherein, The aforementioned chart is a chart comparing the second type of feature points generated in subsequent manufacturing processes across multiple batches.

5. The information processing system as described in request item 3, wherein, The aforementioned charts contain at least one of the following: bar chart, line chart, dot chart, and stacked bar chart.

6. A control method characterized by performing a process comprising the following steps: Step (a), based on first inspection data in a first manufacturing process of manufacturing a wire mesh or performing post-processing on the manufactured wire mesh and second inspection data in a second manufacturing process after the first manufacturing process that performs post-processing on the wire mesh, classifying the feature points contained in each of the first and second inspection data into a first type of feature point present in the first inspection data but not present in the second inspection data, a second type of feature point not present in the first inspection data but present in the second inspection data, and a third type of feature point present in both the first and second inspection data, and retrieving data from a recorded database; Step (b), selecting a plurality of batches of accepted objects or selecting a plurality of inspection intervals in the long side direction of a wire mesh in a batch; Step (c), generating display data from the data retrieved from the database in step (a) and selected by step (b); and Step (d), outputting the display data.

7. As in request item 6, the control method, wherein, In step (b) above, the selection of the types of the classified feature points is further accepted. In step (c) above, the aforementioned display data is generated based on the data of the types of the accepted feature points.

8. As in request item 6, the control method, wherein, The aforementioned data includes charts that compare feature points generated in multiple batches of manufacturing processes.

9. As in request item 8, the control method, wherein, The aforementioned chart is a chart comparing the second type of feature points generated in subsequent manufacturing processes across multiple batches.

10. As in request item 8, the control method, wherein, The aforementioned charts contain at least one of the following: bar chart, line chart, dot chart, and stacked bar chart.

11. A control program characterized in that it causes a computer to perform control methods as requested in items 6 to 10.

Images