Information processing system, control method, and control program

Abstract

An information processing system (50) includes: an acquisition unit (511) that acquires data from a database that classifies feature points included in each of first inspection data and second inspection data acquired by a process into a first type of feature point that exists in the first inspection data and does not exist in the second inspection data, a second type of feature point that does not exist in the first inspection data and exists in the second inspection data, and a third type of feature point that exists in both the first inspection data and the second inspection data, and records the classification; a selection unit (514) that receives selection of a plurality of batches of objects or selection of a plurality of inspection intervals in a length direction of a roll in one batch; a display data generation unit (515) that generates display data based on data selected by the selection unit (514) and acquired from the database by the acquisition unit (511); and an output unit (516) that outputs the display data.

Description

Technical Field

[0001] This invention relates to information processing systems, control methods, and control programs. Background Technology

[0002] As liquid crystal displays (LCDs) are increasingly used in large-screen televisions and monitors, there is a growing demand for wider films used in their display surfaces. For example, wide films with a width of 2000 mm or more are currently required. Furthermore, to anticipate substrate loss (film loss) or reduce transportation costs, it is necessary to manufacture film rolls with winding lengths exceeding 1000 m, and even 3000 m or more.

[0003] In the post-processing stages of manufacturing products based on film and other roll materials, when quality problems such as defects arise, it is necessary to distinguish whether the defect originated in the previous process (i.e., during the manufacturing of the roll material and was already present on the roll material) or a defect arose in the post-processing stage. When it is not clear whether the defect originated in the post-processing stage, improvements to the previous process are sometimes required. If attempts are made to meet these improvement requirements, the shipping specifications of the previous process may become more stringent than necessary, resulting in specification overruns. Furthermore, although the impact on the post-processing stage may not be clear, sometimes the shipping specifications during roll material manufacturing are set excessively strictly in order to prevent quality problems. This also leads to specification overruns. Specification overruns result in decreased yield, increased costs, are not environmentally friendly, and are undesirable for both the operators implementing the previous and post-processing stages.

[0004] Patent document 1 discloses the following technology: an optical thin film inspection system is equipped with first and second inspection units that detect defects at different stages of the manufacturing process, and the defects obtained by these inspection units are combined to determine the predicted yield based on the cutting position and size.

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2013-024868 Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] However, the technology in Patent Document 1 is a technology for integrating defects generated between multiple processes, not a technology for understanding the generation status of defects in a process.

[0009] The present invention was made in view of the above circumstances, and its purpose is to understand the occurrence of defects during the manufacture of films and other roll materials and during the manufacturing process of using the roll material for subsequent processing.

[0010] The present invention achieves the above objectives through the following means.

[0011] (1) An information processing system, comprising:

[0012] The acquisition unit acquires data from a database. The database is based on first inspection data from a first manufacturing process that manufactures or processes manufactured rolls, and second inspection data from a second manufacturing process that processes the rolls after the first manufacturing process. The database classifies feature points contained in the first inspection data and the second inspection data into three categories: first type feature points that exist in the first inspection data but not in the second inspection data; second type feature points that do not exist in the first inspection data but exist in the second inspection data; and third type feature points that exist in both the first inspection data and the second inspection data. The database is then recorded.

[0013] The selection department allows for the selection of multiple batches of the accepted items or the selection of multiple inspection intervals along the length of the roll material within a single batch.

[0014] The display data generation unit generates display data based on the data obtained by the acquisition unit from the database and selected by the selection unit; and

[0015] The output unit outputs the displayed data.

[0016] (2) In the information processing system described in (1) above,

[0017] The selection unit also handles the selection of the types of the classified feature points.

[0018] The display data generation unit generates the display data based on the data of the types of feature points received.

[0019] (3) In the information processing system described in (1) above,

[0020] The displayed data includes charts comparing feature points generated in multiple batches of manufacturing processes.

[0021] (4) In the information processing system described in (3) above,

[0022] The chart is a comparison of second-type feature points generated in subsequent manufacturing processes across multiple batches.

[0023] (5) In the information processing system described in (3) above,

[0024] The charts include at least one of the following: bar chart, line chart, scatter plot, and stacked bar chart.

[0025] (6) A control method for performing a process comprising the following steps:

[0026] Step (a): Obtain data from the database, which is based on the first inspection data in the first manufacturing process of manufacturing rolls or post-processing the manufactured rolls and the second inspection data in the second manufacturing process of post-processing the rolls after the first manufacturing process. The database classifies the feature points contained in the first inspection data and the second inspection data into a first type of feature points that exist in the first inspection data but do not exist in the second inspection data, a second type of feature points that do not exist in the first inspection data but exist in the second inspection data, and a third type of feature points that exist in both the first inspection data and the second inspection data, and records them.

[0027] Step (b): Selecting multiple batches of the accepted items or selecting multiple inspection intervals along the length of the roll material in a batch;

[0028] Step (d): Based on the data obtained from the database in step (a) and selected in step (a), generate display data; and

[0029] Step (e): Output the displayed data.

[0030] (7) In the control method described in (6) above,

[0031] In step (b), the selection of the types of the classified feature points is also accepted.

[0032] In step (d), the display data is generated based on the data of the types of feature points accepted.

[0033] (8) In the control method described in (6) above,

[0034] The displayed data includes charts comparing feature points generated in multiple batches of manufacturing processes.

[0035] (9) In the control method described in (8) above,

[0036] The chart is a comparison of second-type feature points generated in subsequent manufacturing processes across multiple batches.

[0037] (10) In the control method described in (8) above,

[0038] The charts include at least one of the following: bar chart, line chart, scatter plot, and stacked bar chart.

[0039] (11) A control program for causing a computer to perform any one of the control methods described in (6) to (10) above.

[0040] Invention Effects

[0041] The information processing system of the present invention comprises: an acquisition unit that acquires data from a database, the database being based on first inspection data from a first manufacturing process involving the manufacture of rolled materials or the post-processing of already manufactured rolled materials, and second inspection data from a second manufacturing process involving the post-processing of rolled materials after the first manufacturing process; classifying feature points contained in each of the first and second inspection data into first-type feature points present in the first inspection data but absent in the second inspection data, second-type feature points absent in the first inspection data but present in the second inspection data, and third-type feature points present in both the first and second inspection data, and recording these classifications; a selection unit that selects multiple batches of objects to be accepted or multiple inspection intervals along the length direction of rolled materials in a batch; a display data generation unit that generates display data based on data acquired from the database by the acquisition unit and selected by the selection unit; and an output unit that outputs the display data. Thus, the occurrence of defects can be understood during the manufacture of rolled materials and in the manufacturing processes involving the post-processing of rolled materials. Attached Figure Description

[0042] 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 for illustrative purposes only and are not intended to limit the invention.

[0043] Figure 1 This is a schematic diagram illustrating an application example of the information processing system of this embodiment.

[0044] Figure 2A This is a schematic diagram showing the configuration of the inspection device.

[0045] Figure 2B This is a schematic diagram showing the configuration of the inspection device.

[0046] Figure 2C This is a schematic diagram showing the configuration of the inspection device.

[0047] Figure 3 It is a block diagram that represents the general structure of an information processing system.

[0048] Figure 4 These are examples of various types of data stored in the storage department.

[0049] Figure 5 This is a flowchart representing the generation process of the first inspection data performed in the first manufacturing process.

[0050] Figure 6 This is a flowchart illustrating the generation process of the second inspection data performed in the second manufacturing process.

[0051] Figure 7 These are various data examples representing the inspection data DB stored in the storage department.

[0052] Figure 8 It is a flowchart representing the feature point extraction and processing performed in an information processing system.

[0053] Figure 9 This is a schematic diagram used to illustrate the feature point extraction process.

[0054] Figure 10 This is a flowchart of the subroutine for the comparison process in step S34.

[0055] Figure 11 This is an example of a probability density function that represents the location and intensity of a feature point, calculated using kernel density estimation.

[0056] Figure 12 This is an example of a list of corresponding points.

[0057] Figure 13 It is a table used to describe the first to third types of feature points.

[0058] Figure 14 This is an example of data extracted from feature points.

[0059] Figure 15 It is a flowchart that represents the analysis and displays the occurrence of defects.

[0060] Figure 16A This is an example of the operation screen displayed on the terminal device.

[0061] Figure 16B This is an example of the operation screen displayed on the terminal device.

[0062] Figure 17 This is an example of extracting a list of data.

[0063] Figure 18A This is a table showing the analysis results of feature points in batch 1.

[0064] Figure 18B It is used for explanation Figure 18A The table shows the extraction conditions 1 and 2 for feature points in the image.

[0065] Figure 18C It is a table showing the generation status of feature points in each batch.

[0066] Figure 19AThis is an example of displaying data.

[0067] Figure 19B This is an example of displaying data.

[0068] Figure 19C This is an example of displaying data.

[0069] Figure 19D This is an example of displaying data.

[0070] Figure 19E This is an example of displaying data. Detailed Implementation

[0071] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the scope of the present invention is not limited to the disclosed embodiments. Furthermore, in the description of the drawings, the same reference numerals are used for the same elements, and repeated descriptions are omitted. In addition, the dimensions of the drawings are exaggerated for ease of explanation and may differ from the actual scale.

[0072] (Roll material)

[0073] In this embodiment, "roll material" refers to sheet-like materials, including resin films and metal films. Furthermore, the roll material also includes laminates. Hereinafter, the roll material will be described as a long resin film, and the film roll and its processing will be explained. The processing includes applying a coating liquid and a lamination process of overlapping another sheet material to form a laminate.

[0074] (batch)

[0075] In this embodiment, in a typical example, batches are assigned per roll unit (film roll unit). In other examples, batch refers only to the method of ID division, which can be selected as a batch division based on the actual roll or a division based on the time information of the manufacturing or subsequent processes. For example, it can be associated with the inspection time performed by the inspection device set in the process. This can be achieved by creating another table that corresponds multiple inspection times to films or film rolls. In addition, any ID with an additional number (unique ID) can be used as the definition of a batch as needed. Hereinafter, the batch number is described as the case where a unique number is automatically assigned.

[0076] Furthermore, sometimes batch IDs are assigned branch number IDs or new batch IDs in any process, and the correspondence is not one-to-one; there may be one-to-many or many-to-one relationships. For example, sometimes a 3000-meter film in one process might be divided into three 1000-meter rolls in a later process. In this case, the branch number ID or the new batch ID is assigned as the batch ID in the later process. Conversely, sometimes two or three film rolls are joined together into one film in one process and used in a later process. In this case, there are two or three batch IDs in the previous process, but only one batch ID in the later process. In either case, the correspondence between batch IDs in each process is recorded in the batch list (see below). Figure 4 )middle.

[0077] (Feature point information)

[0078] In this embodiment, feature points refer to defects on the thin film, which are generated by analyzing image data. Image analysis can employ known techniques, extracting pixels whose pixel values ​​deviate from the surrounding average by a predetermined margin (difference exceeding a predetermined margin) from image data obtained from photographing the thin film surface as feature points. Alternatively, the "image processing for feature point generation" method described later can be used for calculation. One or more image data obtained from photographing a single roll of thin film (80 km in length) typically generate tens to thousands of feature points. Defects include both problems leading to product defects and minor issues that do not reach the product defect level. Feature points include defects related to poor adhesion, axial misalignment, etc., that occur during the bonding of the thin films together (e.g., ultrasonic welding). Feature point information includes size and position (xy coordinates). Furthermore, information that merges multiple neighboring feature points into one (clustering) can also be used as feature point information. The image processing for feature point generation will be described later.

[0079] Figure 1 This is a schematic block diagram illustrating an applicable example of the information processing system 50 of this embodiment. For example... Figure 1 As shown, the information processing system 50 communicates with terminal devices 70 in factories A and B via a network. The network is a data communication network or similar communication line. In some networks, wired LANs, wireless LANs, etc. (e.g., LANs conforming to the IEEE 802.11 standard) are used. A detailed description of the information processing system 50 will be given later.

[0080] Terminal device 70 is, for example, a PC (personal computer). For example, terminal device 70 is a PC used by employees of a manufacturing company that operates factory A and factory B.

[0081] Factory A is equipped with the aforementioned film roll manufacturing apparatus 1000. Factory A is, for example, operated or managed by a film manufacturer. A first manufacturing process for producing film roll 80 is performed in factory A. This first manufacturing process includes multiple sub-processes such as drying, stretching, and winding. Inspection devices 90a1 and 90a2 (hereinafter collectively referred to as inspection devices 90) are arranged before and after these sub-processes. The film surface of film roll 80 is inspected by the multiple inspection devices 90a1 and 90a2. Figure 1 Although two inspection devices 90a1 and 90a2 are shown, the number of inspection devices 90 is not limited to this; there may be one or more than three.

[0082] Factory B is equipped with a product manufacturing facility 2000. Factory B is operated or managed by, for example, a coating manufacturer (hereinafter also referred to as a user company or user). There are multiple user companies operating each factory B. In factory B, products are manufactured using film rolls 80 shipped and transported from factory A. Factory B includes multiple sub-processes, which involve drawing and unloading film (film F8 described later) from film rolls 80, and performing post-processing such as coating, overlapping with other films, or even bonding. Each sub-process corresponds to a first or second manufacturing process. Multiple inspection devices 90b1 to 90b4 (hereinafter collectively referred to as inspection devices 90) are arranged before and after the multiple sub-processes. Figure 1 Although four inspection devices 90b1, 90b2, 90b3, and 90b4 are shown, the number of inspection devices 90 is not limited to this; it can be three or fewer, or five or more.

[0083] In this embodiment, in a typical example, the process of manufacturing the film (roll) is referred to as the first manufacturing process, and the post-processing performed at factory B using the manufactured film is referred to as the second manufacturing process. For example, the post-processing process includes coating a functional layer onto the surface and laminating another film or roll. In the second manufacturing process, the film surface of the film roll 80 is also inspected by the inspection device 90.

[0084] As Figure 1 The raw materials for the manufactured film F8 shown are not particularly limited, and generally include polycarbonate resin, polysulfone 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, polyurethane resin, polyvinyl acetate resin, polyvinyl alcohol resin, styrene resin, cellulose acetate resin, and vinyl chloride resin, etc. Furthermore, considering factors such as productivity and quality, the width of the film F8 is preferably 1000 mm to 3200 mm. Considering factors such as quality and handling, its thickness is preferably 15 μm to 500 μm.

[0085] As an atypical example of this 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 step, and the subsequent post-processing step is sometimes referred to as the second manufacturing step. Additionally, sometimes the film roll 80 manufactured in factory A is unrolled and post-processed during the post-processing steps. In a typical example, the sub-processes performed at factory B include a lamination process (also called a bonding process) that overlaps and bonds other films. The laminate 80B is formed through the lamination process (see reference...). Figure 1 (Enlarged cross-sectional view of the leader line). Below, through several sub-processes in Factory B, layers 1 through 3 are bonded or coated onto the base film (F8). Note that the labels for the bonding layers between each layer are omitted in the enlarged cross-sectional view of the leader line. For example, film F8 is a PVA (polyvinyl alcohol resin) layer, layer 1 is a TAC (cellulose triacetate) layer, layer 2 is an optical functional film layer such as a polarizer, and layer 3 is a protective film. Alternatively, layer 3 can also be a separating film or an anti-glare film, etc. Layer 3 is an opaque layer.

[0086] The inspection device 90 photographs the thin film, etc., and generates inspection data. As shown above, in Figure 1 In the example shown, multiple inspection devices 90 are positioned before and after sub-processes such as the stretching and laminating processes in the film production line. (Refer to the following...) Figures 2A to 2C The inspection device 90 is described below.

[0087] (Inspection device 90)

[0088] The following methods (1) and (2) are used to detect surface irregularities, bubbles, cracks, strain, etc., of transparent bodies such as thin film F8 as test objects. Additionally, the following methods (2) are used to detect surface irregularities, bubbles, cracks, strain, etc., of opaque bodies as test objects: (1) A transmission-type inspection device that detects defects in the test object by irradiating it with light and receiving the light transmitted through it. (2) A reflection-type inspection device that detects defects in the test object by receiving the light reflected from it.

[0089] Furthermore, both the transmissive and reflective inspection devices include a bright-field inspection device that receives unscattered surface light and a dark-field inspection device that receives scattered light, depending on the positional relationship between the camera's optical axis, the light source, and the inspected object. In the bright-field inspection device, when no defect exists, light emitted from the light source is incident on the light detection unit unobstructed due to the absence of light scattering; when a defect exists, the light is blocked by the defect and does not incident on the light detection unit. Therefore, the defect is observed as a dark spot or stripe against a bright background. In contrast, in the dark-field inspection device, when no defect exists, light is not scattered and therefore does not incident on the light detection unit; however, when a defect exists, the light is scattered by the defect and thus incident on the light detection unit. Therefore, the defect is observed as a bright spot or stripe against a dark background. Any type of inspection device can be used as the inspection device 90 in this embodiment. Preferably, the first inspection data and the second inspection data are obtained by the same type of inspection device, but this is not a limitation.

[0090] (Reflective inspection device)

[0091] Figure 2A This is a schematic diagram showing the configuration of the reflective inspection device 90 as viewed from the width direction (X direction). Figure 2B This 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 analysis unit 93 as a data processing unit, and a storage unit 94. The inspection device 90 performs optical inspection on feature points (hereinafter also referred to as defects) generated on the film F8 during transport. In the inspection device 90, the camera 92 performs optical inspection on the film F8 of the film roll 80 and generates image data as inspection data. The image data includes not only still images but also dynamic image data composed of time-series continuous still images. Alternatively, as inspection data, feature points can be extracted directly from the signal data without digitizing the image data. For the camera 92, the number of cameras, the viewing angle, and the distance to the film surface are set so that the entire width direction of the film F8 becomes the inspection area (shooting range). The reason for setting the number of cameras is that when one camera cannot properly capture the entire width of the film, multiple cameras are arranged side by side along the width direction. Figure 2BThis diagram illustrates, as an example, a configuration where two cameras 92 are arranged along 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 data representing the entire film surface of the film roll 80, or it can store multiple image data in the storage unit 94 corresponding to the capture time. Alternatively, it can combine the same image data acquired by multiple cameras 92 arranged along the width direction. By referring to the stored transport speed (winding speed or delivery speed), the image analysis unit 93 can determine the position of the film F8 in the length direction based on the capture time corresponding to the image data. In the following description, it will be assumed that multiple image data acquired through continuous capture are stored corresponding to the capture time for one film roll 80, and this will be explained accordingly. The image analysis unit 93 generates defect information by analyzing the image data. The inspection device 90 inspects defects generated during manufacturing processes such as the winding of the long-size film F8.

[0092] Light source 91 illuminates the inspection area of ​​film F8. Light source 91 is a device that uniformly illuminates the roll-shaped film F8 in the width direction (orthogonal to the length direction of film F8 and parallel to the film surface). Here, "uniform" means that the illuminance on film F8 is basically consistent throughout the entire width direction of film F8 (the difference between the maximum and minimum values ​​is less than a predetermined value, etc.).

[0093] Camera 92 is an optical sensor that optically reads the inspection area of ​​thin film F8. Camera 92 includes an imaging element such as a CCD (charge-coupled device) or CMOS (complementary metal-oxide-semiconductor), and lenses. Camera 92 is an area array sensor that generates two-dimensional image data from the output signals of each image sensor. Camera 92 detects scattered light in the light illuminated by light source 91 and reflected from the inspection area of ​​thin film F8. Here, either a color camera or a black-and-white camera (monochrome camera) can be used as camera 92.

[0094] One or more cameras 92 have a shooting range spanning the entire width direction of the thin film F8, and can simultaneously read the entire width direction of the thin film F8 in a single shot. The camera 92 can be a device for detecting light in the visible light region or a device for detecting light in the infrared region.

[0095] Furthermore, in the output signal of the camera 92, it is desirable that the contrast between the signal value corresponding to the illuminated portion of the film F8 illuminated by the light source 91 and the signal value corresponding to the unilluminated portion not illuminated by the light source 91 is at least a predetermined value. In other words, it is desirable that only the portion of the film F8 illuminated by the light source 91 (the illuminated portion) appears bright.

[0096] 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 light source 91 with high power and high linearity.

[0097] Here, "high power" means that when the illuminance at an illumination distance of 50mm is set to E50, the illuminance E50 is above 50000lx. In addition, "high directness" means that when the illuminance at an illumination distance of 50mm is set to E50 and the illuminance at an illumination distance of 100mm is set to E100, (E50-E100) / E50 < 0.5.

[0098] The image analysis unit 93 consists of a CPU, RAM, etc. It reads various processing programs stored in the storage unit 94 and expands them in RAM, and performs various processes in cooperation with the programs.

[0099] The storage unit 94, composed of HDD, SSD (solid-state drive), etc., stores various processing programs and data required to execute those programs. Furthermore, the storage unit 94 stores the captured image data (inspection data) in association with the capture time. The storage unit 94 also stores the winding speed (e.g., 100 m / min) in the film roll manufacturing apparatus 1000 or the film F8 release / deletion conditions (e.g., 30 m / min) in the product manufacturing apparatus 2000. These winding speeds and release conditions can also be included in the inspection list of the inspection data DB (database) (see reference). Figure 4 In Table T3).

[0100] The image analysis unit 93 detects feature points (position, intensity) such as defects in the thin film F8 by processing the output signal of the camera 92 (optical sensor). 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 processing data, and quantitative evaluation processing to quantitatively evaluate defects based on the image processing data.

[0101] (Relative position of camera 92 and light source 91)

[0102] The camera 92 can also be configured to receive specularly reflected light from the light source 91 (in the case of a bright-field inspection mode that receives non-scattered light).

[0103] Furthermore, the camera 92 can also be positioned to avoid receiving specularly reflected light from the light source 91 (in the case of a dark-field inspection mode that receives scattered light). That is, it is preferable to position it to receive scattered light from the light reflected by the object being inspected.

[0104] (Transmission-type inspection device)

[0105] Figure 2C An example of a transmissive inspection device 90 is shown. Thus, a transmissive inspection device 90 in which the light source 91 is positioned opposite the camera 92 through the thin film F8 can also be used.

[0106] (Information Processing System 50)

[0107] The following is for reference Figure 3 The information processing system 50 is described below. Figure 3 This is a block diagram showing the general structure of an information processing system 50. The information processing system 50 is, for example, a server. Figure 3 As shown, the information processing system 50 includes a control unit 51, a storage unit 52, and a communication unit 53. The storage unit 52 stores inspection data DB.

[0108] (Control Department 51)

[0109] The control unit 51 includes a CPU and memory such as RAM and ROM. The CPU is a control circuit composed of a multi-core processor, etc., which executes the control and various calculations of the above-mentioned units according to the program. The functions of the information processing system 50 are realized by the CPU executing the corresponding program.

[0110] The control unit 51, in cooperation with the communication unit 53, functions as an acquisition unit 511, a selection unit 514, and an output unit 516. Furthermore, the control unit 51 functions as a comparison unit 512, an extraction unit 513, and a display data generation unit 515. The acquisition unit 511 acquires various data from the inspection data database.

[0111] Furthermore, the acquisition unit 511 acquires first and second inspection data obtained through the inspection processes of the first and second manufacturing steps. The comparison unit 512 extracts feature points from the first and second inspection data respectively. The comparison unit 512 searches for corresponding feature points in each of the first and second inspection data through comparison processing. In the comparison processing, the comparison unit 512 generates a descriptor for the feature points (descriptor 2 described later) for the two inspection data (image data), and performs feature point matching processing between the inspection data using the feature point descriptor, outputting the comparison result (described later). Figure 12 (See the list of corresponding points shown). The extraction unit 513 uses the comparison results to extract (classify) feature points of the first to third categories.

[0112] The selection department 514 accepts users' selections regarding the type of feature points, batch, or inspection range.

[0113] The display data generation unit 515 generates display data based on the data selected by the selection unit 514. The display data is a chart used to visually represent the data. The chart includes tabular data and graphs. The graphs include bar charts, line charts, scatter plots, stacked bar charts, etc., showing the generation status of feature points. For example, it includes bar charts, line charts, scatter plots, and stacked bar charts showing the generation status of feature points in each process between batches. The output unit 516 sends the display data to the terminal device 70 or displays it on the display unit (not shown in the figure) of the terminal device 70 according to the request of the terminal device 70, etc.

[0114] (Storage Department 52)

[0115] Storage unit 52 is a large-capacity auxiliary storage device that stores various programs and data, including the operating system. The storage device can be, for example, a hard disk drive, a solid-state drive, flash memory, or ROM. Storage unit 52 stores user lists, batch lists, and inspection data (DB). The management and registration of user lists and batch lists are performed through an administrator access terminal device 70. For example, this administrator could be the head of the department responsible for the manufacturer operating factory A. The inspection data DB of storage unit 52 can also be an external database independent of information processing system 50.

[0116] (User List)

[0117] Figure 4 These are examples of various data stored in storage unit 52. Figure 4 Table T1 shown is an example of a user list. The user list stores user IDs, usernames, contact information, etc. In addition, users are given access permissions to the database for retrieving data for each user, and are granted access permissions to various data (check data, extract data, etc.) related to the thin film roll 80 (identified by batch ID) associated with the user.

[0118] (Batch list)

[0119] Figure 4 Table T2 is an example of a batch list. The batch list records the batch ID assigned to each film roll, the product name (also known as variety), the recipient user ID (orderer), and multiple manufacturing conditions, dimensions (width, length, thickness), manufacturing date, etc.

[0120] (Check the database)

[0121] Figure 4 Table T3 is an example of an inspection list registered in the inspection data database. The inspection list stores information such as inspection ID, batch ID, inspection device ID, inspection data, and inspection date and time. The inspection device ID corresponds to... Figure 1Examples of inspection devices such as the inspection device 90a1 shown, with respect to inspection data included in the inspection list, will be described later.

[0122] (Ministry of Communications 53)

[0123] The communication section 53 is also an interface used for network connection with external devices such as PCs.

[0124] (Generation and processing of the first and second inspection data)

[0125] The following is for reference Figures 5-7 The generation and processing of the first and second inspection data performed in the first and second manufacturing processes are explained. Figure 5 This is a flowchart illustrating the process of generating the first inspection data performed in the first manufacturing step. Figure 6 This is a flowchart illustrating the process of generating second inspection data performed in the second manufacturing step. Figure 7 It shows through Figure 5 , Figure 6 The diagram shows examples of the first and second inspection data obtained through processing. The first inspection data is generated through the processing described below. Figure 1 In the example shown, the inspection data is generated based on image data acquired by any one of the inspection devices 90a1 to 90b3. The second inspection data is generated based on image data acquired by the inspection device 90, which is located downstream of the inspection device 90 that acquired the first inspection data, through the generation process described below.

[0126] (Generation and processing of the first inspection data)

[0127] Figure 5 This is a flowchart illustrating the process of generating the first inspection data performed in the first manufacturing step.

[0128] (Step S11)

[0129] In the above typical example, in the first manufacturing process, a film roll 80 is manufactured by a film roll manufacturing apparatus 1000.

[0130] (Step S12)

[0131] The inspection device 90 captures images of the thin film and saves the image data. The inspection device 90 is designed to utilize... Figure 3 The apparatus described in section A.

[0132] (Step S13)

[0133] The image analysis unit 93 performs image processing on the image data as described below to generate multiple feature points.

[0134] (Image processing used to generate feature points)

[0135] The image analysis unit 93 acquires two-dimensional image data generated by the camera 92 and stored in the storage unit 94.

[0136] The image analysis unit 93 performs data processing on the image data (inspection data) acquired from the camera 92.

[0137] The image analysis unit 93 divides the image data into multiple 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.

[0138] Next, the image analysis unit 93 acquires image data of region a1 and performs mathematical processing on the image data of region a1. Appropriate mathematical processing is prepared according to the type of defect of the detected object (dark stripes, longitudinal wrinkles, oblique wrinkles, uneven bright spots, light leakage, etc.).

[0139] Mathematical processing includes preprocessing, enhancement processing, signal processing, and image feature extraction.

[0140] As a preprocessing step, the following steps can be taken:

[0141] • Image cropping

[0142] • Low-pass filter, high-pass filter, Gaussian filter, median filter, bilateral filter

[0143] • Morphological transformation, color transformation (L*a*b*, sRGB, HSV, HSL), contrast adjustment, noise removal, restoration of blurred / shaky images, mask processing, Hough transform, projection transformation, etc.

[0144] Examples of enhancement methods include the Sobel filter, Scharr filter, Laplacian filter, Gabor filter, and Canny method.

[0145] As a form of signal processing, the following processes can be listed:

[0146] • Basic statistics (maximum, minimum, mean, median, standard deviation, variance, quartiles), root mean square, difference, sum, product, ratio, distance matrix processing, calculus, threshold processing (binarization, adaptive binarization, etc.).

[0147] • Fourier transform, wavelet transform, peak detection (peak value, number of peaks, full width at half maximum, etc.), etc.

[0148] Examples of image feature extraction methods include template matching and SIFT features.

[0149] Next, the image analysis unit 93 performs thresholding on the values ​​(feature quantities) obtained through mathematical processing of the image data for region a1. Thresholding is a process that determines whether a defect is a defect of the detection object based on a predetermined defect determination threshold, and determines the level (intensity) of the defect.

[0150] In threshold processing, determining the existence and type of a defect is equivalent to "defect determination processing." Furthermore, in threshold processing, classifying defects into multiple levels according to thresholds is equivalent to "quantitative evaluation processing."

[0151] For example, for parameters (features) with values ​​from 1 to 100, defects are classified into multiple levels. For instance, levels can be classified based on defect size (diameter or area). Furthermore, the levels classified by size can be further subdivided based on the parameter value.

[0152] The image analysis unit 93 performs the same processing on regions other than region a1.

[0153] After processing each region a1 to an, the image analysis unit 93 integrates the processing results of each region a1 to an and ends the data processing. Specifically, the image analysis unit 93 generates data that associates the detected defect level with its occurrence location (xy coordinates) for each region (each position in the width direction of the thin film F8).

[0154] After data processing, the image analysis unit 93 saves the data processing results to the storage unit 94. The image analysis unit 93 performs this data processing on multiple image data obtained by examining a single film roll 80 to acquire processing results. By summarizing these processing results, a result is generated as follows: Figure 7 The first inspection data is shown in Table T11.

[0155] (Step S14)

[0156] The terminal device 70 in the first manufacturing process sends inspection data, which includes information on multiple feature points obtained through processing up to step S13, to the information processing system 50. The acquisition unit 511 of the information processing system 50 saves the acquired inspection data as first inspection data to the inspection data DB in the storage unit 52.

[0157] Figure 7 An example of the inspected data content is shown in the inspection list. Figure 7 The first inspection data shown in Table T11 contains the feature point IDs automatically assigned to each feature point with consecutive numbers, and feature point descriptors 1 and 2 (hereinafter referred to as descriptor 1, etc.) for each feature point ID.

[0158] Descriptor 1 contains independent information about the feature point, recording its XY coordinate position and intensity. The intensity is the feature point's level, as described later. Additionally, as intensity information, it may also include information about the feature point's size (diameter, area) and brightness. The XY coordinate position is based on the starting point of the thin film surface (e.g., the left end of the front end). X is the coordinate in the width direction of the thin film, which can be, for example, in the range of 0 to 3000 mm depending on the thin film size (refer to Table T2). Y is the coordinate in the length direction of the thin film, which can be, for example, in the range of 0 to 10000 m depending on the thin film size. The generation of descriptor 1 is performed by the image analysis unit 93 of the inspection device 90.

[0159] Descriptor 2 represents surrounding information, which is a vector or array representing information such as its relationship with other feature points. For example, SIFT feature values ​​can be used as descriptors, or the probability density function of feature points calculated through kernel density estimation can be used as a descriptor. The generation of descriptor 2 is mainly performed by the comparison unit 512.

[0160] (Generation and processing of the second inspection data)

[0161] Figure 6 This is a flowchart illustrating the process of generating second inspection data during the second manufacturing step.

[0162] (Step S21)

[0163] 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.

[0164] (Step S22)

[0165] The inspection device 90 photographs the surface of the film F8 before post-processing, or during or after post-processing, and saves the image data.

[0166] (Step S23)

[0167] The image analysis unit 93 performs the same process as in step S13, storing the inspection data containing feature point information of the generated multiple feature points in the storage unit 94.

[0168] (Step S24)

[0169] The terminal device 70 in the second manufacturing process sends inspection data containing information on multiple feature points obtained through 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 second inspection data in the inspection data DB of the storage unit 52. Figure 7The second inspection data T12 shown is similar to the first inspection data shown in Table T11, and is described using feature point id and feature point descriptors 1 and 2.

[0170] (Feature point extraction and processing, and registration processing in the inspection data database)

[0171] The following is for reference Figures 8 to 14 This describes the feature point extraction process performed in the information processing system 50 and the registration process to the inspection data DB. Figure 8 This is a flowchart illustrating the feature point extraction process. Figure 9 This is a schematic diagram illustrating the feature point extraction process.

[0172] The information processing system 50 initiates the following steps S31 based on the start instruction from the user on the operation screen of the terminal device 70, or when the second check data is registered in the check data DB of the storage unit 52 and a pair of first check data and second check data are ready.

[0173] (Step S31)

[0174] The acquisition unit 511 retrieves a pair of first and second inspection data from the inspection data DN for the same batch. The same batch is associated with the batch ID assigned to the inspection ID.

[0175] (Steps S32 and S33)

[0176] The comparison unit 512 performs preprocessing under the first condition on the first inspection data and preprocessing under the second condition on the second inspection data.

[0177] like Figure 9 As shown, as a preprocessing step for the second condition, the comparison unit 512 performs the following operations on the second inspection data: if there is a difference between winding (first manufacturing process) and unwinding (second manufacturing process), then in order to match them, a preprocessing step of reversing the Y-coordinate (vertical) is performed. Furthermore, in the second manufacturing process, based on information that the shooting area of ​​the camera 92 is set to the front or back of the film F8, the comparison unit 512 performs a preprocessing step of reversing the X-coordinate (horizontal) on the second inspection data (or the first inspection data).

[0178] In addition, the comparison unit 512 performs at least one of the following processes as noise removal processes included in the first and second conditions for the first inspection data and the second inspection data.

[0179] (1) Remove low-level feature points.

[0180] (2) Remove extremely small feature points.

[0181] (3) Remove continuous dots.

[0182] (4) Remove concentrated dots in the width direction. This is especially common at the beginning or end of the F8 film.

[0183] (Step S34)

[0184] The comparison unit 512 performs comparison processing to search for feature points in another set of inspection data that are the same as or correspond to the feature points existing in one set of inspection data, and performs correspondence association (matching) between the feature points. Figure 10 This is a flowchart showing the subroutine processing in step S34.

[0185] (Step S401)

[0186] The comparison unit 512 generates descriptors 2 for each feature point of the first and second inspection data. The comparison unit 512 may use SIFT feature quantities as descriptors, or use the probability density function of the feature points calculated by performing kernel density estimation as descriptors.

[0187] (Steps S402, S403)

[0188] The comparison unit 512 compares the feature points of the first and second inspection data with each other and searches for 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.

[0189] For example, in comparing feature points of the first and second inspection data, the comparison unit 512 searches for feature points in the first inspection data that correspond to the object feature points of the second inspection data. At this time, the comparison unit 512 determines the feature points of the first inspection data that have the same X and Y coordinates as or have the closest intensity to the feature points of the feature points in the second inspection data as the same point. Alternatively, feature points whose distance (Euclidean distance) between the X and Y coordinates of the descriptors 1 is closest are determined to be the same point (corresponding points). The comparison unit 512 excludes feature points whose distance is greater than a set threshold from the determination of corresponding points. Furthermore, in this embodiment, the threshold in the Y direction is set to be 2 to 3 orders of magnitude larger than the threshold in the X direction. For example, the threshold in the X direction is several millimeters, while the threshold in the Y direction is several meters. The threshold in the Y direction is 2 to 3 orders of magnitude larger than the threshold in the X direction because of its larger variation.

[0190] Furthermore, the comparison unit 512 can also use descriptor 1 and descriptor 2 together to extract the most similar feature points based on the distance between vectors in the high-dimensional vector space. In this case, the comparison unit 512 can use the probability density function calculated by kernel density estimation as descriptor 2. Figure 11An example is shown, illustrating the probability density function representing the location and intensity (density) of a feature point, calculated using kernel density estimation. Figure 11 In the diagram, the vertical axis and the horizontal axis represent the X and Y coordinates, and the higher the color concentration, the greater the density.

[0191] The comparison unit 512 determines that each feature point corresponds to only one feature point. For example, for feature points in the second inspection data, the feature points whose descriptor vectors are closest to each other in the first inspection data are registered in the corresponding point list as corresponding points.

[0192] Figure 12 An example of a corresponding point list stored in storage unit 52 is shown. This corresponding point list corresponds to the most similar feature point in the first inspection data for each feature point in the second inspection data. Furthermore, the corresponding point list records the X and Y coordinates of the feature points in the second inspection data, the Euclidean distance between the corresponding feature points, the difference dx in the X-coordinate direction, and the difference dy in the Y-coordinate direction. This concludes the control unit 51. Figure 10 The process shown returns to Figure 8 The process shown is executed, and step S35 and subsequent steps are performed.

[0193] (Step S35)

[0194] Based on the correspondence list, the first inspection data, and the second inspection data, the extraction unit 513 classifies feature points into three categories: first-class feature points, third-class feature points, and so on. The first-class to third-class feature points will be described in detail later. Specifically, the extraction unit 513 classifies feature points in the second inspection data that do not have a corresponding relationship with feature points in the first inspection data into second-class feature points in the correspondence list. 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 have a corresponding relationship with feature points in the second inspection data) into first-class feature points.

[0195] (Feature points of types 1 to 3)

[0196] Figure 13 This is a table used to illustrate the first to third categories of feature points.

[0197] (First type of feature point)

[0198] The first type of feature point is a feature point that exists in the first inspection data but not in the second inspection data. This type of feature point disappears in the second manufacturing process (e.g., coating process, lamination process). This first type of feature point is a feature point that does not require management in the first manufacturing process. In this case, the manufacturing conditions that lead to the generation of the first type of feature point become the object of standard relaxation in the first manufacturing process.

[0199] (Second type of feature point)

[0200] 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. This second type of feature point is a newly generated feature point in the second manufacturing process. Since this second type of feature point originates from the second manufacturing process, it can be used to improve the second manufacturing process.

[0201] (Third type of feature point)

[0202] The third type of feature points exists in both the first inspection data and the second inspection data. These third type of feature points originate from the first manufacturing process and are therefore subject to management. Since these third type of feature points are caused by the first manufacturing process, they can be used to improve the first manufacturing process.

[0203] (Step S36)

[0204] The control unit 51 registers the feature point extraction information extracted through the processing up to step S35 into the inspection data DB (end).

[0205] Figure 14 An example of extracted data is shown. The extracted data records the inspection IDs of the first and second inspection data as sources, as well as the extraction results for each feature point. The extraction results (classes one to three) are... Figure 13 The classification is shown. The merged feature point ID is an automatically assigned sequentially numbered identifier, corresponding to feature points present in one or both of the first and second inspection data, generating merged feature points. The number of merged feature point IDs is greater than or equal to the number of feature point IDs in the first and second inspection data.

[0206] It should be noted that for a single batch ID, multiple inspection devices may sometimes generate multiple first inspection data and second inspection data. For example, in a second manufacturing process, the originally wound film roll 80 is inspected (photographed), and inspections are also performed in several downstream processes, thereby generating multiple second inspection data. In this case, the information processing system 50 can generate multiple feature point extraction data (one-to-many) between a 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 select which inspection data to establish a correspondence with.

[0207] (Analysis and handling of defect occurrence)

[0208] Figure 15 It is a flowchart showing the analysis process that analyzes and displays the occurrence of defects between batches or within inspection intervals. Figure 16A , Figure 16B This is an example of an operation screen displayed on a terminal device 70, etc.

[0209] (Step S51)

[0210] Selection section 514 accepts the user's selection of object data. For example, in Figure 16A In the operation screen 701 shown, when the batch list is selected in area b0 (see...), Figure 4 After the product is inspected, in area b1, the selection of (1) multiple batches or (2) multiple inspection intervals within a single batch is accepted. Multiple batches will be described later. Multiple inspection intervals refer to, for example, in the case of a 3000m film, selecting multiple inspection intervals divided into 500m or 1000m sections along the length direction. Alternatively, selecting multiple inspection intervals divided into 500mm sections along the transverse direction. Then, a comparison of feature points for each of the multiple divisions is performed. In this case, the entire length can also be displayed as a comparison. For example, the total number of feature points in the entire length direction divided by the number of divisions (average) can also be used as a comparison object.

[0211] Figure 16B The operation screen 702 shown is in Figure 16A In the response area b1, multiple batches of buttons are pressed, resulting in the displayed screen. In area b11 of operation screen 702, batches associated with the selected product are displayed in a list. The user enables selection of each batch via button b12. In the example of operation screen 702, batches 1 through 5 are shown to be selected. The user confirms the selection by pressing the OK button b13. Furthermore, when the manufacturing process spans multiple processes, selection of the manufacturing process being targeted within a batch can also be received.

[0212] (Step S52)

[0213] The acquisition unit 511 retrieves the extracted data corresponding to the conditions selected in step S51 from the inspection data DB. Figure 17 This is an example of the extracted data list obtained in step S52. The following explanation is based on the premise that batches 1 to 5 have undergone processing and manufacturing through three consecutive manufacturing processes 1 to 3, and that extracted data between each process has been obtained. For example, in Figure 17 In the example shown, for batch 1, two extracted data points, extracted data 01 and extracted data 02, were entered. Extracted data 01 corresponds to... Figure 14 The extracted data is shown.

[0214] (Step S53)

[0215] The selection unit 514 accepts the user's selection of the type of feature points. Regarding this selection, the user can choose the type of feature points by selecting some options in area b2 of the operation screen 701. In the example of the operation screen 701, the second and third types of feature points are shown as selected. Furthermore, this selection can also be performed automatically by the control unit 51. For example, in area b2, the user can select the "Auto" button, which can also be performed automatically by the control unit 51.

[0216] (Steps S54 and S55)

[0217] The display data generation unit 515 analyzes the feature point data according to the conditions selected in steps S52 and S53, and generates display data. Hereinafter, refer to... Figures 18A to 18C The analysis and processing of feature point data are explained.

[0218] Figure 18A , Figure 18B This is a table displaying the analysis results. Figure 18A In the selected batches 1 to 5, the analysis results of batch 1 are shown as representative. Figure 18B It is used for explanation Figure 18A A table showing the extraction criteria for feature points. (Example) Figure 18A As shown in extraction condition 1, the feature points (defects) generated in process 1 are extracted using extraction data 01 generated from the inspection data of processes 1 and 2 (refer to...). Figure 17 The third type of feature points exists in the data. Furthermore, the feature points generated in step 2 use the second type of feature points existing in the same extracted data 01. The feature points generated in step 3 use the second type of feature points existing in extracted data 02 generated using the inspection data from steps 2 and 3. Step Total uses all feature points extracted using the separate inspection data (inspection data i03) from step 3. In this case, the second type of feature points spanning more than three steps are considered as newly generated feature points. Specifically, as shown in condition 1, the second type of feature points used in step 3 are those classified by comparing the inspection data from step 3 with the inspection data from the previous step 2.

[0219] As a variation, it can also replace Figure 18B Extraction condition 1 is shown, and extraction condition 2 is applied. In extraction condition 2, condition a and condition b are applied using a logical AND condition. For example, feature points generated in process 1 are third-class feature points, excluding first-class feature points. Furthermore, feature points generated in process 2 are third-class feature points between processes 2 and 3, and second-class feature points between processes 1 and 2. Extraction condition 1 is applied in the following example.

[0220] In addition, Figure 18AThe feature points are divided into five levels, from size 1 to size 5, based on their size (area), and the number of feature points for each size is shown. Size 1 is the smallest level, and size 5 is the largest level. The following uses the sum of these sizes, i.e., the total size, but values ​​summed for each size level can also be used based on user input.

[0221] exist Figure 18C The table displays a list of the number of feature points generated in each process for each batch. By performing this analysis, the display data generation unit 515 generates display data. Then, the output unit 516 outputs the generated display data. For example, in area b4 of the operation screen 701 of the terminal device 70 (refer to...) Figure 16A As shown in ) Figure 19A The data shown is as indicated.

[0222] The displayed data can be, for example, Figure 18C The table data shown can also be in the format shown. Figure 18B The charts shown can be bar charts, line charts, scatter plots, or stacked bar charts generated from tabular data. Additionally, Venn diagrams can also be used. For example, for each batch, the degree of overlap between feature points moving through three or more processes can be displayed. Figures 19A to 19E Here is an example of displaying data using this type of graph.

[0223] Figures 19A to 19D Based on Figure 18C Charts generated from tabular data. Figures 19A to 19C For scatter plot, Figure 19D , Figure 19E This is an example of a stacked column chart. Figure 19A The table shows the number of feature points in process Total for batches 1 to 5. Figure 19B The table shows the number of feature points generated in process 3 for batches 1 to 5. (Example) Figure 18B As shown in condition 1, the feature points presented here are of the second type. Figure 19C The table shows the number of feature points generated in process 1 for batches 1 to 5. For example... Figure 18B As shown in condition 1, the feature points presented here are of the third type. Figure 19D The table shows the number of feature points in process Total for batches 1 to 5. Within each column, the table shows the number of feature quantities generated in each of processes 1 to 3. For example... Figure 18B As shown in condition 1, the types of feature quantities presented here are third-type feature points and second-type feature points. Figure 19E The table shows the number of feature points for process Total in batches 1 to 5, and in each column, the number of feature quantities for each of dimensions 1 to 5 is shown in a stacked manner.

[0224] The following effects can be achieved through the methods described above. Figure 19A As can be seen from the data, batches 4 and 5 show an increase in the number of feature points in process 3 compared to batches 1 to 3. This can be compared with reference data. Figure 19B Figure 20C or reference Figure 19D It can be interpreted that the increase in feature points in process 3 (Total) is not due to process 3 itself, but rather to process 1.

[0225] Thus, the information processing system of this embodiment includes an acquisition unit that acquires data from a database. The database, based on first inspection data from a first manufacturing process involving the manufacture of rolled materials or post-processing of already manufactured rolled materials, and second inspection data from a second manufacturing process involving post-processing of rolled materials after the first manufacturing process, classifies feature points contained in both the first and second inspection data into three categories: first-category feature points present in the first inspection data but absent in the second inspection data; second-category feature points absent in the first inspection data but present in the second inspection data; and third-category feature points present in both the first and second inspection data, and records these categories. Furthermore, the information processing system also includes a selection unit that accepts selections for multiple batches of a target or multiple inspection intervals along the length direction of rolled materials within a batch; a display data generation unit that generates display data based on data acquired from the database by the acquisition unit and selected by the selection unit; and an output unit that outputs the display data. With this configuration, the occurrence of defects in both the manufacture of rolled materials such as films and the manufacturing processes involving post-processing of these rolled materials can be monitored. In particular, in the information processing system of this embodiment, the selection unit further accepts the selection of the types of feature points to be classified, and the display data generation unit generates display data using the data on the types of feature points accepted. Thus, the generation status of feature points in each process of a batch can be monitored separately. When manufacturing products through multiple processes, it is possible to identify in which processes changes occur, thereby preventing or anticipating process failures.

[0226] The above description of the information processing system 50 is a summary of its main components to illustrate the features of this embodiment, and is not limited to the above configuration. Various modifications can be made within the scope of the claims. Furthermore, this application does not exclude the configurations found in general information processing apparatuses / systems.

[0227] (Variation Example 1)

[0228] For example, in the above example of displaying data, an example is shown that displays the data in a way that allows for the understanding of changes in conditions across multiple batches. In a variation, unlike the batch-to-batch scenario, when the user selects an inspection interval within a single batch ( Figure 16A The display data generation unit 515 generates display data in a manner that allows it to grasp the changes in conditions between intervals within a batch (region b1). For example, when the length of a batch of film is 3000m, it is divided into three intervals: 0-1000m, 1000-2000m, and 2000-3000m. Then, the display data generation unit 515 generates display data for each interval. Figures 19A-19E The same display data. At this time, the inspection data is segmented according to a specified interval, and extracted data is generated for each segmented inspection data. Then, the display data generation unit 515 generates display data by analyzing the extracted data corresponding to these segmented intervals. Even in this modified example, it is possible to obtain the same display data as... Figures 1 to 17 The same effect is achieved in this embodiment. For example, it is possible to grasp the generation status of feature points (defects) corresponding to time changes within a batch.

[0229] (Variation Example 2)

[0230] exist Figure 16A The example shown illustrates that the user can select the type of feature quantity on a per-type basis, but it could also be configured to select the type per-process. For example, as... Figure 18B As shown in condition 1, the selection of the third or second type can be accepted for each process. Furthermore, as shown in condition 2, multiple types of selections can also be accepted for each process in relation to preceding and following processes. For example, as shown in the table of condition 2, in process 2, when the user selects the second type of feature point in relation to the preceding process (between processes 1 and 2) and the third type of feature point in relation to the following process (processes 2 and 3), the selection is accepted using the AND condition. Alternatively, the user can select the desired type of graphic instead of choosing the type of feature point, and the control unit 51 can automatically select the type of feature point. For example, when visually displaying the status of newly generated feature points in each process, the control unit 51 can automatically set the type of feature point by accepting the user's selection of "defects generated in each process". Figure 18B The types of feature points shown in condition 1 or condition 2.

[0231] (Variation Example 3)

[0232] Alternatively, the above can be executed in real time. Figure 15This involves a series of processes. For example, inspection data acquired in each process is processed in real time and displayed according to pre-set conditions. Additionally, alarms can be output based on the number of newly generated second-type feature points. Specifically, when the number of newly generated second-type feature points exceeds a threshold, an alarm is notified to the process with the set target (e.g., the generation process or any processes before or after it). As a result, faults can be quickly identified and improved, supporting improvement efforts.

[0233] (Variation Example 4)

[0234] Alternatively, the information processing system 50 may also include an inspection device 90 configured in the first manufacturing process and / or the second manufacturing process. Furthermore, the control unit 51 of the information processing system 50 may also perform the feature point generation function of the image analysis unit 93 of the inspection device 90. In this case, the inspection device 90 sends image data obtained from photographing the film surface and its shooting 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.

[0235] Furthermore, the various processing means and methods in the information processing system 50 that performs the above-described embodiments can all be implemented by a dedicated hardware circuit 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 Multifunction Optical Disc)-ROM, or online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is typically transferred and stored in a storage unit such as a hard disk. Moreover, the aforementioned program can be provided as standalone application software, or it can be embedded in the software of the device as a function of the device.

[0236] Although embodiments of the present invention have been described in detail and illustrated, the disclosed embodiments are for illustrative and exemplary purposes only and are not intended to be limiting. The scope of the invention should be interpreted in accordance with the text of the appended claims.

[0237] This application is based on Japanese Patent Application No. 2024-064474, filed on April 12, 2024, the disclosure of which is incorporated herein by reference in its entirety.

[0238] Explanation of reference numerals in the attached figures

[0239] 50: Information processing system; 51: Control unit; 511: Acquisition unit; 512: Comparison unit; 513: Extraction unit; 514: Selection unit; 515: Display data generation unit; 516: Output unit; 52: Storage unit; 90, 90a1~90a2, 90b1~b4: Inspection device; 91: Illumination; 92: Camera; 1000: Thin film roll manufacturing device; 2000: Product manufacturing device.

Claims

1. An information processing system, comprising: The acquisition unit acquires data from a database. The database is based on first inspection data from a first manufacturing process that manufactures or processes manufactured rolls, and second inspection data from a second manufacturing process that processes the rolls after the first manufacturing process. The database classifies feature points contained in the first inspection data and the second inspection data into three categories: first type feature points that exist in the first inspection data but not in the second inspection data; second type feature points that do not exist in the first inspection data but exist in the second inspection data; and third type feature points that exist in both the first inspection data and the second inspection data. The database is then recorded. The selection department allows for the selection of multiple batches of accepted items or multiple inspection intervals along the length of rolls within a single batch. The display data generation unit generates display data based on the data obtained from the database by the acquisition unit and selected by the selection unit; as well as The output unit outputs the displayed data.

2. The information processing system according to claim 1, wherein, The selection unit also handles the selection of the types of the classified feature points. The display data generation unit generates the display data based on the data of the types of feature points received.

3. The information processing system according to claim 1, wherein, The displayed data includes charts comparing feature points generated in multiple batches of manufacturing processes.

4. The information processing system according to claim 3, wherein, The chart is a comparison of second-type feature points generated in subsequent manufacturing processes across multiple batches.

5. The information processing system according to claim 3, wherein, The charts include at least one of the following: bar chart, line chart, scatter plot, and stacked bar chart.

6. A control method, wherein, Perform a process that includes the following steps: Step (a): Obtain data from the database, which is based on the first inspection data in the first manufacturing process of manufacturing rolls or post-processing the manufactured rolls and the second inspection data in the second manufacturing process of post-processing the rolls after the first manufacturing process. The database classifies the feature points contained in the first inspection data and the second inspection data into a first type of feature points that exist in the first inspection data but do not exist in the second inspection data, a second type of feature points that do not exist in the first inspection data but exist in the second inspection data, and a third type of feature points that exist in both the first inspection data and the second inspection data, and records them. Step (b): Selecting multiple batches of the accepted items or selecting multiple inspection intervals along the length of the roll material in a batch; Step (c): Based on the data obtained from the database in step (a) and selected in step (b), generate display data; as well as Step (d): Output the displayed data.

7. The control method according to claim 6, wherein, In step (b), the selection of the types of the classified feature points is also accepted. In step (c), the display data is generated based on the data of the types of feature points accepted.

8. The control method according to claim 6, wherein, The displayed data includes charts comparing feature points generated in multiple batches of manufacturing processes.

9. The control method according to claim 8, wherein, The chart is a comparison of second-type feature points generated in subsequent manufacturing processes across multiple batches.

10. The control method according to claim 8, wherein, The charts include at least one of the following: bar chart, line chart, scatter plot, and stacked bar chart.

11. A control program for causing a computer to execute the control method according to any one of claims 6 to 10.

Images