TW202405411A - Defect occurrence tendency analysis method - Google Patents

Abstract

[Problem] The present invention provides a defect occurrence tendency analysis method that can fully identify the causes of defects in sheet-like products and can sufficiently contribute to improving the yield of sheet-like products. [Solution] The present invention is a method for analyzing the tendencies related to the occurrence of defects based on defects generated in a plurality of sheet products S2 manufactured by cutting the long original sheet S1. The present invention includes: step ST11, The original sheet S1 before cutting is marked with a position information mark so that the position information mark M indicating the position information in the longitudinal direction and the width direction of the original sheet exists in each of the plurality of sheet products; step ST12, check Sheet-like product; reading step ST13, reading the position information mark marked on the sheet-like product, thereby obtaining the position information of the sheet-like product in the original piece; and step ST14, identifying the defect existing in the sheet-like product in the original piece location information, and based on this specific location information, tendencies related to the occurrence of defects are analyzed.

Description

Defect occurrence tendency analysis method

The present invention relates to a method for analyzing the occurrence tendency of defects, which analyzes the tendency related to the occurrence of defects based on the defects produced in a plurality of sheet-like products such as polarizing films and retardation films. The aforementioned sheet-like products are: The long raw sheet wound into a roll is successively fed out, transported and cut to produce, or the long raw sheet wound into a roll is continuously fed out, transported and cut into a large sheet-like intermediate product, and then cut. It is produced by cutting the aforementioned intermediate. In particular, the present invention relates to a defect occurrence tendency analysis method that can fully identify the causes of defects in sheet-like products and can fully contribute to improving the yield of sheet-like products.

Conventionally, for sheet-like products such as polarizing films and retardation films, long original films wound into a roll were continuously fed out, transported and cut, or long original films rolled into a roll were continuously fed out, transported and cut. A large sheet-like intermediate body is cut out, and then the intermediate body is cut to produce a plurality of sheet-like products. Then, each manufactured sheet-like product is bonded to an optical display unit such as a liquid crystal panel, thereby manufacturing an optical display device such as a liquid crystal display device.

Here, it can be considered that if it can be known where the sheet-like product after being bonded to the optical display unit is originally on the original sheet before cutting or the original sheet before cutting out the intermediate body, then to some extent This can identify the cause of defects in sheet products and help improve the yield of sheet products. Therefore, for example, Patent Document 1 proposes a method of marking an original film before cutting with a mark indicating positional information in the original film. Specifically, Patent Document 1 proposes a method of marking an original sheet (a roll original sheet in Patent Document 1) before cutting it into a sheet-like product (an optical film in Patent Document 1) (in Patent Document 1, it is proposed 1 is a method of holding a roll information holding mechanism, and the aforementioned symbols represent the position information of the sheet-like product in the longitudinal direction of the original sheet (in Patent Document 1, it is roll information) (for example, refer to paragraphs 0131 to 0133 of Patent Document 1, etc. ). According to the method described in Patent Document 1, it is considered that the cause of an abnormality in a sheet-like product can be identified to some extent, or that it can contribute to improving the yield of the sheet-like product.

However, in the method described in Patent Document 1, since the position information represented by the mark on the sheet product is only the position information in the longitudinal direction of the original sheet (paragraph 0131 of Patent Document 1), there is a problem. There is a problem that insufficiently identifying the causes of defects cannot sufficiently contribute to improving the yield of sheet products. In addition, when the position information represented by the mark on the sheet product is not only the position information in the length direction of the original piece, but also the position information in the width direction of the original piece, how to use the position information To help identify the causes of defects, there has been no proposal in the past. Prior technical literature patent documents

Patent Document 1: Japanese Patent Application Publication No. 2009-294645

The problem to be solved by the invention

The present invention was made to solve the above-mentioned problems of the conventional technology. The object of the present invention is to provide a defect occurrence tendency analysis method that can fully identify the causes of defects in sheet-like products and can fully assist Improve the yield rate of sheet products. means to solve problems

In order to solve the above-mentioned problems, the present invention provides a method for analyzing the tendency of defect occurrence, which analyzes the tendency related to the occurrence of defects based on the defects that occur in a plurality of sheet-like products. The above-mentioned sheet-like products are: rolled into The long raw sheet rolled into a roll is successively fed out, transported and cut to produce, or the long raw sheet rolled into a roll is fed out one after another, transported and cut into a large sheet-like intermediate body, and the intermediate body is cut. To manufacture, the method for analyzing the occurrence tendency of the aforementioned defects includes: a position information marking step, in which the original sheet, the intermediate body, or a plurality of the sheet-like products before cutting or cutting out the intermediate body are marked with position information marks. , so that the mark indicating the position information in the longitudinal direction and the width direction of the original sheet, that is, the aforementioned position information mark, exists in each of the plurality of aforementioned sheet-like products; the sheet-like product inspection step inspects the plurality of aforementioned sheet-like products. ; Reading step, reading the aforementioned position information mark of the aforementioned sheet-like product whose defect has been detected in the aforementioned sheet-like product inspection step, thereby obtaining the aforementioned position information of the aforementioned sheet-like product in the aforementioned original piece; and the analyzing step , based on the position information of the sheet-like product in the original piece obtained in the reading step, specify the position of the defect in the sheet-like product that has been detected in the sheet-like product inspection step in the original piece. The information is used to analyze the tendency related to the occurrence of the defect based on the position information of the specified defect existing in the sheet-like product in the original sheet.

According to the present invention, in the position information marking step, position information marks are marked on a plurality of sheet-like products so that position information marks, which are marks representing position information in the longitudinal direction and width direction of the original sheet, exist on the plurality of sheets. shape of each product. Therefore, in the reading step, the position information mark marked on each sheet-like product can be read, thereby obtaining the position information (position information in the longitudinal direction and width direction) of each sheet-like product in the original sheet. Furthermore, in the analyzing step, the location information of the defects in the sheet products detected in the sheet product inspection step in the original sheet can be specified based on the position information of each sheet product in the original sheet obtained in the reading step. For example, when the position information of the defect existing in each sheet-like product based on each sheet-like product is unknown, the center position of each sheet-like product can be specified as the position of the defect existing in each sheet-like product in the original sheet. Location information. In addition, when the position information of the defects existing in each sheet product based on each sheet product is known, the position information of each sheet product on the original sheet obtained in the reading step and the position information of each sheet can be The position information of the defects existing in each sheet-like product is used as a reference to specify the position information of the defects existing in each sheet-like product in the original piece. Therefore, in the analysis step, the tendency related to defect generation can be analyzed based on the position information of the specified defect existing in the sheet product in the original sheet (position information in the longitudinal direction and width direction). Therefore, it is possible to fully identify the causes of defects in sheet-like products, and to fully contribute to improving the yield of sheet-like products.

In addition, the "position information in the longitudinal direction and the width direction of the original film" represented by the position information notation of the present invention means that it includes at least the longitudinal direction (transportation direction) of the original film and the width direction orthogonal thereto. Location information. The position in the longitudinal direction of the original film can also be expressed as the distance from the front end (downstream end in the conveying direction) of the original film in the longitudinal direction (conveying direction), or it can be expressed as the distance from the longitudinal direction (conveying direction) of the original film The distance from the front end is expressed as a number with consecutive numbers. The location information token may also represent information about the original film that is used to mutually identify multiple original films. In addition, the location information mark may also indicate other incidental information. In addition, in the present invention, the position information mark can also be marked using general colored ink or transparent ink, or can be marked by laser marking. Transparent ink is an ink that cannot be visually recognized by human eyes under normal lighting. It fluoresces by irradiating light of a specific wavelength and becomes visible. An example of the transparent ink is UV ink that fluoresces when irradiated with ultraviolet rays. If transparent ink is used to mark position information marks, the position information marks will become invisible under normal lighting, which has the advantage of not damaging the appearance of the sheet product. One-dimensional code (barcode) or two-dimensional code can be exemplified as the location information mark. DataMatrix (registered trademark) or QR code (registered trademark) can be exemplified as the two-dimensional code. In addition, when the sheet-like product has a layer such as a protective film that can be removed during use (that is, a layer that is not affected when the sheet-like product is used), it is preferable that the position information mark is marked on this layer. In addition, the "tendency related to the occurrence of defects" in the present invention means, in addition to the tendency of defect occurrence (production mode) itself, it also means that although a defect is detected in a sheet-like product, it is difficult to detect the defect in the original sheet. Trend, tendency of the manufacturing process history information of the original sheet in which defects are easily detected in sheet products, tendency of the type of sheet product (type of original sheet) in which defects are easily detected, tendency of defects being easily detected when inspecting the original sheet Tendencies in inspection methods or inspection conditions are widely related to the occurrence of defects.

The present invention takes into consideration the case where the inspection results of the original sheet are not used (the case where only the inspection results of the sheet-like product are used), and the case where the inspection results of the original sheet are used (both the inspection results of the sheet-like product and the inspection results of the original sheet are used) situation). In the case where the present invention does not use the inspection results of the original film, it is preferable that the aforementioned analysis step includes: a map image generation program, based on the aforementioned position information of the aforementioned specified defect existing in the sheet-like product in the aforementioned original film , generate a map image, where the map image is an image depicting the position of the defect existing in the sheet-like product in the original sheet; and a matching image generation program that combines the map image with a template image prepared in advance Pattern matching is performed to generate a matching image as an image representing a tendency related to the occurrence of defects. The matching image is a drawing in which only the positions of the defects drawn on the map image and the The template image matches the image of the location of the aforementioned defect.

In the above-described ideal method, "generating a map image" is not limited to the state of actually displaying the map image on a display device such as a screen, but includes specifying the position of the defect in the original image (the long side of the original image). direction and width direction), and the map image is set to a displayable state. According to the above-mentioned preferred method, in the map image generation program of the analysis step, a map image is generated which depicts the position of the defect existing in the sheet product in the original sheet. In the matching image In the generation program, a matching image is generated, which is an image depicting only the positions of defects that match the template image among the positions of defects drawn on the map image. Therefore, for example, by visually recognizing the matching image, the tendency related to the occurrence of defects detected for the sheet product (the tendency of defect occurrence (production pattern)) can be grasped. In addition, as the "template image", for example, an image in which pixels are drawn at a certain period in the longitudinal direction in accordance with the period (outer circumference) of the nip roller that transports the original film is prepared to reflect the information to be extracted from the map image. A typical image is sufficient.

In the case where the present invention utilizes the inspection results of the original piece, it is more desirable to have: an original piece inspection step to inspect the original piece before cutting or cutting out the intermediate; and a correlation step to combine the original piece with the original piece. The aforementioned position information of the defects existing in the aforementioned original piece before cutting or cutting out the aforementioned intermediate body that have been detected in the piece inspection step, the types of defects existing in the aforementioned original piece, and the detected defects existing in the aforementioned original piece The execution place of the aforementioned original film inspection step is associated with the aforementioned position information mark and is memorized. The aforementioned analysis step includes: combining a specific program to determine the aforementioned position of the aforementioned specified defect existing in the aforementioned sheet-like product in the aforementioned original film. information, and whether the aforementioned position information of the defect existing in the original film that is associated with the aforementioned position information mark read by the aforementioned reading step and memorized is consistent. If they are consistent, the information read by the aforementioned reading step is specified The combination of the type of defect existing in the aforementioned original film and the execution place of the aforementioned original film inspection step that detects the defect existing in the aforementioned original film is associated and memorized with the aforementioned position information mark; the extraction condition determination program is based on the aforementioned The extraction conditions are determined by combining the combination of the aforementioned types specified by the specific program and the aforementioned execution place; the map image generation program, among all the defects present in the aforementioned original film detected in the aforementioned original film inspection step, is based on the aforementioned extraction conditions. The condition determination program determines the location information of the defect of the extraction condition in the original film, and generates an image depicting the location of the defect in the original film, that is, a map image; and the matching image generation program generates the map image The image is pattern-matched with a template image prepared in advance to generate a matching image as an image representing a tendency related to the occurrence of defects. The matching image is only drawn on the map image. The image of the location of the aforementioned defect that matches the aforementioned template image among the locations of the aforementioned defect.

In the above-mentioned preferred method, the original film inspection step of inspecting the original film is not limited to being performed at a single place in the manufacturing process of the original film, but can also be performed at a plurality of places. According to the above-mentioned ideal method, in the correlation step, the position information of the defect existing in the original film detected by the original film inspection step, the type of defect existing in the original film, and the source of the defect detected in the original film The execution place of the film inspection step will be associated with the location information mark and remembered. Specifically, for example, the position information mark of the mark on the sheet-like product that is the same as the sheet-like product in which the defect detected in the original sheet inspection step is located is associated and memorized. Furthermore, in the combined specifying process of the analysis step, the position information of the defect existing in the sheet-like product specified in the original piece as mentioned above is determined (that is, based on the position information of the sheet-like product in the original piece obtained in the reading step). The position information of a specific defect existing in the sheet product in the original piece (hereinafter referred to as "position information A" appropriately) is associated with the position information mark read in the reading step and the memory exists in the original piece. Whether the position information of the defect of the piece (that is, the position information of the defect existing in the original piece detected by the original piece inspection step, hereinafter appropriately referred to as "position information B") is consistent. Here, the concept that position information A and position information B are consistent is not limited to the position in the length direction and width direction of the original film contained in position information A, and the position in the length direction of the original film contained in position information B. When the positions in the width direction are exactly the same, it also includes the predetermined nearby area for the long side and width direction positions of the original film included in the position information A, and the long side of the original film included in the position information B. direction and position in the width direction. Furthermore, in the combination specific program, when position information A and position information B match (in other words, there is a defect in the original sheet detected in the original sheet inspection step at the same position as the defect detected in the sheet product) (that is, it can be considered that the same defect is detected in both the sheet product and the original piece), the specific position information mark read in the reading step is associated and the memory exists in the original piece. The combination of the type of defect and the execution location of the original film inspection step that detects the defect existing in the original film. In addition, when there is a plurality of position information B (that is, there are a plurality of position information of defects existing in the original film that are associated with the position information mark read in the reading step and memorized), for example, It only needs to be determined whether the position information B of the defect with the largest area is consistent with the position information A. In the extraction condition determination program of the analysis step, the extraction conditions are determined based on the combination of the specific type and execution location of the specific program. Then, in the map image generation program, among all the defects detected in the original image in the original image inspection step, a map image is generated based on the position information of the defects in the original image that meets the extraction conditions determined by the extraction condition determination program. The image of the location of the defect in the original film is the map image. In other words, in the map image generation program of the above-mentioned preferred method, a map image is generated in which only defects detected among all defects present in the original sheet and for the sheet-like product (for those corresponding to The defects detected in the original film) become the positions of the defects in the original film under the same conditions (the combination of the type of defect and the execution place of the original film inspection step). Therefore, for example, the matching image generated from the map image by the matching image generation program can be visually recognized, thereby grasping the tendency (the occurrence (generation type) of the defect) related to the occurrence of defects that may be detected in the sheet product. Such) tendencies).

In the above-mentioned preferred method, when the sheet-shaped product inspection step detects a large number of sheet-shaped products with defects, for example, it is preferred that in the aforementioned combination specific procedure, the sheet-shaped products are inspected for defects in the sheet-shaped products. For each of the plurality of sheet-like products for which defects are detected in the product inspection step, a plurality of combinations of the aforementioned types and the aforementioned execution locations are specified, and in the aforementioned extraction condition determination program, a plurality of combinations specified by the aforementioned combination specifying program are A majority combination among the combinations of the aforementioned types and the aforementioned execution places is determined as the aforementioned extraction condition. As described above, a majority combination among a plurality of specified combinations of types and execution locations is determined as the extraction condition, whereby even if the sheet product inspection step detects a large number of sheet products with defects, and Even if the number of defects detected in the original film inspection step is large, it is still expected to grasp the tendency to generate a map image and matching image depicting the positions of an appropriate number of defects, and to appropriately grasp and target the sheet products. The tendencies associated with the generation of defects that are most likely to be detected. In addition, when the number of sheet-like products for which defects are detected in the sheet-like product inspection step is large, the decision may be made taking into account the calculation load of the analysis step. For example, the number of sheet-like products may be 50 or more, or 100 or more. situation. In addition, the unit period for judging whether the number of plural sheet-like products is large (in other words, the unit period for determining more than half of the combinations as the extraction conditions) can be, for example, one day as a unit or one week as a unit.

On the other hand, in the above-mentioned preferred method, when the number of the plurality of sheet-like products with defects detected in the sheet-like product inspection step is small, for example, it is also possible to target the defects in the aforementioned sheet-like products in the aforementioned combination specific program. For each of the plurality of sheet products for which defects are detected in the product inspection step, a plurality of combinations of the aforementioned types and the aforementioned execution locations are specified, and in the aforementioned extraction condition determination program, a plurality of the plurality of sheet-like products specified in the aforementioned combination specifying program are specified. All combinations of the aforementioned types and the aforementioned execution locations are determined as the aforementioned extraction conditions. Since the number of sheet products whose defects are detected in the sheet product inspection step is small, it is considered that the number of combinations of the plurality of types and execution locations specified by the specific procedure will also be small. Therefore, as described above, even if all combinations of the specified plurality of types and execution locations are determined as extraction conditions, it is expected that the tendency can be grasped to generate a map image and a matching image depicting the positions of an appropriate number of defects, and Appropriately grasp the tendencies related to the occurrence of defects that are most likely to be detected in sheet products.

Furthermore, in the above-mentioned preferred method, there are many cases where the defects detected in the sheet product inspection step are not detected in the original product inspection step (in other words, the defects detected in the sheet product inspection step are also not detected in the original product inspection step). If there are few cases detected in the film inspection step), it may be considered to output this situation as a tendency related to the occurrence of defects without generating a map image or a matching image. That is, in the above-mentioned preferable method, for example, it is preferable that in the above-mentioned combination specifying program, a plurality of defects are specified for each of the plurality of sheet-like products whose defects are detected in the above-mentioned sheet-like product inspection step. combinations of the aforementioned types and the aforementioned execution places, the aforementioned analysis step has an indicator output program, and the aforementioned indicator output program is when the number of combinations of the plurality of the aforementioned types and the aforementioned execution places specified in the aforementioned combination specific program is smaller than the number of the aforementioned plurality of combinations. When the sheet product contains more than half of the total number of defects detected in the sheet product inspection step, the extraction condition determination program, the map image generation program, and the matching image generation program are not executed. In the case of less than half (that is, the defects detected in the sheet product inspection step are also rarely detected in the original film inspection step), it is output as an index indicating a tendency related to the occurrence of defects. As described above, the extraction condition determination program, the map image generation program, and the matching image generation program are not executed. Instead, the index output program combines the number of combinations of plural types and execution locations specified by the specific program (in other words , can be considered as a situation where the number of the same defects detected in both sheet products and original sheets) is less than a majority of the total number of defects detected in a plurality of sheet products, as one of the trends related to the occurrence of defects. By outputting indicators, it is possible to reliably grasp the situation where a defect is detected in a sheet product but cannot be detected in the original film without needlessly generating a map image or matching image, and it is helpful to The reason is found out.

In addition, when the present invention uses the inspection results of the original piece, it is more desirable to further include: an original piece inspection step to inspect the original piece before cutting or cutting out the aforementioned intermediate body; and a correlation step to establish the original piece. The aforementioned location information of the defects in the original piece that have been detected in the aforementioned original piece inspection step before cutting or cutting out the aforementioned intermediate body, the types of defects that exist in the aforementioned original piece, and the detected defects that exist in the aforementioned original piece. The execution place of the original piece inspection step of the defect and the manufacturing step history information of the aforementioned original piece are associated with the aforementioned position information mark to be memorized. The aforementioned analysis step includes: combining a specific program and determining that the aforementioned specified item exists in the aforementioned piece. Whether the aforementioned position information of the defect of the product in the aforementioned original film and the aforementioned position information of the defect existing in the aforementioned original film associated with the aforementioned position information mark read in the aforementioned reading step are consistent. If they are consistent, Next, specify the type of defect existing in the original film that is associated with the position information mark read in the reading step and memorize it, and the execution place of the original film inspection step that detects the defect existing in the original film. , and the combination of the manufacturing step process information of the aforementioned original film; the extraction condition determination program determines the extraction conditions based on the combination of the aforementioned type and the aforementioned execution place specified by the aforementioned combination specific program; and the indicator output program determines the extraction condition after the aforementioned original film inspection Among all the defects that have been detected in the above-mentioned original piece, the aforementioned manufacturing step process information specified in the above-mentioned combination specific step of the above-mentioned original piece will be consistent with the extraction conditions determined by the aforementioned extraction condition determination procedure. , is output as an index indicating the tendency related to the occurrence of defects.

According to the above-mentioned ideal method, different from the above-mentioned ideal method, in the correlation step, in addition to the position information of the defects existing in the original film detected in the original film inspection step, the type of defects existing in the original film, and the detection In addition to the execution place of the original film inspection step for defects that exist in the original film, the original film's manufacturing step process information and position information marks are associated and memorized. Furthermore, unlike the above-mentioned more ideal method, in the combination specifying program of the analysis steps, the type of defect existing in the original film, the execution place of the original film inspection step that detects the defect existing in the original film, and the original film are specified. A combination of manufacturing step process information. Furthermore, in the extraction condition determination program, the extraction conditions are determined based on the specified combination of type and execution location. In the index output program, among all the defects present in the original film, the defects that meet the extraction conditions are determined. The specified manufacturing step history information of the original film is output as an index indicating the tendency related to the occurrence of defects. Therefore, according to the above-mentioned preferable method, it is expected that the tendency of appropriately grasping the manufacturing step history information of the original sheet in which defects may be detected in the sheet-like product can be expected.

In the above-mentioned preferred method, when the sheet-shaped product inspection step detects a large number of sheet-shaped products with defects, for example, it is preferred that in the aforementioned combination specific procedure, the sheet-shaped products are inspected for defects in the sheet-shaped products. For each of the plurality of sheet-like products for which defects are detected in the product inspection step, a plurality of combinations of the aforementioned types and the aforementioned execution locations are specified, and in the aforementioned extraction condition determination program, a plurality of combinations specified by the aforementioned combination specifying program are A majority combination among the combinations of the aforementioned types and the aforementioned execution places is determined as the aforementioned extraction condition.

In addition, when the present invention uses the inspection results of the original piece, it is more desirable to further include: an original piece inspection step to inspect the original piece before cutting or cutting out the aforementioned intermediate body; and a correlation step to establish the original piece. The aforementioned location information of the defects in the original piece that have been detected in the aforementioned original piece inspection step before cutting or cutting out the aforementioned intermediate body, the types of defects that exist in the aforementioned original piece, and the detected defects that exist in the aforementioned original piece. The execution place of the original piece inspection step of the defect and the manufacturing step history information of the aforementioned original piece are associated with the aforementioned position information mark to be memorized. The aforementioned analysis step includes: combining a specific program and determining that the aforementioned specified item exists in the aforementioned piece. Whether the aforementioned position information of the defect of the product in the aforementioned original film and the aforementioned position information of the defect existing in the aforementioned original film associated with the aforementioned position information mark read in the aforementioned reading step are consistent. If they are consistent, Next, specify the type of defect existing in the original film that is associated with the position information mark read in the reading step and memorize it, and the execution place of the original film inspection step that detects the defect existing in the original film. , and the combination of the manufacturing step process information of the aforementioned original film; the extraction condition determination program determines the extraction conditions based on the combination of the aforementioned type specified by the aforementioned combination specific program and the aforementioned execution place; and the determination program performs a learning model using Judgment is a judgment of a tendency related to the occurrence of defects. In the above-mentioned judgment procedure, among all the defects present in the above-mentioned original film detected in the above-mentioned original film inspection step, the ones determined by the above-mentioned extraction condition determination procedure will be met. The aforementioned manufacturing step process information specified in the aforementioned combination specific step of the aforementioned original film in which the defect of the extraction condition exists is input to the aforementioned learning model, and the defects existing in the aforementioned original film that meet the aforementioned extraction condition are output from the aforementioned learning model. Determination result of whether it is detected as a defect of the aforementioned sheet product.

According to the above-mentioned ideal method, in the judgment process, among all the defects existing in the original film, the specified manufacturing step history information of the original film containing the defects that meet the extraction conditions is input to the learning model, and from The learning model outputs a determination result of whether defects existing in the original piece that meet the extraction conditions are detected as defects in the sheet product. Therefore, according to the above-described ideal method, the possibility of detecting (generating) defects in the sheet-like product can be evaluated (determined) based on the manufacturing step history information of the original sheet. In addition, in the above-mentioned more ideal method, the learning model may also be a learning model generated by supervised learning using a known combination of input and output as teacher data, or a learning model generated by unsupervised learning. Invention effect

According to the present invention, the cause of a defect in a sheet-like product can be fully identified, and the invention can fully contribute to improving the yield rate of the sheet-like product.

Form used to implement the invention

Hereinafter, with reference to the appended drawings as appropriate, a description of the defect occurrence tendency analysis method (hereinafter, appropriately referred to as "analysis method") according to the embodiments (first to fifth embodiments) of the present invention will be given. The original film before cutting is marked with position information marks as an example to illustrate. Examples of sheet-like products to which the analysis method of this embodiment is applied include optical films such as polarizing films, retardation films, visual compensation films, brightness enhancement films, and laminated films of two or more types of these films. In this embodiment, a case where the sheet-like product is a laminated film in which a retardation film or the like is laminated on a polarizing film will be explained as an example. In addition, since the structure of each film is well known, detailed description thereof is omitted here.

＜System configuration＞ FIG. 1 is a diagram schematically showing the schematic configuration of a system for executing the analysis method according to this embodiment. In FIG. 1 , the arrow Z refers to the normal direction (vertical direction) of the surface of the original sheet S1. As shown in FIG. 1 , the system 100 of this embodiment includes: a sheet product S2 manufacturing device 100 a disposed in the sheet product manufacturing step of manufacturing the sheet product S2 ; and a reading device 6 disposed in the sheet product S2 manufacturing step. Inspection steps for sheet products.

The manufacturing apparatus 100a of this embodiment is equipped with the inspection apparatus 1, the marking apparatus 2, the cutting apparatus 3, and the control analysis apparatus 4. The control analysis device 4 is electrically connected to the inspection device 1 , the marking device 2 , and the cutting device 3 . Moreover, the manufacturing apparatus 100a of this embodiment is equipped with the delivery roller R1, the nip roller R2, and the conveyor R3. The manufacturing device 100a of this embodiment feeds out the long original sheet S1 wound into a roll shape by the feeding roller R1, conveys it in the X direction by the nip roller R2, the conveyor R3, etc., and cuts it by the cutting device 3 , a device for manufacturing a plurality of sheet products S2. The original sheet S1 is a long laminated film in which a retardation film or the like is laminated on a polarizing film, and is produced through known steps such as a stretching step, an adhesion step, and a laminating step.

The inspection device 1 is a device that detects defects existing in the original sheet S1 by inspecting the original sheet S1 before cutting. The inspection device 1 shown in FIG. 1 includes a light source 11 arranged on one side in the Z direction with respect to the original sheet S1 (under the original sheet S1 in the example shown in FIG. 1 ), and emits light toward the original sheet S1; The imaging mechanism 12 is arranged on the other side in the Z direction with respect to the original film S1 (in the example shown in FIG. 1 , above the original film S1 ), and receives the light transmitted through the original film S1 to form an image (photograph). generate a transmission image; and an image processing unit 13 that detects defects by applying known image processing such as extracting a brightness value and binarizing a pixel area that is different from other pixel areas to the transmission image input from the imaging unit 12 . In this embodiment, the control analysis device 4 also functions as the image processing mechanism 13 of the inspection device 1 . However, the image processing mechanism 13 may be provided separately from the control analysis device 4 .

The inspection device 1 is not limited to a structure that detects defects based on a transmission image as described above. It may also be configured to detect defects based on a reflected image. The reflected image is detected in the Z direction with respect to the original sheet S1. A light source and a shooting mechanism are configured on one side to generate a reflected image. In addition, when the original sheet S1 (sheet product S2) is a polarizing film, the inspection device 1 may also be configured to detect defects based on a cross-polarized image relative to the original. The light source and the inspection polarizing filter are arranged on one side of the sheet S1 in the Z direction, and the photographing mechanism is arranged on the other side in the Z direction with respect to the original sheet S1, or the light source is arranged on one side of the Z direction with respect to the original sheet S1, with respect to the original sheet S1. An image generated by arranging an inspection polarizing filter and a photographing mechanism on the other side of the original film S1 in the Z direction. Furthermore, the inspection device 1 may be configured to detect defects by combining two or more images among a transmission image, a reflection image, and a cross-polarization image. In FIG. 1 , for the sake of convenience, a case where one inspection device 1 is used to inspect the original sheet S1 at a single place is shown. However, the present invention is not limited to this, and it may also be performed in a step before the manufacturing device 100 a. The inspection device 1 is arranged to inspect the original film S1 in a plurality of places.

The control analysis device 4 (image processing mechanism 13) constituting a part of the inspection device 1 can recognize the position (XY coordinate) of the defect in the transmission image. Therefore, for example, the control analysis device 4 can be based on the position (XY coordinate) of the identified defect in the transmission image, the X-direction separation distance L1 between the feed roller R1 and the inspection device 1, and the encoder installed on the nip roller R2. (not shown), etc., to identify the position of the defect existing in the original sheet S1 in the original sheet S1.

The marking device 2 is a device that marks the original sheet S1 before cutting with a position information mark. The position information mark is a mark indicating the position information in the original sheet S1. Specifically, by controlling the marking device 2 by the control analysis device 4, position information marks are marked so that a plurality of position information marks exist on each of the plurality of cut sheet products S2. The marking device 2 of this embodiment is an inkjet marking device using transparent ink (specifically, UV ink). The transparent ink is ejected from a plurality of nozzles arranged along the Y direction to mark positional information. The composition of marks. However, the marking device 2 may also be marked by an inkjet method using general colored ink, or may be marked by laser marking. In addition, when ink is used, the marking method is not limited to the inkjet method, and a pen method may also be used for marking. Since the specific structures of these marking devices are well known, detailed descriptions thereof are omitted here.

The cutting device 3 is a device that cuts the original sheet S1 by a known processing method such as punching processing or laser processing, thereby manufacturing a plurality of sheet products S2. Specifically, the control analysis device 4 controls the cutting device 3 to cut the original sheet S1 along a predetermined cutting line.

The control analysis device 4 is composed of a computer in which a program for controlling the operations of the marking device 2 and the cutting device 3 and a program for executing an analysis method described below are installed.

In addition, the manufacturing apparatus 100a may also be equipped with a marking device (not shown) that marks the position where the defect is detected by inspecting the original sheet S1 by the inspection device 1 or the like on the original sheet S1 before cutting. Mark (defect mark). Specifically, the control analysis device 4 can identify the location of the defect detected by inspecting the original sheet S1 by the inspection device 1 or the like, and the control analysis device 4 can also control the above-mentioned marking device to mark the defect mark at the location where the defect exists. . As the above-mentioned marking device, like the marking device 2 , it is possible to use an inkjet method for marking using a general colored ink or a structure for marking by laser marking.

[Method for manufacturing sheet products] Hereinafter, a method of manufacturing the sheet product S2 using the manufacturing apparatus 100a having the above-described configuration will be described. FIG. 2 is a flowchart showing schematic steps of a method for manufacturing a sheet-like product using the analysis method of the present embodiment. As shown in FIG. 2 , the manufacturing method of this embodiment includes a position information marking step ST1, a cutting step ST2, and a recovery step ST3. In addition, the location information marking step ST1 described here is the same as the location information marking steps ST11, ST22, ST32, ST42, and ST52 in the first to fifth embodiments described below. FIG. 3 is a diagram schematically explaining the state of the original sheet S1 and the sheet-like product S2 in the manufacturing method shown in FIG. 2 . FIG. 3(a) is a diagram schematically showing the state of the original film S1 before the position information marking step ST1 is executed. FIG. 3(b) is a diagram schematically showing the state of the original film S1 just after the position information marking step ST1 is executed. FIG. 3(c) is a diagram schematically showing the state of the original sheet S1 (sheet product S2) immediately after the cutting step ST2 is executed. FIG. 3(d) is a diagram schematically showing the state of the sheet product S2 during execution of the recovery step ST3. Each of steps ST1 to ST3 will be described in order below.

[Location information marking step ST1] As shown in Figure 3(a), the inspection device 1 is used to inspect the original piece S1 before cutting, thereby detecting the defect F (in Figure 3(a), for convenience, any defect F is shown as a black dot. Show). As shown in FIG. 3( b ), in the position information marking step ST1 , the original piece S1 before cutting is marked with a position information mark M indicating the position information in the original piece S1 by the marking device 2 . The position information represented by the position information symbol M refers to information including at least the position (that is, XY coordinates) of the original sheet S1 in the longitudinal direction (transportation direction, X direction) and the width direction (Y direction). The position in the longitudinal direction of the original sheet S1 may also be expressed as a distance from the front end of the original sheet S1 in the longitudinal direction (conveying direction), or may be expressed as a distance from the front end of the original sheet S1 in the longitudinal direction (conveying direction). Distance, expressed as a number followed by a consecutive number. In addition to the position in the transport direction of the original film S1, the position information represented by the position information symbol M may also represent information about the original film S1 that is used to mutually identify the plurality of original films S1. The information may also indicate other incidental information. The location information mark M in this embodiment is DataMatrix (registered trademark), which is a type of two-dimensional code. However, the present invention is not limited to this. In addition to other two-dimensional codes such as QR codes (registered trademarks), or one-dimensional codes (barcodes), various forms of marks can be used as long as they can express the position information in the original film S1 as the location information mark M.

In the position information marking step ST1, the original sheet S1 before cutting is marked with a position information mark M by the marking device 2, so that the position information mark M exists in each of the plurality of sheet products S2 after cutting. Specifically, the planned cutting line CL shown by the dotted line in FIG. 3(b) is determined in advance in accordance with the size and shape of the sheet product S2, and is stored in the control analysis device 4. The planned cutting line CL is not a line actually drawn on the original sheet S1, but is stored as an XY coordinate based on the front end of the original sheet S1 in the longitudinal direction. In the example shown in FIG. 3(b) , the planned cutting lines CL are in a grid shape, and the original lines are located in each rectangle (18 rectangles are shown in FIG. 3(b) ) divided by the planned cutting lines CL. The parts of the sheet S1 will respectively become sheet products S2 after cutting. Therefore, in the position information marking step ST1, the position information mark M is marked by the marking device 2 as follows: the position information mark M will exist in each rectangle divided by the scheduled cutting line CL, and will not be related to the scheduled cutting line CL. Lines CL overlap. In the example shown in FIG. 3(b) , one position information mark M is marked in each rectangle, and the position of the position information mark M based on the planned cutting line CL is set to be the same for any rectangle. (center of each rectangle). However, the present invention is not limited to this. For example, when a defect mark is marked at the location where a defect exists, in order to reduce the possibility that the position information mark overlaps with the defect mark and the position information mark cannot be read, a plurality of position information marks M may be marked in each rectangle. In addition, when a plurality of sheet-like products S2 are stacked on each other for use, in order to reduce the risk of dents occurring in the overlapping portions due to the overlap of position information marks in each sheet-like product S2, marks may also be included in each rectangle. The positions of the position information tokens M are different from each other.

When executing the position information marking step ST1, for example, the control analysis device 4 can measure based on the distance L2 between the delivery roller R1 and the marking device 2 in the X direction, and the encoder (not shown) installed on the nip roller R2. The transport amount of the original sheet S1 is used to calculate the time point when the predetermined portion of the original sheet S1 reaches the marking device 2 . Furthermore, for example, the control analysis device 4 controls the marking device 2 so that the time point when the marking device 2 is reached at a location having predetermined XY coordinates based on the planned cutting line CL (a location where the position information mark M is marked within each rectangle) , the transparent ink is ejected from the nozzle of the marking device 2 corresponding to the Y coordinate of the aforementioned predetermined XY coordinate. By this, the position information mark M can be marked in each rectangle respectively.

[Cutting step ST2] As shown in FIG. 3(c) , in the cutting step ST2, the original sheet S1 marked with the position information mark M is cut by the cutting device 3 along the planned cutting line CL (see FIG. 3(b) ). , to manufacture a plurality of sheet products S2. When a punching processing device is used as the cutting device 3, when the planned cutting line CL of the original sheet S1 reaches the cutting device 3, the conveyance of the original sheet S1 is temporarily stopped and the original sheet S1 is cut. When a laser processing device is used as the cutting device 3 , the original sheet S1 may be cut while being conveyed without stopping the conveyance of the original sheet S1 . When executing the cutting step ST2, for example, the control analysis device 4 may measure based on the distance L3 between the delivery roller R1 and the cutting device 3 in the X direction, the encoder (not shown) installed on the nip roller R2, etc. The conveyance amount of the original sheet S1 is calculated by calculating the time when the planned cutting line CL of the original sheet S1 stored in the control analysis device 4 reaches the cutting device 3 . Then, the control analysis device 4 controls and drives the cutting device 3 at the time when the planned cutting line of the original sheet S1 reaches the cutting device 3 . Thereby, the original sheet S1 can be cut along the planned cutting line CL, and a plurality of sheet products S2 can be manufactured.

[Recycling step ST3] As shown in FIG. 3(d), in the recovery step ST3, while the cut original sheet S1 is conveyed by the conveyor R3, unnecessary parts that have not become the sheet product S2 are removed by a known removal device (not shown). part S11 (refer to Figure 3(c)). Thereafter, the sheet product S2 is conveyed by the conveyor R3, and the sheet product S2 is dropped by gravity from the downstream end in the conveyance direction of the conveyor R3, thereby collecting the sheet product S2.

As shown in FIG. 1 , the sheet product S2 manufactured in the above manner is carried out to the sheet product inspection step, and is visually inspected by, for example, the inspector 5 . However, the present invention is not limited to this, and an optical automatic inspection device (not shown) may be used for inspection. Furthermore, it is also conceivable that, for example, the sheet product manufacturing step is performed in a sheet product manufacturing factory, and the sheet product inspection step is performed in an optical display device manufacturing factory using a sheet-like product. The sheet-like product S2 shipped from the factory is used to manufacture an optical display device. When the sheet-like product S2 is inspected in an optical display device manufacturing factory, it is not limited to this. For example, a known inspection such as a lighting inspection may be performed in a state where the sheet-like product S2 is bonded to the optical display unit. . When a defect is detected through inspection, the position information mark M marked on the sheet product S2 is read by the reading device 6 . The reading device 6 is a reading device that reads the position information mark M marked on the sheet product S2, and a known two-dimensional code reader or the like can be used as the reading device 6.

By reading the position information mark M with the reading device 6, the position information (XY coordinates) of the sheet product S2 in the original sheet S1 can be obtained. The acquired position information will be input to the control analysis device 4 . In addition, the input of the acquired position information to the control analysis device 4 can also be performed manually by humans, or it can be automatically input from the reading device 6 by electrically connecting the reading device 6 and the control analysis device 4 through a wireless communication circuit or the like. to the control analysis device.

＜Analysis method＞ Hereinafter, the contents of the analysis method of the present embodiment (first to fifth embodiments) using the system 100 having the above-described configuration will be described.

<First Embodiment> FIG. 4 is a flowchart showing the schematic steps of the analysis method according to the first embodiment. As shown in FIG. 4 , the analysis method of the first embodiment includes a position information marking step ST11, a sheet product inspection step ST12, a reading step ST13, and an analysis step ST14. The analysis method of the first embodiment is a method that does not use the inspection results of the original film S1. That is, when executing the analysis method of the first embodiment, the inspection device 1 is not required. Each of steps ST12 to ST14 will be described in order below.

[Location information marking step ST11] In the position information marking step ST11, the marking device 2 is used to mark the original sheet S1 before cutting with a position information mark M so that the position information mark M exists in each of the plurality of sheet products S2. The position information mark M is Indicates the position information in the length direction and width direction of the original film S1.

[Sheet product inspection step ST12] In the sheet product inspection step ST12, the inspector 5 inspects a plurality of sheet products S2.

[Reading step ST13] In the reading step ST13, the reading device 6 is used to read the position information mark M marking the sheet product S2 whose defect was detected in the sheet product inspection step ST12, thereby obtaining the position information mark M of the sheet product S2 in the original sheet S1. Location information.

[Analysis step ST14] In the analysis step ST14, the position information obtained in the reading step ST13 is input to the control analysis device 4. The control analysis device 4 specifies the position information of the sheet product S2 in the original sheet S1 obtained in the reading step ST13. Position information of defects in the original sheet S1 of the sheet product S2 detected in the sheet product inspection step ST12. Specifically, when the position information of the defect existing in each sheet product S2 based on each sheet product S2 is unknown (when only the position information of each sheet product S2 in the original sheet S1 is known), control For example, the analysis device 4 specifies the center position of each sheet product S2 as position information of the defect existing in each sheet product S2 in the original sheet S1. In addition, when the position information of the defect existing in each sheet product S2 is known based on each sheet product S2 (based on the four sides of each sheet product S2), the control analysis device 4 can read The position information of each sheet-like product S2 on the original sheet S1 obtained in step ST13 and the position information of the defect existing in each sheet-like product S2 based on each sheet-like product S2 are obtained to specify the defects existing in each sheet-like product S2. The location information of the defect in product S2 in the original film S1. Furthermore, in the analysis step ST14, the control analysis device 4 is used to analyze the tendency related to the occurrence of the defect based on the position information of the specified defect existing in the sheet product S2 in the original sheet S1.

Specifically, as shown in FIG. 4 , the analysis step ST14 of the analysis method of the first embodiment includes a map image generation program ST141 and a matching image generation program ST142. FIG. 5 is a diagram schematically showing an example of a map image and a template image. Figures 5(a) to 5(d) are examples of displaying map images, and Figures 5(e) to 5(i) are examples of displaying template images.

(Map image generation program ST141) In the map image generation program ST141, the control analysis device 4 generates the map image MP based on the specified position information of the defect existing in the sheet product S2 in the original sheet S1. The map image MP depicts the presence of the defect. An image of the position of the defect in the sheet-like product S2 in the original sheet S1. In the map image MP shown in Figures 5(a) to 5(d), the area divided by each rectangle corresponds to the original sheet S1, and the position of the defect existing in the sheet product S2 in the original sheet S1 is shown in black. Display with dots and white circles. In the actual map image MP, pixels represented by black dots and white circles have different brightness values (pixel values) from other pixels. In addition, in the examples shown in FIGS. 5(a) to 5(d) , the map image MP is generated by combining a plurality of original sheets S1 (original sheets S1a to S1d) that are continuously produced in the X direction. , but is not limited to this, and the map image MP may be generated for each single original piece S1.

(Matching image generation program ST142) In the matching image generation program ST142, the control analysis device 4 performs pattern matching on the map image MP and the template image TE prepared in advance as shown in FIGS. 5(e) to 5(i), thereby A matching image is generated as an image representing a tendency related to the occurrence of defects. The matching image is one of only the positions of defects that match the template image TE among the defect positions drawn on the map image MP. images. That is, the control analysis device 4 scans the template image TE on the map image MP, and extracts the pixel areas of the map image MP in which the degree of consistency between the map image MP and the template image TE is equal to or greater than a predetermined threshold. Generate matching images.

The template image TE shown in FIG. 5(e) is an image in which pixels represented by white circles are drawn with a certain period P in the X direction. This period P corresponds to the period of the feed roller R1 or the nip roller R2. (outer perimeter) to set. Preferably, a plurality of template images TE having different cycles P are prepared according to the cycle of each roller used in the manufacturing step of the sheet product S2. In the actual template image TE, pixels represented by white circles have different brightness values (pixel values) from other pixels, and have the same brightness value as pixels represented by black dots and white circles in the map image MP. The same applies to the template images shown in Figures 5(f) to 5(i). For example, on the map image MP shown in FIG. 5(a) , the template image TE shown in FIG. 5(e) is scanned in the X direction and the Y direction to perform pattern matching, thereby extracting the image shown in FIG. 5( pixels of the white circle in the map image MP shown in a), and a matching image in which only the pixels of this white circle are drawn (pixels in which black dots are not drawn) is generated.

The three template images TE shown in FIG. 5(f) are all images depicting pixels represented by white circles densely arranged in a predetermined shape. Although the template image TE display shown on the uppermost side of Fig. 5(f) depicts an example of an image of pixels densely arranged in a parallelogram shape, the template image TE display shown in the center of Fig. 5(f) depicts an image in which pixels are densely arranged. As an example of an image of linear pixels, the template image TE shown at the bottom of FIG. 5(f) shows an example of an image of pixels densely arranged in a rhombus shape. However, the template image TE is not limited to these and may be An image depicting pixels densely arranged in any shape such as a triangle, a square, or a cross is used as the template image TE. For example, on the map image MP shown in FIG. 5(b) , the template image TE shown on the top side of FIG. 5(f) is scanned in the X direction and the Y direction to perform pattern matching, thereby extracting the map image. 5(b), and generates a matching image in which only the pixels of the white circle are drawn (pixels in which the black dots are not drawn) are drawn.

The template image TE shown in FIG. 5(g) is an image in which pixels represented by white circles are drawn at a specific Y coordinate (Y1) and a specific X coordinate (X1). For example, on the map image MP shown in FIG. 5(c), the template image TE shown on the upper side of FIG. 5(g) is scanned in the X direction to perform pattern matching, thereby extracting the image shown in FIG. 5(c). The pixels of the white circle (the pixel whose Y coordinate is Y1) in the map image MP are shown, and a matching image in which only the pixels of this white circle are drawn (pixels where the black dot is not drawn) is generated.

The template image TE shown in FIG. 5(h) is an X-direction front end of the map image MP (corresponding to the longitudinal front end of the original film S1) or a rear end of the map image MP in the X direction (corresponding to the original film S1). Long side direction rear end of S1) applied image. In other words, the template image TE shown in FIG. 5(h) is an image used to extract defects existing at the front end or the rear end of the map image MP. For example, the template image TE shown in FIG. 5(h) is scanned in the Y direction on the front end of the map image MP shown in FIG. 5(d) in the X direction (the upper end part of FIG. 5(d)). Pattern matching is performed to extract the pixels of the white circle in the map image MP shown in FIG. 5(d), and a matching map is generated in which only the pixels of the white circle are drawn (the pixels of which the black dots are not drawn) picture.

The template image TE shown in FIG. 5(i) is an image in which pixels represented by white circles are depicted as swinging in the Y direction. Although specific examples are omitted, by using this template image TE for pattern matching, it is possible to generate a matching image corresponding to the following defects: wobbling in the width direction of the original sheet S1 due to meandering of the original sheet S1, etc. Defects in position.

As described above, according to the analysis method of the first embodiment, in the map image generation program ST141 of the analysis step ST14, the map image MP is generated which depicts the defects existing in the sheet product S2 on the original sheet. For the image of the position in S1, the matching image generation program ST142 generates a matching image in which only defects matching the template image TE are drawn among the positions of the defects drawn on the map image MP. image of the location. Therefore, for example, by visually recognizing the matching image, the tendency related to the occurrence of defects detected for the sheet product S2 (the tendency of defect occurrence (production pattern)) can be grasped.

<Second Embodiment> FIG. 6 is a flowchart showing the schematic steps of the analysis method according to the second embodiment. As shown in FIG. 6 , the analysis method of the second embodiment includes an original film inspection step ST21, a position information marking step ST22, a correlation step ST23, a sheet product inspection step ST24, a reading step ST25, and an analysis step ST26. The analysis method of the second embodiment is different from the analysis method of the first embodiment and uses the inspection results of the original film S1. Therefore, the analysis method of the second embodiment has the original image inspection step ST21 and the correlation step ST23 which are not included in the analysis method of the first embodiment. In addition, the content of the analysis step ST26 is also different from the analysis step ST14 of the analysis method of the first embodiment. Each of steps ST21 to ST26 will be described in order below.

[Original film inspection step ST21] In the original sheet inspection step ST21, the original sheet S1 before cutting is inspected using the inspection device 1 to detect defects existing in the original sheet S1. As mentioned above, the inspection device 1 can be disposed in a plurality of places and can be configured to detect defects based on a transmission image, a reflection image, or a cross-polarized image. Therefore, the control analysis device 4 can determine the type of the defect based on which image the defect was detected, or where the detection device 1 is located, the location information of the defect in the original film S1, etc.

[Location information marking step ST22] In the position information marking step ST22, similarly to the position information marking step ST11 of the analysis method of the first embodiment, the original piece S1 before cutting is marked with the position information mark M using the marking device 2 so that the position information mark M exists. For each of the plurality of sheet-like products S2, the position information mark M represents position information in the longitudinal direction and the width direction of the original sheet S1.

[Association step ST23] In the correlation step ST23, the control analysis device 4 combines the position information of the defect existing in the original sheet S1 before cutting detected in the original sheet inspection step ST21, the type of the defect existing in the original sheet S1, and the detected presence. The location where the original sheet inspection step ST21 for defects in the original sheet S1 is performed (the location where the inspection device 1 is disposed) is associated with the position information mark M and stored. Specifically, the control analysis device 4 associates and memorizes the position information mark M marked on the sheet product S2 that is the same as the sheet product S2 where the defect detected in the original sheet inspection step ST21 is located. Sheet product S2.

[Sheet product inspection step ST24] In the sheet product inspection step ST24, similarly to the sheet product inspection step ST12 of the analysis method of the first embodiment, the inspector 5 inspects a plurality of sheet products S2.

[Reading step ST25] In the reading step ST25, similarly to the reading step ST13 of the analysis method of the first embodiment, the reading device 6 is used to read the position of the sheet product S2 on which the defect was detected in the sheet product inspection step ST24. The information mark M is used to obtain the position information of the sheet product S2 in the original sheet S1.

[Analysis step ST26] In the analysis step ST26, similarly to the analysis step ST14 of the analysis method of the first embodiment, the position information obtained in the reading step ST25 is input to the control analysis device 4, and the control analysis device 4 obtains it based on the reading step ST25. The position information of the sheet product S2 in the original sheet S1 specifies the position information of the defect in the sheet product S2 detected in the sheet product inspection step ST24 in the original sheet S1. Moreover, in the analysis step ST26, similarly to the analysis step ST14 of the analysis method of the first embodiment, the control analysis device 4 is used to determine based on the position information of the specified defect existing in the sheet product S2 in the original sheet S1. Analysis and defect generation related tendencies. However, in the second embodiment, the inspection results of the original sheet S1 are used, so the specific content of the analysis step ST26 is different from the first embodiment in which the inspection results of the original sheet S1 are not used.

Specifically, as shown in FIG. 6 , the analysis step ST26 of the analysis method of the second embodiment includes a combination specifying program ST261, an extraction condition determining program ST262, a map image generating program ST263, and a matching image generating program ST264. FIG. 7 is a diagram schematically explaining the contents of the analysis step ST26 of the analysis method according to the second embodiment.

(Combination specific program ST261) In the combination specifying program ST261, the control analysis device 4 determines: the position information of the specified defect existing in the sheet product S2 in the original sheet S1 (that is, based on the position information of the sheet product S2 obtained in the reading step ST25 in the original sheet The position information in S1 specifies the existence of the defect existing in the sheet product S2 in the original piece S1 (position information A)), and is associated and memorized with the position information mark M read in the reading step ST25. Whether the position information of the defect on the original piece S1 (that is, the position information (position information B) of the defect on the original piece S1 detected in the original piece inspection step ST21) is consistent. Specifically, assuming that an image depicting the positions of all defects detected in the original image inspection step ST21 in the original image S1 (hereinafter, referred to as the "original image") is generated, it may be considered to generate the image as shown in Figure 7 The original image GI shown in (a). The black dots shown in Figure 7(a) are defects. In the example shown in FIG. 7 , it is considered that five pieces of position information A have been identified. In this case, as shown in FIG. 7( b ), in the combination specifying program ST261 , a predetermined nearby area (in In the five areas A1 to A5 shown by dotted lines in Figure 7(b), whether there are positions in the X direction and Y direction of the original piece S1 contained in the position information B. In the example shown in FIG. 7(b) , in addition to the area A3, there are black dots in the areas A1, A2, A4, and A5. That is, it is determined that there are black dots in the areas A1, A2, A4, and A5. The position information B includes the positions in the X direction and the Y direction of the original film S1 (that is, the position information A and the position information B corresponding to the areas A1, A2, A4, and A5 are consistent).

Furthermore, in the combination specifying program ST261, when the position information A and the position information B match (in other words, there is a defect detected in the original sheet inspection step ST21 at the same position as the defect detected in the sheet product S2). In the case of a defect in the sheet S1, that is, in the case where the same defect is detected in both the sheet product S2 and the original sheet S1), the control analysis device 4 will identify and read in the reading step ST25. The location information mark M associates and memorizes a combination of the type of defect present in the original sheet S1 and the execution location of the original sheet inspection step ST21 in which the defect present in the original sheet S1 is detected. For example, consider the following situation: Defects are detected in 11 sheet products S2 of No. 1 to No. 11, and whether each defect is also detected in the original sheet inspection step ST21 (whether position information A and position information B are consistent), And when each defect is also detected in the original film inspection step ST21, the type of the defect and the execution place of the original film inspection step ST21 are as shown in Table 1 below. [Table 1] In the case of the above Table 1, in the combination specifying program ST261, the sheet products S2 corresponding to the sheet products S2 other than No. 3 and No. 9 for which no defects were detected in the original sheet inspection step ST21 are specified and exist in the original sheet S1. combinations of types of defects and execution locations of the original sheet inspection step ST21 where defects present in the original sheet S1 are detected (nine combinations hatched in Table 1).

(Extraction condition determination program ST262) In the extraction condition determination program ST262, the control analysis device 4 determines the extraction condition based on the combination of the type and execution location specified by the combination specification program ST261. Specifically, the control analysis device 4 determines, as the extraction condition, a majority combination among the plurality of types and execution location combinations specified by the combination specifying program ST261. The method of determining a majority combination as the extraction condition is preferably used when there are a large number of sheet-like products S2 in which defects are detected in the sheet-like product inspection step ST24. In the case shown in Table 1 above, among the 9 specified combinations of types and execution locations, the number of combinations in which the type of defect is "foreign matter" and the execution location is "extended step" is 5 and it is excessive. Half, therefore, the combination of "foreign matter" and "extension step" was determined as the extraction condition.

In addition, for example, the following case can be considered: defects are detected in two sheet products S2 of No. 1 and No. 2, and whether each defect is also detected in the original sheet inspection step ST21 (whether the position information A and the position information B are consistent ), and when each defect is also detected in the original inspection step ST21, the type of the defect and the execution location of the original inspection step ST21 are as shown in Table 2 below. [Table 2] In the case of the above Table 2, in the combination specifying program ST261, defects existing in the original sheet S1 corresponding to the sheet product S2 other than the number 3 in which no defect was detected in the original sheet inspection step ST21 are specified. The type and the combination of the execution place of the original sheet inspection step ST21 in which the defect present in the original sheet S1 is detected (the two hatched combinations in Table 2). Furthermore, in the extraction condition determination program ST262, for example, the two sets of combinations of types and execution locations specified by the combination specification program ST261 may be determined based on the combination of the type and execution location specified by the combination specification program ST261 that is determined as the extraction condition. All, determined as extraction conditions. The method of determining all combinations as extraction conditions is preferably used when the number of the plurality of sheet products S2 whose defects are detected in the sheet product inspection step ST24 is small. In the case shown in Table 2 above, the combination of the two specified types and execution locations, that is, the combination of the defect type being "foreign matter" and the execution location being "extended step", and the type of defect The combination of "sag" and "extension step" where the execution location is is determined as the extraction condition.

In the extraction condition determination program ST262, only one of a method of determining a majority of combinations as extraction conditions and a method of determining all combinations as extraction conditions may be used to determine the extraction conditions. Alternatively, a method of determining the extraction conditions may be used. The two methods are switched based on the number of the plurality of sheet products S2 in which defects are detected in the sheet product inspection step ST24.

(Map image generation program ST263) In the map image generation program ST263, the control analysis device 4 controls all the defects (black dots in FIGS. 7(a) and 7(b)) present in the original image S1 detected in the original image inspection step ST21, based on The position information of the defect in the original film S1 that meets the extraction conditions determined by the extraction condition determination program ST262 generates an image depicting the position of the defect in the original film S1 as shown in FIG. 7(c), that is, a map image MP. For example, in the case shown in the aforementioned Table 1, since the combination of "foreign matter" and "stretching step" is determined as the extraction condition, among all the defects present in the original sheet S1 detected in the original sheet inspection step ST21, A combination is selected where the type of defect is "foreign matter" and the execution location of the original sheet inspection step ST21 in which the defect is detected is the "extension step", and a map image MP depicting the position of the selected defect in the original sheet S1 is generated.

(Matching image generation program ST264) In the matching image generation program ST264, the control analysis device 4 combines the map image MP shown in Fig. 7(c) and the template image TE prepared in advance (refer to Figs. 5(e) to 5(i) ) perform pattern matching to generate a matching image MA as shown in FIG. 7(d) as an image representing the tendency related to the occurrence of defects. The matching image MA is only drawn on the map. Among the defect positions in the image MP, the image is an image of a defect position that matches the template image TE. The specific content of the matching image generation program ST264 is the same as the matching image generation program ST142 of the analysis method in the first embodiment, and therefore a detailed description is omitted here.

As described above, according to the analysis method of the second embodiment, the map image MP is generated in the map image generation program ST263 of the analysis step ST26. The map image MP only depicts all the defects existing in the original film S1. Defects under the same conditions (combination of the type of defect and execution location of the original sheet inspection step ST21) as the defects detected for the sheet product S2 (the defects detected for the corresponding original sheet S1) are found in the original sheet S1 s position. Therefore, for example, the matching image MA generated from the map image MP by the matching image generation program ST264 can be visually recognized, thereby grasping the tendency related to the occurrence of defects that may be detected in the sheet product S2 (defects of the sheet product S2). the tendency to produce (produce patterns)).

<Third Embodiment> FIG. 8 is a flowchart showing the schematic steps of the analysis method according to the third embodiment. As shown in FIG. 8 , the analysis method of the third embodiment includes an original film inspection step ST31, a position information marking step ST32, a correlation step ST33, a sheet product inspection step ST34, a reading step ST35, and an analysis step ST36. The analysis method of the third embodiment is also a method that uses the inspection results of the original film S1 in the same manner as the analysis method of the second embodiment. The content of the original film inspection step ST31, the position information marking step ST32, the association step ST33, the sheet product inspection step ST34, and the reading step ST35 of the analysis method of the third embodiment are respectively the same as those of the analysis method of the second embodiment. The contents of the original film inspection step ST21, the position information marking step ST22, the association step ST23, the sheet product inspection step ST24, and the reading step ST25 are the same. Therefore, in the following, the differences between the analysis step ST36 and the analysis step ST26 of the analysis method of the second embodiment will be mainly explained, and detailed descriptions of other steps will be omitted.

[Analysis step ST36] In the analysis step ST36, similarly to the analysis step ST26 of the analysis method of the second embodiment, the position information obtained in the reading step ST35 is input to the control analysis device 4, and the control analysis device 4 obtains it based on the reading step ST35. The position information of the sheet product S2 in the original sheet S1 specifies the position information of the defect in the sheet product S2 detected in the sheet product inspection step ST34 in the original sheet S1. Moreover, in the analysis step ST36, similarly to the analysis step ST26 of the analysis method of the second embodiment, the control analysis device 4 is used to determine based on the position information of the specified defect existing in the sheet product S2 in the original sheet S1. Analysis and defect generation related tendencies. However, the points following analysis step ST36 are different from analysis step ST26.

In the analysis step ST36, the control analysis device 4 determines whether the number of combinations of the plurality of types and execution places specified by the combination specification program ST361, which is the same as the combination specification program ST261 of the analysis method of the second embodiment, is smaller than that of the plurality of combinations. The sheet product S2 has a majority of the total number of defects detected in the sheet product inspection step ST34 (ST362 in FIG. 8). Then, when the number of combinations of the plurality of specified types and execution places is not less than a majority (that is, a majority) (NO in ST362 of FIG. 8 ), the control analysis device 4 is The extraction condition determination program ST364, the map image generation program ST365, and the matching image generation program ST366 are executed. The contents of the extraction condition determination program ST364, the map image generation program ST365, and the matching image generation program ST366 are respectively the same as those of the extraction condition determination program ST262, the map image generation program ST263, and the matching image of the analysis method of the second embodiment. The content of the generation program ST264 is the same. On the other hand, when the number of combinations of the plurality of specified types and execution places is less than a majority (that is, a majority) (YES in ST362 of FIG. 8 ), the analysis device 4 is controlled. The extraction condition determination program ST364, the map image generation program ST365, and the matching image generation program ST366 are not executed, but the index output program ST363 is executed so that less than half of the cases are used as indications of tendencies related to the occurrence of defects. indicators to output.

For example, consider the following situation: Defects are detected in 11 sheet products S2 of No. 1 to No. 11, and whether each defect is also detected in the original sheet inspection step ST31 (whether position information A and position information B are consistent), And when each defect is also detected in the original film inspection step ST31, the type of the defect and the execution place of the original film inspection step ST31 are as shown in Table 3 below. [table 3] In the case of the above Table 3, the combination specifying program ST361 will specify No. 2, No. 3, No. 5, No. 7, No. 9, and No. 11 except for the defects not detected in the original film inspection step ST31. The sheet product S2 corresponds to the combination of the type of defect existing in the original sheet S1 and the execution location of the original sheet inspection step ST31 in which the defect present in the original sheet S1 is detected (the hatched 5 in Table 3 group combination). That is, the number of combinations of the plurality of types and execution places specified by the combination specifying program ST361 (5 sets) is smaller than the total number of defects (11) detected in the sheet product inspection step ST34 for the plurality of sheet products S2 ). Therefore, the control analysis device 4 does not execute the extraction condition determination program ST364, the map image generation program ST365, and the matching image generation program ST366, but executes the index output program ST363 to use less than half of the cases as indications and defects. Outputs indicators of related tendencies.

As described above, according to the analysis method of the third embodiment, when the specific condition is satisfied (YES in ST362 of FIG. 8 ), the extraction condition determination program ST364 and the map image generation program ST365 are not executed. , and the matching image generation program ST366, but in the index output program ST363, the number of combinations of the plurality of types and execution places specified by the combination specifying program ST361 (in other words, it can be considered that the sheet product S2 and the original film When the number of identical defects detected in both S1) is less than a majority of the total number of defects detected in the plurality of sheet products S2, it is output as an index indicating a tendency related to the occurrence of defects. Therefore, it is possible to reliably grasp the situation where a defect is detected in the sheet product S2 but cannot be detected in the original sheet S1 without needlessly generating a map image or a matching image, and contributes to the identification of the cause. .

<Fourth Embodiment> FIG. 9 is a flowchart showing the schematic steps of the analysis method according to the fourth embodiment. As shown in FIG. 9 , the analysis method of the fourth embodiment includes an original sheet inspection step ST41, a position information marking step ST42, a correlation step ST43, a sheet product inspection step ST44, a reading step ST45, and an analysis step ST46. The analysis method of the fourth embodiment is also a method that uses the inspection results of the original film S1 in the same manner as the analysis method of the second embodiment. The content of the original film inspection step ST41, the position information marking step ST42, the sheet product inspection step ST44, and the reading step ST45 of the analysis method of the fourth embodiment are respectively the same as the original film inspection step ST21 of the analysis method of the second embodiment. The contents of the position information marking step ST22, the sheet product inspection step ST24, and the reading step ST25 are the same. Therefore, in the following, the differences between the correlation step ST43 and the analysis step ST46 and the correlation step ST23 and the analysis step ST26 of the analysis method of the second embodiment will be mainly explained, and detailed descriptions of other steps will be omitted.

[Association step ST43] In the correlation step ST43, the control analysis device 4 combines the position information of the defect existing in the original sheet S1 before cutting detected in the original sheet inspection step ST41, the type of the defect existing in the original sheet S1, and the detected defect in the original sheet S1. The execution location of the original sheet inspection step ST41 (the location of the inspection device 1) for defects in the original sheet S1 and the manufacturing step history information of the original sheet S1 are associated with the position information mark M and stored. That is, the correlation step ST43 of the analysis method of the fourth embodiment is different from the correlation step ST23 of the analysis method of the second embodiment, except for the defects existing in the original piece S1 detected in the original piece inspection step ST41. In addition to the location information, the type of defect existing in the original film S1, and the execution place of the original film inspection step ST41 that detects the defect existing in the original film S1, the manufacturing step history information and the position information of the original film S1 are also marked M Make associations to remember. Various parameter values set or measured in the manufacturing steps of the original sheet S1 such as the stretching step, the adhesion step, and the laminating step can be exemplified as the manufacturing step history information.

[Analysis step ST46] In the analysis step ST46, similarly to the analysis step ST26 of the analysis method of the second embodiment, the position information obtained in the reading step ST45 is input to the control analysis device 4, and the control analysis device 4 obtains it based on the reading step ST45. The position information of the sheet product S2 in the original sheet S1 specifies the position information of the defect in the sheet product S2 detected in the sheet product inspection step ST44 in the original sheet S1. Moreover, in the analysis step ST46, similarly to the analysis step ST26 of the analysis method of the second embodiment, the control analysis device 4 is used to determine based on the position information of the specified defect existing in the sheet product S2 in the original sheet S1. Analysis and defect generation related tendencies. However, the points following analysis step ST46 are different from analysis step ST26.

In the combination specifying program ST461 of the analysis step ST46, the position information of the specified defect existing in the sheet product S2 in the original sheet S1 is determined and stored in association with the position information mark M read in the reading step ST45. Whether the location information of the defect existing in the original film S1 is consistent. This point is the same as the combination specifying program ST261 of the analysis step ST26 of the analysis method of the second embodiment. However, in the combination identification program ST461 of the fourth embodiment, if they match, the control analysis device 4 identifies that the position information mark M read in the reading step ST45 is associated with and memorized in the original film S1 The combination of the type of defect, the execution location of the original sheet inspection step ST41 where the defect present in the original sheet S1 is detected, and the manufacturing step history information of the original sheet S1 is different from the combination specific program ST261 of the second embodiment. That is, in the combination specifying program ST461, unlike the combination specifying program ST261, the manufacturing step history information of the original film S1 is also specified.

In the extraction condition determination program ST462 of the analysis step ST46, similarly to the extraction condition determination program ST262 of the analysis step ST26 of the analysis method of the second embodiment, the analysis device 4 is controlled based on the type and execution location specified by the combination specification program ST461. combination to determine the extraction conditions. That is, when determining the extraction conditions, the manufacturing step history information of the specified original sheet S1 is not used. Then, in the index output program ST463 of the analysis step ST46, the analysis device 4 is controlled to determine which of all the defects present in the original sheet S1 detected in the original sheet inspection step ST41 satisfy the extraction conditions determined by the extraction condition determination program ST462. The manufacturing step history information specified by the combination specifying program ST461 of the original piece S1 in which the defect exists is output as an index indicating a tendency related to the occurrence of the defect. For example, in the case of the aforementioned Table 1, the combination of "foreign matter" and "extension step" is determined as the extraction condition, and the manufacturing step history information of the original piece S1 with defects that meet this extraction condition will be used as Outputs an index indicating a tendency related to the occurrence of defects. In addition, in the case of the aforementioned Table 2, the combination of "foreign matter" and "stretching step" and the combination of "dent" and "stretching step" are determined as the extraction conditions, and the defects that meet the extraction conditions are The manufacturing step history information of the original film S1 is output as an index indicating the tendency related to the occurrence of defects.

As described above, according to the analysis method of the fourth embodiment, among all the defects existing in the original piece S1, the specified manufacturing step history information of the original piece S1 in which the defects meeting the extraction conditions exist is expressed as and Outputs indicators of tendencies related to the occurrence of defects. Therefore, it is expected that the tendency of appropriately grasping the manufacturing step history information of the original sheet S1 in which a defect may be detected in the sheet product S2 can be expected.

<Fifth Embodiment> FIG. 10 is a flowchart showing the schematic steps of the analysis method according to the fifth embodiment. As shown in FIG. 10 , the analysis method of the fifth embodiment includes an original film inspection step ST51, a position information marking step ST52, a correlation step ST53, a sheet product inspection step ST54, a reading step ST55, and an analysis step ST56. The analysis method of the fifth embodiment is also a method that uses the inspection results of the original film S1 in the same manner as the analysis method of the second embodiment. The content of the original film inspection step ST51, the position information marking step ST52, the sheet product inspection step ST54, and the reading step ST55 of the analysis method of the fifth embodiment are respectively the same as the original film inspection step ST21 of the analysis method of the second embodiment. The contents of the position information marking step ST22, the sheet product inspection step ST24, and the reading step ST25 are the same. Therefore, in the following, the differences between the correlation step ST53 and the analysis step ST56 and the correlation step ST23 and the analysis step ST26 of the analysis method of the second embodiment will be mainly explained, and detailed descriptions of other steps will be omitted.

[Association step ST53] In the correlation step ST53, the control analysis device 4 combines the position information of the defect existing in the original sheet S1 before cutting detected in the original sheet inspection step ST51, the type of the defect existing in the original sheet S1, and the detected defect in the original sheet S1. The execution location of the original sheet inspection step ST51 (location location of the inspection device 1) for defects in the original sheet S1 and the manufacturing step history information of the original sheet S1 are associated with the position information mark M and stored. That is, the correlation step ST53 of the analysis method of the fifth embodiment is different from the correlation step ST23 of the analysis method of the second embodiment, except for the defect existing in the original piece S1 detected by the original piece inspection step ST51. In addition to the location information, the type of defect existing in the original film S1, and the execution place of the original film inspection step ST51 that detects the defect existing in the original film S1, the manufacturing step history information and the position information of the original film S1 are also marked M Make associations to remember. This point is the same as the correlation step ST43 of the analysis method of the fourth embodiment.

[Analysis step ST56] In the analysis step ST56, similarly to the analysis step ST26 of the analysis method of the second embodiment, the position information obtained in the reading step ST55 is input to the control analysis device 4. The control analysis device 4 obtains the position information in the reading step ST55. The position information of the sheet product S2 in the original sheet S1 specifies the position information of the defect in the sheet product S2 detected in the sheet product inspection step ST54 in the original sheet S1. Moreover, in the analysis step ST56, similarly to the analysis step ST26 of the analysis method of the second embodiment, the control analysis device 4 is used to determine based on the position information of the specified defect existing in the sheet product S2 in the original sheet S1. Analysis and defect generation related tendencies. However, points following analysis step ST56 are different from analysis step ST26.

In the combination specifying program ST561 of the analysis step ST56, the position information of the specified defect existing in the sheet product S2 in the original sheet S1 is determined and stored in association with the position information mark M read in the reading step ST55. Whether the location information of the defect existing in the original film S1 is consistent. This point is the same as the combination specifying program ST261 of the analysis step ST26 of the analysis method of the second embodiment. However, in the combination identification program ST561 of the fifth embodiment, if they match, the control analysis device 4 identifies that the position information mark M read in the reading step ST55 is associated with and memorized in the original film S1 This is different from the combination specific program ST261 of the second embodiment in that the type of defect, the execution location of the original sheet inspection step ST51 where the defect present in the original sheet S1 is detected, and the manufacturing step history information of the original sheet S1 are combined. That is, in the combination specifying program ST561, unlike the combination specifying program ST261, the manufacturing step history information of the original sheet S1 is also specified. This point is the same as the analysis method combination specifying program ST461 of the fourth embodiment.

In the extraction condition determination program ST562 of the analysis step ST56, similarly to the extraction condition determination program ST262 of the analysis step ST26 of the analysis method of the second embodiment, the analysis device 4 is controlled based on the type and execution location specified by the combination specification program ST561. combination to determine the extraction conditions. That is, when determining the extraction conditions, the manufacturing step history information of the specified original sheet S1 is not used. Furthermore, in the analysis step ST56, unlike the analysis step ST26 of the analysis method of the second embodiment, the control analysis device 4 has a judgment program ST563. The judgment program ST563 performs judgment using a learning model as a result of the occurrence of defects. Determination of relevant tendencies. The learning model is stored in the control analysis device 4 in an updateable manner. The learning model may also be a learning model generated by supervised learning in which a known combination of input and output is set as teacher data, or a learning model generated by unsupervised learning. It is sufficient to appropriately use a known learning model such as a neural network or a support vector machine as the learning model.

Specifically, in the determination program ST563, among all defects present in the original sheet S1 detected in the original sheet inspection step ST51, those defects in the original sheet S1 that meet the extraction conditions determined by the extraction condition determination program ST562 are selected. The manufacturing step history information specified in the combination specific program ST561 is input to the learning model, and a determination result (detection result) on whether the defect existing in the original sheet S1 that meets the extraction conditions is detected as a defect in the sheet product S2 is output from the learning model. probability of arrival, etc.).

As described above, according to the analysis method of the fifth embodiment, in the determination program ST563, among all the defects existing in the original sheet S1, the specified manufacturing step history of the original sheet S1 in which the defects meeting the extraction conditions exist is determined. The information is input to the learning model stored in the control analysis device 4, and a determination result is output from the learning model as to whether the defect existing in the original sheet S1 that meets the extraction conditions is detected as a defect in the sheet product S2. Therefore, the possibility of detecting (generating) defects in the sheet product S2 can be evaluated (determined) based on the manufacturing step history information of the original sheet S1.

As described above, according to the analysis method of this embodiment (first to fifth embodiments), it is possible to fully identify the cause of the defect in the sheet product S2 and to fully contribute to the improvement of the sheet product S2. The yield rate is improved.

In addition, in the present embodiment, the description is given as an example in which the long original sheet S1 wound into a roll is successively fed out, transported, and cut to produce a plurality of sheet-like products S2. However, the present invention Application objects are not limited to this. It can also be applied to the following situation: after the long original sheet S1 wound into a roll is successively fed out and transported, and the position information mark M is marked, a large sheet-like intermediate body (size larger than a plurality of sheet-like products) is first cut out. S2 larger sheet-shaped intermediate), and cut this intermediate to produce a plurality of sheet-shaped products S2. In addition, the intermediate body may be cut by being conveyed by conveyor R3 or the like, or may be cut while being placed on a predetermined cutting table.

In addition, in this embodiment, the case where the position information mark M is marked on the original sheet S1 before cutting is taken as an example. However, the present invention is not limited to this, and the original sheet S1 may be cut out. The intermediate product or the plurality of cut sheet products S2 are marked with a position information mark M.

11 is a diagram showing the schematic structure of a manufacturing apparatus for executing an analysis method according to a modification of the present invention (a structure in which position information marks M are marked on a plurality of cut sheet products S2). In FIG. 11 , the same components as those of the manufacturing apparatus 100 a shown in FIG. 1 are assigned the same reference numerals. As shown in FIG. 11 , in the manufacturing apparatus 100a' of the modified example, the marking device 2 is disposed on the conveyor R3 on the downstream side of the cutting device 3 (the downstream side in the conveyance direction of the sheet product S2). Before recycling the product S2, the marking device 2 marks the sheet product S2 with a position information mark M.

Specifically, for example, the control analysis device 4 can control the original sheet S1 measured based on the distance L2' between the feed roller R1 and the marking device 2 in the X direction, an encoder (not shown) mounted on the nip roller R2, etc. The transportation amount of the sheet product S2 measured by an encoder (not shown) mounted on the roller of the conveyor R3 is used to calculate the arrival of the original sheet S1 at a predetermined position after cutting into the sheet product S2. Mark the time point of device 2. Furthermore, for example, the control analysis device 4 is the control marking device 2 and has a planned cutting line CL of the original sheet S1 (a cutting line that becomes the edge of the sheet product S2 after cutting into the sheet product S2). When the location of the reference predetermined XY coordinates (in the example shown in FIG. 3 , the location where the position information mark M is marked within each rectangle) reaches the marking device 2, from the marking device of the Y coordinate corresponding to the aforementioned predetermined XY coordinates 2 nozzles eject transparent ink. Thereby, in the example shown in FIG. 3 , position information marks M are marked within each rectangle (inside the sheet product S2 ).

Alternatively, a method of marking the position information mark M using the identification information described in Japanese Patent Application Laid-Open No. 2005-114624 may be adopted. Specifically, as described in the above-mentioned publication, identification information indicating the position in the conveyance direction of the original sheet S1 is recorded in advance on the end portion in the width direction (Y direction) of the original sheet S1 (the end portion not used as the sheet product S2), and This identification information is read by, for example, a predetermined reading device disposed immediately before the cutting device 3 and input to the control analysis device 4 . The control analysis device 4 can identify the cut sheet product S2 based on the read identification information and the conveyance amount of the sheet product S2 measured by an encoder (not shown) mounted on a roller provided in the conveyor R3. The position of the product S2 in the conveyance direction of the original sheet S1 is calculated to calculate the location with predetermined XY coordinates based on the edge of the sheet-like product S2 that is sequentially conveyed after cutting (in the example shown in FIG. 3, within each rectangle The time point when the location of the marked position information mark M) reaches the marking device 2. Furthermore, the control analysis device 4 may control the marking device 2 so that the transparent ink is ejected from the nozzle of the marking device 2 corresponding to the Y coordinate corresponding to the aforementioned predetermined XY coordinate at the above time point.

In addition, in this embodiment, the case where the position information marking step ST1, the cutting step ST2, and the recovery step ST3 are executed by a single manufacturing apparatus 100a (in other words, a single production line) is exemplified and explained. However, the present invention does not Limited to this. For example, the following aspect may also be adopted: after the position information marking step ST1 is executed, the original film S1 marked with the position information mark M is first wound up on a winding roller (not shown) and transported to another production line. to execute the cutting step ST2 and the recycling step ST3. In other words, the series of steps of the position information marking step ST1, the cutting step ST2, and the recycling step ST3 may be separated between the position information marking step ST1 and the cutting step ST2.

In addition, in the second to fifth embodiments, the case where the original image inspection step (ST21, ST31, ST41, ST51) and the position information marking step (ST22, ST32, ST42, ST52) are sequentially performed is given as an example. , but the present invention is not limited to this, it may also be adopted that the position information marking step is executed first, and then the original film checking step is executed.

In addition, in this embodiment, although the case where the analysis steps (ST14, ST26, ST36, ST46, ST56) are executed independently is taken as an example, the present invention is not limited to this, and the control analysis device 4 may also be used. It is configured to be able to execute at least two or more analysis steps described in each embodiment, and to select which analysis step to execute.

1: Check the device 2: Marking device 3: Cut off device 4: Control analysis device 5:Inspector 6: Reading device 11:Light source 12:Photography agency 13:Image processing mechanism 100:System 100a,100a': Manufacturing equipment A1,A2,A3,A4,A5: area CL: Cut off scheduled line F: Defect GI: original image L1,L2,L2',L3: separation distance M: location information token MA: match image MP: map image P:Period R1: Delivery roller R2: Nip roller R3: Conveyor S1, S1a, S1b, S1c, S1d: original film S2: sheet products S11: Unnecessary parts ST1, ST11, ST22, ST32, ST42, ST52: Location information marking steps ST2: Cutting step ST3: Recycling step ST12, ST24, ST34, ST44, ST54: Inspection steps for sheet products ST13, ST25, ST35, ST45, ST55: Reading steps ST14, ST26, ST36, ST46, ST56: Analysis steps ST21, ST31, ST41, ST51: Original film inspection steps ST23, ST33, ST43, ST53: Steps to establish association ST141, ST263, ST365: Map image generation program ST142, ST264, ST366: matching image generation program ST261, ST361, ST461, ST561: Combination of specific programs ST262, ST364, ST462, ST562: Extraction condition determination program ST362: Program ST363, ST463: indicator output program ST563: Judgment procedure TE: template image X,Y,Z: arrow X1:X coordinate Y1:Y coordinate

FIG. 1 is a diagram schematically showing the schematic structure of a system for executing an analysis method according to an embodiment of the present invention. FIG. 2 is a flowchart showing schematic steps of a method for manufacturing a sheet-like product using an analysis method according to an embodiment of the present invention. FIG. 3 is a diagram schematically explaining the state of the original sheet S1 and the sheet-like product S2 in the manufacturing method shown in FIG. 2 . FIG. 4 is a flowchart showing the schematic steps of the analysis method according to the first embodiment. FIG. 5 is a diagram schematically showing an example of a map image and a template image. FIG. 6 is a flowchart showing the schematic steps of the analysis method according to the second embodiment. FIG. 7 is a diagram schematically explaining the contents of the analysis step ST26 of the analysis method according to the second embodiment. FIG. 8 is a flowchart showing the schematic steps of the analysis method according to the third embodiment. FIG. 9 is a flowchart showing the schematic steps of the analysis method according to the fourth embodiment. FIG. 10 is a flowchart showing the schematic steps of the analysis method according to the fifth embodiment. FIG. 11 is a diagram showing the schematic structure of a manufacturing apparatus for executing an analysis method according to a modification of the present invention.

ST11: Location information marking steps

ST12: Inspection steps for sheet products

ST13: Reading steps

ST14: Analysis step

ST141: Map image generation program

ST142: Matching image generation program

Claims (9)

A method for analyzing the tendency of defect occurrence, which analyzes the tendency related to the occurrence of defects based on the defects that occur in a plurality of sheet-like products. The above-mentioned sheet-like products are: long original sheets wound into a roll shape. It is produced by feeding out, conveying and cutting it, or by successively feeding out, conveying and cutting the long original sheet wound into a roll shape into a large sheet-like intermediate body, and cutting the aforementioned intermediate body to produce it, The methods for analyzing the occurrence tendency of the aforementioned defects include: The position information marking step includes marking position information marks on the original sheet, the intermediate body, or a plurality of the sheet-like products before cutting or cutting out the intermediate body, so as to indicate the longitudinal direction of the original sheet. And the mark of the position information in the width direction, that is, the aforementioned position information mark, exists in each of the plurality of the aforementioned sheet products; The sheet product inspection step is to inspect a plurality of the aforementioned sheet products; The reading step is to read the aforementioned position information mark of the aforementioned sheet-like product whose defect has been detected in the aforementioned sheet-like product inspection step, thereby obtaining the aforementioned position information of the aforementioned sheet-like product in the aforementioned original piece; and The analysis step is to specify the position of the defect in the sheet product that has been detected in the sheet product inspection step in the original piece based on the position information of the sheet product in the original piece obtained in the reading step. The position information is used to analyze the tendency related to the occurrence of the defect based on the position information of the specified defect existing in the sheet-like product in the original sheet. For example, the method for analyzing the occurrence tendency of defects according to claim 1, wherein the aforementioned analysis steps include: The map image generating program generates a map image based on the location information of the specified defect existing in the sheet-like product in the original film. The map image depicts the location of the defect existing in the sheet-like product. an image of the location in the original film; and The matching image generation program performs pattern matching on the map image and a template image prepared in advance to generate a matching image as an image representing a tendency related to the occurrence of defects. The matching image is only An image depicting a position of the defect that matches the template image among the positions of the defect drawn on the map image is drawn. For example, the method for analyzing the occurrence tendency of defects in claim 1 further has: The original film inspection step is to inspect the aforementioned original film before cutting or cutting out the aforementioned intermediate body; and Establish a correlation step to combine the aforementioned location information of the defects in the original piece detected by the aforementioned original piece inspection step before cutting or cutting out the aforementioned intermediate body, the types of defects existing in the aforementioned original piece, and the detected defects. The execution place of the original film inspection step, which contains defects in the aforementioned original film, is associated with the aforementioned position information mark and is memorized. The aforementioned parsing steps include: Combining a specific program to determine the location information of the specified defect existing in the sheet-like product in the original sheet, and associate it with the location information mark read in the reading step to memorize the presence of the defect in the original sheet. Whether the aforementioned position information of the defect in the piece is consistent. If consistent, the type of defect existing in the original piece is identified and memorized in association with the aforementioned position information mark read in the aforementioned reading step, and the presence is detected. A combination of places where the aforementioned original film inspection steps are performed for defects in the aforementioned original film; The extraction condition determination program determines the extraction conditions based on the combination of the aforementioned types specified by the aforementioned combined specific program and the aforementioned execution location; The map image generating program is based on the location information of the defects in the original film that meet the extraction conditions determined by the extraction condition determination program among all the defects detected in the original image inspection step and based on the location information in the original image. Generate an image depicting the location of the defect in the original film, that is, a map image; and The matching image generation program performs pattern matching on the map image and a template image prepared in advance to generate a matching image as an image representing a tendency related to the occurrence of defects. The matching image is only An image depicting a position of the defect that matches the template image among the positions of the defect drawn on the map image is drawn. The defect generation tendency analysis method of claim 3, wherein in the combination specifying program, a plurality of the aforementioned types and the aforementioned plurality of the aforementioned sheet-like products are specified for each of the plurality of the aforementioned sheet-like products for which defects are detected in the aforementioned sheet-like product inspection step. combination of execution venues, In the aforementioned extraction condition determination program, a combination that is more than half of the plurality of combinations of the aforementioned types and the aforementioned execution locations specified by the aforementioned combination specifying program is determined as the aforementioned extraction condition. The defect generation tendency analysis method of claim 3, wherein in the combination specifying program, a plurality of the aforementioned types and the aforementioned plurality of the aforementioned sheet-like products are specified for each of the plurality of the aforementioned sheet-like products for which defects are detected in the aforementioned sheet-like product inspection step. combination of execution venues, In the extraction condition determination program, all combinations of the plurality of types and execution places specified by the combination specification program are determined as the extraction conditions. The defect generation tendency analysis method of claim 3, wherein in the combination specifying program, a plurality of the aforementioned types and the aforementioned plurality of the aforementioned sheet-like products are specified for each of the plurality of the aforementioned sheet-like products for which defects are detected in the aforementioned sheet-like product inspection step. combination of execution venues, The aforementioned analysis step has an index output program, and the aforementioned index output program is when the number of combinations of the plurality of aforementioned types and the aforementioned execution places specified in the aforementioned combination specific program is less than the aforementioned plurality of aforementioned sheet-like products, and the aforementioned sheet-like product inspection In the case where the total number of defects detected in the step is more than half, the aforementioned extraction condition determination program, the aforementioned map image generation program, and the aforementioned matching image generation program are not executed, but the cases that are less than half are regarded as indications and defects. To output indicators related to the generation of tendencies. For example, the method for analyzing the occurrence tendency of defects in claim 1 further has: The original film inspection step is to inspect the aforementioned original film before cutting or cutting out the aforementioned intermediate body; and Establishing a correlation step, the aforementioned position information of the defects existing in the aforementioned original piece before cutting or cutting out the aforementioned intermediate body, the types of defects existing in the aforementioned original piece, and the detected existence of the defects detected in the aforementioned original piece inspection step The execution place of the original film inspection step for defects in the aforementioned original film, and the manufacturing step history information of the aforementioned original film are associated with the aforementioned position information mark to memorize, The aforementioned parsing steps include: Combining a specific program to determine the location information of the specified defect existing in the sheet-like product in the original sheet, and associate it with the location information mark read in the reading step to memorize the presence of the defect in the original sheet. Whether the aforementioned position information of the defect in the piece is consistent. If they are consistent, the type of defect existing in the original piece is identified and memorized in association with the aforementioned position information mark read in the aforementioned reading step, and the type of defect present in the original piece is detected. A combination of the execution place of the original film inspection step and the manufacturing step process information of the aforementioned original film regarding defects in the aforementioned original film; The extraction condition determination program determines the extraction conditions based on the combination of the aforementioned types and the aforementioned execution locations specified by the aforementioned combined specific procedures; and The index output program specifies, among all the defects present in the original film that have been detected in the original film inspection step, the defects in the original film that meet the extraction conditions determined by the aforementioned extraction condition determination program in the aforementioned combination. The aforementioned manufacturing step history information specified by the step is output as an index indicating a tendency related to the occurrence of defects. The defect generation tendency analysis method of Claim 7, wherein in the combination specifying program, a plurality of the aforementioned types and the aforementioned plurality of the aforementioned sheet products are specified for each of the plurality of the aforementioned sheet-like products for which defects are detected in the aforementioned sheet-like product inspection step. combination of execution venues, In the aforementioned extraction condition determination program, a combination that is more than half of the plurality of combinations of the aforementioned types and the aforementioned execution locations specified by the aforementioned combination specifying program is determined as the aforementioned extraction condition. For example, the method for analyzing the occurrence tendency of defects in claim 1 further has: The original film inspection step is to inspect the aforementioned original film before cutting or cutting out the aforementioned intermediate body; and Establishing a correlation step, the aforementioned position information of the defects existing in the aforementioned original piece before cutting or cutting out the aforementioned intermediate body, the types of defects existing in the aforementioned original piece, and the detected existence of the defects detected in the aforementioned original piece inspection step The execution place of the original film inspection step for defects in the aforementioned original film, and the manufacturing step history information of the aforementioned original film are associated with the aforementioned position information mark to memorize, The aforementioned parsing steps include: Combining a specific program to determine the location information of the specified defect existing in the sheet-like product in the original sheet, and associate it with the location information mark read in the reading step to memorize the presence of the defect in the original sheet. Whether the aforementioned position information of the defect in the piece is consistent. If they are consistent, the type of defect existing in the original piece is identified and memorized in association with the aforementioned position information mark read in the aforementioned reading step, and the type of defect present in the original piece is detected. A combination of the execution place of the original film inspection step and the manufacturing step process information of the aforementioned original film regarding defects in the aforementioned original film; The extraction condition determination program determines the extraction conditions based on the combination of the aforementioned types and the aforementioned execution locations specified by the aforementioned combined specific procedures; and The judgment program performs judgment using a learning model as a judgment on the tendency related to the occurrence of defects, In the aforementioned determination process, among all the defects present in the aforementioned original film detected in the aforementioned original film inspection step, the defects existing in the aforementioned original film that meet the extraction conditions determined by the aforementioned extraction condition determination program are combined in the aforementioned combination. The aforementioned manufacturing step process information specified by the specific step is input to the aforementioned learning model, and a determination result is output from the aforementioned learning model as to whether a defect existing in the aforementioned original piece that meets the aforementioned extraction condition is detected as a defect of the aforementioned sheet-like product.

Images