Product Management Approach

Abstract

A product management method uses a computer to manage a membrane electrode structure (21) or a fuel cell stack manufactured through a joining process (S8), wherein the joining process (S8) is to join an electrode catalyst layer (25a, 26a) to a gas diffusion layer (25b, 26b) with a carbon paper substrate. The product management method includes: steps (S2, S5) of taking images of specific parts of each of a plurality of gas diffusion layers to obtain primary feature vector data, and storing each of the acquired primary feature vector data in a storage medium; and steps (S9, S11, S12) of comparing the feature vector data obtained by taking images of specific parts of the gas diffusion layer after these steps (S2, S5) with a management database stored in the storage medium.

Description

Technical Field

[0001] The present invention relates to a product management method, and more particularly to a product management method for managing products made of carbon paper using a computer. Background Art

[0002] A fuel cell cell is formed by sandwiching a membrane electrode structure (so-called membrane electrode assembly (MEA)) with a pair of diaphragms, and the membrane electrode structure is formed by arranging an electrolyte layer containing a solid polymer between an anode electrode body and a cathode electrode body. In addition, a fuel cell stack is formed by stacking a plurality of such fuel cell cells, and is mounted on a vehicle, for example, as a power source for generating power to supply to a drive motor.

[0003] However, the substrates of the anode electrode bodies and cathode electrode bodies constituting each fuel cell monomer mostly use carbon paper with conductivity and acid resistance. Therefore, multiple sheets of carbon paper are used in a fuel cell stack. Moreover, the performance of the fuel cell stack depends to a large extent on the performance of each piece of carbon paper. Therefore, in the manufacturing process of manufacturing a fuel cell stack, a management system is required to manage what kind of carbon paper is used in the cathode electrode body, the anode electrode body, the fuel cell monomer containing these electrode structures, or the fuel cell stack composed of stacking these fuel cell monomers.

[0004] [Prior Technical Literature]

[0005] (Patent Document)

[0006] Patent Document 1: Japanese Patent No. 6217614 Summary of the invention

[0007] [Problems to be solved by the invention]

[0008] For example, Patent Document 1 shows a management system that manages a fuel cell stack by installing an identifier printed with information related to its inspection results on the MEA. Therefore, in the process of manufacturing a fuel cell stack using this technology, it is possible to consider installing an identifier on carbon paper. However, in this case, since the identifier needs to be installed directly on the carbon paper, the portion of the carbon paper where the identifier is installed cannot be used for power generation, or the carbon paper may be damaged. In addition, in order to obtain information from the identifier, a dedicated reader is required, and management may become complicated.

[0009] The object of the present invention is to provide a product management method, which is a method for managing parts or products with carbon paper as a substrate, and can manage without damaging the carbon paper.

[0010] [Technical means to solve the problem]

[0011] (1) The product management method of the present invention manages a structure (e.g., the anode electrode body 25, the cathode electrode body 26, and the membrane electrode structure 21 described below) or a product having the structure as a part (e.g., the fuel cell monomer 2, the fuel cell stack 1 described below) manufactured through a material forming process (e.g., the joining process S8 described below) in which a material (e.g., the first electrode catalyst layer 25a and the second electrode catalyst layer 26a described below) is joined or coated on a workpiece having a carbon paper substrate (e.g., the carbon paper CA, CC and the first gas diffusion layer 25b and the second gas diffusion layer 26b described below), and the product management method is characterized in that it comprises: a registration process (e.g., the anode side initial registration process S2 and the cathode side initial registration process S5 described below) for each of a plurality of workpieces, capturing an image of a specific portion (e.g., the specific portion P, PA, PC described below) in a portion to which the material is not joined or coated, thereby acquiring primary workpiece data (e.g., the specific portion P, PA, PC described below) Figure 6 ), and storing the acquired primary workpiece data of each workpiece in a storage medium (for example, the storage medium 55 described later); and, a comparison process (for example, the unit management process S9, the unit inspection process S11, and the stack assembly / stack management process S12 described later), taking an image of the aforementioned specific part of the workpiece after the aforementioned registration process to obtain reference workpiece data, and comparing the reference workpiece data with the data stored in the aforementioned storage medium.

[0012] (2) In this case, it is preferable that the specific portion is a portion of a surface of the workpiece to which the material is not joined or applied (for example, second surfaces CAb and CCb described later).

[0013] (3) At this time, it is preferred that the product management method further includes an updating process (e.g., the monomer management process S9 described later), wherein the updating process is to capture an image of the specific portion of the workpiece after the registration process and the material forming process to obtain secondary workpiece data (e.g., Figure 6 The secondary feature vector data in the workpiece is compared with the multiple primary workpiece data stored in the storage medium, and the primary workpiece data with the highest degree of consistency is associated with the secondary workpiece data and stored in the storage medium.

[0014] (4) The product management method of the present invention manages an integrated electrode structure (e.g., MEA 21 described below) or a product using the integrated electrode structure as a component (e.g., fuel cell monomer 2 described below, fuel cell stack 1 described below), wherein the integrated electrode structure has an anode electrode body (e.g., anode electrode body 25 described below) in which an anode electrode material (e.g., first electrode catalyst layer 25 described below) is bonded or coated on a first gas diffusion layer (e.g., first gas diffusion layer 25b described below), and a cathode electrode material (e.g., second electrode catalyst layer 26a described below) is bonded or coated on a second gas diffusion layer (e.g., second gas diffusion layer 26b described below). The product management method is characterized in that it comprises: an anode side registration process (for example, an anode side initial registration process S2 described below), for each of the plurality of first gas diffusion layers, taking an image of a first specific portion (for example, a specific portion PA described below) in a portion not bonded to or not coated with the anode electrode material, thereby obtaining a first anode electrode data (for example, a specific portion PA described below). Figure 6 The primary feature vector data within the dotted line 6a) is obtained, and the primary anode electrode data of each first gas diffusion layer is stored in a storage medium (for example, the storage medium 55 described later); a cathode side registration process (for example, the cathode side initial registration process S5 described later) is performed to capture an image of a second specific portion (for example, the specific portion PC described later) in a portion that is not bonded or coated with the aforementioned cathode electrode material for each of the plurality of second gas diffusion layers, thereby obtaining the primary cathode electrode data (for example, the specific portion PC described later). Figure 6 The primary characteristic vector data within the dotted line 6b) is obtained, and the primary cathode electrode data of each second gas diffusion layer is stored in the aforementioned storage medium; and, a comparison process (for example, the later-described monomer management process S9, the monomer inspection process S11, and the stack assembly / stack management process S12) is to capture an image of the aforementioned first specific portion of the first gas diffusion layer that has undergone the aforementioned anode side registration process or the aforementioned second specific portion of the second gas diffusion layer that has undergone the aforementioned cathode side registration process, thereby obtaining reference electrode data, and comparing the reference electrode data with the data stored in the aforementioned storage medium.

[0015] (5) At this time, it is preferred that the aforementioned product management method also includes a monomer management process (for example, the monomer management process S9 described later), and the monomer management process is to establish an association between the primary anode electrode data of the first gas diffusion layer contained in the aforementioned integrated electrode structure and the primary cathode electrode data of the second gas diffusion layer contained in the integrated electrode structure and store them in the aforementioned storage medium.

[0016] (6) At this time, it is preferred that the aforementioned product management method also includes a stack management process (for example, the stack assembly / stack management process S12 described later), and the stack management process is to establish an association between the primary anode electrode data of each of the multiple first gas diffusion layers contained in a stacked body (for example, the fuel cell stack 1 described later) formed by stacking a plurality of the aforementioned integrated electrode structures and the primary cathode electrode data of each of the multiple second gas diffusion layers contained in the stacked body and store them in the aforementioned storage medium.

[0017] (Effects of the Invention)

[0018] (1) The patterns on the surface of the workpieces with carbon paper as the substrate are different. Taking advantage of this, in the registration process, an image of a specified specific part of each of the multiple workpieces is taken to obtain primary workpiece data, and the acquired primary workpiece data of each workpiece is stored in a storage medium. Moreover, in the comparison process, an image of a specific part of the workpiece after the registration process is taken to obtain reference workpiece data, and the reference workpiece data is compared with the data stored in the above-mentioned storage medium. Therefore, according to the product management method of the present invention, it is possible to determine what kind of workpiece is used in the workpiece after various processes are implemented, or in the product using the workpiece as a part. Moreover, in the product management method of the present invention, when performing the registration process and the comparison process, etc., only the image of the specific part of the workpiece is taken, so the workpiece will not be damaged, or even the performance of the parts and products will not be reduced. Moreover, in the product management method of the present invention, the specific part used to obtain the primary workpiece data and the reference workpiece data is determined as the part of the workpiece that is not bonded or coated with material. By determining the specific part at this position, it is possible to easily capture an image of the specific part of the workpiece after the material forming process, and further compare the obtained reference workpiece data with the primary workpiece data to determine the origin and characteristics of the workpiece.

[0019] (2) When a material is joined or coated on a workpiece using a processing method such as crimping and thermal transfer, the pattern on the surface of the workpiece will change due to this processing. However, the change in pattern caused by this processing is considered to be smaller on the surface where the material is not joined or coated than on the surface where the material is joined or coated. Therefore, in the product management method of the present invention, the specific portion is set as a portion of the surface of the workpiece where the material is not joined or coated and where the change in pattern caused by the processing is considered to be small. Therefore, according to the product management method of the present invention, the specific portion is determined at this position, thereby reducing the change in pattern of the specific portion before and after the material forming process, thereby improving the accuracy in the comparison process.

[0020] (3) As described above, the pattern of a specific part may sometimes change before and after the material forming process. Therefore, in the updating process, an image of a specific part of the workpiece after the registration process and the material forming process is taken to obtain secondary workpiece data, and this secondary workpiece data is compared with a plurality of primary workpiece data stored in the storage medium, and the primary workpiece data with the highest degree of consistency is associated with this secondary workpiece data and stored in the storage medium. In this way, the secondary workpiece data obtained after the material forming process is associated with the primary workpiece data obtained before the material forming process and stored in the storage medium, so that in the subsequent comparison process, the reference workpiece data can be compared with the latest secondary workpiece data, thereby further improving the accuracy of this comparison process.

[0021] (4) The surface patterns of the first gas diffusion layer or the second gas diffusion layer are different. Taking advantage of this, in the cathode side registration step, an image of a first specific portion of a portion not bonded or coated with a cathode electrode material is captured for each of the plurality of first gas diffusion layers, thereby obtaining primary cathode electrode data, and the acquired primary cathode electrode data of each first gas diffusion layer is stored in a storage medium. In the anode side registration step, an image of a second specific portion of a portion not bonded or coated with an anode electrode material is captured for each of the plurality of second gas diffusion layers, thereby obtaining primary anode electrode data, and the acquired primary anode electrode data of each second gas diffusion layer is stored in a storage medium. Furthermore, in the comparison step, an image of a first specific portion of a first gas diffusion layer that has passed the cathode side registration step or a second specific portion of a second gas diffusion layer that has passed the anode side registration step is captured, thereby obtaining reference electrode data, and the reference electrode data is compared with the data stored in the storage medium. Therefore, according to the product management method of the present invention, it is possible to determine what kind of gas diffusion layer is used in an integrated electrode structure having a pair of cathode electrode bodies and anode electrode bodies, or in a stacked body formed by stacking the integrated electrode structure. Moreover, in the product management method of the present invention, when performing the cathode side registration process, the anode side registration process, and the comparison process, etc., only the image of the specific part of the gas diffusion layer is taken, so that the gas diffusion layer is not damaged or the performance of the stacked body is not reduced. Moreover, in the product management method of the present invention, the specific part used to obtain the primary cathode electrode data, the primary anode electrode data, or the reference electrode data is determined to be a part of the gas diffusion layer that is not bonded or coated with the electrode material. The specific part is determined at such a position, so that the image of the specific part can be easily taken for the integrated electrode structure or the stacked body, and the reference electrode data obtained can be compared with the primary cathode electrode data or the primary anode electrode data to determine the origin and characteristics of the gas diffusion layer.

[0022] (5) In the monomer management process, the primary cathode electrode data of the first gas diffusion layer included in the integrated electrode structure including a pair of cathode electrode bodies and anode electrode bodies is associated with the primary anode electrode data of the second gas diffusion layer included in the same integrated electrode structure and stored in a storage medium. Thus, it is possible to determine the origin and characteristics of the gas diffusion layer used in the fuel cell monomer having the integrated electrode structure.

[0023] (6) In the stack management process, the primary cathode electrode data of each of the plurality of first gas diffusion layers included in the stacked body formed by stacking the integrated electrode structure is associated with the primary anode electrode data of each of the plurality of second gas diffusion layers included in the same stacked body and stored in the storage medium. Thus, it is possible to determine the origin and characteristics of the gas diffusion layer used in the fuel cell stack having the stacked body. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a diagram showing the structure of a fuel cell stack that is a management target of a product management method according to an embodiment of the present invention.

[0025] Figure 2 This is a diagram showing the structure of a management system used in the product management method.

[0026] Figure 3 It is a functional block diagram implemented in a computer.

[0027] Figure 4 This is a diagram showing the structure of the eigenvector calculation unit.

[0028] Figure 5 The diagram shows the steps of a manufacturing process of a fuel cell stack.

[0029] Figure 6 This is a diagram showing an example of a management database constructed in a storage medium.

[0030] Figure 7 This is a diagram showing an example of a specific location set in carbon paper.

[0031] Figure 8 This is a diagram showing an example of a specific location set in an MEA. DETAILED DESCRIPTION

[0032] The following is a description of a product management method according to an embodiment of the present invention with reference to the accompanying drawings. Figure 1The manufacturing process of the fuel cell stack 1 shown is performed, and the multiple fuel cell stacks 1 manufactured in this manufacturing process, the multiple fuel cell monomers 2 constituting these fuel cell stacks 1, the multiple membrane electrode structures 21 constituting these multiple fuel cell monomers 2, the multiple electrode bodies 25, 26 constituting these multiple membrane electrode structures 21, or the multiple gas diffusion layers 25b, 26b constituting these electrode bodies 25, 26, etc., which are made of carbon paper and described later, are managed as management objects, and their manufacturing numbers or origins, etc. are managed.

[0033] Figure 1 FIG. 1 is a diagram showing the structure of a fuel cell stack 1 which is a management target of the product management method of this embodiment. Figure 1 Only a part of the plurality of fuel cell cells 2 constituting the fuel cell stack 1 is shown in the figure.

[0034] The fuel cell unit 2 includes a membrane electrode assembly 21 (hereinafter referred to as "MEA 21"), and a first diaphragm 22 and a second diaphragm 23 that sandwich the MEA 21. The MEA 21 includes an electrolyte membrane 24 such as a perfluorosulfonic acid film as an ion exchange layer containing a solid polymer, an anode electrode body 25 provided on one surface of the electrolyte membrane 24, and a cathode electrode body 26 provided on the other surface of the electrolyte membrane 24.

[0035] The anode electrode body 25 is a porous body, and includes a first electrode catalyst layer 25a on one side facing the electrolyte membrane 24, and a first gas diffusion layer 25b stacked on the first electrode catalyst layer 25a. The cathode electrode body 26 is a porous body, and includes a second electrode catalyst layer 26a on the other side facing the electrolyte membrane 24, and a second gas diffusion layer 26b stacked on the second electrode catalyst layer 26a.

[0036] The first electrode catalyst layer 25a and the second electrode catalyst layer 26a include: catalyst particles (electrode catalysts) composed of catalyst metals such as platinum supported on a catalyst carrier made of carbon such as carbon black; and an ion-conductive polymer binder. In addition, the electrode catalyst may only include a catalyst metal such as platinum black without including a catalyst carrier.

[0037] The first gas diffusion layer 25b and the second gas diffusion layer 26b are sheets having a carbon paper substrate, for example. The first gas diffusion layer 25b is disposed so as to face the first diaphragm 22, and the second gas diffusion layer 26b is disposed so as to face the second diaphragm 23. For example, a carbon diaphragm is used as the first diaphragm 22 and the second diaphragm 23, but a metal diaphragm may be used instead.

[0038] An anode side gas flow channel 27 is formed on the surface of the first diaphragm 22 facing the first gas diffusion layer 25b, and the anode side gas flow channel 27 is connected to an anode side gas inlet connecting hole (not shown) for supplying the anode side gas and an anode side gas outlet connecting hole (not shown) for discharging the anode side gas.

[0039] A cathode side gas flow channel 28 is formed on the surface of the second membrane 23 facing the second gas diffusion layer 26b, and the cathode side gas flow channel 28 is connected to a cathode side gas inlet connecting hole (not shown) for supplying cathode side gas and a cathode side gas outlet connecting hole (not shown) for discharging the cathode side gas.

[0040] The fuel cell stack 1 is formed by stacking a plurality of fuel cell cells 2 as described above.

[0041] Figure 2 FIG. 1 is a diagram showing the structure of a management system S used in a product management method. The management system S is introduced into a fuel cell stack manufacturing process (see the following). Figure 5 ) in a part of a production line 3. The management system S comprises: a camera C for taking images of n (n is an integer greater than or equal to 2) workpieces W1, ..., Wn, etc., which are objects of management and flow on the production line 3; and a computer 5 installed with a program for processing the image data obtained by the camera C.

[0042] The n workpieces W1, ..., Wn flowing on the production line 3 are a fuel cell stack 1, a fuel cell monomer 2, a membrane electrode structure 21, an anode electrode body 25, a cathode electrode body 26, a first gas diffusion layer 25b, and a second gas diffusion layer 26b. These workpieces W1, ..., Wn include gas diffusion layers 25b, 26b with carbon paper as a substrate as a material. The pattern formed on the surface of the carbon paper varies from one individual to another. Therefore, in the management system S, the pattern of the carbon paper in a specific portion P predetermined for these workpieces W1, ..., Wn is used as an identifier to manage these workpieces W1, ..., Wn.

[0043] The camera C captures an image of a specific portion P of the workpieces W1 , . . . , Wn flowing on the production line 3 , and transmits the obtained image data to the computer 5 .

[0044] Figure 3This is a functional block diagram implemented in the computer 5 by a program installed in the computer 5. The computer 5 is provided with: a feature vector calculation unit 51, which calculates feature vector data representing the workpiece W based on the image data of the specific part P of the workpiece W photographed by the camera C; an initial registration unit 52, which associates the feature vector data calculated by the feature vector calculation unit 51 with various information representing the workpiece W (carbon sheet manufacturing number or inherent information described later) and stores them in a storage medium 55, thereby newly constructing a management database; and an update registration unit 53, which compares the feature vector data calculated by the feature vector calculation unit 51 with the management database stored in the storage medium 55, and updates the management database.

[0045] Figure 4 2 is a diagram showing the structure of the feature vector calculation unit 51. The feature vector calculation unit 51 includes, for example, 256 types of filters from the first filter F1 to the 256th filter F256. By using these filters, 256-dimensional vector data having 256 scalars from the first feature quantity to the 256th feature quantity as components is calculated based on the image data of the specific part P obtained by the camera C, that is, feature vector data. When the pixel values ​​of the image data representing the specific part P are respectively input, each filter F1 to F256 outputs the first feature quantity to the 256th feature quantity, which are integers within a specified range (for example, 0 to 99). Each filter F1 to F256 is composed of, for example, a four-layer neural network having a first layer, a second layer, a third layer, and a fourth layer, respectively.

[0046] The neural network constituting each filter F1 to F256 uses the following network, that is, a plurality of sheets of carbon paper are prepared as samples, and the network is pre-learned so that the appropriate sample can be identified based on the feature vector calculated from the image data of these samples. More specifically, a camera is used to capture images of a predetermined portion of a plurality of sheets of carbon paper prepared as samples at different times and environments, and learning image data and verification image data are acquired for each sample. Moreover, the neural network constituting each filter F1 to F256 is learned so that the degree of consistency between the feature vector data calculated using the learning image data prepared for each sample and the feature vector data calculated using the verification image data obtained by capturing each sample at different times and environments is evaluated, and the degree of consistency between the two feature vector data obtained from the same sample becomes the highest. Here, the degree of consistency between the two feature vector data can be digitized by calculating the norm value of the differential vector data whose components are the differences of the components of the two feature vector data. That is, the smaller the norm value of the differential vector data is, the higher the degree of consistency between the two feature vector data can be evaluated.

[0047] Figure 5The figure shows the steps of the manufacturing process of the fuel cell stack in which the product management method of the present embodiment is introduced. The manufacturing process of the fuel cell stack includes: an anode side trimming process S1, an anode side initial registration process S2, an anode side cleaning process S3, a cathode side trimming process S4, a cathode side initial registration process S5, a cathode side cleaning process S6, an electrode layer bonding process S7, a bonding process S8, a monomer management process S9, a monomer cleaning process S10, a monomer inspection process S11 and a stack assembly / stack management process S12.

[0048] In the anode side trimming step S1, a base paper roll RA1 of carbon paper prepared in advance for the first gas diffusion layer 25b of the anode electrode body 25 is fed out and cut by a trimming device (not shown) to thereby cut out a plurality of rectangular carbon papers CA. Figure 5 In the description, four sheets of carbon paper CA are cut out in a row along the width direction of the base paper roll RA1, but the present invention is not limited thereto. The plurality of sheets of carbon paper CA cut out from the base paper roll RA1 in the anode side trimming step S1 become the first gas diffusion layer 25b in the fuel cell stack 1.

[0049] In the anode side initial registration step S2, the management system S is used to register the information of each of the plurality of carbon papers CA cut out in the anode side trimming step S1, and a new system is constructed as follows: Figure 6 More specifically, in the anode side initial registration step S2, as shown in FIG. Figure 7 As shown, the camera C captures an image of a predetermined specific portion PA of each carbon paper CA. The specific portion PA is determined to be a portion of the carbon paper CA to which the anode electrode material is not bonded in the bonding step S8 described later. More specifically, the specific portion PA is set on a portion of the second surface CAb of the carbon paper CA that is opposite to the first surface CAa to which the anode electrode material is bonded in the bonding step S8.

[0050] Next, in the initial registration process S2 on the anode side, the feature vector calculation unit 51 calculates feature vector data based on the image data of the specific part PA captured by the camera C. Next, in the initial registration process S2 on the anode side, the initial registration unit 52 uses the feature vector data calculated one by one by the feature vector calculation unit 51 as primary feature vector data, and stores the primary feature vector data in the storage medium 55. Moreover, at this time, the initial registration unit 52 associates the primary feature vector data calculated one by one, the carbon sheet manufacturing number assigned to each of the carbon paper CA cut out in the anode side trimming process S1 in a prescribed order, and the inherent information inherent in the target carbon paper CA, and stores them in the storage medium 55. Here, the inherent information includes, for example, the manufacturing date of the carbon paper CA, the roll number assigned to each base paper roll RA1, and the cutting position of the carbon paper CA. Based on the above, in the initial registration process S2 on the anode side, Figure 6 The management database indicated by the middle dotted line 6 a is constructed in the storage medium 55 .

[0051] return Figure 5 In the anode side cleaning step S3, air is blown to the carbon paper CA that has passed through the anode side initial registration step S2, thereby removing dust and foreign matter attached to the carbon paper CA.

[0052] In the cathode side trimming step S4, a base paper roll RC1 of carbon paper prepared in advance for the second gas diffusion layer 26b of the cathode electrode body 26 is fed out and cut by a trimming device (not shown), thereby cutting out a plurality of rectangular carbon papers CC. Figure 5 In the description, four sheets of carbon paper CC are cut out in a row along the width direction of the base paper roll RC1, but the present invention is not limited thereto. The plurality of carbon paper CC cut out from the base paper roll RC1 in the cathode side trimming step S4 becomes the second gas diffusion layer 26b in the fuel cell stack 1.

[0053] In the cathode side initial registration step S5, the management system S is used to register the information of each of the plurality of carbon papers CC cut out in the cathode side trimming step S4, and a new system is constructed as follows: Figure 6 More specifically, in the cathode side initial registration step S5, as shown in FIG. Figure 7 As shown, the camera C captures an image of a predetermined specific portion PC of each carbon paper CC. The specific portion PC is determined to be a portion of the carbon paper CC that is not joined to the cathode electrode material in the joining step S8 described later. More specifically, the specific portion PC is set on a portion of the second surface CCb of the carbon paper CC that is opposite to the first surface CCa to which the cathode electrode material is joined in the joining step S8.

[0054] Next, in the cathode side initial registration process S5, the feature vector calculation unit 51 calculates feature vector data based on the image data of the specific part PC captured by the camera C. Next, in the cathode side initial registration process S5, the initial registration unit 52 uses the feature vector data calculated one by one by the feature vector calculation unit 51 as primary feature vector data, and stores the primary feature vector data in the storage medium 55. Moreover, at this time, the initial registration unit 52 associates the primary feature vector data calculated one by one, the carbon sheet manufacturing number assigned to each carbon paper CC cut out in the cathode side trimming process S4 in a prescribed order, and the inherent information inherent in the target carbon paper CC, and stores them in the storage medium 55. Here, the inherent information includes, for example, the manufacturing date of the carbon paper CC, the roll number assigned to each base paper roll RC1, or the cutting position of the carbon paper CC. Based on the above, in the cathode side initial registration process S5, Figure 6 The management database indicated by the middle dotted line 6 b is constructed in the storage medium 55 .

[0055] return Figure 5 In the cathode side cleaning step S6, air is blown to the carbon paper CC that has passed through the cathode side initial registration step S5, thereby removing dust and foreign matter attached to the carbon paper CC.

[0056] In the electrode layer bonding step S7, the anode electrode material cut out from the base paper roll RA2 of the anode electrode material prepared in advance for the first electrode catalyst layer 25a of the anode electrode body 25 and the cathode electrode material cut out from the base paper roll RC2 of the cathode electrode material prepared in advance for the second electrode catalyst layer 26a of the cathode electrode body 26 are bonded to both surfaces of the pre-prepared sheet-shaped electrolyte membrane 24 by, for example, thermal transfer. Thus, the first electrode catalyst layer 25a and the second electrode catalyst layer 26a are bonded to both surfaces of the electrolyte membrane 24, respectively.

[0057] In the joining process S8, the electrolyte membrane 24 joined with the electrode catalyst layer 25a and the second electrode catalyst layer 26a through the electrode layer joining process S7 is clamped and crimped by the carbon paper CA through the anode side cleaning process S3 and the carbon paper CC through the cathode side cleaning process S6. Thus, the carbon paper CA is joined to the first electrode catalyst layer 25a on its first surface CAa, and the carbon paper CC is joined to the second electrode catalyst layer 26a on its first surface CCa, thereby manufacturing the MEA 21 in which the electrolyte membrane 24 is clamped by the anode electrode body 25 and the cathode electrode body 26. As described above, the specific parts PA, PC are set on the second surfaces CAb, CCb of the carbon papers CA, CC. Thus, these specific parts PA, PC can also be visually confirmed from the outside in the MEA 21 manufactured through the joining process S8.

[0058] In the monomer management step S9, the management system S is used to register the information of each of the plurality of MEAs 21 manufactured through the bonding step S8. Figure 6 More specifically, in the monomer management step S9, as shown in FIG. Figure 8 As shown, camera C captures an image of a specific portion PA set in a portion other than a portion joined to the first electrode catalyst layer 25a in the first gas diffusion layer 25b constituting the MEA 21, and camera C captures an image of a specific portion PC set in a portion other than a portion joined to the second electrode catalyst layer 26a in the second gas diffusion layer 26b constituting the MEA 21.

[0059] Next, in the monomer management step S9, the feature vector calculation unit 51 calculates feature vector data based on the image data of the specific parts PA and PC taken by the camera C. Next, in the monomer management step S9, the update registration unit 53 uses the feature vector data calculated based on the image data of the specific part PA as secondary feature vector data, and compares the secondary feature vector data with the management database stored in the storage medium 55 to determine the carbon sheet manufacturing number of the first gas diffusion layer 25b constituting the target MEA 21. More specifically, the update registration unit 53 reads out a plurality of primary feature vector data included in the management database, extracts the primary feature vector data with the highest degree of consistency with the secondary feature vector data calculated based on the image data of the specific part PA from the plurality of primary feature vector data, and determines the carbon sheet manufacturing number associated with the primary feature vector data with the highest degree of consistency. Here, as described above, the degree of consistency of two feature vector data can be numerically expressed using the norm value of the difference vector data whose components are the differences of the components of the two feature vector data. That is, the closer the two feature vector data are, the smaller the norm value of the differential vector data is, and therefore, it can be determined that the combination with the smallest norm value has a high degree of consistency. In addition, the update registration unit 53 associates the secondary feature vector data calculated based on the image data of the specific part PA with the carbon sheet manufacturing number or the primary feature vector data determined as described above and stores them in the storage medium 55.

[0060] Moreover, the update registration unit 53 uses the feature vector data calculated based on the image data of the specific part PC as secondary feature vector data, and compares this secondary feature vector data with the management database stored in the storage medium 55, and uses the same steps as above to determine the carbon sheet manufacturing number of the second gas diffusion layer 26b constituting the target MEA21. Then, the update registration unit 53 associates the secondary feature vector data calculated based on the image data of the specific part PC with the carbon sheet manufacturing number or the primary feature vector data determined as described above and stores them in the storage medium 55. Moreover, when the update registration unit 53 stores the secondary feature vector data assigned to two groups of MEA 21 as described above in the storage medium 55, it associates these secondary feature vector data with the monomer manufacturing numbers assigned to each group of MEA21 manufactured in the joining process S8 in a prescribed order and stores them in the storage medium 55. Based on the above, in the monomer management process S9, Figure 6 The management database indicated by the middle dotted line 6 c is constructed in the storage medium 55 .

[0061] In addition, according to Figure 6 For example, the first gas diffusion layer with the carbon sheet manufacturing number "An*****1" is associated with the second gas diffusion layer with the carbon sheet manufacturing number "Ca*****1" which is assigned the same monomer manufacturing number "****1". Figure 6 For example, it can be determined that the MEA with the monomer manufacturing number "****1" is assembled with the carbon sheet with the carbon sheet manufacturing number "An*****1" as the first gas diffusion layer and the carbon sheet with the carbon sheet manufacturing number "Ca*****1" as the second gas diffusion layer. Figure 6 As shown, there is some deviation between the primary feature vector data and the secondary feature vector data associated therewith. This deviation is caused by the fact that the pattern in the specific parts PA and PC of the carbon sheet changes due to the anode side cleaning process, cathode side cleaning process and bonding process, etc., during the period from the acquisition of the primary feature vector data to the acquisition of the secondary feature vector data. Therefore, when comparing the feature vector data calculated based on the image taken by the camera C in the process after the monomer management process with the management database, it is preferable to calculate the consistency between the newly acquired feature vector data and the secondary feature vector data that is considered to reflect the latest state of the carbon paper.

[0062] return Figure 5 In the monomer cleaning step S10 , air is blown to the MEA 21 that has passed through the monomer management step S9 , thereby removing dust, foreign matter, and the like attached to the MEA 21 .

[0063] In the monomer inspection process S11, various inspections are performed on the MEA 21 that has passed the monomer cleaning process S10 to determine whether sufficient performance is ensured. Moreover, in the monomer inspection process S11, the management system S is used to register information related to the results of this inspection and update the management database. More specifically, in the monomer inspection process S11, the camera C captures an image of a specific part PA of the MEA 21 that has passed the monomer cleaning process S10. The feature vector calculation unit 51 calculates feature vector data based on the image data of the specific part PA. Moreover, the update registration unit 53 compares the feature vector data calculated based on the image data of the specific part PA with the management database stored in the storage medium 55, and determines the monomer manufacturing number associated with the secondary feature vector data that has the highest degree of consistency with this feature vector data. Moreover, the update registration unit 53 associates the information related to the inspection results described above with the monomer manufacturing number determined as described above and stores it in the storage medium 55. Based on the above, in the monomer inspection process S11, Figure 6 The management database indicated by the middle dotted line 6 d is constructed in the storage medium 55 .

[0064] In addition, according to Figure 6 For example, it can be determined that the MEA with the monomer manufacturing number "****1" is assembled by using the carbon sheet with the carbon sheet manufacturing number "An*****1" as the first gas diffusion layer and the carbon sheet with the carbon sheet manufacturing number "Ca*****1" as the second gas diffusion layer, and its inspection results are: the result of inspection A is "aa points", the result of inspection B is "ba points", and the result of inspection C is "ca points".

[0065] In the stack assembly / stack management step S12, m (m is an integer greater than or equal to 2) MEAs 21 are selected from the plurality of MEAs 21 that have passed the unit inspection step S11, and the selected m MEAs 21 are stacked to assemble the fuel cell stack 1. In addition, in this stack assembly / stack management step S12, the management system S is used to register information related to the fuel cell stack 1, such as Figure 6 As illustrated, the management database is updated.

[0066] More specifically, in the stack assembly / stack management process S12, a camera C is used to capture images of the specific parts PA of each of the m MEAs 21 selected for assembling a group of fuel cell stacks 1. The feature vector calculation unit 51 calculates feature vector data based on the image data of the specific parts PA of these m MEAs 21. The update registration unit 53 compares the feature vector data calculated based on the image data of the specific parts PA of these multiple MEAs 21 with the management database stored in the storage medium 55, and determines the monomer manufacturing number associated with the secondary feature vector data with the highest degree of consistency with each feature vector data. Moreover, the update registration unit 53 associates the stack manufacturing numbers assigned to the fuel cell stacks 1 assembled in the stack assembly / stack management process S12 in a prescribed order, and the layer numbers corresponding to the positions of the MEAs 21 as the objects inserted in a group of fuel cell stacks 1 with the monomer manufacturing numbers determined as described above, and stores them in the storage medium 55. Based on the above, in the stack assembly / stack management process S12, Figure 6 The management database indicated by the middle dotted line 6 e is constructed in the storage medium 55 .

[0067] In addition, according to Figure 6 For example, it can be determined that the fuel cell stack with the stack manufacturing number "***1" uses the MEA with the single manufacturing number "****1" and the MEA with the single manufacturing number "****2". Figure 6 For example, it can also be determined that, in the fuel cell stack with the stack manufacturing number "***1", the MEA with the monomer manufacturing number "****1" is used as the "a1th layer", and the MEA with the monomer manufacturing number "****2" is used as the "a2th layer".

[0068] Although one embodiment of the present invention has been described above, the present invention is not limited thereto, and the detailed structure may be appropriately changed within the scope of the gist of the present invention.

[0069] For example, in the above embodiment, the case where the anode electrode body 25 and the cathode electrode body 26 are manufactured by bonding the first gas diffusion layer 25b and the second gas diffusion layer 26b to the first electrode catalyst layer 25a and the second electrode catalyst layer 26a, respectively, is described, but the present invention is not limited thereto. The anode electrode body 25 and the cathode electrode body 26 may be manufactured by coating the first electrode catalyst layer 25a and the second electrode catalyst layer 26a on the first gas diffusion layer 25b and the second gas diffusion layer 26b.

[0070] Reference numerals

[0071] S: Management System

[0072] C: Camera

[0073] 1: Fuel cell stack (product)

[0074] 2: Fuel cell monomer (product)

[0075] 21: MEA (structure)

[0076] 24: Electrolyte membrane (ion exchange layer)

[0077] 25: Anode electrode body (structure, anode electrode body)

[0078] 25a: First electrode catalyst layer (material, anode electrode material)

[0079] 25b: First gas diffusion layer (workpiece, first gas diffusion layer)

[0080] 26: Cathode electrode body (structure, cathode electrode body)

[0081] 26a: Second electrode catalyst layer (material, cathode electrode material)

[0082] 26b: Second gas diffusion layer (workpiece, second gas diffusion layer)

[0083] 5: Computer

[0084] 51: Eigenvector calculation unit

[0085] 52: Initial Registration Department

[0086] 53: Update registration department

[0087] 55: Storage Media

[0088] CA, CC: Carbon paper (workpiece)

Claims

1. A product management method, using a computer to manage a structure or a product having the structure as a part manufactured through a material forming process, wherein the material forming process is to join or coat a material on a workpiece having a carbon paper as a substrate, wherein the product management method is characterized by comprising: A registration step of capturing an image of a specific portion of each of the plurality of workpieces in a portion not bonded or coated with the aforementioned material, thereby acquiring primary workpiece data, and associating the acquired primary workpiece data of each workpiece with information inherent in each workpiece and storing the data in a storage medium; and a comparison step of capturing an image of the specific portion of the workpiece after the registration step to obtain reference workpiece data, and comparing the reference workpiece data with the data stored in the storage medium to determine information associated with the primary workpiece data having the highest degree of consistency with the reference workpiece data; The specific portion is a portion of the surface of the workpiece that is not joined or coated with the material.

2. The product management method according to claim 1, wherein: It also includes an updating process, wherein the updating process is to obtain secondary workpiece data by photographing an image of the aforementioned specific portion of the workpiece after the aforementioned registration process and the aforementioned material forming process, and to compare the secondary workpiece data with a plurality of primary workpiece data stored in the aforementioned storage medium, and to associate the primary workpiece data with the highest degree of consistency with the aforementioned secondary workpiece data and store them in the aforementioned storage medium.

3. A product management method for managing an integrated electrode structure or a product using the integrated electrode structure as a component, wherein the integrated electrode structure comprises an anode electrode body having an anode electrode material bonded or coated on a first gas diffusion layer, a cathode electrode body having a cathode electrode material bonded or coated on a second gas diffusion layer, and an ion exchange layer sandwiched between the anode electrode body and the cathode electrode body, wherein the product management method comprises: an anode-side registration step of capturing an image of a first specific portion of each of the plurality of first gas diffusion layers, which is determined to be a portion not bonded or coated with the anode electrode material, thereby acquiring primary anode electrode data, and associating the acquired primary anode electrode data of each first gas diffusion layer with information inherent in each first gas diffusion layer and storing the data in a storage medium; A cathode side registration step, for each of the plurality of second gas diffusion layers, photographing an image of a second specific portion determined to be a portion not bonded or coated with the aforementioned cathode electrode material, thereby acquiring primary cathode electrode data, and associating the acquired primary cathode electrode data of each second gas diffusion layer with information inherent in each second gas diffusion layer and storing the data in the aforementioned storage medium; and, A comparison process is to capture an image of the first specific portion of the first gas diffusion layer that has undergone the anode side registration process or the second specific portion of the second gas diffusion layer that has undergone the cathode side registration process, thereby obtaining reference electrode data, and comparing the reference electrode data with the data stored in the storage medium to determine information associated with the primary anode electrode data or the primary cathode electrode data that has the highest degree of consistency with the reference electrode data.

4. The product management method according to claim 3, wherein: The method further includes a monomer management step of associating primary anode electrode data of a first gas diffusion layer included in the integrated electrode structure with primary cathode electrode data of a second gas diffusion layer included in the integrated electrode structure and storing the data in the storage medium.

5. The product management method according to claim 3 or 4, wherein: It also includes a stack management process, which is to establish an association between the primary anode electrode data of each of the multiple first gas diffusion layers contained in a stacked body formed by stacking multiple of the above-mentioned integrated electrode structures and the primary cathode electrode data of each of the multiple second gas diffusion layers contained in the stacked body and store them in the above-mentioned storage medium.

Images