Image Recognition-Based Method and Apparatus for Detecting Fuel Cell Bipolar Plate Coatings

Abstract

This application relates to the field of fuel cell bipolar plate coating inspection, and discloses a method and apparatus for fuel cell bipolar plate coating inspection based on image recognition. The method includes: determining the flow channel region corresponding to the flow channel on the fuel cell bipolar plate in the bipolar plate image, and determining the flow channel central axis in the flow channel region; dividing the flow channel region into two inspection regions through the flow channel central axis, determining the flow channel coating uniformity corresponding to the two inspection regions respectively, and determining the flow channel coating uniformity difference between the flow channel coating uniformity corresponding to the two inspection regions respectively; when the flow channel coating uniformity difference is greater than or equal to a preset flow channel coating uniformity difference value, the coating uniformity of the fuel cell bipolar plate is determined to be unqualified; when the flow channel coating uniformity difference is less than the preset flow channel coating uniformity difference value, the coating uniformity of the fuel cell bipolar plate is determined to be qualified. This application can detect the coating uniformity on fuel cell bipolar plates through image recognition.

Description

Technical Field

[0001] This application relates to the field of fuel cell bipolar plate coating detection technology, and more specifically, to a fuel cell bipolar plate coating detection method and apparatus based on image recognition. Background Technology

[0002] Fuel cell bipolar plates are key components in fuel cell stacks. Their primary function is to guide reactant gases (such as hydrogen and oxygen) and provide electrical current. The structure of a fuel cell metal bipolar plate typically consists of a substrate and a coating. Common substrate materials include stainless steel or titanium. Because stainless steel is susceptible to corrosion in acidic environments and is not resistant to high electrical potentials, the corrosion-resistant conductive coating applied to stainless steel bipolar plates is particularly important.

[0003] The primary function of the coating on the bipolar plate is to provide corrosion protection, improve conductivity, and reduce contact resistance. Commonly used coating types include conductive polymer coatings (e.g., polyaniline and poly3,4-ethylenedioxythiophene), noble metal coatings (e.g., platinum and gold), ceramic coatings (e.g., indium tin oxide), and non-noble metal coatings (e.g., non-noble metal carbon-based coatings). The uneven flow channels on the fuel cell bipolar plate cause uneven light reflection and scattering in the area where the channels are located, making it difficult to detect the coating uniformity on the fuel cell bipolar plate using image recognition. Summary of the Invention

[0004] The purpose of this application is to provide a method and apparatus for detecting coating uniformity on fuel cell bipolar plates based on image recognition, which solves the technical problem of difficulty in detecting coating uniformity on fuel cell bipolar plates through image recognition, and achieves the technical effect of detecting coating uniformity on fuel cell bipolar plates.

[0005] This application provides an image recognition-based method for detecting the coating of a fuel cell bipolar plate. The method includes: acquiring an image of a fuel cell bipolar plate with flow channels; determining the flow channel region corresponding to the flow channels on the fuel cell bipolar plate in the bipolar plate image; determining the flow channel central axis in the flow channel region; dividing the flow channel region into two detection regions through the flow channel central axis; determining the flow channel coating uniformity corresponding to the two detection regions respectively; and determining the flow channel coating uniformity difference between the flow channel coating uniformity of the two detection regions respectively; when the flow channel coating uniformity difference is greater than or equal to a preset flow channel coating uniformity difference value, determining that the coating uniformity of the fuel cell bipolar plate is unqualified; when the flow channel coating uniformity difference is less than the preset flow channel coating uniformity difference value, determining that the coating uniformity of the fuel cell bipolar plate is qualified.

[0006] In one possible implementation, the method further includes: determining multiple straight-segment flow channel regions within the flow channel region; dividing each straight-segment flow channel region into two straight-segment detection regions via the flow channel central axis; determining the uniformity of the straight-segment flow channel coating corresponding to the two straight-segment detection regions of each straight-segment flow channel region; and determining the difference in the uniformity of the straight-segment flow channel coating corresponding to the two straight-segment detection regions of each straight-segment flow channel region; when at least one difference in the uniformity of the straight-segment flow channel coating is greater than or equal to a preset difference in the uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the difference in the uniformity of the coating of each straight-segment flow channel is less than the preset difference in the uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0007] In another possible implementation, the method further includes: determining the uniformity of the coating of the straight-segment flow channel from two straight-segment detection areas from two different straight-segment flow channel regions, and determining the difference between the uniformity of the coating of the straight-segment flow channel from the two straight-segment detection areas from two different straight-segment flow channel regions as the cross difference value of the uniformity of the coating of the straight-segment flow channel; wherein the two straight-segment detection areas from two different straight-segment flow channel regions are located on the same side of the flow channel; when at least one cross difference value of the uniformity of the coating of the straight-segment flow channel is greater than or equal to a preset cross difference value of the uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is determined to be unqualified; when all cross differences value of the uniformity of the flow channel coating is less than the preset cross difference value of the uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is determined to be qualified.

[0008] In another possible implementation, the method further includes: identifying multiple curved flow channel regions within the flow channel region; dividing each curved flow channel region into two curved flow channel detection regions via the flow channel central axis; determining the uniformity of the curved flow channel coating corresponding to the two curved flow channel detection regions of each curved flow channel region; and determining the difference in the uniformity of the curved flow channel coating corresponding to the two curved flow channel detection regions of each curved flow channel region; when at least one curved flow channel coating uniformity difference is greater than or equal to a preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the uniformity difference of the coating of each curved flow channel is less than the preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0009] In another possible implementation, the method further includes: dividing each straight segment flow channel region into multiple sub-straight segment flow channel regions, identifying a first sub-straight segment flow channel region located in the middle of the straight segment flow channel region, and obtaining a first curved segment flow channel region at the end of the straight segment flow channel region where the first sub-straight segment flow channel region is located; dividing the first sub-straight segment flow channel region into two first sub-straight segment detection regions through the flow channel centerline, dividing the first curved segment flow channel region into two first curved segment detection regions through the flow channel centerline, and identifying two first sub-straight segment detection regions. The coating uniformity of the first sub-straight segment and the coating uniformity of the first curved segment corresponding to the two first curved segment detection areas are respectively determined, and the difference between the coating uniformity of the first sub-straight segment detection area and the coating uniformity of the first curved segment detection area located on the same side of the flow channel is determined; when the difference between the first sub-coating uniformity is greater than or equal to the preset difference between the first sub-coating uniformity, the coating uniformity of the fuel cell bipolar plate is determined to be unqualified; when all the differences between the first sub-coating uniformity are less than the preset difference between the first sub-coating uniformity, the coating uniformity of the fuel cell bipolar plate is determined to be qualified.

[0010] In another possible implementation, the method further includes: determining the planar regions at the four corners of the fuel cell bipolar plate in the bipolar plate image, excluding the flow channels, and determining the planar coating uniformity of the planar regions, and determining the planar coating uniformity difference between different planar coating uniformities; when the planar coating uniformity difference is greater than or equal to a preset planar coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when all planar coating uniformity differences are less than the preset planar coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0011] This application also provides an image recognition-based fuel cell bipolar plate coating uniformity evaluation device, including a unit for performing the method described in any of the above embodiments.

[0012] This application also provides an image recognition-based fuel cell bipolar plate coating uniformity evaluation device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in any of the preceding claims.

[0013] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0014] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the preceding claims.

[0015] The beneficial effects of the embodiments in this application compared with the prior art are:

[0016] This application provides an image recognition-based method for detecting the coating of a fuel cell bipolar plate. The method includes: acquiring an image of a fuel cell bipolar plate with flow channels; determining the flow channel region corresponding to the flow channels on the fuel cell bipolar plate in the bipolar plate image; determining the flow channel central axis within the flow channel region; dividing the flow channel region into two detection regions along the flow channel central axis; determining the flow channel coating uniformity corresponding to each of the two detection regions; and determining the flow channel coating uniformity difference between the two detection regions. When the flow channel coating uniformity difference is greater than or equal to a preset flow channel coating uniformity difference value, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the flow channel coating uniformity difference is less than the preset flow channel coating uniformity difference value, the coating uniformity of the fuel cell bipolar plate is deemed qualified. This image recognition-based fuel cell bipolar plate coating detection method can accurately detect the coating uniformity in the flow channel region, avoiding inaccurate coating uniformity detection caused by uneven light reflection and scattering in the flow channel region, thus improving the accuracy of the uniformity detection and evaluation of the fuel cell bipolar plate coating. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic flowchart illustrating an image recognition-based method for detecting bipolar plate coatings in fuel cells, provided in an embodiment of this application;

[0019] Figure 2 A schematic diagram illustrating the working process of the first image recognition-based fuel cell bipolar plate coating detection method provided in this application embodiment;

[0020] Figure 3 A schematic diagram of the cross-sectional structure of a fuel cell bipolar plate provided in an embodiment of this application;

[0021] Figure 4 A schematic flowchart of the second image recognition-based fuel cell bipolar plate coating detection method provided in this application embodiment;

[0022] Figure 5 A schematic flowchart illustrating the third image recognition-based fuel cell bipolar plate coating detection method provided in this application embodiment;

[0023] Figure 6 A schematic diagram of the logic structure of a fuel cell bipolar plate coating uniformity evaluation device based on image recognition provided in an embodiment of this application;

[0024] Figure 7 This is a schematic diagram of the physical structure of a fuel cell bipolar plate coating uniformity evaluation device based on image recognition, provided in an embodiment of this application. Detailed Implementation

[0025] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0026] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0027] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0028] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0030] Because the flow channels on the bipolar plates of fuel cells are uneven, the area where the flow channels are located will cause uneven reflection and scattering of light, making it difficult to detect the uniformity of the coating on the bipolar plates of fuel cells through image recognition.

[0031] Based on the above reasons, this application provides an image recognition-based method for detecting the coating of a fuel cell bipolar plate. The method includes: acquiring an image of a fuel cell bipolar plate with flow channels; determining the flow channel region corresponding to the flow channels on the fuel cell bipolar plate in the bipolar plate image; determining the flow channel central axis within the flow channel region; dividing the flow channel region into two detection regions via the flow channel central axis; determining the flow channel coating uniformity corresponding to each of the two detection regions; and determining the flow channel coating uniformity difference between the two detection regions; when the flow channel coating uniformity difference is greater than or equal to a preset flow channel coating uniformity difference value, determining that the coating uniformity of the fuel cell bipolar plate is unqualified; when the flow channel coating uniformity difference is less than the preset flow channel coating uniformity difference value, determining that the coating uniformity of the fuel cell bipolar plate is qualified. The image recognition-based fuel cell bipolar plate coating detection method in this application embodiment can accurately detect the uniformity of the coating in the flow channel area, avoiding inaccurate coating uniformity detection caused by uneven light reflection and scattering in the flow channel area, and improving the accuracy of uniformity detection and evaluation of fuel cell bipolar plate coating.

[0032] In some scenarios, the image recognition-based fuel cell bipolar plate coating detection method of this application embodiment can be applied to the coating uniformity detection of various fuel cell bipolar plates, which can improve the accuracy of fuel cell bipolar plate coating uniformity detection.

[0033] The following describes in detail, with specific examples, a fuel cell bipolar plate coating detection method based on image recognition provided in the embodiments of this application.

[0034] Figure 1 A flowchart illustrating an image recognition-based method for detecting bipolar plate coatings in fuel cells, as provided in this application embodiment, is shown below. Figure 1 As shown, this method includes S110 to S130, and S110 to S130 will be described in detail below.

[0035] S110. Obtain a bipolar plate image of a fuel cell bipolar plate with a flow channel, determine the flow channel region corresponding to the flow channel on the fuel cell bipolar plate in the bipolar plate image, and determine the flow channel centerline in the flow channel region.

[0036] Figure 2 A schematic diagram illustrating the working process of the first image recognition-based fuel cell bipolar plate coating detection method provided in this application embodiment is shown below. Figure 2As shown, the method in this embodiment can first illuminate the bipolar plate of the fuel cell directly, and then acquire an image 1 of the bipolar plate with flow channels using a high-precision CCD camera. Then, the coating uniformity of the bipolar plate image 1 can be detected.

[0037] When performing coating uniformity testing on bipolar plates, the flow channel region 11 corresponding to the flow channel on the fuel cell bipolar plate in bipolar plate image 1 can be determined, and the flow channel central axis 111 can be determined in the flow channel region 11. Then, the coating uniformity of the flow channel on the fuel cell bipolar plate can be tested using the flow channel central axis 111 as the standard.

[0038] For example, when determining the flow channel region 11 corresponding to the flow channel on the bipolar plate of the fuel cell in the bipolar plate image 1, the outline of the flow channel region 11 can be identified in the bipolar plate image 1 by image recognition, thereby realizing the identification of the flow channel region 11.

[0039] For example, when determining the flow channel centerline 111 in the flow channel region 11, the centerlines of the two contours of the flow channel region 11 can be identified as the flow channel centerline 111. Figure 2 In the middle, the central axis 111 of the flow channel is represented by a dotted line.

[0040] S120. Divide the flow channel area into two detection areas through the flow channel centerline, determine the flow channel coating uniformity corresponding to the two detection areas respectively, and determine the flow channel coating uniformity difference between the two detection areas respectively.

[0041] When performing coating uniformity testing, the flow channel region 11 can be divided into two testing regions 112 through the flow channel central axis 111. The two testing regions 112 are distributed on both sides of the flow channel central axis 111. Since the two testing regions 112 reflect and scatter light in different directions, the coating uniformity can be tested separately for the two testing regions 112 to avoid coating uniformity errors caused by different light reflection and scattering directions.

[0042] Figure 3 This is a schematic diagram of the cross-sectional structure of a fuel cell bipolar plate provided in an embodiment of this application, as shown below. Figure 3 As shown, the bipolar plate 1a is provided with a flow channel 11a. The flow channel 11a is divided into two flow channel sidewalls 112a corresponding to two detection areas 112 by the flow channel central axis 111. Since the two flow channel sidewalls 112a of the flow channel 11a have different characteristics in terms of the change of light reflection and scattering direction, it may lead to poor coating uniformity detection effect of the flow channel 11a as a whole when the flow channel 11a is used as a whole.

[0043] When performing uniformity testing on the flow channel region 11, the uniformity of the flow channel coating corresponding to the two test regions 112 can be determined. The uniformity of the flow channel coating corresponding to each test region 112 characterizes the coating uniformity of that test region 112. Furthermore, the difference in flow channel coating uniformity between the two test regions 112 can be determined, and the difference in flow channel coating uniformity can be used to evaluate the coating uniformity difference between the two test regions 112.

[0044] For example, when determining the uniformity of the flow channel coating corresponding to each detection area 112, the pixel value of each pixel of the image corresponding to the detection area 112 can be determined, and the variance of the pixel values ​​of all pixels in the detection area 112 can be used as the uniformity of the flow channel coating corresponding to the detection area 112.

[0045] For example, when determining the uniformity of the channel coating, the average value of all pixel values ​​in the detection area 112 can be calculated first as the reference pixel value of the area. Then, the deviation between each pixel value and the reference pixel value can be calculated, and all deviation values ​​can be added together and divided by the total number of pixels to obtain the average deviation. The smaller the average deviation, the more uniform the coating is; the larger the average deviation, the less uniform the coating is.

[0046] S130. When the difference in uniformity of the flow channel coating is greater than or equal to the preset difference in uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is deemed unqualified. When the difference in uniformity of the flow channel coating is less than the preset difference in uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0047] When evaluating the uniformity of the flow channel coating, if the difference in the uniformity of the flow channel coating is greater than or equal to the preset difference in the uniformity of the flow channel coating, it indicates that the difference between the uniformity of the flow channel coating corresponding to the two detection areas 112 is too large. This indicates that the uniformity of the coating on both sides of the central axis of the bipolar plate is too large, and thus it can be determined that the uniformity of the coating of the fuel cell bipolar plate is unqualified.

[0048] When the difference in uniformity of the flow channel coating is less than the preset difference in uniformity of the flow channel coating, it indicates that the difference between the uniformity of the flow channel coating corresponding to the two detection areas 112 is small, indicating that the difference in uniformity of the coating on both sides of the central axis of the bipolar plate is small, and thus it can be determined that the uniformity of the coating of the fuel cell bipolar plate is qualified.

[0049] For example, the preset channel coating uniformity difference can be 10 to 20.

[0050] The beneficial effect of the above implementation is that, since the two sidewalls of the flow channel have different characteristics in terms of the change of light reflection and scattering direction, it may lead to poor coating uniformity detection effect when the flow channel is detected as a whole. The method in this embodiment can determine the flow channel coating uniformity corresponding to the two detection areas respectively, and determine the flow channel coating uniformity difference between the two detection areas respectively, and judge the coating uniformity based on the flow channel coating uniformity difference, thereby realizing accurate detection of flow channel coating uniformity.

[0051] The beneficial effect of the above implementation method is that the coating uniformity of the bipolar plate is evaluated by using the difference in the uniformity of the coating in the two detection areas in the flow channel, and the coating uniformity in the flow channel is used as a key indicator to evaluate the coating uniformity of the bipolar plate, thereby improving the detection effect of the coating uniformity of the bipolar plate.

[0052] The beneficial effect of the above implementation method is that the coating uniformity at the flow channel has an important impact on the performance of the bipolar plate. By focusing on evaluating the coating uniformity at the flow channel, the production quality of the bipolar plate is improved.

[0053] In some implementations, the above method also includes S210 to S220, which will be described in detail below.

[0054] S210. Determine multiple straight-segment flow channel regions in the flow channel region, divide each straight-segment flow channel region into 2 straight-segment detection regions through the flow channel centerline, determine the uniformity of the straight-segment flow channel coating corresponding to the 2 straight-segment detection regions of each straight-segment flow channel region, and determine the difference in the uniformity of the straight-segment flow channel coating corresponding to the 2 straight-segment detection regions of each straight-segment flow channel region.

[0055] Figure 4 A schematic flowchart of the second image recognition-based fuel cell bipolar plate coating detection method provided in this application embodiment is shown below. Figure 4 As shown, when evaluating the coating uniformity, multiple straight-segment flow channels can be identified in the flow channel region. These multiple straight-segment flow channels can include straight-segment flow channel region 1101, straight-segment flow channel region 1102, straight-segment flow channel region 1103, straight-segment flow channel region 1104, etc., and then the coating uniformity of the bipolar plate can be detected based on these multiple straight-segment flow channels.

[0056] For example, such as Figure 4 As shown, when identifying multiple straight-segment flow channel regions through image recognition, curved flow channels can be segmented in flow channel region 11 through image recognition to obtain multiple straight-segment flow channel regions.

[0057] like Figure 4 As shown, for each straight-segment flow channel region, each straight-segment flow channel region can be divided into two straight-segment detection regions through the flow channel centerline. For example, the straight-segment flow channel region 1101 can be divided into two straight-segment detection regions 1101b through the flow channel centerline 1101a. Since the two straight-segment detection regions 1101b have different reflection and scattering conditions for light, the coating uniformity can be evaluated by separately evaluating the two straight-segment detection regions 1101b.

[0058] During operation, the coating uniformity of the two straight-segment detection areas 1101b corresponding to each straight-segment flow channel region 1101b can be determined separately. The coating uniformity of the straight-segment flow channel corresponding to each straight-segment detection area 1101b is used to evaluate the coating uniformity of each straight-segment detection area 1101b. The influence of different characteristics of light reflection and scattering in the curved section of the flow channel is eliminated. The straight-segment flow channels have the same light reflection and scattering characteristics, and the light reflection and scattering characteristics of the straight-segment detection areas are the same. Therefore, the coating uniformity difference of the two straight-segment detection areas corresponding to each straight-segment flow channel region can be determined. Then, the coating uniformity of the bipolar plate can be evaluated based on the coating uniformity difference of the two side walls on both sides of the flow channel central axis.

[0059] S220. When the coating uniformity difference of at least one straight segment of the flow channel is greater than or equal to the preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed unqualified. When the coating uniformity difference of each straight segment of the flow channel is less than the preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0060] When evaluating the coating uniformity, if the coating uniformity difference of at least one straight channel segment is greater than or equal to the preset coating uniformity difference, it indicates that the coating uniformity difference of at least one straight channel segment on both sides of the channel axis is too large, and thus the coating uniformity of the fuel cell bipolar plate can be determined to be unqualified.

[0061] When the coating uniformity difference of each straight segment of the flow channel is less than the preset coating uniformity difference, it indicates that the coating uniformity difference on both sides of the flow channel axis is small, and thus it can be determined that the coating uniformity of the fuel cell bipolar plate is qualified.

[0062] The beneficial effect of the above implementation method is that it eliminates the influence of different characteristics of light reflection and scattering in the curved section of the flow channel, while the straight section of the flow channel has the same light reflection and scattering characteristics, thus improving the accuracy of coating uniformity assessment.

[0063] The beneficial effect of the above implementation method is that the coating uniformity is evaluated by using the difference in coating uniformity between the two straight-segment detection areas of the straight-segment flow channel, which ensures the accuracy of the coating uniformity evaluation of the bipolar plate.

[0064] The beneficial effect of the above implementation method is that by evaluating the coating uniformity difference of the straight segment flow channel corresponding to each straight segment flow channel, the coating uniformity characteristics of the local coating of the bipolar plate are taken into account when evaluating the coating uniformity of the entire bipolar plate, thus improving the accuracy of evaluating the coating uniformity of the bipolar plate.

[0065] In some implementations, the above method also includes S310 to S320, which will be described in detail below.

[0066] S310. Determine the uniformity of the coating of the straight section flow channel in two straight section detection areas from two different straight section flow channel regions, and determine the difference between the uniformity of the coating of the straight section flow channel in two straight section detection areas from two different straight section flow channel regions as the cross difference of the uniformity of the coating of the straight section flow channel; wherein, the two straight section detection areas from two different straight section flow channel regions are located on the same side of the flow channel.

[0067] When evaluating coating uniformity, the coating uniformity of different straight-segment flow channel regions can be compared and tested. Specifically, two straight-segment test areas can be identified. These two straight-segment test areas come from two different straight-segment flow channel regions, and the inclination direction of the flow channels corresponding to the two straight-segment test areas is the same.

[0068] like Figure 3 As shown, the two straight segment detection areas correspond to two flow channels 113a respectively. The two straight segment detection areas 113a from two different straight segment flow channel areas are located on the same side of the flow channel, so that the reflection and scattering conditions of light in the two straight segment detection areas are the same. Therefore, the coating uniformity of the two straight segment detection areas can be evaluated to evaluate the coating uniformity at different flow channels.

[0069] During the evaluation, the uniformity of the coating in the straight section of the flow channel can be determined in two straight section detection areas from two different straight section flow channel regions. The difference between the uniformity of the coating in the straight section of the flow channel from two different straight section flow channel regions can be determined as the cross difference value of the uniformity of the coating in the straight section of the flow channel. The cross difference value of the uniformity of the coating in the straight section of the flow channel represents the difference in the uniformity of the coatings with the same light reflection and scattering characteristics from different flow channels.

[0070] For example, such as Figure 4As shown, the straight segment detection area 1102b from the straight segment flow channel area 1102 and the straight segment detection area 1103b from the straight segment flow channel area 1103 can be determined, and the uniformity of the straight segment flow channel coating in the straight segment detection area 1102b and the straight segment detection area 1103b can be determined respectively. Then, the difference between the uniformity of the straight segment flow channel coating in the straight segment detection area 1102b from the straight segment flow channel area 1102 and the straight segment detection area 1103b from the straight segment flow channel area 1103 can be determined as the cross difference value of the uniformity of the straight segment flow channel coating.

[0071] S320. When the cross difference of the uniformity of the coating of at least one straight channel segment is greater than or equal to the preset cross difference of the uniformity of the coating of the channel, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the cross difference of the uniformity of the coating of all channels is less than the preset cross difference of the uniformity of the coating of the channel, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0072] When evaluating coating uniformity, if the cross difference of coating uniformity in at least one straight channel segment is greater than or equal to the preset cross difference of coating uniformity in the channel segment, it indicates that the coating uniformity difference of the straight segment detection areas with the same light reflection and scattering characteristics from different channels is too large, and thus it can be determined that the coating uniformity of the fuel cell bipolar plate is unqualified.

[0073] When evaluating the coating uniformity, if the cross difference of coating uniformity across all flow channels is less than the preset cross difference of coating uniformity across all flow channels, it indicates that the coating uniformity difference of all straight-line segments with the same light reflection and scattering characteristics from different flow channels is small, and thus the coating uniformity of the fuel cell bipolar plate can be determined to be qualified.

[0074] For example, when calculating the cross difference of coating uniformity for all flow channels, the cross difference of coating uniformity for all flow channel coatings in the detection area of ​​straight segments from different flow channels can be calculated exhaustively to achieve the evaluation of coating uniformity for all different flow channels.

[0075] The beneficial effect of the above implementation method is that it calculates the coating uniformity difference of the detection area of ​​the straight segment with the same light reflection and scattering characteristics from different flow channels, evaluates the coating uniformity of different flow channels, realizes the evaluation of coating uniformity of different flow channels on the bipolar plate, and improves the evaluation effect of the overall coating uniformity of the bipolar plate.

[0076] In some implementations, the above method also includes S410 to S420, which are described in detail below.

[0077] S410. Determine multiple curved flow channel regions in the flow channel region, divide each curved flow channel region into two curved flow channel detection regions through the flow channel centerline, determine the uniformity of the curved flow channel coating corresponding to the two curved flow channel detection regions of each curved flow channel region, and determine the difference in the uniformity of the curved flow channel coating corresponding to the two curved flow channel detection regions of each curved flow channel region.

[0078] When evaluating coating uniformity, multiple curved flow channel regions can be identified within the flow channel area, and coating uniformity can be evaluated through these curved flow channel regions.

[0079] like Figure 4 As shown, each curved section of the flow channel can be divided into two curved section detection areas by the flow channel centerline. The light reflection and scattering characteristics of the two curved section detection areas are different, so the uniformity of the curved section flow channel coating corresponding to the two curved section detection areas of each curved section flow channel area can be determined. Then, the coating uniformity can be evaluated by the coating uniformity corresponding to the two curved section detection areas.

[0080] For example, such as Figure 4 As shown, when multiple curved segment detection areas are identified by image recognition, straight segment flow channels can be segmented in flow channel region 11 by image recognition to obtain multiple curved segment flow channel regions.

[0081] like Figure 4 As shown, the curved section flow channel region may include curved section flow channel region 121, curved section flow channel region 122, curved section flow channel region 123, etc., and the curved section flow channel region 121 may include two curved section detection regions 121a.

[0082] When evaluating the coating uniformity, the difference in coating uniformity between the two bends in the flow channel region of each bend can be determined. Then, the coating uniformity of the bipolar plate can be evaluated based on the difference in coating uniformity between the two bends.

[0083] For example, the uniformity of the curved channel coating corresponding to the two curved channel detection areas 121a of each curved channel region 121 can be determined, and the difference in the uniformity of the curved channel coating corresponding to the two curved channel detection areas 121a can be determined.

[0084] S420. When the coating uniformity difference of at least one curved section of the flow channel is greater than or equal to the preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed unqualified. When the coating uniformity difference of each curved section of the flow channel is less than the preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0085] When evaluating the coating uniformity, if the coating uniformity difference of at least one curved section of the flow channel is greater than or equal to the preset flow channel coating uniformity difference, it indicates that the coating uniformity difference of the two curved section detection areas 121a of at least one curved section of the flow channel is too large, and thus it can be determined that the coating uniformity of the fuel cell bipolar plate is unqualified.

[0086] When the difference in coating uniformity of each curved section is less than the preset difference in coating uniformity of the flow channel, it indicates that the difference in coating uniformity of the two curved section detection areas 121a of each curved section flow channel is small, and thus it can be determined that the coating uniformity of the fuel cell bipolar plate is qualified.

[0087] The beneficial effect of the above implementation method is that it enables coating uniformity detection in the curved sections of the flow channel, thereby improving the comprehensiveness of coating uniformity detection in the flow channel.

[0088] The beneficial effect of the above implementation method is that each curved section of the flow channel is divided into two curved section detection areas through the central axis of the flow channel. The light reflection and scattering characteristics of the two curved section detection areas are different, which realizes the coating uniformity evaluation of curved section flow channels with different light reflection and scattering characteristics, and avoids the influence of different light reflection and scattering characteristics on the coating uniformity evaluation.

[0089] In some implementations, the above method also includes S510 to S530, which are described in detail below.

[0090] S510. Divide each straight segment flow channel region into multiple sub-straight segment flow channel regions, determine the first sub-straight segment flow channel region located in the middle of the straight segment flow channel region, and obtain the first curved segment flow channel region at the end of the straight segment flow channel region where the first sub-straight segment flow channel region is located.

[0091] Figure 5 A flowchart illustrating the third image recognition-based fuel cell bipolar plate coating detection method provided in this application is shown below. Figure 5 As shown, each straight-segment flow channel region can be divided into multiple sub-segment straight-segment flow channel regions, and the coating uniformity of each sub-segment straight-segment flow channel region can be evaluated separately.

[0092] For example, such as Figure 5As shown, the straight-line flow channel region 11 can be divided into sub-straight-line flow channel regions 131, 132, 133, 134 and 135 by image recognition.

[0093] like Figure 5 As shown, after determining the multi-segment sub-straight channel region, the first sub-straight channel region 133 located in the middle of the straight channel region can be determined. The coating uniformity of the first sub-straight channel region 133 characterizes the coating uniformity at the middle channel of the bipolar plate.

[0094] At the same time, such as Figure 5 As shown, the first curved section flow channel region 136 at the end of the straight section flow channel region where the first sub-straight section flow channel region 133 is located can be obtained. The coating uniformity on the first curved section flow channel region 136 characterizes the coating uniformity in the flow channel at the edge of the bipolar plate.

[0095] S520. Divide the first sub-straight segment flow channel region into two first sub-straight segment detection regions through the flow channel centerline, divide the first curved segment flow channel region into two first curved segment detection regions through the flow channel centerline, and determine the coating uniformity of the first sub-straight segment corresponding to the two first sub-straight segment detection regions and the coating uniformity of the first curved segment corresponding to the two first curved segment detection regions, and determine the first sub-coating uniformity difference between the coating uniformity of the first sub-straight segment detection region and the coating uniformity of the first curved segment detection region located on the same side of the flow channel.

[0096] When evaluating coating uniformity, such as Figure 5 As shown, the first sub-straight segment flow channel region 133 can be divided into two first sub-straight segment detection regions 133a through the flow channel central axis. The light reflection and scattering characteristics of the two first sub-straight segment detection regions 133a are different, so the coating uniformity of the two first sub-straight segment detection regions 133a can be evaluated separately.

[0097] When evaluating the coating uniformity of the two first sub-straight line segment detection areas 133a, the coating uniformity of the first sub-straight line segment corresponding to the two first sub-straight line segment detection areas 133a can be determined respectively.

[0098] Meanwhile, the first curved section flow channel region 136 can be divided into two first curved section detection regions 136a through the flow channel central axis. The light reflection and scattering characteristics of the two first curved section detection regions 136a are different, so the coating uniformity of the two first curved section detection regions 136a can be evaluated separately.

[0099] When evaluating the coating uniformity of the two first curved section detection areas, the coating uniformity of the first curved section corresponding to the two first curved section detection areas 136a can be determined, and the coating uniformity difference between the first sub-straight section detection area 133a and the coating uniformity of the first curved section detection area 136a located on the same side of the flow channel can be determined. The first sub-coating uniformity difference characterizes the difference in coating uniformity detection values ​​between straight sections and curved sections in areas with the same light reflection and scattering characteristics.

[0100] S530. When the uniformity difference of the first sub-coating is greater than or equal to the preset uniformity difference of the first sub-coating, the coating uniformity of the fuel cell bipolar plate is deemed unqualified. When the uniformity difference of all first sub-coatings is less than the preset uniformity difference of the first sub-coating, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0101] When evaluating the coating uniformity, if the uniformity difference of the first sub-coating is greater than or equal to the preset uniformity difference of the first sub-coating, it indicates that the difference in the coating uniformity detection values ​​of the straight and curved sections in the area with the same light reflection and scattering characteristics is large, and thus the coating uniformity of the fuel cell bipolar plate can be determined to be unqualified.

[0102] When all the uniformity differences of the first sub-coating are less than the preset uniformity difference of the first sub-coating, it indicates that the difference in the coating uniformity detection values ​​of the straight and curved segments in the region with the same light reflection and scattering characteristics is small, and thus the coating uniformity of the fuel cell bipolar plate can be determined to be qualified.

[0103] The beneficial effect of the above implementation method is that the coating uniformity in the middle flow channel of the bipolar plate and the coating uniformity in the flow channel at the edge of the bipolar plate are calculated separately, and the coating uniformity on the same side of the flow channel is compared, which improves the accuracy of evaluating the coating uniformity in the bipolar plate.

[0104] In some implementations, the above method also includes S610 to S620, which will be described in detail below.

[0105] S610. Determine the planar regions at the four corners of the fuel cell bipolar plate in the bipolar plate image, excluding the flow channels, and determine the uniformity of the planar coating in the planar regions, and determine the difference in planar coating uniformity between different uniformities.

[0106] like Figure 5 As shown, the planar regions 137 at the four corners of the fuel cell bipolar plate in bipolar plate image 1, excluding the flow channels, can be determined, and the uniformity of the planar coating in the planar regions 137 can be determined, and the difference in the uniformity of the planar coating between different uniformities can be determined, so as to achieve the evaluation of the coating uniformity of different planar regions on the bipolar plate.

[0107] For example, when calculating the difference in uniformity of a planar coating between different planar coating uniformities, the difference in coating uniformity between the planar regions 137 located at the upper left and lower left corners can be calculated as the planar coating uniformity difference.

[0108] S620. When the difference in uniformity of the planar coating is greater than or equal to the preset difference in uniformity of the planar coating, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when all the differences in uniformity of the planar coating are less than the preset difference in uniformity of the planar coating, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

[0109] When evaluating the uniformity of the coating, if the difference in uniformity of the planar coating is greater than or equal to the preset difference in uniformity of the planar coating, it indicates that the difference in uniformity of the planar coating in different planar areas is too large, and the coating uniformity of the fuel cell bipolar plate can be judged to be unqualified.

[0110] When the uniformity difference of all planar coatings is less than the preset uniformity difference of planar coatings, it indicates that the uniformity difference of planar coatings in different planar areas is small, and the uniformity of the coating of the fuel cell bipolar plate can be judged to be qualified.

[0111] The beneficial effect of the above implementation method is that it can evaluate the coating uniformity of planar areas at different locations of the bipolar plate, thereby improving the evaluation effect of coating uniformity of the bipolar plate.

[0112] This application also provides an image recognition-based fuel cell bipolar plate coating uniformity evaluation device, including a unit for performing the method described in any of the above embodiments.

[0113] Figure 6 A schematic diagram of the logic structure of a fuel cell bipolar plate coating uniformity evaluation device based on image recognition, as provided in an embodiment of this application, is shown below. Figure 6 As shown, the apparatus 2 in this embodiment includes a processing unit 21, a storage unit 22, and a transceiver unit 23. The processing unit 21 is used to process data, the storage unit 22 is used to store data, and the transceiver unit 23 is used to send and receive data. The processing unit 21, the storage unit 22, and the transceiver unit 23 cooperate with each other to implement the above-described method. The beneficial effects brought about by the embodiments of this application have been described in the above-described method and will not be repeated here.

[0114] This application also provides an image recognition-based fuel cell bipolar plate coating uniformity evaluation device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in any of the preceding claims.

[0115] Figure 7 A schematic diagram of the physical structure of a fuel cell bipolar plate coating uniformity evaluation device based on image recognition, as provided in an embodiment of this application, is shown below. Figure 7 As shown, the device 3 of this embodiment includes: at least one processor 30 ( Figure 7 Only one processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30 are shown. When the processor 30 executes the computer program 32, it implements the steps in any of the above-described method embodiments. The beneficial effects of the embodiments of this application have been described in the above-described methods and will not be repeated here.

[0116] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0117] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0118] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0119] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0120] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0121] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0122] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0123] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0124] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting the coating of a fuel cell bipolar plate based on image recognition, characterized in that, The method includes: Obtain an image of a bipolar plate of a fuel cell with flow channels, determine the flow channel region corresponding to the flow channel on the fuel cell bipolar plate in the bipolar plate image, and determine the flow channel centerline in the flow channel region; The flow channel area is divided into two detection areas through the flow channel central axis. The flow channel coating uniformity corresponding to the two detection areas is determined, and the flow channel coating uniformity difference between the two detection areas is determined. When the difference in uniformity of the flow channel coating is greater than or equal to the preset difference in uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the difference in uniformity of the flow channel coating is less than the preset difference in uniformity of the flow channel coating, the coating uniformity of the fuel cell bipolar plate is deemed qualified. The flow channel region is segmented by image recognition to obtain multiple curved flow channel regions and straight flow channel regions; The two detection areas include any two of the straight segment detection area and the curved segment detection area; The detection area for the straight line segment is determined by one or more of the following methods: Each straight-segment flow channel region is divided into multiple sub-segments of straight-segment flow channel regions; Multiple straight-segment flow channel regions are identified in the flow channel region. Each straight-segment flow channel region is divided into two straight-segment detection regions through the flow channel centerline. The uniformity of the straight-segment flow channel coating corresponding to the two straight-segment detection regions of each straight-segment flow channel region is determined, and the difference in the uniformity of the straight-segment flow channel coating corresponding to the two straight-segment detection regions of each straight-segment flow channel region is determined. When the coating uniformity difference of at least one straight channel segment is greater than or equal to the preset coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the coating uniformity difference of each straight channel segment is less than the preset coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed qualified. The detection area for the curved section is determined by the following method: Each curved section of the flow channel is divided into two curved section detection areas by using the central axis of the flow channel; Multiple curved flow channel regions are identified in the flow channel region. Each curved flow channel region is divided into two curved flow channel detection regions through the flow channel centerline. The uniformity of the curved flow channel coating corresponding to the two curved flow channel detection regions of each curved flow channel region is determined, and the difference in the uniformity of the curved flow channel coating corresponding to the two curved flow channel detection regions of each curved flow channel region is determined. When the coating uniformity difference of at least one curved section of the flow channel is greater than or equal to the preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the coating uniformity difference of each curved section of the flow channel is less than the preset flow channel coating uniformity difference, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

2. The method as described in claim 1, characterized in that, The method further includes: The uniformity of the coating in two straight-segment flow channels from two different straight-segment flow channel regions is determined, and the difference between the uniformity of the coating in two straight-segment flow channels from two different straight-segment flow channel regions is determined as the cross difference of the uniformity of the coating in the straight-segment flow channels; wherein, the two straight-segment flow channel regions from two different straight-segment flow channel regions are located on the same side of the flow channel. When at least one straight segment of the flow channel has a coating uniformity cross-difference value greater than or equal to a preset flow channel coating uniformity cross-difference value, The coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the cross difference of the coating uniformity of all flow channels is less than the preset cross difference of the coating uniformity of the flow channels, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

3. The method as described in claim 2, characterized in that, The method further includes: Each straight segment flow channel region is divided into multiple sub-straight segment flow channel regions, and the first sub-straight segment flow channel region located in the middle of the straight segment flow channel region is determined. The first curved segment flow channel region at the end of the straight segment flow channel region where the first sub-straight segment flow channel region is located is obtained. The first sub-straight segment flow channel region is divided into two first sub-straight segment detection regions through the flow channel centerline. The first curved segment flow channel region is divided into two first curved segment detection regions through the flow channel centerline. The coating uniformity of the first sub-straight segment corresponding to the two first sub-straight segment detection regions and the coating uniformity of the first curved segment corresponding to the two first curved segment detection regions are determined. The coating uniformity difference between the coating uniformity of the first sub-straight segment detection region and the coating uniformity of the first curved segment detection region located on the same side of the flow channel is determined. When the uniformity difference of the first sub-coating is greater than or equal to the preset uniformity difference of the first sub-coating, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when the uniformity difference of all the first sub-coatings is less than the preset uniformity difference of the first sub-coating, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

4. The method as described in claim 3, characterized in that, The method further includes: Identify the planar regions at the four corners of the fuel cell bipolar plate in the bipolar plate image, excluding the flow channels, determine the uniformity of the planar coating in the planar regions, and determine the difference in planar coating uniformity between different uniformities. When the difference in uniformity of the planar coating is greater than or equal to the preset difference in uniformity of the planar coating, the coating uniformity of the fuel cell bipolar plate is deemed unqualified; when all the differences in uniformity of the planar coating are less than the preset difference in uniformity of the planar coating, the coating uniformity of the fuel cell bipolar plate is deemed qualified.

5. A device for evaluating the uniformity of bipolar plate coating in fuel cells based on image recognition, characterized in that, Including for execution A unit that performs the method according to any one of claims 1 to 4.

6. A fuel cell bipolar plate coating uniformity evaluation device based on image recognition, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images