Pole piece defect detection method, control device and computer readable storage medium

Abstract

The invention relates to the technical field of battery detection, and discloses a defect detection method of a pole piece, a control device and a computer readable storage medium. The defect detection method of the pole piece comprises the following steps: acquiring image data of the pole piece; performing first region division processing on a detection region of the pole piece based on the image data to obtain an internal region and an external region; performing second region division processing on the internal region to obtain at least one internal sub-region; for each of the external region and all the internal sub-regions, obtaining a corresponding defect detection rule, and detecting the corresponding region according to the defect detection rule to generate a region detection result; and determining the detection result of the pole piece based on the detection result of each region. The detection area of the pole piece is partitioned, and each area is provided with an independent detection algorithm, so that the detection result is more accurate, and the problem of inaccurate detection result caused by direct defect detection on the inner and outer areas of the edge after edge grabbing is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery detection, and particularly relates to a method for defect detection of a pole piece, a control device, and a computer-readable storage medium. Background Art

[0002] With the continuous development of lithium-ion battery technology, the requirements for battery performance are also getting higher and higher. The pole piece is an important part of the lithium-ion battery, and its quality directly affects the performance and life of the battery. Therefore, defect detection of the pole piece is one of the important means to ensure battery quality.

[0003] In the related art, the defect detection method of the pole piece usually uses a camera to collect an image of the pole piece, and then performs edge detection on the image. After edge detection, defect detection is directly performed on the inner and outer regions of the edge. Due to the accuracy problem of the camera, distortion will occur, resulting in the failure of defect detection in the region inside or outside the edge of the pole piece, and the detection result is inaccurate, which will seriously affect the performance, life, and safety of the lithium battery. Summary of the Invention

[0004] In view of this, the present invention provides a method for defect detection of a pole piece, a control device, and a computer-readable storage medium to solve the problem that the detection result is inaccurate when defect detection is directly performed on the inner and outer regions of the edge after edge detection.

[0005] In a first aspect, the present invention provides a method for defect detection of a pole piece, including: acquiring image data of the pole piece; performing a first region division process on the detection region of the pole piece based on the image data to obtain an inner region and an outer region; performing a second region division process on the inner region to obtain at least one inner sub-region; for each region in the outer region and all the inner sub-regions, acquiring a corresponding defect detection rule, and detecting the corresponding region according to the defect detection rule to generate a region detection result; and determining the detection result of the pole piece based on the region detection results.

[0006] In a second aspect, the present invention further provides a defect detection control device for controlling the above defect detection method. The defect detection control device includes: an acquisition module for acquiring image data of the pole piece; a first division process module for performing a first region division process on the detection region of the pole piece based on the image data to obtain an inner region and an outer region; a second division process module for performing a second region division process on the inner region to obtain at least one inner sub-region; an acquisition and detection generation module for, for each region in the outer region and all the inner sub-regions, acquiring a corresponding defect detection rule, and detecting the corresponding region according to the defect detection rule to generate a region detection result; and a determination module for determining the detection result of the pole piece based on the region detection results.

[0007] In a third aspect, the present invention also provides a computer-readable storage medium storing computer instructions for causing a computer to execute the above-described defect detection method.

[0008] Advantageous effects: By partitioning the detection area of the pole piece and setting independent detection algorithms for each area, the detection results are more accurate, effectively solving the problem that inaccurate detection results are caused by directly performing defect detection on the inner and outer areas of the edge after edge grasping. Description of the Drawings

[0009] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0010] Figure 1 It is a partial top view of the outer area of a pole piece according to an embodiment of the present invention;

[0011] Figure 2 It is Figure 1 A top view of the remaining part of the outer area of the pole piece shown;

[0012] Figure 3 It is Figure 1 A top view of the inner area inside the pole piece shown;

[0013] Figure 4 It is a top view of another pole piece according to an embodiment of the present invention;

[0014] Figure 5 It is a schematic flowchart of the defect detection method for the pole piece according to an embodiment of the present invention.

[0015] Description of the reference numerals:

[0016] 1. Pole piece; 101. Inner area; 1011. Inner sub-area;

[0017] 111. First edge; 112. Second edge; 113. Third edge; 114. Fourth edge;

[0018] 121. First detection frame; 122. Second detection frame; 123. Third detection frame; 124. Fourth detection frame;

[0019] 131. Inner detection frame; 132. Inner detection sub-frame; 1321. First inner detection sub-frame; 1322. Second inner detection sub-frame. Specific Embodiments

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0021] The following will describe the embodiments of the present invention in conjunction with Figures 1 to 5 , to describe the embodiments of the present invention.

[0022] According to an embodiment of the present invention, on the one hand, a method for detecting defects of a pole piece 1 is provided, including:

[0023] Obtaining image data of the pole piece 1; wherein, an image of the pole piece 1 is captured by an image acquisition component such as a camera.

[0024] Based on the image data, performing a first region division process on the detection region of the pole piece 1 to obtain an internal region 101 and an external region;

[0025] Performing a second region division process on the internal region 101 to obtain at least one internal sub-region 1011;

[0026] For each region in the external region and all the internal sub-regions 1011, obtaining corresponding defect detection rules, and detecting the corresponding region according to the defect detection rules to generate a region detection result;

[0027] Based on the region detection results, determining the detection result of the pole piece 1.

[0028] Applying the method for detecting defects of the pole piece 1 in this embodiment, by partitioning the detection region of the pole piece 1 and setting an independent detection algorithm for each region, the detection result is more accurate, effectively solving the problem that the detection result is inaccurate when directly detecting defects in the inner and outer regions of the edge after edge grasping.

[0029] It should be noted that the pole piece 1 includes a current collector and an active material layer, and the active material layer is coated on the surface of the current collector. If the pole piece 1 is a positive pole piece 1, the material of the current collector can be aluminum, and the material of the active material layer can be lithium cobaltate, lithium iron phosphate, ternary lithium, lithium manganate, etc. If the pole piece 1 is a negative pole piece 1, the material of the current collector can be copper, and the material of the active material layer can be carbon or silicon, etc.

[0030] In one embodiment, the step of performing a first region division process on the detection region of the pole piece 1 based on the image data includes:

[0031] Determining the four edges of the pole piece 1 based on the image data;

[0032] The inner region 101 and the outer region are obtained based on the four edges of the electrode tab 1.

[0033] Determining the inner region 101 and the outer region through the edges of the electrode tab 1 is easy to implement and simplifies the detection process.

[0034] Furthermore, the steps of determining the four edges of the electrode tab 1 based on the image data include:

[0035] Determining the four edge point sets of the electrode tab 1 based on the image data;

[0036] Fitting the four edges of the electrode tab 1 based on the four edge point sets of the electrode tab 1; for example, fitting the four edge straight lines of the electrode tab 1 through the Canny edge detection algorithm.

[0037] It should be noted that Canny comes from the name of the inventor, John F. Canny.

[0038] In one embodiment, the four edges are respectively the first edge 111, the second edge 112, the third edge 113, and the fourth edge 114. The first edge 111 and the third edge 113 are oppositely arranged, the second edge 112 and the fourth edge 114 are oppositely arranged, and the outer region includes a first outer sub-region, a second outer sub-region, a third outer sub-region, and a fourth outer sub-region.

[0039] Obtaining the outer region based on the four edges of the electrode tab 1 includes:

[0040] Obtaining the first outer sub-region based on the first edge 111;

[0041] Obtaining the second outer sub-region based on the second edge 112;

[0042] Obtaining the third outer sub-region based on the third edge 113;

[0043] Obtaining the fourth outer sub-region based on the fourth edge 114.

[0044] It should be noted that the first edge 111 is arranged close to the tab, Figures 1 to 4 the white region on the left in is the tab region, and the tab region is the region on the current collector where the active material layer is not coated, Figures 1 to 4 the gray region on the right in is the region where the active material layer is coated, and the four edges of the electrode tab 1 refer to the edges of the active material layer.

[0045] Furthermore, the steps of obtaining the first outer sub-region based on the first edge 111 include:

[0046] Determining a first straight line at a first preset distance D1 from the first edge 111 inside the first edge 111;

[0047] Determine a second straight line at a second preset distance D2 from the first edge 111 outside the first edge 111;

[0048] Determine a third straight line at a third preset distance D3 from the second edge 112 inside the second edge 112;

[0049] Determine a fourth straight line at a fourth preset distance D4 from the fourth edge 114 inside the fourth edge 114;

[0050] The first straight line, the second straight line, the third straight line and the fourth straight line enclose a first detection frame 121 of a rectangle, and the area inside the first detection frame 121 forms a first external sub-region.

[0051] By shrinking or expanding with the first edge 111 as a reference to form the first external sub-region, problems such as abnormal coating of active substances and damage at the first edge 111 can be accurately detected, the detection accuracy is improved, and it is effectively avoided that the detection result is inaccurate due to unclear and blurred boundaries caused by the camera accuracy.

[0052] Specifically, D1 is 0.1 mm - 5 mm, D2 is 0.1 mm - 5 mm, D3 and D4 are both 0.1 mm - 3 mm. Exemplarily, D1 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, 5 mm or within the range composed of any two of the above values, D2 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, 5 mm or within the range composed of any two of the above values, D3 is 0.1 mm, 1 mm, 2 mm, 3 mm or within the range composed of any two of the above values, D4 is 0.1 mm, 1 mm, 2 mm, 3 mm or within the range composed of any two of the above values.

[0053] Preferably, D1 is 3 mm, D2 is 4 mm, and D3 and D4 are both 1 mm.

[0054] In one embodiment, the step of obtaining the second external sub-region based on the second edge 112 includes:

[0055] Determine a second detection frame 122 inside the second edge 112. The distance between the second detection frame 122 and the second edge 112 is a first set distance L1, the distance between the second detection frame 122 and the first edge 111 is a second set distance L2, the distance between the second detection frame 122 and the third edge 113 is a third set distance L3, and the width of the second detection frame 122 along the extension direction of the first edge 111 is a fourth set distance L4;

[0056] The area inside the second detection frame 122 forms the second external sub-region.

[0057] Shrinking inward with the second edge 112 as a reference to form a second outer sub-region can accurately detect problems such as edge material loss and damage at the second edge 112, improve the detection accuracy, and effectively avoid inaccurate detection results caused by unclear and blurred boundaries due to the camera accuracy.

[0058] Specifically, L1 is 0.1 mm - 3 mm, L2 is 0.1 mm - 4 mm, L3 is 0.1 mm - 3 mm, L4 is 0.1 mm - 5 mm. Exemplarily, L1 is 0.1 mm, 1 mm, 2 mm, 3 mm or within the range composed of any two of the above values, L2 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm or within the range composed of any two of the above values, L3 is 0.1 mm, 1 mm, 2 mm, 3 mm or within the range composed of any two of the above values, L4 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, 5 mm or within the range composed of any two of the above values.

[0059] Preferably, L1 is 1 mm, L2 is 2 mm, L3 is 2 mm, and L4 is 3 mm.

[0060] In one embodiment, the step of obtaining the third outer sub-region based on the third edge 113 includes:

[0061] Determine a third detection frame 123 inside the third edge 113. The distance between the third detection frame 123 and the third edge 113 is a first specified distance E1, the distance between the third detection frame 123 and the second edge 112 is a second specified distance E2, the distance between the three detection frames and the fourth edge 114 is a third specified distance E3, and the width of the third detection frame 123 along the extension direction of the second edge 112 is a fourth specified distance E4;

[0062] The area inside the third detection frame 123 forms the third outer sub-region.

[0063] Shrinking inward with the third edge 113 as a reference to form the third outer sub-region can accurately detect problems such as edge material loss and damage at the third edge 113, improve the detection accuracy, and effectively avoid inaccurate detection results caused by unclear and blurred boundaries due to the camera accuracy.

[0064] Specifically, E1 ranges from 0.1 mm to 3 mm, E2 ranges from 0.1 mm to 3 mm, E3 ranges from 0.1 mm to 4 mm, and E4 ranges from 0.1 mm to 4 mm. Exemplarily, E1 is 0.1 mm, 1 mm, 2 mm, 3 mm, or within the range formed by any two of the above values; E2 is 0.1 mm, 1 mm, 2 mm, 3 mm, or within the range formed by any two of the above values; E3 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, or within the range formed by any two of the above values; E4 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, or within the range formed by any two of the above values.

[0065] Preferably, E1 is 1 mm, E2 is 2 mm, E3 is 2 mm, and E4 is 2 mm.

[0066] In one embodiment, the step of obtaining the fourth external sub-region based on the fourth edge 114 includes:

[0067] Determine a fourth detection frame 124 inside the fourth edge 114. The distance between the fourth detection frame 124 and the fourth edge 114 is a first predetermined distance F1, the distance between the fourth detection frame 124 and the first edge 111 is a second predetermined distance F2, the distance between the fourth detection frame 124 and the third edge 113 is a third predetermined distance F3, and the width of the fourth detection frame 124 along the extension direction of the first edge 111 is a fourth predetermined distance F4.

[0068] The area inside the fourth detection frame 124 forms the fourth external sub-region.

[0069] By shrinking inward with the fourth edge 114 as the reference to form the fourth external sub-region, problems such as edge material loss and damage at the fourth edge 114 can be accurately detected, the detection accuracy can be improved, and it can effectively avoid inaccurate detection results caused by unclear or blurred boundaries due to the camera accuracy.

[0070] Specifically, F1 ranges from 0.1 mm to 3 mm, F2 ranges from 0.1 mm to 4 mm, F3 ranges from 0.1 mm to 3 mm, and F4 ranges from 0.1 mm to 5 mm. Exemplarily, F1 is 0.1 mm, 1 mm, 2 mm, 3 mm, or within the range formed by any two of the above values; F2 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, or within the range formed by any two of the above values; F3 is 0.1 mm, 1 mm, 2 mm, 3 mm, or within the range formed by any two of the above values; F4 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, 5 mm, or within the range formed by any two of the above values.

[0071] Preferably, F1 is 1 mm, F2 is 2 mm, F3 is 2 mm, and F4 is 3 mm.

[0072] In one embodiment, the step of obtaining the internal region 101 based on the four edges of the electrode tab 1 includes:

[0073] Determine an inner detection frame 131 inside the four edges of the electrode tab 1. The distance between the inner detection frame 131 and the first edge 111 is the first distance A1, the distance between the inner detection frame 131 and the second edge 112 is the second distance A2, the distance between the inner detection frame 131 and the third edge 113 is the third distance A3, and the distance between the inner detection frame 131 and the fourth edge 114 is the fourth distance A4;

[0074] The region inside the inner detection frame 131 forms the internal region 101.

[0075] Shrinking inward with the four edges as the reference to form the internal region 101 can accurately detect the defects existing on the surface of the electrode tab 1 and improve the detection accuracy.

[0076] Specifically, A1 is 1.5 mm - 2 mm, A2 is 1.5 mm - 2 mm, A3 is 1.5 mm - 2 mm, and A4 is 1.5 mm - 2 mm.

[0077] Preferably, A1 is 1.5 mm, 1.6 mm, 1.7 mm, 1.8 mm, 1.9 mm, 2 mm or within the range composed of any two of the above values; A2 is 1.5 mm, 1.6 mm, 1.7 mm, 1.8 mm, 1.9 mm, 2 mm or within the range composed of any two of the above values; A3 is 1.5 mm, 1.6 mm, 1.7 mm, 1.8 mm, 1.9 mm, 2 mm or within the range composed of any two of the above values; A4 is 1.5 mm, 1.6 mm, 1.7 mm, 1.8 mm, 1.9 mm, 2 mm or within the range composed of any two of the above values.

[0078] In one embodiment, chamfers are provided at the four corners of the inner detection frame 131, and the length C of the right-angle side of the chamfer is 0 - 2 mm.

[0079] Further, when the electrode tab 1 is the positive electrode tab 1, the right-angle side of the chamfer is preferably 2 mm; when the electrode tab 1 is the positive electrode tab 1, the right-angle side of the chamfer is preferably 0, that is, no chamfer is provided.

[0080] In one embodiment, the step of performing a second region division process on the internal region 101 includes:

[0081] At least two inner detection sub - frames 132 arranged along the extension direction of the second edge 112 are determined within the inner region 101. Along the extension direction of the second edge 112, the distance between the inner detection frame 131 and the inner detection sub - frame 132 closest to the first edge 111 is the first spacing B1, and the distance between the inner detection frame 131 and the inner detection sub - frame 132 closest to the third edge 113 is the second spacing B2. Along the extension direction of the first edge 111, the distances between the inner detection frame 131 and the inner detection frame 131 are the third spacing B3 and the fourth spacing B4, and the distance between two adjacent inner detection sub - frames 132 is the fifth spacing B5;

[0082] The inner region 101 of the inner detection sub - frame 132 forms an inner sub - region 1011.

[0083] Further, one inner detection sub - frame 132 close to the tab region is the first inner detection sub - frame 1321, and the remaining inner detection sub - frames 132 are the second inner detection sub - frames 1322. The first inner detection sub - frame 1321 is closer to the tab region than the second inner detection sub - frames 1322, and the active material layer corresponding to the second inner detection sub - frame 1322 is thinner than the active material layer corresponding to the second inner detection sub - frame 1322.

[0084] Specifically, B1 is 0.1 mm - 4 mm, B2 is 0.1 mm - 4 mm, B3 is 0.1 mm - 6 mm, B4 is 0.1 mm - 6 mm, B5 is 0.1 mm - 6 mm. Exemplarily, B1 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm or within the range composed of any two of the above values, B2 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm or within the range composed of any two of the above values, B3 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, 5 mm, 6 mm or within the range composed of any two of the above values, B4 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, 5 mm, 6 mm or within the range composed of any two of the above values, B5 is 0.1 mm, 1 mm, 2 mm, 3 mm, 4 mm, 5 mm, 6 mm or within the range composed of any two of the above values.

[0085] Preferably, B1 is 2 mm, B2 is 2 mm, B3 is 2 mm, B4 is 2 mm, B5 is 2 mm.

[0086] In one embodiment, the defect detection rule includes a preset gray - value range, and the region includes a plurality of pixel points;

[0087] The steps of detecting the corresponding region according to the defect detection rule and generating a region detection result include:

[0088] Obtain the gray - value of each pixel point;

[0089] Generate regional detection results based on the grayscale value and the grayscale value range.

[0090] The grayscale value is single-channel data, which removes color information, retains brightness information, reduces the amount of data, and is simpler and more efficient to process. The grayscale value range can be flexibly adjusted according to actual needs to adapt to different detection tasks, with high flexibility.

[0091] Further, the first edge 111 divides the first outer sub-region into an ear detection region and a coating detection region. When detecting the ear detection region, the steps of generating regional detection results based on the grayscale value and the grayscale value range include:

[0092] Judge whether the grayscale value of at least one pixel point in the ear detection region is within the first grayscale value range;

[0093] If the grayscale value of at least one pixel point in the ear detection region is within the first grayscale value range, it indicates that the ear detection region is abnormal, that is, foreign objects have fallen into the ear detection region;

[0094] If the grayscale value of each pixel point in the ear detection region is less than the first grayscale value range, it indicates that the ear detection region is normal, that is, no foreign objects have fallen into the ear detection region.

[0095] Specifically, the first grayscale value range is 200 - 240.

[0096] Further, when detecting the ear detection region, the steps of generating regional detection results based on the grayscale value and the grayscale value range include:

[0097] Judge whether the grayscale value of at least one pixel point in the ear detection region is within the second grayscale value range;

[0098] If the grayscale value of at least one pixel point in the ear detection region is within the second grayscale value range, it indicates that the ear detection region is abnormal, that is, the ear detection region has not been rolled;

[0099] If the grayscale value of each pixel point in the ear detection region is greater than the second grayscale value range, it indicates that the ear detection region is normal, that is, the ear detection region has been rolled.

[0100] Specifically, the second grayscale value range is 0 - 40.

[0101] It should be noted that there are stripes after the ear region is rolled, and the corresponding grayscale value after rolling is larger than the corresponding grayscale value before rolling.

[0102] Further, when detecting the coating detection area, the second outer sub-area, the third outer sub-area, the fourth outer sub-area, the first inner detection sub-frame 1321, and the second inner detection sub-frame 1322, the steps of generating a region detection result according to the gray value and the gray value range include:

[0103] Determine whether the gray value of at least one pixel point in a region is less than the third gray value range;

[0104] If the gray value of at least one pixel point in the region is less than the third gray value range, it indicates that the region is abnormal, that is, there is a missing foil in the region;

[0105] If the gray value of each pixel point in the region is within the third gray value range, it indicates that the region is normal, that is, there is no missing foil in the region.

[0106] Specifically, the third gray value range can be set to any range between 160 and 240.

[0107] It should be noted that the second gray value ranges corresponding to each region may be different. For example, the third gray value range corresponding to the first inner detection sub-frame 1321 is 160 - 230, and the third gray value range corresponding to the second inner detection sub-frame 1322 is 170 - 240.

[0108] In one embodiment, the defect detection rule includes a preset gray difference range, and the region includes multiple pixel points;

[0109] The steps of detecting the corresponding region according to the defect detection rule and generating a region detection result include:

[0110] Obtain the gray value of each pixel point;

[0111] Calculate the gray difference between any two pixel points;

[0112] Generate a region detection result according to the gray difference and the gray difference range.

[0113] By calculating the gray difference, the brightness or darkness change between adjacent pixel points can be captured more clearly, and defects such as scratches, pits, indentations, or bubbles in the region can be accurately detected, improving the detection accuracy.

[0114] Further, when detecting the tab detection area, the coating detection area, the second outer sub-area, the third outer sub-area, the fourth outer sub-area, the first inner detection sub-frame 1321, and the second inner detection sub-frame 1322, the steps of generating a region detection result according to the gray difference and the gray difference range include:

[0115] Determine whether the gray difference between any two pixel points in a region is within the gray difference range;

[0116] If the gray difference between any two pixel points in this area is within the gray difference range, it indicates that this area is abnormal, that is, there are defects such as scratches, pits, indentations or bubbles in this area;

[0117] If the gray difference between any two pixel points in this area is less than the gray difference range, it indicates that this area is normal, that is, there are no defects such as scratches, pits, indentations or bubbles in this area.

[0118] Specifically, the gray difference range is 15-30.

[0119] In this embodiment, after grasping the edge of the pole piece 1, it is shrunk and expanded based on the edge of the pole piece 1, and an independent detection area is established. Different items are detected for different areas, and different standards are used to achieve follow-up partition control and improve the detection accuracy.

[0120] In a second aspect, the present invention also provides a defect detection control device for the pole piece 1, which is used to control the above-mentioned defect detection method. The defect detection control device includes:

[0121] An acquisition module, which is used to acquire the image data of the pole piece 1;

[0122] A first partitioning processing module, which is used to perform a first area partitioning process on the detection area of the pole piece 1 based on the image data to obtain an internal area 101 and an external area;

[0123] A second partitioning processing module, which is used to perform a second area partitioning process on the internal area 101 to obtain at least one internal sub-area 1011;

[0124] An acquisition and detection generation module, which is used to obtain the corresponding defect detection rules for each of the external area and all the internal sub-areas 1011, and detect the corresponding areas according to the defect detection rules to generate area detection results;

[0125] A determination module, which is used to determine the detection result of the pole piece 1 based on the area detection results.

[0126] For the specific effects of the above-mentioned defect detection control device, refer to the above-mentioned defect detection control method for understanding, and details are not described here.

[0127] In a third aspect, the present invention also provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the above-mentioned defect detection method.

[0128] Further, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (abbreviation: HDD), or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above types of memories.

[0129] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for detecting defects in a pole piece, characterized in that: include: Acquiring image data of the pole piece (1); Based on the image data, a first area division process is performed on the detection area of ​​the pole piece (1) to obtain an internal area (101) and an external area; Performing a second region division process on the internal region (101) to obtain at least one internal sub-region (1011); For each of the external area and all the internal sub-areas (1011), a corresponding defect detection rule is obtained, and the corresponding area is detected according to the defect detection rule to generate an area detection result; Based on the detection results of each of the regions, the detection result of the pole piece (1) is determined.

2. The defect detection method according to claim 1, characterized in that: The step of performing a first area division process on the detection area of ​​the pole piece (1) based on the image data comprises: Determining four edges of the pole piece (1) based on the image data; The inner region (101) and the outer region are obtained based on the four edges of the pole piece (1).

3. The defect detection method according to claim 2, characterized in that: The four edges are respectively a first edge (111), a second edge (112), a third edge (113) and a fourth edge (114); the first edge (111) and the third edge (113) are arranged opposite to each other; the second edge (112) and the fourth edge (114) are arranged opposite to each other; and the external region comprises a first external sub-region, a second external sub-region, a third external sub-region and a fourth external sub-region; The outer region obtained based on the four edges of the pole piece (1) includes: obtaining the first outer sub-region based on the first edge (111); obtaining the second outer sub-region based on the second edge (112); obtaining the third outer sub-region based on the third edge (113); The fourth outer sub-region is obtained based on the fourth edge (114).

4. The defect detection method according to claim 3, characterized in that: The step of obtaining the first external sub-region based on the first edge (111) comprises: Determining a first straight line at a first preset distance D1 from the first edge (111) on the inner side of the first edge (111); Determining a second straight line at a second preset distance D2 from the first edge (111) outside the first edge (111); Determining a third straight line at a third preset distance D3 from the second edge (112) on the inner side of the second edge (112); Determining a fourth straight line at a fourth preset distance D4 from the fourth edge (114) on the inner side of the fourth edge (114); The first straight line, the second straight line, the third straight line and the fourth straight line enclose a first rectangular detection frame (121), and the area within the first detection frame (121) forms the first external sub-area.

5. The defect detection method according to claim 3, characterized in that: The step of obtaining the second external sub-region based on the second edge (112) comprises: A second detection frame (122) is determined on the inner side of the second edge (112), the distance between the second detection frame (122) and the second edge (112) is a first set distance L1, the distance between the second detection frame (122) and the first edge (111) is a second set distance L2, the distance between the second detection frame (122) and the third edge (113) is a third set distance L3, and the width of the second detection frame (122) along the extension direction of the first edge (111) is a fourth set distance L4; The area within the second detection frame (122) forms the second outer sub-area.

6. The defect detection method according to claim 3, characterized in that: The step of obtaining the third external sub-region based on the third edge (113) comprises: A third detection frame (123) is determined on the inner side of the third edge (113), the distance between the third detection frame (123) and the third edge (113) is a first specified distance E1, the distance between the third detection frame (123) and the second edge (112) is a second specified distance E2, the distance between the third detection frame and the fourth edge (114) is a third specified distance E3, and the width of the third detection frame (123) along the extension direction of the second edge (112) is a fourth specified distance E4; The area within the third detection frame (123) forms the third external sub-area.

7. The defect detection method according to claim 3, characterized in that: The step of obtaining the fourth outer sub-region based on the fourth edge (114) comprises: A fourth detection frame (124) is determined on the inner side of the fourth edge (114), the distance between the fourth detection frame (124) and the fourth edge (114) is a first predetermined distance F1, the distance between the fourth detection frame (124) and the first edge (111) is a second predetermined distance F2, the distance between the fourth detection frame (124) and the third edge (113) is a third predetermined distance F3, and the width of the fourth detection frame (124) along the extension direction of the first edge (111) is a fourth predetermined distance F4; The area within the fourth detection frame (124) forms the fourth external sub-area.

8. The defect detection method according to claim 3, characterized in that: The step of obtaining the inner region (101) based on the four edges of the pole piece (1) comprises: An inner detection frame (131) is determined on the inner sides of the four edges of the pole piece (1), the distance between the inner detection frame (131) and the first edge (111) is a first distance A1, the distance between the inner detection frame (131) and the second edge (112) is a second distance A2, the distance between the inner detection frame (131) and the third edge (113) is a third distance A3, and the distance between the inner detection frame (131) and the fourth edge (114) is a fourth distance A4; The area within the inner detection frame (131) forms the inner area (101).

9. The defect detection method according to claim 8, characterized in that: Chamfers are arranged at the four corners of the inner detection frame (131), and the length C of the right-angled side of the chamfer is 0 to 2 mm.

10. The defect detection method according to claim 8, characterized in that: The step of performing a second area division process on the internal area (101) comprises: Determine, within the internal area (101), at least two inner detection subframes (132) arranged along the extension direction of the second edge (112); along the extension direction of the second edge (112), the distance between the inner detection frame (131) and the inner detection subframe (132) closest to the first edge (111) is a first spacing B1; the distance between the inner detection frame (131) and the inner detection subframe (132) closest to the third edge (113) is a second spacing B2; along the extension direction of the first edge (111), the distance between the inner detection frame (131) and the inner detection frame (131) is a third spacing B3 and a fourth spacing B4; and the distance between two adjacent inner detection subframes (132) is a fifth spacing B5; The inner region (101) of the inner detection sub-frame (132) forms the inner sub-region (1011).

11. The defect detection method according to claim 1, characterized in that: The defect detection rule includes a preset gray value range, and the region includes a plurality of pixels; The steps of detecting the corresponding area according to the defect detection rule and generating the area detection result include: Obtaining the grayscale value of each pixel; The region detection result is generated according to the grayscale value and the grayscale value range.

12. The defect detection method according to claim 1, characterized in that: The defect detection rule includes a preset grayscale difference range, and the region includes a plurality of pixels; The steps of detecting the corresponding area according to the defect detection rule and generating the area detection result include: Obtaining the grayscale value of each pixel; Calculate the grayscale difference between any two pixels; The region detection result is generated according to the grayscale difference and the grayscale difference range.

13. A defect detection control device for a pole piece, characterized in that: Used to control the defect detection method according to claim 1, the defect detection control device comprises: An acquisition module, used for acquiring image data of the pole piece (1); A first division processing module, used for performing a first area division processing on the detection area of ​​the pole piece (1) based on the image data to obtain an internal area (101) and an external area; A second division processing module, used for performing a second region division processing on the internal region (101) to obtain at least one internal sub-region (1011); Acquiring a detection generation module, used for acquiring corresponding defect detection rules for each area in the external area and all the internal sub-areas (1011), and detecting the corresponding area according to the defect detection rules to generate area detection results; A determination module is used to determine the detection result of the pole piece (1) based on the detection results of each of the regions.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the defect detection method according to any one of claims 1 to 12.

Images