Battery pole piece burr detection device and detection method based on machine vision

Abstract

The invention discloses a pole piece burr detection device and detection method based on machine vision, and belongs to the technical field of battery pole piece burr detection.The method comprises the steps that a to-be-detected slice is imaged through an area-array camera with a telecentric lens, and a to-be-detected picture is obtained and stored in a cache queue; the to-be-detected picture is preprocessed; performing monitoring area positioning on the preprocessed to-be-detected picture; performing burr detection on each positioning area to obtain a burr detection result; according to the invention, automatic focus tracking of the camera can be realized; the requirement of double-sided detection can be met in an extremely small space; high-speed optical imaging of transverse and longitudinal burrs of the laser edge / slitting edge of the pole piece is realized; the detection equipment can automatically avoid the material belt to adapt to the production process of belt threading and the like; full inspection at the speed of 120 meters per second is supported; the appearance size can be adjusted according to the installation position, the dustproof function is achieved, and shading measures are taken.

Description

Technical Field

[0001] The present invention belongs to the technical field of burr detection for battery electrodes, and particularly relates to a burr detection device and method for battery electrodes based on machine vision. Background Art

[0002] Under the background of the "dual carbon" goal, the global attention to clean energy and sustainable development has been increasing, and fields such as new energy vehicles, energy storage devices, and 3C devices have developed rapidly. As the core energy component in these fields, the market demand for lithium batteries has increased sharply. In 2024, the sales volume of new energy vehicles has continued to rise, and the safety of batteries has always been a key project for market promotion. Quality defects of batteries are one of the important factors leading to safety hazards.

[0003] In the manufacturing process of battery cells, the detection and control of electrode burrs are crucial parts for making high-quality battery electrodes. Electrode burrs refer to the tiny and sharp metal protrusions formed on the edges of electrodes during the processes of pulping, coating, and rolling, and then in the slitting and die-cutting processes in the manufacturing process of battery cells. These protrusions have various shapes and are uneven. Their generation is due to factors such as tool wear during cutting, material tearing, or unreasonable setting of processing parameters, and their sizes range from several micrometers to hundreds of micrometers. Burrs or beads on the electrodes not only reduce the energy density of the battery, but also, because the battery separator is relatively thin (from a dozen to dozens of micrometers), the burrs piercing the separator will cause the positive and negative electrodes to be connected, leading to self-discharge or internal short-circuit faults. In severe cases, there will be safety hazards such as battery swelling and explosion, causing huge losses.

[0004] To improve the performance and safety of batteries, Section 5.3.6 "Burr Control" of the IEEE 1725-2021 standard recommends that the height of electrode burrs should be lower than 50% of the lower tolerance limit of the separator thickness. Therefore, in the manufacturing of battery cells, there is an urgent need for more efficient and advanced detection equipment to timely detect electrode burrs, optimize the processing technology in a timely manner, and effectively control the generation of burrs by selecting the tool material and geometry, and precisely regulating the slitting and die-cutting process parameters (such as cutting speed, pressure, etc.).

[0005] In the manufacturing of battery cells, the control of electrode burrs is extremely crucial. Most manufacturers currently use manual detection with microscopes, but long-term "hand-shaking and eye-watching" is prone to missing burrs, beads, and other defects on the electrodes due to visual fatigue.

[0006] The size of burrs is usually at the micrometer level, and their tiny scale makes the detection difficulty significantly increase. Also, factors such as the complex production process and large production demand of battery electrodes further exacerbate the complexity of detection. In the actual working process, it is also necessary to consider the compatible detection of various complex defects. Therefore, there are many challenges in the manufacturing and detection processes of battery electrodes:

[0007] It is difficult to balance efficiency and accuracy. Traditional methods require equipment such as microscopes for "manual operation and visual inspection", which have high requirements for personnel skills, low detection efficiency, high misjudgment rates, and cannot achieve full inspection.

[0008] Full-automatic detection cannot be achieved. In the workshop, full-automatic detection of burrs on the electrode sheet is required, replacing manual manual focusing, including calibration, detection, and data analysis.

[0009] The customized data management system is lacking. Traditional manual microscope burr detection requires on-site personnel to manually collect and count the results again, with low data analysis and management efficiency.

[0010] It is difficult to balance size detection and burr detection. For traditional battery electrode sheet detection, an image measuring instrument is needed to detect the size, and then the machine is replaced to use a microscope to observe the burrs, with low efficiency and inaccurate detection results.

[0011] Large-size measurement cannot be satisfied. When using manual measurement and the microscope method, the platform is small and only supports small-size measurement, unable to meet the requirements for detecting the outer shape size of larger electrode sheets.

[0012] Multiple defect detection requirements. In addition to traditional burr detection, automatic detection of exposed foil, decarburization, etc. can also be carried out.

[0013] In summary, based on the technical defects in the existing technology, a method for detecting burrs on electrode sheets based on machine vision is needed to meet the requirements of detection stability. Summary of the Invention

[0014] The technical problem to be solved by the present invention is to provide a device and method for detecting burrs on electrode sheets based on machine vision in view of the deficiencies in the background technology. By assembling a special algorithm for electrode sheet burrs and a customized optical system, it can synchronously detect burrs on the front and side of the battery electrode sheet, and can also detect defects such as decarburization and exposed foil. It integrates the basic outer shape size function of an image measuring instrument and has characteristics such as high detection efficiency, diverse functions, and automatic detection.

[0015] The present invention adopts the following technical solutions to solve the above technical problems:

[0016] A device for detecting burrs on electrode sheets based on machine vision includes a prism. A longitudinal detection camera is installed on the right side of the prism. A longitudinal avoidance motor module is fixedly connected to the rear side of the longitudinal detection camera. A transverse focusing motor module is installed at the bottom left of the longitudinal detection camera. A transverse detection camera is installed at the bottom left of the transverse focusing motor module. A Y-axis travel groove is fixedly connected to the rear right end of the transverse detection camera. A transmissive edge measurement sensor is fixedly connected to the bottom left of the transverse detection camera.

[0017] A detection method for a device for detecting burrs on battery electrode sheets based on machine vision specifically includes the following steps;

[0018] Step 1: Image the slice to be detected by an area array camera with a telecentric lens, obtain the image to be detected and store it in the buffer queue;

[0019] Step 2: Preprocess the image to be detected to obtain the burr area to be detected;

[0020] Step 3: Preprocess the image of the burr area to reduce noise interference, and based on the position of the pole piece film area, screen out possible burrs according to different thresholds. According to the actual production size requirements, judge the number and coordinates of the burrs based on the area and length regional features of the burrs, and perform monitoring area positioning;

[0021] Step 4: Perform burr detection on each positioning area to obtain the burr detection result.

[0022] Compared with the prior art, the present invention adopts the above technical solutions and has the following technical effects:

[0023] 1. The present invention provides a method for detecting burrs in pole piece slitting based on vision detection. Image the slice to be detected by an area array camera with a telecentric lens, obtain the image to be detected and store it in the buffer queue; preprocess the image to be detected; perform monitoring area positioning on the preprocessed image to be detected; perform burr detection on each positioning area to obtain the burr detection result. The present invention can achieve automatic focusing of the camera; can meet the requirements of double-sided detection in a very small space; achieve high-speed optical imaging of the transverse and longitudinal burrs on the laser edge / slitting edge of the pole piece; the detection device can automatically avoid the material tape and adapt to the production process such as threading the tape; support full inspection at a speed of 120 meters per second; the external dimensions can be adjusted according to the installation position, have a dust-proof function, and have a light-shielding measure.

[0024] 2. The present invention provides a device for detecting burrs in pole piece slitting based on vision detection. The transverse detection camera is responsible for collecting images of the transverse surface of the workpiece, and the transverse focusing motor module works together. According to the actual position and surface conditions of the workpiece, the focal length and position of the transverse detection camera are adjusted by motor drive to ensure that the camera can always clearly and accurately capture the image of the transverse surface of the workpiece. The image data collected by the longitudinal detection camera is also transmitted to image processing and integrated and analyzed with the data collected by the transverse detection camera. Through the comprehensive processing of the image data in two directions, it is possible to more comprehensively and accurately judge whether there are burrs on the surface of the workpiece and the specific position, size and shape of the burrs, and thus complete the burr detection. Description of the Drawings

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 Front three-dimensional view of the burr detection device proposed by the present invention;

[0027] Figure 2 Partial structure disassembly diagram of the burr detection device proposed by the present invention;

[0028] Figure 3 Partial structure diagram of the burr detection device proposed by the present invention;

[0029] Figure 4 Partial structure display diagram of the burr detection device proposed by the present invention;

[0030] Figure 5 Partial structure schematic diagram of the burr detection device proposed by the present invention;

[0031] Figure 6 Flowchart of the method for detecting burrs on the pole piece based on machine vision provided by the present invention;

[0032] Figure 7 Schematic diagram of the imaging effect of the camera of the present invention;

[0033] Figure 8 Schematic diagram of the effect of finding burr defects in the foil area in the pole piece of the present invention;

[0034] Figure 9 Schematic diagram of the final display panel of the burr detection effect of the present invention;

[0035] Figure 10 Schematic diagram of the structure of the camera autofocus mechanism of the present invention. Detailed implementation manners

[0036] The following further elaborates on the technical solutions of the present invention in conjunction with the drawings:

[0037] To help those skilled in the art better understand the present invention, the following will provide a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments represent only a portion of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments derived by persons of ordinary skill in the art without inventive effort should fall within the scope of protection of the present invention. It should be noted that the terms "first" and "second" in the specification and claims of the present invention, as well as in the accompanying drawings, are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that such terms are interchangeable where appropriate, such that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "including," "comprising," and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not necessarily limited to the steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.

[0038] Please see the attached Figure 1 - Attachment Figure 3 The present invention provides an embodiment of a battery pole piece burr detection device based on machine vision, comprising a prism 1, a longitudinal detection camera 6 is installed on the right side of the prism 1, a longitudinal avoidance motor module 5 is fixedly connected to the rear side of the longitudinal detection camera 6, a transverse focus tracking motor module 4 is installed on the right bottom of the longitudinal detection camera 6, a transverse detection camera 3 is installed on the left side of the bottom of the transverse focus tracking motor module 4, a Y-axis driving groove 7 is fixedly connected to the right end of the rear side of the transverse detection camera 3, and a through-beam edge measurement sensor 2 is fixedly connected to the left side of the bottom of the transverse detection camera 3;

[0039] Specifically, this longitudinal detection camera 6 not only has high-resolution imaging capabilities, but also has fast image processing capabilities. It can capture and process image information on the right side of the prism 1 in real time to ensure that the image of the required detection area can be accurately captured. At the bottom right side of the longitudinal detection camera 6, a transverse focus tracking motor module 4 is also installed. This transverse focus tracking motor module 4 is also a high-precision driving device. After receiving the control signal, it can drive the camera lens to move laterally. At the rear right end of the transverse detection camera 3, a Y-axis driving groove 7 is also fixedly connected. This Y-axis driving groove 7 is a guide rail structure, which can provide stable support and guidance for the transverse detection camera 3, so that it can move in the direction of the Y-axis driving groove 7, thereby improving the stability and accuracy of the entire device and meeting the needs of tracking the target object.

[0040] Please see the attached Figure 3 - AttachmentFigure 5 The bottom right side of the through-beam edge measurement sensor 2 is rotatably connected to a rotating rod 2 9, the left side of the through-beam edge measurement sensor 2 is rotatably connected to a rotating rod 1 8, and the rear right end of the through-beam edge measurement sensor 2 is rotatably connected to a rotating rod 3 10. The prism 1 and the longitudinal detection camera 6 both adopt a square design;

[0041] Specifically, through the cooperation between the rotating rod 1 8 and the rotating rod 2 9, the inclination angle and position of the through-beam edge measurement sensor 2 can be further adjusted to meet the measurement requirements in different scenarios and improve the measurement stability. A rotating rod 3 10 is also rotatably connected. The addition of the rotating rod 3 10 enables the through-beam edge measurement sensor 2 to be adjusted in all directions to meet more complex measurement requirements. Whether it is adjusting the up and down angles or the left and right angles of the sensor, it can be achieved through the rotating rod 3 10.

[0042] Working principle: The lateral detection camera 3 is responsible for capturing images of the lateral surface of the workpiece, and the lateral focus tracking motor module 4 works in conjunction with it. According to the actual position and surface condition of the workpiece, the focal length and position of the lateral detection camera 3 are adjusted by the motor drive to ensure that the camera can always clearly and accurately capture images of the lateral surface of the workpiece. The through-type edge measurement sensor 2 plays an important role in lateral detection and can accurately measure the position and shape information of the lateral edge of the workpiece. When the workpiece is placed in the detection area, the through-type edge measurement sensor 2 quickly senses the edge of the workpiece and provides an accurate edge positioning reference for the lateral detection camera 3, so that the camera can focus more specifically on the edge area of the workpiece when capturing images, thereby improving the detection accuracy of burrs on the edge. The longitudinal detection camera 6 is mainly responsible for capturing image information of the longitudinal surface of the workpiece. During this process, the longitudinal avoidance motor module 5, according to the height of the workpiece and possible obstacles, the image data captured by the longitudinal detection camera 6 is also transmitted to the image processing, and integrated and analyzed with the data captured by the lateral detection camera 3. By comprehensive processing of image data in two directions, it is possible to more comprehensively and accurately determine whether there are burrs on the workpiece surface and the specific position, size and shape of the burrs to complete burr detection.

[0043] like Figure 6 As shown, a battery electrode burr detection method based on machine vision specifically includes the following steps:

[0044] Step 1: Use an area array camera with a telecentric lens to image the slice to be inspected, obtain the image to be inspected and store it in a cache queue;

[0045] Step 2: pre-process the image to be detected to obtain the burr area to be detected;

[0046] Step 3: Perform image preprocessing on the burr area to reduce noise interference. Based on the position of the pole piece film area, filter out possible burrs according to different thresholds. Determine the number and coordinates of burrs based on the area and length regional features according to the actual production size requirements, and perform monitoring area positioning.

[0047] Step 4: Perform burr detection on each positioning area to obtain burr detection results.

[0048] Figure 7 Schematic diagram of the camera imaging effect of the present invention; Figure 8 Schematic diagram of the effect of finding burr defects in the foil area in the pole piece of the present invention; Figure 9 Schematic diagram of the final display panel of the burr detection effect of the present invention; Figure 10 Schematic diagram of the structure of the camera automatic focusing mechanism of the present invention. The present invention can achieve automatic focusing of the camera; can meet the requirements of double-sided detection in a very small space; achieve high-speed optical imaging of the transverse and longitudinal burrs on the laser edge / slit edge of the pole piece; the detection device can automatically avoid the material tape and adapt to production processes such as threading; support full inspection at a speed of 120 meters per second; the external dimensions can be adjusted according to the installation position, with dust-proof function and light-shielding measures.

[0049] The specific steps of step 1 are as follows:

[0050] Step 1.1: Adjust the focusing module of the detection device according to actual needs.

[0051] Step 1.2: Adjust the appropriate light source intensity according to the material characteristics.

[0052] Step 1.3: Take a photo of the slice to be detected through an area array camera with a telecentric lens for imaging.

[0053] Step 1.4: The device sensor continuously detects the position of the pole piece.

[0054] Step 1.5: The motor drives the coordinate axis to move, adjusts the position of the camera, and saves the image to be detected into the cache queue.

[0055] The specific steps of step 2 are as follows;

[0056] Step 2.1: Name the initial image of the slice to be detected collected as A.

[0057] Step 2.2: Perform threshold processing on the initial image A. By setting one or more thresholds, divide the pixels of the image into different categories for binary processing to separate the target area from the background; adopt a fixed threshold method, and select the concave point at the boundary between the background and the foreground in the histogram as the threshold through histogram analysis.

[0058] Step 2.3, after selecting an appropriate threshold according to the image boundary, separate the polar region B from the original image A;

[0059] Step 2.4, performing a pre-processing operation of smoothing and denoising on the obtained pole piece region B using a denoising method of image morphological operation;

[0060] The opening operation is recorded as: Where: I represents the input image, B represents the structural element;

[0061] Among them, corrosion Under the action of the structural element B, the minimum grayscale value in the neighborhood is taken with (x, y) as the center position, where (s, t)∈B, s and t represent the offset coordinates in the structural element B; it is used to remove small areas, shrink the target area, and eliminate isolated noise points;

[0062] Expansion Under the action of the structural element B, the maximum grayscale value in the neighborhood is taken with (x, y) as the center position, where (s, t)∈B, s and t represent the offset coordinates in the structural element B; it is used to restore the main structure of the target area after corrosion.

[0063] Step 2.5, after performing an opening operation on the pole piece region B, the pole piece region C is obtained after removing small noises and smoothing the target boundary;

[0064] In step 2.5, in a digital image, the connectivity of a pixel is based on the relationship between its neighboring pixels; for a pixel point

[0065] p(x,y), its neighborhood is defined by different connection rules: 4-neighborhood and 8-neighborhood. The 4-neighborhood method is adopted, that is, the four adjacent pixels above, below, left and right of a pixel are the 4-neighborhood;

[0066] Neighborhood definition formula: N4(p) = {(x,y-1),(x-1,y),(x+1,y),(x,y+1)}.

[0067] A pixel seed is selected through the seed filling algorithm, and all adjacent pixels are recursively expanded until all connected pixels are marked, and different regions in the connected component mark image C are obtained. In 4-connectivity, the connected region C is a set of pixels such that any two pixels are connected in C, that is,

[0068]

[0069] Where: p, q are pixels in the image; f(p) is the grayscale value or label of pixel p; P represents a path from p to q, and all pixels on the path satisfy: connectivity and consistent grayscale values.

[0070] Step 2.6, perform connectivity analysis on the electrode tab area C; obtain the actual area film area D of the electrode tab film area after removing the influence of various noises, etc.;

[0071] Step 2.7, crop the film area obtained after circumscribing the rectangle from the original image A to obtain the film area image E; then perform threshold processing on the film area image E, with the aim of obtaining the foil area F;

[0072] In Step 2.6, after obtaining the set of pixel points, the required set is screened out through morphological features, and feature screening is performed through area, roundness, aspect ratio, and circumscribed rectangle size, with area used as the screening feature;

[0073] The area is defined as the total number of all pixels inside the region, A = ∑1, (x,y) ∈ R; where: A is the number of pixels in the region, and R represents the target region;

[0074] Connect the screened set of pixel points into a whole; given a set of regions R = {R1, R2,..., Rn}, its union is defined as: where: R i represents each individual region, and R union is the merged region. After merging, the outer boundaries of all regions become a whole; obtain the actual area film area D of the electrode tab film area after removing the influence of various noises;

[0075] Perform circumscribed rectangle operation on the film area D, using the minimum circumscribed rotated rectangle operation. For a region, its minimum circumscribed rotated rectangle refers to a rectangle with the smallest area that can completely enclose the region; this rectangle is tilted and rotated, not horizontally aligned;

[0076] Let (x,y) be the coordinates of the center point of the rectangle; \(\phi\) is the rotation angle of the rectangle; L1 is the length of the rectangle, i.e., the major axis direction; L2 is the width of the rectangle, i.e., the minor axis direction;

[0077] The calculated rectangle satisfies: where: the area of the rectangle L1×L2 takes the minimum value, and the rectangle completely encloses the region R.

[0078] Step 2.8, connect the small divided regions after screening out abnormal points into a whole region, and then expand the whole region according to the process standard foil thickness to obtain the expanded foil area G;

[0079] In Step 2.8, perform connectivity analysis on the foil area F, and divide the region after connectivity analysis of the foil area F into multiple small rectangles in the row and column directions;

[0080] Let the size of the input rectangular region R be W×H, and the division parameters: nr: the number of divisions in the row direction; nc: the number of divisions in the column direction;

[0081] The size of each sub-rectangle is: After partitioning, nr × nc small rectangles will be obtained;

[0082] Perform morphological feature screening on the segmented small regions. At this time, the lower limit of the area will be set relatively high to retain the effective target regions, eliminate irrelevant small regions or noise points, and ensure that subsequent processing is only carried out on the effective regions;

[0083] Then, sort the regions after morphological feature screening for subsequent processing in order, and sort them according to the region order; The mathematical definition of sorting is: Let the input region set R = {R1, R2,..., Rn} contain n connected regions; Let each region Ri have the following attributes:

[0084] Starting point of the region: (x i , y i ); Center of gravity of the region: Area of the region: A i ; After sorting, a new order is obtained: R σ(1) , R σ(2) , …, R σ(n) ;

[0085] After sorting, calculate the area and the center point of each region, and use the center point of the region; The definition of the center point of the region is: Let the region R consist of a set of pixel points (xi, yi); Then:

[0086] Let the area A of the region be calculated as the total number of pixels within the region,

[0087] Then, the center of gravity (cx, cy) of the region is calculated by the following formula:

[0088] Where: Cx is the horizontal center point of the region, i.e., the center of gravity in the X direction; Cy is the vertical center point of the region, i.e., the center of gravity in the Y direction;

[0089] The calculation method is similar to the centroid calculation, that is, the sum of the coordinates of all points is taken and the average value is calculated;

[0090] After obtaining the center points of the above-mentioned segmented regions, use the normal distribution method to screen out the discrete points among them as outliers to enhance the stability of the algorithm;

[0091] Mathematical definition of the normal distribution: Where: μ is the mean value, which determines the central position of the normal distribution; σ is the standard deviation, which determines the width of the normal distribution; σ2 is the variance, which represents the degree of dispersion of the data, that is, the fluctuation size of the data around the mean value;

[0092] Connect the small divided regions after screening out abnormal points into a whole region, and then expand the whole region according to process standards to obtain the expanded foil region G.

[0093] Step 2.9: Perform a regional difference operation on the actual foil region F and the expanded foil region G; remove the actual foil region F from the expanded foil region G to obtain a remaining region, and the remaining region is the region where burrs exist, that is, the burr detection region H.

[0094] In step 2.9, let region A and region B be two set regions in the image, and their pixel point coordinates are respectively expressed as:

[0095] A = {(x, y) | (x, y) belongs to A}; B = {(x, y) | (x, y) belongs to B}

[0096] The regional difference operation Difference(A, B) is calculated as follows: A - B = {(x, y) | (x, y) ∈ A, (x, y) ∉ B};

[0097] That is, remove all pixel points within B from A to obtain the remaining region. Remove the actual foil region F from the expanded foil region G to obtain the remaining region, and the remaining region is the region where burrs may exist, that is, the burr detection region H.

[0098] In H, we perform threshold processing (the same method as above), then perform connectivity analysis (the same method as above), and then screen the regions obtained after connectivity analysis according to area for morphological feature screening to screen out the burr defect regions considered in actual process production. Subsequently, sort these burr defect regions according to area for subsequent collation, statistics, and output.

[0099] Those of ordinary skill in the art can understand that the above are only preferred examples of the invention and are not used to limit the invention. Although the invention has been described in detail with reference to the foregoing examples, for those skilled in the art, they can still modify the technical solutions described in the foregoing examples, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, etc. made within the spirit and principle of the invention shall be included within the protection scope of the invention. All technical features in this embodiment can be freely combined according to actual needs.

[0100] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A battery pole piece burr detection device based on machine vision, characterized by: The invention comprises a prism (1), characterized in that: a longitudinal detection camera (6) is installed on the right side of the prism (1), a longitudinal avoidance motor module (5) is fixedly connected to the rear side of the longitudinal detection camera (6), a transverse focus tracking motor module (4) is installed on the bottom right side of the longitudinal detection camera (6), and a transverse detection camera (3) is installed on the left side of the bottom of the transverse focus tracking motor module (4).

2. The burr detection device for battery electrodes based on machine vision according to claim 1, characterized in that: The rear right end of the lateral detection camera (3) is fixedly connected to a Y-axis travel groove (7); the bottom left side of the lateral detection camera (3) is fixedly connected to a through-beam edge measurement sensor (2); the left side of the through-beam edge measurement sensor (2) is rotatably connected to a rotating rod 1 (8); the bottom right side of the through-beam edge measurement sensor (2) is rotatably connected to a rotating rod 2 (9); the rear right end of the through-beam edge measurement sensor (2) is rotatably connected to a rotating rod 3 (10); the prism (1) and the longitudinal detection camera (6) both adopt a square design.

3. A detection method for a burr detection device of battery electrodes based on machine vision according to any one of claims 1 to 2, characterized in that: The specific steps include: Step 1: image the slice to be inspected, obtain the image to be inspected and store it in a cache queue; Step 2: pre-process the image to be detected to obtain the burr area to be detected; Step 3: Preprocess the image of the burr area to reduce noise interference, and screen out possible burrs based on the position of the electrode film area according to different thresholds. According to the actual production size, the number of burrs and their coordinates are determined by the regional characteristics of area and length to locate the monitoring area; Step 4: Perform burr detection on each positioning area to obtain a burr detection result.

4. The method for detecting burrs on battery electrode sheets based on machine vision according to claim 3, wherein: The step 1 specifically includes the following steps: Step 1.1: Adjust the focus tracking module of the detection equipment according to actual needs; Step 1.2, adjust the appropriate light source intensity according to the material characteristics; Step 1.3, photograph the slice to be inspected using an area array camera with a telecentric lens; Step 1.4: The equipment sensor detects the position of the pole piece in real time; In step 1.5, the motor drives the coordinate axis to move, adjusts the camera position, obtains the image to be detected and stores it in the cache queue.

5. The method for detecting burrs on battery electrodes based on machine vision according to claim 3, characterized in that: The step 2 specifically includes the following steps: Step 2.1, the collected initial image of the slice to be detected is named A; Step 2.2: threshold the initial image A. By setting one or more thresholds, the pixels of the image are divided into different categories for binarization, so that the target area is separated from the background. A fixed threshold is used, and the concave point at the boundary between the background and foreground in the histogram is selected as the threshold through histogram analysis. Step 2.3, after selecting an appropriate threshold according to the image boundary, separate the polar region B from the original image A; Step 2.4, performing a pre-processing operation of smoothing and denoising on the obtained pole piece region B using a denoising method of image morphological operation; Step 2.5, after performing an opening operation on the pole piece region B, the pole piece region C is obtained after removing small noises and smoothing the target boundary; Step 2.6, perform connectivity analysis on the electrode area C; obtain the actual area membrane area D of the electrode membrane area after removing various noises and other influences; Step 2.7, cropping the film area obtained by the circumscribed rectangle from the original image A to obtain the film area image E; then performing threshold processing on the film area image E to obtain the foil area F; Step 2.8: Connect the segmented small areas after filtering out the abnormal points into a whole area, and then expand the whole area according to the process standard foil thickness to obtain the expanded foil area G; In step 2.9, a regional difference operation is performed on the actual foil area F and the expanded foil area G; the actual foil area F is removed from the expanded foil area G to obtain a remaining area, which is the area where the burrs exist, namely the burr detection area H.

6. The method for detecting burrs on battery electrodes based on machine vision according to claim 5, characterized in that: In step 2.4, the principle of the opening operation is as follows: let the input image I(x,y) be a grayscale image; let the structure element SE be B; The opening operation is recorded as: Where: I represents the input image, B represents the structural element; Among them, corrosion Under the action of the structural element B, the minimum gray value in the neighborhood is taken with (x, y) as the central position, where (s, t) ∈ B, and s and t represent the offset coordinates in the structural element B; it is used to remove small areas, shrink the target area, and eliminate isolated noise points; Dilation I⊕B: Under the action of the structuring element B, the maximum gray value in the neighborhood is taken with (x, y) as the center position, where (s, t) ∈ B, and s and t represent the offset coordinates in the structuring element B; it is used to restore the main structure of the target area after erosion.

7. A method for detecting burrs on battery electrodes based on machine vision according to claim 5, characterized in that: In step 2.5, in a digital image, the connectivity of pixels is based on the relationship between their neighboring pixels. For a pixel p(x, y), its neighborhood is defined by different connectivity rules: 4-neighborhood and 8-neighborhood. The 4-neighborhood method is used, that is, the four adjacent pixels above, below, left, and right of a pixel constitute the 4-neighborhood. A pixel seed is selected through the seed filling algorithm, and all adjacent pixels are recursively expanded until all connected pixels are marked, and different regions in the connected component mark image C are obtained. In 4-connectivity, the connected region C is a set of pixels such that any two pixels are connected in C, that is, Where: p, q are pixels in the image; f(p) is the grayscale value or label of pixel p; P represents a path from p to q, and all pixels on the path satisfy: connectivity and consistent grayscale values.

8. A method for detecting burrs on battery electrodes based on machine vision according to claim 3, characterized in that: In step 2.6, after obtaining the pixel set, the required set is screened out using morphological features. Feature screening is performed based on area, roundness, aspect ratio, and circumscribed rectangle size, with area being used as the screening feature. The area is defined as the total number of pixels within the region, A = ∑1, (x, y) ∈ R; where: A is the number of pixels in the region, R represents the target area; Connect the filtered set of pixel points into a whole; given a set of regions \(R = \{R_1, R_2, \ldots, R_n\}\), its union is defined as: where: \(R\) i represents each individual region, and \(R\) union is the merged region. After merging, the outer boundaries of all regions become a whole; the actual region of the pole piece film area \(D\) after removing the influence of various noises is obtained. Perform a bounding rectangle operation on the membrane area D using the minimum bounding rotated rectangle operation. For a region, its minimum bounding rotated rectangle is a rectangle with the smallest area that can completely enclose the region; this rectangle is tilted and rotated, and is not horizontally aligned. Let (x, y) be the coordinates of the center point of the rectangle; \phi is the rotation angle of the rectangle; L1 is the length of the rectangle, i.e. the direction of the major axis; L2 is the width of the rectangle, i.e. the direction of the minor axis; The calculated rectangle satisfies: where: the area L1×L2 of the rectangle takes the minimum value, and the rectangle completely encloses the region R.

9. A method for detecting burrs on battery electrodes based on machine vision according to claim 8, characterized in that: In step 2.8, a connectivity analysis is performed on the foil region F, and the region after the connectivity analysis of the foil region F is divided into a plurality of small rectangles in row and column directions; Assume that the size of the input rectangular region R is W×H, and the partitioning parameters are: nr: the number of partitions in the row direction; nc: the number of partitions in the column direction; The size of each sub-rectangle is: After partitioning, nr × nc small rectangles will be obtained; Morphological feature screening is performed on the segmented small areas. The lower limit of the area is set higher in this case to retain the valid target area and remove irrelevant small areas or noise points, ensuring that subsequent processing is performed only on the valid area. Next, sort the regions after morphological feature screening to facilitate subsequent processing in order, and sort them according to the region order; the mathematical definition of sorting is: Let the input region set R = {R1, R2,..., Rn} contain n connected regions; Let each region Ri have the property: Region starting point: (x i , y i ); Region centroid: Region area: A i ; After sorting, a new order is obtained: R σ (1), R σ (2), …, R σ ( n ); After sorting, calculate the area and the center point of each region, and use the center point of the region; the definition of the center point of the region is: Let the region R be composed of a set of pixel points (xi, yi); then: Let the area A of the region be calculated as the total number of pixels within the region, The center of gravity (cx, cy) of the region is calculated by the following formula: where: Cx is the horizontal center point of the region, i.e., the centroid in the X direction; Cy is the vertical center point of the region, i.e., the centroid in the Y direction; The calculation method is similar to the centroid calculation, that is, the sum of the coordinates of all points is taken and averaged; After obtaining the center points of the above-mentioned segmented regions, use the method of normal distribution to screen out the discrete points among them as abnormal points to be removed to enhance the stability of the algorithm; Mathematical definition of normal distribution: Where: μ is the mean, which determines the central position of the normal distribution; σ is the standard deviation, which determines the width of the normal distribution; σ2 is the variance, representing the degree of dispersion of the data, that is, the magnitude of the fluctuation of the data around the mean; Connect the small segmented regions after removing the abnormal points into a whole region, and then expand the whole region according to the process standard to obtain the expanded foil region G.

10. The method for detecting burrs on battery pole pieces based on machine vision according to claim 9, characterized in that: In step 2.9, let regions A and B be two set regions in the image, and their pixel point coordinates are respectively expressed as: A = {(x, y) | (x, y) belongs to A}; B = {(x, y) | (x, y) belongs to B} The region difference operation Difference(A, B) is calculated as follows: A - B = {(x, y) | (x, y) ∈ A, (x, y) ∈ / B}; That is, remove all pixel points in B from A to obtain the remaining region. Remove the actual foil region F from the expanded foil region G to obtain the remaining region. The remaining region is the region where burrs may exist, that is, the burr detection region H.

Images