Battery piece laser spot width measuring method and system based on machine vision

Abstract

The invention relates to a method and a system for measuring the width of a laser spot of a battery piece based on machine vision. Comprising the following steps of image acquisition, image color space conversion, image binaryzation, laser spot detection, image positioning and segmentation, segmented image amplification, segmented image binaryzation, segmented image closed operation, segmented image laser spot detection, laser spot width calculation and result output. According to the battery piece laser spot width measurement method based on machine vision, laser spot width measurement is carried out based on a camera, in a certain height range, a high-power lens does not need to be repeatedly adjusted, the width of the laser spot can be simply and rapidly measured, the measurement precision is improved, the measurement speed is high, the equipment cost is low, and the method is suitable for large-scale popularization and application. Online detection can be realized, and the automation degree is high.

Description

Technical Field

[0001] The present invention relates to a method for grooving a solar cell, and in particular to a method and system for measuring the laser spot width of a solar cell based on machine vision. Background Art

[0002] In the photovoltaic industry, solar cells are the core components of photovoltaic modules, and their production quality directly impacts the performance and efficiency of these modules. Laser technology is widely used in the production and testing of solar cells, with related processes including laser doping and laser grooving. Laser grooving creates fine grooves on the surface of the cell, creating selective emitters or localized back fields, thereby improving the cell's photoelectric conversion efficiency. Laser grooving is a non-contact processing technology that optimizes electrode contact on the cell surface. It offers high precision, flexibility, fast processing speed, and low manufacturing costs, enabling high-efficiency cell technology.

[0003] Slot width is one of the key parameters affecting battery performance. Slot width that is too wide or too narrow will increase series resistance or carrier recombination rate, thereby reducing battery efficiency. Accurately measuring slot width is an important means of ensuring the quality of the laser slotting process. The main measurement methods include optical microscopy, laser scanning, confocal microscopy, and machine vision. Optical microscopy is slow, making it difficult to meet online testing requirements and requiring a high level of operator skill. Laser scanning measurement equipment is expensive and requires high laser beam focusing accuracy and stability. Confocal microscopy is expensive and slow, making it difficult to meet large-scale production requirements. Machine vision measurement is fast and suitable for automated online testing. Summary of the Invention

[0004] To solve the above problems, the present invention provides a method for measuring the laser spot width of a cell based on machine vision. The specific technical solution is as follows: A method for measuring the width of a laser spot of a cell based on machine vision comprises the following steps: image acquisition, acquiring a color image of the cell; image color space conversion, obtaining an H-component image of a type A cell; image binarization, removing noise by selecting a minimum threshold and a maximum threshold to obtain a binary image; laser spot detection, extracting edge information of the laser spot of the cell according to the binary image, and obtaining an image with one or more laser spots by a contour detection algorithm; image positioning and segmentation, first positioning a spot area on the obtained image with one or more laser spots, and then segmenting the H-component image of the type A cell according to the positioning information and the width information of the real-time acquired image; segmented image amplification, and adjusting the scale factor along the horizontal axis. fx Set to 1, the scale factor along the vertical axis fySet to 10, use the bicubic interpolation method to enlarge the segmented image; binarize the segmented image, remove noise through the selected minimum threshold and maximum threshold; close the segmented image, use the closing operation according to the segmented binary image, first connect the disconnected areas of the laser spot, and then refine the upper and lower boundaries of the laser spot; detect the laser spot of the segmented image, extract the laser spot area through the contour detection algorithm according to the closed operation image, and the number of this area is 1; calculate the laser spot width, calculate the fitting line width midWidth, the new width set average avgWidth and the new width set median medWidth according to the contour information of the laser spot; output the result, output the laser spot edge display image and the obtained laser spot width data.

[0005] Preferably, the contour detection algorithm includes the following steps: extracting the contour of the laser spot, detecting only the outermost contour, compressing the horizontal, vertical and diagonal line segments, and retaining only their endpoints, first finding all contours, each contour is stored as a vector of a point, and filtering out the laser spot area through area features; extracting the contour of the laser spot, detecting only the outermost contour, compressing the horizontal, vertical and diagonal line segments, and retaining only their endpoints; finding all contours, each contour is stored as a vector of a point; filtering out the enlarged laser spot area through area features.

[0006] Preferably, the image positioning and segmentation includes the following steps: when it is assumed that the length of the upper boundary is greater than a certain ratio of the width of the acquired image for the first time, it is determined that this boundary is the upper boundary of the first laser spot found, the number of rows of the upper margin is topPoint, the coordinates of the upper left vertex of the first spot are found to be (0, topPoint), this point is offset upward by 300 pixels, and the coordinates of the upper left vertex of the segmented image are (0, topPoint-300). If topPoint-300 is less than 0, the vertex coordinates are (0,0); starting from the number of rows of the upper boundary topPoint found, the lower boundary of the laser spot is found. When it is assumed that the size of the lower boundary is greater than a certain ratio of the width of the acquired image for the first time, it is determined that this boundary is the lower boundary of the first laser spot found. The number of rows of the lower boundary is bottomPoint, the coordinates of the lower left bottom point of the first laser spot are found to be (0, bottomPoint), this point is offset downward by 300 pixels, and the coordinates of the lower left bottom point of the segmented image are (0, bottomPoint +300). If bottomPoint +300 is less than the height h of the acquired image, then the bottom point coordinate is (0, h); the segmented image width is calculated based on the coordinates of the upper left vertex and the lower left bottom point of the first laser spot after the offset; the H component image of the type A battery cell is segmented based on the coordinates of the upper left vertex of the first laser spot after the offset, the segmented image width and the width information of the acquired image.

[0007] Preferably, the laser spot width calculation includes the following steps: according to the amplified laser spot area image, extracting the contour information of the upper boundary of the laser spot, first establishing a dynamic array topPoints of a two-dimensional point type, and then using a contour detection algorithm to store the points that meet the conditions into topPoints; according to the topPoints two-dimensional point set, iteratively fitting a straight line based on the M estimation method, and the M estimator uses Manhattan distance to robustly measure the degree of deviation between the data points and the straight line; wherein the radial accuracy and the angular accuracy are both 0.01, and the fitted laser spot upper boundary straight line contains a 4-element vector (vx, vy, x0, y0), wherein (vx, vy) is a normalized vector collinear with the straight line, and (x0, y0) is a point on the straight line; based on the amplified laser spot area image, the contour information of the lower boundary of the laser spot is extracted, and a dynamic array of two-dimensional point type botPoints is first established. Then, the contour detection algorithm is used to search for the lower boundary point from bottom to top, and then the point that meets the conditions is stored in botPoints; based on the botPoints two-dimensional point set, a straight line is iteratively fitted based on the M estimation method, and the radial accuracy and angular accuracy are both 0.01. The fitted laser spot lower boundary straight line contains a 4-element vector (vx, vy, x0, y0), where (vx, vy) is a normalized vector collinear with the straight line, and (x0, y0) is a point on the straight line; the distance midWidth between the two straight lines is calculated based on the fitted laser spot upper boundary line parameters and the lower boundary line parameters.

[0008] Furthermore, the calculation of the distance midWidth between the two straight lines includes the following steps: establishing a dynamic array widths, and then calculating a laser spot width set based on the upper and lower boundary point sets of the laser spot and storing it in widths; after deleting a certain proportion of width values ​​that are too large and too small in the width set widths, generating a new laser spot width set newWidths; calculating the average value avgWidth and median medWidth of the new width set newWidths; and converting the pixel width into the actual physical width according to the actual calibration parameters.

[0009] A machine vision-based cell laser spot width measurement system, used for the machine vision-based cell laser spot width measurement method, comprises: a camera; a high-magnification lens, provided on the camera; a light source, provided on the high-magnification lens; a conveyor, used for conveying cells and located below the high-magnification lens; and an industrial computer, respectively connected to the camera, the light source and the conveyor, for acquiring images through the camera and processing the acquired images to obtain the cell laser spot width.

[0010] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method for measuring the width of a laser spot of a battery cell based on machine vision. The method measures the width of the laser spot using a camera. Within a certain height range, the method does not require repeated adjustment of a high-magnification lens. The method can be operated simply and quickly to measure the width of the laser spot, thereby improving the measurement accuracy. The method also has a fast measurement speed and low equipment cost, and can realize online detection with a high degree of automation. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a flow chart of the measurement method of this application; Figure 2 It is a structural diagram of the measurement system of this application. DETAILED DESCRIPTION

[0012] The present invention will now be further described with reference to the accompanying drawings.

[0013] A machine vision-based method for measuring the width of a cell laser spot uses hardware such as a camera, a high-magnification lens, and a light source to measure the width of the laser spot. Within a certain height range, there is no need to repeatedly adjust the high-magnification lens. The method can be operated simply and quickly to measure the width of the laser spot, thereby improving measurement accuracy.

[0014] like Figure 1 As shown, a method for measuring the width of a laser spot of a cell based on machine vision includes the following steps: S01: Image acquisition: Coaxial light is irradiated vertically on the solar cell to be measured. When the cell reaches the field of view of the high-magnification lens, the industrial camera captures a color image in real time through the high-magnification lens. S02: Image color space conversion; Comparing the edge information of the laser spot of type A cells in grayscale color space, BGR color space, and HSV color space, the results show that the edge information of type A cells is more obvious in HSV color space, especially in the hue H component. Therefore, the following operations are all based on the hue H component image.

[0015] S03: image binarization; The H component image of the A-type battery sheet is binarized. The H component image is an 8-bit single-channel image. Noise is removed by selecting the minimum and maximum thresholds, that is, pixels with values ​​that are too small or too large are filtered out, and an image of the same size, type, and number of channels as the input is output.

[0016] S04: Laser spot detection; In the image obtained in S03, non-zero pixels are regarded as 1 and zero pixels are regarded as 0. Based on this image, the contour detection algorithm is used to extract the contour of the laser spot. The contour retrieval mode is to detect only the outermost contour. The contour approximation method is to compress the horizontal, vertical and diagonal line segments and retain only their endpoints. According to the above method, all contours are first found, and each contour is stored as a vector of points. The laser spot area is screened out by area features. Since the areas of the laser spots are relatively close, there are one or more laser spots on the image at this time.

[0017] S05: Image localization and segmentation; Next, we need to locate a light spot area for analysis. According to the image obtained in S04, there are other light spots and other invalid information areas. Therefore, we first locate the required light spot area and then segment it according to the located area. The following steps can be included: b01: When the upper boundary is assumed to be larger than a certain ratio of the original image width, this boundary is determined to be the upper boundary of the first light spot found. From this, it can be concluded that the row number at this time is topPoint. Then the coordinates of the upper left vertex of the first light spot are found to be (0, topPoint). This point is offset 300 pixels upward, and the coordinates of the upper left vertex of the segmented image are (0, topPoint-300). If topPoint-300 is less than 0, the vertex coordinates are (0,0). b02: Start from the row number topPoint of the upper boundary found to find the lower boundary of the laser spot. When it is assumed that the size of the lower boundary is larger than a certain ratio of the width of the original image, this boundary is determined to be the lower boundary of the first spot found. It can be concluded that the row number at this time is bottomPoint. Then the coordinates of the lower left bottom point of the first spot are found to be (0, bottomPoint). This point is offset 300 pixels downward. The coordinates of the lower left bottom point of the segmented image are (0, bottomPoint +300). If bottomPoint +300 is less than the height h of the acquired image, the coordinates of the bottom point are (0, h). b03: Calculating the segmented image width according to the coordinates of the upper left vertex and the lower left base point of the first laser spot after the shift; b04: Segment the hue H component image according to the coordinates of the upper left vertex of the first laser spot after the shift, the segmented image width, and the width information of the collected image.

[0018] S06: Segmented image enlargement; To improve the width measurement accuracy, the scale factor along the horizontal axis is changed fx and the scale factor along the vertical axis fy The two parameters amplify and segment the image. The parameter that has the greatest impact on the measurement accuracy of the laser spot width is the scale factor along the vertical axis. fyIt can be set to 10 or 20, etc., and the laser spot length can remain unchanged. fx Set to 1 to use the bicubic interpolation method, which is a bicubic interpolation method based on a 4x4 pixel neighborhood. When enlarging the image, although this method is slightly slower, it is the best for enhancing image details and avoiding aliasing. Therefore, the segmented image obtained by S05 is enlarged according to the above method.

[0019] S07: Segmentation image binarization; The obtained segmented image is binarized and noise is removed by the selected minimum and maximum thresholds, that is, pixels with values ​​that are too small or too large are filtered out. Since image magnification enhances the details in the image, the two thresholds at this time are different from the thresholds before magnification, and the output is an image of the same size, type, and number of channels as the input.

[0020] S08: Segmented image closing operation; According to the segmented binary image obtained by S07, there are many isolated noise points on it, which may affect the image quality. At the same time, there are many disconnected areas in the laser spot area of ​​this binary image. The degree of disconnection of the spot area collected at different heights is different, which is not conducive to the extraction of the spot area. Therefore, in order to improve the robustness, morphological processing is used; Morphological processing is widely used in machine vision. It mainly includes corrosion, expansion and closing operations that are a combination of the former two methods. Erosion is a basic morphological processing method. As shown in formula (1), this method uses the specified structural element B To erode the source image, the structural element determines the shape of the pixel neighborhood where the minimum value is taken. B The origin of the segmented binary image moves along the boundary of the white area set A, and the structural elements beyond the boundary are not included in the set A In the comparison of the initial set A Significantly reduced, which manifests itself on the image as "thinning" of the laser spot edge, noise, and disconnected areas. If only the erosion operation is used, the disconnected area will increase, and if there are large or numerous defects in the spot area, it will be difficult to determine the lower boundary position. (1); Dilation is also a basic morphological processing method, as shown in formula (2), this method uses the specified structural element B To dilate the source image, the structural element determines the shape of the pixel neighborhood that takes the maximum value. B The origin of the segmented binary image is along the white area set A The boundary of the structure element is moved and collection A The intersection is not empty, compared with the initial setA The image is significantly enlarged, which manifests as "coarsening" of the laser spot edge, noise, and disconnected areas. If only the dilation operation is used, when there is a lot of noise smaller than the structural element on the edge, the dilation will connect the noise and the boundary, which is not conducive to the accurate positioning of the boundary position; (2); The closing operation is a composite operation, which manifests itself on the image as first dilating ("coarsening") and then corroding ("refining") the laser spot edge and noise. When setting the size of the structural element, both the boundary noise distribution and the degree of connectivity of the disconnected area must be considered. The shape of the structural element is a rectangle with the origin at the center of the element. It should be noted that the closing operation with two iterations is dilation > dilation > erosion > erosion. The pixel extrapolation method uses the constant filling method. Processing the image according to the above method can achieve the effect of connecting disconnected areas while improving the accuracy of edge detection.

[0021] S09: Segmentation image laser spot detection; Based on the image obtained in S08, a contour detection algorithm is used to extract the contour of the laser spot. The contour retrieval mode is to detect only the outermost contour. The contour approximation method is to compress horizontal, vertical, and diagonal line segments and retain only their endpoints. According to the above method, all contours are first found, and each contour is stored as a vector of points. The laser spot area is filtered out by area features. It should be noted that since image magnification enhances the details in the image, the area feature value at this time is different from that before magnification.

[0022] S10: Calculation of laser spot width; According to the contour information of the laser spot, calculate its width. The specific steps are as follows: c01: Extract the contour information of the upper boundary of the laser spot. First, create a dynamic array of two-dimensional point type topPoints, and then use the contour detection algorithm to store the points that meet the conditions into topPoints; c02: Based on the topPoints two-dimensional point set, a straight line is iteratively fitted based on the M estimation method. Although the least squares method is the most commonly used straight line fitting method, this method is easily affected by noise. The noise distribution distance around the boundary of the image to be analyzed is very large. Therefore, the distance calculation formula used by the M estimator is shown in formula (3). The radial accuracy (the distance between the coordinate origin and the straight line) and the angular accuracy are both 0.01. The upper boundary straight line of the laser spot fitted in the above way contains a vector of 4 elements (vx, vy, x0, y0), where (vx, vy) is a normalized vector collinear with the straight line, and (x0, y0) is a point on the straight line; (3); In the formula, the distance Dis the Manhattan distance (L1 norm), which is used to robustly measure the degree of deviation between the data point and the straight line; the coordinates of the data point ( x 1, y 1) is the input observation value, ( x 2, y 2) It is the projection point on the line closest to the data point.

[0023] c03: Extract the contour information of the lower boundary of the laser spot. First, create a dynamic array of two-dimensional point type botPoints. Since the image obtained according to S09 is basically noise-free outside the laser spot and there are disconnected areas in the spot area, a contour detection algorithm is used to search for the lower boundary point from bottom to top, and then the points that meet the conditions are stored in botPoints; c04: Based on the botPoints two-dimensional point set, a straight line is iteratively fitted using the M estimation method. The distance calculation formula used by the M estimator is shown in formula (3). The radial accuracy (the distance between the coordinate origin and the straight line) and the angular accuracy are both 0.01. The lower boundary line of the laser spot fitted in the above way contains a vector of 4 elements (vx, vy, x0, y0), where (vx, vy) is a normalized vector collinear with the straight line, and (x0, y0) is a point on the line; c05: The distance between the two straight lines is calculated as midWidth based on the fitted straight lines c02 and c04; c06: First, a dynamic array widths is created, and then the laser spot width set is calculated based on the upper and lower boundary point sets of the c01 and c03 laser spots and stored in widths; c07: After deleting a certain proportion of excessively large and small width values ​​in the width set widths, a new laser spot width set newWidths is generated; c08: Calculate the average value avgWidth and median value medWidth of the new width set newWidths; c09: Convert pixel width to actual physical width based on actual calibration parameters.

[0024] S11: result output; Output the laser spot width measurement results, mainly including the laser spot edge display image and the laser spot width data obtained by the three calculation methods described in S10, including the fitting line width midWidth, the new width set average value avgWidth and the new width set median medWidth.

[0025] like Figure 2As shown, a machine vision-based solar cell laser spot width measurement system includes a camera 1, a high-magnification lens 2, a light source 3, a conveyor 5 and an industrial computer 6; the camera 1 can be an industrial camera, the high-magnification lens 2 is mounted on the camera 1 and is located above the conveyor 5, and the conveyor 5 is a belt conveyor; the light source 3 can be a coaxial light source, and the light source 3 is mounted on the high-magnification lens 2. The industrial computer 6 is respectively connected to the camera 1, the light source 3 and the conveyor 5, and is used to collect images through the camera 1 and process the collected images to obtain the solar cell laser spot width.

[0026] The camera 1 and the high-power lens 2 are connected in sequence and fixed vertically by the profile. The coaxial light source 3 is placed horizontally in the observation hole on the right side of the high-power lens. The battery cell 4 is placed horizontally on the conveyor 5. In order to facilitate positioning, a battery cell 4 positioning device is set to adjust the position before the battery cell 4 reaches the field of view of the high-power lens 2. The camera 1 maintains a communication connection with the industrial computer 6, which integrates a communication module, an image processing module, and a storage module.

[0027] When the battery cell 4 passes through the conveyor 5 and reaches the field of view of the high-power lens 2, the light emitted by the light source 3 is vertically irradiated on the battery cell 4. At this time, a very small part of the light is absorbed by the object, and most of the light is reflected on the surface of the battery cell 4. This part of the reflected light enters the high-power lens 2, and the industrial computer 6 sends a control signal to the camera 1. When the camera 1 receives the control signal, it starts to collect the image of the battery cell 4 and feeds back the image information to the industrial computer 6. The image processing module of the industrial computer 6 calculates the width of the laser spot, and the storage module stores the relevant data. The implementation method in the image processing module is the machine vision battery laser spot width measurement method based on the above embodiment.

[0028] The technical principles of the present invention have been described above with reference to specific embodiments. These descriptions are intended solely to illustrate the principles of the present invention and are not to be construed in any way as limiting the scope of protection of the present invention. Based on the explanations herein, those skilled in the art will readily devise other specific embodiments of the present invention without inventive effort, and such embodiments will fall within the scope of protection of the claims of the present invention.

Claims

1. A method for measuring the width of a laser spot of a cell based on machine vision, characterized in that: The following steps are involved: Image acquisition, collecting color images of battery cells; Image color space conversion to obtain the H component image of type A battery; Image binarization, removing noise by selecting minimum and maximum thresholds to obtain a binary image; Laser spot detection: extracting edge information of the laser spot of the cell based on the binary image, and obtaining an image with one or more laser spots using a contour detection algorithm; Image positioning and segmentation: first locate a spot area on the image with one or more laser spots, and then segment the H component image of the A-type battery cell based on the positioning information and the width information of the real-time acquired image; Segmented image magnification, scale factor along the horizontal axis fx Set to 1, the scale factor along the vertical axis fy Set to 10, use bicubic interpolation method to enlarge the segmented image; The segmented image is binarized and noise is removed by selecting the minimum and maximum thresholds; Segmentation image closing operation, based on the segmented binary image, adopts closing operation to first connect the disconnected areas of the laser spot, and then refine the upper and lower boundaries of the laser spot; Segmentation image laser spot detection, extracting the laser spot area through the contour detection algorithm according to the closed operation image, and the number of this area is 1; Laser spot width calculation: according to the laser spot profile information, calculate the fitting line width midWidth, the new width set average value avgWidth and the new width set median medWidth; The result is output, which includes the laser spot edge display image and the obtained laser spot width data.

2. The method for measuring the laser spot width of a cell based on machine vision according to claim 1, characterized in that: The contour detection algorithm comprises the following steps: Extract the contour of the laser spot, only detect the outermost contour, compress the horizontal, vertical and diagonal line segments, and retain only their endpoints. First, find all contours, each contour is stored as a vector of points, and the laser spot area is filtered out by area features; Extract the contour of the laser spot, detect only the outermost contour, compress the horizontal, vertical and diagonal line segments, and only retain their endpoints; Find all contours, each stored as a vector of points; The amplified laser spot area is selected through area characteristics.

3. The method for measuring the laser spot width of a cell based on machine vision according to claim 1, characterized in that: The image positioning and segmentation comprises the following steps: When it is assumed that the length of the upper boundary is greater than a certain ratio of the width of the acquired image for the first time, this boundary is determined to be the upper boundary of the first laser spot found, the number of rows of the upper margin is topPoint, the coordinates of the upper left vertex of the first laser spot are found to be (0, topPoint), and this point is offset 300 pixels upward. The coordinates of the upper left vertex of the segmented image are (0, topPoint-300). If topPoint-300 is less than 0, the vertex coordinates are (0,0); Starting from the topPoint of the upper boundary, the lower boundary of the laser spot is found. When the size of the lower boundary is assumed to be greater than a certain ratio of the width of the acquired image for the first time, this boundary is determined to be the first lower boundary of the laser spot found. The number of rows of the lower boundary is bottomPoint. The coordinates of the lower left bottom point of the first laser spot are found to be (0, bottomPoint). This point is offset downward by 300 pixels. The coordinates of the lower left bottom point of the segmented image are (0, bottomPoint +300). If bottomPoint +300 is less than the height h of the acquired image, the coordinates of the bottom point are (0, h). The width of the segmented image is calculated based on the coordinates of the upper left vertex and the lower left base point of the first laser spot after the offset; The H component image of the A-type battery sheet is segmented according to the coordinates of the upper left vertex of the first laser spot after the shift, the segmented image width, and the width information of the collected image.

4. The method for measuring the laser spot width of a cell based on machine vision according to claim 1, characterized in that: The laser spot width calculation includes the following steps: According to the amplified laser spot area image, the contour information of the upper boundary of the laser spot is extracted, a dynamic array topPoints of a two-dimensional point type is first established, and then the points that meet the conditions are stored in topPoints using a contour detection algorithm; According to the topPoints two-dimensional point set, a straight line is iteratively fitted based on the M-estimator method. The M-estimator uses Manhattan distance to robustly measure the degree of deviation between the data points and the straight line. The radial accuracy and angular accuracy are both 0.

01. The fitted upper boundary line of the laser spot contains a four-element vector (vx, vy, x0, y0), where (vx, vy) is a normalized vector collinear with the line, and (x0, y0) is a point on the line. According to the amplified laser spot area image, the contour information of the lower boundary of the laser spot is extracted, and a dynamic array of two-dimensional point type botPoints is first established. Then, the contour detection algorithm is used to find the lower boundary point from bottom to top, and then the points that meet the conditions are stored in botPoints; Based on the botPoints two-dimensional point set, a straight line is iteratively fitted using the M-estimation method. The radial and angular accuracies are both 0.

01. The fitted lower boundary line of the laser spot contains a four-element vector (vx, vy, x0, y0), where (vx, vy) is a normalized vector collinear with the line, and (x0, y0) is a point on the line. The distance midWidth between the two lines is calculated based on the fitted upper boundary line parameters and lower boundary line parameters of the laser spot.

5. The method for measuring the laser spot width of a cell based on machine vision according to claim 4, characterized in that: The calculation of the distance midWidth between two straight lines includes the following steps: Create a dynamic array widths, and then calculate the laser spot width set according to the upper and lower boundary point sets of the laser spot and store it in widths; After deleting a certain proportion of the width values ​​that are too large or too small in the width set widths, a new laser spot width set newWidths is generated; Calculate the average value avgWidth and median value medWidth of the new width set newWidths; Convert the pixel width to the actual physical width according to the actual calibration parameters.

6. A machine vision-based solar cell laser spot width measurement system, used in the machine vision-based solar cell laser spot width measurement method according to claim 1, characterized in that: include: camera; a high-magnification lens, provided on the camera; a light source, disposed on the high-power lens; A conveyor, used for conveying battery cells, and located below the high-power lens; as well as An industrial computer is connected to the camera, the light source and the conveyor respectively, and is used to collect images through the camera and process the collected images to obtain the laser spot width of the battery cell.

Images