Method and system for measuring welding mark height of new energy lithium battery

Abstract

The invention provides a new energy lithium battery welding mark height-oriented measurement method and measurement system, and the method comprises the steps: carrying out the line structure light scanning of a lithium battery pole piece through the measurement system for the new energy lithium battery welding mark height, and obtaining a light strip image; graying the light strip image to obtain a grayscale image; performing bilateral filtering on the grayscale image to obtain a filtered image; performing threshold segmentation on the filtered image based on a maximum between-class variance method, and extracting a region of interest to obtain a target image; performing sub-pixel center extraction on the target image based on a line center extraction algorithm to obtain sub-pixel coordinates of a light strip center line; and on the basis of a predetermined relational expression and the sub-pixel coordinates, obtaining the height of the lithium battery pole piece welding print corresponding to the sub-pixel coordinates.

Description

Technical Field

[0001] The present disclosure relates to the fields of computer vision technology and precision engineering measurement technology, and more specifically, to a method and system for measuring weld mark height of new energy lithium batteries. Background Art

[0002] High-precision measurement technology is widely needed in advanced manufacturing and cutting-edge scientific research. With the advancement of science and technology and industrial manufacturing, especially the vigorous development of new energy vehicles, integrated circuits and other industries, the detection accuracy requirements for key geometric parameters such as the size and morphology of key components in related fields are getting higher and higher, which puts forward higher demands on high-precision detection technology.

[0003] With the rapid development of the new energy vehicle industry, the demand for new energy lithium batteries has increased significantly. Lithium batteries are mainly composed of positive and negative electrodes, diaphragms and electrolytes. The positive and negative electrodes realize the charging and discharging functions of lithium batteries and are the core components of lithium batteries. The welding process of the electrode is a key part of the lithium battery production process chain. In the welding process of new energy lithium batteries, defects such as bulges on the welding surface will inevitably appear, which will affect the quality and life of the battery. When the weld print height of the lithium battery electrode is inconsistent, it will cause a higher weld print to break through the dielectric layer, resulting in battery failure and causing major safety hazards. Therefore, it is necessary to measure the weld print height of the lithium battery electrode to monitor and detect the welding quality and ensure the quality of the welding process.

[0004] At present, the degree of automation in lithium battery production workshops is not high. Domestic inspection of lithium battery after welding is mainly based on manual inspection. Generally, a micrometer is used to measure the height of the weld mark. The measurement mode is contact measurement. The measurement process will affect the actual height of the weld. In addition, manual inspection is heavily dependent on the technical level and experience of the inspectors, and is affected by human subjective factors. It has great uncertainty and poor measurement repeatability, making it difficult to ensure the quality and efficiency of the inspection. Summary of the invention

[0005] In view of this, the present disclosure provides a method and system for measuring the weld mark height of new energy lithium batteries.

[0006] According to one aspect of the present disclosure, a method for measuring the weld mark height of a new energy lithium battery is provided, comprising: performing line structured light scanning on a lithium battery pole piece using a measurement system for the weld mark height of a new energy lithium battery to obtain a light strip image, wherein the spatial position of each device included in the measurement system for the weld mark height of a new energy lithium battery is determined based on the system parameters of the measurement system for the weld mark height of a new energy lithium battery, and the system parameters of the measurement system for the weld mark height of a new energy lithium battery are calculated using a Monte Carlo optimization algorithm with system sensitivity as the objective function, and the system sensitivity characterizes the physical properties of the lithium battery pole piece. When the point moves a unit distance in the depth direction, the image point corresponding to the above object point deviates from the reference point by a moving distance; the above light strip image is grayed to obtain a grayscale image; the above grayscale image is bilaterally filtered to obtain a filtered image; based on the maximum inter-class variance method, the above filtered image is threshold segmented and the region of interest is extracted to obtain a target image, wherein the above target image includes a lithium battery pole piece weld mark; based on the line center extraction algorithm, the sub-pixel center of the above target image is extracted to obtain the sub-pixel coordinates of the light strip center line; based on a predetermined relationship and the above sub-pixel coordinates, the height of the lithium battery pole piece weld mark corresponding to the above sub-pixel coordinates is obtained.

[0007] According to an embodiment of the present disclosure, the system parameters of the above-mentioned measurement system for the weld mark height of new energy lithium batteries are obtained according to the following operations: determining the objective function according to the working angle, object distance and lens focal length, wherein the above-mentioned working angle represents the angle between the optical axis of the laser in the above-mentioned measurement system for the weld mark height of new energy lithium batteries and the optical axis of the camera in the above-mentioned measurement system for the weld mark height of new energy lithium batteries, the above-mentioned object distance represents the distance between the center of the lens of the above-mentioned camera and the point where the optical axis of the laser is projected onto the above-mentioned lithium battery pole piece, and the above-mentioned lens focal length represents the focal length of the lens of the above-mentioned camera; determining the constraint functions corresponding to the above-mentioned working angle, image distance and height measurement range respectively according to the above-mentioned working angle, the above-mentioned object distance and the above-mentioned lens focal length; generating M groups of random numbers corresponding to the above-mentioned working angle, the above-mentioned object distance and the above-mentioned lens focal length respectively according to the Monte Carlo optimization algorithm, wherein M is a positive integer; determining the above-mentioned system parameters according to the M groups of random numbers, the above-mentioned objective function and the above-mentioned constraint function.

[0008] According to an embodiment of the present disclosure, each group of random numbers includes a working angle random number corresponding to the working angle, an object distance random number corresponding to the object distance, and a lens focal length random number corresponding to the lens focal length. The system parameters are determined based on the M groups of random numbers, the objective function, and the constraint function. The system parameters are determined by looping the following operations until m is equal to M, and obtaining an updated maximum system sensitivity value, working angle, object distance, and lens focal length, wherein m is a positive integer less than or equal to M. When the mth working angle random number, the mth object distance random number, and the mth lens focal length random number satisfy the constraint function, the system parameters are determined based on the mth working angle random number, the objective function, and the constraint function. The mth system sensitivity value is calculated using the mth object distance random value, the mth receiving lens focal length random value and the objective function; when the mth system sensitivity value is greater than the maximum system sensitivity value, the maximum system sensitivity value is updated using the mth system sensitivity value, and the working angle, the object distance and the lens focal length are updated respectively using the mth working angle random number, the mth object distance random number and the mth lens focal length random number, wherein the initial value of the maximum system sensitivity value is a predetermined value; the system parameters are determined based on the updated maximum system sensitivity value, working angle, object distance and lens focal length.

[0009] According to an embodiment of the present disclosure, the above-mentioned filtered image is threshold segmented based on the maximum inter-class variance method and the region of interest is extracted to obtain the target image, which includes: using the maximum inter-class variance method to calculate the inter-class variance and the intra-class variance of the filtered image to obtain the target threshold; according to the above-mentioned target threshold, the above-mentioned target image is binarized to obtain a segmented image; the region of interest is extracted from the above-mentioned segmented image to obtain the above-mentioned target image.

[0010] According to an embodiment of the present disclosure, the above-mentioned method of obtaining the height of the lithium battery pole piece weld mark corresponding to the above-mentioned sub-pixel coordinates based on the predetermined relationship and the above-mentioned sub-pixel coordinates includes: calculating the target moving distance according to the above-mentioned sub-pixel coordinates and the reference coordinates of the reference point corresponding to the above-mentioned sub-pixel coordinates; and calculating the height of the lithium battery pole piece weld mark corresponding to the above-mentioned sub-pixel coordinates according to the above-mentioned target moving distance and the above-mentioned predetermined relationship.

[0011] According to an embodiment of the present disclosure, the line structured light projected by the above-mentioned system for measuring the weld mark height of new energy lithium batteries onto the above-mentioned lithium battery pole piece is blue line structured light or red line structured light.

[0012] According to another aspect of the present disclosure, a system for measuring the weld mark height of a new energy lithium battery is provided, which is used to implement the above-mentioned method for measuring the weld mark height of a new energy lithium battery, including: a laser for projecting line structured light onto a lithium battery pole piece; a camera for collecting the lithium battery pole piece projecting the line structured light to obtain a light strip image, wherein the spatial positions of the above-mentioned laser, the lens of the above-mentioned camera, and the photosensitive detector of the above-mentioned camera are determined by the system parameters of the above-mentioned system for measuring the weld mark height of a new energy lithium battery, and the system parameters of the above-mentioned system for measuring the weld mark height of a new energy lithium battery are calculated using a Monte Carlo optimization algorithm with system sensitivity as the objective function, and the above-mentioned system sensitivity The degree represents the movement distance of the image point corresponding to the object point on the above-mentioned lithium battery pole piece from the reference point when the object point moves a unit distance in the depth direction; the processor is used to grayscale the above-mentioned light strip image to obtain a grayscale image; bilaterally filter the above-mentioned grayscale image to obtain a filtered image; threshold segment the above-mentioned filtered image based on the maximum between-class variance method and extract the region of interest to obtain a target image, wherein the above-mentioned target image includes the lithium battery pole piece weld mark; sub-pixel center extraction is performed on the above-mentioned target image based on the line center extraction algorithm to obtain the sub-pixel coordinates of the light strip center line; based on a predetermined relationship and the above-mentioned sub-pixel coordinates, the height of the lithium battery pole piece weld mark corresponding to the above-mentioned sub-pixel coordinates is obtained.

[0013] According to an embodiment of the present disclosure, the lens of the camera is an aspherical lens.

[0014] According to an embodiment of the present disclosure, the above-mentioned system for measuring the weld mark height of new energy lithium batteries also includes a mobile platform for placing the above-mentioned lithium battery pole piece and moving the above-mentioned lithium battery pole piece in a direction perpendicular to the light strip on the above-mentioned lithium battery pole piece based on a predetermined speed.

[0015] According to an embodiment of the present disclosure, the above-mentioned measurement system for weld mark height of new energy lithium batteries also includes: a narrow-band filter, which is used to filter the line structured light reflected by the above-mentioned lithium battery pole piece before the line structured light reflected by the above-mentioned lithium battery pole piece passes through the lens of the above-mentioned camera.

[0016] According to the embodiment of the present disclosure, since the spatial position of each device included in the measurement system for the weld mark height of new energy lithium batteries is determined based on the system parameters of the measurement system for the weld mark height of new energy lithium batteries, and the system parameters of the measurement system for the weld mark height of new energy lithium batteries are calculated using the Monte Carlo optimization algorithm with the system sensitivity as the objective function, the system parameters are optimized based on the intelligent optimization algorithm to improve the efficiency of system construction. By using the measurement system for the weld mark height of new energy lithium batteries to perform line structured light scanning on the lithium battery pole piece, a light strip image is obtained, and the light strip image is grayed to obtain a grayscale image; bilateral filtering is performed on the grayscale image to obtain a filtered image; based on the maximum inter-class variance method, the filtered image is threshold segmented and the region of interest is extracted to obtain a target image; based on the line center extraction algorithm, the sub-pixel center of the target image is extracted to obtain the sub-pixel coordinates of the center line of the light strip, and the high reflectivity of the weld mark of the new energy lithium battery pole piece is realized. The bilateral filtering combined with the maximum inter-class variance method is used to denoise and segment the image, and on this basis, the line center extraction algorithm is used to extract the center of the light strip to achieve sub-pixel image processing. Then, based on the predetermined relationship and sub-pixel coordinates, the height of the lithium battery pole piece weld mark corresponding to the sub-pixel coordinates is obtained, thereby realizing non-contact automatic measurement of the height of the lithium battery pole piece weld mark, avoiding the damage of the lithium battery pole piece weld mark by contact measurement, reducing manual measurement errors, and improving measurement accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0018] Figure 1 A flow chart schematically shows a method for measuring weld mark height of new energy lithium batteries according to an embodiment of the present disclosure;

[0019] Figure 2 A schematic diagram of a system for measuring weld mark height of new energy lithium batteries according to an embodiment of the present disclosure is schematically shown;

[0020] Figure 3 A schematic diagram schematically shows a laser triangulation measurement based on a measurement system for weld mark height of new energy lithium batteries according to an embodiment of the present disclosure; and

[0021] Figure 4 A flowchart for optimizing system parameters according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0022] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0023] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0024] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0025] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0026] In recent years, with the development of digital image processing technology, photoelectric precision detection technology based on line structured light has been widely used in the field of precision engineering measurement. However, photoelectric precision detection technology based on line structured light still faces some challenges in the detection of weld height of new energy lithium batteries, mainly in the selection of optimal system parameters and image processing. The selection of system parameters affects the final measurement accuracy of the system. The determination of the optimal parameters of the traditional line structured light measurement system requires a lot of experiments, which is inefficient. And due to the high reflectivity of the weld of new energy lithium batteries, the images collected by the measurement system are noisy and difficult to identify and extract features, resulting in low accuracy of the measurement system.

[0027] In view of this, the embodiments of the present disclosure provide a method and system for measuring the weld mark height of new energy lithium batteries, which can be applied to the fields of computer vision technology and precision engineering measurement technology.

[0028] Figure 1 The flowchart of the method for measuring the weld mark height of a new energy lithium battery according to an embodiment of the present disclosure is schematically shown.

[0029] like Figure 1 As shown, the method for measuring the weld mark height of a new energy lithium battery includes operations S110 to S160.

[0030] In operation S110, a line structured light scan is performed on a lithium battery pole piece using a measurement system for the weld mark height of a new energy lithium battery to obtain a light strip image. The spatial position of each device included in the measurement system for the weld mark height of a new energy lithium battery is determined based on the system parameters of the measurement system for the weld mark height of a new energy lithium battery, and the system parameters of the measurement system for the weld mark height of a new energy lithium battery are calculated using a Monte Carlo optimization algorithm with system sensitivity as the objective function, and the system sensitivity represents the movement distance of the image point corresponding to the object point from the reference point when the object point on the lithium battery pole piece moves a unit distance in the depth direction.

[0031] According to an embodiment of the present disclosure, a lithium battery electrode sheet includes a lithium battery weld mark.

[0032] According to the embodiments of the present disclosure, the spatial position distribution of each device included in the measurement system for the height of the weld mark of a new energy lithium battery satisfies the Scheimpflug principle, and its physical meaning is that the object plane, the image plane and the plane where the lens is located are three planes collinear, so that the weld marks of lithium batteries of different heights can be constantly focused on the camera to obtain a comprehensive and clear image, thereby expanding the imaging depth of field and improving the measurement range.

[0033] In operation S120, the light bar image is grayscaled to obtain a grayscale image.

[0034] For example, the light bar image captured by the board-level camera can be read by the host computer, and converted to grayscale using the processor in the host computer to obtain a grayscale image.

[0035] After obtaining the grayscale image, the grayscale image may be preprocessed, which may include, for example, image filtering, threshold segmentation, and region of interest extraction.

[0036] In operation S130, bilateral filtering is performed on the grayscale image to obtain a filtered image.

[0037] According to the embodiments of the present disclosure, due to the high reflectivity of lithium battery welding marks, halos appear at the edges of the light strips captured by the camera. When filtering grayscale images, the filtering effects of traditional mean filtering, median filtering, Gaussian filtering, frequency domain filtering and other methods are not ideal. The embodiments of the present disclosure select appropriate spatial standard deviation and intensity standard deviation based on the characteristics of the actual light strip image, and use a bilateral filter to perform bilateral filtering on the grayscale image, which can effectively eliminate the halos at the edges of the light strips.

[0038] In operation S140 , threshold segmentation is performed on the filtered image based on the maximum inter-class variance method and a region of interest is extracted to obtain a target image.

[0039] According to the embodiments of the present disclosure, when performing threshold segmentation on the filtered image, the maximum inter-class variance method OTSU can be used to segment the filtered image, that is, the OTSU algorithm finds the optimal threshold according to the characteristics of the filtered image, so that the inter-class variance of the light bar body and the background after the threshold segmentation is maximized, thereby achieving the optimal threshold segmentation of the light bar image and the background. After that, the region of interest is extracted, and only the image feature region of interest, that is, the target image, is retained to reduce the image processing area and improve the measurement efficiency. The target image includes the welding mark of the lithium battery pole piece.

[0040] According to the embodiments of the present disclosure, after preprocessing the grayscale image, most of the noise in the grayscale image can be filtered out, reducing the interference of the noise on the extraction of the light strip center. At the same time, the amount of calculation during image processing can be greatly reduced by extracting the region of interest, and the speed of subsequent extraction of the light strip center can be increased.

[0041] In operation S150, sub-pixel center extraction is performed on the target image based on a line center extraction algorithm to obtain sub-pixel coordinates of the center line of the light stripe.

[0042] According to an embodiment of the present disclosure, when using a line center extraction algorithm, i.e., the Steger algorithm, to extract the sub-pixel center of a light stripe from a target image, the normal direction of the light stripe center line is obtained through the Hessian matrix, and then the light stripe grayscale distribution is Taylor expanded in the normal direction to obtain the sub-pixel coordinates of the light stripe center line.

[0043] In operation S160, based on a predetermined relationship and the sub-pixel coordinates, a height of a lithium battery electrode weld mark corresponding to the sub-pixel coordinates is obtained.

[0044] According to the embodiments of the present disclosure, the light reflected at different heights of the lithium battery pole piece weld mark corresponds to different light bar pixel positions in the light bar image. The height of the new energy lithium battery pole piece weld mark can be calculated by solving the distance between the sub-pixel coordinates of the center lines of different light strips and the corresponding reference coordinates and combining it with a predetermined relationship.

[0045] According to an embodiment of the present disclosure, before operation S160, a high-precision step calibration block can be used to perform system calibration on a measurement system for the weld mark height of a new energy lithium battery. System calibration may, for example, be: using a measurement system for the weld mark height of a new energy lithium battery to measure a high-precision step calibration block, and obtain the actual measured movement distance of the object point along the depth direction and the movement distance of the image point from the reference point. The relationship between the actual measured movement distance of the object point along the depth direction and the movement distance of the image point from the reference point is expressed by a polynomial. By solving the parameters of the polynomial, the mapping relationship between the movement distance of the real-world object point along the depth direction and the movement distance of the image point from the reference point is obtained, thereby completing the system calibration and obtaining a predetermined relationship.

[0046] According to the embodiment of the present disclosure, since the spatial position of each device included in the measurement system for the weld mark height of new energy lithium batteries is determined based on the system parameters of the measurement system for the weld mark height of new energy lithium batteries, and the system parameters of the measurement system for the weld mark height of new energy lithium batteries are calculated using the Monte Carlo optimization algorithm with the system sensitivity as the objective function, the system parameters are optimized based on the intelligent optimization algorithm to improve the efficiency of system construction. By using the measurement system for the weld mark height of new energy lithium batteries to perform line structured light scanning on the lithium battery pole piece, a light strip image is obtained, and the light strip image is grayed to obtain a grayscale image; bilateral filtering is performed on the grayscale image to obtain a filtered image; based on the maximum inter-class variance method, the filtered image is threshold segmented and the region of interest is extracted to obtain a target image; based on the line center extraction algorithm, the sub-pixel center of the target image is extracted to obtain the sub-pixel coordinates of the center line of the light strip, and the high reflectivity of the weld mark of the new energy lithium battery pole piece is realized. The bilateral filtering combined with the maximum inter-class variance method is used to denoise and segment the image, and on this basis, the line center extraction algorithm is used to extract the center of the light strip to achieve sub-pixel image processing. Then, based on the predetermined relationship and sub-pixel coordinates, the height of the lithium battery pole piece weld mark position corresponding to the sub-pixel coordinates is obtained, thereby realizing non-contact automatic measurement of the lithium battery pole piece weld mark height, avoiding the damage of the lithium battery pole piece weld mark by contact measurement, reducing manual measurement errors, and improving measurement accuracy and efficiency.

[0047] According to the embodiments of the present disclosure, Figure 1 Operation S140 in the embodiment performs threshold segmentation on the filtered image based on the maximum inter-class variance method and extracts the region of interest to obtain a target image, which may include the following operations: performing inter-class variance calculation and intra-class variance calculation on the filtered image using the maximum inter-class variance method to obtain a target threshold; binarizing the target image according to the target threshold to obtain a segmented image; extracting the region of interest from the segmented image to obtain a target image.

[0048] For example, a threshold can be initialized based on the filtered image, and pixels can be divided into background and target categories according to the threshold. The intra-class variance and inter-class variance are calculated, and each threshold (0-255) is traversed to find the optimal threshold that maximizes the inter-class variance, which is the target threshold.

[0049] According to the embodiments of the present disclosure, the target threshold is obtained by calculating the inter-class variance and the intra-class variance of the filtered image using the maximum inter-class variance method; the target image is binarized according to the target threshold to obtain a segmented image; the region of interest is extracted from the segmented image to obtain the target image, so that when the sub-pixel center is subsequently extracted from the target image, the amount of calculation during image processing can be greatly reduced compared to directly extracting the sub-pixel center of the filtered image, and the speed of subsequent sub-pixel center extraction of the light strip center can be increased.

[0050] According to the embodiments of the present disclosure, Figure 1 Operation S160 in the method obtains the height of the lithium battery pole piece weld mark corresponding to the sub-pixel coordinates based on a predetermined relationship and sub-pixel coordinates, which may include the following operations: calculating a target moving distance according to the sub-pixel coordinates and the reference coordinates of a reference point corresponding to the sub-pixel coordinates; and calculating the height of the lithium battery pole piece weld mark corresponding to the sub-pixel coordinates according to the target moving distance and a predetermined relationship.

[0051] According to an embodiment of the present disclosure, the target moving distance is calculated based on the sub-pixel coordinates and the reference coordinates of the reference point corresponding to the sub-pixel coordinates; the height of the lithium battery pole piece weld mark corresponding to the sub-pixel coordinates is calculated based on the target moving distance and a predetermined relationship, thereby automatically calculating the height of the lithium battery pole piece weld mark based on the target moving distance and the predetermined relationship, avoiding the influence of human errors caused by manual detection of lithium battery pole piece weld marks, and effectively improving the detection quality and efficiency.

[0052] Figure 2 A schematic diagram of a system for measuring weld mark height of new energy lithium batteries according to an embodiment of the present disclosure is schematically shown.

[0053] like Figure 2 As shown, the measurement system 200 for the weld mark height of new energy lithium batteries includes: a laser 210, a camera 220 and a processor 230. The measurement system 200 for the weld mark height of new energy lithium batteries can be used to achieve Figure 1 A measurement method for weld mark height of new energy lithium batteries.

[0054] The laser 210 can be used to project line structured light onto the lithium battery electrode 201 .

[0055] The camera 220 can be used to collect the lithium battery pole piece 201 that projects the wired structured light to obtain a light strip image. Among them, the spatial positions of the laser 210, the lens of the camera 220 and the photosensitive detector of the camera are determined by the system parameters of the measurement system 200 for the weld mark height of new energy lithium batteries. The system parameters of the measurement system 200 for the weld mark height of new energy lithium batteries are calculated using the Monte Carlo optimization algorithm with the system sensitivity as the objective function. The system sensitivity characterizes the movement distance of the image point corresponding to the object point from the reference point when the object point on the lithium battery pole piece 201 moves a unit distance in the depth direction.

[0056] For example, the plane where the line structured light emitted by the laser 210 is located, the plane where the lens of the camera 220 is located, and the image plane where the image formed by the photosensitive detector of the camera is located are collinear, so that the spatial position distribution of the laser 210, the lens of the camera 220, and the photosensitive detector of the camera satisfies the Scheimpflug principle.

[0057] The processor 230 can be used to grayscale the light bar image to obtain a grayscale image. Perform bilateral filtering on the grayscale image to obtain a filtered image. Perform threshold segmentation on the filtered image based on the maximum inter-class variance method and extract the region of interest to obtain a target image. Perform sub-pixel center extraction on the target image based on the line center extraction algorithm to obtain the sub-pixel coordinates of the light bar center line. Based on a predetermined relationship and the sub-pixel coordinates, obtain the height of the lithium battery pole piece weld mark corresponding to the sub-pixel coordinates.

[0058] According to an embodiment of the present disclosure, the processor 230 may be used to perform operations S120 to S160, which will not be described in detail herein for the sake of brevity.

[0059] For example, the processor 230 may be a processor in a host computer.

[0060] The measurement system 200 for weld mark height of new energy lithium battery may further include a mobile platform 240. The mobile platform 240 may be used to place the lithium battery pole piece 201 and move the lithium battery pole piece 201 in a direction perpendicular to the light strip on the lithium battery pole piece 201 based on a predetermined speed.

[0061] like Figure 2 As shown, the lithium battery pole piece 201 is mounted on the mobile platform 240. When the mobile platform 240 moves at a constant speed based on a predetermined speed, the measurement system 200 for the weld mark height of the new energy lithium battery can scan the lithium battery pole piece 201 to obtain the three-dimensional morphology of the weld mark on the lithium battery pole piece 201, thereby realizing the measurement of the weld mark height.

[0062] like Figure 2As shown, the process of measuring the weld mark height of new energy lithium batteries by the measurement system 200 for lithium battery pole pieces can be as follows: the laser 210 emits line structured light to the lithium battery pole piece 201, diffuse reflection or mirror reflection occurs, and the reflected light is received by the camera 220. The processor 230 performs image processing on the light strip image received by the camera 220, and obtains the measurement result of the weld mark height of the lithium battery pole piece in combination with the predetermined relationship obtained by system calibration.

[0063] According to an embodiment of the present disclosure, a measurement system 200 for the weld mark height of a new energy lithium battery is constructed based on the principle of laser triangulation, and can realize non-contact measurement of the weld mark height of a new energy lithium battery pole piece.

[0064] Figure 3 The schematic diagram of laser triangulation measurement based on the measurement system for weld mark height of new energy lithium batteries according to an embodiment of the present disclosure is schematically shown.

[0065] exist Figure 3 In the figure, the camera 220 may include a lens 221 and a photosensitive detector 222. 202 is a reference plane, and 203 is a measured plane.

[0066] When laser triangulation is performed based on the measurement system 200 for the weld mark height of new energy lithium batteries, the laser 210 emits line structured light to illuminate point A on the object to be measured on the reference plane 202, and then reflects. The reflected light is received by the photosensitive detector 222 after passing through the lens 221, forming an image point A'. When the object to be measured moves in the depth direction and reaches point B on the measured plane 203, the image point on the photosensitive detector 222 moves accordingly to form an image point B'. The moving distance x of the image point, that is, the distance between the image point A' and the image point B', combined with the geometric trigonometric relationship, can calculate the moving distance y of the object to be measured in the depth direction.

[0067] The line structured light projected by the measurement system 200 for the weld mark height of new energy lithium batteries to the lithium battery pole piece 201 can be a blue line structured light of 400nm-470nm or a red line structured light of 605nm-700nm.

[0068] For example, the line structured light projected by the measurement system 200 for the weld mark height of new energy lithium batteries to the lithium battery pole piece 201 may be a 405nm blue line structured light.

[0069] According to an embodiment of the present disclosure, under the same conditions, the beam of blue light is thinner than that of red light. Therefore, when the measurement system 200 for the weld mark height of new energy lithium batteries performs three-dimensional measurement, it projects 405nm blue line structured light to the lithium battery pole piece 201 to achieve higher precision measurement.

[0070] The camera 220 may be a high-resolution CMOS (Complementary Metal Oxide Semiconductor) board-level camera. The photosensitive detector of the camera 220 may be a photosensitive detector in a high-resolution CMOS board-level camera. For example, the size of the photosensitive detector may be 5472×3648 pixels.

[0071] According to the embodiments of the present disclosure, the board-level camera can avoid the problem of CMOS being blocked due to an excessively large Sham angle, so that the full-size CMOS can receive reflected light, thereby improving the measurement range of the system.

[0072] According to the embodiments of the present disclosure, in actual use, light sources of different wavelengths and photosensitive detectors of different sizes or types may be selected according to the characteristics of the object to be measured.

[0073] The lens of the camera 220 is an aspherical lens.

[0074] For example, the lens of the camera 220 may be an aspherical lens with a large aperture, which can greatly increase the amount of light entering.

[0075] The measurement system 200 for weld mark height of new energy lithium battery may also include a narrowband filter. The narrowband filter may be used to filter the line structured light reflected by the lithium battery pole piece 201 before the line structured light reflected by the lithium battery pole piece 201 passes through the lens of the camera 220.

[0076] According to an embodiment of the present disclosure, a narrow-band filter is placed in front of the lens to reduce interference from ambient light.

[0077] According to the embodiments of the present disclosure, when building a measurement system 200 for the weld mark height of a new energy lithium battery, it is necessary to determine the position and angle of each component included in the measurement system 200 for the weld mark height of a new energy lithium battery. Since there is a mathematical relationship between the system parameters, it is only necessary to determine the working angle α, the object distance a and the focal length f of the lens to calculate other parameters and determine the position and angle of each component of the system. In order to improve the efficiency of determining the system parameters, when determining the system parameters, the present disclosure adopts an intelligent optimization algorithm, and the intelligent optimization algorithm directly gives the optimal system parameters that meet the constraints. Then, a measurement system 200 for the weld mark height of a new energy lithium battery is built according to the optimal system parameter values, striving to achieve the highest measurement accuracy under the constraints of the measurement range.

[0078] like Figure 3As shown, the working angle α represents the angle between the optical axis of the laser 210 in the measurement system 200 for the weld mark height of new energy lithium batteries and the optical axis of the camera 220 in the measurement system 200 for the weld mark height of new energy lithium batteries. The object distance a represents the distance between the center of the lens 221 of the camera 220 and the point where the optical axis of the laser 210 is projected onto the lithium battery pole piece. The lens focal length f represents the focal length of the lens 221 of the camera 220. The Sham angle β is the angle between the photosensitive detector 222 and the optical axis of the camera 220.

[0079] According to an embodiment of the present disclosure, the system parameters of the measurement system 200 for the weld mark height of a new energy lithium battery are obtained according to the following operations: determining the objective function according to the working angle α, the object distance a and the focal length of the lens f; determining the constraint functions corresponding to the working angle α, the image distance b and the height measurement range R respectively according to the working angle α, the object distance a and the focal length of the lens f, wherein the image distance b represents the distance between the center of the lens 221 of the camera 220 and the image point A'; generating M groups of random numbers corresponding to the working angle α, the object distance a and the focal length of the lens f respectively according to the Monte Carlo optimization algorithm, wherein M is a positive integer; determining the system parameters according to the M groups of random numbers, the objective function and the constraint function.

[0080] Depend on Figure 3 It can be seen that when the moving distance of the measured object along the depth direction is y, the corresponding moving distance of the image point on the photosensitive detector is x. According to geometric trigonometric operations, formula (1) can be obtained.

[0081] (1)

[0082] By finding the inverse function of formula (1), we can get formula (2).

[0083] (2)

[0084] By taking the derivative of formula (2), we can get the system sensitivity δ in formula (3).

[0085] (3)

[0086] When the size of the photosensitive detector is (-X, X), substituting it into formula (1) can obtain the system height measurement range R in formula (4).

[0087] (4)

[0088] According to an embodiment of the present disclosure, the system sensitivity δ reflects the moving distance of the image point deviating from the reference point when the object point moves a unit distance along the depth direction. If the measurement accuracy of the system is to be improved, the system sensitivity δ should be made to take a larger value. Since there is a negative correlation between the system measurement accuracy and the measurement range, when improving the measurement accuracy, attention should also be paid to the system measurement range, and efforts should be made to maximize the measurement accuracy of the system when the measurement range meets the measurement requirements.

[0089] It can be seen from formulas (3) and (4) that the parameters affecting the system sensitivity δ and the height measurement range R are a, b, α, and β. According to the Scheimpflug's law, as shown in formula (5), and the Gaussian imaging formula, as shown in formula (6), there are operational relationships among the parameters a, b, α, β, and f, and they can be converted to each other. Then, through simplification, only by determining the parameters a, α, and f can the system sensitivity δ and the system height measurement range R be determined, and the objective function and the constraint function corresponding to the height measurement range R can be determined based on the parameters a, α, and f.

[0090] (5)

[0091] (6)

[0092] The constraint function corresponding to the working angle α can be 0 < α < 60°. The constraint function corresponding to the image distance b can be 0 < b < 200 mm. The height measurement range R can be 0 < R < 4 mm.

[0093] According to an embodiment of the present disclosure, each set of random numbers includes a working angle random number corresponding to the working angle, an object distance random number corresponding to the object distance, and a lens focal length random number corresponding to the lens focal length. According to the M sets of random numbers, the objective function, and the constraint function, the system parameters are determined as follows:

[0094] The following operations are repeatedly executed until m is equal to M to obtain the updated maximum system sensitivity value, working angle, object distance, and lens focal length, where m is a positive integer less than or equal to M;

[0095] When the m-th working angle random number, the m-th object distance random number, and the m-th lens focal length random number satisfy the constraint function, the m-th system sensitivity value is calculated according to the m-th working angle random number, the m-th object distance random value, the m-th receiving lens focal length random value, and the objective function;

[0096] When the m-th system sensitivity value is greater than the maximum system sensitivity value, the maximum system sensitivity value is updated using the m-th system sensitivity value, and the working angle, object distance, and lens focal length are updated using the m-th working angle random number, the m-th object distance random number, and the m-th lens focal length random number respectively, where the initial value of the maximum system sensitivity value is a predetermined value;

[0097] The system parameters are determined based on the updated maximum system sensitivity value, working angle, object distance, and lens focal length.

[0098] For example, the updated maximum system sensitivity value can be determined as the optimal system sensitivity, the updated working angle can be determined as the optimal working angle, the updated object distance can be determined as the optimal object distance, and the updated lens focal length can be determined as the optimal lens focal length. Then, based on the optimal working angle, the optimal object distance, the optimal lens focal length and formulas (5) and (6), the optimal b and the optimal β can be determined, thereby obtaining the optimal system parameters.

[0099] According to the embodiments of the present disclosure, M can be selected according to actual conditions and is not limited here. The predetermined value can be selected according to actual conditions and is not limited here. For example, M can be 10000, 50000, 100000 or 1000000, etc., and the predetermined value can be -∞ or 0, etc.

[0100] Figure 4 A flowchart for optimizing system parameters according to an embodiment of the present disclosure is schematically shown.

[0101] like Figure 4 As shown, the method for optimizing system parameters includes operations S410 to S419.

[0102] exist Figure 4 In operation S410, the method of optimizing system parameters begins.

[0103] In operation S411 , an objective function corresponding to the system sensitivity δ is determined, and constraint functions corresponding to the working angle α, the image distance b, and the height measurement range R are determined respectively.

[0104] In operation S412, an mth group of random numbers respectively corresponding to the working angle α, the object distance a, and the lens focal length f are generated.

[0105] In operation S413, it is determined whether the mth working angle random number, the mth object distance random number and the mth lens focal length random number satisfy the constraint function. If yes, operation S414 is executed; if not, m is increased by 1, that is, m is incremented to make m=m+1, and then operation S413 is returned to be executed.

[0106] In operation S414, the mth system sensitivity value δ is calculated according to the mth working angle random number, the mth object distance random value, the mth receiving lens focal length random value and the objective function. m .

[0107] In operation S415, it is determined that m >δ max Among them, δ maxis the maximum system sensitivity value. If yes, then execute operation S416_2, if no, then execute operation S416_1.

[0108] In operation S416_1, output δ m , the mth working angle random number, the mth object distance random value, the mth lens focal length random value.

[0109] In operation S416_2, δ max =δ m , α max = random number of the mth working angle, a max = random number of the mth object distance, f max = random value of the focal length of the mth lens. max is the updated working angle in the mth iteration, a max is the updated object distance in the mth iteration, f max is the updated lens focal length in the mth iteration.

[0110] In operation S417, it is determined whether m>M. If yes, operation S418 is performed, and if no, the process returns to operation S413.

[0111] In operation S418, output δ max , α max 、a max and f max , and according to δ max , α max 、a max and f max Determine system parameters.

[0112] In operation S419, the method of optimizing system parameters ends.

[0113] Depend on Figure 4 It can be seen that the embodiment of the present disclosure adopts an intelligent optimization algorithm, namely the Monte Carlo optimization algorithm, which obtains the optimal system sensitivity value by random sampling parameter values ​​and continuous iteration.

[0114] According to the embodiments of the present disclosure, in actual use, the measurement range, system size, etc. can be used as the objective function, and other similar intelligent optimization algorithms can be used to optimize the system parameters.

[0115] According to the embodiments of the present disclosure, the present disclosure optimizes system parameters through an intelligent optimization algorithm, such as a Monte Carlo optimization algorithm, and can quickly and accurately solve the optimal system parameters. Traditional system parameter selection requires a large number of experiments to find a set of parameters that meet the requirements. The process is cumbersome and susceptible to human interference, and due to the limitations of experimental conditions, it is impossible to traverse all parameter values ​​for experiments. The intelligent optimization algorithm used in the present disclosure can quickly find the global optimal solution of system parameters through parameter traversal, avoiding cumbersome experimental processes and improving the efficiency and quality of system parameter selection.

[0116] According to the embodiments of the present disclosure, although the present disclosure fixes the lithium battery pole pieces on a mobile platform that can move at a uniform speed, and fixes the measurement system for the weld mark height of the new energy lithium battery on the mobile platform to achieve scanning, in actual use, the lithium battery pole pieces can also be fixed, and the measurement system for the weld mark height of the new energy lithium battery can be fixed on the mobile platform to achieve scanning.

[0117] The method and system for measuring the weld mark height of new energy lithium batteries provided in the embodiments of the present disclosure improve the automation level of lithium battery production workshops, avoid the influence of human errors caused by manual inspection of lithium batteries, and effectively improve the inspection quality and efficiency.

[0118] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0119] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for measuring the weld mark height of new energy lithium batteries, comprising: A line structured light scan is performed on a lithium battery pole piece using a measurement system for the weld mark height of a new energy lithium battery to obtain a light strip image, wherein the spatial position of each device included in the measurement system for the weld mark height of a new energy lithium battery is determined based on the system parameters of the measurement system for the weld mark height of a new energy lithium battery, and the system parameters of the measurement system for the weld mark height of a new energy lithium battery are calculated using a Monte Carlo optimization algorithm with system sensitivity as the objective function, and the system sensitivity represents the movement distance of an image point corresponding to the object point on the lithium battery pole piece from a reference point when the object point moves a unit distance in the depth direction; Gray-scaling the light bar image to obtain a gray-scale image; Performing bilateral filtering on the grayscale image to obtain a filtered image; Performing threshold segmentation on the filtered image based on the maximum inter-class variance method and extracting the region of interest to obtain a target image, wherein the target image includes a lithium battery electrode welding mark; Perform sub-pixel center extraction on the target image based on a line center extraction algorithm to obtain sub-pixel coordinates of the center line of the light strip; Based on the predetermined relationship and the sub-pixel coordinates, the height of the lithium battery electrode weld mark corresponding to the sub-pixel coordinates is obtained.

2. The measuring method according to claim 1, wherein: The system parameters of the measurement system for the weld mark height of new energy lithium batteries are obtained according to the following operations: Determine the objective function according to the working angle, object distance and lens focal length, wherein the working angle represents the angle between the optical axis of the laser in the measurement system for the weld mark height of new energy lithium batteries and the optical axis of the camera in the measurement system for the weld mark height of new energy lithium batteries, the object distance represents the distance between the center of the lens of the camera and the point where the optical axis of the laser is projected onto the lithium battery pole piece, and the lens focal length represents the focal length of the lens of the camera; According to the working angle, the object distance and the focal length of the lens, determining constraint functions corresponding to the working angle, the image distance and the height measurement range respectively; Generate M groups of random numbers corresponding to the working angle, the object distance and the focal length of the lens, respectively, according to a Monte Carlo optimization algorithm, wherein M is a positive integer; The system parameters are determined according to the M groups of random numbers, the objective function and the constraint function.

3. The measuring method according to claim 2, wherein: Each group of random numbers includes a working angle random number corresponding to the working angle, an object distance random number corresponding to the object distance, and a lens focal length random number corresponding to the lens focal length. Determining the system parameters according to the M groups of random numbers, the objective function, and the constraint function includes: The following operations are performed cyclically until m is equal to M, and the updated maximum system sensitivity value, working angle, object distance and lens focal length are obtained, where m is a positive integer less than or equal to M; When the mth working angle random number, the mth object distance random number and the mth lens focal length random number satisfy the constraint function, the mth system sensitivity value is calculated according to the mth working angle random number, the mth object distance random value, the mth receiving lens focal length random value and the objective function; In the case where the m-th system sensitivity value is greater than the maximum system sensitivity value, the maximum system sensitivity value is updated using the m-th system sensitivity value, and the working angle, the object distance and the lens focal length are updated using the m-th working angle random number, the m-th object distance random number and the m-th lens focal length random number, respectively, wherein the initial value of the maximum system sensitivity value is a predetermined value; The system parameters are determined according to the updated maximum system sensitivity value, working angle, object distance and lens focal length.

4. The measuring method according to claim 1, wherein: The method of performing threshold segmentation on the filtered image based on the maximum inter-class variance method and extracting the region of interest to obtain the target image includes: Using the maximum inter-class variance method to calculate the inter-class variance and the intra-class variance of the filtered image, to obtain a target threshold; According to the target threshold, binarizing the target image to obtain a segmented image; The region of interest is extracted from the segmented image to obtain the target image.

5. The measuring method according to any one of claims 1 to 4, wherein: The step of obtaining the height of the lithium battery electrode weld mark corresponding to the sub-pixel coordinate based on the predetermined relationship and the sub-pixel coordinate comprises: Calculating a target moving distance according to the sub-pixel coordinates and reference coordinates of a reference point corresponding to the sub-pixel coordinates; The height of the lithium battery electrode weld mark corresponding to the sub-pixel coordinate is calculated according to the target moving distance and the predetermined relationship.

6. The measuring method according to claim 5, wherein: The line structured light projected by the measurement system for the weld mark height of new energy lithium batteries onto the lithium battery pole piece is blue line structured light or red line structured light.

7. A system for measuring weld mark height of new energy lithium battery, used to implement the method for measuring weld mark height of new energy lithium battery according to any one of claims 1 to 6, comprising: Laser, used to project line structured light onto lithium battery electrodes; A camera is used to collect the lithium battery pole piece projecting wired structured light to obtain a light strip image, wherein the spatial positions of the laser, the lens of the camera and the photosensitive detector of the camera are determined by the system parameters of the measurement system for the weld mark height of the new energy lithium battery, and the system parameters of the measurement system for the weld mark height of the new energy lithium battery are calculated by using the Monte Carlo optimization algorithm with the system sensitivity as the objective function, and the system sensitivity represents the movement distance of the image point corresponding to the object point on the lithium battery pole piece from the reference point when the object point moves a unit distance in the depth direction; A processor is used to grayscale the light strip image to obtain a grayscale image; perform bilateral filtering on the grayscale image to obtain a filtered image; perform threshold segmentation on the filtered image based on a maximum inter-class variance method and extract a region of interest to obtain a target image, wherein the target image includes a lithium battery pole piece weld mark; perform sub-pixel center extraction on the target image based on a line center extraction algorithm to obtain the sub-pixel coordinates of the light strip center line; and obtain a height of the lithium battery pole piece weld mark corresponding to the sub-pixel coordinates based on a predetermined relationship and the sub-pixel coordinates.

8. The measurement system according to claim 7, wherein: The lens of the camera is an aspherical lens.

9. The measuring system according to claim 7 or 8, wherein: It also includes a moving platform for placing the lithium battery pole piece and moving the lithium battery pole piece in a direction perpendicular to the light strip on the lithium battery pole piece based on a predetermined speed.

10. The measuring system according to claim 7 or 8, wherein: Also includes: A narrow-band filter is used to filter the line structured light reflected by the lithium battery pole piece before the line structured light reflected by the lithium battery pole piece passes through the lens of the camera.

Images