Battery cell pole welding quality detection method and device, electronic equipment and storage medium
By combining 3D point cloud data and 2D texture image detection methods, the problem of poor detection effect of defects such as false welding and smooth pits and protrusions in the welding quality inspection of battery cell terminals has been solved. This has achieved automated and high-precision welding quality inspection and reduced the influence of ambient light and surface reflection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA FAW CO LTD
- Filing Date
- 2025-12-15
- Publication Date
- 2026-05-15
AI Technical Summary
Existing cell electrode welding quality inspection methods are not effective in detecting defects such as incomplete welds, pits or protrusions with gradual height changes, and are easily affected by ambient light and workpiece surface reflection, resulting in poor imaging stability.
A detection method combining 3D point cloud data and 2D texture images is adopted. By acquiring 3D point cloud data and 2D texture images of the battery cell electrode welding area, 3D and 2D features are extracted. Feature analysis is performed using preset fusion judgment rules and machine learning models to achieve full-mark detection of welding defects.
It achieves automated, high-precision, and high-efficiency inspection of battery cell welding quality, reduces the influence of ambient light and workpiece surface reflection, and ensures the stability and accuracy of the inspection.
Smart Images
Figure CN122048784A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of battery manufacturing and testing technology, and in particular to a method, apparatus, electronic device and storage medium for testing the welding quality of battery cell terminals. Background Technology
[0002] During the assembly of power battery modules (PACK), the battery cell terminals are usually connected by means of laser welding, such as using a busbar. The welding quality directly determines the conductivity, mechanical strength, and long-term safety and reliability of the battery module. Common welding defects include incomplete welding, burn-through, and bursting.
[0003] In related technologies, welding quality inspection mainly relies on manual visual inspection and inspection methods based on 2D machine vision. Among them, the inspection method based on 2D machine vision achieves defect detection through grayscale threshold segmentation, which can identify surface stains, obvious pits or protrusions to a certain extent; manual visual inspection judges the weld height information by the flatness of the laser line on the image.
[0004] However, the 2D machine vision detection methods in related technologies are not effective in detecting defects such as cold welds (insufficient connection strength but possibly intact surface) and pits or protrusions with gradual height changes. They are easily affected by ambient lighting and surface reflections of the workpiece, resulting in poor imaging stability. Furthermore, manual visual inspection in related technologies often leads to thicker laser lines and a large number of pixels in the edge transition zone, which in turn leads to inaccurate detection. These issues urgently need to be addressed. Summary of the Invention
[0005] This application provides a method, apparatus, electronic device, and storage medium for inspecting the welding quality of battery cell terminals, in order to solve the problems of poor detection effect of related technologies for defects such as cold welds, pits or protrusions with gradual height changes, susceptibility to ambient light and reflections from the workpiece surface, and poor imaging stability. It achieves full marking detection of welding defects, is not easily affected by ambient light interference, ensures long-term stable detection performance, and realizes automated, high-precision, and high-efficiency inspection of battery cell welding quality.
[0006] The first aspect of this application provides a method for detecting the welding quality of battery cell terminals, including the following steps: Determine the welding area of the battery cell terminals; Acquire three-dimensional point cloud data of the weld bead to be inspected within the electrode welding area of the battery cell, and acquire two-dimensional texture images of the surface of the weld bead to be inspected; Three-dimensional features are extracted from the three-dimensional point cloud data, and two-dimensional features are extracted from the two-dimensional texture image. The quality inspection results of the battery cell electrode welding area are obtained based on the three-dimensional and two-dimensional features.
[0007] Optionally, in some embodiments, extracting 3D features from 3D point cloud data includes: Generate a point cloud map from 3D point cloud data; The point cloud image is segmented into a region of interest (ROI) to obtain the segmentation results. Based on a preset height threshold, the protrusion height feature, the depression depth feature, and the weld width feature are obtained from the segmentation results. The three-dimensional features are obtained based on the characteristics of the protrusion height, the depression depth, and the weld width.
[0008] Optionally, in some embodiments, extracting two-dimensional features from a two-dimensional texture image includes: The two-dimensional texture image is processed by grayscale and contrast enhancement to obtain the processed image. Based on a preset threshold segmentation algorithm and / or edge detection algorithm, at least one region that meets the preset requirements is extracted from the processed image, and two-dimensional features are obtained based on the welding area of each region.
[0009] Optionally, in some embodiments, the quality inspection results of the cell electrode welding area are obtained based on three-dimensional features and two-dimensional features, including: Based on preset fusion judgment rules and / or preset machine learning models, feature analysis is performed on three-dimensional and two-dimensional features to obtain quality detection results.
[0010] Optionally, in some embodiments, the quality inspection results include at least one of poor solder joints, pores, and weld spatter.
[0011] A second aspect of this application provides a battery cell electrode welding quality inspection device, comprising: The module is used to determine the welding area of the battery cell terminals; The acquisition module is used to acquire the three-dimensional point cloud data of the weld bead to be inspected within the welding area of the battery cell electrode post, and to collect the two-dimensional texture image of the surface of the weld bead to be inspected. The detection module is used to extract three-dimensional features from three-dimensional point cloud data and two-dimensional features from two-dimensional texture images, and obtain the quality detection results of the battery cell electrode welding area based on the three-dimensional features and two-dimensional features.
[0012] Optionally, in some embodiments, the detection module is specifically used for: Generate a point cloud map from 3D point cloud data; The point cloud map is segmented into ROI regions to obtain segmentation results. Based on a preset height threshold, the protrusion height feature, depression depth feature, and weld width feature are obtained from the segmentation results. The three-dimensional features are obtained based on the characteristics of the protrusion height, the depression depth, and the weld width.
[0013] Optionally, in some embodiments, the detection module is specifically used for: The two-dimensional texture image is processed by grayscale and contrast enhancement to obtain the processed image. Based on a preset threshold segmentation algorithm and / or edge detection algorithm, at least one region that meets the preset requirements is extracted from the processed image, and two-dimensional features are obtained based on the welding area of each region.
[0014] Optionally, in some embodiments, the detection module is specifically used for: Based on preset fusion judgment rules and / or preset machine learning models, feature analysis is performed on three-dimensional and two-dimensional features to obtain quality detection results.
[0015] Optionally, in some embodiments, the quality inspection results include at least one of poor solder joints, pores, and weld spatter.
[0016] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the cell electrode welding quality inspection method described in the first aspect embodiment.
[0017] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the cell electrode welding quality inspection method described in the first aspect embodiment.
[0018] Therefore, by acquiring the three-dimensional point cloud data of the weld bead to be inspected within the welding area of the battery cell electrode post and its two-dimensional texture image, its three-dimensional and two-dimensional features can be extracted, and the quality inspection results of the battery cell electrode post welding area can be obtained based on the three-dimensional and two-dimensional features. This solves the problems of poor detection effect of related technologies on defects such as cold welds, pits or protrusions with gradual height changes, susceptibility to ambient light and workpiece surface reflection, and poor imaging stability. It achieves full-marking detection of welding defects, is less affected by ambient light interference, ensures long-term stable detection performance, and realizes automated, high-precision, and high-efficiency battery cell welding quality inspection.
[0019] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0020] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a method for inspecting the welding quality of battery cell terminals according to an embodiment of this application; Figure 2 This is a schematic diagram of a post-weld visual inspection station layout according to an embodiment of this application; Figure 3 This is a schematic diagram illustrating a qualified result of photo recognition according to an embodiment of this application; Figure 4 This is a schematic diagram illustrating a photographic recognition of a non-compliant result according to an embodiment of this application; Figure 5 This is a schematic diagram of a partial camera detection setting range according to an embodiment of this application; Figure 6 This is a flowchart illustrating a 3D camera algorithm according to an embodiment of this application; Figure 7 This is a flowchart illustrating a 2D camera algorithm according to an embodiment of this application; Figure 8 This is a flowchart illustrating a 2D camera detection method according to one embodiment of this application; Figure 9 This is a block diagram of a battery cell electrode welding quality inspection device according to an embodiment of this application; Figure 10 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0021] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0022] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for inspecting the welding quality of battery cell terminals according to embodiments of this application. Addressing the shortcomings of existing detection methods mentioned in the background art, such as poor detection performance for defects like cold welds and gently varying height pits or protrusions, susceptibility to ambient lighting and workpiece surface reflections, and poor imaging stability, this application provides a method for inspecting the welding quality of battery cell terminals. This method acquires three-dimensional point cloud data of the weld bead to be inspected within the welding area of the battery cell terminal and a two-dimensional texture image of its surface, extracts its three-dimensional and two-dimensional features, and obtains the quality inspection result of the welding area based on these features. This solves the problems of poor detection performance for defects like cold welds and gently varying height pits or protrusions, susceptibility to ambient lighting and workpiece surface reflections, and poor imaging stability in existing detection methods. It achieves full-marking detection of welding defects, is less susceptible to ambient light interference, ensures long-term stable detection performance, and realizes automated, high-precision, and high-efficiency battery cell welding quality inspection.
[0023] Specifically, Figure 1 A flowchart illustrating the battery cell electrode welding quality inspection method provided in this application embodiment.
[0024] like Figure 1 As shown, the method for inspecting the welding quality of the battery cell terminals includes the following steps: In step S101, the cell electrode welding area is determined.
[0025] The welding area refers to the connection area formed by welding and the surrounding area to be inspected.
[0026] In step S102, the three-dimensional point cloud data of the weld to be inspected within the electrode welding area of the battery cell is acquired, and the two-dimensional texture image of the surface of the weld to be inspected is collected.
[0027] Among them, the weld bead to be detected is the continuous weld trajectory formed by welding; the three-dimensional point cloud data is a set of coordinate points describing the three-dimensional features of the welding area; and the two-dimensional texture image is a two-dimensional image describing the gray-scale distribution, detailed texture and morphological features of the surface of the welding area.
[0028] Specifically, in this embodiment, a 3D line-scanning laser camera and a 2D area array camera mounted on a three-axis linear motion mechanism can be used to collaboratively acquire images of the welded cell electrode area. The specific process is as follows: after the module is transported to a fixed position by the production line and positioned, the three-axis mechanism is controlled to drive the vision acquisition unit (i.e., the camera assembly) to move precisely above the first weld to be inspected and trigger a signal simultaneously. Then, the 3D line-scanning camera moves and scans along the direction of the weld to be inspected (e.g., the X-axis) (or the weld moves under the camera) to acquire continuous three-dimensional point cloud data bands of the weld to be inspected. At the same time, the 2D area array camera takes one or more shots to acquire two-dimensional texture images of the surface of the same weld to be inspected. The above process is repeated until all welds to be inspected have been inspected.
[0029] It should be understood that the three-axis linear motion mechanism in this embodiment of the application is driven by a high-precision servo motor, and in conjunction with linear guides and ball screws, it can move in the X, Y, and Z directions with a positioning accuracy of ±0.05mm. Its load platform is used to mount the vision acquisition unit. The vision acquisition unit includes a 3D line-scan laser camera using laser triangulation and a high-resolution 2D area array camera. The two are fixed together by a rigid aluminum alloy mounting plate, and their relative positions remain unchanged. Focusing is unified through Z-axis movement. Different angled ring light sources or strip light sources can be selected as needed to reduce glare and enhance contrast. Furthermore, the computing control unit includes an industrial computer (International Patent Classification, IPC) and a motion control card. The IPC is responsible for running the detection algorithm, human-machine interface, and database, while the motion control card is responsible for receiving IPC commands and precisely controlling the movement of the three-axis mechanism.
[0030] In step S103, three-dimensional features are extracted from the three-dimensional point cloud data, and two-dimensional features are extracted from the two-dimensional texture image. The quality inspection results of the battery cell electrode welding area are obtained based on the three-dimensional features and the two-dimensional features.
[0031] In some embodiments, extracting three-dimensional features from three-dimensional point cloud data includes: generating a point cloud map from the three-dimensional point cloud data; performing ROI region segmentation on the point cloud map to obtain segmentation results, and obtaining protrusion height features, depression depth features, and weld width features based on a preset height threshold; and obtaining three-dimensional features based on the protrusion height features, depression depth features, and weld width features.
[0032] In some embodiments, extracting two-dimensional features from a two-dimensional texture image includes: performing grayscale processing and contrast enhancement processing on the two-dimensional texture image to obtain a processed image; extracting at least one region that meets preset requirements from the processed image based on a preset threshold segmentation algorithm and / or edge detection algorithm, and obtaining two-dimensional features based on the welding area of each region.
[0033] In some embodiments, the quality inspection results of the battery cell electrode welding area are obtained based on three-dimensional features and two-dimensional features, including: performing feature analysis on the three-dimensional features and two-dimensional features based on preset fusion judgment rules and / or preset machine learning models to obtain quality inspection results.
[0034] In some embodiments, the quality inspection results include at least one of incomplete solder joints, pores, and weld spatter.
[0035] Among them, the three-dimensional features describe the three-dimensional spatial morphology of the welding area; the two-dimensional features describe the surface condition of the welding area; the quality inspection result is the conclusion of whether the welding area is qualified or not; the point cloud map is a visual image describing the three-dimensional spatial structure of the welding area; the preset height threshold is a pre-set benchmark value used to determine whether the height of the welding area meets the requirements; the protrusion height feature describes the maximum vertical distance of the surface of the welding area above the benchmark plane; the depression depth feature describes the maximum vertical distance of the surface of the welding area below the benchmark plane; the weld width feature is the average width of the weld bead to be inspected along the horizontal direction or the width of the feature section; the preset requirements are the qualified ranges of various features pre-set based on welding quality standards; the welding area is the physical area corresponding to the actual pixels occupied by the welding area in the two-dimensional image; the preset fusion judgment rule is a pre-set logical criterion for quality judgment by combining three-dimensional features and two-dimensional features; and the preset machine learning model is an algorithm model that can perform target state judgment or defect identification based on input features after being trained on samples.
[0036] Specifically, in this embodiment, the point cloud image can first be segmented into ROI regions, and point clouds that are significantly higher or lower than the substrate plane can be segmented using a height threshold to preliminarily determine the weld area. At the same time, the two-dimensional texture image can be preprocessed such as grayscale conversion and contrast enhancement. Then, small and bright areas that are not connected to the main body of the weld to be detected can be extracted from the image through edge detection or threshold segmentation algorithms, and their area and number can be calculated. Subsequently, height, width, and depression depth features can be extracted from the 3D point cloud data, and texture, color, and spatter features can be extracted from the 2D image. Finally, the above features can be comprehensively analyzed based on preset fusion judgment rules or machine learning models to output welding quality results or quality inspection results containing defect types such as cold welds and bursts, and the relevant results can be transmitted to the host computer to display OK or NG.
[0037] Therefore, this application embodiment integrates the advantages of 2D and 3D vision technologies, using a combination of both cameras for post-weld inspection: 2D images can clearly distinguish surface weld edges and surface welding defects such as pores and weld spatter; 3D line-scan laser uses an active light source with anti-ambient light characteristics, and when combined with 2D detection, algorithms can eliminate misjudgments caused by reflections. This solves the problems of poor detection effect of related technologies for defects such as cold welds, pits or protrusions with gradual height changes, susceptibility to ambient light and workpiece surface reflections, and poor imaging stability. It achieves full marking detection of welding defects, effectively improving the accuracy and precision of defect detection and the product qualification rate; the entire detection process is automated and intelligent, requiring no manual intervention from automatic positioning and data acquisition to fusion analysis, and automatically marking welding defects on the host computer after identification, ultimately achieving automated, high-precision, and high-efficiency inspection of battery cell electrode welding quality.
[0038] Furthermore, to enable those skilled in the art to better understand the cell electrode welding quality inspection method of this application, the following is combined with... Figures 2 to 5 Specific embodiments will be described below.
[0039] Figure 2 This application provides a schematic diagram of a post-weld visual inspection station layout as an embodiment. Figure 3 This application provides a schematic diagram of a qualified result for image recognition as an embodiment of the present application. Figure 4 This application provides a schematic diagram illustrating a photographic recognition of a non-compliant result, as one embodiment of the present application. Figure 5 This is a schematic diagram of a partial camera detection setting range provided in one embodiment of this application.
[0040] like Figure 2 As shown in the schematic diagram, the post-weld visual inspection station layout mainly includes: a safety roller shutter door 201, a protective cover 202, a vision mounting frame 203, a pack transfer trolley (AGV) 204, a trolley positioning mechanism 205, a gantry square tube frame 206, a cleaning three-axis assembly 207, a cleaning mechanism 208, a 3D vision system 209, and a cleaning fixture 210. Specifically, in this embodiment, after cleaning, the battery assembly can be transported to this station by an AGV and photographed to obtain a 2D image of the welding area.
[0041] Furthermore, such as Figure 3 As shown in the embodiment of this application, the weld is matched with the preset requirements and the adaptability score is calculated. The actual area of the weld corresponding to the OK surface is 150.69 mm²; while as Figure 4 As shown, since the actual weld width exceeds the preset requirement, this embodiment determines it to be in an NG (Not Acceptable) state. The preset requirement can be as follows: Figure 5 As shown; where, Figure 5(a) is a schematic diagram of the detection range set by the 2D camera. Figure 5 (b) is a schematic diagram of the 3D camera detection setting range. Figure 5 (c) is a schematic diagram of the inspection at this workstation. It should be understood that the 2D camera is used to detect and process the acquired images to achieve accurate identification of the welding area and weld; the 3D camera is used to identify the weld depth; the inspection at this workstation is used to further complete the multi-dimensional comprehensive inspection of weld width, weld area, pore depth, pore area, incomplete weld depth, and incomplete weld area.
[0042] Furthermore, to enable those skilled in the art to better understand how 3D camera inspection and 2D camera inspection are implemented in the battery cell electrode welding quality inspection method of this application, the following will be combined with... Figures 6 to 8 Specific embodiments will be described below.
[0043] Figure 6 This is a flowchart of a 3D camera algorithm provided in one embodiment of this application.
[0044] As one possible way to achieve this, such as Figure 6 As shown, the 3D camera algorithm includes the following steps: S601, Agv carrier module enters the workstation.
[0045] The S602 uses a 2D camera to position the module.
[0046] S603, a three-axis mechanism guides the 3D inspection camera and 2D inspection camera to align with the weld.
[0047] S604: 3D camera generates point cloud map, 2D camera takes picture.
[0048] S605 generates a 3D model from point cloud images, determines the tangent plane of the weld, and detects the depth of depressions or the height of protrusions; after taking pictures with a 2D camera, it performs threshold segmentation and edge extraction; the welding area is calculated by the weld width, and surface defects are determined by grayscale value processing.
[0049] S606 transmits the results to the industrial control computer.
[0050] Furthermore, Figure 7 A flowchart of a 2D camera algorithm provided in one embodiment of this application.
[0051] As one possible way to achieve this, such as Figure 7 As shown, the 2D camera algorithm includes the following steps: 701, 2D camera image acquisition.
[0052] 702, Image Preprocessing: Denoising and Contrast Enhancement.
[0053] 703, ROI positioning: Matching with the standard template weld position.
[0054] 704, Extract welding features: (1) Perform texture analysis: Determine whether the surface is uniform, rough or raised; (2) Detect spatter: Since spatter is usually a bright white spot, set a high grayscale threshold to separate it from the dark background; (3) Two-dimensional geometric measurement: Measure the weld area, width, etc.
[0055] 705, send the judgment result to the host computer.
[0056] Furthermore, Figure 8 This is a flowchart illustrating a 2D camera detection method as provided in one embodiment of this application.
[0057] As one possible way to achieve this, such as Figure 8 As shown, the 2D camera detection includes the following steps: S801, 3D line scan to obtain point cloud.
[0058] S802, filtering and noise reduction.
[0059] S803, establish the reference plane.
[0060] S804, extract the profile.
[0061] S805, threshold positioning: filter 1mm≤z≤4mm.
[0062] S806, Height calculation: Take the average of points from 0.3-2.75mm; Width calculation: Take the span from 0.625-2.75mm.
[0063] S807: Take the maximum height from all cross-sections; take the average width from all cross-sections.
[0064] S808, output results.
[0065] The battery cell electrode welding quality inspection method proposed in this application can extract three-dimensional point cloud data of the weld bead to be inspected within the battery cell electrode welding area and two-dimensional texture images of its surface by acquiring the three-dimensional point cloud data and two-dimensional texture images of the surface. Based on these three-dimensional and two-dimensional features, the quality inspection result of the battery cell electrode welding area is obtained. This solves the problems of poor detection effect of related technologies on defects such as cold welds, pits or protrusions with gradual height changes, susceptibility to ambient light and workpiece surface reflection, and poor imaging stability. It achieves full-marking detection of welding defects, is less susceptible to ambient light interference, ensures long-term stable detection performance, and realizes automated, high-precision, and high-efficiency battery cell welding quality inspection.
[0066] Next, the battery cell electrode welding quality inspection device proposed in this application is described with reference to the accompanying drawings.
[0067] Figure 9 This is a block diagram of the battery cell electrode welding quality inspection device proposed in the embodiments of this application.
[0068] like Figure 9 As shown, the battery cell electrode welding quality inspection device 10 includes: a determination module 100, an acquisition module 200, and an inspection module 300.
[0069] The module 100 is used to determine the welding area of the battery cell electrode post; the module 200 is used to acquire the three-dimensional point cloud data of the weld to be inspected within the welding area of the battery cell electrode post, and to collect the two-dimensional texture image of the surface of the weld to be inspected; the module 300 is used to extract three-dimensional features from the three-dimensional point cloud data, extract two-dimensional features from the two-dimensional texture image, and obtain the quality inspection result of the welding area of the battery cell electrode post based on the three-dimensional features and the two-dimensional features.
[0070] Optionally, in some embodiments, the detection module 300 is specifically used to: generate a point cloud map based on the three-dimensional point cloud data; perform ROI region segmentation on the point cloud map to obtain segmentation results, and obtain protrusion height features, depression depth features and weld width features based on the segmentation results according to a preset height threshold; and obtain three-dimensional features based on the protrusion height features, depression depth features and weld width features.
[0071] Optionally, in some embodiments, the detection module 300 is specifically used to: perform grayscale processing and contrast enhancement processing on the two-dimensional texture image to obtain a processed image; extract at least one region that meets the preset requirements from the processed image based on a preset threshold segmentation algorithm and / or edge detection algorithm, and obtain two-dimensional features based on the welding area of each region.
[0072] Optionally, in some embodiments, the detection module 300 is specifically used to: perform feature analysis on three-dimensional features and two-dimensional features based on preset fusion judgment rules and / or preset machine learning models to obtain quality detection results.
[0073] Optionally, in some embodiments, the quality inspection results include at least one of poor solder joints, pores, and weld spatter.
[0074] It should be noted that the foregoing explanation of the embodiment of the cell electrode welding quality inspection method also applies to the cell electrode welding quality inspection device of this embodiment, and will not be repeated here.
[0075] The battery cell electrode welding quality inspection device proposed in this application can acquire three-dimensional point cloud data of the weld bead to be inspected within the battery cell electrode welding area and two-dimensional texture images of its surface, extract its three-dimensional and two-dimensional features, and obtain the quality inspection result of the battery cell electrode welding area based on the three-dimensional and two-dimensional features. This solves the problems of poor detection effect of related technologies on defects such as cold welds, pits or protrusions with gradual height changes, susceptibility to ambient light and workpiece surface reflection, and poor imaging stability. It achieves full-marking detection of welding defects, is less susceptible to ambient light interference, ensures long-term stable detection performance, and realizes automated, high-precision, and high-efficiency battery cell welding quality inspection.
[0076] Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 1001, the processor 1002, and the computer program stored on the memory 1001 and capable of running on the processor 1002.
[0077] When the processor 1002 executes the program, it implements the cell electrode welding quality detection method provided in the above embodiments.
[0078] Furthermore, the electronic device also includes: Communication interface 1003 is used for communication between memory 1001 and processor 1002.
[0079] The memory 1001 is used to store computer programs that can run on the processor 1002.
[0080] The memory 1001 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
[0081] If the memory 1001, processor 1002, and communication interface 1003 are implemented independently, then the communication interface 1003, memory 1001, and processor 1002 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0082] Optionally, in a specific implementation, if the memory 1001, processor 1002, and communication interface 1003 are integrated on a single chip, then the memory 1001, processor 1002, and communication interface 1003 can communicate with each other through an internal interface.
[0083] The processor 1002 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0084] This application also provides a computer-readable storage medium having a computer program stored thereon, which is implemented when executed by a processor. Figure 1 The method for inspecting the welding quality of battery cell terminals as described in the embodiment.
[0085] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0086] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0087] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0088] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0089] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0090] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
[0091] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0092] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.
Claims
1. A method for inspecting the welding quality of battery cell terminals, characterized in that, Includes the following steps: Determine the welding area of the battery cell terminals; Acquire three-dimensional point cloud data of the weld bead to be inspected within the welding area of the battery cell electrode post, and acquire two-dimensional texture images of the surface of the weld bead to be inspected; Three-dimensional features are extracted from the three-dimensional point cloud data, and two-dimensional features are extracted from the two-dimensional texture image. The quality inspection result of the battery cell electrode welding area is obtained based on the three-dimensional features and the two-dimensional features.
2. The method according to claim 1, characterized in that, The step of extracting 3D features from the 3D point cloud data includes: Generate a point cloud map based on the three-dimensional point cloud data; The point cloud map is segmented into ROI regions to obtain segmentation results, and based on a preset height threshold, the protrusion height feature, the depression depth feature, and the weld width feature are obtained according to the segmentation results. The three-dimensional features are obtained based on the protrusion height feature, the depression depth feature, and the weld width feature.
3. The method according to claim 2, characterized in that, The step of extracting two-dimensional features from the two-dimensional texture image includes: The two-dimensional texture image is subjected to grayscale processing and contrast enhancement processing to obtain the processed image; Based on a preset threshold segmentation algorithm and / or edge detection algorithm, at least one region that meets the preset requirements is extracted from the processed image, and the two-dimensional feature is obtained by calculating the welding area of each region.
4. The method according to claim 1, characterized in that, The quality inspection results of the cell electrode welding area are obtained based on the three-dimensional features and the two-dimensional features, including: Based on preset fusion judgment rules and / or preset machine learning models, feature analysis is performed on the three-dimensional features and the two-dimensional features to obtain the quality detection results.
5. The method according to any one of claims 1-4, characterized in that, The quality inspection results include at least one of the following: incomplete soldering, pores, and weld spatter.
6. A device for inspecting the welding quality of battery cell terminals, characterized in that, include: The module is used to determine the welding area of the battery cell terminals; The acquisition module is used to acquire three-dimensional point cloud data of the weld bead to be detected within the welding area of the battery cell electrode post, and to collect two-dimensional texture images of the surface of the weld bead to be detected. The detection module is used to extract three-dimensional features from the three-dimensional point cloud data, extract two-dimensional features from the two-dimensional texture image, and obtain the quality detection result of the battery cell electrode welding area based on the three-dimensional features and the two-dimensional features.
7. The apparatus according to claim 6, characterized in that, The detection module is specifically used for: Generate a point cloud map based on the three-dimensional point cloud data; The point cloud map is segmented into ROI regions to obtain segmentation results, and based on a preset height threshold, the protrusion height feature, the depression depth feature, and the weld width feature are obtained according to the segmentation results. The three-dimensional features are obtained based on the protrusion height feature, the depression depth feature, and the weld width feature.
8. The apparatus according to claim 6, characterized in that, The detection module is specifically used for: The two-dimensional texture image is subjected to grayscale processing and contrast enhancement processing to obtain the processed image; Based on a preset threshold segmentation algorithm and / or edge detection algorithm, at least one region that meets the preset requirements is extracted from the processed image, and the two-dimensional feature is obtained by calculating the welding area of each region.
9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the cell electrode welding quality inspection method as described in any one of claims 1-5.
10. A computer-readable storage medium storing a computer program, characterized in that, When executed by the processor, the program implements the cell electrode welding quality inspection method as described in any one of claims 1-5.