Battery pack appearance defect detection method, device, equipment, medium and program product

Abstract

The embodiment of the invention provides a battery pack appearance defect detection method, device and equipment, a medium and a program product, and the method comprises the steps: determining an initial conversion matrix between two frames of point cloud data of an adjacent collection sequence based on the collection sequence of multiple frames of point cloud data corresponding to a battery pack; wherein the collection view angles of all frames of point cloud data are different; adjusting the initial conversion matrix based on the global structure feature of each frame of point cloud data and the point cloud quality and the local geometric feature of each point in each frame of point cloud data to obtain a conversion matrix corresponding to each frame of point cloud data; converting the multi-frame point cloud data based on the conversion matrix to obtain a fusion point cloud structure of the battery pack; and based on the fused point cloud structure, performing defect detection on the battery pack to obtain a detection result. Point cloud conversion is constrained through the global structure features, the point cloud quality and the local geometric features of the multi-frame point cloud data, a complete and accurate battery pack structure is reconstructed, and the accuracy of surface detection is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of battery technology, and are related to but not limited to a method, device, equipment, medium and program product for detecting appearance defects of a battery pack. Background Art

[0002] Point cloud data is widely used in current applications such as 3D modeling and appearance inspection. For example, when inspecting the appearance of a battery pack, the surface of the battery pack may have a metal shell and may have concave-convex structures, curved surfaces or slight deformations. When performing defect detection through image recognition, it is difficult to quantify depth information, and the reflection and shadow of the metal on the 2D image will lead to inaccurate inspection results. Therefore, 3D modeling through point cloud data is required to accurately perform appearance inspection.

[0003] However, the solutions provided by related technologies are mostly single-view or small-scale point cloud registration optimization, which usually have problems such as occlusion, noise, and low point cloud quality in some areas, making it impossible to achieve complete, accurate, and high-fidelity 3D reconstruction. The battery pack has a large area, and the size and type of defects vary greatly. When the methods in related technologies are used for registration, a single point cloud data cannot cover the entire battery pack, or when multiple point cloud data are spliced, the low point cloud quality in some areas and the local optimal point cloud cannot be solved. The reconstructed battery pack point cloud structure cannot be used for accurate defect detection. Summary of the invention

[0004] In order to solve the problems existing in the related technologies, the embodiments of the present application provide a battery pack appearance defect detection method, device, equipment, medium and program product, which constrains the point cloud conversion through the global structural characteristics, point cloud quality and local geometric characteristics of multi-frame point cloud data, reconstructs a complete and accurate battery pack structure, and improves the accuracy of surface detection.

[0005] In a first aspect, the present application provides a method for detecting defects in the appearance of a battery pack, and the method for detecting defects in the appearance of a battery pack includes: determining an initial transformation matrix between two frames of point cloud data in adjacent acquisition sequences based on an acquisition sequence of multiple frames of point cloud data corresponding to the battery pack; wherein the acquisition perspectives of each frame of point cloud data are different; based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and local geometric features, adjusting the initial transformation matrix to obtain a transformation matrix corresponding to each frame of point cloud data; based on the transformation matrix, transforming multiple frames of point cloud data to obtain a fused point cloud structure of the battery pack; based on the fused point cloud structure, performing defect detection on the battery pack to obtain a detection result.

[0006] In the above embodiment, multi-frame point cloud data collected from different perspectives can supplement local data from different angles, reduce blind spots, and reconstruct a complete battery pack structure; the embodiment of the present application adjusts the initial transformation matrix through the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features. The transformation matrix can be adjusted based on point cloud data with high point cloud quality, which can reduce the influence of noise and make the conversion of point cloud data more reliable. The transformation matrix is ​​constrained by local features and global features during the registration process, so that the transformation matrix can improve the registration accuracy while reducing the registration deviation caused by local optimality, thereby obtaining a more accurate fused point cloud structure for the battery pack. Defect detection is performed based on the fused point cloud structure, which can improve the accuracy and efficiency of battery pack surface defect detection, reduce the false detection rate of manual and two-dimensional image detection, and provide reliable quality assurance for new energy battery manufacturing.

[0007] In some embodiments, the method for detecting defects in the appearance of a battery pack also includes: extracting multi-scale features of each point in each frame of point cloud data to obtain multi-scale features of each point in each frame of point cloud data; fusing the multi-scale features of each point in each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, and the global structural features of each frame of point cloud data to obtain fused features of each point in each frame of point cloud data; determining an initial transformation matrix between two frames of point cloud data in adjacent acquisition sequences based on the acquisition sequence of the multi-frame point cloud data corresponding to the battery pack, including: obtaining a preset transformation matrix between two frames of point cloud data in adjacent acquisition sequences; determining the initial transformation matrix between two frames of point cloud data in adjacent acquisition sequences based on the preset transformation matrix, the fused features of each point in each frame of point cloud data, and the initial position of each point in each frame of point cloud data in the initial coordinate system of each frame of point cloud data.

[0008] In the above embodiment, the change matrix is ​​adjusted by the fusion features corresponding to the two point clouds, so that the feature information of the point cloud surface can be better used to achieve point cloud matching and improve the accuracy of point cloud registration.

[0009] In some embodiments, multi-scale feature extraction is performed on each point in each frame of point cloud data to obtain multi-scale features of each point in each frame of point cloud data, including: extracting features from multiple neighborhoods of different radii corresponding to each point in each frame of point cloud data to obtain multiple neighborhood features of each point; and splicing the multiple neighborhood features of each point to obtain multi-scale features of each point in each frame of point cloud data.

[0010] In some embodiments, based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features, the initial transformation matrix is ​​adjusted to obtain the transformation matrix corresponding to each frame of point cloud data, including: constructing a global optimization function based on two frames of point cloud data in adjacent acquisition order and the corresponding initial transformation matrix; determining the initial transformation matrix when the global optimization function satisfies the first target condition as the optimization matrix; based on the point cloud quality of each point in each frame of point cloud data, performing weighted calculation on the optimization matrix to obtain a weighted transformation matrix between two frames of point cloud data in adjacent acquisition order; based on the global structural features of each frame of point cloud data and the local geometric features of each point in each frame of point cloud data, adjusting the weighted transformation matrix to obtain the transformation matrix corresponding to each frame of point cloud data.

[0011] In the above embodiment, two frames of point cloud data in adjacent acquisition order and the corresponding initial transformation matrix are globally optimized so that multiple local point clouds can be spliced ​​into a complete point cloud, providing high-precision input data for battery pack defect detection; the optimization matrix is ​​adjusted according to the point cloud quality of each point in each frame of point cloud data, which can suppress the interference of noise areas and avoid the registration from falling into local optimality, making the registration more dependent on reliable areas and improving the registration accuracy; finally, the point cloud transformation is comprehensively constrained by combining local geometric features and global structural features, so that the registration result can reflect local details while maintaining overall consistency.

[0012] In some embodiments, based on the global structural features of each frame of point cloud data and the local geometric features of each point in each frame of point cloud data, the weighted transformation matrix is ​​adjusted to obtain the transformation matrix corresponding to each frame of point cloud data, including: constructing a target optimization function based on the global structural features of each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, the weighted transformation matrix between two frames of point cloud data in adjacent acquisition order, the local weight coefficient and the global weight coefficient; the weighted transformation matrix when the target optimization function satisfies the second target condition is determined as the transformation matrix.

[0013] In some embodiments, multiple frames of point cloud data are converted based on a transformation matrix to obtain a fused point cloud structure of the battery pack, including: based on the transformation matrix corresponding to each frame of point cloud data, each frame of point cloud data is converted to a global coordinate system to obtain multiple frames of converted point cloud data; multiple frames of converted point cloud data are spliced ​​to obtain a fused point cloud structure.

[0014] In the above embodiment, by converting each frame of point cloud data into a global coordinate system and stitching them together, these local point cloud data can be integrated into a complete three-dimensional model, thereby being able to more comprehensively and accurately reflect the geometric structure of the battery pack, provide accurate input data for defect detection of the battery pack, and improve the accuracy of defect detection.

[0015] In some embodiments, the method for detecting defects in the appearance of a battery pack further includes: extracting local features of each point in each frame of point cloud data based on the neighborhood of each point in each frame of point cloud data to obtain local geometric features of each point in each frame of point cloud data; extracting features at different levels on each frame of point cloud data to obtain global structural features of each frame of point cloud data; determining the point density of each point in each frame of point cloud data based on the average distance between each point in the corresponding neighborhood of each point in each frame of point cloud data; determining the point cloud quality of each point in each frame of point cloud data based on the local geometric features and point density of each point in each frame of point cloud data.

[0016] In the above embodiment, detailed information on the battery pack surface (such as dents and cracks) can be captured through local feature extraction, while the overall shape of the battery pack can be captured through global feature extraction, and the point cloud quality of each point can be obtained, ensuring that stable and reliable features can still be extracted in complex scenarios.

[0017] In some embodiments, different levels of feature extraction are performed on each frame of point cloud data to obtain global structural features of each frame of point cloud data, including: performing multiple different levels of local feature extraction on each frame of point cloud data to obtain multiple local features corresponding to each frame of point cloud data; performing global convolution on multiple local features corresponding to each frame of point cloud data to obtain global structural features corresponding to each frame of point cloud data.

[0018] In some embodiments, the point cloud quality of each point in each frame of point cloud data is determined based on the local geometric features and point density of each point in each frame of point cloud data, including: determining the covariance matrix of the neighborhood corresponding to each point and the covariance eigenvalue of each point based on the local geometric features of each point in each frame of point cloud data; determining the noise of each point in each frame of point cloud data based on the covariance eigenvalue; performing weighted calculation on the noise and point density of each point in each frame of point cloud data to obtain the point cloud quality of each point in each frame of point cloud data.

[0019] In a second aspect, an embodiment of the present application provides a battery pack appearance defect detection device, which includes: a determination module for determining an initial transformation matrix between two frames of point cloud data in adjacent acquisition sequences based on the acquisition sequence of multiple frames of point cloud data corresponding to the battery pack; an adjustment module for adjusting the initial transformation matrix based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and local geometric features to obtain a transformation matrix corresponding to each frame of point cloud data; a conversion module for converting multiple frames of point cloud data based on the transformation matrix to obtain a fused point cloud structure of the battery pack; and a defect detection module for performing defect detection on the battery pack based on the fused point cloud structure to obtain a detection result.

[0020] In a third aspect, an embodiment of the present application provides a battery pack appearance defect detection device, the battery pack appearance defect detection device comprising: a memory for storing executable instructions; and a processor for implementing the above-mentioned battery pack appearance defect detection method when executing the executable instructions stored in the memory.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing executable instructions for causing a processor to execute the executable instructions to implement the above-mentioned battery pack appearance defect detection method.

[0022] In the fifth aspect, an embodiment of the present application provides a computer program product or a computer program, which includes executable instructions, and the executable instructions are stored in a computer-readable storage medium; when the processor of the battery pack appearance defect detection device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the above-mentioned battery pack appearance defect detection method is implemented.

[0023] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a schematic diagram of the structure of a battery pack appearance defect detection device provided in an embodiment of the present application; Figure 2 This is an optional process diagram of the battery pack appearance defect detection method provided in the embodiment of the present application. Figure 1 ; Figure 3 This is an optional process diagram of the battery pack appearance defect detection method provided in the embodiment of the present application. Figure 2 ; Figure 4 This is an optional process diagram of the battery pack appearance defect detection method provided in the embodiment of the present application. Figure 3 ; Figure 5 It is an optional flowchart of the battery pack detection process provided in the embodiment of the present application; Figure 6 It is an optional flow chart of point cloud stitching provided in an embodiment of the present application; Figure 7 It is an optional structural diagram of point cloud stitching provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0026] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. Unless otherwise defined, all technical and scientific terms used in the embodiments of the present application have the same meaning as those commonly understood by those skilled in the art of the technical field of the embodiments of the present application. The terms used in the embodiments of the present application are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0027] At present, since the acquisition range of sensors is usually limited, when a large-area 3D environment model needs to be constructed, a single sensor cannot cover the entire target area. Therefore, point cloud data from multiple sensors or multiple perspectives must be registered and spliced ​​to form a complete large-scale point cloud. In order to obtain a complete large-scale point cloud, point clouds from different perspectives or different positions must be effectively registered and spliced. However, due to the possible displacement, rotation and scale differences between each point cloud, the registration process is complicated and prone to errors. In addition, point cloud data usually contains noise, and due to occlusion, reflection and other reasons, the collected point cloud may be incomplete, affecting the subsequent registration and splicing accuracy.

[0028] Point cloud stitching technology in related technologies can be divided into feature-based registration methods, iterative closest point (ICP) algorithms, global optimization methods, etc. Among them, the ICP algorithm is often used for point cloud registration, but the algorithm relies on initial alignment and is easily affected by error accumulation when registering multiple point clouds, resulting in poor stitching effect; feature-based registration extracts geometric features of point clouds for matching, but when stitching over a large range, feature matching is not stable enough and is easily affected by noise and occlusion; global optimization methods such as the Globally Optimal Iterative Closest Point (GO-ICP) avoid local optimality through global search, but the amount of calculation is large, cannot meet real-time requirements, and have poor performance in large-scale stitching. These methods are effective in simple scenarios, but when facing large-scale point cloud stitching, there are still problems such as low accuracy, large amount of calculation, and poor noise resistance.

[0029] For targets to be inspected such as battery packs, the battery packs have a large area, and the surface often has concave-convex structures (such as heat dissipation grooves, sealing edges), curved surfaces or slight deformations (such as assembly errors, collision depressions). It is difficult for two-dimensional images to accurately quantify depth information; the surface of the battery pack may be a reflective material (such as an aluminum alloy shell) or a dark coating, and traditional optical imaging is easily disturbed by reflections and shadows; and the battery pack needs to detect hidden areas such as the side, bottom, and seams. However, the registration and stitching methods in the existing technology are mostly optimized for the registration of a single perspective or a small-scale point cloud. For the stitching of multiple large-scale point clouds, it is impossible to effectively handle the displacement, rotation, occlusion and noise problems between sensors, nor can it solve the problem of low point cloud quality and local optimality in some areas, and it is impossible to accurately perform defect detection, and the calculation efficiency is low. Therefore, a new detection method is needed that can efficiently complete the stitching of multiple point clouds on the basis of ensuring detection accuracy, so as to form a complete multi-perspective, large-scale point cloud to realize accurate detection of the battery pack surface.

[0030] In order to alleviate the problems existing in the related art, the applicant believes that by transforming the multi-perspective point cloud data, the multi-perspective point cloud data can cover the entire surface of the battery pack, reduce occlusion, and eliminate blind spots that cannot be captured by a single perspective, and is suitable for the complex structure of the battery pack surface; and the present application adjusts the transformation matrix through local features, global features and point cloud quality, thereby avoiding local optimality and interference from low-quality areas, which can improve the alignment accuracy and obtain the accurate point cloud structure of the battery pack, thereby improving the accuracy of battery pack defect detection.

[0031] Based on the above considerations, the inventors have conducted in-depth research and provided a method for detecting defects in the appearance of a battery pack. The method can obtain multi-frame point cloud data by adopting different acquisition perspectives. The initial transformation matrix between two frames of point cloud data in adjacent acquisition sequences is determined based on the acquisition sequence of the multi-frame point cloud data corresponding to the battery pack. The initial transformation matrix is ​​adjusted based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features. The transformation matrix corresponding to each frame of point cloud data is obtained. The multi-frame point cloud data is transformed based on the transformation matrix to obtain a fused point cloud structure of the battery pack. Based on the fused point cloud structure, the battery pack is subjected to defect detection to obtain a detection result.

[0032] In this way, the multi-frame point cloud data collected by the embodiment of the present application from different perspectives can supplement the local data from different angles, reduce blind spots, and reconstruct the complete battery pack structure; the embodiment of the present application adjusts the initial transformation matrix through the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features, and can adjust the transformation matrix based on point cloud data with high point cloud quality, which can reduce the influence of noise and make the conversion of point cloud data more reliable. The transformation matrix is ​​constrained by local features and global features in the alignment process, so that the transformation matrix can improve the alignment accuracy while reducing the alignment deviation caused by local optimality, and obtain a more accurate fused point cloud structure of the battery pack. Defect detection is performed based on the fused point cloud structure, which can improve the accuracy and efficiency of battery pack surface defect detection, reduce the false detection rate of manual and two-dimensional image detection, and provide reliable quality assurance for new energy battery manufacturing.

[0033] New energy batteries are increasingly used in life and industry. New energy batteries are not only used in energy storage power systems such as hydropower, thermal power, wind power and solar power stations, but are also widely used in electric vehicles such as electric bicycles, electric motorcycles, electric vehicles, and aerospace and other fields. With the continuous expansion of the application field of power batteries, the market demand is also constantly expanding. In the embodiments of the present application, the battery involved may be a battery cell, also known as a battery cell. A battery cell refers to a basic unit that can realize the mutual conversion of chemical energy and electrical energy, which can be used to make a battery module or a battery pack, and thus used to supply power to an electrical device. A battery cell may be a secondary battery, which refers to a battery cell that can be used to activate the active material by charging after the battery cell is discharged. The battery cell may be a lithium-ion battery, a sodium-ion battery, a sodium-lithium-ion battery, a lithium metal battery, a sodium metal battery, a lithium-sulfur battery, a magnesium-ion battery, a nickel-hydrogen battery, a nickel-cadmium battery, a lead-acid battery, etc., and the embodiments of the present application are not limited to this.

[0034] In the embodiments of the present application, the battery cell can refer to a battery cell of any shape, such as a square battery cell or a circular battery cell. And the battery cell generally refers to a Battery Cell, that is, one of the basic units constituting the battery. The battery cell is the core component of the battery and is responsible for storing and releasing electrical energy. The battery cell can be: a lithium-ion battery cell (Li-ion Cell), a lithium polymer battery cell (Li-polymer Cell), a nickel-metal hydride battery cell (NiMH Cell), etc. The embodiments of the present application do not make any limitation on the type of the battery cell, and can be specifically selected according to the actual application scenario. In the embodiments of the present application, the battery cell is the core component of the battery pack. A battery pack generally includes multiple battery cells, and these battery cells are combined together to provide the required electrical energy capacity and voltage. The components of the battery pack at least include: battery monomers, a battery management system (BMS, Battery Management System), a housing, a connection harness, connectors, and interfaces, etc. These components work together to combine the battery monomers into a fully functional battery pack for various application scenarios. For example, the battery pack can be applied to electric vehicles, energy storage systems, portable electrical devices, solar systems, wind energy systems, emergency backup power supplies, power tools, or electric bicycles, etc. The embodiments of the present application do not make any limitation on this, and can be specifically selected according to the actual application scenario.

[0035] It should be noted that the battery pack can use different types of battery monomers. For example, lithium-ion batteries, nickel-metal hydride batteries, lithium polymer batteries, etc., which are specifically determined according to the requirements and performance requirements of the actual application.

[0036] In the embodiments of the present application, the battery can also be a single physical module including one or more battery monomers to provide a higher voltage and capacity. When there are multiple battery monomers, the multiple battery monomers are connected in series, parallel, or in a hybrid connection through a busbar component.

[0037] The following describes an exemplary application of the battery pack appearance defect detection device according to the embodiments of the present application. The battery pack appearance defect detection device provided by the embodiments of the present application can be executed by a processor of a computer device. In implementation, the computer device can be any suitable device with data processing capabilities. It can be understood that in battery industrial production, the computer device can refer to any one of a programmable logic controller (PLC), a single-chip microcomputer, a middle-level computer, and a host computer, or it can also be a server, a notebook computer, a tablet computer, a desktop computer, a smart phone, etc. The computer device can also refer to a lower-level computer, such as an industrial control computer, a programmable logic controller (PLC), etc. In some embodiments, the computer device may include a memory and a processor. Among them, the memory stores a computer program that can run on the processor, and when the processor executes the program, the battery pack appearance defect detection method is implemented.

[0038] Figure 1 is a schematic structural diagram of the battery pack appearance defect detection device provided by the embodiments of the present application. Figure 1 The battery pack appearance defect detection device 10 shown may include at least one processor 110, a memory 150, at least one network interface 120, and a user interface 130. Each component in the battery pack appearance defect detection device 10 is coupled together through a bus system 140. It can be understood that the bus system 140 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 140 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clear description, in Figure 1 all kinds of buses are labeled as the bus system 140.

[0039] The processor 110 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0040] The user interface 130 includes one or more output devices 131 that enable the presentation of media content, and one or more input devices 132.

[0041] The memory 150 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, and the like. The memory 150 may optionally include one or more storage devices physically located away from the processor 110. The memory 150 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 150 described in the embodiments of the present application is intended to include any suitable type of memory. In some embodiments, the memory 150 is capable of storing data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as exemplified below.

[0042] Operating system 151, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks; A network communication module 152, used to reach other computing devices via one or more (wired or wireless) network interfaces 120, exemplary network interfaces 120 include: Bluetooth, Wireless LAN (WiFi), and Universal Serial Bus (USB); The input processing module 153 is used to detect one or more inputs or interactions from one of the one or more input devices 132.

[0043] In some embodiments, the device provided in the embodiments of the present application can be implemented in software. Figure 1 A battery pack appearance defect detection device 154 stored in the memory 150 is shown. The battery pack appearance defect detection device 154 can be a battery pack appearance defect detection device in a battery pack appearance defect detection device, which can be software in the form of a program and a plug-in, including the following software modules: a determination module 1541, an adjustment module 1542, a conversion module 1543 and a defect detection module 1544. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.

[0044] In other embodiments, the device provided in the embodiments of the present application can be implemented in hardware. As an example, the device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the battery pack appearance defect detection method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs) or other electronic components.

[0045] In the embodiment of the present application, the battery pack appearance defect detection method can be to perform surface defect detection on structures such as battery packs, battery modules, single cells or pole pieces. Therefore, the battery pack appearance defect detection device can be any one of a programmable logic controller (PLC), a single-chip microcomputer, a middle computer and a host computer at any appearance inspection station on the battery production line. The technical solution of the present application will be described in detail below in conjunction with the accompanying drawings.

[0046] Figure 2 This is an optional process diagram of the battery pack appearance defect detection method provided in the embodiment of the present application. Figure 1 ,like Figure 2 As shown, the battery pack appearance defect detection method provided in the embodiment of the present application can be implemented through steps S201 to S204: Step S201: determining an initial conversion matrix between two frames of point cloud data in adjacent acquisition sequences based on the acquisition sequence of multiple frames of point cloud data corresponding to the battery pack; wherein the acquisition viewing angles of each frame of point cloud data are different.

[0047] In an embodiment of the present application, when the battery pack arrives at the designated position after entering the station, the host computer can obtain the geometric structure information of the battery pack, plan the scanning path of the battery pack based on the scanning range of the scanner, and control the scanner to scan the battery pack based on the scanning path to obtain multiple frames of point cloud data. There may be overlapping areas between adjacent point cloud data.

[0048] Here, each frame of point cloud data may be a spatial data set of multiple points, each point containing three-dimensional coordinates and other additional information (such as color, intensity, etc.).

[0049] Here, the scanner can be a light detection and ranging (LiDAR) system, a depth camera, a laser radar, or a millimeter wave radar. There can be multiple acquisition points on the scanning path. When scanning based on the scanning path, the acquisition point is collected once to obtain multiple original signals. The original signal is converted into point cloud data. For example, the signal of the millimeter wave radar needs to be converted to a digital signal and filtered, and the depth image is converted into a three-dimensional point cloud through the internal parameter matrix. The LiDAR data may need to be processed by a triangulation algorithm to obtain a three-dimensional point cloud.

[0050] In an embodiment of the present application, the different collection perspectives of each frame of point cloud data can supplement local data through different angles, reduce blind spots, include more geometric features (such as edges, contours, planes, etc.), improve the stability and accuracy of alignment, and reconstruct a more comprehensive battery pack structure.

[0051] In an embodiment of the present application, the initial transformation matrix may be the geometric transformation parameters required to align the spatial position of the point cloud data Pj (current frame) to the coordinate system of the point cloud data Pi (previous frame) through rotation and translation transformation.

[0052] When stitching and registering multiple frames of point cloud data, the transformation and stitching is performed through the relative position and posture between adjacent frames, that is, the initial transformation matrix. In the embodiment of the present application, the nearest neighbor search can be used to match the feature point pairs of adjacent frame point cloud data, and the rotation matrix and translation vector between two adjacent point cloud data can be calculated by singular value decomposition (SVD, Singular Value Decomposition) and other methods, and the rotation matrix and translation vector are combined to obtain the initial transformation matrix.

[0053] Here, the initial transformation matrix can optimize the relative position between each pair of adjacent point clouds, and use the initial transformation matrix to perform registration between adjacent point clouds.

[0054] Step S202: Based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features, the initial transformation matrix is ​​adjusted to obtain the transformation matrix corresponding to each frame of point cloud data.

[0055] In an embodiment of the present application, the global structural features of each frame of point cloud data are used to describe the overall shape, size and spatial distribution characteristics of the point cloud frame, which can be obtained by performing global feature extraction on each point cloud data. For example, it can be extracted by a global pooling method, or it can be obtained by aggregating multi-level global information and expanding the receptive field layer by layer, expanding the neighborhood range of each layer, capturing a larger range of contextual relationships, and finally outputting global features.

[0056] Here, the point cloud quality of each point in each frame of point cloud data is used to evaluate the acquisition reliability of the point cloud data, including data integrity, noise level and density distribution, which can be determined by the point density and noise level of the point cloud.

[0057] The local geometric features of each point in each frame of point cloud data are used to describe the geometric characteristics of a specific area or point in the point cloud, which is used for detail matching and defect location, and can be obtained by extracting features from the neighborhood of each point.

[0058] In some embodiments, the initial transformation matrix is ​​adjusted based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features. This may refer to global optimization of multiple initial change matrices to obtain multiple optimization matrices, so that multiple local point clouds can be spliced ​​into a complete point cloud based on the optimization matrix, and then the initial transformation matrix is ​​weightedly calculated based on the point cloud quality of each point in each frame of point cloud data, so that high-quality point clouds (such as points with low noise and significant structural features) can be given a greater weight, and a weighted feature matrix is ​​obtained, so that key structural points can be more accurately matched in the transformation matrix alignment; in each alignment, local features and global features can be used to jointly constrain the transformation between point clouds to obtain a transformation matrix, thereby improving the alignment accuracy.

[0059] Here, global optimization can adopt a global optimization strategy based on particle swarm optimization (PSO) and genetic algorithm (GA) to improve the relative transformation between point clouds and avoid local optimality.

[0060] In an embodiment of the present application, the transformation matrix can be a set of multiple matrices, each frame of point cloud data corresponds to a matrix, and the transformation matrix can realize the rotation and translation of each frame of point cloud data to align all point cloud data into a coordinate system.

[0061] Step S203: convert the multi-frame point cloud data based on the conversion matrix to obtain a fused point cloud structure of the battery pack.

[0062] In some embodiments, after obtaining the transformation matrix, the coordinates of each frame of point cloud data can be multiplied by the corresponding transformation matrix, and finally the multiple frames of point cloud data are aligned into a coordinate system to obtain a fused point cloud structure of the battery pack. The fused point cloud structure presents the three-dimensional geometric features of the battery pack, including details such as surface concave-convex structure, electrode distribution, welds and surface defects.

[0063] Step S204: Based on the fused point cloud structure, perform defect detection on the battery pack to obtain a detection result.

[0064] In the embodiment of the present application, defect detection can be to detect surface dents, unevenness, cracks, assembly errors, etc. The fused point cloud structure can be used for battery pack status analysis, for example, by calculating the point cloud normal vector and curvature features, dent detection, shell deformation or weld defects can be achieved; the fused point cloud structure can be compared with the design model of the battery pack to determine whether there is an assembly error; the neural network can be used to identify whether there are cracks on the surface of the battery pack, thereby obtaining the battery pack detection result.

[0065] In an embodiment of the present application, multi-frame point cloud data collected from different viewing angles can supplement local data from different angles, reduce blind spots, and reconstruct a complete battery pack structure; the embodiment of the present application adjusts the initial transformation matrix through the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features. The transformation matrix can be adjusted based on point cloud data with high point cloud quality, which can reduce the influence of noise and make the conversion of point cloud data more reliable. The transformation matrix is ​​constrained in the alignment process through local and global features, so that the transformation matrix can improve the alignment accuracy while reducing the alignment deviation caused by local optimality, thereby obtaining a more accurate fused point cloud structure of the battery pack. Defect detection is performed based on the fused point cloud structure, which can improve the accuracy and efficiency of battery pack surface defect detection, reduce the false detection rate of manual and two-dimensional image detection, and provide reliable quality assurance for new energy battery manufacturing.

[0066] In order to deal with the scale differences of surface defects of battery packs (Packs) (such as small dents and large-area deformations) and capture geometric information of different scales, the embodiment of the present application can extract multi-scale features of point cloud data through neighborhood radii of different sizes. Therefore, the battery pack appearance defect detection method provided by the embodiment of the present application can also include steps S1 and S2: Step S1, extracting multi-scale features of each point in each frame of point cloud data to obtain multi-scale features of each point in each frame of point cloud data.

[0067] In some embodiments, step S1 may be implemented by steps S11 and S12: Step S11, respectively extracting features of a plurality of neighborhoods with different radii corresponding to each point in each frame of point cloud data to obtain a plurality of neighborhood features of each point.

[0068] In the embodiment of the present application, for each point in the point cloud data , you can build multiple neighborhoods with different radii , , each neighborhood corresponds to a different scale, and feature extraction is performed on the points in each neighborhood. The features of the points in the field are extracted to obtain the neighborhood features corresponding to the neighborhood, and finally multiple neighborhood features of each point are obtained.

[0069] In some embodiments, a small radius neighborhood can detect micron-level scratches or protrusions, and a large radius neighborhood can identify defects such as overall flatness and overall deformation of the battery.

[0070] Step S12: splicing multiple neighborhood features of each point to obtain multi-scale features of each point in each frame of point cloud data.

[0071] In some embodiments, multiple neighborhood features of each point are concatenated to obtain a multi-scale feature of each point. , as shown in formula (1): (1); in, Indicate point Local features at the kth scale.

[0072] The embodiment of the present application uses multi-scale feature extraction to achieve small-radius neighborhood to capture local details and large-radius neighborhood to cover a wider area, and can flexibly handle feature extraction of sparse and dense areas. The combination of the two can simultaneously detect local looseness and overall deformation of the battery pack surface, avoid missed detection caused by a single scale, and improve the accuracy of battery pack appearance inspection.

[0073] Step S2: fuse the multi-scale features of each point in each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, and the global structural features of each frame of point cloud data to obtain the fused features of each point in each frame of point cloud data.

[0074] In the embodiment of the present application, the local geometric features of each point in each frame of point cloud data are: , the global structural characteristics of each frame point cloud data are , the multi-scale features of each point in each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, and the global structural features of each frame of point cloud data can be fused through the Fusion function, as shown in formula (2): (2); in, Represents the fusion feature corresponding to the i-th point in the point cloud.

[0075] Correspondingly, step S201 can be implemented by steps S2011 and S2022: Step S2011: Obtain a preset transformation matrix between two frames of point cloud data in an adjacent acquisition sequence.

[0076] In an embodiment of the present application, since the shape and parameters of the battery pack are known, the approximate relative rotation and translation between two frames of point cloud data in adjacent acquisition sequences are known, so that these values ​​can be used as a preset transformation matrix; or a voxel grid-based downsampling method can be used to quickly align two frames of point cloud data in adjacent acquisition sequences to obtain a preset transformation matrix.

[0077] Step S2012, based on the preset transformation matrix, the fusion features of each point in each frame of point cloud data and the initial position of each point in each frame of point cloud data in the initial coordinate system of each frame of point cloud data, determine the initial transformation matrix between two frames of point cloud data in adjacent acquisition order.

[0078] In some embodiments, two adjacent point cloud data may be and The relative transformation between them is matched to obtain the initial transformation matrix , and the fusion features corresponding to the two point clouds are used to adjust the change matrix, so that the feature information of the point cloud surface can be better used to achieve point cloud matching, as shown in formulas (3) and (4): (3); exp (4); in, and Point Cloud and The fusion feature of the kth point in Point Cloud and The initial positions of the kth point in the initial coordinate systems of point clouds Pi and Pj is a preset transformation matrix, and σ is a parameter that controls the speed of weight decay, which can be set based on prior experience.

[0079] In the embodiment of the present application, by adjusting the change matrix through the fusion features corresponding to the two point clouds, the feature information of the point cloud surface can be better utilized to achieve point cloud matching and improve the accuracy of point cloud registration.

[0080] Figure 3 This is an optional process diagram of the battery pack appearance defect detection method provided in the embodiment of the present application. Figure 2 ,like Figure 3 As shown, step S202 in the battery pack appearance defect detection method provided in the embodiment of the present application can be implemented by steps S301 to S304: Step S301: construct a global optimization function based on two frames of point cloud data in adjacent acquisition order and the corresponding initial transformation matrix.

[0081] In the embodiment of the present application, on the basis of step-by-step registration, any feasible global optimization strategy (such as global least squares and matrix decomposition, deep learning or exchange average algorithm, etc.) can be adopted to further improve the relative transformation between point clouds and avoid local optimality. The constructed global optimization function S is shown in formula (5): (5); Step S302: Determine the initial transformation matrix when the global optimization function satisfies the first target condition as the optimization matrix.

[0082] In some embodiments, the first target condition may be an initial transformation matrix that enables the global optimization function S to obtain a minimum value. The optimization matrix may be obtained by formula (6): (6); Formula (6) represents the global transformation optimization between multiple point clouds, ensuring that the registration result of each pair of point clouds can meet the global optimal solution.

[0083] In some embodiments, the optimization matrix may be a set of multiple matrices, and each point cloud data corresponds to a matrix.

[0084] Step S303: Based on the point cloud quality of each point in each frame of point cloud data, weighted calculation is performed on the optimization matrix to obtain a weighted transformation matrix between two frames of point cloud data in adjacent acquisition order.

[0085] In the embodiments of the present application, is the point cloud quality of the kth point in the point cloud data Pi. The point cloud quality can be determined based on the point density and noise level of the point cloud. Point density can refer to the number of points per unit volume, measured by the average distance of points in the neighborhood of the kth point; noise level can refer to the degree to which a point deviates from the true surface, measured by calculating the change in the normal vector of the local plane through local features. Low-density or high-noise areas can be considered low-quality areas.

[0086] In the process of stitching multiple point clouds, different point clouds may have different qualities, such as point cloud density, noise level, etc. Therefore, the embodiment of the present application introduces a dynamic weighting mechanism to adjust the optimization matrix according to the quality of the point cloud. Based on the quality of different points in the point cloud data, the contribution weight of each point in calculating the matrix can be determined to adjust the optimization matrix. For example, high-quality areas (high density, low noise, complete features) are given higher weights during the registration process, and low-quality areas are given lower weights to reduce their negative impact on the overall registration results. The adjustment of weights can be achieved through key point optimization or sparse Mixed-ICP algorithm.

[0087] The weighted transformation matrix after weighting can be calculated by formula (7): (7); Step S304: Based on the global structural features of each frame of point cloud data and the local geometric features of each point in each frame of point cloud data, the weighted transformation matrix is ​​adjusted to obtain a transformation matrix corresponding to each frame of point cloud data.

[0088] In some embodiments, in the step-by-step registration process, in order to more accurately stitch point clouds, the present application can improve the robustness and accuracy of the registration process by combining local geometric features and global structural features. For example, in each registration, the local geometric features and global structural features can be used to jointly constrain the transformation between point clouds, and the weighted transformation matrix can be adjusted to obtain the transformation matrix corresponding to each frame of point cloud data.

[0089] Therefore, step S304 can be implemented by steps S3041 and S3042: Step S3031, construct a target optimization function based on the global structural features of each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, the weighted transformation matrix between two frames of point cloud data in adjacent acquisition order, the local weight coefficient and the global weight coefficient.

[0090] In some embodiments, the target optimization function X may be as shown in formula (8): (8); in, and is the weight coefficient of local features and global features, which can be set based on experience. Point Cloud A collection of local geometric features, It is a point cloud global structural features.

[0091] Step S3032: determine the weighted transformation matrix when the target optimization function satisfies the second target condition as the conversion matrix.

[0092] In some embodiments, the target optimization function satisfies the second target condition, which may mean, as shown in formula (9), determining the weighted transformation matrix that minimizes the target optimization function X as the transformation matrix of the point cloud data Pi.

[0093] (9); Here, the transformation matrix is ​​a matrix set, and each point cloud data corresponds to a transformation matrix. After each point cloud data is transformed by Tcombined, the aligned point clouds are directly added to obtain a complete point cloud.

[0094] In an embodiment of the present application, two frames of point cloud data in an adjacent acquisition order and the corresponding initial transformation matrix are globally optimized so that multiple local point clouds can be spliced ​​into a complete point cloud, providing high-precision input data for battery pack defect detection; the optimization matrix is ​​adjusted by the point cloud quality of each point in each frame of point cloud data, which can suppress the interference of noise areas and avoid the registration from falling into local optimality, making the registration more dependent on reliable areas and improving the registration accuracy; finally, the point cloud transformation is comprehensively constrained by combining local geometric features and global structural features, so that the registration result can reflect local details while maintaining overall consistency.

[0095] In some embodiments, step S203 may be implemented by steps S2031 and S2032: Step S2031: based on the transformation matrix corresponding to each frame of point cloud data, transform each frame of point cloud data into a global coordinate system to obtain multiple frames of transformed point cloud data.

[0096] In an embodiment of the present application, the transformation matrix contains rotation and translation information. For each frame of point cloud data, its corresponding transformation matrix is ​​used to transform it from the original coordinate system to the global coordinate system. This can be achieved through matrix multiplication, where the coordinates of each point in the point cloud are multiplied by the transformation matrix.

[0097] Step S2032: splice multiple frames of converted point cloud data to obtain a fused point cloud structure.

[0098] In an embodiment of the present application, after multiple frames of point cloud data are converted to the global coordinate system, the point sets of all point cloud data can be merged into a large point set through point cloud stitching or merging operations, thereby obtaining a fused point cloud structure of the battery pack to achieve visualization of the battery pack.

[0099] Here, duplicate points and noise points can be removed during stitching to improve the quality of the fused point cloud structure.

[0100] In an embodiment of the present application, by converting each frame of point cloud data into a global coordinate system and stitching them together, these local point cloud data can be integrated into a complete three-dimensional model, thereby being able to more comprehensively and accurately reflect the geometric structure of the battery pack, providing accurate input data for defect detection of the battery pack, and improving the accuracy of defect detection.

[0101] Figure 4 This is an optional process diagram of the battery pack appearance defect detection method provided in the embodiment of the present application. Figure 3 ,like Figure 4 As shown, the battery pack appearance defect detection method provided in the embodiment of the present application may also include steps S401 to S404: Step S401 : Based on the neighborhood of each point in each frame of point cloud data, local features are extracted for each point in each frame of point cloud data to obtain local geometric features of each point in each frame of point cloud data.

[0102] In the embodiment of the present application, local feature extraction may refer to the process of extracting features of each point by using a local perception mechanism (such as k-nearest neighbor search) to extract features of points in the neighborhood of each point through a convolution operation, thereby forming local geometric features of each point in each frame of point cloud data. The local feature vector It can be expressed by formula (10): (10); in, The first Points, is the neighborhood of the point, Represents a local convolution operation.

[0103] Step S402: extract features at different levels from each frame of point cloud data to obtain global structural features of each frame of point cloud data.

[0104] In an embodiment of the present application, performing feature extraction at different levels on each frame of point cloud data may refer to performing feature extraction at different levels through multi-layer convolution operations to obtain global structural features of each frame of point cloud data.

[0105] In some embodiments, step S402 may be implemented by steps S4021 and S4022: Step S4021: perform multiple local feature extractions at different levels on each frame of point cloud data to obtain multiple local features corresponding to each frame of point cloud data.

[0106] Here, we can use convolution kernels of different sizes to extract local features of each frame of point cloud data at different levels. The first layer uses a small convolution kernel (such as 3×3) to extract fine features, and the second layer uses a slightly larger convolution kernel (such as 5×5) to extract more extensive features, so as to obtain multiple local features corresponding to each frame of point cloud data. .

[0107] Step S4022: Perform global convolution on multiple local features corresponding to each frame of point cloud data to obtain global structural features corresponding to each frame of point cloud data.

[0108] In an embodiment of the present application, local features can be aggregated through feature aggregation, fully connected layers or global convolution to obtain global structural features, so as to aggregate context information layer by layer. For example, local features at different levels can be aggregated using skip connections to obtain global structural features; global convolution can also be used to convert multiple local features into global structural features.

[0109] In some embodiments, the global structural features As shown in formula (11): (11); in, is the local feature of the kth point, Represents the global convolution operation, which outputs the global structural features corresponding to each point cloud data.

[0110] Step S403: determining the point density of each point in each frame of point cloud data based on the average distance between each point in the neighborhood corresponding to each point in each frame of point cloud data.

[0111] In the embodiment of the present application, the point density can be calculated by calculating the kth point in the point cloud data Pi It is measured by the average distance between each point in the neighborhood of and the kth point, as shown in formula (12): (12); Among them, Daverage is the average distance between each point in the neighborhood corresponding to the kth point and the kth point, and e is a small constant used to avoid division by zero errors.

[0112] Step S404: determining the point cloud quality of each point in each frame of point cloud data based on the local geometric features and point density of each point in each frame of point cloud data.

[0113] In the embodiment of the present application, the noise level of each point can be obtained through local geometric features.

[0114] In some embodiments, step S404 may be implemented by steps S4041 and S4043: Step S4041: Based on the local geometric features of each point in each frame of point cloud data, determine the covariance matrix of the neighborhood corresponding to each point and the covariance eigenvalue of each point.

[0115] In the embodiment of the present application, the covariance matrix can reflect the overall distribution of the data, and the degree of concentration or dispersion of the data can be determined by the covariance eigenvalue. After the local geometric features of each point in each frame of point cloud data have been determined, the covariance matrix of the neighborhood of each point can be determined based on the local geometric features. For example, the centroid of all points in the neighborhood of each point is calculated based on the local geometric features, and the coordinates of the points in the neighborhood are centered relative to the centroid, and the covariance matrix is ​​calculated using the centered coordinates.

[0116] Perform eigendecomposition on the covariance matrix to obtain the covariance eigenvalues .

[0117] Step S4042: Determine the noise of each point in each frame of point cloud data based on the covariance eigenvalue.

[0118] In the embodiment of the present application, the noise of each point in each frame of point cloud data can be determined by the covariance eigenvalue by formula (13): (13); in, are the eigenvalues ​​of the covariance matrix, is the minimum eigenvalue, reflecting the noise level. Here, when the point cloud data is locally a perfect plane, Approaching 0, the noise level approaches 0, which is in line with expectations.

[0119] Step S4043: perform weighted calculation on the noise and point density of each point in each frame of point cloud data to obtain the point cloud quality of each point in each frame of point cloud data.

[0120] In the embodiment of the present application, the point cloud quality of each point can be achieved by formula (14): (14); in, Point Cloud The point density of the kth point in , Point Cloud The noise of the kth point, , It can be an empirical parameter.

[0121] The embodiment of the present application can capture detailed information (such as dents and cracks) on the surface of the battery pack through local feature extraction, and capture the overall shape of the battery pack through global feature extraction, and obtain the point cloud quality of each point, ensuring that stable and reliable features can still be extracted in complex scenarios.

[0122] The following is an explanation of an exemplary application of the embodiments of the present application in a practical application scenario.

[0123] In view of the large amount of point cloud data, large pack area, and many variations in defect size in battery pack surface inspection scenarios, there is a need to stitch multiple large-scale point clouds. An embodiment of the present application proposes a multi-scale point cloud stitching method based on global registration optimization (GROMS, Global Registration of Multiple Scales), which solves the problem of effective registration and stitching of multiple limited-range point clouds through deep learning-enhanced multi-scale feature extraction and global convergence optimization methods.

[0124] In the Pack inspection scenario, there may be defects such as dents and cracks on the surface of the battery pack, and traditional inspection methods have difficulty dealing with noise, occlusion, and local optimality problems in point cloud data. In order to meet the needs of high-precision, high-efficiency point cloud registration and defect detection in Pack inspection tasks, this application achieves efficient and robust point cloud registration and defect detection of packs through multi-level feature extraction, step-by-step registration and global optimization, dynamic weighting and adaptive adjustment, and local and global information combination.

[0125] Among them, multi-level feature extraction can refer to the noise and occlusion problems in the point cloud scanning of the Pack surface. Local feature extraction (which can be through k-nearest neighbor search and local convolution) is performed through a new multi-scale hierarchical feature extraction network (MS-HFEN) to capture the detailed information on the battery pack surface (such as dents and cracks). At the same time, global feature extraction (aggregating context information layer by layer) is used to capture the overall shape of the battery pack to ensure that robust features can still be extracted in complex scenarios.

[0126] Gradual registration and global optimization can refer to the situation in which, in the Pack inspection task, a single scan can only obtain a local point cloud due to the limited viewing angle of the scanner. This application generates an initial transformation matrix through gradual registration, and combines particle swarm optimization (PSO) and genetic algorithm (GA) for global optimization to ensure that multiple local point clouds can be spliced ​​into a complete point cloud, providing high-precision input data for subsequent defect detection.

[0127] Dynamic weighting and adaptive adjustment can refer to the problem of uneven quality of point cloud on the Pack surface (such as low point cloud density or high noise in some areas), introducing a point cloud quality scoring mechanism, and dynamically adjusting the registration weights, thereby improving the stability and accuracy of the detection results.

[0128] The combination of local and global information can mean that in Pack inspection, both local defects (such as dents) and overall morphology (such as the flatness of the battery pack surface) need to be inspected. This application combines local geometric information and global structural information to comprehensively constrain point cloud transformation to ensure that the registration result can reflect local details while maintaining overall consistency.

[0129] Figure 5 is an optional flow chart of the battery pack detection process provided in the embodiment of the present application, such as Figure 5 As shown, the battery pack detection process provided in the embodiment of the present application can be implemented through steps S501 to S504: Step S501: The battery pack enters a designated position of a testing station.

[0130] In the embodiment of the present application, sensors such as lasers or infrared rays are provided at the entrance of the detection station to detect whether the battery pack enters the station. When the pack to be detected enters the detection area of the detection station, the host computer can control the ranging sensor or the metal detection sensor to detect the approximate position of the battery pack, so as to detect whether the battery pack reaches the designated position for detection.

[0131] Step S502: Collect data from the battery pack to obtain multiple frames of point cloud data.

[0132] In the embodiment of the present application, the host computer controls a movable mechanism (such as a robotic arm) to clamp or manually hold a scanner (such as a lidar, a depth camera, etc.) to scan the battery pack comprehensively, and obtains multiple local point clouds. Each point in the local point cloud contains three-dimensional coordinates and other additional information (such as color, intensity, etc.).

[0133] Step S503: Perform registration and stitching processing on the multiple frames of point cloud data to obtain a complete point cloud.

[0134] Use the multi-scale point cloud stitching method (GROMS) of the embodiment of the present application to stitch multiple local point clouds into a complete point cloud.

[0135] Step S504: Perform defect detection on the battery pack based on the complete point cloud.

[0136] The embodiment of the present application can use a defect detection algorithm at the point cloud level (for example, by calculating the local curvature and normal direction change of the point cloud to identify surface anomalies (such as dents, protrusions, cracks)) based on the complete point cloud data to identify defects (such as dents, cracks, etc.) on the surface of the battery pack.

[0137] The embodiment of the present application solves common problems such as noise, occlusion, and local optimality in point cloud registration through feature extraction, step-by-step optimization, dynamic weighting, and information fusion, and also provides an efficient and reliable solution for Pack detection, which can improve the registration accuracy.

[0138] In the embodiment of the present application, Figure 6 is an optional process schematic diagram of point cloud stitching provided by the embodiment of the present application. As Figure 6 shown, the battery pack detection process provided by the embodiment of the present application can be implemented through steps S601 to S607: Step S601: Obtain multiple frames of point cloud data.

[0139] In the embodiment of the present application, the scanner moves to a position to collect a frame of point cloud data. After the entire battery pack is collected, multiple frames of point cloud data are obtained.

[0140] Step S602: Perform multi-level feature extraction on multi-frame point cloud data to obtain local features, multi-scale features, global features and fusion features.

[0141] In the point cloud registration problem, dealing with noise, occlusion, scale differences and other issues usually requires extracting features from different scales (or levels). In the Pack inspection task, there may be defects such as dents and cracks on the surface of the battery pack, and traditional methods find it difficult to extract effective features from point clouds with severe noise and occlusion. In order to effectively capture the global and local structural information of the point cloud, this application provides a multi-scale hierarchical feature extraction network (MS-HFEN, Multi-Scale Hierarchical Feature Extraction Network), including the extraction of local features (i.e., local geometric features), multi-scale features, global features (i.e., global structural features) and fusion features.

[0142] Among them, local feature extraction can refer to the use of local perception mechanism (such as k nearest neighbor search) in the feature extraction process of each layer, extracting the local geometric features of each point through convolution operation, and forming the local feature vector (i.e. local geometric features) of each point in each frame of point cloud data. , local eigenvector It can be expressed by formula (15): (15); in, The first Points, is the neighborhood of the point, Represents a local convolution operation.

[0143] Multi-scale feature extraction can refer to designing a multi-scale feature extraction module to deal with the scale differences of the Pack surface point cloud (such as small dents and large area deformation) and capture geometric information of different scales. Multi-scale features are extracted through neighborhood radii of different sizes: for each point , construct multiple neighborhoods with different radii , , corresponding to different scales. For each scale neighborhood, use the local feature extraction module to extract features, and splice the multi-scale features to obtain the multi-scale features of each point , as shown in formula (16): (16); in, Indicate point Local features at the kth scale.

[0144] Global feature extraction can refer to aggregating multi-level global information, increasing the receptive field layer by layer, so that the features of each layer can incorporate more point cloud context information. Finally, the global features are output , to represent the overall shape information of the point cloud, the global features (i.e., global structural features) , as shown in formula (17): (17); wherein, is the local feature of the k-th layer, represents the global convolution operation, and outputs the global features corresponding to each local point cloud finally.

[0145] Feature fusion can be achieved by fusing local and global features to obtain a comprehensive feature vector , which contains both local detailed information and global morphological information, as shown in formula (18): (18); wherein, represents the fused feature corresponding to the i-th point in the point cloud.

[0146] Step S603, perform progressive registration on the multi-frame point cloud data based on the fused features to obtain the initial transformation matrix between two point cloud data in adjacent acquisition orders.

[0147] In some embodiments, progressive registration means aligning the multi-frame point cloud data to the same coordinate system. First, by performing a preliminary matching on the relative transformation between and (two adjacent point cloud data) to obtain the initial transformation matrix (i.e., the initial transformation matrix) , and at the same time adjusting the transformation matrix using the features corresponding to the two point clouds, so as to better utilize the feature information of the surface pack point cloud to achieve point cloud matching. Then, gradually optimize the relative positions between each pair of point clouds and perform registration using the initial transformation matrix. As shown in formulas (19) and (20): (19); exp (20); wherein, and are the fused features of the positions of the k-th points in the point clouds and respectively, are the positions of the k-th points in the point clouds and respectively is the initial matrix between the manually entered point clouds, and σ is a parameter that controls the speed of weight decay.

[0148] Step S604: globally optimize the initial transformation matrix to obtain a globally optimized matrix.

[0149] On the basis of step-by-step registration, a global optimization strategy based on particle swarm optimization (PSO) and genetic algorithm (GA) can be used to further improve the relative transformation between point clouds and avoid local optimality. The optimization objective is shown in formula (21): (twenty one); This formula represents the global transformation optimization between multiple point clouds, ensuring that the registration result of each pair of point clouds can meet the global optimal solution.

[0150] Step S605: dynamically weight the global optimization matrix to obtain a weighted transformation matrix.

[0151] In some embodiments, during the process of stitching multiple point clouds, different point clouds may have different qualities, such as point cloud density, noise level, etc. Therefore, the present invention introduces a dynamic weighting mechanism to adjust the transformation matrix according to the point cloud quality.

[0152] The quality function of the point cloud is set to , then the weighted transformation matrix It can be expressed as formula (22): (twenty two); in, is the quality scoring function of the kth point cloud point, which is usually determined according to the point density and noise level of the point cloud. It can be expressed as formula (23): (twenty three); in, Point Cloud The point density of the kth point, Point Cloud The noise at the kth point, , It can be an empirical parameter.

[0153] Among them, the point density can be calculated by calculating the kth point in the point cloud Pi It is measured by the average distance between each point and the kth point in the local neighborhood of , as shown in formula (24): (twenty four); Where Daverage is the average distance of the kth point, and e is a small constant used to avoid division by zero errors.

[0154] The noise level can be analyzed by local geometric features, and the normal vector change of the local plane at the kth point is calculated using principal component analysis, as shown in formula (25): (25); in, are the eigenvalues ​​of the covariance matrix, is the minimum eigenvalue, reflecting the noise level. When the point cloud is locally a perfect plane, Approaching 0, the noise level approaches 0, which is in line with expectations.

[0155] Step S606: Adjust the weighted transformation matrix based on the local features and the global features to obtain the transformation matrix of each frame of point cloud data.

[0156] Step S607: based on the transformation matrix of each frame of point cloud data, stitching the frame of point cloud data is performed to obtain a complete point cloud.

[0157] In order to more accurately stitch point clouds during the step-by-step registration process, the embodiment of the present application combines local geometric information and global structural information to improve the robustness and accuracy of the registration process. In each registration, local features and global features can be used to jointly constrain the transformation between point clouds, thereby improving the registration accuracy. This process can be expressed as formula (26) by optimizing the objective function: (26); in, and is the weight coefficient of local features and global features (can be set manually), Point Cloud A collection of local features, It is a point cloud global features.

[0158] Here, Tcombined can be a matrix set, and each point cloud data corresponds to a transformation matrix. After each point cloud data is transformed by Tcombined, the aligned point clouds are directly added to obtain a complete point cloud.

[0159] Figure 7 is an optional structural diagram of point cloud stitching provided in an embodiment of the present application, such as Figure 7 As shown, 701 is the point cloud Point cloud data, 702 is point cloud Point cloud data, 703 is point cloud With point cloud Point cloud structure after registration.

[0160] To ensure the effectiveness of the multi-scale feature extraction network (MS-HFEN) and the point cloud registration algorithm, the multi-scale feature extraction network and the point cloud registration algorithm can be trained, and the training process is as follows: First, publicly available point cloud datasets (such as ModelNet40, KITTI dataset) or custom datasets can be used as training data. The dataset contains multiple point cloud samples and their corresponding ground truth transformation matrices.

[0161] To train the multi-scale hierarchical feature extraction network (MS-HFEN) and the registration algorithm, a loss function can be designed as shown in Equation (27): =λ1 +λ2 (27); where is the feature extraction loss; is the registration loss.

[0162] The contrastive loss can be used to train the feature extraction network. The goal of the contrastive loss is to make the feature vectors of similar point clouds close in the feature space, while the feature vectors of dissimilar point clouds are far apart. The feature extraction loss can be as shown in Equation (28): (28); where are the feature vectors of the point clouds respectively. is the Euclidean distance between the feature vectors. is the label, when if they are similar point clouds otherwise . is the margin parameter, which is used to control the minimum distance between dissimilar point clouds.

[0163] To optimize the accuracy of point cloud registration, the mean square error (MSE) of point cloud registration can be used as the loss function to measure the error between the predicted transformation matrix and the ground truth transformation matrix. The registration loss can be as shown in Equation (29): (29); where is the predicted transformation matrix. , are the positions of the k-th point in the point clouds respectively. N is the number of points in the point cloud.

[0164] During training, the convolutional layer parameters of the multi-scale feature extraction network (MS-HFEN) are initialized, the Adam optimizer is used for training, and the initial learning rate and learning rate decay strategy are set. The sample point cloud data is input into the multi-scale hierarchical feature extraction network (MS-HFEN) to extract local features and global features. Based on the extracted features, the transformation matrix is ​​calculated. The loss function is used Calculate the error and update the network parameters through back propagation. Repeat the above process until the loss function converges or reaches the predetermined number of training rounds.

[0165] The embodiments of the present application significantly improve the accuracy of stitching multiple point clouds, especially in complex environments, by combining multi-level feature extraction with global optimization; the multi-scale features extracted by deep learning are used to enhance the anti-noise and occlusion capabilities of the present application when facing noise and occlusion, and have stronger robustness; 3) through dynamic weighting and step-by-step alignment strategies, the computational redundancy is reduced, the efficiency of the stitching process is improved, and large-scale point cloud data can be better handled; it can handle the stitching of large-scale and multiple point clouds to meet the needs of large-scale three-dimensional modeling and environmental reconstruction.

[0166] based on Figure 1 A battery pack appearance defect detection device 154 is provided, and the battery pack appearance defect detection device 154 may include a determination module 1541, an adjustment module 1542, a conversion module 1543 and a defect detection module 1544, wherein the determination module 1541 is used to determine the initial transformation matrix between two frames of point cloud data in adjacent acquisition sequences based on the acquisition sequence of multiple frames of point cloud data corresponding to the battery pack; wherein the acquisition perspectives of each frame of point cloud data are different; the adjustment module 1542 is used to adjust the initial transformation matrix based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features, to obtain the transformation matrix corresponding to each frame of point cloud data; the conversion module 1543 is used to convert multiple frames of point cloud data based on the transformation matrix to obtain a fused point cloud structure of the battery pack; the defect detection module 1544 is used to perform defect detection on the battery pack based on the fused point cloud structure to obtain a detection result.

[0167] In some embodiments, the battery pack appearance defect detection device also includes: a multi-scale feature extraction module, which is used to extract multi-scale features of each point in each frame of point cloud data to obtain multi-scale features of each point in each frame of point cloud data; a fusion module, which is used to fuse the multi-scale features of each point in each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, and the global structural features of each frame of point cloud data to obtain the fusion features of each point in each frame of point cloud data; the determination module 1541 is also used to obtain a preset transformation matrix between two frames of point cloud data in adjacent acquisition sequences; based on the preset transformation matrix, the fusion features of each point in each frame of point cloud data, and the initial position of each point in each frame of point cloud data in the initial coordinate system of each frame of point cloud data, determine the initial transformation matrix between two frames of point cloud data in adjacent acquisition sequences.

[0168] In some embodiments, the multi-scale feature extraction module is also used to extract features from multiple neighborhoods with different radii corresponding to each point in each frame of point cloud data to obtain multiple neighborhood features of each point; and to splice the multiple neighborhood features of each point to obtain multi-scale features of each point in each frame of point cloud data.

[0169] In some embodiments, the adjustment module 1542 is also used to construct a global optimization function based on two frames of point cloud data in adjacent acquisition order and the corresponding initial transformation matrix; determine the initial transformation matrix when the global optimization function satisfies the first target condition as the optimization matrix; based on the point cloud quality of each point in each frame of point cloud data, perform weighted calculation on the optimization matrix to obtain a weighted transformation matrix between two frames of point cloud data in adjacent acquisition order; based on the global structural features of each frame of point cloud data and the local geometric features of each point in each frame of point cloud data, adjust the weighted transformation matrix to obtain the transformation matrix corresponding to each frame of point cloud data.

[0170] In some embodiments, the adjustment module 1542 is also used to construct a target optimization function based on the global structural features of each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, the weighted transformation matrix between two frames of point cloud data in adjacent acquisition order, the local weight coefficient and the global weight coefficient; and the weighted transformation matrix when the target optimization function meets the second target condition is determined as the conversion matrix.

[0171] In some embodiments, the conversion module 1543 is also used to convert each frame of point cloud data to a global coordinate system based on the transformation matrix corresponding to each frame of point cloud data to obtain multiple frames of converted point cloud data; and to splice the multiple frames of converted point cloud data to obtain a fused point cloud structure.

[0172] In some embodiments, the battery pack appearance defect detection device also includes: a local feature extraction module, which is used to perform local feature extraction on each point in each frame of point cloud data based on the neighborhood of each point in each frame of point cloud data, so as to obtain the local geometric features of each point in each frame of point cloud data; a feature extraction module, which is used to perform feature extraction at different levels on each frame of point cloud data, so as to obtain the global structural features of each frame of point cloud data; a first determination module, which is used to determine the point density of each point in each frame of point cloud data based on the average distance between each point in the corresponding neighborhood of each point in each frame of point cloud data; and a second determination module, which is used to determine the point cloud quality of each point in each frame of point cloud data based on the local geometric features and point density of each point in each frame of point cloud data.

[0173] In some embodiments, the feature extraction module is also used to perform multiple local feature extractions at different levels on each frame of point cloud data to obtain multiple local features corresponding to each frame of point cloud data; and perform global convolution on the multiple local features corresponding to each frame of point cloud data to obtain global structural features corresponding to each frame of point cloud data.

[0174] In some embodiments, the second determination module is also used to determine the covariance matrix of the neighborhood corresponding to each point and the covariance eigenvalue of each point based on the local geometric features of each point in each frame of point cloud data; determine the noise of each point in each frame of point cloud data based on the covariance eigenvalue; perform weighted calculation on the noise and point density of each point in each frame of point cloud data to obtain the point cloud quality of each point in each frame of point cloud data.

[0175] It should be noted that the description of the device of the embodiment of the present application is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment, so it is not repeated. For technical details not disclosed in the embodiment of the device, please refer to the description of the method embodiment of the present application for understanding.

[0176] The embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented. The computer-readable storage medium can be transient or non-transient.

[0177] An embodiment of the present application provides a computer program, including a computer-readable code. When the computer-readable code is run in a computer device, a processor in the computer device executes some or all of the steps for implementing the above method.

[0178] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented in hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0179] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.

[0180] The present application uses descriptions such as "upper", "lower", "top", "bottom", "front", "back", "inside" and "outside" to indicate directions or positional relationships. This is only for the convenience of describing the present application, and does not indicate or imply that the device referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, it should not be understood as limiting the scope of protection of the present application.

[0181] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to the specific circumstances.

[0182] It should be noted that, in this application, the terms "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0183] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0184] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the embodiments of the present application may be all integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0185] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for detecting appearance defects of a battery pack, characterized in that: The battery pack appearance defect detection method comprises: Based on the acquisition sequence of multiple frames of point cloud data corresponding to the battery pack, an initial conversion matrix between two frames of point cloud data in adjacent acquisition sequences is determined; wherein the acquisition perspectives of each frame of point cloud data are different; Based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features, the initial transformation matrix is ​​adjusted to obtain the transformation matrix corresponding to each frame of point cloud data; Convert the multi-frame point cloud data based on the conversion matrix to obtain a fused point cloud structure of the battery pack; Based on the fused point cloud structure, defect detection is performed on the battery pack to obtain a detection result.

2. The method for detecting appearance defects of a battery pack according to claim 1, characterized in that: The battery pack appearance defect detection method further includes: Perform multi-scale feature extraction on each point in each frame of point cloud data to obtain multi-scale features of each point in each frame of point cloud data; The multi-scale features of each point in each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, and the global structural features of each frame of point cloud data are fused to obtain the fusion features of each point in each frame of point cloud data; The method of determining an initial conversion matrix between two frames of point cloud data in adjacent acquisition order based on the acquisition order of multiple frames of point cloud data corresponding to the battery pack includes: Obtain a preset transformation matrix between two frames of point cloud data in adjacent acquisition order; Based on the preset transformation matrix, the fusion features of each point in each frame of point cloud data and the initial position of each point in each frame of point cloud data in the initial coordinate system of each frame of point cloud data, the initial transformation matrix between two frames of point cloud data in adjacent acquisition order is determined.

3. The method for detecting appearance defects of a battery pack according to claim 2, characterized in that: The multi-scale feature extraction of each point in each frame of point cloud data to obtain the multi-scale features of each point in each frame of point cloud data includes: Feature extraction is performed on multiple neighborhoods with different radii corresponding to each point in each frame of point cloud data to obtain multiple neighborhood features of each point; Multiple neighborhood features of each point are spliced ​​to obtain multi-scale features of each point in each frame of point cloud data.

4. The method for detecting appearance defects of a battery pack according to claim 2, characterized in that: The initial transformation matrix is ​​adjusted based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features to obtain the transformation matrix corresponding to each frame of point cloud data, including: Based on two frames of point cloud data acquired in adjacent order and the corresponding initial transformation matrix, a global optimization function is constructed; Determine the initial transformation matrix when the global optimization function satisfies the first objective condition as the optimization matrix; Based on the point cloud quality of each point in each frame of point cloud data, weighted calculation is performed on the optimization matrix to obtain a weighted transformation matrix between two frames of point cloud data in adjacent acquisition order; Based on the global structural features of each frame of point cloud data and the local geometric features of each point in each frame of point cloud data, the weighted transformation matrix is ​​adjusted to obtain a transformation matrix corresponding to each frame of point cloud data.

5. The method for detecting appearance defects of a battery pack according to claim 4, characterized in that: The weighted transformation matrix is ​​adjusted based on the global structural features of each frame of point cloud data and the local geometric features of each point in each frame of point cloud data to obtain a transformation matrix corresponding to each frame of point cloud data, including: Constructing a target optimization function based on the global structural features of each frame of point cloud data, the local geometric features of each point in each frame of point cloud data, the weighted transformation matrix between two frames of point cloud data in adjacent acquisition order, the local weight coefficient and the global weight coefficient; The weighted transformation matrix when the objective optimization function satisfies the second objective condition is determined as the conversion matrix.

6. The method for detecting appearance defects of a battery pack according to any one of claims 1 to 5, characterized in that: The converting the multi-frame point cloud data based on the conversion matrix to obtain a fused point cloud structure of the battery pack includes: Based on the transformation matrix corresponding to each frame of point cloud data, each frame of point cloud data is transformed into a global coordinate system to obtain multiple frames of transformed point cloud data; The multiple frames of converted point cloud data are spliced ​​to obtain the fused point cloud structure.

7. The method for detecting appearance defects of a battery pack according to any one of claims 1 to 5, characterized in that: The battery pack appearance defect detection method further includes: Based on the neighborhood of each point in each frame of point cloud data, local feature extraction is performed on each point in each frame of point cloud data to obtain local geometric features of each point in each frame of point cloud data; Performing feature extraction at different levels on each frame of point cloud data to obtain global structural features of each frame of point cloud data; Based on the average distance between each point in the neighborhood corresponding to each point in each frame of point cloud data, the point density of each point in each frame of point cloud data is determined; Based on the local geometric features and point density of each point in each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data is determined.

8. The method for detecting appearance defects of a battery pack according to claim 7, characterized in that: The extracting features of each frame of point cloud data at different levels to obtain the global structural features of each frame of point cloud data includes: Performing multiple local feature extractions at different levels on each frame of point cloud data to obtain multiple local features corresponding to each frame of point cloud data; Global convolution is performed on multiple local features corresponding to each frame of point cloud data to obtain global structural features corresponding to each frame of point cloud data.

9. The method for detecting appearance defects of a battery pack according to claim 8, characterized in that: Determining the point cloud quality of each point in each frame of point cloud data based on the local geometric features and point density of each point in each frame of point cloud data includes: Based on the local geometric features of each point in each frame of point cloud data, determining the covariance matrix of the neighborhood corresponding to each point and the covariance eigenvalue of each point; Based on the covariance eigenvalue, determining the noise of each point in each frame of point cloud data; The noise and point density of each point in each frame of point cloud data are weightedly calculated to obtain the point cloud quality of each point in each frame of point cloud data.

10. A battery pack appearance defect detection device, characterized in that: The battery pack appearance defect detection device comprises: A determination module, used to determine an initial conversion matrix between two frames of point cloud data in adjacent acquisition sequences based on an acquisition sequence of multiple frames of point cloud data corresponding to the battery pack; An adjustment module, used to adjust the initial transformation matrix based on the global structural features of each frame of point cloud data, the point cloud quality of each point in each frame of point cloud data, and the local geometric features, so as to obtain a transformation matrix corresponding to each frame of point cloud data; A conversion module, used for converting the multi-frame point cloud data based on the conversion matrix to obtain a fused point cloud structure of the battery pack; A defect detection module is used to perform defect detection on the battery pack based on the fused point cloud structure to obtain a detection result.

11. A battery pack appearance defect detection device, characterized in that: The battery pack appearance defect detection device comprises: A memory for storing executable instructions; a processor for implementing the battery pack appearance defect detection method according to any one of claims 1 to 9 when executing the executable instructions stored in the memory.

12. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to cause the processor to execute the executable instructions to implement the battery pack appearance defect detection method described in any one of claims 1 to 9.

13. A computer program product or a computer program, characterized in that The computer program product or computer program comprises executable instructions stored in a computer-readable storage medium; When the processor of the battery pack appearance defect detection device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the battery pack appearance defect detection method according to any one of claims 1 to 9 is implemented.

Images