Milling control method and device, milling equipment and computer storage medium

Abstract

The invention relates to a milling control method and device, milling equipment and a computer storage medium, and belongs to the technical field of machine tool machining.The milling control method comprises the steps that three-dimensional point cloud data of the connecting part of a battery cell and a conductive connecting piece is obtained, and a welding area of the connecting part is determined based on the three-dimensional point cloud data; planning a multi-layer milling path of the welding area based on the welding center and the welding depth of the welding area; and obtaining a surface three-dimensional point cloud of a milling surface formed when the milling cutter carries out milling along the multi-layer milling path and milling resistance borne by the milling cutter, and stopping milling of the welding area when the surface three-dimensional point cloud and / or the milling resistance meet a preset milling stopping condition. The battery cell milling device can improve the milling efficiency and prevent the battery cell from being damaged.

Description

Technical Field

[0001] The present invention relates to the technical field of machine tool processing, and in particular to a milling control method, device, milling equipment and computer storage medium. Background Art

[0002] With the continuous development of new energy vehicle technology, the number of new energy vehicles is increasing. With the use of new energy vehicles, the number of retired power batteries is also increasing.

[0003] Although retired power batteries can no longer be used as a power source for new energy vehicles, they can still play a huge role in other fields. The battery cells of retired power batteries are usually fixed to the Busbar (conductive connecting piece) by welding. The battery cells of retired power batteries need to be separated from the conductive connecting piece. The existing technology uses manual operation or milling of the welds according to the same milling path. Manual operation is time-consuming and labor-intensive, and the milling is unstable. The existing machine milling cannot adapt to different welding depths. If the milling depth is too deep, the battery cell structure will be damaged. If it is too shallow, it cannot be completely separated, and it cannot meet diverse needs, resulting in low efficiency or battery cell scrapping.

[0004] It can be seen that the existing technology cannot meet diverse needs when separating battery cells from conductive connecting sheets, resulting in low efficiency or battery cell scrapping. Summary of the Invention

[0005] In view of this, it is necessary to provide a milling control method, device, milling equipment and computer storage medium to solve the problem that the existing technology cannot meet diverse needs when separating battery cells from conductive connecting sheets, resulting in low efficiency or battery cell scrapping.

[0006] In order to solve the above problems, in a first aspect, the present invention provides a milling control method, comprising: Acquire three-dimensional point cloud data of the connection portion between the battery cell and the conductive connecting piece, and determine the welding area of ​​the connection portion based on the three-dimensional point cloud data; Plan the multi-layer milling path of the welding area based on the welding center and welding depth of the welding area; The three-dimensional point cloud of the milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance encountered by the milling cutter are obtained. When the three-dimensional point cloud of the surface and / or the milling resistance meet the preset stop milling conditions, the milling of the welding area is stopped.

[0007] In one possible implementation, comparing the three-dimensional point cloud data with preset welding three-dimensional point cloud template data to determine the welding area of ​​the connection part includes: Construct a 3D mesh model of the connection part based on 3D point cloud data; Perform multi-view projection on the three-dimensional mesh model to obtain multiple mesh images; A preset welding area recognition model is used to identify multiple grid images to obtain the welding area of ​​the connection part and the depth information of the welding area.

[0008] In a possible implementation, after determining the welding area of ​​the connection part based on the three-dimensional point cloud data, the method includes: determining a welding center of the welding area based on a connected domain of a welding mesh area corresponding to the welding area; The depth of the weld area is compensated based on the surface normal vector of the weld mesh area.

[0009] In one possible implementation, planning a multi-layer milling path of the welding area based on the welding center and welding depth of the welding area includes: Determining a milling entry point and a milling exit point for each weld region based on weld centers of adjacent weld regions and a diameter of a milling cutter; A multi-layer milling path from a milling entry point to a milling exit point in each welding area is planned based on the welding depth of the welding area, and the milling depth of each layer of the multi-layer milling path is determined according to the welding depth.

[0010] In one possible embodiment, the milling cutter satisfies the following conditions when milling along the multi-layer milling path:

[0011] Where L is the distance between adjacent welding centers, D is the diameter of the milling cutter, It is the preset safety distance parameter.

[0012] In one possible implementation, obtaining a three-dimensional point cloud of a milling surface formed when a milling cutter performs milling along a multi-layer milling path and a milling resistance experienced by the milling cutter includes: A preset coded grating pattern is projected onto the milling surface formed when the milling cutter performs milling along a multi-layer milling path, and a deformed light band reflected from the milling surface is obtained. A phase decoding algorithm is used to extract a three-dimensional point cloud of the milling surface based on the deformed light band. A six-dimensional force sensor is used to collect the milling resistance of the milling cutter in real time during milling.

[0013] In a possible implementation, the preset milling stop condition is that the three-dimensional point cloud of the surface shows that the milling surface is a battery cell and / or the milling resistance has a sudden change.

[0014] In a second aspect, the present invention further provides a milling control device, comprising: A welding area determination module is used to obtain three-dimensional point cloud data of the connection part between the battery cell and the conductive connecting piece, and determine the welding area of ​​the connection part based on the three-dimensional point cloud data; Milling path planning module, used to plan the multi-layer milling path of the welding area based on the welding center and welding depth of the welding area; The milling stop control module is used to obtain the surface three-dimensional point cloud of the milling surface formed by the milling cutter when milling along the multi-layer milling path and the milling resistance encountered by the milling cutter. When the surface three-dimensional point cloud and / or the milling resistance meet the preset stop milling conditions, the milling of the welding area is stopped.

[0015] In a third aspect, the present invention further provides a milling device, comprising a memory and a processor, wherein: Memory, used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the milling control method of any one of the above embodiments.

[0016] In a fourth aspect, the present invention further provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the milling control method of any of the above-mentioned embodiments.

[0017] The beneficial effects of the present invention are as follows: the milling control method provided by the present invention, when milling the welds between the battery cell and the conductive connecting piece of the power battery, obtains the three-dimensional point cloud data of the connection part between the battery cell and the conductive connecting piece, determines the welding area of ​​the connection part based on the three-dimensional point cloud data, and adopts the three-dimensional point cloud data method to more accurately realize the automatic identification of the welding area, plans the multi-layer milling path of the welding area based on the welding center and welding depth of the welding area, adopts the multi-layer milling strategy, can prevent over-milling during single milling, and can avoid insufficient milling, improve milling efficiency and improve milling accuracy; obtain the surface three-dimensional point cloud of the milling surface formed by the milling cutter when milling along the multi-layer milling path and the milling resistance encountered by the milling cutter, and stop milling the welding area when the surface three-dimensional point cloud and / or milling resistance meet the preset stop milling conditions. By controlling the milling stop through the combination of vision and force, it is possible to further prevent the battery cell from being damaged by milling, improve the milling yield rate, and save costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic flow chart of a milling control method provided by an embodiment of the present invention; Figure 2 A schematic flow chart of a welding area identification method provided in an embodiment of the present invention; Figure 3 A schematic flow chart of a method for determining a welding center and welding depth provided by an embodiment of the present invention; Figure 4 A schematic flow chart of a multi-layer milling path planning method provided by an embodiment of the present invention; Figure 5 A schematic flow chart of an implementation method of S103 provided in an embodiment of the present invention; Figure 6 A schematic structural diagram of a milling control device provided by an embodiment of the present invention; Figure 7 A schematic structural diagram of a milling device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0021] In the description of the embodiments of the present invention, unless otherwise specified, "plurality" means two or more. "And / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone.

[0022] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] A specific embodiment of the present invention, as Figure 1 As shown, a milling control method is disclosed, comprising: S101 , obtaining three-dimensional point cloud data of a connection portion between a battery cell and a conductive connecting piece, and determining a welding area of ​​the connection portion based on the three-dimensional point cloud data.

[0024] In an embodiment of the present invention, the three-dimensional point cloud data of the connection part between the battery cell and the conductive connecting piece can be obtained by a binocular industrial camera and a structured light projector, and the three-dimensional point cloud data is analyzed to obtain the welding area of ​​the connection part, wherein the welding area refers to the welding point between the battery cell and the conductive connecting piece. Generally, the welding area is circular, and the welding depth of the welding points between different battery cells and conductive connecting pieces is different. For multiple battery cells, it is necessary to obtain the three-dimensional point cloud data of the connection part between each battery cell and the conductive connecting piece, and determine the welding area of ​​each battery cell and the conductive connecting piece based on the three-dimensional point cloud data of each connection part. Specifically, the specific method of analyzing the three-dimensional point cloud data to obtain the welding area can be through the method of neural network model recognition, which is described in detail later in the present invention.

[0025] S102 , planning a multi-layer milling path of the welding area based on the welding center and welding depth of the welding area.

[0026] In an embodiment of the present invention, after determining the welding area between the battery cell and the conductive connecting plate, the multi-layer milling path of the welding area can be planned according to the welding center point and welding depth of the welding area. The multi-layer milling path should avoid single milling being too deep, avoiding being too small, avoiding contact between the milling cutter and the battery cell, etc. The specific planning method of the multi-layer milling path will be described in detail later in the present invention.

[0027] S103, obtaining the surface three-dimensional point cloud of the milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance encountered by the milling cutter, and stopping the milling of the welding area when the surface three-dimensional point cloud and / or the milling resistance meet the preset stop milling conditions.

[0028] In an embodiment of the present invention, when a milling cutter is milling along a multi-layer milling path, in order to prevent excessive milling damage to the battery cell, a three-dimensional point cloud of the milling surface formed by the milling cutter along the multi-layer milling path and the milling resistance encountered by the milling cutter during milling can be obtained. The three-dimensional point cloud data of the surface is then analyzed. When the milling surface and / or the milling resistance meet a preset stop milling condition, milling of the welding area is stopped. The specific stop milling condition is described in detail later in the present invention.

[0029] The milling control method provided by the present invention, when milling the welds between the battery cells and the conductive connecting pieces of a power battery, obtains three-dimensional point cloud data of the connection parts between the battery cells and the conductive connecting pieces, determines the welding area of ​​the connection parts based on the three-dimensional point cloud data, and uses the three-dimensional point cloud data to more accurately realize automatic identification of the welding area. The multi-layer milling path of the welding area is planned based on the welding center and welding depth of the welding area. The multi-layer milling strategy is adopted to prevent over-milling during single milling and avoid insufficient milling, thereby improving milling efficiency and milling accuracy. The method also obtains the surface three-dimensional point cloud of the milling surface formed by the milling cutter when milling along the multi-layer milling path and the milling resistance encountered by the milling cutter. When the surface three-dimensional point cloud and / or the milling resistance meet the preset stop milling conditions, the milling of the welding area is stopped. By controlling the milling stop through the combination of vision and force, it is possible to further prevent the battery cells from being damaged by milling, improve the milling yield rate, and save costs.

[0030] In some possible embodiments of the present invention, Figure 2 As shown, the 3D point cloud data is compared with the preset welding 3D point cloud template data to determine the welding area of ​​the connection part, including: S301, constructing a three-dimensional mesh model of the connection part based on the three-dimensional point cloud data; S302, performing multi-view projection on the three-dimensional mesh model to obtain multiple mesh images; S303: Using a preset welding area recognition model to recognize the multiple grid images, obtain the welding area of ​​the connection part and the depth information of the welding area.

[0031] In an embodiment of the present invention, after obtaining the three-dimensional point cloud data of the battery cell and the conductive connecting piece, a three-dimensional mesh model of the connection part is constructed based on the three-dimensional point cloud data. The three-dimensional mesh model is then projected from multiple perspectives to obtain multiple mesh images. Multi-perspective projection can capture features at different angles, which may help improve segmentation accuracy. A preset welding area recognition model is used to identify the multiple mesh images to obtain the welding area of ​​the connection part and the depth information of the welding area. Accurate segmentation of the welding area is achieved through three-dimensional data voxelization and multi-perspective projection preprocessing combined with a deep attention mechanism. The model uses multi-task learning to simultaneously output the segmentation mask, center coordinates, and depth information. In the post-processing stage, the center of the weld is located through connected domain analysis.

[0032] The embodiment of the present invention first voxelizes the original three-dimensional point cloud data and converts it into a voxel grid; then, these voxels are projected from multiple perspectives to generate multiple two-dimensional images; features are extracted from the images from each perspective, and a deep attention mechanism is combined to enhance the features of important areas; then, the features from multiple perspectives are fused, such as using 3D convolution or other fusion methods, and finally a segmentation result is output to ensure the accuracy of the identification of the welding area.

[0033] In some possible embodiments of the present invention, Figure 3 As shown, after determining the welding area of ​​the connection part based on the 3D point cloud data, the following steps are included: S301, determining a welding center of the welding area based on a connected domain of a welding mesh area corresponding to the welding area; S302: Compensate the depth of the welding area based on the surface normal vector of the welding mesh area.

[0034] In an embodiment of the present invention, the welding center of the welding area can be determined by analyzing the connected domain of the welding mesh area corresponding to the welding area, thereby obtaining the welding center of the welding area. For example, all the welding mesh areas in the welding area are subjected to connected domain detection to obtain the largest connected domain, and the center of the largest connected domain is calculated by geometric calculation (such as the centroid method), and the center of the largest connected domain is determined as the welding center of the welding area. As for the determination of the welding depth, the welding depth obtained by the neural network model in the aforementioned embodiment may have errors. The surface normal vector calculation and CT value compensation algorithm can be used to improve the depth measurement accuracy, and ultimately achieve sub-millimeter detection accuracy. Specifically, the CT compensation coefficient of the welding material can be found by the table lookup method, and then the actual welding depth of the welding area can be calculated by the following formula:

[0035] in, is the actual welding depth of the welding area, is the original welding depth identified by the neural network model, is the CT compensation coefficient of the welding material, The surface compensation depth can be obtained through the surface normal vector of the welding area.

[0036] The embodiment of the present invention can accurately locate the welding center and welding depth of the welding area between the battery cell and the conductive connecting piece, which facilitates the planning of subsequent multi-layer milling paths.

[0037] In some possible embodiments of the present invention, Figure 4 As shown, the multi-layer milling path of the welding area is planned based on the welding center and welding depth of the welding area, including: S401, determining a milling entry point and a milling exit point of each welding area based on the welding centers of adjacent welding areas and the diameter of the milling cutter; S402, planning a multi-layer milling path from a milling entry point to a milling exit point in each welding area based on the welding depth of the welding area, wherein the milling depth of each layer of the multi-layer milling path is determined according to the welding depth.

[0038] In an embodiment of the present invention, when planning a multi-layer milling path, due to the different heights of the battery cells, the battery cells in the field of view can be transposed into several layers, and the milling cutter plans the milling path based on the multi-layer milling points divided by the height of the posture, and starts milling step by step. For example, a three-dimensional coordinate system of the welding area can be constructed, and the multi-layer milling path can be planned according to the depth of the welding point (1-2mm). The cutting depth of each layer is ≤0.2mm to avoid single overcutting, and an avoidance path is automatically generated to ensure that the distance between the milling cutter and the battery cell is >0.5mm. Specifically, 3D structured light is used to measure the spatial coordinates (x, y, z) of the pole center, the distance L between adjacent poles, and the diameter d of the milling cutter are measured, the milling cutter is moved above the pole, and the entry and exit points of each pole are calculated. Milling in hierarchical order is the robot movement path. The milling cutter meets the following conditions when milling along the multi-layer milling path:

[0039] Where L is the distance between adjacent welding centers, D is the diameter of the milling cutter, It is the preset safety distance parameter.

[0040] The embodiment of the present invention prevents damage to the battery cell during multi-layer milling by determining the milling entry point and milling exit point of each welding area and ensuring the distance between the milling cutter and the battery cell pole and the battery cell.

[0041] In some possible embodiments of the present invention, Figure 5 As shown, the three-dimensional point cloud of the milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance suffered by the milling cutter are obtained, including: S501, projecting a preset coded grating pattern onto a milling surface formed when a milling cutter performs milling along a multi-layer milling path, acquiring a deformed light band reflected from the milling surface, and extracting a three-dimensional point cloud of the milling surface based on the deformed light band using a phase decoding algorithm; S502, using a six-dimensional force sensor to collect the milling resistance of the milling cutter during milling in real time.

[0042] In an embodiment of the present invention, the determination of complete separation of the welding area is achieved through structured light three-dimensional scanning, in which a specific coded grating pattern is projected onto the welding area, the deformed light band is captured by a camera, and the surface three-dimensional point cloud is extracted by a phase decoding algorithm. When a continuous fracture is detected at the interface between the layers and a sudden change in surface roughness is detected, it is determined to be completely separated. The visual re-inspection uses a binocular optical system to synchronously collect orthogonal views, generates a high-precision three-dimensional reconstruction model through a stereo matching algorithm, and automatically identifies defects such as cracks and pores in combination with a deep learning network, and finally outputs an integrity report containing the defect location, size and three-dimensional distribution. The six-dimensional sensor can be used to obtain the milling resistance of the milling cutter in real time during the milling process. Because the materials of the welding material and the battery cell are different, the resistance they generate to the milling cutter during the milling process is also different. Therefore, it is possible to judge whether the welding area has been milled based on the resistance encountered by the milling cutter.

[0043] Furthermore, the preset stopping condition for milling is that the three-dimensional point cloud of the surface shows that the milling surface is a battery cell and / or the milling resistance has a sudden change. The force and vision fusion feedback system captures the milling resistance signal in real time through a six-dimensional force sensor, combines the binocular optical system to project structured light to generate a depth map, and simultaneously monitors the three-dimensional morphology of the milling area. When the force signal suddenly changes or the vision detects that the tool is approaching the surface of the battery cell, the system fuses multimodal data through a federal Kalman filter to trigger the impedance control mode: dynamically adjust the feed rate and plan a spiral obstacle avoidance path, while using a feedforward compensation algorithm to predict the cutting trend to ensure that the machining process completes a safe response within 0.1 seconds. This closed-loop control architecture improves machining accuracy while reducing collision risks through real-time data synchronization and adaptive parameter optimization.

[0044] The embodiments of the present invention achieve high-precision, zero-damage milling of the welding parts of retired power batteries, solving the problems of low efficiency and high risk of traditional methods. It can significantly improve the battery cell recovery rate and economic benefits, and is suitable for power battery disassembly and other precision separation scenarios.

[0045] In order to better implement the milling control method in the embodiment of the present invention, based on the milling control method, correspondingly, Figure 6 As shown, the embodiment of the present invention further provides a milling control device, the milling control device 600 includes: The welding area determination module 601 is used to obtain three-dimensional point cloud data of the connection part between the battery cell and the conductive connecting piece, and determine the welding area of ​​the connection part based on the three-dimensional point cloud data; A milling path planning module 602 is used to plan a multi-layer milling path of the welding area based on the welding center and welding depth of the welding area; The milling stop control module 603 is used to obtain the surface three-dimensional point cloud of the milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance encountered by the milling cutter. When the surface three-dimensional point cloud and / or the milling resistance meet the preset stop milling conditions, the milling of the welding area is stopped.

[0046] The milling control device 600 provided in the above embodiment can implement the technical solution described in the above milling control method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above milling control method embodiment, which will not be repeated here.

[0047] like Figure 7 As shown, the present invention also provides an electronic device 700. The electronic device 700 includes a processor 701, a memory 702 and a display 703. Figure 7 Only some of the components of the electronic device 700 are shown, but it should be understood that it is not required to implement all of the shown components, and more or fewer components may be implemented instead.

[0048] In some embodiments, the processor 701 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 702 , such as the milling control method of the present invention.

[0049] In some embodiments, the processor 701 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 701 may be local or remote. In some embodiments, the processor 701 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, multiple clouds, or any combination thereof.

[0050] In some embodiments, the memory 702 may be an internal storage unit of the electronic device 700, such as a hard disk or memory of the electronic device 700. In other embodiments, the memory 702 may also be an external storage device of the electronic device 700, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 700.

[0051] Furthermore, the memory 702 may include both an internal storage unit of the electronic device 700 and an external storage device. The memory 702 is used to store application software installed in the electronic device 700 and various data.

[0052] In some embodiments, display 703 can be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 703 is used to display information about electronic device 700 and to display a visual user interface. Components 701-703 of electronic device 700 communicate with each other via a system bus.

[0053] In some embodiments, when the processor 701 executes the milling control program in the memory 702, the following steps may be implemented: Acquire three-dimensional point cloud data of the connection portion between the battery cell and the conductive connecting piece, and determine the welding area of ​​the connection portion based on the three-dimensional point cloud data; Plan the multi-layer milling path of the welding area based on the welding center and welding depth of the welding area; The three-dimensional point cloud of the milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance encountered by the milling cutter are obtained. When the three-dimensional point cloud of the surface and / or the milling resistance meet the preset stop milling conditions, the milling of the welding area is stopped.

[0054] It should be understood that, when the processor 701 executes the milling control program in the memory 702 , in addition to the above functions, it can also implement other functions. For details, please refer to the description of the corresponding method embodiment above.

[0055] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by the processor, the steps or functions in the milling control method provided in the above-mentioned method embodiments can be implemented.

[0056] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0057] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention should be covered by the scope of protection of the present invention.

Claims

1. A milling control method, characterized in that: include: Acquire three-dimensional point cloud data of a connection portion between the battery cell and the conductive connecting piece, and determine a welding area of ​​the connection portion based on the three-dimensional point cloud data; planning a multi-layer milling path for the welding area based on a welding center and a welding depth of the welding area; Acquire the surface three-dimensional point cloud of the milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance encountered by the milling cutter, and stop milling the welding area when the surface three-dimensional point cloud and / or the milling resistance meet the preset stop milling conditions.

2. The milling control method according to claim 1, characterized in that: The step of comparing the three-dimensional point cloud data with preset welding three-dimensional point cloud template data to determine the welding area of ​​the connection part includes: Constructing a three-dimensional mesh model of the connection part based on the three-dimensional point cloud data; Performing multi-view projection on the three-dimensional grid model to obtain multiple grid images; The plurality of grid images are identified using a preset welding area identification model to obtain the welding area of ​​the connection portion and depth information of the welding area.

3. The milling control method according to claim 2, characterized in that: After determining the welding area of ​​the connection part based on the three-dimensional point cloud data, the method includes: Determining a welding center of the welding area based on a connected domain of a welding mesh area corresponding to the welding area; The depth of the welding area is compensated based on the surface normal vector of the welding mesh area.

4. The milling control method according to claim 1, wherein: The planning of the multi-layer milling path of the welding area based on the welding center and the welding depth of the welding area includes: Determining a milling entry point and a milling exit point for each weld region based on weld centers of adjacent weld regions and a diameter of a milling cutter; A multi-layer milling path from the milling entry point to the milling exit point in each welding area is planned based on the welding depth of the welding area, and the milling depth of each layer of the multi-layer milling path is determined according to the welding depth.

5. The milling control method according to claim 4, characterized in that: The milling cutter satisfies the following conditions when milling along the multi-layer milling path: Where L is the distance between adjacent welding centers, D is the diameter of the milling cutter, It is the preset safety distance parameter.

6. The milling control method according to claim 1, characterized in that: The obtaining of a three-dimensional point cloud of a milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance experienced by the milling cutter comprises: Projecting a preset coded grating pattern on a milling surface formed when a milling cutter performs milling along the multi-layer milling path, acquiring a deformed light band reflected by the milling surface, and extracting a surface three-dimensional point cloud of the milling surface based on the deformed light band using a phase decoding algorithm; A six-dimensional force sensor is used to collect the milling resistance of the milling cutter in real time during milling.

7. The milling control method according to claim 1, characterized in that: The preset milling stopping condition is that the surface three-dimensional point cloud shows that the milling surface is a battery core and / or the milling resistance has a sudden change.

8. A milling control device, characterized in that: include: a welding area determination module, configured to obtain three-dimensional point cloud data of a connection portion between the battery cell and the conductive connecting piece, and determine a welding area of ​​the connection portion based on the three-dimensional point cloud data; A milling path planning module, configured to plan a multi-layer milling path of the welding area based on a welding center and a welding depth of the welding area; The milling stop control module is used to obtain the surface three-dimensional point cloud of the milling surface formed when the milling cutter performs milling along the multi-layer milling path and the milling resistance encountered by the milling cutter. When the surface three-dimensional point cloud and / or the milling resistance meet the preset stop milling conditions, the milling of the welding area is stopped.

9. A milling device, characterized in that: comprising a memory and a processor, wherein, The memory is used to store programs; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the milling control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the milling control method according to any one of claims 1 to 7.

Images