A method and system for manufacturing control of a battery housing part

Abstract

The embodiment of the application provides a battery shell part manufacturing control method and system, comprising: obtaining point cloud data of the battery shell part; calculating the equivalent characteristic area of the partition corresponding to the point cloud data; obtaining the optimal resolution according to the equivalent characteristic area, generating a sparse point cloud through the optimal resolution; performing normal vector calculation, defect group clustering and defect segmentation operation on the sparse point cloud, and extracting the defect geometric parameters of the sparse point cloud; calculating the stress fluctuation frequency according to the defect geometric parameters; calculating the current resonance frequency of the micro resonant cavity; adjusting the neck geometric parameters in the micro resonant cavity array according to the fusion parameters, adjusting the local stiffness of the mold, and controlling the stamping die to perform the stamping operation. The variable resolution point cloud sparseness and clustering recognition algorithm is adopted to detect the contour deviation in real time, and through the dynamic adjustment of the micro resonant cavity neck parameters and the online optimization of the stamping process parameters, the size error is reduced, and the consistency and interchangeability of the shell are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a manufacturing control method and a manufacturing control system for battery casing parts, a computer device, and a storage medium. Background Technology

[0002] Stamping is currently the most common forming process for battery casings, especially suitable for the mass production of prismatic and cylindrical casings. In recent years, with the increase in battery size, the requirements for stamping depth have significantly increased, with the deep drawing ratio rising from 3.5 to 4, placing higher demands on materials and processes. Stamping, especially deep drawing, has multiple drawbacks.

[0003] First, during high-speed deep drawing, the shell is prone to excessive thinning or even cracking in dangerous areas, severely affecting the product qualification rate. Second, since traditional stamping processes are designed for curved parts such as car roofs and doors, wrinkles, cracks, and bathtub-shaped arc deformations are easily generated when processing the flat surfaces and small rounded corners required for rectangular shells, posing a sealing risk.

[0004] The dimensional tolerances of the battery casing must be within a preset range to meet the requirements for sealing and module-free assembly, but traditional processing methods generally suffer from insufficient precision. For cylindrical batteries, outer diameter deviations directly affect the internal winding tightness and the contact condition of the electrode separator, thus affecting the battery's energy density and cycle life. Batteries with poor dimensional accuracy experience uneven changes in internal resistance during charging and discharging, leading to overheating in some areas and accelerated aging. Summary of the Invention

[0005] This invention provides a manufacturing control method for battery casing parts, a manufacturing control system for battery casing parts, a computer device, and a storage medium, aiming to solve the technical problems of local excessive thinning, tearing, wrinkling, and springback deformation that cannot be suppressed in real time during the stamping process.

[0006] To address the aforementioned problems, this invention discloses a manufacturing control method for battery casing parts. The battery casing parts are obtained through a stamping process using a stamping die, wherein the stamping die is equipped with a micro-resonant cavity array; including: Obtain point cloud data of battery casing parts; Calculate the equivalent feature area of ​​the corresponding partition of the point cloud data; The optimal resolution is obtained based on the equivalent feature area, and a sparse point cloud is generated using the optimal resolution. Normal vector calculation, defect group clustering, and defect segmentation operations are performed on sparse point clouds to extract the defect geometric parameters of the sparse point clouds. The stress fluctuation frequency is calculated based on the defect geometric parameters. Calculate the current resonant frequency of the micro-resonant cavity; The fusion parameters are generated based on the equivalent characteristic area ratio, stress fluctuation frequency, and current resonance frequency. Adjust the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjust the local stiffness of the mold, and control the stamping mold to perform stamping operations.

[0007] Preferably, calculating the equivalent feature area of ​​the corresponding partition of the point cloud data includes: The point cloud data is initially partitioned to obtain point cloud regions; Establish the mapping relationship between stamping process parameters and local peak stress in each point cloud region; The local peak stress was found based on the current stamping process parameters and mapping relationships; The equivalent feature area is obtained based on the local peak stress and the projected area of ​​the point cloud region.

[0008] Preferably, the step of obtaining the optimal resolution based on the equivalent feature area and generating a sparse point cloud using the optimal resolution includes: Establish a mapping relationship between the equivalent feature area and the resolution of each point cloud region; Based on the mapping relationship, all point cloud regions are traversed to obtain multiple resolutions, and the lowest resolution among these multiple resolutions is determined as the optimal resolution. The initial point cloud is sparsed by applying a uniform grid to it based on the optimal resolution, thus generating a sparse point cloud.

[0009] Preferably, the step of performing normal vector calculation, defect group clustering, and defect segmentation operations on the sparse point cloud to extract the defect geometric parameters of the sparse point cloud includes: Neighbor search is performed on the data in the sparse point cloud to generate a neighbor set; plane fitting is performed on the neighbor set to obtain an initial normal vector; The initial normal vector is subjected to reweighted plane fitting, and the process is iterated according to the preset objective to obtain the converged normal vector. Using the normal vectors of all points as input features, the number of defect groups and the type of defect group to which each point cloud belongs are determined; For each defect group type, extract the boundary of a single defect to obtain the defect entity; The equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and profile deviation angle of the defect entity are calculated. The equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and profile deviation angle are determined as the defect geometric parameters.

[0010] Preferably, calculating the stress fluctuation frequency based on the defect geometric parameters includes: Extract the stamping speed from the stamping process parameters; Extract the equivalent trace length from the defect geometric parameters; The stress fluctuation frequency is generated by the stamping speed and the equivalent trace length.

[0011] Preferably, the step of generating fusion parameters based on the equivalent characteristic area ratio, stress fluctuation frequency, and current resonant frequency includes...

[0012] Obtain the material elastic modulus, neck geometry parameters, and cavity volume of the microresonant cavity; The current resonant frequency is generated based on the material's elastic modulus, neck geometry parameters, and cavity volume. The ratio of the equivalent feature area is generated based on the equivalent feature area and the initial area. The fusion criterion is calculated based on the equivalent feature area ratio, stress fluctuation frequency, and current resonance frequency. When the fusion criterion meets the preset threshold range, the current stamping process parameters are adjusted to obtain the fusion parameters.

[0013] Preferably, each microcavity in the micro-resonant cavity array has a sheet-like SMA actuator embedded in its neck sidewall; the neck geometry parameters include neck width and neck embedding depth; adjusting the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjusting the local stiffness of the mold, and controlling the stamping die to perform the stamping operation includes: The circuit output current of the SMA driver is controlled according to the fusion parameters to raise the Joule temperature to the phase transition temperature. Controlling the SMA actuator to retract drives the mechanical linkage, changing the neck width and / or neck embedment depth, adjusting the local stiffness of the die, and controlling the stamping die to perform stamping operations.

[0014] This invention discloses a manufacturing control system for battery casing parts, wherein the battery casing parts are obtained by a stamping process using a stamping die, and the stamping die is provided with a micro resonant cavity array; comprising: The first acquisition module is used to acquire point cloud data of the battery casing parts; An area calculation module is used to calculate the equivalent feature area of ​​the corresponding partition of the point cloud data; A sparse module is used to obtain the optimal resolution based on the equivalent feature area, and to generate a sparse point cloud using the optimal resolution. The defect extraction module is used to perform normal vector calculation, defect group clustering, and defect segmentation operations on sparse point clouds to extract the defect geometric parameters of sparse point clouds. The stress calculation module is used to calculate the stress fluctuation frequency based on the defect geometric parameters; The resonance calculation module is used to calculate the current resonance frequency of the micro-resonant cavity; The fusion module is used to generate fusion parameters based on the equivalent feature area ratio, stress fluctuation frequency, and current resonant frequency. The control module is used to adjust the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjust the local stiffness of the mold, and control the stamping mold to perform stamping operations.

[0015] This invention also discloses a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described steps for manufacturing control of the battery casing parts.

[0016] This invention also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the aforementioned steps for manufacturing control of the battery casing parts.

[0017] The embodiments of the present invention have the following advantages: In this embodiment of the invention, the manufacturing control method for the battery casing part includes: acquiring point cloud data of the battery casing part; and calculating the equivalent feature area of ​​the partition corresponding to the point cloud data. The optimal resolution is obtained based on the equivalent feature area, and a sparse point cloud is generated using this optimal resolution. Normal vector calculation, defect group clustering, and defect segmentation are performed on the sparse point cloud to extract its defect geometric parameters. The stress fluctuation frequency is calculated based on these defect geometric parameters. The current resonance frequency of the micro-resonant cavity is calculated. Fusion parameters are generated based on the equivalent feature area ratio, stress fluctuation frequency, and current resonance frequency. The neck geometric parameters in the micro-resonant cavity array are adjusted according to the fusion parameters to regulate the local stiffness of the mold and control the stamping operation. This invention significantly improves the yield by arranging a micro-resonant cavity array in the high-risk area of ​​the mold and actively absorbing excess forming energy using a resonance dissipation mechanism. Combined with online defect identification and closed-loop control, this significantly improves the yield rate. A variable-resolution point cloud sparsity and clustering identification algorithm is used to detect contour deviations in real time. Furthermore, dynamic adjustment of the micro-resonant cavity neck parameters and online optimization of stamping process parameters reduce dimensional errors, significantly improving the consistency and interchangeability of the shell. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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 effort.

[0019] Figure 1 This is a flowchart illustrating the steps of a manufacturing control method for a battery casing part according to an embodiment of the present invention. Figure 2 This is a schematic diagram of a micro-resonant cavity for a stamping die according to an embodiment of the present invention; Figure 3 This is a structural block diagram of an embodiment of a manufacturing control system for a battery casing part according to an embodiment of the present invention; Figure 4 This is an internal structural diagram of a computer device according to one embodiment. Detailed Implementation

[0020] To make the technical problems, technical solutions, and beneficial effects solved by the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0021] Reference Figure 1 This diagram illustrates a flowchart of a manufacturing control method for a battery casing part according to an embodiment of the present invention. The battery casing part is obtained through a stamping process using a stamping die, and the stamping die is equipped with a micro-resonant cavity array. Specifically, it may include the following steps: Step 101: Obtain point cloud data of the battery casing parts; In this embodiment of the invention, a high-resolution laser profilometer, such as a line-scanning laser device, can be embedded at the exit end of the stamping die. This embodiment of the invention does not impose too many restrictions on this, and obtains three-dimensional point cloud data of the surface of the formed battery shell parts with a preset sampling interval. Furthermore, the battery casing part is obtained through a stamping process using a stamping die. The stamping die is equipped with a micro-resonant cavity array. The micro-resonant cavity is an artificial microstructure disposed on the surface of the stamping die, comprising a neck (narrow channel) and a cavity, the geometric parameters of which determine the mechanical resonant frequency; such as Figure 2 As shown, the stamping die adopts a three-layer composite structure, which includes a bottom layer, an intermediate layer, and a surface layer. The bottom layer can be a rigid substrate made of die steel. The intermediate layer is a micro-resonant cavity array layer with embedded resonant cavity micro-cavity structures made of high thermal conductivity alloys, such as beryllium copper alloy. The surface layer is the opening surface of the micro-cavity neck, which directly contacts the sheet metal. The neck opening of the micro-resonant cavity is located in the surface layer, the cavity body is located in the intermediate layer, and the SMA actuator is embedded in the side wall of the neck of the intermediate layer.

[0022] In this embodiment of the invention, to broaden the control frequency band, 3 to 5 sets of micro-resonant cavity units with different fundamental resonant frequencies can be arranged in the same stamping die to form a micro-resonant cavity array. The resonant frequency of the resonator mainly depends on the volume of the micro-resonator cavity and the geometric parameters of the micro-resonator neck. Specifically, in a battery casing part manufacturing system based on acoustic characteristics, the micro-resonant cavity array is the core actuator for achieving local forming energy dissipation and suppressing cracking and wrinkling. Its placement in the die and its internal structural composition are described in detail below.

[0023] Each micro-resonant cavity may include a neck opening, a neck channel, a cavity, an SMA driver, a mechanical linkage, a return spring, and an insulating layer. It may also include cooling channels, sealing rings, etc. The embodiments of the present invention do not impose too many restrictions on the types of components and structural composition of the micro-resonant cavity. The return spring and the insulating layer are not shown in the figure. Specifically, the neck opening is a rectangular slit (lengthwise either circumferentially or longitudinally), where the narrow region of the channel through which sound / stress waves enter the cavity generates viscous dissipation; the neck channel is a rectangular straight tube connecting the opening to the cavity; the cavity refers to a rectangular or cylindrical hollow space, which is the spring part of the resonant system, storing and releasing energy; the SMA actuator can be a sheet-like or wire-like nickel-titanium alloy, which contracts upon heating, changing the neck width s and / or neck embedment depth h; the mechanical linkage can be a micro-link, micro-push rod, or slider mechanism, transmitting the SMA contraction force to the neck wall; the return spring is a micro-compression spring that pushes the neck wall back to its initial position after the SMA cools; the insulating layer can be a ceramic coating or an air gap, preventing excessive heat conduction from the SMA to the mold body. Regarding the adjustment of the neck width in the neck geometry, the neck consists of two parallel movable sidewalls. Each sidewall has an SMA plate attached to its back. The SMA plate can be 15mm long × 2mm wide × 0.2mm thick. One end of the SMA is fixed to a fixed support in the middle layer, and the other end is connected to the movable sidewall via a mechanical linkage. When the SMA is heated to above 70℃, it contracts along its length to a preset amount. Both SMAs contract simultaneously, pushing the movable sidewall inward, thus reducing the neck width s from an initial value (e.g., 3mm) to a target value (e.g., 2.4mm).

[0024] On the other hand, during the adjustment of the neck embedding depth in the neck geometry parameters, a liftable baffle is installed at the bottom of the neck. A miniature push rod is connected to the back of the baffle, and the other end of the push rod is connected to an SMA wire. The SMA wire can have a diameter of 0.5 mm and a length of 20 mm. It is spirally wound to increase the stroke. When the SMA wire contracts, the stroke is amplified through a lever mechanism, pushing the baffle upward, thereby reducing the neck embedding depth h, i.e., shortening the neck channel. The effective neck depth can be reduced from the initial value to the minimum value. After power is cut off, another return spring pulls the baffle back to the lowest position. The micro-resonant cavities are not uniformly distributed across the entire die surface, but are only positioned in high-risk areas where stress is concentrated, deformation is severe, and defects are prone to occur during the stamping process. These high-risk areas may include the bottom rounded corner transition area (i.e., R-corner), the connection area between the sidewall and the bottom, the middle of the deep-drawn sidewall, and the area behind the cutting edge. Specifically, the material in the bottom rounded corner transition area is subjected to both tensile and bending stresses during deep drawing, resulting in the most severe thinning and making it a high-risk location for cracking. The abrupt change in material flow direction in the connection area between the sidewall and the bottom makes it prone to wrinkles and curvature deformation. When the deep drawing ratio exceeds a preset threshold, localized excessive thinning occurs in the middle of the deep-drawn sidewall. The area behind the cutting edge is the main location for burr generation.

[0025] For example, the bottom rounded transition area R-corner can be arranged with 3 to 4 rings of micro resonant cavities along the circumference of the arc surface, with a ring spacing of 10 mm. Each ring contains 40 to 60 micro resonant cavity units. The planar area connecting the side wall and the bottom can be arranged at the four corners (where the curvature changes), with 5 to 8 micro resonant cavity units arranged longitudinally at each corner. The embodiments of the present invention do not impose too many restrictions on this.

[0026] In this embodiment of the invention, a line-scanning laser device can be controlled to acquire point cloud data of battery casing parts. Specifically, scanning is performed along the circumference and axial direction of the battery casing at a preset sampling interval. During scanning, a laser line is projected onto the surface of the battery casing part, and a camera receives the reflected light. The three-dimensional spatial coordinates of each point on the surface are calculated using the principle of triangulation. Scanning one battery casing part can obtain multiple point data, forming three-dimensional point cloud data.

[0027] Step 102: Calculate the equivalent feature area of ​​the corresponding partition of the point cloud data; In this embodiment of the invention, calculating the equivalent feature area of ​​the corresponding partition of the point cloud data includes: The point cloud data is initially partitioned to obtain point cloud regions; Establish the mapping relationship between stamping process parameters and local peak stress in each point cloud region; The local peak stress was found based on the current stamping process parameters and mapping relationships; The equivalent feature area is obtained based on the local peak stress and the projected area of ​​the point cloud region.

[0028] Specifically, in this embodiment of the invention, the initial point cloud is first coarsely partitioned. Then, using a finite element simulation database or offline calibration experiments, the stamping process parameters (such as blank holder force, stamping speed, and friction coefficient) and the local peak stress of each point cloud region of the battery casing parts are pre-established. The mapping relationship is established. For the currently produced battery casing model, the mapping table is consulted to obtain the local peak stress of each point cloud region. Simultaneously, the projected area of ​​this region is also determined. If the feature area of ​​the point cloud region in the stamping direction is determined, then the equivalent feature area is... .

[0029] Step 103: Obtain the optimal resolution based on the equivalent feature area, and generate a sparse point cloud using the optimal resolution; Further applied to embodiments of the present invention, the step of obtaining the optimal resolution based on the equivalent feature area and generating a sparse point cloud using the optimal resolution includes: Establish a mapping relationship between the equivalent feature area and the resolution of each point cloud region; Based on the mapping relationship, all point cloud regions are traversed to obtain multiple resolutions, and the lowest resolution among these multiple resolutions is determined as the optimal resolution. The initial point cloud is sparsed by applying a uniform grid to it based on the optimal resolution, thus generating a sparse point cloud.

[0030] In this embodiment of the invention, a mapping table between the equivalent feature area and the resolution of each point cloud region can first be established. For example, if the equivalent feature area is ≤200mm², then the resolution is 20mm. After scanning the point cloud data of the entire battery casing, all point cloud regions are traversed, and the lowest resolution is determined as the optimal resolution R. The three-dimensional bounding box of the initial point cloud is divided into several small cubes (i.e., bounding boxes) according to the side length R using a uniform grid method. For each bounding box, the coordinates of all points inside are extracted. The system calculates the median point, retains the median point, and deletes all other points within the bounding box to obtain a sparse point cloud. It can automatically match the optimal resolution for different battery casing models and different stamping process conditions without the need for manual parameter adjustment, thus improving adaptability.

[0031] Step 104: Perform normal vector calculation, defect group clustering, and defect segmentation operations on the sparse point cloud to extract the defect geometric parameters of the sparse point cloud. In practical application to this embodiment of the invention, the steps of performing normal vector calculation, defect group clustering, and defect segmentation operations on the sparse point cloud to extract the defect geometric parameters of the sparse point cloud include: Neighbor search is performed on the data in the sparse point cloud to generate a neighbor set; plane fitting is performed on the neighbor set to obtain an initial normal vector; The initial normal vector is subjected to reweighted plane fitting, and the process is iterated according to the preset objective to obtain the converged normal vector. Using the normal vectors of all points as input features, the number of defect groups and the type of defect group to which each point cloud belongs are determined; For each defect group type, extract the boundary of a single defect to obtain the defect entity; The equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and profile deviation angle of the defect entity are calculated. The equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and profile deviation angle are determined as the defect geometric parameters.

[0032] Specifically, each point in a sparse point cloud As input, using Euclidean distance as the metric, search distance The nearest K neighbors are used to form a neighbor set, denoted as . Ni The least squares method was used to... Ni Perform plane fitting to obtain the initial plane normal vector. ; Initial plane normal vector Perform iterative reweighted plane fitting. Iterate according to the following optimization objective (convergence is expected after 5-10 iterations): ; in: , where is the fitting residual of the j-th neighbor at k iterations. It is the first Spatial coordinate vectors of neighboring points ; It refers to the first In the next iteration, the distance from the fitted plane to the origin is... It is the first The fitting plane normal vector at the next iteration; It refers to the distance weighting function, which is based on the distance between neighboring points and the center point. Euclidean distance, It is the distance-weighted bandwidth, which is 1.5 times the average distance of the neighboring point set, and is used to reduce the influence of distant points; It refers to the residual weighting function, which is based on the fitting residuals from the previous iteration. This is the residual weight bandwidth, set to 0.5mm, used to suppress outliers with large residuals; It refers to the normal vector deviation weight function, which is based on the angle between the neighboring normal vectors and the currently fitted normal vector. This is the normal vector deviation bandwidth, set to 15°, used to maintain the consistency of the normal vector and obtain the final converged normal vector output. .

[0033] Normal vectors of all points As a feature vector, the number of defect groups and the affiliation of each point are determined.

[0034] First, the distance between two points i and j is the angle between their normal vectors. : ; The angle between the statistic and the normal vector of point i is less than the cutoff distance. The number of points is the local density. For the point with the highest density, the relative distance is... ,by x-axis A decision map is plotted on the vertical axis, and points with ρ and δ values ​​greater than preset values ​​are identified as cluster centers. Each cluster center corresponds to a defect group type. For the point cloud within each defect group, for example, a crack group contains hundreds of points, which may correspond to multiple independent crack defects, and it is necessary to further segment out individual defect entities. Further, input the spatial coordinates of this set of point clouds. The system calculates the core distance and reachability distance for each point, generating a reachability map. Valleys in the reachability map correspond to the interiors of high-density clusters, while peaks correspond to the gaps between clusters. The system automatically analyzes the valley locations and selects the value between a valley and a peak as the optimal neighborhood radius. Set the minimum number of neighboring points MinPts = 25. The value between the trough and the peak is taken, and spatial clustering is performed. Points with a spatial distance less than ε and mutually reachable density are grouped into the same class (the same defect entity), and points with a distance greater than the threshold are divided into different defects. This embodiment of the invention does not impose too many restrictions on the defect type.

[0035] For each identified individual defect entity, the equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and contour deviation angle are calculated. The equivalent trace length (TL) refers to the maximum Euclidean distance of the defect point cloud in the extension direction; the equivalent trace width (TW) refers to the maximum width of the defect point cloud in the direction perpendicular to TL; and the actual feature area... Maximum depth refers to the difference between the minimum Z-coordinate of the point cloud of the crack defect and the mean Z-coordinate of the surrounding normal area; contour deviation angle refers to the angle between the actual contour normal vector of the rebound defect and the target contour normal vector.

[0036] Step 105: Calculate the stress fluctuation frequency based on the defect geometric parameters; In practical application to this embodiment of the invention, the step of calculating the stress fluctuation frequency based on the defect geometric parameters includes: extracting the stamping speed from the stamping process parameters; extracting the equivalent trace length from the defect geometric parameters; and generating the stress fluctuation frequency using the stamping speed and the equivalent trace length.

[0037] Utilizing stamping speed (In this embodiment, the speed can be 80 mm / s) and the geometric scale of the defect region, such as determining half of the equivalent trace length as the feature length. The stress fluctuation frequency was calculated. : ; Step 106: Calculate the current resonant frequency of the micro-resonant cavity; Furthermore, the material elastic modulus, neck geometry parameters, and cavity volume of the micro-resonant cavity can be obtained; the current resonant frequency can be generated based on the material elastic modulus, neck geometry parameters, and cavity volume. The micro-cavity array is pre-arranged in a mold, and the resonant frequency of each microcavity is... Calculated using the following formula: ; In the formula: s is the elastic modulus of aluminum, h is the neck width, and s is the neck embedment depth. The volume of the cavity is a fixed value, determined by the mold manufacturing process. The length of the neck (equal to h). This refers to the corrected length at the end of the neck.

[0038] Step 107: Generate fusion parameters based on the equivalent feature area ratio, stress fluctuation frequency, and current resonance frequency; In practical application to embodiments of the present invention, the step of generating fusion parameters based on the equivalent characteristic area ratio, stress fluctuation frequency, and current resonant frequency includes... The equivalent feature area ratio is generated based on the equivalent feature area and the initial area. The equivalent feature area ratio is the ratio of the equivalent feature area to the initial area. The fusion criterion is calculated based on the equivalent feature area ratio, stress fluctuation frequency, and current resonance frequency. When the fusion criterion meets the preset threshold range, the current stamping process parameters are adjusted to obtain the fusion parameters.

[0039] Among them, the fusion criterion ξ is ; If the fusion criterion ξ meets the first preset threshold range, then the microcavity fine-tuning is activated, and the target neck width to be adjusted is calculated. and target depth This makes the adjusted (i.e., achieving resonance matching); The target neck width is obtained by solving the current resonance frequency equation. and target depth ; If the fusion criterion ξ meets the second preset threshold range, then the adjustment of the stamping process parameters is activated, and the stamping speed is adjusted. Decrease or increase the blank holder force, and send the corresponding fusion parameters of the adjustment command to the stamping equipment.

[0040] Step 108: Adjust the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjust the local stiffness of the mold, and control the stamping mold to perform the stamping operation.

[0041] In this embodiment of the invention, each microcavity in the micro-resonant cavity array has a sheet-like SMA actuator embedded in its neck sidewall; the neck geometry parameters include neck width and neck embedding depth; adjusting the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjusting the local stiffness of the mold, and controlling the stamping die to perform the stamping operation includes: The circuit output current of the SMA driver is controlled according to the fusion parameters to raise the Joule temperature to the phase transition temperature. In this embodiment of the invention, the SMA actuator can be controlled to retract and drive the mechanical linkage, changing the neck width and / or neck embedment depth to achieve the target neck width. and target depth Adjusting the local rigidity of the mold controls the stamping operation of the stamping mold.

[0042] Alternatively, Modbus / TCP commands can be sent to the PLC of the stamping equipment to modify the blank holder force setpoint or the stamping speed curve. The adjusted stamping process parameters will take effect in the next stamping cycle.

[0043] In this embodiment of the invention, the output actual feature area and stress frequency This directly determines the number of micro-resonant cavities that need to be activated and the adjustment amount. The specific linkage logic is as follows: like Greater than the preset value and Within the 1200Hz-1300Hz range, activate group B (intermediate frequency) and adjust s or h to... Approaching .like Less than the preset value but Within the 1800Hz-1900Hz range, group C (high frequency) is activated for preventative fine-tuning. If multiple regions... If the limit is exceeded simultaneously, multiple cavities will be activated at the same time.

[0044] In this embodiment of the invention, by precisely arranging a micro-resonant cavity array in the high-risk area of ​​the mold and employing an SMA-driven neck geometry parameter dynamic adjustment structure, cavities are placed only in stress concentration areas, avoiding the decrease in mold strength and increase in cost caused by large-area processing. Both the neck width and depth can be dynamically adjusted, allowing the mechanical resonance frequency of the micro-resonant cavity to be continuously adjustable over a wide range. Multiple cavities with different fundamental frequencies are connected in parallel, covering the main frequency band of actual stamping stress waves. The total effective control bandwidth is significantly better than a single resonant structure, enabling it to cope with stress fluctuations over a wider frequency range.

[0045] In this embodiment of the invention, the manufacturing control method for the battery casing part includes: acquiring point cloud data of the battery casing part; and calculating the equivalent feature area of ​​the partition corresponding to the point cloud data. The optimal resolution is obtained based on the equivalent feature area, and a sparse point cloud is generated using this optimal resolution. Normal vector calculation, defect group clustering, and defect segmentation are performed on the sparse point cloud to extract its defect geometric parameters. The stress fluctuation frequency is calculated based on these defect geometric parameters. The current resonance frequency of the micro-resonant cavity is calculated. Fusion parameters are generated based on the equivalent feature area ratio, stress fluctuation frequency, and current resonance frequency. The neck geometric parameters in the micro-resonant cavity array are adjusted according to the fusion parameters to regulate the local stiffness of the mold and control the stamping operation. This invention significantly improves the yield by arranging a micro-resonant cavity array in the high-risk area of ​​the mold and actively absorbing excess forming energy using a resonance dissipation mechanism. Combined with online defect identification and closed-loop control, this significantly improves the yield rate. A variable-resolution point cloud sparsity and clustering identification algorithm is used to detect contour deviations in real time. Furthermore, dynamic adjustment of the micro-resonant cavity neck parameters and online optimization of stamping process parameters reduce dimensional errors, significantly improving the consistency and interchangeability of the shell.

[0046] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0047] Reference Figure 3 The diagram illustrates a structural block diagram of a manufacturing control system for a battery casing part according to an embodiment of the present invention, which may specifically include the following modules: The first acquisition module 301 is used to acquire point cloud data of the battery casing parts; The area calculation module 302 is used to calculate the equivalent feature area of ​​the corresponding partition of the point cloud data; The sparse module 303 is used to obtain the optimal resolution based on the equivalent feature area, and generate a sparse point cloud using the optimal resolution. The defect extraction module 304 is used to perform normal vector calculation, defect group clustering and defect segmentation operations on sparse point clouds to extract the defect geometric parameters of sparse point clouds. The stress calculation module 305 is used to calculate the stress fluctuation frequency based on the defect geometric parameters. The resonance calculation module 306 is used to calculate the current resonance frequency of the micro-resonant cavity; Fusion module 307 is used to generate fusion parameters based on the equivalent feature area ratio, stress fluctuation frequency and current resonant frequency; The control module 308 is used to adjust the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjust the local stiffness of the mold, and control the stamping mold to perform stamping operations.

[0048] Preferably, the area calculation module includes: The partitioning submodule is used to perform preliminary partitioning of the point cloud data to obtain point cloud regions. The mapping submodule is used to establish the mapping relationship between stamping process parameters and local peak stress in each point cloud region; The query submodule is used to query local peak stresses based on the current stamping process parameters and mapping relationships. The area submodule is used to obtain the equivalent feature area based on the local peak stress and the projected area of ​​the point cloud region.

[0049] Preferably, the sparse module includes: The resolution mapping submodule is used to establish the mapping relationship between the equivalent feature area and the resolution of each point cloud region; The traversal submodule is used to traverse all point cloud regions according to the mapping relationship to obtain multiple resolutions, and determine the lowest resolution among the multiple resolutions as the optimal resolution. The sparse processing submodule is used to perform sparse processing on the initial point cloud using a uniform grid based on the optimal resolution, thereby generating a sparse point cloud.

[0050] Preferably, the defect extraction module includes: The normal vector submodule is used to perform neighbor search on the data in the sparse point cloud to generate a neighbor set; perform plane fitting on the neighbor set to obtain an initial normal vector; perform reweighted plane fitting on the initial normal vector and iterate according to a preset target to obtain a converged normal vector. The clustering submodule is used to take the normal vectors of all points as input features to determine the number of defect groups and the defect group type to which each point cloud belongs; The boundary submodule is used to extract the boundary of a single defect for each defect group type, thus obtaining the defect entity; The parameter calculation submodule is used to calculate the equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and contour deviation angle of the defect entity; and to determine the equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and contour deviation angle as the defect geometric parameters.

[0051] Preferably, the stress calculation module includes: The speed extraction submodule is used to extract the stamping speed from the stamping process parameters; The trace length extraction submodule is used to extract the equivalent trace length from the defect geometric parameters; The frequency generation submodule is used to generate stress fluctuation frequency based on the stamping speed and equivalent trace length.

[0052] Preferably, the fusion module includes: The resonance acquisition submodule is used to acquire the material elastic modulus, neck geometry parameters, and cavity volume of the micro-resonant cavity; and to generate the current resonance frequency based on the material elastic modulus, neck geometry parameters, and cavity volume. The area ratio submodule is used to generate the equivalent feature area ratio based on the equivalent feature area and the initial area; The criterion submodule is used to calculate the fusion criterion based on the equivalent feature area ratio, stress fluctuation frequency and current resonance frequency; The parameter adjustment submodule is used to adjust the current stamping process parameters to obtain the fusion parameters when the fusion criterion meets the preset threshold range.

[0053] Preferably, the control module includes: The current control submodule is used to control the circuit output current of the SMA driver according to the fusion parameters, so that the Joule heating is raised to the phase transition temperature; The drive submodule is used to control the SMA driver to retract and drive the mechanical linkage, change the neck width and / or neck embedment depth, adjust the local stiffness of the die, and control the stamping die to perform stamping operations.

[0054] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0055] Specific limitations regarding the manufacturing control system for battery casing components can be found in the above description of the manufacturing control methods for battery casing components, and will not be repeated here. Each module in the aforementioned manufacturing control system for battery casing components can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0056] The manufacturing control system for the battery casing parts provided above can be used to execute the manufacturing control method for the battery casing parts provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0057] In one embodiment, a computer device is provided, which may be a terminal for controlling stamping equipment, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a manufacturing control method for a battery casing part. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0058] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0059] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the steps described above.

[0060] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the steps described above.

[0061] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0062] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0063] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] The foregoing has provided a detailed description of a manufacturing control method and a manufacturing control system for battery casing parts, a computer device, and a storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A manufacturing control method for a battery casing component, characterized in that, The battery casing part is obtained by a stamping process using a stamping die, the stamping die being provided with a micro resonant cavity array; including: Obtain point cloud data of battery casing parts; Calculate the equivalent feature area of ​​the corresponding partition of the point cloud data; The optimal resolution is obtained based on the equivalent feature area, and a sparse point cloud is generated using the optimal resolution. Normal vector calculation, defect group clustering, and defect segmentation operations are performed on sparse point clouds to extract the defect geometric parameters of the sparse point clouds. The stress fluctuation frequency is calculated based on the defect geometric parameters. Calculate the current resonant frequency of the micro-resonant cavity; The fusion parameters are generated based on the equivalent characteristic area ratio, stress fluctuation frequency, and current resonance frequency. Adjust the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjust the local stiffness of the mold, and control the stamping mold to perform stamping operations.

2. The method according to claim 1, characterized in that, The calculation of the equivalent feature area of ​​the corresponding partition of the point cloud data includes: The point cloud data is initially partitioned to obtain point cloud regions; Establish the mapping relationship between stamping process parameters and local peak stress in each point cloud region; The local peak stress was found based on the current stamping process parameters and mapping relationships; The equivalent feature area is obtained based on the local peak stress and the projected area of ​​the point cloud region.

3. The method according to claim 1, characterized in that, The step of obtaining the optimal resolution based on the equivalent feature area, and generating a sparse point cloud using the optimal resolution, includes: Establish a mapping relationship between the equivalent feature area and the resolution of each point cloud region; Based on the mapping relationship, all point cloud regions are traversed to obtain multiple resolutions, and the lowest resolution among these multiple resolutions is determined as the optimal resolution. The initial point cloud is sparsed by applying a uniform grid to it based on the optimal resolution, thus generating a sparse point cloud.

4. The method according to claim 1, characterized in that, The process of performing normal vector calculation, defect group clustering, and defect segmentation on the sparse point cloud to extract the defect geometric parameters of the sparse point cloud includes: Neighbor search is performed on the data in the sparse point cloud to generate a neighbor set; plane fitting is performed on the neighbor set to obtain an initial normal vector; The initial normal vector is subjected to reweighted plane fitting, and the process is iterated according to the preset objective to obtain the converged normal vector. Using the normal vectors of all points as input features, the number of defect groups and the type of defect group to which each point cloud belongs are determined; For each defect group type, extract the boundary of a single defect to obtain the defect entity; The equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and profile deviation angle of the defect entity are calculated. The equivalent trace length, equivalent trace width, maximum depth, peak-to-trough height difference, and profile deviation angle are determined as the defect geometric parameters.

5. The method according to claim 1, characterized in that, The step of calculating the stress fluctuation frequency based on the defect geometric parameters includes: Extract the stamping speed from the stamping process parameters; Extract the equivalent trace length from the defect geometric parameters; The stress fluctuation frequency is generated by the stamping speed and the equivalent trace length.

6. The method according to claim 5, characterized in that, The process of generating fusion parameters based on the equivalent characteristic area ratio, stress fluctuation frequency, and current resonant frequency includes... Obtain the material elastic modulus, neck geometry parameters, and cavity volume of the microresonant cavity; The current resonant frequency is generated based on the material's elastic modulus, neck geometry parameters, and cavity volume. The ratio of the equivalent feature area is generated based on the equivalent feature area and the initial area. The fusion criterion is calculated based on the equivalent feature area ratio, stress fluctuation frequency, and current resonance frequency. When the fusion criterion meets the preset threshold range, the current stamping process parameters are adjusted to obtain the fusion parameters.

7. The method according to claim 6, characterized in that, Each microcavity in the micro-resonant cavity array has a sheet-like SMA actuator embedded in its neck sidewall; the neck geometry parameters include neck width and neck embedding depth; adjusting the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjusting the local stiffness of the mold, and controlling the stamping die to perform the stamping operation includes: The circuit output current of the SMA driver is controlled according to the fusion parameters to raise the Joule temperature to the phase transition temperature. Controlling the SMA actuator to retract drives the mechanical linkage, changing the neck width and / or neck embedment depth, adjusting the local stiffness of the die, and controlling the stamping die to perform stamping operations.

8. A manufacturing control system for battery casing parts, characterized in that, The battery casing part is obtained by a stamping process using a stamping die, the stamping die being provided with a micro resonant cavity array; including: The first acquisition module is used to acquire point cloud data of the battery casing parts; An area calculation module is used to calculate the equivalent feature area of ​​the corresponding partition of the point cloud data; A sparse module is used to obtain the optimal resolution based on the equivalent feature area, and to generate a sparse point cloud using the optimal resolution. The defect extraction module is used to perform normal vector calculation, defect group clustering, and defect segmentation operations on sparse point clouds to extract the defect geometric parameters of sparse point clouds. The stress calculation module is used to calculate the stress fluctuation frequency based on the defect geometric parameters; The resonance calculation module is used to calculate the current resonance frequency of the micro-resonant cavity; The fusion module is used to generate fusion parameters based on the equivalent feature area ratio, stress fluctuation frequency, and current resonant frequency. The control module is used to adjust the neck geometry parameters in the micro-resonant cavity array according to the fusion parameters, adjust the local stiffness of the mold, and control the stamping mold to perform stamping operations.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the manufacturing control method for the battery casing part according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the manufacturing control method for the battery casing part according to any one of claims 1 to 7.

Images