A new energy battery square aluminum shell burr non-destructive removal method and system

Abstract

The application discloses a new energy battery square aluminum shell burr nondestructive removal method and system, belongs to data processing technical field, the method includes: through image acquisition equipment carries out multi-angle image acquisition to battery square aluminum shell, obtains aluminum shell multi-angle image information;Image recognition is carried out, burr identification information is determined, burr position information is determined;Further obtain burr shape feature, burr size information;Burr shape feature, burr size information, burr position information are input into burr analysis model, and burr removal parameter is obtained;Obtain removal equipment parameter information, burr material information, determine burr removal step requirement, obtain burr removal strategy based on burr removal distribution requirement and remove aluminum shell.The application solves the technical problems of low intelligent degree and poor removal quality of aluminum shell burr removal in the prior art, and achieves the technical effects of improving the burr removal efficiency of aluminum shell, improving the nondestructive degree of burr removal, and ensuring the quality of aluminum shell.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and system for non-destructive removal of burrs from the square aluminum shell of a new energy battery. Background Technology

[0002] Driven by environmental protection policies, the new energy vehicle industry has become one of the hottest sectors, and its related industrial chains have grown rapidly. As a core component of new energy vehicles, the demand for new energy batteries has also increased significantly. Researching the processing technology of new energy battery casings is of great importance for ensuring battery quality and supporting the rapid development of the new energy industry.

[0003] Currently, during the processing of new energy battery casings, burrs easily form at the intersections of aluminum casing surfaces due to manufacturing process issues. These burrs, mainly consisting of barbs or flash, affect casing assembly or may fall off during use, causing severe frictional damage between the battery and other automotive components, thus reducing the lifespan of the parts. Therefore, deburring methods are used, such as manual deburring with tools like steel files and sandpaper, or high-temperature deburring and tumbling deburring methods.

[0004] However, manual deburring methods are limited by worker experience, complex to operate, and time-consuming. High-temperature deburring and tumbling deburring methods can only treat specific types of burrs. In actual production, due to the diverse types of burrs, using only a single treatment method cannot guarantee the quality of deburring. Switching between multiple deburring processes cannot be intelligently adjusted according to the actual burr situation, resulting in low removal efficiency. Existing technologies suffer from low levels of intelligence and poor removal quality in aluminum shell burr removal. Summary of the Invention

[0005] The purpose of this application is to provide a non-destructive method and system for removing burrs from the square aluminum shell of new energy batteries, in order to solve the technical problems of low intelligence and poor removal quality in the existing aluminum shell burr removal technology.

[0006] In view of the above problems, this application provides a method and system for non-destructive removal of burrs from the square aluminum shell of new energy batteries.

[0007] In a first aspect, this application provides a method for non-destructive removal of burrs from the square aluminum shell of a new energy battery. The method includes: acquiring multi-angle images of the square aluminum shell of the battery using an image acquisition device to obtain multi-angle image information of the aluminum shell; performing image recognition on the multi-angle image information of the aluminum shell to determine burr identification information, and determining burr location information based on the identified image information; obtaining burr shape features and burr size information based on the burr identification information; inputting the burr shape features, burr size information, and burr location information into a burr analysis model to obtain burr removal parameters; obtaining removal equipment parameter information and burr material information; determining burr removal step-by-step requirements based on the removal equipment parameter information, burr material information, burr removal parameters, and burr shape features; and obtaining a burr removal strategy based on the burr removal distribution requirements to remove burrs from the aluminum shell.

[0008] On the other hand, this application also provides a non-destructive burr removal system for square aluminum shells of new energy batteries. The system includes: a multi-angle image acquisition module, used to acquire multi-angle images of the square aluminum shell of the battery using an image acquisition device to obtain multi-angle image information of the aluminum shell; a burr location information determination module, used to perform image recognition on the multi-angle image information of the aluminum shell to determine burr identification information and burr location information based on the identified image information; a size information acquisition module, used to obtain burr shape features and burr size information based on the burr identification information; a removal parameter acquisition module, used to input the burr shape features, burr size information, and burr location information into a burr analysis model to obtain burr removal parameters; and a burr removal module, used to obtain removal equipment parameter information and burr material information, determine burr removal step-by-step requirements based on the removal equipment parameter information, burr material information, burr removal parameters, and burr shape features, and obtain a burr removal strategy based on the burr removal distribution requirements to remove burrs from the aluminum shell.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application uses an image acquisition device to acquire multi-angle images of the square aluminum casing of a battery, obtaining multi-angle image information of the aluminum casing. Then, image recognition is performed on this multi-angle image information to determine burr identification information and burr location information. Based on the burr identification information, burr shape features and burr size information are obtained. By inputting the burr shape features, burr size information, and burr location information into a burr analysis model, burr removal parameters are obtained. Then, removal equipment parameters and burr material information are obtained. Based on the removal equipment parameters, burr material information, burr removal parameters, and burr shape features, step-by-step burr removal requirements are determined. Based on the burr removal distribution requirements, a burr removal strategy is obtained to remove burrs from the aluminum casing. Thus, intelligent step-by-step burr removal is achieved, improving the technical effect of burr removal quality. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a method for non-destructive removal of burrs from a square aluminum shell of a new energy battery, provided in an embodiment of this application;

[0013] Figure 2 This is a flowchart illustrating the process of determining burr identification information in a non-destructive burr removal method for square aluminum shells of new energy batteries, provided in an embodiment of this application.

[0014] Figure 3 A flowchart illustrating the process of obtaining burr removal parameters in a non-destructive burr removal method for a square aluminum shell of a new energy battery, provided in an embodiment of this application.

[0015] Figure 4 This is a schematic diagram of the structure of a non-destructive burr removal system for a square aluminum shell of a new energy battery according to this application.

[0016] Explanation of reference numerals in the attached figures: 11 Multi-angle image acquisition module, 12 Burr location information determination module, 13 Size information acquisition module, 14 Removal parameter acquisition module, 15 Burr removal module. Detailed Implementation

[0017] This application provides a non-destructive method and system for removing burrs from the square aluminum shell of new energy batteries, solving the technical problems of low intelligence and poor removal quality in existing aluminum shell burr removal technologies. It achieves the technical effects of intelligent removal based on burr type, improving processing efficiency, coordinating resources, and ensuring removal quality.

[0018] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0019] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0020] Example 1

[0021] like Figure 1 As shown, this application provides a method for non-destructive removal of burrs from the square aluminum shell of a new energy battery, wherein the method includes:

[0022] Step S100: Use an image acquisition device to acquire multi-angle images of the square aluminum casing of the battery to obtain multi-angle image information of the aluminum casing;

[0023] Specifically, the image acquisition device is used to acquire images of the square aluminum casing of the battery, including a camera, scanner, infrared camera, etc. The square aluminum casing is any aluminum casing to be deburred. To fully acquire images of the square aluminum casing, the image acquisition device captures images from multiple different angles, preferably from the front, top, side, and connecting lines, obtaining multi-angle image information of the aluminum casing. This multi-angle image information reflects the smoothness of the aluminum casing surface at different angles. Thus, the technical effect of acquiring images of the aluminum casing surface is achieved, providing identification images for subsequent burr information recognition.

[0024] Step S200: Perform image recognition on the multi-angle image information of the aluminum shell to determine burr recognition information, and determine burr location information based on the recognized image information;

[0025] Furthermore, such as Figure 2 As shown, image recognition is performed on the multi-angle image information of the aluminum shell to determine burr identification information. In this embodiment, step S200 includes:

[0026] Step S210: Obtain a preset burr recognition model, wherein the burr recognition model is a machine learning model obtained by training and testing a training dataset and a test dataset with multiple types of burr identification data;

[0027] Step S220: Perform noise reduction and bias correction preprocessing on the multi-angle image information of the aluminum shell;

[0028] Step S230: Input the preprocessed multi-angle image information of the aluminum shell into the burr recognition model, perform burr recognition processing, and obtain the burr recognition information.

[0029] Specifically, the burr recognition model is a functional model used for intelligent recognition of burrs in image information. The multi-type burr labeling data is data obtained by labeling burrs with a certain type of burr feature in an image according to different types of burr features, including burr images and burr feature labels. Preferably, the dataset containing the multi-type burr labeling data is divided into a training dataset and a test dataset in a 2:1 ratio. The burr recognition model is trained using the training dataset, with the multi-type labeling data as supervision, until convergence. Then, the accuracy of the burr recognition model is tested using the test dataset. When the model's accuracy meets the requirements, the trained burr recognition model is obtained.

[0030] Specifically, during the image acquisition process of the aluminum shell, the influence of the environment and angle results in a large amount of noise and excessive image distortion in the acquired images, making it impossible to accurately reflect the surface condition of the aluminum shell. By performing noise reduction and bias correction preprocessing on the multi-angle image information of the aluminum shell, the images are optimized to make them usable. Preferably, a spatial pixel feature denoising algorithm is used to remove random noise from the image, directly processing noise in the image space. The bias correction preprocessing involves acquiring the image contour and, according to a certain reference, performing perspective transformation, projection, stretching, and other operations on the distorted parts of the image to correct the image tilt. Then, the preprocessed multi-angle image information of the aluminum shell is input into the burr recognition model to identify the types of burrs in the image, obtaining burr recognition information. This burr recognition information reflects the type and basic information of the burrs. Furthermore, based on the burr recognition information, the specific location of each burr in the square aluminum shell of the battery is determined, obtaining burr location information, which provides a basis for subsequent burr localization and removal processing. Furthermore, by intelligently identifying burrs in images, the technical effect of providing basic analytical data for burr processing is achieved, thereby improving the intelligence level of burr processing and increasing processing efficiency.

[0031] Step S300: Based on the burr identification information, obtain the burr shape features and burr size information;

[0032] Specifically, feature extraction is performed on the burr identification information to obtain burr shape features. These burr shape features describe the appearance and shape of the burr, including ring-shaped, conical, elongated, and gear-shaped features. Based on the burr identification information and the burr shape features, multi-angle graphic information of the aluminum shell is extracted for a specific burr shape feature, resulting in an image corresponding to that burr shape feature. By acquiring the multi-angle image of the feature burr, dimensional information such as the burr's length and width is obtained. This achieves the technical effect of providing quantifiable data information for subsequent burr removal, thereby improving the accuracy of burr removal.

[0033] Step S400: Input the burr shape features, burr size information, and burr location information into the burr analysis model to obtain burr removal parameters;

[0034] Furthermore, such as Figure 3 As shown, the burr shape features, burr size information, and burr location information are input into the burr analysis model to obtain burr removal parameters. In this embodiment, step S400 includes:

[0035] Step S410: Classify the burrs according to their shape characteristics and size information to determine the burr category information;

[0036] Step S420: Determine the burr contact area based on the burr size information;

[0037] Step S430: Based on the burr type information, determine the burr force information according to the burr contact area and the burr shape characteristics;

[0038] Step S440: Based on the burr location information, perform a location impact analysis to determine the location removal parameter requirements;

[0039] Step S450: Based on the burr force information and the position removal parameter requirements, perform parameter requirement fusion to determine the burr removal parameters.

[0040] Furthermore, step S450 in this embodiment of the application also includes:

[0041] Step S451: Using the multi-angle image information of the aluminum shell, perform color recognition on the burr identification information to determine the burr color distribution information;

[0042] Step S452: Determine whether the burr contains impurities based on the burr color distribution information;

[0043] Step S453: When the burrs contain impurities, perform doping analysis on the production environment, production equipment, and process flow of the aluminum shell production process to determine the impurity information;

[0044] Step S454: Based on the impurity information and the burr color distribution information, determine the burr force influence information;

[0045] Step S455: Add the burr force influence information to the burr analysis model for incremental learning. Input the burr shape features, burr size information, burr location information, and burr force influence information into the incrementally learned burr analysis model to obtain the burr removal parameters.

[0046] Specifically, the burr analysis model is a functional model that determines specific parameters for burr removal operations based on different burr types and burr information. Historical production and processing data from manufacturing enterprises are collected to obtain historical burr shape characteristics, historical burr size information, historical burr location information, and historical burr removal parameters. These historical burr shape characteristics, historical burr size information, historical burr location information, and historical burr removal parameters are used as a historical dataset, and the historical burr removal parameters are labeled. The historical dataset is divided into a training set, a test set, and a validation set according to a certain ratio. Preferably, the test set and validation set have the same ratio; the specific ratio is set by the staff and is not limited here. Then, the burr analysis model is trained using the training set, and the output results are validated using the historical burr removal parameters as validation data. After the model training converges, the accuracy of the model output results is tested using the test set. When the accuracy meets the requirements, the applicability range of the model is validated using the validation set. When the applicability range meets the requirements, the burr analysis model is obtained. The burr removal parameters are parameters related to the amount of burrs removed, the removal force, and the removal location when removing burrs.

[0047] Specifically, cluster analysis is performed on the burrs based on their shape and size information. Using the burr shape feature as the first dividing node, multiple burr features are distinguished to obtain multiple burr feature sets. Each of these multiple burr feature sets corresponds to different burr features. Furthermore, the multiple burr feature sets are divided by size based on the burr size information, using the burr size as the second dividing node, thereby obtaining the burr category information. The burr category information refers to the information obtained after classifying burrs according to their shape and size information to obtain different burr categories.

[0048] Specifically, the contact area between the burr and the aluminum shell surface is obtained based on the burr size information, thus determining the burr contact area. For example, the burr is conical in shape with a base size of 3cm. 2 The contact area between the burr and the aluminum shell is 3 cm². 2The force applied to a burr during deburring is determined based on its type information. The direction of the force is then determined based on the burr's contact area, and the angle of the force is determined based on the burr's shape. This yields the burr force information, which refers to the force applied during burr removal. Further, the influence of the burr's location on the removal process is determined based on its location information. For example, if a burr is located at a seam on an aluminum shell surface, the surface impact must be considered during burr removal to prevent damage from the cutting tool. This results in the required location removal parameters, which are parameters determining the tool position during deburring, including the removal amount and the removal positioning position.

[0049] Specifically, the burr force information and the location removal parameter requirements are fused according to their respective categories to obtain the burr removal parameters. This fusion refers to combining the burr force information and location removal parameters corresponding to the same burr category, based on the burr category corresponding to the burr force information and the burr category corresponding to the location removal parameter requirements. This achieves the technical effect of improving the rationality of burr removal parameter design, designing different burr removal parameters for different burr categories, and improving removal quality.

[0050] Specifically, the color of the burr identification information is identified based on the multi-angle image information of the aluminum shell, thereby collecting and summarizing the color of each burr to obtain the burr color distribution information. This burr color distribution information is obtained based on the color distribution of burrs at different locations on the aluminum shell. Furthermore, the material of the burr is determined according to the processing technology of the aluminum shell; for example, if the burr is aluminum, then the color of aluminum is the color of the burr, which is silver-white. By judging the burr color distribution information to determine whether it is silver-white, it can be determined whether the burr contains impurities. When the judgment result is that the burr contains impurities, the aluminum shell production process is analyzed from multiple angles to filter impurity information. Preferably, the analysis is conducted from three angles: production environment, production equipment, and process flow, to analyze the source of impurities mixed in with the aluminum burrs. For example, in the plasma-enhanced electrochemical surface ceramicization process of aluminum shells, different locations of the aluminum shells are colored, resulting in different burr colors corresponding to different colored aluminum shells. During the machining process of the aluminum shells using a machine tool, the fly slag generated during the cutting process of the tool itself becomes embedded in the burrs, resulting in the burrs containing tool fly slag. The impurity information reflects the nature of the impurities in the burrs, including the impurity type and impurity color. The impurity types include iron, copper, plastic, etc. The impurity colors include yellow, green, etc. Therefore, different impurity colors correspond to different impurity types.

[0051] Specifically, based on the impurity information and the burr color distribution information, the impurity type corresponding to the burrs on the aluminum shell surface is determined, and then the impact on the burr stress is determined based on the impurity type. For example, if the impurity is iron, which is harder than aluminum, the presence of aluminum in the impurity significantly affects the burr hardness, potentially causing the tool to jam if processed with the original cutting force. Therefore, by incorporating the burr stress impact information into the burr analysis model for incremental learning, the model can further consider the burr stress impact information, thereby obtaining the burr removal parameters. This achieves the technical effect of improving the accuracy of the burr removal parameters and improving the removal quality.

[0052] Step S500: Obtain the removal equipment parameter information and burr material information. Based on the removal equipment parameter information, burr material information, burr removal parameters, and burr shape characteristics, determine the burr removal step requirements. Based on the burr removal distribution requirements, obtain the burr removal strategy to remove the aluminum shell.

[0053] Furthermore, based on the removal equipment parameter information, burr material information, burr removal parameters, and burr shape characteristics, the burr removal step-by-step requirements are determined. In this embodiment, step S500 further includes:

[0054] Step S510: Determine the removal step adjustment range and grinding wheel speed range based on the removal equipment parameter information;

[0055] Step S520: Obtain the burr removal force requirement and grinding angle information based on the burr removal parameters;

[0056] Step S530: Based on the burr material information and burr shape characteristics, perform material stress analysis to obtain burr stress information;

[0057] Step S540: Determine the removal step information based on the burr removal force requirements and burr shape characteristics;

[0058] Step S550: Based on the removal step information, the removal step adjustment range, and the grinding wheel speed range, obtain the step removal parameter information, and based on the removal step information and the corresponding step removal parameter information, obtain the burr removal step requirements.

[0059] Furthermore, based on the removal step information, the removal step adjustment range, and the grinding wheel speed range, step removal parameter information is obtained. In this embodiment, step S550 further includes:

[0060] Step S551: Determine the removal requirements for each step based on the removal step information;

[0061] Step S552: Based on the removal requirements of the first step, determine the first rotational speed information and the first step feed information;

[0062] Step S553: ​​Based on the first rotation speed information and the first step forward information, predict the grinding effect to obtain the first step grinding effect, wherein the first step grinding effect includes the shape information of the remaining burrs and the size information of the remaining burrs.

[0063] Step S554: Based on the remaining burr shape information and remaining burr size information, determine the removal requirements for the second step and obtain the second rotation speed information and the second step information;

[0064] Step S555: Predict the polishing effect based on the second rotation speed information and the second step information to obtain the second polishing effect. When the remaining burr size is 0, use the first rotation speed information and the first step information as the first removal parameter information, and use the second rotation speed information and the second step information as the second removal parameter information, and so on, to obtain the removal parameter information for all steps.

[0065] Specifically, the deburring equipment parameter information reflects the basic operating status of the deburring equipment, including equipment type, equipment power, and cutter type. The deburring material information is determined by the material of the battery's square aluminum casing, and the deburring material is also aluminum. Furthermore, based on the deburring equipment parameter information, deburring material information, deburring parameters, and deburring shape characteristics, the deburring requirements for each step in the deburring process are determined, and then a deburring strategy is determined based on these requirements. The step-by-step deburring requirements refer to the requirements that each deburring step must meet.

[0066] Specifically, based on the deburring equipment parameter information, the adjustment range for deburring using the equipment is obtained, including the deburring step adjustment range and the grinding wheel speed range. The deburring step adjustment range refers to the cutting amount range when the tool cuts the burr each time. The step length adjustment range is the range of movement of the grinding wheel towards the workpiece during grinding. Using step adjustment, a fixed step length can be used to move closer to the workpiece to achieve the desired grinding effect. The grinding wheel speed range refers to the range of grinding wheel speeds during the deburring process. A higher grinding wheel speed results in a larger grinding amount per unit time, while a lower speed results in a smaller grinding amount per unit time. Furthermore, the deburring force requirement is obtained based on the burr force information in the deburring parameters. The deburring force requirement refers to the magnitude of the force applied during the burr removal process. The grinding angle information is the angle between the grinding wheel and the burr determined based on the positional deburring parameter requirements to avoid damage to the aluminum shell surface during grinding. The stress distribution and magnitude of the burr are related to the material and shape of the burr. By performing stress analysis based on the burr material information and burr shape characteristics, preferably, the burr material is aluminum and the shape is circular. The stress magnitude determined based on the material is 370 MPa. The stress magnitude is adjusted based on the shape of the burr to obtain the burr stress information.

[0067] Specifically, each deburring step is determined based on the required deburring force and the burr shape characteristics. The deburring step information reflects the number of steps in the deburring process and the object to be removed in each step. The requirements for each step are determined based on the deburring step information, including the amount to be removed and the removal effect. Furthermore, based on the removal requirements of each step, the first rotational speed information and the first step forward information of the deburring equipment for the first deburring are obtained. The first rotational speed information refers to the rotational speed of the grinding wheel. The first step forward information refers to the distance the tool travels during rotation. Then, the burr is removed based on the first rotational speed information and the first step forward information, and the appearance of the removed burr is predicted to obtain the first step grinding effect. The first step grinding effect includes the shape information and size information of the remaining burrs. The shape information of the remaining burrs is obtained by calculating the amount of burr removed based on the first step forward information and the first rotational speed information, and also based on the grinding angle. The size information of the remaining burrs is calculated based on the burr size information, using the grinding amount and cutting amount.

[0068] Specifically, the second-step removal requirements, namely the cutting amount and grinding speed, are obtained based on the remaining burr shape and size information. The second rotation speed information is the grinding wheel speed during the second burr removal process. The second step information is the tool cutting amount during the second burr removal process. Then, using the same prediction method as the first-step grinding effect, the second-step grinding effect is obtained. This continues until the remaining burr size is 0, at which point the burrs have been completely removed without damaging the aluminum shell. The first-step removal parameter information refers to the parameters used during the first burr removal process, and the second-step removal parameter information refers to the parameters used during the second burr removal process. Thus, the technical effect of determining the removal parameters for each step in all steps and ensuring the quality of burr removal is achieved.

[0069] Furthermore, step S555 of this application embodiment also includes:

[0070] Step S5551: Based on the steps before and after removing the step information, construct a time chain, wherein the nodes of the time chain are the aluminum shell burr polishing state.

[0071] Step S5552: Associate the removal parameter information of each step as the external action of the node with the burr grinding state of the aluminum shell, evaluate the burr grinding effect of the removal parameter information of each step as the node reward value, and construct a Markov chain prediction model.

[0072] Step S5553: Based on the Markov chain prediction model, predict the grinding state probability of each node to obtain the final grinding state probability of the node.

[0073] Step S5554: Determine whether the probability of the polishing state meets the preset requirements. If it does, determine the step-by-step removal parameter information.

[0074] Step S5555: If the condition is not met, adjust the step-by-step removal parameter information until the grinding state probability of the final output node reaches the preset requirement.

[0075] Specifically, by following the steps before and after removing the distribution information, a time-series chain is obtained based on the order of the steps and nodes. The nodes in this time-series chain represent the polishing state of the aluminum shell burrs. The time-series chain establishes a correlation between the burr state after each polishing node and the polishing operations and effects of previous nodes. Furthermore, by using the removal parameter information of each step as the external action of the node, and establishing a one-to-one correspondence between each step and the node, the polishing state of the aluminum shell burrs is associated with the removal parameter information of each step. The polishing effect of each step is evaluated based on the removal parameter information, and a node reward value is obtained based on the evaluation result. For example, an excellent evaluation result awards a reward value of 3, a good evaluation result awards a reward value of 2, and a fair evaluation result awards a reward value of 1. Then, based on the node reward values, a Markov chain prediction model is constructed. This Markov chain prediction model is a functional model for predicting the polishing state of the aluminum shell burrs.

[0076] Specifically, the probability of each node achieving different polishing states is predicted based on the Markov chain prediction model. A node reward value is obtained for each node based on its probability evaluation. The final node's polishing state probability is obtained by analyzing the predictions of previous nodes. The total node reward value is then calculated by summing the node reward values. Furthermore, the node reward value can be used to determine whether the polishing state probability meets a preset requirement. If it does, it indicates that burr removal using the current distribution removal parameters is sufficient. If not, the distribution removal parameters are adjusted to change the processing parameters until the final node's polishing state probability meets the preset requirement, thus improving the quality of burr removal processing.

[0077] In summary, the non-destructive burr removal method for square aluminum shells of new energy batteries provided in this application has the following technical effects:

[0078] This application embodiment utilizes an image acquisition device to acquire multi-angle images of the square aluminum casing of the battery, thereby achieving the goal of comprehensively obtaining the surface condition of the aluminum casing and obtaining multi-angle image information of the aluminum casing. Then, image recognition is performed on the multi-angle image information of the aluminum casing to obtain burr identification information, achieving the goal of identifying and determining information such as the type of burr. Furthermore, the burr location information is determined based on the identified image information, providing data for subsequent analysis of the impact of burr location on burr removal processing. Based on the burr identification information, burr shape features and burr size information are obtained. Then, the burr shape features, burr size information, and burr location information are input into a burr analysis model to obtain burr removal parameters. These burr removal parameters are intelligently set to improve processing efficiency. Furthermore, by obtaining the removal equipment parameter information and burr material information, combined with the burr removal parameters and burr shape features, the burr removal operation requirements for each step are determined. Finally, a burr removal strategy is obtained based on the burr removal distribution requirements to remove burrs from the aluminum casing. This achieves the technical effect of intelligent burr removal and improved burr processing efficiency.

[0079] Example 2

[0080] Based on the same inventive concept as the non-destructive removal method for square aluminum shells of new energy batteries in the foregoing embodiments, such as Figure 4 As shown, this application also provides a non-destructive burr removal system for square aluminum shells of new energy batteries, wherein the system includes:

[0081] Multi-angle image acquisition module 11, which is used to acquire multi-angle images of the square aluminum shell of the battery through an image acquisition device, and obtain multi-angle image information of the aluminum shell.

[0082] The burr location information determination module 12 is used to perform image recognition on the multi-angle image information of the aluminum shell, determine burr recognition information, and determine burr location information based on the recognized image information.

[0083] The size information acquisition module 13 is used to obtain burr shape features and burr size information based on the burr identification information.

[0084] The parameter removal module 14 is used to input the burr shape features, burr size information, and burr location information into the burr analysis model to obtain burr removal parameters.

[0085] The burr removal module 15 is used to obtain removal equipment parameter information and burr material information, determine burr removal step requirements based on the removal equipment parameter information, burr material information, burr removal parameters, and burr shape characteristics, and obtain a burr removal strategy based on the burr removal distribution requirements to remove burrs from the aluminum shell.

[0086] Furthermore, the system also includes:

[0087] The learning model acquisition unit is used to obtain a preset burr recognition model, which is a machine learning model obtained by training and testing a training dataset and a test dataset with multiple types of burr identification data.

[0088] A correction preprocessing unit is used to perform noise reduction and correction preprocessing on the multi-angle image information of the aluminum shell.

[0089] The identification information acquisition unit is used to input the pre-processed multi-angle image information of the aluminum shell into the burr recognition model, perform burr recognition processing, and obtain the burr recognition information.

[0090] Furthermore, the system also includes:

[0091] A category information determination unit is used to classify burrs according to the burr shape features and burr size information, and determine the burr category information.

[0092] A contact area determination unit is used to determine the burr contact area based on the burr size information.

[0093] The force information analysis unit is used to determine the force information of the burr based on the burr type information, the burr contact area, and the burr shape characteristics.

[0094] The parameter removal unit is used to perform positional impact analysis based on the burr position information and determine the positional removal parameter requirements.

[0095] The burr removal parameter determination unit is used to determine the burr removal parameters by fusing similar parameter requirements based on the burr force information and the position removal parameter requirements.

[0096] Furthermore, the system also includes:

[0097] A speed range determination unit is used to determine the removal step adjustment range and the grinding wheel speed range based on the removal equipment parameter information.

[0098] A grinding angle information determination unit is used to obtain the burr removal force requirement and grinding angle information based on the burr removal parameters.

[0099] The stress information acquisition unit is used to perform material stress analysis based on the burr material information and burr shape characteristics to obtain burr stress information.

[0100] The removal distribution information determination unit is used to determine the removal step information based on the burr removal force requirement and burr shape characteristics.

[0101] The step-by-step requirement acquisition unit is used to obtain step-by-step removal parameter information based on the removal step information, the removal step adjustment range, and the grinding wheel speed range, and to obtain the burr removal step requirements based on the removal step information and the corresponding step-by-step removal parameter information.

[0102] Furthermore, the system also includes:

[0103] The step-by-step removal requirement determination unit is used to determine the removal requirements for each step based on the removal step information.

[0104] A step information determination unit is used to determine the first rotation speed information and the first step information according to the first step removal requirements;

[0105] The first polishing effect acquisition unit is used to predict the polishing effect based on the first rotation speed information and the first step information to obtain the first step polishing effect, wherein the first step polishing effect includes the shape information of the remaining burrs and the size information of the remaining burrs.

[0106] The second step information acquisition unit is used to determine the second step removal requirements based on the remaining burr shape information and remaining burr size information, and to obtain the second rotation speed information and the second step information.

[0107] The parameter information acquisition unit is used to predict the polishing effect based on the second rotation speed information and the second step information, obtain the second step polishing effect, and continue until the remaining burr size is 0. Then, the first rotation speed information and the first step information are used as the first step removal parameter information, the second rotation speed information and the second step information are used as the second step removal parameter information, and so on, to obtain the removal parameter information for all steps.

[0108] Furthermore, the system also includes:

[0109] The color distribution information determination unit is used to perform color recognition on the burr identification information through the multi-angle image information of the aluminum shell, and determine the burr color distribution information.

[0110] A burr and impurity determination unit is used to determine whether a burr contains impurities based on the burr color distribution information.

[0111] An impurity information determination unit is used to perform doping analysis on the production environment, production equipment, and process flow of the aluminum shell production process when the burr contains impurities, and to determine the impurity information.

[0112] A force influence information determination unit is used to determine the force influence information of the burrs based on the impurity information and the burr color distribution information.

[0113] The model incremental learning unit is used to add the burr force influence information into the burr analysis model for incremental learning. The burr shape features, burr size information, burr location information, and burr force influence information are input into the incrementally learned burr analysis model to obtain the burr removal parameters.

[0114] Furthermore, the system also includes:

[0115] A timing chain construction unit is used to construct a timing chain based on the steps before and after removing the step information, wherein the nodes of the timing chain are in the aluminum shell burr polishing state.

[0116] A prediction model building unit is used to associate the removal parameter information of each step as the external action of the node with the burr grinding state of the aluminum shell, evaluate the burr grinding effect of the removal parameter information of each step as the node reward value, and build a Markov chain prediction model.

[0117] A state probability acquisition unit is used to predict the polishing state probability of each node based on the Markov chain prediction model, and obtain the final polishing state probability of the node.

[0118] A state probability determination unit is used to determine whether the grinding state probability reaches a preset requirement. When it does, the step-by-step removal parameter information is determined.

[0119] A parameter adjustment unit is used to adjust the step-by-step removal parameter information when the target is not met, until the grinding state probability of the final output node reaches the preset requirement.

[0120] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The method and specific examples for non-destructive removal of burrs from the square aluminum shell of a new energy battery in Example 1 are also applicable to the non-destructive removal system for the square aluminum shell of a new energy battery in this embodiment. Through the foregoing detailed description of the method for non-destructive removal of burrs from the square aluminum shell of a new energy battery, those skilled in the art can clearly understand the non-destructive removal system for the square aluminum shell of a new energy battery in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0121] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for non-destructive removal of burrs from the square aluminum shell of a new energy battery, characterized in that, The method includes: Multi-angle image acquisition of the battery's square aluminum casing is performed using an image acquisition device to obtain multi-angle image information of the aluminum casing. Image recognition is performed on the multi-angle image information of the aluminum shell to determine burr identification information, and burr location information is determined based on the identified image information; Based on the burr identification information, the burr shape features and burr size information are obtained; Input the burr shape features, burr size information, and burr location information into the burr analysis model to obtain burr removal parameters; Obtain the removal equipment parameter information and burr material information. Based on the removal equipment parameter information, burr material information, burr removal parameters, and burr shape characteristics, determine the burr removal step requirements. Based on the burr removal step requirements, obtain the burr removal strategy to remove the aluminum shell. The method further includes: By using the multi-angle image information of the aluminum shell, the color recognition information of the burr identification information is performed to determine the color distribution information of the burr. Based on the burr color distribution information, determine whether the burr contains impurities; When burrs contain impurities, doping analysis is performed on the production environment, production equipment, and process flow of the aluminum shell production process to determine the impurity information. Based on the impurity information and the burr color distribution information, determine the burr force influence information; The burr force influence information is added to the burr analysis model for incremental learning. The burr shape features, burr size information, burr location information, and burr force influence information are input into the incrementally learned burr analysis model to obtain the burr removal parameters.

2. The method as described in claim 1, characterized in that, Image recognition is performed on the multi-angle image information of the aluminum shell to determine burr identification information, including: A preset burr recognition model is obtained, which is a machine learning model obtained by training and testing a training dataset and a test dataset with multiple types of burr identification data. The multi-angle image information of the aluminum shell is subjected to noise reduction and bias correction preprocessing. The pre-processed multi-angle image information of the aluminum shell is input into the burr recognition model for burr recognition processing to obtain the burr recognition information.

3. The method as described in claim 1, characterized in that, The burr shape features, burr size information, and burr location information are input into the burr analysis model to obtain burr removal parameters, including: Based on the burr shape characteristics and burr size information, the burrs are classified to determine the burr category information; Based on the burr size information, determine the burr contact area; Based on the burr type information, the burr force information is determined according to the burr contact area and the burr shape characteristics; Based on the burr location information, a location impact analysis is performed to determine the required location removal parameters; Based on the burr force information and the position removal parameter requirements, the parameter requirements are fused to determine the burr removal parameters.

4. The method as described in claim 3, characterized in that, Based on the removal equipment parameter information, burr material information, burr removal parameters, and burr shape characteristics, the step-by-step requirements for burr removal are determined, including: Based on the removal equipment parameter information, determine the removal step adjustment range and the grinding wheel speed range; Based on the burr removal parameters, the burr removal force requirement and grinding angle information are obtained; Based on the burr material information and burr shape characteristics, material stress analysis is performed to obtain burr stress information; Based on the burr removal force requirements and burr shape characteristics, the removal step information is determined; Based on the removal step information, the removal step adjustment range, and the grinding wheel speed range, step removal parameter information is obtained. Based on the removal step information and the corresponding step removal parameter information, the burr removal step requirements are obtained.

5. The method as described in claim 4, characterized in that, Based on the removal step information, the removal step adjustment range, and the grinding wheel speed range, step removal parameter information is obtained, including: Based on the removal step-by-step information, determine the removal requirements for each step; Based on the removal requirements of the first step, determine the first rotation speed information and the first step feed information; Based on the first rotation speed information and the first step forward information, the grinding effect is predicted to obtain the first step grinding effect, wherein the first step grinding effect includes the shape information of the remaining burrs and the size information of the remaining burrs. Based on the shape and size information of the remaining burrs after polishing, the removal requirements for the second step are determined, and the second rotation speed and the second step information are obtained. The polishing effect is predicted based on the second rotation speed information and the second step information to obtain the second polishing effect. When the remaining burr size is 0, the first rotation speed information and the first step information are used as the first removal parameter information, and the second rotation speed information and the second step information are used as the second removal parameter information. This process is repeated to obtain the removal parameter information for all steps.

6. The method as described in claim 5, characterized in that, The method further includes: Based on the steps before and after removing the step information, a time-series chain is constructed, wherein the nodes of the time-series chain are the aluminum shell burr polishing state. The removal parameter information of each step is associated with the external action of the node and the burr grinding state of the aluminum shell. The burr grinding effect of the removal parameter information of each step is evaluated and used as the node reward value to construct a Markov chain prediction model. Based on the Markov chain prediction model, the grinding state probability of each node is predicted to obtain the final grinding state probability of the node. Determine whether the probability of the polishing state meets the preset requirements; if it does, determine the step-by-step removal parameter information. If the target is not met, the step-by-step removal parameters are adjusted until the polishing probability of the final output node reaches the preset requirement.

7. A non-destructive burr removal system for square aluminum shells of new energy batteries, characterized in that, The system is used to implement the non-destructive removal method for square aluminum shells of new energy batteries according to any one of claims 1-6, the system comprising: A multi-angle image acquisition module is used to acquire multi-angle images of the square aluminum shell of the battery through an image acquisition device, thereby obtaining multi-angle image information of the aluminum shell. The burr location information determination module is used to perform image recognition on the multi-angle image information of the aluminum shell, determine burr recognition information, and determine burr location information based on the recognized image information. A size information acquisition module is used to obtain burr shape features and burr size information based on the burr identification information. A parameter removal module is used to input the burr shape features, burr size information, and burr location information into the burr analysis model to obtain burr removal parameters. The burr removal module is used to obtain burr removal equipment parameter information and burr material information, determine burr removal step requirements based on the burr removal equipment parameter information, burr material information, burr removal parameters, and burr shape characteristics, and obtain a burr removal strategy based on the burr removal step requirements to remove the aluminum shell.

Images