Multi-laser cutting method and electronic equipment for lithium battery

Abstract

The present invention provides a multi-laser cutting method, electronic device and storage medium for lithium batteries, and relates to the field of laser cutting. The method comprises: obtaining a sample lithium battery vector set, performing k-means clustering on the sample lithium battery vectors, obtaining a first clustering range and a second clustering range, if the first clustering range and the second clustering range have no intersection, using the sample lithium battery vectors included in the first sample clustering cluster as positive sample data, and the sample lithium battery vectors included in the second clustering cluster as negative sample data, using the positive sample data and the negative sample data to train a preset classification model, obtaining a target classification model, using the target classification model to classify the target vector, and determining the laser type used for the target lithium battery; thereby more accurately obtaining the laser type used for the target lithium battery.

Description

Technical Field

[0001] The present invention relates to the field of lithium batteries, and in particular to a multi-laser cutting method, electronic equipment and storage medium for lithium batteries. Background Art

[0002] In the manufacturing of new energy batteries, laser cutting technology can perform fine cutting on various types of new energy batteries to meet size and shape requirements. The types of new energy batteries include solid-state lithium batteries, lithium phosphate batteries, solid-state lithium phosphate batteries and other lithium batteries.

[0003] Laser cutting is a technology that uses a high-power laser beam to irradiate materials and cut materials through processes such as melting, burning or evaporation. This technology has been widely used in the field of new energy due to its high precision, flexibility and wide applicability.

[0004] At present, two or more lasers are used to cut multiple lithium batteries at the same time. The advantage of cutting with multiple lasers at the same time is that it can improve cutting efficiency and optimize cutting paths. However, when using multiple lasers at the same time, it becomes particularly important to choose which laser to cut the target lithium battery. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is: a multi-laser cutting method for lithium batteries, the method is used to determine the laser type when cutting the target lithium battery, and the method comprises the following steps:

[0006] S100, obtaining a sample lithium battery vector set A = {A1, A2, ..., A i , …, A m}, where the sample lithium battery vector A of the i-th sample lithium battery i The fields include (sample lithium battery centroid, first laser energy, first cutting speed, second laser energy, second cutting speed), i ranges from 1 to m, m is the number of sample lithium battery vectors, the first laser energy is different from the second laser energy, and the first cutting speed is different from the second cutting speed;

[0007] S200, for A1 to A m Perform k-means clustering to obtain a first clustering range and a second clustering range, wherein the first clustering range is obtained based on a first cluster center and a first cluster radius of the first sample cluster, and the second clustering range is obtained based on a second cluster center and a second cluster radius of the second cluster, wherein k=2;

[0008] S300, if the first clustering range and the second clustering range do not intersect, taking the sample lithium battery vectors included in the first sample clustering cluster as positive sample data, and taking the sample lithium battery vectors included in the second clustering cluster as negative sample data;

[0009] S400, training a preset classification model using positive sample data and negative sample data to obtain a target classification model;

[0010] S500, classify the target vector using the target classification model to determine the laser type used for the target lithium battery, wherein the fields of the target vector include (target lithium battery center of mass, third laser energy, third cutting speed, fourth laser energy, fourth cutting speed), the third laser energy is different from the fourth laser energy, and the third cutting speed is different from the fourth cutting speed.

[0011] According to another aspect of the present invention, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the aforementioned method.

[0012] According to yet another aspect of the present invention, an electronic device is provided, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0013] The present invention has at least the following beneficial effects: In summary, a set of sample lithium battery vectors is obtained, and k-means clustering is performed on the sample lithium battery vectors to obtain a first clustering range and a second clustering range. If the first clustering range and the second clustering range have no intersection, the sample lithium battery vectors contained in the first sample clustering cluster are used as positive sample data, and the sample lithium battery vectors contained in the second clustering cluster are used as negative sample data. The positive sample data and the negative sample data are used to train a preset classification model to obtain a target classification model, and the target classification model is used to classify the target vector to determine the type of laser used for the target lithium battery. The present application trains a preset classification model using sample lithium battery vectors to obtain a target classification model, classifies the target vector by the target classification model, and determines the laser type of the target vector by clustering, so as to more accurately obtain the type of laser used by the target lithium battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A flow chart of a multi-laser cutting method for lithium batteries provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] The embodiment of the present invention provides a multi-laser cutting method for lithium batteries, the method is used to determine the laser type when cutting a target lithium battery, such as Figure 1 As shown, the method comprises the following steps:

[0018] S100, obtaining a sample lithium battery vector set A = {A1, A2, ..., A i , …, A m}, where the i-th sample lithium battery vector A i The fields include (sample lithium battery centroid, first laser energy, first cutting speed, second laser energy, second cutting speed), i ranges from 1 to m, m is the number of sample lithium battery vectors, the first laser energy is different from the second laser energy, and the first cutting speed is different from the second cutting speed.

[0019] Specifically, the sample lithium battery can be a historical lithium battery that has been laser cut, or a lithium battery to be cut that needs laser cutting. Further, those skilled in the art know that any method of obtaining the centroid of a sample lithium battery in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0020] Specifically, the sample lithium battery vector A i (Sample lithium battery centroid value, first laser energy value, first cutting speed value, second laser energy value, second cutting speed value) has been normalized.

[0021] Specifically, the first laser energy is the first preset laser energy for cutting the sample lithium battery, and the first cutting speed is the first preset speed for cutting the sample lithium battery; the second laser energy is the second preset laser energy for cutting the sample lithium battery, and the second cutting speed is the second preset speed for cutting the sample lithium battery; it can be understood that when the sample lithium battery is laser cut, the local temperature of the sample lithium battery will rise after absorbing the laser energy. At this time, the first laser energy will be reduced to the second laser energy, and the first cutting speed will be reduced to the second cutting speed, thereby reducing the impact of temperature on the sample lithium battery.

[0022] Specifically, in one embodiment of the present invention, the sample lithium battery is a solid-state lithium battery, a lithium phosphate battery, or a solid-state lithium phosphate battery.

[0023] S200, for A1 to A m Perform k-means clustering to obtain a first clustering range and a second clustering range, wherein the first clustering range is obtained based on a first cluster center and a first cluster radius of a first sample cluster, and the second clustering range is obtained based on a second cluster center and a second cluster radius of a second cluster, wherein k=2.

[0024] Specifically, the first gathering range is a circular area with the center of the first cluster as the center and the radius of the first cluster as the radius; the second gathering range is a circular area with the center of the second cluster as the center and the radius of the second cluster as the radius.

[0025] Specifically, for A1 to A m Perform k-means clustering, k=2, to obtain a first cluster cluster and a second cluster cluster, obtain a first cluster center and a first cluster radius based on the first cluster cluster, and obtain a second cluster center and a second cluster radius based on the second cluster cluster, wherein the first cluster center represents the average position of all data points in the first cluster cluster, and the second cluster center represents the average position of all data points in the second cluster cluster.

[0026] Specifically, those skilled in the art know that any method of obtaining the cluster center of a cluster in the prior art falls within the protection scope of the present invention, for example, the first cluster center is obtained by calculating the average value of all sample lithium battery vectors in each field in the first cluster.

[0027] Among them, the first radius is used to measure the size of the first cluster, and the second radius is used to measure the size of the second cluster. Specifically, those skilled in the art know that any method for obtaining the radius of a cluster in the prior art belongs to the protection scope of the present invention. For example, the first radius is obtained by using the maximum distance method, that is, calculating the distance of the point farthest from the center of mass in the first cluster as the first radius.

[0028] S300: If the first clustering range and the second clustering range do not intersect, the sample lithium battery vectors included in the first sample clustering cluster are used as positive sample data, and the sample lithium battery vectors included in the second clustering cluster are used as negative sample data.

[0029] S400, using positive sample data and negative sample data to train a preset classification model to obtain a target classification model.

[0030] Specifically, those skilled in the art know that any method in the prior art for training using positive sample data and negative sample data falls within the protection scope of the present invention and will not be described in detail here.

[0031] S500, classify the target vector using the target classification model to determine the laser type used for the target lithium battery, wherein the fields of the target vector include (target lithium battery center of mass, third laser energy, third cutting speed, fourth laser energy, fourth cutting speed), the third laser energy is different from the fourth laser energy, and the third cutting speed is different from the fourth cutting speed.

[0032] Specifically, the target vector (target lithium battery center of mass value, third laser energy value, third cutting speed value, fourth laser energy value, fourth cutting speed value) has been normalized.

[0033] Specifically, the target vector is a vector corresponding to a target lithium battery. In one embodiment of the present invention, the type of the target lithium battery is a solid-state lithium battery, a lithium phosphate battery, or a solid-state lithium phosphate battery.

[0034] Specifically, the third laser energy is the third preset laser energy for cutting the target lithium battery, and the third cutting speed is the third preset speed for cutting the target lithium battery; the fourth laser energy is the fourth preset laser energy for cutting the target lithium battery, and the fourth cutting speed is the fourth preset speed for cutting the target lithium battery; it can be understood that the fourth laser energy is the laser energy of the target lithium battery after the laser energy is reduced after the temperature rises, and the fourth cutting speed is the cutting speed of the target lithium battery after the speed is reduced after the temperature rises.

[0035] In summary, a set of sample lithium battery vectors is obtained, and k-means clustering is performed on the sample lithium battery vectors to obtain a first clustering range and a second clustering range. If the first clustering range and the second clustering range have no intersection, the sample lithium battery vectors contained in the first sample clustering cluster are used as positive sample data, and the sample lithium battery vectors contained in the second clustering cluster are used as negative sample data. The positive sample data and the negative sample data are used to train a preset classification model to obtain a target classification model, and the target classification model is used to classify the target vector to determine the type of laser used for the target lithium battery. The present application trains a preset classification model using sample lithium battery vectors to obtain a target classification model, classifies the target vector by the target classification model, and determines the laser type of the target vector by clustering, so as to more accurately obtain the type of laser used by the target lithium battery.

[0036] Furthermore, in the present invention, k=2, that is, the sample lithium battery vectors are divided into two categories for training, that is, the laser type in the present invention is 2 types of laser types, and the target vector is classified into the first type of laser type or the second type of laser type.

[0037] Furthermore, S300 further includes, if the first aggregation range and the second aggregation range have an intersection, executing the following steps:

[0038] S001, obtain a preset clustering information list B = {B1, B2, ..., B j , …, B n}, the jth preset clustering information B j =(FB j , S.B. j ), FB j is the jth preset neighborhood radius, SB j is the jth preset minimum number of points, the value range of j is 1 to n, and n is the number of preset clustering information.

[0039] Specifically, the preset clustering information can be determined according to actual needs. In one embodiment of the present invention, the clustering information can be preset based on historical data. In one embodiment of the present invention, two lasers are located at diagonal positions. By taking the laser as the center point, the radius is gradually expanded. In the process of gradually expanding the radius, the (preset neighborhood radius, minimum number of points) of each radius of the historical data is obtained as the preset clustering information, thereby obtaining a preset clustering information list, so that A1 to A m When clustering is performed using preset clustering information, clustering is gradually performed from a position close to the laser.

[0040] S002, the initial sample lithium battery vector is based on B i Perform unsupervised clustering to obtain the intermediate cluster C g , where the initial sample lithium battery vector is initialized to A1 to A m , B i Initialize to B1, C g Initialized to C1.

[0041] Specifically, S002 also includes: based on FB j and SB j , the DBSCAN clustering algorithm is used to perform unsupervised clustering on the initial sample lithium battery vector.

[0042] S003, get A1 to A m The sample lithium battery vectors that are not in the middle cluster are marked as middle vectors. m In the figure, the sample lithium battery vectors that are not clustered into the intermediate clusters are marked as intermediate vectors.

[0043] S004: If the number of intermediate vectors is less than the preset number threshold, execute S005; otherwise, mark the intermediate vector as the initial sample lithium battery vector, B j =B j+1 , C g =C g+1 , execute S002.

[0044] Specifically, the preset number threshold can be determined according to actual needs. It can be understood that if the number of intermediate vectors is less than the preset number threshold, it is considered that there are very few vectors that have not been clustered into intermediate clusters and no clustering is required; if the number of intermediate vectors is greater than the preset number threshold, it is considered that there are still many vectors that have not been clustered into clusters, so B j+1 Assign to B j , C g+1 Assign to Cg , continue clustering.

[0045] S005, obtain the intermediate cluster list C = {C1, C2, ..., C g , …, C z}, the value of g ranges from 1 to z, and z is the number of intermediate clusters.

[0046] Specifically, z is the number of intermediate clusters, which is also the number of times S001-S004 is executed.

[0047] S006, dividing the intermediate cluster list into positive sample data and negative sample data based on the distance between the intermediate cluster centers of the intermediate clusters and the number of sample lithium battery vectors contained in the intermediate clusters.

[0048] Specifically, in one embodiment of the present invention, S006 further includes: taking sample lithium battery vectors that are not in the middle cluster as positive sample data.

[0049] Specifically, in another embodiment of the present invention, S006 further includes: taking sample lithium battery vectors that are not in the middle cluster as negative sample data.

[0050] In summary, if there is an intersection between the first clustering range and the second clustering range, obtain a preset clustering information list, perform unsupervised clustering on the initial sample lithium battery vector based on the preset clustering information, obtain intermediate clustering clusters, obtain sample lithium battery vectors that are not in the intermediate clustering clusters in the sample lithium battery vector set and mark them as intermediate vectors. If the number of intermediate vectors is not less than the preset number threshold, continue clustering. If the number of intermediate vectors is less than the preset number threshold, obtain an intermediate clustering cluster list, and divide the intermediate clustering cluster list into positive sample data and negative sample data based on the distance between the intermediate cluster centers of the intermediate clusters and the number of sample lithium battery vectors contained in the intermediate clustering clusters. By performing unsupervised clustering in a loop, cluster the sample lithium battery vector set into multiple intermediate clustering clusters, and then divide the positive sample data and negative sample data, thereby avoiding the intersection problem caused by k-means clustering k=2, and dividing the sample lithium battery vector set more accurately.

[0051] Specifically, S006 also includes:

[0052] S061, obtain the intermediate cluster C gThe center of the middle cluster D g , thereby obtaining the intermediate cluster center list D = {D1, D2, ..., D g , …, D z}.

[0053] S062, for D1 to D z Perform k-means clustering to obtain a first candidate cluster and a second candidate cluster, and obtain the number E1 of sample lithium battery vectors included in the first candidate cluster and the number E2 of sample lithium battery vectors included in the second candidate cluster, where k=2.

[0054] Specifically, D1 to D z Divided into two categories.

[0055] S063: If |E1-E2|<preset quantity difference threshold E0, the sample lithium battery vectors included in the first candidate cluster are used as positive sample data, and the sample lithium battery vectors included in the second candidate cluster are used as negative sample data.

[0056] Specifically, in order to ensure that the data amounts of the positive sample data and the negative sample data are substantially equal, that is, the number of target objects processed by the two lasers is substantially the same, the difference between E1 and E2 is made smaller than a preset quantity difference threshold.

[0057] S064, if |E1-E2|≥E0, perform manual adjustment to obtain the adjusted first candidate cluster and the adjusted second candidate cluster, and use the sample lithium battery vector included in the adjusted first candidate cluster as positive sample data, and use the sample lithium battery vector included in the adjusted second candidate cluster as negative sample data.

[0058] Specifically, if the difference between E1 and E2 is not less than the preset quantity difference threshold, manual adjustment is performed, and the sample lithium battery vectors included in the adjusted first candidate cluster are used as positive sample data, and the sample lithium battery vectors included in the adjusted second candidate cluster are used as negative sample data.

[0059] In summary, the intermediate cluster center of the intermediate cluster is obtained, thereby obtaining the intermediate cluster center list, clustering the intermediate cluster centers, obtaining the first candidate cluster cluster and the second candidate cluster cluster, and obtaining the number of sample lithium battery vectors contained in the first candidate cluster cluster and the number of sample lithium battery vectors contained in the second candidate cluster cluster. If the difference between the number of sample lithium battery vectors contained in the first candidate cluster cluster and the number of sample lithium battery vectors contained in the second candidate cluster cluster meets the preset number difference threshold, the sample lithium battery vector contained in the first candidate cluster cluster is used as the positive sample data, and the sample lithium battery vector contained in the second candidate cluster cluster is used as the negative sample data. Negative sample data: if the difference between the number of sample lithium battery vectors included in the first candidate clustering cluster and the number of sample lithium battery vectors included in the second candidate clustering cluster does not meet the preset quantity difference threshold, manual adjustment is performed to obtain the adjusted first candidate clustering cluster and the adjusted second candidate clustering cluster, and the sample lithium battery vectors included in the adjusted first candidate clustering cluster are used as positive sample data, and the sample lithium battery vectors included in the adjusted second candidate clustering cluster are used as negative sample data. The present invention obtains positive sample data and negative sample data based on the distance between the centers of the intermediate clusters and the number of sample lithium battery vectors included in the intermediate clusters.

[0060] Furthermore, the present invention also includes: if the value of the field (fourth laser energy, fourth cutting speed) of the target vector is empty, executing the following steps:

[0061] S010, obtain the historical vector set F = {F1, F2, ..., F r , …, F s}, F r is the rth history vector, the fields of which include: the centroid of the historical object, the number of nodes of the cutting path of the historical object, and the total distance of the cutting path of the historical object. The value range of r is 1 to s, where s is the number of history vectors.

[0062] S020, obtaining a designated vector of the target lithium battery, wherein the fields of the designated vector include: the centroid of the target lithium battery, the number of nodes of the cutting path of the target lithium battery, and the total distance of the cutting path of the target lithium battery.

[0063] S030, obtain the specified vector and historical vector F r The similarity G r , thus obtaining the similarity list G = {G1, G2, ..., G r , …, G s}.

[0064] Specifically, the field values ​​of the historical vector and the designated vector are normalized, and similarity is obtained by calculation based on the normalized field values ​​of the historical vector and the normalized designated vector.

[0065] Specifically, those skilled in the art know that any method for obtaining similarity in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0066] S040, obtain G0=max{G1, G2, ..., G r , …, G s} and the history vector G0 corresponding to F0, and the laser type used by the historical object corresponding to G0 is determined as the laser type of the target lithium battery.

[0067] In summary, if the value of the field (fourth laser energy, fourth cutting speed) of the target vector is empty, obtain the historical vector set, obtain the designated vector of the target lithium battery, obtain the similarity between the designated vector and the historical vector, obtain the historical vector corresponding to the maximum similarity, and determine the laser type used by the historical vector as the laser type of the target lithium battery, so that when the value of the field (fourth laser energy, fourth cutting speed) of the target vector is empty, the laser type of the target lithium battery can be quickly obtained.

[0068] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0069] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0070] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A multi-laser cutting method for lithium batteries, the method is used to determine the laser type when cutting a target lithium battery, characterized in that: The method comprises the following steps: S100, obtain a sample lithium battery vector set A={A1, A2, …, A i , …, A m }, where the sample lithium battery vector A of the i-th sample lithium battery i The fields include: sample lithium battery centroid, first laser energy, first cutting speed, second laser energy and second cutting speed, i ranges from 1 to m, m is the number of sample lithium battery vectors, the first laser energy is different from the second laser energy, and the first cutting speed is different from the second cutting speed; S200, for A1 to A m Perform k-means clustering to obtain a first clustering range and a second clustering range, wherein the first clustering range is obtained based on a first cluster center and a first cluster radius of the first sample cluster, and the second clustering range is obtained based on a second cluster center and a second cluster radius of the second cluster, wherein k=2; S300, if the first clustering range and the second clustering range do not intersect, taking the sample lithium battery vectors included in the first sample clustering cluster as positive sample data, and taking the sample lithium battery vectors included in the second clustering cluster as negative sample data; S400, training a preset classification model using positive sample data and negative sample data to obtain a target classification model; S500, using the target classification model to classify the target vector, determine the type of laser used for the target lithium battery, wherein the fields of the target vector include: the center of mass of the target lithium battery, the third laser energy, the third cutting speed, the fourth laser energy and the fourth cutting speed, the third laser energy is different from the fourth laser energy, and the third cutting speed is different from the fourth cutting speed.

2. The multi-laser cutting method for lithium batteries according to claim 1, characterized in that: S300 further includes, if the first aggregation range and the second aggregation range have an intersection, executing the following steps: S001, obtain a preset clustering information list B = {B1, B2, ..., B j , …, B n }, the jth preset clustering information B j =(FB j , S.B. j ), FB j is the jth preset neighborhood radius, SB j is the jth preset minimum number of points, the value range of j is 1 to n, and n is the number of preset clustering information; S002, the initial sample lithium battery vector is based on B j Perform unsupervised clustering to obtain the intermediate cluster C g , where the initial sample lithium battery vector is initialized to A1 to A m , B j Initialize to B1, C g Initialize to C1; S003, get A1 to A m The sample lithium battery vectors that are not in the middle cluster are marked as middle vectors; S004: If the number of intermediate vectors is less than the preset number threshold, execute S005; otherwise, mark the intermediate vector as the initial sample lithium battery vector, B j =B j+1 , C g =C g+1 , execute S002; S005, obtain the intermediate cluster list C = {C1, C2, ..., C g , …, C z }, the value of g ranges from 1 to z, where z is the number of intermediate clusters; S006, dividing the intermediate cluster list into positive sample data and negative sample data based on the distance between the intermediate cluster centers of the intermediate clusters and the number of sample lithium battery vectors contained in the intermediate clusters.

3. The multi-laser cutting method for lithium batteries according to claim 2, characterized in that: S006 also includes: S061, obtain the intermediate cluster C g The center of the middle cluster D g , thereby obtaining the intermediate cluster center list D = {D1, D2, ..., D g , …, D z }; S062, for D1 to D z Perform k-means clustering to obtain a first candidate cluster and a second candidate cluster, and obtain the number E1 of sample lithium battery vectors included in the first candidate cluster and the number E2 of sample lithium battery vectors included in the second candidate cluster, where k=2; S063, if |E1-E2|<preset quantity difference threshold E0, the sample lithium battery vectors included in the first candidate cluster are used as positive sample data, and the sample lithium battery vectors included in the second candidate cluster are used as negative sample data; S064, if |E1-E2|≥E0, perform manual adjustment to obtain the adjusted first candidate cluster and the adjusted second candidate cluster, and use the sample lithium battery vector included in the adjusted first candidate cluster as positive sample data, and use the sample lithium battery vector included in the adjusted second candidate cluster as negative sample data.

4. The multi-laser cutting method for lithium batteries according to claim 2, characterized in that: S006 also includes: taking the sample lithium battery vectors that are not in the middle cluster as positive sample data.

5. The multi-laser cutting method for lithium batteries according to claim 2, characterized in that: S006 also includes: taking the sample lithium battery vectors that are not in the middle cluster as negative sample data.

6. The multi-laser cutting method for lithium batteries according to claim 2, characterized in that: S002 also includes: Based on FB j and SB j , the DBSCAN clustering algorithm is used to perform unsupervised clustering on the initial sample lithium battery vector.

7. The multi-laser cutting method for lithium batteries according to claim 1, characterized in that: The first gathering range is a circular area with the center of the first cluster as the center and the radius of the first cluster as the radius.

8. The multi-laser cutting method for lithium batteries according to claim 1, characterized in that: The second gathering range is a circular area with the center of the second cluster as the center and the radius of the second cluster as the radius.

9. The multi-laser cutting method for lithium batteries according to claim 1, characterized in that: After S500, the method further includes: if the values ​​of the fourth laser energy and the fourth cutting speed fields of the target vector are both empty, executing the following steps: S010, obtain the historical vector set F={F1, F2, ..., F r , …, F s }, F r is the rth history vector, the fields of which include: the centroid of the history object, the number of nodes of the cutting path of the history object, and the total distance of the cutting path of the history object. The value range of r is 1 to s, where s is the number of history vectors; S020, obtaining a designated vector of a target lithium battery, wherein the fields of the designated vector include: a centroid of the target lithium battery, a number of nodes of a cutting path of the target lithium battery, and a total distance of the cutting path of the target lithium battery; S030, obtain the specified vector and historical vector F r The similarity G r , thus obtaining the similarity list G={G1, G2, …, G r , …, G s }; S040, obtain G0=max{G1, G2, ..., G r , …, G s } and the history vector G0 corresponding to F0, and the laser type used by the historical object corresponding to G0 is determined as the laser type of the target lithium battery.

10. An electronic device, characterized in that: A processor is included for executing the multi-laser cutting method for lithium batteries as described in claim 9.

Images