Battery welding quality detection method, device and electronic equipment
By calculating the Mahastellar distance of the battery and updating the threshold, the problem of difficult battery welding quality in the prior art is solved, and high-accurate welding quality detection is achieved, and the battery pass rate is improved.
Patent Information
- Application Number
- CN202410940719.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-07-15
AI Technical Summary
The prior art is difficult to detect the welding quality of the battery, resulting in unqualified welding of batteries may be misjudged or misjudged, affecting the overall performance and reliability of the battery.
By calculating the Mahastellar distance of the battery to be tested and testing the Mahastellar distance threshold of multiple sample batteries that pass the welding quality, the welding quality is avoided, destructive detection is reduced, and the detection is improved by updating the Mahastellar distance threshold. accuracy.
Accurate detection of battery welding quality is achieved, the error judgment and misjudgment rate is reduced, and the battery pass rate and detection accuracy are improved.
Smart Images

Figure CN118455829B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of battery manufacturing, and specifically, to a battery welding quality detection method, device and electronic equipment. Background Art
[0002] Battery welding is a key technology in the battery manufacturing process. It is mainly used to firmly connect the various components of the battery (such as tabs, leads, terminals, sealing pins, etc.) together to ensure that the electrical connection inside the battery is stable and reliable.
[0003] In related technologies, visual inspection equipment (such as a CCD camera, where CCD stands for Charge-Coupled Device) can be used to inspect battery quality. However, this only checks the battery's external quality and is difficult to verify the quality of its welds. Summary of the Invention
[0004] The purpose of the embodiments of the present application is to provide a battery welding quality detection method, device and electronic equipment for detecting the welding quality of a battery.
[0005] In a first aspect, an embodiment of the present application provides a battery welding quality detection method, the method comprising: determining a Mahalanobis distance to be measured corresponding to the battery to be tested based on welding parameters corresponding to the battery to be tested and a Mahalanobis distance relationship; detecting the welding quality of the battery to be tested based on the Mahalanobis distance to be measured and a Mahalanobis distance threshold; the Mahalanobis distance threshold is obtained by respectively obtaining the welding parameters corresponding to a plurality of sample batteries that have passed the welding quality detection.
[0006] In this implementation, the weld quality of a battery under test can be tested based on the Mahalanobis distance corresponding to the battery under test and a Mahalanobis distance threshold derived from the welding parameters of multiple sample batteries. This solves the difficulty in testing battery weld quality, a problem that exists in related technologies. Furthermore, the safety interval of the Mahalanobis distance is determined by the characteristics of its distribution, thus improving the accuracy that may be low due to human error.
[0007] Furthermore, since the present implementation detects the welding quality of the battery to be tested based on the welding parameters of the battery to be tested, destructive testing is avoided and costs are reduced.
[0008] In addition, this implementation uses welding parameters of multiple sample batteries that have passed welding quality inspection to determine the Mahalanobis distance threshold. Since there are many sample batteries that have passed welding quality inspection, the number of samples is large, which facilitates the determination of the Mahalanobis distance threshold.
[0009] Optionally, after detecting the welding quality of the battery to be tested based on the Mahalanobis distance to be tested and the Mahalanobis distance threshold, the method further includes: updating the Mahalanobis distance threshold if a condition for updating the Mahalanobis distance threshold is satisfied; and detecting the welding quality of subsequent batteries based on the updated Mahalanobis distance threshold. In this way, the Mahalanobis distance threshold can be updated in a timely manner based on the condition for updating the Mahalanobis distance threshold during the process of detecting the welding quality of multiple batteries to be tested, thereby improving detection accuracy.
[0010] Optionally, the updating condition for the Mahalanobis distance threshold includes at least one of the following: the number of batteries with qualified welding quality that have been tested exceeds a preset number threshold, the number of times the Mahalanobis distance threshold has been used exceeds a preset number threshold, the quality inspection equipment is shut down, the type of battery to be tested has changed, or the configured welding parameters have changed. In this way, the Mahalanobis distance threshold can be updated based on the conditions met in actual situations.
[0011] Optionally, before detecting the welding quality of the battery to be tested based on the Mahalanobis distance to be tested and the Mahalanobis distance threshold, the method further includes: determining, for each of the multiple sample batteries, a Mahalanobis distance corresponding to the sample battery based on the welding parameters of the sample battery and the Mahalanobis distance relationship; and determining the Mahalanobis distance threshold based on the Mahalanobis distances corresponding to the multiple sample batteries. This improves detection accuracy by relieving inaccurate detection caused by large variations in welding parameters.
[0012] Optionally, the welding parameters of the sample battery include first and second welding parameters; the fluctuation range of the values of the first welding parameters is greater than the fluctuation range of the values of the second welding parameters. Thus, determining the Mahalanobis distance corresponding to each sample battery in the plurality of sample batteries based on the welding parameters of the sample battery and the Mahalanobis distance relationship includes: for each sample battery in the plurality of sample batteries, substituting the residual of the moving average value of the first welding parameters and the second welding parameters for the sample battery into a Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery. Thus, for first welding parameters with larger fluctuation ranges, the Mahalanobis distance of the sample battery can be calculated using the residual of the moving average value and the second welding parameters. This reduces the probability of an inaccurate Mahalanobis distance threshold value due to the larger fluctuation range of the first welding parameters, thereby improving the accuracy of welding quality testing of the tested battery.
[0013] Optionally, the sample battery comprises a lithium-ion battery obtained by ultrasonic welding; the first type of welding parameter comprises welding power. Thus, for each sample battery among the plurality of sample batteries, substituting the residual of the moving average value corresponding to the first type of welding parameter and the second type of welding parameter for the sample battery into a Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery includes: for each sample battery among the plurality of sample batteries, substituting the residual of the moving average value corresponding to the welding power of the sample battery and the second type of welding parameter for the sample battery into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery. In this way, the Mahalanobis distance threshold corresponding to the sample battery can be determined based on the residual of the moving average value of the welding power and other welding parameters, thereby improving the accuracy of detecting the welding quality of the battery to be tested.
[0014] Optionally, detecting the welding quality of the battery under test based on the measured Mahalanobis distance and the Mahalanobis distance threshold includes: if the measured Mahalanobis distance is greater than a preset multiple of the Mahalanobis distance threshold, determining that the welding quality of the battery under test is unqualified; and / or if the measured Mahalanobis distance is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery under test is greater than a power residual threshold, determining that the welding quality of the battery under test is unqualified; the power residual threshold is obtained by the residual of the moving average corresponding to the welding power of the multiple sample batteries; and / or if the measured Mahalanobis distance is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery under test is less than the power residual threshold, determining that the welding quality of the battery under test is qualified; and / or if the measured Mahalanobis distance is less than the Mahalanobis distance threshold, determining that the welding quality of the battery under test is qualified. In this way, the welding quality of lithium-ion batteries obtained by ultrasonic welding can be determined, reducing the probability of false positives and improving detection accuracy.
[0015] Optionally, before determining the Mahalanobis distance to be measured corresponding to the battery to be tested based on the welding parameters corresponding to the battery to be tested and the Mahalanobis distance relationship, the method further includes: obtaining multiple historical welding parameters and historical welding quality test results corresponding to batteries whose welding quality has been tested; and determining multiple welding parameters for the battery to be tested based on the degree of correlation between the multiple historical welding parameters and the historical welding quality test results. In this way, multiple welding parameters used to detect the welding quality of the battery to be tested can be determined based on historical data. Because these multiple welding parameters have a high degree of correlation with the welding quality test results, the probability of misjudgment and missed judgment can be reduced, thereby improving the accuracy of detecting the welding quality of the battery to be tested.
[0016] Optionally, determining the multiple welding parameters of the battery under test based on the correlation between the multiple historical welding parameters and the historical welding quality test results includes: calculating the Spearman rank correlation coefficients between the multiple historical welding parameters and the historical welding quality test results; and determining the multiple historical welding parameters corresponding to the multiple Spearman rank correlation coefficients that meet preset requirements as the multiple welding parameters of the battery under test. In this way, the multiple welding parameters of the battery under test can be determined using the Spearman rank correlation coefficient, thereby improving the accuracy of welding quality testing of the battery under test to a certain extent.
[0017] Optionally, the method further includes: if the number of batteries that have continuously failed the welding quality test exceeds a preset abnormal number threshold, determining an abnormal welding parameter based on the changing trend of each of the multiple welding parameters; and determining the abnormal cause of the batteries that have continuously failed the welding quality test based on the abnormal welding parameter. In this way, the cause of the abnormality can be determined based on the test results, and feedback can be provided to the welding equipment, allowing the welding equipment to detect the abnormality in a timely manner, thereby improving the battery qualification rate.
[0018] Optionally, the method further includes: if it is determined that the welding quality of the battery under test is unqualified, retesting the welding quality of the battery under test; and if it is determined that the number of times the welding quality of the battery under test is unqualified reaches a threshold number of times, determining that the battery under test is defective. In this way, multiple tests can be performed when the welding quality of the battery under test is unqualified, thereby reducing the false positive rate and improving the accuracy of the test.
[0019] In a second aspect, embodiments of the present application provide a battery welding quality testing device, comprising: a determination module for determining a Mahalanobis distance corresponding to the battery under test based on the welding parameters of the battery under test and a Mahalanobis distance relationship; and a detection module for detecting the welding quality of the battery under test based on the Mahalanobis distance and a Mahalanobis distance threshold; the Mahalanobis distance threshold being determined by the welding parameters corresponding to multiple sample batteries that have passed the welding quality test. This allows for relatively accurate detection of battery welding quality.
[0020] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect above are executed.
[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are executed.
[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, runs the method described in the first aspect.
[0023] Other features and advantages of the present application will be described in the following description and, in part, will become apparent from the description or be understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.
[0025] Figure 1 A flow chart of a battery welding quality detection method provided in an embodiment of the present application;
[0026] Figure 2 A data graph corresponding to a Spearman rank correlation coefficient provided in an embodiment of the present application;
[0027] Figure 3 A Mahalanobis distance data distribution diagram corresponding to a plurality of batteries to be tested provided in an embodiment of the present application;
[0028] Figure 4 A structural block diagram of a battery welding quality detection device provided in an embodiment of the present application;
[0029] Figure 5 A schematic structural diagram of an electronic device for performing a battery welding quality detection method provided in an embodiment of the present application. DETAILED DESCRIPTION
[0030] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.
[0031] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.
[0032] It should be noted that, unless there is any conflict, the embodiments in this application or the technical features in the embodiments may be combined.
[0033] In the related art, there is a problem that the welding quality of batteries is difficult to detect; in order to solve this problem, the present application provides a battery welding quality detection method, device and electronic equipment; further, the welding quality of the battery to be tested can be determined by the welding parameters of the battery to be tested.
[0034] It should be noted that the battery welding quality inspection method provided in this application can be applied to quality inspection equipment, which may include, for example, a tablet computer, a desktop computer, etc., or a server, a server cluster or a cloud platform, etc.
[0035] Furthermore, the present application can be used to detect batteries obtained by ultrasonic welding, and can also be used to detect batteries obtained by laser welding, etc.
[0036] The defects existing in the solutions in the above-mentioned related technologies are the results obtained by the inventors after practice and careful research. Therefore, the process of discovering the above-mentioned problems and the solutions proposed in the embodiments of the present invention below for the above-mentioned problems should all be the contributions made by the inventors to the present invention during the process of the invention.
[0037] Please refer to Figure 1 , which shows a flow chart of a battery welding quality detection method provided by an embodiment of the present application. Figure 1 As shown, the battery welding quality detection method includes the following steps 101 to 102.
[0038] Step 101, determining a Mahalanobis distance to be measured corresponding to the battery to be tested based on welding parameters corresponding to the battery to be tested and a Mahalanobis distance relationship;
[0039] The battery to be tested is also the battery whose welding quality is to be tested.
[0040] The above-mentioned welding parameters may include a variety of welding parameters, which may include, for example, welding energy, welding power, welding time, welding pressure, welding amplitude, etc.
[0041] The above Mahalanobis distance relationship can be represented by the Mahalanobis distance calculation formula, which is ;in, Characterize Mahalanobis distance; An index that characterizes the battery under test; Characterize the numerical values corresponding to various welding parameters; Characterize the average values corresponding to various welding parameters; Represents the covariance matrix.
[0042] Therefore, after obtaining the various welding parameters corresponding to the battery to be tested, the quality inspection equipment can substitute the numerical values corresponding to the various welding parameters into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the battery to be tested.
[0043] Step 102 : detecting the welding quality of the battery to be tested according to the Mahalanobis distance to be tested and a Mahalanobis distance threshold; the Mahalanobis distance threshold is obtained by respectively obtaining welding parameters corresponding to a plurality of sample batteries that have passed the welding quality test.
[0044] In some application scenarios, the quality inspection equipment can obtain the welding parameters of multiple sample batteries that have passed the welding quality inspection. The quality inspection equipment can then calculate the Mahalanobis distance corresponding to each sample battery based on the welding parameters of the sample battery and the Mahalanobis distance calculation formula. This calculation process is similar to the above-mentioned process for calculating the Mahalanobis distance of the battery under test and is not further described here.
[0045] Furthermore, the quality inspection equipment can determine the Mahalanobis distance threshold based on the Mahalanobis distances corresponding to the multiple sample batteries. In some application scenarios, the above Mahalanobis distance threshold can be the Mahalanobis distance percentile, which can be calculated according to the Mahalanobis distance percentile formula: Calculate. Among them, Characterize the mean Mahalanobis distance of multiple sample batteries; Characterize the standard deviation of the Mahalanobis distance of multiple sample batteries; Characterizes the quantiles of the standard normal distribution.
[0046] In some application scenarios, the quality inspection equipment can detect the welding quality of the battery under test based on the relationship between the measured Mahalanobis distance and the Mahalanobis distance threshold. For example, if the measured Mahalanobis distance is less than the Mahalanobis distance threshold, the welding quality of the battery under test is determined to be qualified.
[0047] In this implementation, the weld quality of a battery under test can be tested based on the Mahalanobis distance corresponding to the battery under test and a Mahalanobis distance threshold derived from the welding parameters of multiple sample batteries. This solves the difficulty in testing battery weld quality, a problem that exists in related technologies. Furthermore, the safety interval of the Mahalanobis distance (i.e., the Mahalanobis distance threshold) is determined based on the characteristics of its distribution, thus improving the accuracy that can be reduced due to human error.
[0048] Furthermore, since the present implementation detects the welding quality of the battery to be tested based on the welding parameters of the battery to be tested, destructive testing is avoided and costs are reduced.
[0049] In addition, this implementation uses welding parameters of multiple sample batteries that have passed welding quality inspection to determine the Mahalanobis distance threshold. Since there are many sample batteries that have passed welding quality inspection, the number of samples is large, which facilitates the determination of the Mahalanobis distance threshold.
[0050] In some optional implementations, after step 102, the method further includes: first, if an update condition of the Mahalanobis distance threshold is met, updating the Mahalanobis distance threshold.
[0051] In some optional implementations, the update condition of the Mahalanobis distance threshold includes at least one of the following: the number of batteries with qualified welding quality is greater than a preset number threshold, the number of times the Mahalanobis distance threshold is used is greater than a preset number threshold, the quality inspection equipment is shut down, the type of battery to be tested changes, and the configured welding parameters change.
[0052] It should be noted that quality inspection equipment may be shut down when abnormal conditions occur or maintenance is required.
[0053] Therefore, if the quality inspection device detects that any of the above update conditions are met, the Mahalanobis distance threshold can be updated based on the welding parameters corresponding to multiple batteries that passed the welding quality test. Here, the multiple batteries that passed the welding quality test can be all batteries tested before the update condition is met, or they can be a portion of the batteries. For example, after the quality inspection device inspects 202 batteries to be tested, it determines that the welding quality of 200 batteries is qualified. In this case, if the update condition for the Mahalanobis distance threshold is met, the Mahalanobis distance threshold can be updated based on the welding parameters corresponding to these 200 batteries that passed the welding quality test, or based on the welding parameters corresponding to 190 batteries that passed the welding quality test.
[0054] Furthermore, when updating the Mahalanobis distance threshold, the quality inspection device may, for example, use the welding parameters corresponding to multiple batteries that have passed the welding quality inspection to recalculate the Mahalanobis distance percentile, thereby obtaining an updated Mahalanobis distance percentile.
[0055] Then, the welding quality of subsequent batteries is detected according to the updated Mahalanobis distance threshold.
[0056] It should be noted that the process of detecting the welding quality of subsequent batteries according to the updated Mahalanobis distance threshold may be the same as or similar to the implementation process of step 102 above, and will not be described in detail here.
[0057] In this implementation, during the process of detecting the welding quality of a plurality of batteries to be tested, the Mahalanobis distance threshold can be updated in a timely manner according to the updating condition of the Mahalanobis distance threshold, thereby improving the accuracy of the detection.
[0058] In some optional implementations, before step 102, the method further includes: determining, for each sample battery among the multiple sample batteries, a Mahalanobis distance corresponding to the sample battery based on the welding parameters of the sample battery and the Mahalanobis distance relationship; and determining the Mahalanobis distance threshold based on the Mahalanobis distances corresponding to the multiple sample batteries.
[0059] It should be noted that the process of calculating the Mahalanobis distance threshold of the sample battery has been described in detail in the previous article and will not be repeated here.
[0060] In some application scenarios, when the welding parameters of historical batteries whose welding quality has been tested are used to calculate the Mahalanobis distance threshold, if the welding parameters of the battery to be tested have changed significantly compared with the welding parameters of the historical batteries, inaccurate detection may occur.
[0061] In this implementation, the Mahalanobis distance threshold can be iteratively updated during the detection process, thereby improving the situation where inaccurate detection is caused by large changes in welding parameters and improving the accuracy of detection.
[0062] In some optional implementations, the welding parameters of the sample battery include a first type of welding parameters and a second type of welding parameters; the fluctuation range of the values of the first type of welding parameters is greater than the fluctuation range of the values of the second type of welding parameters;
[0063] The numerical fluctuation range may include, for example, the numerical fluctuation range of welding energy, the numerical fluctuation range of welding power, or the numerical fluctuation range of welding time, etc. Thus, various welding parameters may be classified according to the numerical fluctuation range of the welding parameters.
[0064] In some application scenarios, if the numerical fluctuation range of a welding parameter is within a first fluctuation range, the welding parameter can be classified as a first-category welding parameter, and if the numerical fluctuation range of a welding parameter is within a second fluctuation range, the welding parameter can be classified as a second-category welding parameter. The first fluctuation range is larger than the second fluctuation range. For example, if the numerical fluctuation range of welding power is larger than the numerical fluctuation range of welding energy and also larger than the numerical fluctuation range of welding time, then the welding power can be classified as a first-category welding parameter, and welding energy, welding time, etc. can be classified as second-category welding parameters.
[0065] In this way, when determining the Mahalanobis distance corresponding to each sample battery among the multiple sample batteries based on the welding parameters of the sample battery and the Mahalanobis distance relationship, the residual of the moving average corresponding to the first type of welding parameters and the second type of welding parameters of the sample battery can be substituted into the Mahalanobis distance calculation formula for each sample battery among the multiple sample batteries to obtain the Mahalanobis distance corresponding to the sample battery.
[0066] That is to say, for the first type of welding parameters with large fluctuation range, the residual of its moving average can be calculated. For example, if the first type of welding parameter is welding power, the calculation formula for calculating the residual of the moving average of welding power is: ; The residual of the moving average representing the welding power, An index that characterizes welding power, Characterize the total number of sample batteries.
[0067] Then, the calculated residual of the moving average and the second type of welding parameters are substituted into the Mahalanobis distance calculation formula to calculate the corresponding Mahalanobis distance.
[0068] In this implementation, for first-category welding parameters with large numerical fluctuations, the Mahalanobis distance of the sample battery can be calculated using the residual of their moving average and the second-category welding parameters. This reduces the probability of inaccurate Mahalanobis distance thresholds due to large numerical fluctuations in first-category welding parameters, thereby improving the accuracy of welding quality testing for the battery under test.
[0069] In some application scenarios, the moving average of the first type of welding parameters can also be calculated, and then the moving average and the second type of welding parameters are substituted into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery, thereby improving the detection accuracy of the welding quality of the battery to be tested to a certain extent.
[0070] It should be noted that in some application scenarios, for example, the residual of the moving average of the first type of welding parameters and the residual of the moving average of the second type of welding parameters can be substituted into the Mahalanobis distance calculation formula to calculate the corresponding Mahalanobis distance, or the first type of welding parameters and the second type of welding parameters can be directly substituted into the Mahalanobis distance calculation formula to calculate the corresponding Mahalanobis distance, thereby improving the detection accuracy of the welding quality of the battery to be tested to a certain extent.
[0071] In some optional implementations, the sample battery includes a lithium-ion battery obtained by ultrasonic welding; the first type of welding parameter includes welding power. In this way, the above-mentioned method of substituting the residual of the moving average value corresponding to the first type of welding parameter of the sample battery and the second type of welding parameter into the Mahalanobis distance calculation formula for each sample battery among the multiple sample batteries to obtain the Mahalanobis distance corresponding to the sample battery includes: substituting the residual of the moving average value corresponding to the welding power of the sample battery and the second type of welding parameter into the Mahalanobis distance calculation formula for each sample battery among the multiple sample batteries to obtain the Mahalanobis distance corresponding to the sample battery.
[0072] For lithium-ion batteries obtained by ultrasonic welding, the numerical fluctuation of the welding power is large. Therefore, the Mahalanobis distance threshold corresponding to the sample battery can be determined by the residual of the moving average of the welding power and other welding parameters, thereby improving the accuracy of the welding quality detection of the battery to be tested.
[0073] In some optional implementations, the above-mentioned step 102 may specifically include: if the Mahalanobis distance to be measured is greater than a preset multiple of the Mahalanobis distance threshold, determining that the welding quality of the battery to be tested is unqualified; and / or, if the Mahalanobis distance to be measured is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery to be tested is greater than the power residual threshold, determining that the welding quality of the battery to be tested is unqualified; the power residual threshold is obtained by the residual of the moving average value corresponding to the welding power of the multiple sample batteries; and / or, if the Mahalanobis distance to be measured is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery to be tested is less than the power residual threshold, determining that the welding quality of the battery to be tested is qualified; and / or, if the Mahalanobis distance to be measured is less than the Mahalanobis distance threshold, determining that the welding quality of the battery to be tested is qualified.
[0074] The preset multiple can include, for example, two or three times a preset value, which can be obtained through experience. Thus, when the Mahalanobis distance to be measured is greater than the preset multiple Mahalanobis distance threshold, it indicates that the welding quality of the battery to be tested deviates from the normal range and is unqualified.
[0075] In some applications, higher welding power can produce better weld quality when welding batteries ultrasonically. Therefore, when the Mahalanobis distance and the Mahalanobis distance percentile (also known as the Mahalanobis distance threshold) are insufficient to determine the weld quality of the battery under test, data related to welding power can be used to assist in determining the quality.
[0076] Furthermore, since the numerical fluctuation of the welding power is large when the battery is welded by ultrasonic welding, it is possible to determine whether the residual of the moving average value corresponding to the welding power of the battery to be tested is greater than the residual of the moving average value corresponding to the welding power of the sample battery when the Mahalanobis distance to be tested is between the Mahalanobis distance percentile and the Mahalanobis distance percentile of a preset multiple. If it is greater, it can be determined that the welding quality of the battery to be tested is unqualified; if it is less, it can be determined that the welding quality of the battery to be tested is qualified.
[0077] Furthermore, when the Mahalanobis distance to be measured is less than the Mahalanobis distance percentile, it indicates that the welding quality of the battery to be measured is within a normal range, and thus it is qualified.
[0078] In some application scenarios, the above detection process can be characterized by the following calculation formula: ,in, An index that characterizes the battery under test, Characterize the Mahalanobis distance of the battery under test, Characterizes the Mahalanobis distance percentile, Characterizes the residual threshold of the moving average value corresponding to the welding power of the sample battery, The calculation process of the residual of the moving average value corresponding to the welding power of the battery to be tested is similar to the residual of the moving average value corresponding to the welding power of the sample battery, which will not be repeated here.
[0079] In this implementation, the welding quality of the lithium-ion battery obtained by ultrasonic welding can be determined, thereby reducing the probability of misjudgment and improving detection accuracy.
[0080] In some optional implementations, before step 101, the method further includes:
[0081] Step 1: Obtain multiple historical welding parameters and historical welding quality test results corresponding to historical batteries whose welding quality has been tested;
[0082] The aforementioned multiple historical welding parameters may include, for example, different types of welding parameters such as welding energy, welding power, welding time, welding pressure, and welding amplitude corresponding to historical batteries.
[0083] The above historical welding quality test results also refer to whether the welding quality of the historical batteries is qualified or unqualified.
[0084] Step 2: determining a plurality of welding parameters of the battery to be tested according to the correlation between the plurality of historical welding parameters and the historical welding quality test results.
[0085] The above-mentioned correlation degree is also the correlation degree of the historical welding parameters to the determination of the historical welding quality test results.
[0086] For example, the specific welding parameters for detecting welding quality can be determined based on the degree of correlation between welding energy, welding power, welding time, welding pressure, welding amplitude, etc. and historical welding quality detection results.
[0087] Furthermore, if it is determined that the three historical welding parameters of welding energy, welding power, and welding time are highly correlated with the weld quality test result, these three welding parameters can be used to detect the weld quality of the battery under test. In other words, the weld quality of the battery under test can be detected based on the corresponding welding energy, welding power, and welding time.
[0088] In some application scenarios, for example, the above correlation degree can be determined by random forest.
[0089] In this implementation, multiple welding parameters for detecting the welding quality of the battery to be tested can be determined through historical data. Since these multiple welding parameters are highly correlated with the welding quality detection results, the probability of misjudgment and missed judgment can be reduced, thereby improving the detection accuracy of the welding quality of the battery to be tested.
[0090] In some optional implementations, the step 2 described above of determining the multiple welding parameters of the battery to be tested based on the degree of correlation between the multiple historical welding parameters and the historical welding quality test results includes: calculating the Spearman rank correlation coefficients between the multiple historical welding parameters and the historical welding quality test results; and determining the multiple historical welding parameters corresponding to the multiple Spearman rank correlation coefficients that meet preset requirements as the multiple welding parameters of the battery to be tested.
[0091] In some application scenarios, the Spearman correlation coefficient (also known as the Spearman rank correlation coefficient) can be used to characterize the above correlation degree.
[0092] Furthermore, the Spearman rank correlation coefficient can be calculated by To calculate the Spearman rank correlation coefficient corresponding to various historical welding parameters. Characterizes the Spearman rank correlation coefficient, Characterize various historical welding parameters, Characterize historical welding quality inspection results, Representation index.
[0093] In some application scenarios, after calculating the Spearman rank correlation coefficients between various historical welding parameters and historical welding quality test results, the Spearman rank correlation coefficients can be sorted in descending order, and the N historical welding parameters corresponding to the top N Spearman rank correlation coefficients with the largest values can be determined as the N welding parameters of the battery under test. Alternatively, the multiple historical welding parameters corresponding to multiple Spearman rank correlation coefficients whose Spearman rank correlation coefficients have values greater than a preset numerical threshold can be determined as the multiple welding parameters of the battery under test. Here, the top N largest values or the value greater than the preset numerical threshold also meet the above-mentioned preset requirements.
[0094] In this implementation, various welding parameters of the battery to be tested can be determined by using the Spearman rank correlation coefficient, which improves the detection accuracy of the welding quality of the battery to be tested to a certain extent.
[0095] It should be noted that the various welding parameters determined for the battery under test are applicable to all batteries under test, that is, the Mahalanobis distance or Mahalanobis distance percentile can be determined for both the battery under test and the sample battery using these various welding parameters.
[0096] In some applications, if the welding equipment experiences an anomaly, multiple unqualified batteries may be welded consecutively. Consequently, the quality inspection equipment will detect multiple unqualified batteries consecutively. Therefore, the quality inspection equipment can determine the cause of the anomaly based on the test results.
[0097] In some optional implementations, if the number of batteries that fail the welding quality test continuously is greater than a preset abnormal number threshold, it is determined that an abnormal welding parameter has occurred based on a change trend of each of the multiple welding parameters;
[0098] In other words, if multiple unqualified batteries are detected consecutively, it indicates that the welding equipment may be abnormal. Furthermore, if the welding equipment is abnormal, the corresponding welding parameters will typically rise or fall sharply. Therefore, abnormal welding parameters can be determined based on the changing trends of the welding parameters. For example, if the welding energy of multiple unqualified batteries shows a sharp increase, it is determined that the welding energy is abnormal.
[0099] Then, based on the abnormal welding parameter, the cause of the battery failure that continuously fails the welding quality test is determined. For example, if the abnormal welding parameter is welding energy, the cause of the abnormality is an abnormality in the transducer. If the abnormal welding parameter is welding power, the cause of the abnormality is an abnormality in the power detection device or the power output device.
[0100] In this implementation, the cause of the abnormality can be determined through the detection results, and can be fed back to the welding equipment so that the welding equipment can detect the abnormality in time, thereby improving the qualified rate of the battery.
[0101] In some optional implementations, the method further includes: if it is determined that the welding quality of the battery to be tested is unqualified, then retesting the welding quality of the battery to be tested; if it is determined that the number of times the welding quality of the battery to be tested is unqualified reaches a threshold number, then determining that the battery to be tested has defects.
[0102] In some application scenarios, to reduce the false positive rate, if the welding quality of the battery under test fails, the welding quality of the battery under test can be tested multiple times until the number of tests reaches a threshold. If the number of tests reaches the threshold, it can be considered that the battery under test has a defect, resulting in unqualified welding quality. The threshold number can be, for example, 3 or 4 times.
[0103] In this implementation, multiple tests can be performed when the welding quality of the battery to be tested is unqualified, thereby reducing the misjudgment rate and improving the accuracy of the test.
[0104] Furthermore, the present application illustrates the implementation process and technical effects of the above steps through the following experimental process:
[0105] First, the quality inspection equipment can select welding parameters that can be used to detect welding quality through the welding parameters of historical batteries (batteries obtained by ultrasonic welding). The selected historical welding parameters include welding energy, welding power, welding amplitude, welding pressure and welding time, and then calculate the Spearman correlation coefficient between each historical welding parameter and the corresponding historical welding quality inspection result. For example, according to Figure 2 The magnitude relationship of the Spearman correlation coefficients shown determines that welding energy, welding power, and welding time are used as welding parameters for detecting the welding quality of the battery to be tested.
[0106] Then, the quality inspection equipment can collect the welding energy data, welding power data and welding time data corresponding to the sample battery. Respectively represent the collected Welding energy data, The welding power and Welding time data, The initial value of is 1. If 20 sample batteries are collected, the residual of the moving average corresponding to the welding power of these 20 sample batteries can be calculated , The value of is 20. Then, 20 sample batteries can be selected again, and the corresponding welding parameters can be expressed as , , the average values of various corresponding welding parameters can be expressed as Then, the Mahalanobis distance of each of the 20 sample batteries selected again can be calculated as Then, the Mahalanobis distance of these 20 sample batteries can be expressed as Furthermore, the initial Mahalanobis distance percentiles can be calculated based on the three welding parameters of the 20 sample batteries. ,in, Represents the mean Mahalanobis distance of the sample battery , represents the standard deviation of the Mahalanobis distance of the sample battery , Represents the quantile of the standard normal distribution.
[0107] After the quality inspection equipment obtains the first Mahalanobis distance percentile, it can be calculated by The welding quality of the battery to be tested is tested. The initial value of is 1. , , represents the mean value of welding power in the sample battery, Indicates the standard deviation of welding power in the sample battery .
[0108] If the quality inspection equipment determines that the product is defective, the product can be processed later; if the welding quality of the product is determined to be unqualified (the product is abnormal), multiple inspections can be carried out. If the number of inspections exceeds 3, the product can be determined to be defective. If the welding quality of the product is determined to be qualified (the product is normal), the corresponding multiple welding parameter values can be recorded and used. =j+1. When When the update condition of the Mahalanobis distance percentile is met, the various welding parameters corresponding to the 200 batteries that passed the welding quality inspection can be used as the welding parameters of the sample batteries to re-determine the new Mahalanobis distance percentile. At this time, the various welding parameters corresponding to the 200 batteries can be expressed as , the average values of various welding parameters corresponding to them can be expressed as Then, we can proceed to calculate the Mahalanobis distance of each sample battery , the Mahalanobis distance at this time can be expressed as , and recalculate the new Mahalanobis distance percentile And the residual threshold of the moving average corresponding to the new welding power .in, , , . , , Then, by The value reaches 200, and the Mahalanobis distance percentile is iteratively updated, thereby improving the detection accuracy of the welding quality of the battery to be tested.
[0109] Furthermore, 59 battery cells were prepared for testing in the experiment, of which 9 had risk points in welding quality. These 9 battery cells had abnormalities such as smearing butter on the tabs, misalignment of the tabs, and reduced parallelism of the welding seat.
[0110] The quality inspection equipment then tested the welding quality of each of the 59 cells individually based on their welding parameters. The test results showed that of the 47 cells in the sample battery, 40 were normal and 1 was abnormal, resulting in an overall recall rate of 97.5%. Furthermore, the model correctly detected 6 of the 7 cells with poor solder joints, with an abnormality detection rate exceeding 85.7%. Of the 12 cells in the validation set, 10 were normal and 2 were abnormal, for a 100% accuracy rate.
[0111] See also Figure 3 This is a distribution diagram of Mahalanobis distance data corresponding to each battery under test during large-scale testing. The quality inspection equipment inspected 186,572 battery cells. The test results showed that the solder joints of 6 cells failed the test, including 2 cells that were confirmed to have poor solder joints after disassembly. The poor solder joint detection rate was 100%, indicating no missed defects, and the over-detection rate was 0.002%, demonstrating the high accuracy of the quality inspection equipment.
[0112] Those skilled in the art will understand that, in the above-mentioned method of a specific embodiment, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.
[0113] Please refer to Figure 4 , which shows a structural block diagram of a battery welding quality detection device provided by an embodiment of the present application. The battery welding quality detection device can be a module, program segment or code on an electronic device. It should be understood that the device is similar to the above Figure 1 The method embodiment corresponds to the embodiment that can be executed Figure 1 The various steps involved in the method embodiment.
[0114] Optionally, the battery welding quality detection device includes a determination module 401 and a detection module 402. The determination module 401 is configured to determine a Mahalanobis distance to be measured corresponding to the battery to be tested based on welding parameters corresponding to the battery to be tested and a Mahalanobis distance relationship; the detection module 402 is configured to detect the welding quality of the battery to be tested based on the Mahalanobis distance to be measured and a Mahalanobis distance threshold; the Mahalanobis distance threshold is obtained by respectively determining the welding parameters corresponding to a plurality of sample batteries that have passed the welding quality test.
[0115] Optionally, the device further includes an update module, which is configured to: after detecting the welding quality of the battery to be tested based on the Mahalanobis distance to be tested and the Mahalanobis distance threshold, update the Mahalanobis distance threshold if an update condition of the Mahalanobis distance threshold is met; and detect the welding quality of subsequent batteries based on the updated Mahalanobis distance threshold.
[0116] Optionally, the update condition of the Mahalanobis distance threshold includes at least one of the following: the number of batteries with qualified welding quality is greater than a preset number threshold, the number of times the Mahalanobis distance threshold is used is greater than a preset number threshold, the quality inspection equipment is shut down, the type of battery to be tested changes, and the configured welding parameters change.
[0117] Optionally, the device further includes a threshold determination module, which is configured to: before detecting the welding quality of the battery to be tested based on the measured Mahalanobis distance and the Mahalanobis distance threshold, determine, for each sample battery among the multiple sample batteries, the Mahalanobis distance corresponding to the sample battery based on the welding parameters of the sample battery and the Mahalanobis distance relationship; and determine the Mahalanobis distance threshold based on the Mahalanobis distances corresponding to the multiple sample batteries.
[0118] Optionally, the welding parameters of the sample battery include a first type of welding parameters and a second type of welding parameters; the numerical fluctuation amplitude of the first type of welding parameters is greater than the numerical fluctuation amplitude of the second type of welding parameters; thus, the threshold determination module is further used to: for each sample battery among the multiple sample batteries, substitute the residual of the moving average value corresponding to the first type of welding parameters of the sample battery and the second type of welding parameters into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery.
[0119] Optionally, the sample battery includes a lithium-ion battery obtained by ultrasonic welding; the first type of welding parameter includes welding power, so that the above-mentioned threshold determination module is further used to: for each sample battery among the multiple sample batteries, substitute the residual of the moving average value corresponding to the welding power of the sample battery and the second type of welding parameter into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery.
[0120] Optionally, the detection module 402 is further used to: if the Mahalanobis distance to be measured is greater than a preset multiple of the Mahalanobis distance threshold, determine that the welding quality of the battery to be tested is unqualified; and / or, if the Mahalanobis distance to be measured is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery to be tested is greater than the power residual threshold, determine that the welding quality of the battery to be tested is unqualified; the power residual threshold is obtained by the residual of the moving average value corresponding to the welding power of the multiple sample batteries; and / or, if the Mahalanobis distance to be measured is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery to be tested is less than the power residual threshold, determine that the welding quality of the battery to be tested is qualified; and / or, if the Mahalanobis distance to be measured is less than the Mahalanobis distance threshold, determine that the welding quality of the battery to be tested is qualified.
[0121] Optionally, the device further includes a parameter determination module, which is configured to: before determining the measured Mahalanobis distance corresponding to the battery to be tested based on the welding parameters corresponding to the battery to be tested and the Mahalanobis distance relationship, obtain a plurality of historical welding parameters and historical welding quality test results corresponding to historical batteries whose welding quality has been tested; and determine the plurality of welding parameters of the battery to be tested based on the degree of correlation between the plurality of historical welding parameters and the historical welding quality test results.
[0122] Optionally, the parameter determination module is further used to: calculate the Spearman rank correlation coefficients between the multiple historical welding parameters and the historical welding quality test results; and determine the multiple historical welding parameters corresponding to the multiple Spearman rank correlation coefficients that meet preset requirements as the multiple welding parameters of the battery to be tested.
[0123] Optionally, the device further includes an abnormality determination module, which is used to: if the number of batteries that fail the welding quality test continuously is greater than a preset abnormal number threshold, determine the abnormal welding parameters based on the change trend of each welding parameter among the multiple welding parameters; and determine the abnormal cause of the battery that fails the welding quality test continuously based on the abnormal welding parameters.
[0124] Optionally, the device also includes a judgment module, which is used to: if it is determined that the welding quality of the battery to be tested is unqualified, then re-test the welding quality of the battery to be tested; if it is determined that the number of times the welding quality of the battery to be tested is unqualified reaches a number threshold, then determine that the battery to be tested has defects.
[0125] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.
[0126] Please refer to Figure 5 , Figure 5 A structural diagram of an electronic device for executing a battery welding quality detection method provided in an embodiment of the present application, the electronic device may include: at least one processor 501, such as a CPU, at least one communication interface 502, at least one memory 503 and at least one communication bus 504. Among them, the communication bus 504 is used to realize direct connection and communication between these components. Among them, the communication interface 502 of the device in the embodiment of the present application is used to communicate signaling or data with other node devices. The memory 503 can be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 503 can optionally also be at least one storage device located away from the aforementioned processor. Computer-readable instructions are stored in the memory 503. When the computer-readable instructions are executed by the processor 501, the electronic device can execute the above-mentioned Figure 1 The method process shown.
[0127] I understand. Figure 5 The structure shown is for illustration only. The electronic device may also include Figure 5 More or fewer components than shown, or with Figure 5 Different configurations shown. Figure 5 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0128] The embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the following can be performed: Figure 1 The method process in the illustrated method embodiment is executed by the electronic device.
[0129] An embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the methods provided by the above-mentioned method embodiments. For example, the method may include: determining a Mahalanobis distance to be measured corresponding to the battery to be tested based on the welding parameters corresponding to the battery to be tested and the Mahalanobis distance relationship; detecting the welding quality of the battery to be tested based on the Mahalanobis distance to be measured and a Mahalanobis distance threshold; the Mahalanobis distance threshold is obtained by respectively obtaining the welding parameters corresponding to a plurality of sample batteries that have passed the welding quality test.
[0130] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0131] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0132] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0133] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.
[0134] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.
Claims
1. A battery welding quality detection method, It is characterized in that include: According to the welding parameters corresponding to the battery to be tested and the Mahalanobis distance relationship, the Mahalanobis distance to be tested corresponding to the battery to be tested is determined; the Mahalanobis distance relationship is characterized by a Mahalanobis distance calculation formula, and the Mahalanobis distance calculation formula is: ;in, Characterizing the Mahalanobis distance to be measured; An index characterizing the battery to be tested; Characterize the numerical values corresponding to various welding parameters; Characterize the average values corresponding to various welding parameters; Characterize the covariance matrix; The welding quality of the battery to be tested is detected according to the Mahalanobis distance to be tested and the Mahalanobis distance threshold; the Mahalanobis distance threshold is obtained by respectively obtaining welding parameters corresponding to a plurality of sample batteries that have passed the welding quality test; Before detecting the welding quality of the battery to be tested according to the Mahalanobis distance to be tested and the Mahalanobis distance threshold, the method further includes: For each sample battery among the plurality of sample batteries, determining a Mahalanobis distance corresponding to the sample battery according to a welding parameter of the sample battery and a Mahalanobis distance relationship; Determining the Mahalanobis distance threshold according to the Mahalanobis distances respectively corresponding to the plurality of sample batteries; The welding parameters of the sample battery include a first type of welding parameters and a second type of welding parameters; the fluctuation range of the numerical value of the first type of welding parameters is greater than the fluctuation range of the numerical value of the second type of welding parameters; and The step of determining, for each sample battery among the plurality of sample batteries, a Mahalanobis distance corresponding to the sample battery according to the welding parameters of the sample battery and the Mahalanobis distance relationship, comprises: For each sample battery among the plurality of sample batteries, the residual of the moving average value corresponding to the first type of welding parameters and the second type of welding parameters of the sample battery are substituted into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery.
2. The method according to claim 1, It is characterized in that After detecting the welding quality of the battery to be tested according to the Mahalanobis distance to be tested and the Mahalanobis distance threshold, the method further includes: If the updating condition of the Mahalanobis distance threshold is met, then the Mahalanobis distance threshold is updated; The welding quality of subsequent batteries is detected according to the updated Mahalanobis distance threshold.
3. The method according to claim 2, It is characterized in that The update condition of the Mahalanobis distance threshold includes at least one of the following: the number of batteries with qualified welding quality is greater than a preset number threshold, the number of times the Mahalanobis distance threshold is used is greater than a preset number threshold, the quality inspection equipment is shut down, the type of battery to be tested changes, and the configured welding parameters change.
4. The method according to claim 1, It is characterized in that The sample battery includes a lithium-ion battery obtained by ultrasonic welding; the first type of welding parameters includes welding power, and For each sample battery among the plurality of sample batteries, the residual of the moving average value corresponding to the first type of welding parameters and the second type of welding parameters of the sample battery are substituted into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery, including: For each sample battery among the plurality of sample batteries, the residual of the moving average value corresponding to the welding power of the sample battery and the second type of welding parameters are substituted into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery.
5. The method according to claim 4, It is characterized in that The step of detecting the welding quality of the battery to be tested according to the Mahalanobis distance to be tested and the Mahalanobis distance threshold comprises: If the Mahalanobis distance to be measured is greater than a preset multiple of the Mahalanobis distance threshold, it is determined that the welding quality of the battery to be measured is unqualified; or If the Mahalanobis distance to be tested is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery to be tested is greater than the power residual threshold, it is determined that the welding quality of the battery to be tested is unqualified; the power residual threshold is obtained by the residual of the moving average value corresponding to the welding power of the multiple sample batteries; or If the Mahalanobis distance to be tested is between the Mahalanobis distance threshold and the preset multiple of the Mahalanobis distance threshold, and the power residual corresponding to the battery to be tested is less than the power residual threshold, it is determined that the welding quality of the battery to be tested is qualified; or If the Mahalanobis distance to be measured is less than the Mahalanobis distance threshold, it is determined that the welding quality of the battery to be measured is qualified.
6. The method according to claim 1, It is characterized in that Before determining the Mahalanobis distance to be measured corresponding to the battery to be tested according to the welding parameters corresponding to the battery to be tested and the Mahalanobis distance relationship, the method further includes: Obtaining a variety of historical welding parameters and historical welding quality test results corresponding to historical batteries whose welding quality has been tested; According to the correlation between the plurality of historical welding parameters and the historical welding quality detection results, the plurality of welding parameters of the battery to be tested are determined.
7. The method according to claim 6, It is characterized in that Determining the multiple welding parameters of the battery to be tested according to the correlation between the multiple historical welding parameters and the historical welding quality test results respectively includes: Calculating the Spearman rank correlation coefficients between the plurality of historical welding parameters and the historical welding quality test results; The multiple historical welding parameters corresponding to the multiple Spearman rank correlation coefficients that meet the preset requirements are determined as the multiple welding parameters of the battery to be tested.
8. The method according to claim 7, It is characterized in that The method further comprises: If the number of batteries that fail the welding quality test continuously is greater than a preset abnormal number threshold, determining that an abnormal welding parameter has occurred according to a change trend of each of the multiple welding parameters; According to the abnormal welding parameters, the abnormal reasons for the batteries failing the welding quality inspection continuously are determined.
9. The method according to any one of claims 1 to 8, It is characterized in that The method further comprises: If it is determined that the welding quality of the battery to be tested is unqualified, retesting the welding quality of the battery to be tested; If it is determined that the number of times that the welding quality of the battery to be tested is unqualified reaches a number threshold, it is determined that the battery to be tested has defects.
10. A battery welding quality detection device, It is characterized in that include: The determination module is used to determine the Mahalanobis distance to be measured corresponding to the battery to be tested according to the welding parameters corresponding to the battery to be tested and the Mahalanobis distance relationship; the Mahalanobis distance relationship is characterized by a Mahalanobis distance calculation formula, and the Mahalanobis distance calculation formula is: ;in, Characterizing the Mahalanobis distance to be measured; An index characterizing the battery to be tested; Characterize the numerical values corresponding to various welding parameters; Characterize the average values corresponding to various welding parameters; Characterize the covariance matrix; A detection module, used to detect the welding quality of the battery to be tested according to the Mahalanobis distance to be tested and the Mahalanobis distance threshold; the Mahalanobis distance threshold is obtained by respectively obtaining welding parameters corresponding to a plurality of sample batteries that have passed the welding quality test; The device further includes a threshold determination module, which is used to: before detecting the welding quality of the battery to be tested according to the Mahalanobis distance to be tested and the Mahalanobis distance threshold, determine the Mahalanobis distance corresponding to each sample battery among the multiple sample batteries according to the welding parameters of the sample battery and the Mahalanobis distance relationship; determine the Mahalanobis distance threshold according to the Mahalanobis distances respectively corresponding to the multiple sample batteries; The welding parameters of the sample battery include first-type welding parameters and second-type welding parameters; the numerical fluctuation range of the first-type welding parameters is greater than the numerical fluctuation range of the second-type welding parameters; and the threshold determination module is further used to: for each sample battery among the multiple sample batteries, substitute the residual of the moving average value corresponding to the first-type welding parameters of the sample battery and the second-type welding parameters into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance corresponding to the sample battery.
11. An electronic device, It is characterized in that The method comprises a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 9 is executed.
12. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is executed.
13. A computer program product comprising a computer program or instructions, It is characterized in that When the computer program or instruction is executed by a processor, the method according to any one of claims 1 to 9 is performed.
