Battery welding detection method, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a battery welding detection method, electronic equipment and a storage medium, and the method comprises the steps: obtaining to-be-detected spectral data generated in the welding process of a battery when welding equipment is in a running state; performing in-welding detection on the battery based on the to-be-detected spectral data to determine an initial welding result of the battery; if the initial welding result is qualified, a to-be-verified image of a battery welding area is obtained after battery welding is completed; and after-welding detection is conducted on the battery based on the to-be-verified image to determine the target welding result of the battery, so that the misjudgment condition of battery welding detection is avoided, the accuracy of battery welding detection is improved, and then the welding quality of the battery is improved.

Description

Technical Field

[0001] The present application relates to the technical field of battery detection, and in particular, to a welding detection method for a battery, an electronic device, and a storage medium. Background Art

[0002] With the continuous development of electronic technology, batteries play an increasingly important role in life. In the manufacturing process of batteries, from cell manufacturing to component assembly, welding, etc. are all important processes. Among them, the quality of welding affects the service life and safety of the battery.

[0003] In the related art, laser welding has become the preferred method for battery welding due to its flexibility, precision, and high efficiency. However, in the actual production process, due to the influence of factors such as equipment, process, process, and environment, welding will inevitably produce defects such as poor welding, explosion welding, wire offset, and welding holes. Therefore, whether it is to extend the battery life from the product appearance or from the consideration of the user's life safety, it is necessary to improve the welding detection of the battery to ensure product quality. At present, the welding detection methods of batteries mostly rely on manual or single vision detection systems, and it is difficult to comprehensively monitor the welding quality. Summary of the Invention

[0004] Embodiments of the present application provide a welding detection method for a battery, an electronic device, and a storage medium, so as to avoid misjudgment in battery welding detection, improve the accuracy of battery welding detection, and further improve the welding quality of the battery.

[0005] In a first aspect, embodiments of the present application provide a welding detection method for a battery, including:

[0006] When the welding device is in an operating state, obtaining the spectral data to be detected generated by the battery during the welding process;

[0007] Based on the spectral data to be detected, performing in-welding detection on the battery to determine the initial welding result of the battery;

[0008] If the initial welding result is qualified, obtaining the image to be verified of the welding area of the battery after the battery welding is completed;

[0009] Based on the image to be verified, performing post-welding detection on the battery to determine the target welding result of the battery.

[0010] Optionally, in some embodiments of the present application, before obtaining the spectral data to be detected generated by the battery during the welding process, the method further includes:

[0011] Obtaining a plurality of initial spectral data generated by the battery during the welding process;

[0012] Remove abnormal spectral data from the multiple initial spectral data based on a preset algorithm;

[0013] Perform data processing on the multiple initial spectral data after removing the abnormal spectral data to determine a preset spectral threshold.

[0014] Optionally, in some embodiments of the present application, the performing in-process welding detection on the battery based on the spectral data to be detected to determine an initial welding result of the battery includes:

[0015] Compare the spectral data to be detected with the preset spectral threshold;

[0016] If the spectral data to be detected is less than or equal to the preset spectral threshold, the initial welding result of the battery is qualified;

[0017] If the spectral data to be detected is greater than the preset spectral threshold, the initial welding result of the battery is unqualified.

[0018] Optionally, in some embodiments of the present application, the spectral data to be detected includes at least one of infrared thermal radiation data, laser backscattered radiation data, and ultraviolet visible light data. The if the spectral data to be detected is less than or equal to the preset spectral threshold, the initial welding result of the battery is qualified includes:

[0019] If the spectral data to be detected includes one type of spectral data, when the infrared thermal radiation data is less than or equal to a first preset spectral threshold, or the laser backscattered radiation data is less than or equal to a second preset spectral threshold, or the ultraviolet visible light data is less than or equal to a third preset spectral threshold, the initial welding result of the battery is qualified;

[0020] If the spectral data to be detected includes two types of spectral data, when the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the laser backscattered radiation data is less than or equal to the second preset spectral threshold, or the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, or the laser backscattered radiation data is less than or equal to the second preset spectral threshold and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, the initial welding result of the battery is qualified;

[0021] If the spectral data to be detected includes three types of spectral data, when the infrared thermal radiation data is less than or equal to the first preset spectral threshold, the laser backscattered radiation data is less than or equal to the second preset spectral threshold, and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, the initial welding result of the battery is qualified.

[0022] Optionally, in some embodiments of the present application, if the spectral data to be detected is greater than the preset spectral threshold, the initial welding result of the battery is unqualified, including:

[0023] If the spectral data to be detected includes one type of spectral data, when the infrared thermal radiation data is greater than the first preset spectral threshold, or the laser backscattered radiation data is greater than the second preset spectral threshold, or the ultraviolet visible light data is greater than the third preset spectral threshold, the initial welding result of the battery is unqualified;

[0024] If the spectral data to be detected includes two types of spectral data, when the infrared thermal radiation data is greater than the first preset spectral threshold and / or the laser backscattered radiation data is greater than the second preset spectral threshold, or the infrared thermal radiation data is greater than the first preset spectral threshold and / or the ultraviolet visible light data is greater than the third preset spectral threshold, or the laser backscattered radiation data is greater than the second preset spectral threshold and / or the ultraviolet visible light data is greater than the third preset spectral threshold, the initial welding result of the battery is unqualified;

[0025] If the spectral data to be detected includes three types of spectral data, when the infrared thermal radiation data is greater than the first preset spectral threshold, and / or the laser backscattered radiation data is greater than the second preset spectral threshold, and / or the ultraviolet visible light data is greater than the third preset spectral threshold, the initial welding result of the battery is unqualified.

[0026] Optionally, in some embodiments of the present application, the post-welding inspection of the battery based on the image to be verified to determine the target welding result of the battery includes:

[0027] Match the image to be verified with the images in the preset image library;

[0028] If the match is unsuccessful, determine that the target welding result of the battery is qualified;

[0029] If the match is successful, determine that the target welding result of the battery is unqualified.

[0030] Optionally, in some embodiments of the present application, after the image to be verified is matched with the images in the preset image library, the method further includes:

[0031] If the match is unsuccessful, perform a metallographic inspection on the battery to obtain a first inspection result;

[0032] If the first inspection result indicates that the target welding result of the battery is unqualified, add the image to be verified to the preset image library to update the preset image library.

[0033] Optionally, in some embodiments of the present application, after performing in-process welding detection on the battery based on the to-be-detected spectral data to determine the initial welding result of the battery, the method further includes:

[0034] If the initial welding result is unqualified, stop welding the battery, adjust the welding parameters of the welding equipment, and re-weld the battery with the adjusted welding parameters.

[0035] Optionally, in some embodiments of the present application, after the to-be-detected spectral data is greater than the preset spectral threshold and the initial welding result of the battery is unqualified, the method further includes:

[0036] If the initial welding result is unqualified, perform appearance detection and / or metallographic sectioning detection on the welding area of the battery to obtain a second detection result;

[0037] If the second detection result indicates that the battery is a qualified product, adjust the preset spectral threshold based on the to-be-detected spectral data;

[0038] If the second detection result indicates that the battery is an unqualified product, stop welding the battery, adjust the welding parameters of the welding equipment, and re-weld the battery with the adjusted welding parameters.

[0039] In a second aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the welding detection method of any of the above batteries are implemented.

[0040] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, where the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the welding detection method of any of the above batteries are implemented.

[0041] An embodiment of the present application provides a welding detection method, an electronic device, and a storage medium for a battery, including: when the welding equipment is in an operating state, obtaining to-be-detected spectral data generated by the battery during welding; performing in-process welding detection on the battery based on the to-be-detected spectral data to determine the initial welding result of the battery; if the initial welding result is qualified, obtaining an image to be verified of the welding area of the battery after the battery welding is completed; performing post-welding detection on the battery based on the image to be verified to determine the target welding result of the battery, thereby avoiding misjudgment in battery welding detection, improving the accuracy of battery welding detection, and further improving the welding quality of the battery. Description of the Drawings

[0042] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0043] Figure 1 It is the first flow schematic diagram of the battery welding detection method provided by the embodiment of the present application;

[0044] Figure 2 It is the second flow schematic diagram of the battery welding detection method provided by the embodiment of the present application;

[0045] Figure 3 It is the third flow schematic diagram of the battery welding detection method provided by the embodiment of the present application;

[0046] Figure 4 It is the fourth flow schematic diagram of the battery welding detection method provided by the embodiment of the present application;

[0047] Figure 5 It is the structural schematic diagram of the electronic device provided by the embodiment of the present application. Detailed implementation manners

[0048] To make the features and advantages of the present application more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0049] When the following description involves drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0050] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0051] To improve the welding detection quality of the battery, an embodiment of this application provides a welding detection method for the battery. The following will be described in detail respectively. It should be noted that the description order of the following embodiments does not limit the priority order of the embodiments.

[0052] Please refer to Figure 1 , Figure 1 which is the first process schematic diagram of the welding detection method for the battery provided by the embodiment of this application. The specific process of this welding detection method for the battery can be as follows:

[0053] 101. When the welding equipment is in the operating state, obtain the spectral data to be detected generated by the battery during the welding process.

[0054] In this embodiment, welding preparation work is carried out before running the welding equipment. Specifically, open the Welding Signal Management (WSM) software, input the product name of the battery, and set corresponding parameters such as product signal parameters, station signal parameters, and product slice parameters. Among them, the product signal parameters can define the signal types to be collected during the welding process, such as infrared thermal radiation signals, laser backscattered radiation signals, and ultraviolet visible light signals, etc.; the station signal parameters correspond to the station information of the welding equipment to ensure that the signal collection matches the welding station; the product slice parameters can set the slice parameters for data collection according to the structure and welding process of the battery for subsequent analysis.

[0055] When the welding equipment is in the operating state, that is, during the process of the welding equipment welding the battery, control the spectral sensor to collect the spectral data to be detected generated by the welded area of the battery in real time during the welding process. The data collection volume of the spectral data to be detected needs to reach 500 data points or samples or more to ensure the representativeness and reliability of the data.

[0056] Optionally, the data types collected by the spectral sensor include infrared thermal radiation signals, laser backscattered radiation signals, and ultraviolet visible light signals. The infrared thermal radiation signals, laser backscattered radiation signals, and ultraviolet visible light signals can all be used as the spectral data to be detected generated by the battery during the welding process. Among them, the infrared thermal radiation signals are used to monitor the temperature change of the welding area; the laser backscattered radiation signals are used to monitor the reflected light intensity after the interaction between the laser and the materials in the battery welding area; the ultraviolet visible light signals are used to capture the ultraviolet light and visible light generated during the welding process to analyze the stability of the welding process.

[0057] 102. Perform in-welding detection on the battery based on the spectral data to be detected to determine the initial welding result of the battery.

[0058] Before performing in - process welding detection on the battery based on the spectral data to be detected, it is necessary to establish a baseline for the spectral data generated during the welding process of the battery for comparison with the spectral data to be detected collected in real - time. Specifically, the process of establishing the baseline data can include data screening, baseline setting, algorithm selection, and baseline creation. Among them, data screening can import the collected spectral data into the WSM software, observe the image formed by the data, and delete abnormal data, such as abnormal data caused by noise, interference signals, etc.; baseline setting is to select all the screened data, set the selection area and baseline parameters for pre - processing, such as smoothing processing, normalization processing, etc.; algorithm selection is to select a suitable global detection algorithm according to the welding process and defect type for subsequent real - time comparison; baseline creation is to create the pre - processed data as a baseline, which serves as a reference standard for subsequent in - process welding detection.

[0059] During the welding process, the WSM software obtains the spectral data to be detected in the welding area of the battery in real - time and compares it with the above - mentioned baseline data. Specifically, when the welding equipment is running, the spectral sensor continuously collects the spectral signals generated during the welding process and converts the spectral signals into voltage signals to form the spectral data to be detected; the WSM software compares the spectral data to be detected collected in real - time with the baseline data and analyzes the differences between the two. If the difference between the real - time spectral data to be detected and the baseline data is within the preset threshold range, the initial welding result is determined to be qualified; if the difference between the real - time spectral data to be detected and the baseline data exceeds the preset threshold range, the initial welding result is determined to be unqualified, and the defect type is recorded, such as poor welding, explosion welding, wire offset, etc.

[0060] 103. If the initial welding result is qualified, obtain the image to be verified in the welding area of the battery after the battery welding is completed.

[0061] Before performing post - welding detection, it is necessary to set a sample for calibration, that is, a calibration piece. The calibration piece is usually a battery with defects in the welding appearance, such as the welding wire having explosion points, yellowing, blackening, incompleteness, offset, etc. The role of the calibration piece is to calibrate and verify the accuracy of the detection system.

[0062] In some embodiments, the detection system is based on the image sensing technology of the charge-coupled device (CCD), and the image information of the battery welding area is collected by the CCD image sensor, and the image is analyzed and processed to realize the detection function. Specifically, the CCD detection system captures the image of the battery welding area through a camera, and converts the optical signal into an electrical signal, analyzes the electrical signal through an image processing algorithm, extracts the characteristic information of the target, and makes a judgment according to the preset rules, that is, after the welding process of the battery is completed, the CCD detection system is controlled to perform a comprehensive additional visual inspection of the welding area of ​​the battery, and detects whether there are appearance defects in the welding area through high-resolution image acquisition and analysis. CCD detection has the advantages of high precision, high degree of automation, objectivity and traceability.

[0063] Optionally, the post-weld CCD inspection can detect the weld continuity, weld shape, surface defects, foreign matter or residues, and welding position accuracy of the welding area. Specifically, weld continuity is to detect whether the weld is continuous and whether there is a broken weld or a cold weld; weld shape is to detect whether the shape of the weld meets the design requirements, such as whether the weld height and width are uniform; weld surface defects are to detect whether the surface of the welding area has abnormal conditions such as burst points, yellowing, blackening, incompleteness, and offset; welding position accuracy is to confirm whether the welding position is accurate and whether it deviates from the predetermined welding trajectory.

[0064] In some embodiments, when the initial welding result is qualified, it is necessary to obtain a verified image of the battery welding area through a CCD detection device after the battery welding is completed. The verified image includes the macroscopic appearance of the battery welding area, such as the continuity of the weld, the shape of the weld, the alignment of the weld, etc.

[0065] 104. Perform post-welding inspection on the battery based on the image to be verified to determine a target welding result of the battery.

[0066] After obtaining the image to be verified, the image to be verified is preprocessed, such as adjusting brightness, contrast, removing noise, etc., to improve image quality and ensure that the image is clear and can accurately reflect the details of the welding area. Use image analysis software or algorithms to analyze the preprocessed image to be verified, and compare the image to be verified with the images in the preset image library. The images in the image library have preset defect features, so as to automatically identify whether there are appearance defects in the welding area based on the preset defect features such as weld line burst points, yellowing, blackening, incompleteness, deflection, etc., and classify and annotate the identified defects, and record the location, type and severity of the defects to facilitate subsequent rectification of welding strategies.

[0067] Correlate the target welding result of the image to be verified in post-weld inspection with the initial welding result in in-weld inspection. For the cells with qualified initial welding results in in-weld inspection, analyze the image to be verified in post-weld inspection to determine whether new appearance defects occur. Specifically, if the initial welding result in in-weld inspection is qualified and no appearance defects are found in the image to be verified in post-weld inspection, determine that the target welding result of the cell is qualified; if appearance defects are found in the image to be verified in post-weld inspection, even if the initial welding result in in-weld inspection is qualified, the target welding result can still be determined as unqualified.

[0068] In some embodiments, if appearance defects are found in the image to be verified in post-weld inspection, metallographic analysis can be performed on the cells with appearance defects to confirm whether the appearance defects affect the internal quality of the welding. If the internal welding quality is not affected, the target welding result is determined as qualified; if the internal welding quality is affected, the target welding result is determined as unqualified. Among them, the judgment basis for determining whether the appearance defects affect the internal quality of the welding can be set accordingly according to the actual situation, and no specific limitation is made here.

[0069] As can be seen from the above, in this embodiment, when the welding equipment is in operation, the spectral data to be detected generated during the welding process of the cell is obtained; based on the spectral data to be detected, in-weld inspection of the cell is performed to determine the initial welding result of the cell; if the initial welding result is qualified, the image to be verified of the welding area of the cell is obtained after the cell welding is completed; based on the image to be verified, post-weld inspection of the cell is performed to determine the target welding result of the cell, so as to avoid misjudgment in cell welding inspection through multiple inspections of in-weld inspection and post-weld inspection, improve the accuracy of cell welding inspection, and further improve the welding quality of the cell.

[0070] To improve the accuracy of welding inspection of cells, this embodiment provides an in-weld inspection method for cells. Please refer to Figure 2 , Figure 2 which is the second process schematic diagram of the welding inspection method for cells provided by the embodiments of the present application. The specific process of the welding inspection method for cells provided by this embodiment can be as follows:

[0071] 201. Obtain a plurality of initial spectral data generated during the welding process of the cell.

[0072] In this embodiment, welding preparation work is carried out before welding the battery. Specifically, the WSM software is opened, the product name of the battery is input, and corresponding parameters such as product signal parameters, station signal parameters, and product slicing parameters are set. During the operation of the welding equipment, that is, during the process of the welding equipment welding the battery, the spectral sensor is controlled to collect multiple initial spectral data generated in the welded area of the battery in real time during welding. The amount of data collected needs to reach 500 data points or samples or more to ensure the representativeness and reliability of the data.

[0073] 202. Remove abnormal spectral data from the multiple initial spectral data based on a preset algorithm.

[0074] Perform data preprocessing on the multiple initial spectral data collected, that is, import the collected initial spectral data into the WSM software, observe the data image, and initially identify the abnormal spectral data in the data. Among them, the abnormal spectral data can include noise, interference signals, data points that significantly deviate from the normal range, etc.

[0075] Specifically, use a preset algorithm such as statistical analysis, filtering algorithm, etc. to identify and mark the abnormal spectral data. Among them, statistical analysis is to calculate the mean and standard deviation of the initial spectral data, and mark the data points that exceed a certain multiple of the standard deviation as abnormal spectral data; the filtering algorithm is to use low-pass filtering or high-pass filtering to remove high-frequency noise or low-frequency interference to determine the abnormal spectral data.

[0076] Perform data screening on the preprocessed initial spectral data. Data screening can include steps such as deleting abnormal spectral data and data integrity check. Specifically, when deleting abnormal spectral data, according to the result identified by the preset algorithm, delete the abnormal spectral data and retain the normal data points; the data integrity check is to ensure that after deleting the abnormal spectral data, the remaining spectral data still has sufficient quantity and representativeness to support subsequent analysis.

[0077] 203. Perform data processing on the multiple initial spectral data after removing the abnormal spectral data to determine the preset spectral threshold.

[0078] Performing data processing on the multiple initial spectral data after removing the abnormal spectral data can include steps such as data smoothing processing, normalization processing, and feature extraction. Specifically, data smoothing processing is to perform smoothing processing on the multiple initial spectral data after removing the abnormal spectral data to reduce data fluctuations and improve data stability; normalization processing is to perform normalization processing on the smoothed spectral data so that it is within the same dimension range for subsequent comparison and analysis; when extracting features, according to the welding process and defect type, extract key features in the initial spectral data, such as peaks, valleys, spectral intensity changes, etc.

[0079] In some embodiments, a preset spectral threshold is determined through establishing reference data, setting thresholds, and selecting and validating algorithms. Specifically, for establishing reference data, all the initial spectral data that has been screened and processed is selected as the reference data, selection and reference parameters are set, and the normal range of the spectral data is determined according to the results of feature extraction; for setting thresholds, preset spectral thresholds are set according to the statistical features of the reference data such as mean, standard deviation, extreme values, etc. The setting of the threshold can distinguish normal welding processes and welding defects such as insufficient soldering, explosion welding, and wire offset. The specific setting of the preset spectral threshold can be adjusted according to the actual situation and is not specifically limited here; for algorithm selection and validation, appropriate global detection algorithms such as threshold comparison and pattern recognition are selected for subsequent real-time comparison; the effectiveness of the threshold and algorithm is verified through a small amount of sample data with known defects to ensure that welding defects can be accurately identified, thereby reducing the misjudgment rate.

[0080] 204. When the welding equipment is in an operating state, acquire the spectral data to be detected generated during the welding of the battery.

[0081] The data types collected by the spectral sensor include infrared thermal radiation signals, laser backscattered radiation signals, and ultraviolet and visible light signals. The infrared thermal radiation signals, laser backscattered radiation signals, and ultraviolet and visible light signals can all be used as the spectral data to be detected generated during the battery welding process. Among them, the infrared thermal radiation signal is used to monitor the temperature change in the welding area; the laser backscattered radiation signal is used to monitor the reflected light intensity after the interaction between the laser and the materials in the battery welding area; the ultraviolet and visible light signal is used to capture the ultraviolet and visible light generated during the welding process to analyze the stability of the welding process.

[0082] 205. Compare the spectral data to be detected with the preset spectral threshold.

[0083] 206. If the spectral data to be detected is less than or equal to the preset spectral threshold, the initial welding result of the battery is qualified.

[0084] The WSM software compares the spectral data to be detected collected in real time with the preset spectral threshold. Specifically, if the spectral data to be detected is less than or equal to the preset spectral threshold, it is considered that the welding process is normal and the initial welding result of the battery is qualified.

[0085] It should be noted that the spectral data collected by the spectral sensor includes infrared thermal radiation data, laser backscattered radiation data, ultraviolet and visible light data, etc. Therefore, each type of spectral data needs to be compared with the corresponding preset spectral threshold respectively, and the initial welding result of the battery is confirmed based on multiple comparison results, thereby further improving the accuracy of the detection result.

[0086] Optionally, if the spectral data to be detected includes one type of spectral data, the initial welding result of the battery is qualified when the infrared thermal radiation data is less than or equal to the first preset spectral threshold, or the laser backscattered radiation data is less than or equal to the second preset spectral threshold, or the ultraviolet and visible light data is less than or equal to the third preset spectral threshold. Among them, the numerical values of the first preset spectral threshold, the second preset spectral threshold, and the third preset spectral threshold can be set accordingly according to the actual situation, and no specific limitation is made here.

[0087] Optionally, if the spectral data to be detected includes two types of spectral data, the initial welding result of the battery is qualified when the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the laser backscattered radiation data is less than or equal to the second preset spectral threshold, or the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the ultraviolet and visible light data is less than or equal to the third preset spectral threshold, or the laser backscattered radiation data is less than or equal to the second preset spectral threshold and the ultraviolet and visible light data is less than or equal to the third preset spectral threshold.

[0088] Optionally, if the spectral data to be detected includes three types of spectral data, the initial welding result of the battery is qualified when the infrared thermal radiation data is less than or equal to the first preset spectral threshold, the laser backscattered radiation data is less than or equal to the second preset spectral threshold, and the ultraviolet and visible light data is less than or equal to the third preset spectral threshold.

[0089] 207. If the spectral data to be detected is greater than the preset spectral threshold, the initial welding result of the battery is unqualified.

[0090] Specifically, if the spectral data to be detected is greater than the preset spectral threshold, it is considered that defects such as poor welding, explosion welding, and wire offset occur during the welding process, and the initial welding result of the battery is unqualified.

[0091] Optionally, if the spectral data to be detected includes one type of spectral data, the initial welding result of the battery is unqualified when the infrared thermal radiation data is greater than the first preset spectral threshold, or the laser backscattered radiation data is greater than the second preset spectral threshold, or the ultraviolet and visible light data is greater than the third preset spectral threshold.

[0092] Optionally, if the spectral data to be detected includes two types of spectral data, the initial welding result of the battery is unqualified when the infrared thermal radiation data is greater than the first preset spectral threshold and / or the laser backscattered radiation data is greater than the second preset spectral threshold, or the infrared thermal radiation data is greater than the first preset spectral threshold and / or the ultraviolet and visible light data is greater than the third preset spectral threshold, or the laser backscattered radiation data is greater than the second preset spectral threshold and / or the ultraviolet and visible light data is greater than the third preset spectral threshold.

[0093] Optionally, if the spectral data to be detected includes three types of spectral data, the initial welding result of the battery is unqualified when the infrared thermal radiation data is greater than the first preset spectral threshold, and / or the laser backscattered radiation data is greater than the second preset spectral threshold, and / or the ultraviolet visible light data is greater than the third preset spectral threshold.

[0094] 208. If the initial welding result is unqualified, stop welding the battery, adjust the welding parameters of the welding equipment, and re-weld the battery with the adjusted welding parameters.

[0095] During the in-welding detection process of the battery, the WSM software compares the collected spectral data to be detected with the preset spectral threshold in real time. For example, if the spectral data to be detected is greater than the preset spectral threshold, the initial welding result of the battery is unqualified. At this time, when the WSM software determines that the initial welding result is unqualified, it will immediately issue an instruction to stop welding. After receiving the instruction, the welding equipment stops the current welding operation to avoid further welding defects.

[0096] According to the analysis results, determine the welding parameters that need to be adjusted, such as laser power, welding speed, defocus amount, and shielding gas flow rate. Among them, if the spectral data to be detected shows insufficient energy, such as a virtual weld, the laser power needs to be increased; if the weld line is offset or discontinuous, the welding speed needs to be adjusted; if the welding depth or the shape of the molten pool is abnormal, the defocus amount of the laser needs to be adjusted; if oxidation or yellowing appears in the welding area, the shielding gas flow rate needs to be adjusted.

[0097] In the control software of the welding equipment, adjust the relevant parameters according to the analysis results, re-weld the battery with the adjusted welding parameters, and record the adjusted parameters in the system for subsequent traceability and analysis. Optionally, record the parameter adjustment content of each welding, the result of re-welding, and the relevant detection data, save the spectral data and appearance images of unqualified welds for subsequent analysis and improvement, save the analysis results and the adjusted welding parameters for optimizing the welding process, and regularly summarize the causes of welding defects and adjustment experiences to update the welding process parameter library to reduce the recurrence of welding defect problems.

[0098] 209. If the initial welding result is unqualified, perform an appearance inspection and / or a metallographic sectioning inspection on the welding area of the battery to obtain a second detection result.

[0099] During the in-welding detection process, if the spectral data to be detected is greater than the preset spectral threshold, the WSM software will determine that the initial welding result of the battery is unqualified. For batteries with an unqualified initial welding result, further detection is performed to verify the welding quality.

[0100] Specifically, the specific methods for further detection may include appearance detection and metallographic sectioning detection. Among them, for appearance detection, a CCD detection device or other appearance detection tools are used to check whether there are obvious appearance defects in the welding area, such as wire bonding blowouts, yellowing, blackening, mutilation, skewing, etc.; during metallographic sectioning detection, the welding area is sectioned and analyzed to check the internal quality of the welding and confirm whether there are internal defects, such as false soldering, lack of fusion in the weld seam, etc.

[0101] 210. If the second detection result indicates that the battery is a qualified product, the preset spectral threshold is adjusted based on the spectral data to be detected.

[0102] If the appearance detection and / or metallographic sectioning detection results show that the battery is a qualified product, it indicates that there may be misjudgment in the spectral data detected during welding. At this time, the preset spectral threshold needs to be adjusted to improve the accuracy and reliability of the detection system.

[0103] In some embodiments, the spectral data at the initial welding is compared with the results of the appearance detection and / or metallographic sectioning detection to analyze the reasons for misjudgment. If the characteristics of the spectral data, such as intensity, peak value, etc., are close to the standards of qualified welding but are judged as unqualified, the range of the preset spectral threshold needs to be increased to reset the threshold according to statistical analysis to avoid the recurrence of misjudgment. Optionally, a small number of known qualified battery samples are used for testing to verify whether the adjusted threshold can correctly determine the welding quality.

[0104] 211. If the second detection result indicates that the battery is an unqualified product, stop welding the battery, adjust the welding parameters of the welding equipment, and re-weld the battery with the adjusted welding parameters.

[0105] If the appearance detection and / or metallographic sectioning detection results indicate that the battery is an unqualified product, it means that there are indeed defects during the welding process. At this time, the welding operation needs to be stopped, the parameters of the welding equipment are adjusted, and re-welding is performed. Specifically, the WSM software issues a stop welding instruction, and the welding equipment immediately stops the current welding operation after receiving the instruction. It should be noted that the specific description of stopping welding the battery, adjusting the welding parameters of the welding equipment, and re-welding the battery with the adjusted welding parameters can refer to the description in step 208 and will not be elaborated here.

[0106] In some embodiments, if the initial welding result of the battery is qualified, appearance detection and / or metallographic sectioning detection can also be performed, and based on the analysis after the appearance detection and / or metallographic sectioning detection, it is determined whether the specific welding quality of the battery is qualified. Specifically, if the initial welding result of the battery is qualified, but the appearance detection and / or metallographic sectioning detection indicates that the battery is unqualified, the preset spectral threshold needs to be reduced.

[0107] As can be seen from the above, in this embodiment, a preset spectral threshold is set before in-welding detection as the determination criterion for the spectral data to be detected, so as to improve the accuracy of welding detection. In addition, by adding appearance detection and / or metallographic sectioning detection to further detect the welding of the battery, the occurrence of misjudgment can be avoided, thereby further improving the accuracy and reliability of battery welding detection and improving the welding quality of the battery.

[0108] To further improve the accuracy of welding detection of the battery, this embodiment also provides a post-welding detection method for the battery. Please refer to Figure 3 , Figure 3 which is the third flow schematic diagram of the battery welding detection method provided by the embodiment of the present application. The specific process of the battery welding detection method provided by this embodiment can be as follows:

[0109] 301. When the welding equipment is in an operating state, obtain the spectral data to be detected generated during the welding of the battery.

[0110] For the descriptions of steps 301-303, please refer to the descriptions of steps 101-103 above, and will not be repeated here.

[0111] 302. Based on the spectral data to be detected, perform in-welding detection on the battery to determine the initial welding result of the battery.

[0112] 303. If the initial welding result is qualified, obtain the image to be verified of the battery welding area after the battery welding is completed.

[0113] 304. Match the image to be verified with the images in the preset image library.

[0114] It can be understood that in order to determine whether the image to be verified meets the welding standard, it is necessary to establish a preset image library in advance, that is, the preset image library is the basis for post-welding detection. Among them, the images included in the preset image library are standard defect images, that is, each image in the preset image library is an image of the battery welding area with unqualified welding quality. The welding defect types can include solder wire explosion points, yellowing, blackening, incompleteness, skewing, etc.

[0115] Optionally, when the welding equipment is operating stably and the welding parameters are optimized, collect the images of the battery welding areas with known welding defects (such as false soldering, explosion welding, solder wire offset, etc.), label the collected images, clarify the welding quality status corresponding to each image, and label the specific defect types and positions of the defect images. To improve the comparison effect, the images can be preprocessed, such as adjusting the brightness, contrast, removing noise, etc., to improve the image quality, and store the processed images in the preset image library.

[0116] After the battery welding is completed, use a CCD detection device to obtain the image to be verified of the welding area, ensuring that the image is clear and can accurately reflect the details of the welding area. Preprocess the image to be verified, such as adjusting brightness and contrast, etc., to make the image clearer, remove noise, reduce interference, and standardize the image size to ensure consistency with the images in the preset image library.

[0117] In some embodiments, feature extraction is performed on the image to be verified and the images in the preset image library. The key features extracted may include weld shape and continuity, solder joint appearance, color change, and defect features, etc. Specifically, the weld shape and continuity can determine whether the weld is complete and continuous, and whether there are interruptions or offsets; the solder joint appearance can determine whether the shape and size of the solder joint meet the standards; the color change can determine whether there are abnormal color changes such as yellowing or blackening in the welding area; the defect features can determine whether there are obvious defects such as blowouts or mutilations.

[0118] Specifically, use image matching algorithms such as template matching, feature point matching, deep learning methods, etc. to compare the image to be verified with the images in the preset image library, and calculate the similarity between the image to be verified and the preset image. Among them, in template matching, the image to be verified is compared with the standard images in the preset image library one by one to calculate the matching degree; in feature point matching, the key feature points of the image to be verified and the preset image are extracted, and whether the images are similar is judged by the matching degree of the feature points; in the deep learning method, a deep learning model such as a convolutional neural network is used, and the image to be verified is input into the model, and the model will output the classification result corresponding to the image.

[0119] 305. If the matching is unsuccessful, determine that the target welding result of the battery is qualified.

[0120] Optionally, if the image to be verified does not match the images in the preset image library, it means that no obvious defect features are found in the appearance of the welding area. At this time, determine that the target welding result of the battery is qualified.

[0121] 306. If the matching is successful, determine that the target welding result of the battery is unqualified.

[0122] Optionally, if the image to be verified matches the images in the preset image library, it means that there are defect features similar to those in the preset image library in the appearance of the welding area. At this time, determine that the target welding result of the battery is unqualified.

[0123] In some embodiments, the target detection results are recorded in the system, such as battery numbers, welding parameters, and detection times, to verify the matching results between the image to be verified and the preset image library. For batteries determined to be unqualified, the specific defect types and locations are recorded, and the reasons are further analyzed. The welding parameters are adjusted or the detection algorithm is optimized, and the preset image library is updated regularly to add images of new defect types to improve the adaptability of the detection system.

[0124] To further improve the accuracy of welding detection for batteries, this embodiment also provides a post-welding detection method for batteries. Please refer to Figure 4 , Figure 4 which is the fourth process schematic diagram of the battery welding detection method provided by the embodiments of the present application. The specific process of the battery welding detection method provided by this embodiment can be as follows:

[0125] 401. When the welding equipment is in an operating state, obtain the spectral data to be detected generated during the welding of the battery.

[0126] For the descriptions of steps 401-403, please refer to the descriptions of steps 101-103 above, and will not be repeated here.

[0127] 402. Based on the spectral data to be detected, perform in-welding detection on the battery to determine the initial welding result of the battery.

[0128] 403. If the initial welding result is qualified, obtain the image to be verified of the battery welding area after the battery welding is completed.

[0129] 404. Match the image to be verified with the images in the preset image library.

[0130] For the description of step 404, please refer to the description of step 303 above, and will not be repeated here.

[0131] 405. If the matching is unsuccessful, perform metallographic sectioning detection on the battery to obtain the first detection result.

[0132] If the image to be verified does not match the images in the preset image library, it means that no similar defect features are found in the preset image library for the image to be verified. At this time, perform metallographic sectioning detection on the battery to further verify the welding quality. Specifically, the metallographic sectioning detection steps can include section preparation and metallographic analysis. Among them, section preparation is to section the battery welding area to prepare a metallographic sample; metallographic analysis is to use a microscope or other metallographic analysis equipment to check the internal quality of the welding to confirm whether there are internal defects such as lack of fusion, incomplete penetration, porosity, etc.

[0133] Determine the target welding result of the battery according to the cutting metallographic inspection result. If the cutting metallographic inspection result shows that the welding quality is qualified, it is determined that the target welding result of the battery is qualified; if the cutting metallographic inspection result shows that the welding quality is unqualified, it is determined that the target welding result of the battery is unqualified.

[0134] 406. If the first inspection result indicates that the target welding result of the battery is unqualified, add the image to be verified to the preset image library to update the preset image library.

[0135] If the cutting metallographic inspection result indicates that the target welding result of the battery is unqualified, it means that the image to be verified may represent a new defect feature. Then add the image to be verified to the preset image library and label it as "unqualified", that is, make a detailed annotation of the image, including the defect type, location, feature description, etc.

[0136] After updating the preset image library, retrain or adjust the image matching algorithm to ensure that the system can recognize the new defect feature, and regularly review and optimize the preset image library, delete duplicate or outdated images, and ensure the accuracy and effectiveness of the image library.

[0137] Correspondingly, the embodiment of the present application further provides an electronic device. Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of the electronic device provided by the embodiment of the present application.

[0138] The electronic device 500 may include a processor 501 with one or more processing cores, a memory 502 with one or more computer-readable storage media, etc. Among them, the processor 501 is electrically connected to the memory 502. Those skilled in the art can understand that Figure 4 the structure of the electronic device shown in

[0139] The processor 501 is the control center of the electronic device 500 and may include one or more processing cores. The processor 501 connects various parts of the entire electronic device through various interfaces and lines. By running or calling the computer programs stored in the memory 502 and calling the data stored in the memory 502, it executes various functions of the electronic device and processes data, thereby performing overall management and control of the electronic device. Optionally, the processor 501 may be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), or programmable logic array (PLA). The processor 501 may integrate one or a combination of several of a CPU, a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interfaces, and application programs, etc.; the GPU is responsible for rendering and drawing the displayed content; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501 and may be implemented separately through a communication chip.

[0140] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the computer programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. Among them, the program storage area may store the operating system, computer programs required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device.

[0141] In addition, the memory 502 may include high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. Correspondingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0142] In the embodiment of the present application, the processor 501 in the electronic device 500 loads the instructions corresponding to the processes of one or more computer programs into the memory 502 according to the following steps, and the processor 501 runs the computer programs stored in the memory 502 to implement various functions as follows:

[0143] When the welding device is in an operating state, obtain the to-be-detected spectral data generated by the battery during welding;

[0144] Based on the to-be-detected spectral data, perform in-welding detection on the battery to determine the initial welding result of the battery;

[0145] If the initial welding result is qualified, obtain the image to be verified of the battery welding area after the battery welding is completed;

[0146] Perform post-welding inspection on the battery based on the image to be verified to determine the target welding result of the battery.

[0147] Optionally, in some embodiments of the present application, before the processor executes to obtain the spectral data to be detected generated during the welding of the battery, it specifically executes: obtaining a plurality of initial spectral data generated during the welding of the battery; removing abnormal spectral data from the plurality of initial spectral data based on a preset algorithm; performing data processing on the plurality of initial spectral data after removing the abnormal spectral data to determine a preset spectral threshold.

[0148] Optionally, in some embodiments of the present application, when the processor executes to perform in-welding inspection on the battery based on the spectral data to be detected to determine the initial welding result of the battery, it specifically executes: comparing the spectral data to be detected with the preset spectral threshold; if the spectral data to be detected is less than or equal to the preset spectral threshold, the initial welding result of the battery is qualified; if the spectral data to be detected is greater than the preset spectral threshold, the initial welding result of the battery is unqualified.

[0149] Optionally, in some embodiments of the present application, the spectral data to be detected includes at least one of infrared thermal radiation data, laser backscattered radiation data, and ultraviolet visible light data. When the processor executes that if the spectral data to be detected is less than or equal to the preset spectral threshold, the initial welding result of the battery is qualified, it specifically executes: if the spectral data to be detected includes one type of spectral data, when the infrared thermal radiation data is less than or equal to the first preset spectral threshold, or the laser backscattered radiation data is less than or equal to the second preset spectral threshold, or the ultraviolet visible light data is less than or equal to the third preset spectral threshold, the initial welding result of the battery is qualified; if the spectral data to be detected includes two types of spectral data, when the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the laser backscattered radiation data is less than or equal to the second preset spectral threshold, or the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, or the laser backscattered radiation data is less than or equal to the second preset spectral threshold and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, the initial welding result of the battery is qualified; if the spectral data to be detected includes three types of spectral data, when the infrared thermal radiation data is less than or equal to the first preset spectral threshold, the laser backscattered radiation data is less than or equal to the second preset spectral threshold, and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, the initial welding result of the battery is qualified.

[0150] Optionally, in some embodiments of the present application, when the processor executes that if the spectral data to be detected is greater than a preset spectral threshold, the initial welding result of the battery is unqualified, it specifically executes: if the spectral data to be detected includes one type of spectral data, when the infrared thermal radiation data is greater than a first preset spectral threshold, or the laser backscattered radiation data is greater than a second preset spectral threshold, or the ultraviolet visible light data is greater than a third preset spectral threshold, the initial welding result of the battery is unqualified; if the spectral data to be detected includes two types of spectral data, when the infrared thermal radiation data is greater than the first preset spectral threshold and / or the laser backscattered radiation data is greater than the second preset spectral threshold, or the infrared thermal radiation data is greater than the first preset spectral threshold and / or the ultraviolet visible light data is greater than the third preset spectral threshold, or the laser backscattered radiation data is greater than the second preset spectral threshold and / or the ultraviolet visible light data is greater than the third preset spectral threshold, the initial welding result of the battery is unqualified; if the spectral data to be detected includes three types of spectral data, when the infrared thermal radiation data is greater than the first preset spectral threshold, and / or the laser backscattered radiation data is greater than the second preset spectral threshold, and / or the ultraviolet visible light data is greater than the third preset spectral threshold, the initial welding result of the battery is unqualified.

[0151] Optionally, in some embodiments of the present application, when the processor executes post-weld inspection of the battery based on the image to be verified to determine the target welding result of the battery, it specifically executes: matching the image to be verified with the images in the preset image library; if the matching is unsuccessful, determining that the target welding result of the battery is qualified; if the matching is successful, determining that the target welding result of the battery is unqualified.

[0152] Optionally, in some embodiments of the present application, after the processor executes matching the image to be verified with the images in the preset image library, it further specifically executes: if the matching is unsuccessful, performing a metallographic sectioning inspection on the battery to obtain a first inspection result; if the first inspection result indicates that the target welding result of the battery is unqualified, adding the image to be verified to the preset image library to update the preset image library.

[0153] Optionally, in some embodiments of the present application, after the processor executes in-process inspection of the battery based on the spectral data to be detected to determine the initial welding result of the battery, it further specifically executes: if the initial welding result is unqualified, stopping welding the battery, adjusting the welding parameters of the welding equipment, and re-welding the battery with the adjusted welding parameters.

[0154] Optionally, in some embodiments of the present application, after the processor executes that if the spectral data to be detected is greater than the preset spectral threshold, the initial welding result of the battery is unqualified, the processor further specifically executes: if the initial welding result is unqualified, perform an appearance inspection and / or a metallographic sectioning inspection on the welding area of the battery to obtain a second inspection result; if the second inspection result indicates that the battery is a qualified product, adjust the preset spectral threshold based on the spectral data to be detected; if the second inspection result indicates that the battery is an unqualified product, stop welding the battery, adjust the welding parameters of the welding equipment, and re-weld the battery with the adjusted welding parameters.

[0155] For the specific implementation of each of the above operations, reference may be made to the previous embodiments and will not be elaborated here.

[0156] In the embodiments of the present application, when the welding equipment is in an operating state, the spectral data to be detected generated during the welding of the battery is obtained; the in-welding inspection of the battery is performed based on the spectral data to be detected to determine the initial welding result of the battery; if the initial welding result is qualified, the image to be verified of the welding area of the battery is obtained after the battery welding is completed; the post-welding inspection of the battery is performed based on the image to be verified to determine the target welding result of the battery, thereby avoiding misjudgment in the battery welding inspection, improving the accuracy of the battery welding inspection, and further improving the welding quality of the battery.

[0157] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions or by controlling related hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0158] Therefore, the embodiments of the present application provide a computer-readable storage medium, in which multiple instructions are stored. The instructions can be loaded by a processor to execute the steps in any one of the battery welding detection methods provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0159] Obtain the spectral data to be detected generated during the welding of the battery; perform an in-welding inspection of the battery based on the spectral data to be detected to determine the initial welding result of the battery; if the initial welding result is qualified, obtain the image to be verified of the welding area of the battery after the battery welding is completed; perform a post-welding inspection of the battery based on the image to be verified to determine the target welding result of the battery.

[0160] For the specific implementation of each of the above operations, reference may be made to the previous embodiments and will not be elaborated here.

[0161] Among them, the storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

[0162] Since the instructions stored in the storage medium can execute the steps in any one of the battery welding detection methods provided by the embodiments of the present application, the beneficial effects achievable by any one of the battery welding detection methods provided by the embodiments of the present application can be realized. For details, refer to the previous embodiments and will not be elaborated here.

[0163] The above has introduced in detail a battery welding detection method, an electronic device, and a storage medium provided by the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A battery welding detection method, characterized in that: include: When the welding equipment is in operation, obtaining the spectrum data to be detected generated by the battery during the welding process; Performing in-weld inspection on the battery based on the spectral data to be inspected to determine an initial welding result of the battery; If the initial welding result is qualified, obtaining an image to be verified of the battery welding area after the battery welding is completed; The battery is subjected to post-welding inspection based on the image to be verified to determine a target welding result of the battery.

2. The battery welding detection method according to claim 1, characterized in that: Before acquiring the spectrum data to be detected generated by the battery during the welding process, the method further includes: Acquire a plurality of initial spectral data generated by the battery during the welding process; Removing abnormal spectral data from the plurality of initial spectral data based on a preset algorithm; Data processing is performed on a plurality of initial spectral data after the abnormal spectral data is removed to determine a preset spectral threshold.

3. The battery welding detection method according to claim 2, characterized in that: The performing welding detection on the battery based on the spectrum data to be detected to determine the initial welding result of the battery includes: Comparing the spectral data to be detected with a preset spectral threshold; If the spectrum data to be detected is less than or equal to the preset spectrum threshold, the initial welding result of the battery is qualified; If the spectrum data to be detected is greater than the preset spectrum threshold, the initial welding result of the battery is unqualified.

4. The battery welding detection method according to claim 3, characterized in that: The spectral data to be detected includes at least one spectral data of infrared thermal radiation data, laser back reflection radiation data and ultraviolet visible light data. If the spectral data to be detected is less than or equal to the preset spectral threshold, the initial welding result of the battery is qualified, including: If the spectral data to be detected includes one spectral data, then when the infrared thermal radiation data is less than or equal to a first preset spectral threshold, or the laser back reflection radiation data is less than or equal to a second preset spectral threshold, or the ultraviolet visible light data is less than or equal to a third preset spectral threshold, the initial welding result of the battery is qualified; If the spectral data to be detected includes two spectral data, then when the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the laser back reflection radiation data is less than or equal to the second preset spectral threshold, or the infrared thermal radiation data is less than or equal to the first preset spectral threshold and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, or the laser back reflection radiation data is less than or equal to the second preset spectral threshold and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, the initial welding result of the battery is qualified; If the spectral data to be detected includes three spectral data, then when the infrared thermal radiation data is less than or equal to the first preset spectral threshold, the laser back reflection radiation data is less than or equal to the second preset spectral threshold, and the ultraviolet visible light data is less than or equal to the third preset spectral threshold, the initial welding result of the battery is qualified.

5. The battery welding detection method according to claim 4, characterized in that: If the spectral data to be detected is greater than the preset spectral threshold, the initial welding result of the battery is unqualified, including: If the spectral data to be detected includes one spectral data, then when the infrared thermal radiation data is greater than a first preset spectral threshold, or the laser back reflection radiation data is greater than a second preset spectral threshold, or the ultraviolet visible light data is greater than a third preset spectral threshold, the initial welding result of the battery is unqualified; If the spectral data to be detected includes two spectral data, then when the infrared thermal radiation data is greater than the first preset spectral threshold and / or the laser back reflection radiation data is greater than the second preset spectral threshold, or the infrared thermal radiation data is greater than the first preset spectral threshold and / or the ultraviolet visible light data is greater than the third preset spectral threshold, or the laser back reflection radiation data is greater than the second preset spectral threshold and / or the ultraviolet visible light data is greater than the third preset spectral threshold, the initial welding result of the battery is unqualified; If the spectral data to be detected includes three types of spectral data, then when the infrared thermal radiation data is greater than the first preset spectral threshold, and / or the laser back reflection radiation data is greater than the second preset spectral threshold, and / or the ultraviolet visible light data is greater than the third preset spectral threshold, the initial welding result of the battery is unqualified.

6. The battery welding detection method according to claim 1, characterized in that: The performing post-weld inspection on the battery based on the image to be verified to determine a target welding result of the battery includes: Matching the image to be verified with images in a preset image library; If the matching is unsuccessful, determining that the target welding result of the battery is qualified; If the matching is successful, it is determined that the target welding result of the battery is unqualified.

7. The battery welding detection method according to claim 6, characterized in that: After matching the image to be verified with the images in the preset image library, the method further includes: If the matching is unsuccessful, performing metallographic testing on the battery to obtain a first testing result; If the first detection result indicates that the target welding result of the battery is unqualified, the image to be verified is added to the preset image library to update the preset image library.

8. The battery welding detection method according to claim 3, characterized in that: After performing in-weld inspection on the battery based on the spectrum data to be inspected to determine an initial welding result of the battery, the method further includes: If the initial welding result is unqualified, the welding of the battery is stopped, the welding parameters of the welding equipment are adjusted, and the battery is re-welded with the adjusted welding parameters.

9. The battery welding detection method according to claim 3, characterized in that: After the initial welding result of the battery is unqualified if the spectral data to be detected is greater than the preset spectral threshold, the method further includes: If the initial welding result is unqualified, performing appearance inspection and / or metallographic inspection on the welding area of ​​the battery to obtain a second inspection result; If the second detection result indicates that the battery is a qualified product, adjusting the preset spectrum threshold based on the spectrum data to be detected; If the second detection result indicates that the battery is a substandard product, the welding of the battery is stopped, the welding parameters of the welding equipment are adjusted, and the battery is re-welded with the adjusted welding parameters.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the battery welding detection method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the steps of the battery welding detection method according to any one of claims 1 to 8 are implemented.

Images