Method for improving battery component yield, storage medium, and electronic device

Abstract

The present invention relates to the field of photovoltaic module battery technology, and provides a method for improving the yield rate of battery modules, a storage medium, and an electronic device. The method comprises: determining the defect type of a welded battery module and the current operating parameters of a welding device; inputting the defect type of the welded battery module and the current operating parameters of the welding device into a parameter generation model to obtain preliminary operating parameters of the welding device; determining whether the preliminary operating parameters of the welding device meet the operating conditions of the welding device; and, if the preliminary operating parameters of the welding device meet the operating conditions, controlling the welding device to weld unwelded battery modules using the preliminary operating parameters to improve the yield rate of the battery module. When a defective battery module occurs, the method performs defect analysis and generates optimized process parameters for the equipment, automatically adjusting the equipment operating state, and effectively avoiding production capacity losses caused by batch defects and equipment downtime for testing and adjustment.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic module batteries, and in particular to a method for improving the yield rate of a battery module, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the advancement of the energy revolution, solar photovoltaic power generation as a green energy source has attracted more and more attention. The welding quality of battery components (such as battery cells) directly affects the conversion efficiency of photovoltaic cells. Poor welding of battery components will seriously affect the performance of the battery cells and reduce the life of the battery components. Therefore, the quality control of battery component welding, which concentrates multiple resources such as equipment, materials, and processes, has become the focus of industry attention.

[0003] In order to control the quality of welded battery assemblies in the prior art, some methods are used to improve the yield rate of welded battery assemblies. However, the methods of improving the yield rate of welded battery assemblies in the prior art are inefficient and require a long downtime of the welding equipment, which affects the battery assembly production. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method for improving the yield of battery components, a computer-readable storage medium and an electronic device to solve the problem that the methods for improving the yield of welded battery components in the prior art are inefficient and affect the production of battery components.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present invention, a method for improving the yield rate of battery assemblies is provided, comprising: determining the defect type of the welded battery assembly and the current operating parameters of the welding equipment; inputting the defect type of the welded battery assembly and the current operating parameters of the welding equipment into a parameter generation model to obtain the preliminary operating parameters of the welding equipment; judging whether the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, the operating conditions being preset conditions for the trouble-free operation of the welding equipment; and when the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, using the preliminary operating parameters to control the welding equipment to weld unwelded battery assemblies to improve the yield rate of the battery assemblies.

[0006] Furthermore, the preparatory operating parameters of the welding equipment include at least a preparatory welding temperature of the welding equipment and a preparatory welding time of the welding equipment, and judging whether the preparatory operating parameters of the welding equipment meet the operating conditions of the welding equipment includes: determining a calculated power of the welding equipment according to the preparatory welding temperature of the welding equipment and the preparatory welding time of the welding equipment; if the calculated power of the welding equipment is less than or equal to a preset power, determining that the preparatory operating parameters of the welding equipment meet the operating conditions of the welding equipment; if the calculated power of the welding equipment is greater than the preset power, determining that the preparatory operating parameters of the welding equipment do not meet the operating conditions of the welding equipment.

[0007] Furthermore, the defect type of the welded battery assembly and the current operating parameters of the welding equipment are determined, including: obtaining the defect types of multiple welded battery assemblies and determining the defect position of each welded battery assembly; if the defect types of a preset number of welded battery assemblies are all target types within a preset time range, and the defect positions of the preset number of welded battery assemblies are all the same, the defect type of the welded battery assembly is determined to be the target type, and the current operating parameters of the welding equipment are determined.

[0008] Furthermore, the method also includes: when the preparatory operating parameters of the welding equipment do not meet the operating conditions of the welding equipment, performing a secondary test on the preparatory operating parameters of the welding equipment to obtain a test result, wherein the test result indicates whether the welding equipment is fault-free when operating with the preparatory operating parameters; using the defect type of the welded battery assembly, the current operating parameters of the welding equipment, the preparatory operating parameters and the test result to correct the parameter generation model to obtain a corrected generation model; and when the test result shows that the welding equipment is fault-free when operating with the preparatory operating parameters, using the preparatory operating parameters to control the welding equipment to weld the unwelded battery assembly.

[0009] Furthermore, before determining the defect type of the welded battery assembly and the current operating parameters of the welding equipment, the method also includes: obtaining an electroluminescent image of the welded battery assembly; inputting the electroluminescent image of the welded battery assembly into a defect recognition model to obtain defect parameters of the welded battery assembly, wherein the defect parameters are no defect or the defect type of the welded battery assembly, and the defect recognition model includes multiple sub-models, wherein the defect types identified by different sub-models are different.

[0010] Furthermore, the multiple sub-models include at least a deep learning algorithm, a random forest model and an autoregressive time series model, and the electroluminescent image of the welded battery assembly is input into a defect recognition model to obtain the defect parameters of the welded battery assembly, including: inputting the electroluminescent image of the welded battery assembly into a first recognition sub-model; when the first recognition sub-model cannot identify whether the battery assembly has a defect, inputting the electroluminescent image of the welded battery assembly into a second recognition sub-model; when the second recognition sub-model cannot identify whether the battery assembly has a defect, inputting the electroluminescent image of the welded battery assembly into a third recognition sub-model to obtain the defect parameters of the welded battery assembly; wherein the first recognition sub-model, the second recognition sub-model and the third recognition sub-model are respectively one of the deep learning algorithm, the random forest model and the autoregressive time series model, and the first recognition sub-model, the second recognition sub-model and the third recognition sub-model are different.

[0011] Furthermore, after inputting the electroluminescent image of the welded battery assembly into a defect recognition model to obtain the defect parameters of the welded battery assembly, the method further includes: performing secondary inspection on the battery assembly to obtain an inspection result, wherein the inspection result indicates whether the battery assembly has defects and the type of defects when defects exist; when the defect parameters of the welded battery assembly are non-defective and the inspection result indicates the presence of defects in the battery assembly and the defect type of the welded battery assembly, the defect parameters of the welded battery assembly and the inspection result are used to correct the defect recognition model to obtain a corrected recognition model.

[0012] Furthermore, the current operating parameters of the welding equipment include the current welding temperature of the welding equipment, the current welding time of the welding equipment, and the current lamp power of the welding equipment; the preparatory operating parameters of the welding equipment include the preparatory welding temperature of the welding equipment, the preparatory welding time of the welding equipment, and the preparatory lamp power of the welding equipment. Wherein, when the defect type of the welded battery assembly is a cold weld, the magnitude relationship between the current operating parameters of the welding equipment and the preparatory operating parameters of the welding equipment satisfies at least one of the following: the preparatory lamp power of the welding equipment is greater than the current lamp power of the welding equipment, the preparatory welding temperature of the welding equipment is greater than the current welding temperature of the welding equipment, and the preparatory welding time of the welding equipment is greater than the current welding time of the welding equipment.

[0013] According to another aspect of the present invention, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the methods for improving the yield of battery components.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the battery component yield improvement methods.

[0015] The beneficial effects of the present application are as follows: the above-mentioned method for improving the yield rate of battery assemblies first determines the defect type of the welded battery assembly and the current operating parameters of the welding equipment; then inputs the defect type of the welded battery assembly and the current operating parameters of the welding equipment into a parameter generation model to obtain the preliminary operating parameters of the welding equipment; then determines whether the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, where the operating conditions are preset conditions for the welding equipment to operate without faults; and finally, if the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, uses the preliminary operating parameters to control the welding equipment to weld the unwelded battery assembly to improve the yield rate of the battery assembly. This method eliminates manual re-judgment. When a battery assembly has a defect, the root cause of the defect is analyzed in real time, and equipment optimization process parameters are generated in real time. The optimized process parameters of the production equipment are distributed to the machine, and the equipment operating status is automatically adjusted in real time, effectively avoiding the production capacity loss caused by batch defects and equipment downtime for testing and adjustment, and solving the problem that the existing method for improving the yield rate of welded battery assemblies is inefficient and affects battery assembly production. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0017] Figure 1 A schematic flow chart of a method for improving the yield rate of a battery assembly according to an embodiment of the present invention is shown;

[0018] Figure 2 A flow chart of another method for improving the yield rate of a battery assembly according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0019] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] As described in the background, in the prior art, a 4K line scan camera and an industrial computer are installed on each piece of production equipment in the welding process of the component workshop. The 4K line scan camera is used to capture images and monitor the quality of the battery cells online in real time. If a defective product is detected on the production line, the industrial computer software will determine that the corresponding image is defective and upload it to the component workshop for manual re-evaluation. The production line automation equipment will release products that have been manually re-evaluated as good and automatically reject products that have been manually re-evaluated as defective. However, if the centralized re-evaluation room staff discovers the same type of defective product three times in a row, they will need to call the workshop production line process personnel to force a line stop and optimize the equipment operating parameters, which seriously affects production capacity. In addition, if the re-evaluation room staff only call to stop the production line after discovering the same type of defective product three times in a row, it will cause a time lag, which can easily lead to the outflow of a large number of defective products.

[0023] In order to solve the problem that the methods of improving the yield rate of welded battery assemblies in the prior art are inefficient and affect the battery assembly production, the embodiments of the present application provide a method for improving the yield rate of battery assemblies, a computer-readable storage medium and an electronic device.

[0024] The present application is further described in detail below with reference to specific embodiments. These embodiments should not be construed as limiting the scope of protection claimed in this application.

[0025] In this embodiment, a method for improving the yield rate of battery components running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 Flowchart of the method for improving the yield rate of battery components according to the embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0027] Step S101, determining the defect type of the welded battery assembly and the current operating parameters of the welding equipment;

[0028] Specifically, the welded battery assembly is a battery cell that has been welded by welding equipment. The current operating parameters include but are not limited to key parameters such as welding temperature, welding time, and flux concentration of the welding equipment.

[0029] During the welding process of photovoltaic cell modules, various types of defects may occur, including but not limited to cold solder joints, cracks, short circuits, foreign matter contamination, and weld offset. These defects can affect the electrical performance and mechanical integrity of the cell module, thereby reducing the overall efficiency and lifespan of the module. By using image acquisition and other technologies to determine the defect type of the welded cell module and record the current operating parameters of the welding equipment at that time, it is possible to analyze the relationship between the defects of the welded cell module and the current operating parameters of the welding equipment, thereby enabling subsequent adjustments to the welding equipment operating parameters to eliminate defects in subsequent cell modules. Image acquisition can use a high-precision camera (such as a 4K line scan camera) to continuously scan the module to capture images of the weld area, or to obtain electroluminescence images for defect analysis. The current operating parameters of the welding equipment can be monitored and recorded in real time using sensors on the equipment.

[0030] Step S102: Inputting the defect type of the welded battery assembly and the current operating parameters of the welding equipment into a parameter generation model to obtain preliminary operating parameters of the welding equipment;

[0031] Specifically, the parameter generation model is obtained based on random forest model training, and the preparatory operating parameters include but are not limited to key parameters such as welding temperature, welding time, flux concentration, etc. of the welding equipment.

[0032] In some embodiments, the parameter generation model may also be obtained by training models such as deep learning models, autoregressive time series models, support vector machines, gradient boosting trees, and neural networks.

[0033] Before inputting the defect types of the welded battery modules and the current operating parameters of the welding equipment into the parameter generation model, the collected data can be preprocessed to extract features that are helpful for analysis. For example, to identify defect types, it may be necessary to extract image features such as grayscale, texture, and shape; for operating parameters, it may be necessary to normalize historical data to eliminate dimensionality effects.

[0034] In addition, a parameter generation model is trained using machine learning or deep learning algorithms based on historical processes. The model's training dataset consists of historical defect data and corresponding operating parameters. The goal is to learn the correlation between defect types and operating parameters, specifically, which operating parameter combinations are most likely to cause which types of defects. When the system detects a new defect type, the defect type and current operating parameters are input into the trained parameter generation model in real time. Based on the learned patterns, the model predicts which operating parameter adjustments are most likely to reduce or eliminate the defect. The model outputs preliminary operating parameters for a specific defect, which are recommended equipment adjustment plans. These parameters may include adjustments to welding temperature, welding pressure, welding time, ribbon speed, etc., to accommodate different defect types and reduce defect incidence.

[0035] Suppose that during the welding process of a photovoltaic cell module, the system repeatedly identifies "cold solder joints" in the already welded modules. The current operating parameters of the welding equipment are a welding temperature of 200°C, a welding pressure of 150N, and a welding time of 2s. The "cold solder joint" defect type and the current operating parameters (for example, a welding temperature of 200°C and a welding pressure of 150N) are input into the parameter generation model. The model analyzes historical data and finds a strong correlation between lower welding temperatures and cold solder joints. Based on this, the model predicts that increasing the welding temperature can reduce the occurrence of cold solder joints. The model outputs preliminary operating parameters, recommending adjusting the welding temperature from 200°C to 210°C. Therefore, a welding temperature of 210°C is considered the preliminary operating parameters for the welding equipment.

[0036] In addition, in addition to the defect types of the welded battery components and the current operating parameters of the above-mentioned welding equipment, the influence of external conditions such as ambient temperature and humidity on the welding effect can also be considered. That is, the ambient temperature and ambient humidity are both input into the parameter generation model, so that the parameter generation model considers the influence of ambient temperature and ambient humidity, generates preliminary operating parameters that better meet the conditions, and adjusts the welding parameters in real time to ensure that the welding quality can remain stable under different environments.

[0037] Step S103, determining whether the preparatory operating parameters of the welding equipment meet the operating conditions of the welding equipment, where the operating conditions are preset conditions for trouble-free operation of the welding equipment;

[0038] Specifically, each welding equipment has its own specific physical limitations, including but not limited to the maximum and minimum temperature, pressure, speed and other parameter ranges. The preparatory operating parameters must fall within these limits, otherwise the equipment cannot physically execute these parameters, or the equipment may be damaged during execution. A series of safety standards must be observed during the welding process, such as preventing overheating, preventing arc generation, and ensuring operator safety. The preparatory operating parameters need to be compared with these safety specifications to ensure that the equipment operation does not violate safety regulations under the adjusted parameters. In addition to physical limitations and safety specifications, the impact of parameter adjustments on production efficiency also needs to be considered. For example, if the preparatory operating parameters recommend a significant reduction in welding speed, although it may improve welding quality, it will significantly reduce productivity and may not be adopted. Therefore, it is necessary to ensure that the impact of the parameter adjustment plan on production efficiency is acceptable while meeting quality requirements.

[0039] In some embodiments, whether the preparatory operating parameters of the welding equipment meet the operating conditions of the welding equipment is generally determined by manual re-judgment. The parameter generation model is obtained by training based on a random forest model, and an artificial semi-supervised learning training mechanism is adopted. That is, the parameter generation model is first predicted, and then it is manually judged whether the preparatory operating parameters predicted by the model can be actually applied, thereby performing real-time training on the parameter generation model to ensure the real-time accuracy of the parameter generation model.

[0040] Step S104, when the preparatory operating parameters of the welding equipment meet the operating conditions of the welding equipment, the preparatory operating parameters are used to control the welding equipment to weld the unwelded battery assemblies to improve the yield rate of the battery assemblies.

[0041] Specifically, based on the above analysis, established parameter generation models (such as deep learning models, random forests, and autoregressive time series models) are used to predict a new set of operating parameters (preliminary operating parameters) that theoretically can reduce or eliminate the previously encountered defects. Before applying the preliminary operating parameters to the equipment, it is necessary to ensure that these parameters do not exceed the equipment's physical limits, safety regulations, or production efficiency requirements. This is achieved by comparing them with equipment specifications, safety operating guidelines, and production efficiency targets. Once it is confirmed that the preliminary operating parameters meet the equipment's operating conditions, they become the actual operating parameters and are used to control the welding equipment for subsequent unwelded battery modules. After implementing the new parameters, the system continuously monitors welding quality and production efficiency to evaluate the effectiveness of the parameter adjustments. If the yield rate improves and production efficiency remains stable or improves, the parameter adjustment is successful.

[0042] In the prior art, when a defective module cell is detected, images of the defect are uploaded to the module workshop for manual review. If an inspector detects the same defect three times in a row, the inspector calls the on-site process staff to shut down the production line and adjust equipment parameters. This inspection method requires high levels of experience and expertise from the inspectors, and the large number of cells that require manual inspection is significantly impacted by both physiological and psychological factors. Factors like emotions and attention can interfere with judgment, leading to missed or over-judgment. Furthermore, different inspectors have different definitions of pass / fail, so the same product may receive different judgments from different inspectors, increasing the likelihood of missed detections. Furthermore, manual inspection requires the employment of a large number of specialized personnel, with frequent staff turnover, requiring ongoing training and maintenance, and resulting in high labor costs. Furthermore, this traditional inspection method relies on post-processing, where defects are analyzed offline and machine parameters are manually adjusted. This line stoppage to optimize equipment parameters can significantly impact system capacity. Furthermore, the time lag required to call and shut down the production line after the re-inspection room staff detect three consecutive instances of the same defective product can easily lead to the outflow of large quantities of defective product.

[0043] The method for improving the yield rate of battery assemblies of the present application first determines the defect type of the welded battery assembly and the current operating parameters of the welding equipment; then, the defect type of the welded battery assembly and the current operating parameters of the welding equipment are input into a parameter generation model to obtain preliminary operating parameters of the welding equipment; then, a determination is made as to whether the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, where the operating conditions are preset conditions for the welding equipment to operate without failure; finally, if the preliminary operating parameters of the welding equipment meet the operating conditions, the preliminary operating parameters are used to control the welding equipment to weld the unwelded battery assembly to improve the yield rate of the battery assembly. This method eliminates manual re-judgment and, in the event of a defective battery assembly, performs a real-time root cause analysis of the defect and generates equipment optimization process parameters in real time. The optimized process parameters of the production equipment are distributed to the machine, and the equipment operating status is automatically adjusted in real time, effectively avoiding the production capacity loss caused by batch defects and equipment downtime for testing and adjustment. This solves the problem of low efficiency and low battery assembly production capacity in the existing method for improving the yield rate of welded battery assemblies.

[0044] Before determining the defect type of the welded battery assembly, it is necessary to first perform defect detection on the welded battery assembly, that is, to detect whether the welded battery assembly has defects. That is, before determining the defect type of the welded battery assembly and the current operating parameters of the welding equipment, the above method further includes the following steps:

[0045] Step S201, obtaining an electroluminescent image of the welded battery assembly;

[0046] After soldering, specialized electroluminescence (EL) testing equipment applies an appropriate voltage or current to the battery assembly, causing the semiconductor material inside the assembly to emit visible light. This generates an EL image. These images reveal the internal structure of the battery assembly, particularly the state of the welds, such as presence of cold solder joints, cracks, or other defects.

[0047] The specific steps of obtaining the electroluminescence image of the above-mentioned welded battery assembly include the following:

[0048] 1. Set an appropriate current or voltage based on the characteristics of the cell (typically between a few hundred milliamperes and tens of amperes). Electroluminescence detection relies on the light radiation generated by internal electron transitions in photovoltaic cells under the influence of current or voltage. Applying current or voltage to the cell stimulates internal electron transitions, producing electroluminescence.

[0049] 2. The camera should be positioned correctly to ensure that it captures the entire battery assembly or the area to be inspected. Adjust camera parameters such as exposure time and gain to capture a clear, high-contrast EL image. Exposure time is generally longer to fully capture weak electroluminescence. While applying current or voltage, the camera captures the EL image of the battery assembly. To improve inspection efficiency, a high-speed scanning camera may be used, capable of capturing multiple images in a short period of time.

[0050] 3. The captured raw image may need to be corrected to eliminate effects such as lens distortion and uneven lighting. The processed image should be saved to a computer system for analysis by the defect recognition model. The captured and processed EL image should be transferred to the server or workstation of the defect recognition system. Ensure that the image is stored in an appropriate format to facilitate subsequent data management and analysis.

[0051] In step S202, the electroluminescent image of the welded battery assembly is input into a defect recognition model to obtain defect parameters of the welded battery assembly. The defect parameters are either no defect or the defect type of the welded battery assembly. The defect recognition model includes multiple sub-models, wherein different defect types are identified using different sub-models.

[0052] The electroluminescence image (EL image) is input into a defect recognition model composed of multiple sub-models. These sub-models may include, but are not limited to, deep learning models, support vector machines (SVMs), and decision trees. Each sub-model has its own unique strengths and ability to identify specific types of defects. Each sub-model focuses on identifying a specific type of defect, and by working together, comprehensive defect detection results can be obtained. For example, one sub-model may specialize in identifying cold solder joints, while another may be more adept at detecting cracks. The defect recognition model analyzes EL image features such as brightness distribution, texture variations, and color differences to determine whether a battery component has defects and the specific defect type.

[0053] In existing technology, 4K line scan cameras are generally used to capture images of welded battery components and then input these images into existing defect recognition models for defect identification. A 4K line scan camera is a high-resolution linear array camera primarily used for high-precision inspection and imaging applications in industrial automation. Line scan cameras operate by scanning and imaging the surface of a continuously moving object using one or more linear image sensors. Unlike area scan cameras, which capture an entire area at once, line scan cameras capture image information line by line (or point by point) as the object moves. 4K resolution refers to a pixel count of 4096 or 3840 per line, depending on the standard. For example, digital films typically use a resolution of 4096×2160, while consumer-grade ultra-high-definition televisions use a resolution of 3840×2160.

[0054] The electroluminescence (EL) images used in the embodiments of this application offer multiple advantages over images obtained with 4K line scan cameras in photovoltaic module inspection. These advantages are primarily reflected in defect detection sensitivity, image interpretability, and the ability to reveal internal defects. Specifically, they are as follows:

[0055] 1. Highly sensitive identification of internal defects: EL images can reveal subtle defects within battery components, such as microcracks, hidden cracks, or localized cell performance degradation, which are difficult to detect with surface images (such as those captured by 4K line scan cameras). Under the electroluminescence effect, defective areas will appear different in brightness from normal areas, providing a direct and obvious signal for defect identification.

[0056] 2. Visually Demonstrate Electrical Performance: EL images not only reveal physical defects but also provide a visual representation of the electrical performance of the battery module. In EL images, the brightness of the cell is closely correlated with its electrical performance. Therefore, EL images can be used to quickly assess the cell's operating status, such as short circuits or power drops, which is crucial for ensuring the overall performance of the battery module.

[0057] 3. Adaptability to Complex Environments: EL imaging is performed in a darkroom, effectively shielding against external light interference and ensuring image quality is unaffected by external light. However, the imaging quality of 4K line scan cameras can be affected by factors such as ambient lighting conditions and camera settings. In particular, unstable lighting conditions can affect image clarity and contrast.

[0058] 4. Detailed Defect Type Identification: EL images can more accurately distinguish different types of defects, such as cold solder joints, cracks, short circuits, and power loss. This is critical for targeted adjustments to production parameters and process optimization. Images from 4K line scan cameras are primarily used to detect surface defects and are less capable of distinguishing internal or electrical defects.

[0059] In summary, EL images demonstrate significant advantages in revealing internal defects, displaying electrical properties, and adapting to complex testing environments. They are particularly suitable for the production and quality control of photovoltaic modules, providing strong support for precise detection and process optimization.

[0060] Therefore, automatic detection and analysis of EL images replaces manual visual inspection, greatly improving detection efficiency, reducing labor costs, and avoiding human error. By continuously collecting and analyzing EL images and their corresponding defect parameters, a large amount of valuable data can be accumulated to train the model, making it perform better when dealing with more diverse and complex defects. In summary, the above steps S201-S202, through automation and intelligent means, not only improve the efficiency and accuracy of battery module welding quality inspection, but also provide important data support for dynamic parameter optimization on the production line, which helps to continuously improve the production process and enhance product quality.

[0061] In addition, the existing defect recognition model is only one model, and its recognition accuracy is low, generally below 95%. The defect recognition model of this embodiment includes multiple sub-models, each sub-model focuses on the recognition of different types of defects, and therefore can provide more accurate defect detection results, reduce the probability of false positives and false negatives, and the recognition accuracy can reach more than 99%, greatly improving the recognition rate of battery cell defects. Moreover, the existing defect recognition model does not have an autonomous learning function.

[0062] Existing defect recognition detection models generally only include one model, resulting in low accuracy of detection results. This results in 90% of the workload of manual re-judgment in the existing technology being ineffective due to the low recognition accuracy of the existing defect recognition model. In this embodiment, the multiple sub-models mentioned above include at least a deep learning algorithm, a random forest model, and an autoregressive time series model. The electroluminescent image of the above-mentioned welded battery assembly is input into the defect recognition model to obtain the defect parameters of the above-mentioned welded battery assembly, including the following steps:

[0063] Step S2021, inputting the electroluminescent image of the welded battery assembly into the first recognition sub-model;

[0064] Step S2022: If the first identification sub-model cannot identify whether the battery assembly is defective, inputting the electroluminescent image of the welded battery assembly into a second identification sub-model;

[0065] Step S2023, when the second identification sub-model cannot identify whether the battery assembly has defects, the electroluminescent image of the welded battery assembly is input into the third identification sub-model to obtain the defect parameters of the welded battery assembly; wherein the first identification sub-model, the second identification sub-model, and the third identification sub-model are respectively one of the deep learning algorithm, the random forest model, and the autoregressive time series model, and the first identification sub-model, the second identification sub-model, and the third identification sub-model are different.

[0066] Typically, the first recognition sub-model is a deep learning algorithm, such as a convolutional neural network (CNN). Deep learning models excel in image recognition and can capture complex features in EL images, such as cold solder joints and cracks. Due to their high accuracy, CNNs are used first to analyze and quickly filter out obvious defects. If the first sub-model cannot clearly identify a battery component defect, or if there is uncertainty in the defect identification, a second recognition sub-model, such as a random forest model, is activated. Random forest models can handle multi-dimensional data and are highly tolerant to data imbalance and noise, making them suitable for providing supplementary judgments when the first model is inconclusive. If the second sub-model also fails to provide a clear judgment, a third recognition sub-model, such as an autoregressive time series model, is used for further analysis. Autoregressive time series models excel at processing time series data and can analyze trends in equipment operating parameters over time and how these trends affect battery component soldering quality. In continuous production environments, such models can identify potential quality issues that are time-dependent.

[0067] Through multi-stage recognition models, defect recognition can be gradually refined and recognition accuracy can be improved, especially when dealing with complex or borderline cases. The complementarity of different types of models in recognition can enhance the robustness of the overall recognition process. Even if a single model performs poorly under certain conditions, the entire system can still make accurate judgments through the supplementation of other models. The use of a multi-model recognition strategy can analyze images from different angles, significantly reducing misjudgments and missed judgments, and improving production efficiency and product quality. In the recognition process, a model with lighter computing resources is first used for rapid screening, and a more complex model is only called when further analysis is required. This can optimize the model's training and operation resource allocation, reducing overall computing costs.

[0068] In addition, the first identification sub-model, the second identification sub-model, and the third identification sub-model include but are not limited to the above three models, and the order of the three models can also be adjusted according to actual conditions. The above steps only illustrate an optimal embodiment.

[0069] After inputting the electroluminescent image of the welded battery assembly into the defect recognition model to obtain the defect parameters of the welded battery assembly, the method further includes the following steps:

[0070] Step S301, performing a secondary inspection on the battery assembly to obtain an inspection result, wherein the inspection result indicates whether the battery assembly has a defect and the type of defect if a defect exists;

[0071] After initial defect identification, battery modules undergo secondary inspection. This step typically involves manual re-inspection or the use of higher-precision inspection equipment to verify the results of the initial defect identification. The purpose of secondary inspection is to confirm the presence of defects and more precisely define the defect type. This prevents the defect identification model from misidentifying the presence of defects in battery modules or incorrectly identifying the defect type, thereby providing a baseline or "true value" for subsequent model corrections.

[0072] Step S302, when the defect parameters of the above-mentioned welded battery assembly are defect-free, and the above-mentioned detection results indicate the presence of defects in the above-mentioned battery assembly and the defect type of the above-mentioned welded battery assembly, the above-mentioned defect recognition model is corrected using the defect parameters of the above-mentioned welded battery assembly and the above-mentioned detection results to obtain a corrected recognition model.

[0073] Specifically, if the initial defect recognition model determines that a battery component is free of defects, but secondary inspection results reveal a defect, this "false positive" or "missed negative" instance is used to correct the model. By comparing the model's predictions with actual inspection results, the machine learning algorithm can identify deficiencies in the model and adjust the model parameters accordingly. This correction is typically achieved through model training: feeding the model real data containing the defect type, allowing it to learn from its mistakes and improve its recognition capabilities in similar situations.

[0074] That is, step S301 and step S302 can actually be regarded as a semi-supervised learning process of a machine model. In the early stage, multiple manual secondary inspections may be required to continuously correct the defect recognition model. With continuous correction over a certain period of time, the recognition accuracy of the defect recognition model continues to improve, and the number of manual secondary inspections can be gradually reduced until no manual secondary inspection is required.

[0075] Through the feedback correction mechanism described above, the defect recognition model learns more comprehensive defect characteristics, gradually reducing the probability of false positives and missed detections, and improving overall detection accuracy. As the model is corrected by more false positives, it better understands the defect patterns of battery components and can make more accurate judgments even for previously unseen defect types or slight variations. As the model's accuracy improves, the number of battery components requiring manual re-inspection decreases, reducing labor costs and improving production efficiency.

[0076] Determining the defect type of the welded battery assembly and the current operating parameters of the welding equipment includes the following steps:

[0077] Step S1011, obtaining defect types of the plurality of welded battery assemblies, and determining defect locations of the respective welded battery assemblies;

[0078] The system first obtains the defect types of multiple soldered battery modules from electroluminescence (EL) images or other types of defect detection and determines the specific locations of these defects on the modules. This process relies on advanced image processing technology and pattern recognition algorithms to accurately identify defect areas such as cold solder joints and cracks and determine whether these defects occur in the same location on the battery module.

[0079] Step S1012: If the defect types of a preset number of welded battery assemblies are all target types within a preset time range, and the defect positions of the above-mentioned preset welded battery assemblies are all the same, the defect type of the above-mentioned welded battery assemblies is determined to be the above-mentioned target type, and the current operating parameters of the above-mentioned welding equipment are determined.

[0080] The preset time range may be set to 5 minutes, and the preset number is generally 3. The above step S1012 may also be equivalent to determining the target type according to the frequency of occurrence of the defect type of the welded battery assembly.

[0081] Within a certain preset time range, if the system detects that a preset number of welded battery components have the same type of defects and the locations of these defects are consistent, the system will determine the current defect type as the target type and simultaneously record the current operating parameters of the welding equipment when these defects occur, such as welding temperature, pressure, speed, etc.

[0082] Suppose the system detects defects in five battery modules within five consecutive minutes. The first module has a cold solder joint, the second has a cold solder joint, the third has a crack, the fourth has a short circuit, and the fifth has a cold solder joint. Furthermore, if the locations of the cold solder joints are identical, the target type is considered a cold solder joint. This means that if the frequency of the same defect reaches a preset level, the welding equipment parameters must be adjusted.

[0083] In other embodiments, the parameters of the welding equipment are also adjusted when the same defect occurs three times in a row. That is, the defect type of the first battery assembly, the second battery assembly, and the third battery assembly are all cold solder joints, and the cold solder joints are located in the same position.

[0084] This process of determining whether to update the welding equipment's operating parameters based on the frequency and number of defect types effectively prevents the occasional battery module defect from causing welding equipment operating parameter changes, which can lead to excessive parameter changes. For example, if frequency and number requirements are not set, then each battery module defect will require a change in the welding equipment's operating parameters, which can significantly damage the welding equipment and easily shorten its lifespan.

[0085] In some embodiments, the preparatory operating parameters of the welding device include at least a preparatory welding temperature of the welding device and a preparatory welding time of the welding device. Determining whether the preparatory operating parameters of the welding device meet the operating conditions of the welding device includes the following steps:

[0086] Step S1031, determining the calculated power of the welding equipment according to the preparatory welding temperature and the preparatory welding time of the welding equipment;

[0087] Among them, the energy demand in the welding process mainly comes from converting electrical energy into thermal energy to heat the solder so that it melts and forms good contact with the battery cell.

[0088] In some embodiments, the energy required for the welding process can be calculated according to the energy calculation formula Q=m×c×ΔT, where Q is the energy required for the welding process, m is the mass of the solder, c is the specific heat capacity of the solder, and ΔT is the temperature change, that is, the temperature change value from room temperature to the pre-welding temperature.

[0089] After calculating the energy required for the welding process according to the energy calculation formula, the power of the welding equipment required to provide the energy required for the welding process is calculated according to the power calculation formula P=Q / t, where P is the required power and t is the preparatory welding time.

[0090] The power required by the welding equipment when welding at the preparatory welding temperature and preparatory welding time is calculated according to the above energy calculation formula and power calculation formula, and it is determined whether the power exceeds the maximum power that the welding equipment can provide, so as to prevent the maximum load of the welding equipment from being exceeded during welding at the preparatory welding temperature and preparatory welding time, resulting in damage to the welding equipment.

[0091] Step S1032: if the calculated power of the welding device is less than or equal to the preset power, determining that the preliminary operation parameters of the welding device meet the operation conditions of the welding device;

[0092] The calculated theoretical power requirement is compared with a preset safe power threshold. If the calculated power is less than or equal to the preset threshold, it means that the equipment can operate safely at the currently set welding temperature and time without overload, and there is sufficient energy to complete the welding, meeting the equipment's operating conditions.

[0093] Step S1033: When the calculated power of the welding equipment is greater than the preset power, it is determined that the preliminary operation parameters of the welding equipment do not meet the operation conditions of the welding equipment.

[0094] The above steps are determined by machine learning and other judgment models. If the calculated power demand exceeds the preset power threshold, the current welding temperature and time settings will be judged as unsatisfactory for the equipment's operation. In this case, the system prevents the equipment from operating under unsafe parameters to avoid damage to the equipment or degradation of weld quality.

[0095] Specifically, the above steps ensure that the equipment operates within a safe power range, preventing overload or damage, and ensuring production safety. By verifying the equipment's power requirements under given parameters, weak welds caused by insufficient energy or component damage caused by excessive welding can be avoided, thereby improving welding quality and production efficiency. Avoiding prolonged operation of the equipment at high power reduces wear and tear on the equipment and extends its service life. This process supports automated parameter verification and adjustment, reducing reliance on manual intervention, improving production automation, and reducing the risk of human error.

[0096] In general, the preset power setting is relatively small, usually around 2W. This ensures that the preparatory operating parameters automatically selected by the system are basically within a safe range and will not exceed the maximum power withstand of the welding equipment.

[0097] If the preset power is exceeded, manual secondary testing is required to determine whether welding can be performed using the preparatory welding temperature and preparatory welding time. That is, the above method further includes the following steps:

[0098] Step S401, if the preparatory operating parameters of the welding equipment do not meet the operating conditions of the welding equipment, performing a secondary test on the preparatory operating parameters of the welding equipment to obtain a test result, wherein the test result indicates whether the welding equipment is fault-free when operating with the preparatory operating parameters;

[0099] If the preliminary operating parameters do not meet the theoretical operating conditions, these parameters will be retested, usually manually. The purpose of manual retesting is to verify the performance and stability of the welding equipment when using these preliminary operating parameters to ensure trouble-free operation of the equipment.

[0100] Step S402: The parameter generation model is corrected using the defect type of the welded battery assembly, the current operating parameters of the welding equipment, the preparatory operating parameters and the test results to obtain a corrected generation model. When the test results show that the welding equipment operates without faults using the preparatory operating parameters, the preparatory operating parameters are used to control the welding equipment to weld the unwelded battery assembly.

[0101] Specifically, if the secondary test results indicate that the welding equipment can weld without problems and that the weld quality meets the requirements when operating with the preliminary operating parameters, the system will use the defect type of the welded battery module, the current operating parameters of the welding equipment, the preliminary operating parameters, and the test results to modify the parameter generation model. The goal is to make the model more accurately reflect the relationship between the actual equipment performance and weld quality, thereby improving the model's predictive accuracy and parameter optimization capabilities.

[0102] The above steps S401 and S402 can also be viewed as a semi-supervised learning process for the machine model, where the test results of the secondary test and the corresponding preparatory operating parameters are recorded and the model is continuously trained based on this data. For example, if a set of preparatory operating parameters is obtained, and the calculated power calculated based on them is greater than the preset power, but the test result obtained from the manual secondary test indicates that welding can be performed using this set of preparatory operating parameters, then this set of preparatory operating parameters and the test result obtained from the manual secondary test are recorded in the model training. The next time this set of preparatory operating parameters is encountered, the model can directly determine that welding can be performed, without the need for manual testing again. Similarly, if a set of preparatory operating parameters is obtained, and the calculated power calculated based on them is greater than the preset power, but the test result obtained from the manual secondary test indicates that welding cannot be performed using this set of preparatory operating parameters, then this set of preparatory operating parameters and the test result obtained from the manual secondary test are recorded in the model training. The next time this set of preparatory operating parameters is encountered, the model can directly determine that welding cannot be performed, again without the need for manual testing.

[0103] In the early stages, multiple manual secondary tests may be required to continuously correct the judgment model. After a period of continuous correction, the recognition accuracy of the judgment model will continue to improve, and the number of manual secondary tests can be gradually reduced until no manual secondary tests are required.

[0104] In some embodiments, the current operating parameters of the welding device include the current welding temperature of the welding device, the current welding time of the welding device, and the current lamp power of the welding device; the preparatory operating parameters of the welding device include the preparatory welding temperature of the welding device, the preparatory welding time of the welding device, and the preparatory lamp power of the welding device. In the case where the defect type of the welded battery assembly is a cold solder joint, the magnitude relationship between the current operating parameters of the welding device and the preparatory operating parameters of the welding device satisfies at least one of the following: the preparatory lamp power of the welding device is greater than the current lamp power of the welding device, the preparatory welding temperature of the welding device is greater than the current welding temperature of the welding device, and the preparatory welding time of the welding device is greater than the current welding time of the welding device.

[0105] Specifically, for cold solder joints in already soldered battery modules, the system automatically adjusts the welding equipment's preparatory operating parameters to improve solder joint quality. Cold solder joints are typically caused by insufficient heat energy during the welding process, resulting in insufficient fusion of the solder joint. Therefore, increasing the welding equipment's lamp power, welding temperature, or welding time can increase heat supply, improve solder joint fusion, and thus reduce the occurrence of cold solder joint defects.

[0106] Suppose that a battery module produced by the welding equipment under the current welding parameters (welding temperature 350°C, welding time 2.5 seconds, lamp power 800W) has a cold solder joint defect. Based on this situation, the system adjusts the preparatory operating parameters as follows: Preparatory lamp power: Increase from 800W to 850W (increasing heat input). Preparatory welding temperature: Maintain 350°C (maintaining stable heat input). Preparatory welding time: Increase from 2.5 seconds to 3 seconds (extending heat exposure time).

[0107] By increasing heat input, such as by raising lamp power or soldering temperature, and extending the heat exposure time (i.e., soldering time), cold solder joints can be significantly reduced, improving the fusion of solder joints and the overall quality of soldered assemblies. While increasing power and temperature may slightly increase energy consumption, by reducing defective products and improving the success rate of first-time soldering, overall production efficiency is improved, reducing the cost of resoldering and material waste, ultimately leading to effective energy and cost optimization. Automated parameter adjustment reduces reliance on human judgment and manual adjustments, minimizing product quality issues caused by human error. The system makes intelligent adjustment decisions based on historical defect data and current operating parameters. Through continuous learning and optimization, it can more accurately set preliminary operating parameters, improving the scientific and rational nature of decision-making.

[0108] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for improving the yield rate of battery modules of the present application will be described in detail below with reference to specific embodiments.

[0109] This embodiment relates to a specific method for improving the yield rate of battery components, such as Figure 2As shown, the cells are first loaded from a magazine and placed onto a conveyor table using suction cups for stringing. The cells are then welded to ribbons and stringed together. The welded strings are then inspected using a defect recognition model (a combination of a deep learning algorithm, a random forest model, and an autoregressive time series model). The machine then determines whether the welded strings contain welding defects based on set thresholds and identifies the type of defect. If the welded strings are found to be free of defects, stitch welding and layout are performed. If defects are found, manual secondary testing is performed to confirm the accuracy of the determination. If the secondary testing confirms the determination is correct (i.e., a true defect is present), the parameter generation model generates new welding parameters for the welding equipment, automatically adjusting the parameters (implementing closed-loop control of the welding system). The defective strings are then repaired. If the same defects recur, photos are taken as feedback to determine the subsequent treatment strategy. If manual secondary testing confirms a misjudgment (i.e., the model misjudgment, the actual battery string has no fault or the fault type is incorrect), manual identification of the misjudgment (i.e., manual secondary testing) is performed to determine whether the battery string actually has a fault or the true fault type. Based on the results of the manual secondary testing, the defect recognition model is iteratively optimized to implement a supervised machine learning strategy, and the fault-free battery strings identified are then stitch-welded and laid out.

[0110] In existing technology, 80% of defective cell welding products are caused by cold solder joints. This defect recognition model intelligently analyzes the root cause of these defects and, based on a parameter generation model, automatically adjusts the cell welding equipment process parameters in real time, reducing the proportion of cold solder joint defects and preventing batch defects. The introduction of deep learning algorithms, random forest models, and autoregressive time series models improves AI recognition rates, conducts real-time root cause analysis of defective products, and dynamically adjusts equipment process parameters, reducing the cell string soldering defect rate and minimizing production equipment downtime.

[0111] The above-described embodiment is applicable to the online intelligent detection of defects and intelligent adjustment of equipment operating parameters during the production process of photovoltaic module cell welding. This approach addresses existing AI systems that accurately identify defects, conduct in-depth analysis of the defects, and design correction solutions for cold solder joints. The correction process involves automatically distributing the optimal parameter configuration derived from the intelligent analysis to the production equipment to achieve immediate improvement. Furthermore, the system records the results of each correction operation in detail, enabling it to iteratively optimize future parameter adjustment strategies.

[0112] The low recognition rate of component cell welding process detection in existing technologies is a pain point in the photovoltaic industry. The above-mentioned embodiments improve the accuracy of AI algorithm models through deep learning algorithms, random forest models, autoregressive time series models, etc., gradually eliminate manual re-judgment, and all detection is performed in real time by online AI of digital systems. If the same type of defect occurs three times in a row during AI quality inspection, root cause analysis is performed through AI, and the production equipment optimizes the process parameters and sends them to the machine, automatically adjusting the equipment operating status in real time, thus solving the production capacity loss caused by stopping the equipment for testing and adjustment. Defective products are eliminated in real time through automated mechanisms to prevent them from being transferred to the next process.

[0113] Compared to existing technologies, the above-mentioned embodiment adds multiple advanced AI algorithms to the existing welding equipment hardware and software. This improves the accuracy of AI models through deep learning algorithms, random forest models, and autoregressive time series models. This eliminates manual review. AI detects defects, performs real-time root cause analysis, generates optimized process parameters for the equipment, and adjusts the machine in real time, effectively preventing batch defects.

[0114] Based on a recommendation algorithm and automatic parameter adjustment technology route, with machine equipment parameters and cold soldering defect rate as input, and with the goal of reducing the cold soldering defect rate, a comprehensive consideration of process principles and machine status was implemented to build a data model. Based on a supervised machine learning algorithm, within the scope allowed by actual process conditions, the battery string defects (cold soldering) were reduced, the target cold soldering defect rate of less than 0.27% was achieved, and a steady increase in the yield rate was achieved. Based on the AI ​​detection results and the automatic parameter adjustment feedback defect rate results, the battery module failure rate caused by cold soldering decreased by approximately 79%, and the revenue in the coverage area increased by approximately 64.77 million yuan per year.

[0115] From the above description, it can be seen that the above embodiments of the present invention achieve the following technical effects:

[0116] The method for improving the yield rate of battery assemblies of the present application first determines the defect type of the welded battery assembly and the current operating parameters of the welding equipment; then, the defect type of the welded battery assembly and the current operating parameters of the welding equipment are input into a parameter generation model to obtain preliminary operating parameters of the welding equipment; then, a determination is made as to whether the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, where the operating conditions are preset conditions for the welding equipment to operate without failure; finally, if the preliminary operating parameters of the welding equipment meet the operating conditions, the preliminary operating parameters are used to control the welding equipment to weld the unwelded battery assembly to improve the yield rate of the battery assembly. This method eliminates manual re-judgment and, in the event of a defective battery assembly, performs a real-time root cause analysis of the defect and generates equipment optimization process parameters in real time. The optimized process parameters of the production equipment are distributed to the machine, and the equipment operating status is automatically adjusted in real time, effectively avoiding the production capacity loss caused by batch defects and equipment downtime for testing and adjustment. This solves the problem of low efficiency and low battery assembly production capacity in the existing method for improving the yield rate of welded battery assemblies.

[0117] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for improving the yield rate of battery components, characterized in that: include: Acquire electroluminescence images of soldered battery components; Inputting the electroluminescent image of the welded battery assembly into a defect recognition model to obtain defect parameters of the welded battery assembly, including: inputting the electroluminescent image of the welded battery assembly into a first recognition sub-model, where the first recognition sub-model is a deep learning algorithm; if the first recognition sub-model cannot identify whether the battery assembly has a defect, inputting the electroluminescent image of the welded battery assembly into a second recognition sub-model, where the second recognition sub-model is a random forest model; if the second recognition sub-model cannot identify whether the battery assembly has a defect, inputting the electroluminescent image of the welded battery assembly into a third recognition sub-model to obtain defect parameters of the welded battery assembly, where the third recognition sub-model is an autoregressive time series model, wherein the defect parameter is the defect type of the welded battery assembly, and different defect types are identified by different sub-models; Determine the current operating parameters of the welding equipment; Inputting the defect type of the welded battery assembly and the current operating parameters of the welding equipment into a parameter generation model to obtain preliminary operating parameters of the welding equipment, wherein the parameter generation model is a model trained based on an autoregressive time series model and a random forest model; Determining whether the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, where the operating conditions are preset conditions for trouble-free operation of the welding equipment; When the preliminary operating parameters of the welding equipment meet the operating conditions of the welding equipment, the preliminary operating parameters are used to control the welding equipment to weld the unwelded battery assemblies, so as to improve the yield rate of the battery assemblies.

2. The method for improving the yield rate of battery components according to claim 1, characterized in that: The preparatory operation parameters of the welding equipment include at least a preparatory welding temperature of the welding equipment and a preparatory welding time of the welding equipment. Determining whether the preparatory operation parameters of the welding equipment meet the operating conditions of the welding equipment includes: determining a calculated power of the welding device according to a pre-welding temperature of the welding device and a pre-welding time of the welding device; When the calculated power of the welding device is less than or equal to the preset power, determining that the preliminary operation parameters of the welding device meet the operation conditions of the welding device; In a case where the calculated power of the welding device is greater than the preset power, it is determined that the preliminary operation parameters of the welding device do not meet the operation conditions of the welding device.

3. The method for improving the yield rate of battery components according to claim 1, characterized in that: Determine the defect type of the welded battery assembly and the current operating parameters of the welding equipment, including: Obtaining defect types of the plurality of welded battery assemblies and determining defect locations of the respective welded battery assemblies; If within a preset time range, the defect types of a preset number of welded battery assemblies are all target types, and the defect positions of the preset number of welded battery assemblies are all the same, the defect type of the welded battery assemblies is determined as the target type, and the current operating parameters of the welding equipment are determined.

4. The method for improving the yield rate of battery components according to claim 1, characterized in that: The method further comprises: If the preliminary operating parameters of the welding equipment do not meet the operating conditions of the welding equipment, performing a secondary test on the preliminary operating parameters of the welding equipment to obtain a test result, wherein the test result indicates whether the welding equipment is fault-free when operating with the preliminary operating parameters; The parameter generation model is corrected using the defect type of the welded battery assembly, the current operating parameters of the welding equipment, the preliminary operating parameters and the test results to obtain a corrected generation model. When the test result shows that the welding equipment has no faults when operating with the preliminary operating parameters, the preliminary operating parameters are used to control the welding equipment to weld the unwelded battery assembly.

5. The method for improving the yield rate of battery components according to claim 1, characterized in that: After inputting the electroluminescent image of the welded battery assembly into a defect recognition model to obtain defect parameters of the welded battery assembly, the method further includes: Performing a secondary inspection on the battery assembly to obtain an inspection result, wherein the inspection result indicates whether the battery assembly has a defect and the type of defect if a defect exists; When the defect parameters of the welded battery assembly are defect-free and the detection results indicate the presence of defects in the battery assembly and the defect type of the welded battery assembly, the defect parameters of the welded battery assembly and the detection results are used to correct the defect recognition model to obtain a corrected recognition model.

6. The method for improving the yield rate of battery components according to claim 1, characterized in that: The current operating parameters of the welding equipment include the current welding temperature of the welding equipment, the current welding time of the welding equipment, and the current lamp power of the welding equipment. The preparatory operating parameters of the welding equipment include the preparatory welding temperature of the welding equipment, the preparatory welding time of the welding equipment, and the preparatory lamp power of the welding equipment. Among them, when the defect type of the welded battery assembly is a cold weld, the size relationship between the current operating parameters of the welding equipment and the preparatory operating parameters of the welding equipment satisfies at least one of the following: the preparatory lamp tube power of the welding equipment is greater than the current lamp tube power of the welding equipment, the preparatory welding temperature of the welding equipment is greater than the current welding temperature of the welding equipment, and the preparatory welding time of the welding equipment is greater than the current welding time of the welding equipment.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the method for improving the yield rate of battery components according to any one of claims 1 to 6.

8. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for improving the yield of a battery component according to any one of claims 1 to 6.

Images