A performance evaluation method and system based on battery tab production data analysis

Abstract

This application proposes a performance evaluation method and system based on battery tab production data analysis, relating to the field of battery tab production data analysis technology. The method includes acquiring production line data and environmental parameters during the battery tab production process. The production line data includes process parameters and equipment status information. It analyzes the characteristics in the production line data and, in conjunction with the impact of environmental parameters on microscopic defects, obtains a potential risk index for microscopic defects in the battery tabs. The characteristics include at least the characteristics of the operating process parameters. Based on the potential risk index for microscopic defects, and combined with environmental parameters and equipment status information, it generates process parameter adjustment suggestions for defect prevention. It simulates the process parameter adjustment suggestions and evaluates their effectiveness to obtain evaluation results. Based on the evaluation results, it flexibly adjusts the process parameters of the production equipment. This application can improve the overall performance and long-term reliability of batteries.

Description

Technical Field

[0001] This application relates to the field of battery tab production data analysis technology, and more specifically, to a performance evaluation method and system based on battery tab production data analysis. Background Technology

[0002] In related technologies, the battery tabs are the core components for battery current conduction. Their quality stability and consistency directly determine the overall performance and long-term reliability of the battery, making them a critical quality control link in power battery production. Currently, tab production lines are equipped with monitoring systems that can collect massive amounts of production data in real time, including process parameters, equipment status, and product testing. However, traditional manual analysis methods struggle to uncover deep-seated quality patterns in the data, making it impossible to accurately assess the comprehensive performance of products, resulting in significant shortcomings in quality control efficiency and accuracy. In actual production, tab products that pass macroscopic quality inspection still have potential quality issues. Some products are prone to slight deformation and alignment deviations during battery assembly, leading to uneven electrode layer spacing and increased assembly failure rates. This can also cause electrochemical anomalies such as high internal resistance and capacity deviations during cell formation. These problems are not caused by macroscopic defects but rather stem from differences in microscopic morphology and residual stress, such as micron-level burrs from punching and localized stress concentration. Traditional macroscopic inspection data cannot cover these microscopic physical characteristics. Although the industry has introduced high-precision testing equipment to obtain multidimensional microscopic data, the structures and dimensions of multi-source data vary greatly, making it difficult for traditional statistical methods to integrate and analyze them, and limiting the predictive capabilities of models. Meanwhile, fluctuations in variables such as workshop temperature and humidity, cleanliness, and microscopic wear of molds can have complex nonlinear interactions with process and material parameters, affecting the microscopic quality of the electrode tabs, yet these factors are not incorporated into the existing quality control system. Current technologies cannot identify early signs of defects or adaptively adjust process parameters, making it difficult to prevent subsequent production and performance anomalies from the outset. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a performance evaluation method and system based on battery tab production data analysis, which aims to solve the problem in the prior art of effectively integrating multi-source data, identifying early signs of micro-defects, and making flexible process adjustments, thereby avoiding the risk of battery tab deformation, alignment deviation, and abnormal electrochemical performance in the early stage of battery cell during subsequent battery assembly.

[0004] In a first aspect, embodiments of this application provide a performance evaluation method based on battery tab production data analysis, including: Acquire production line data and environmental parameters during the battery tab production process, wherein the production line data includes process parameters and equipment status information; By analyzing the characteristics in the production line data and combining them with the influence of the environmental parameters on micro-defects, the potential risk index of micro-defects of the battery tabs is obtained, wherein the characteristics include at least the characteristics of the operating process parameters. Based on the micro-defect potential risk index, combined with the environmental parameters and the equipment status information, process parameter adjustment suggestions for preventing defects are generated. The proposed process parameter adjustment is simulated, and its effectiveness is evaluated to obtain the evaluation results. Based on the evaluation results, the process parameters of the production equipment are flexibly adjusted.

[0005] According to some embodiments of this application, obtaining production line data and environmental parameters during the battery tab production process includes: To obtain the temperature, humidity, and air cleanliness of the production workshop during the battery tab production process; The environmental parameters are obtained based on the temperature, humidity, and air cleanliness. Acquire acoustic emission signals from the punching station and welding parameters from the welding station during the battery tab production process, wherein the welding parameters include amplitude and energy; The process parameters are obtained based on the acoustic emission signal and the welding parameters; The cumulative number of punching operations, mold material type, and punching force variation trend extracted from acoustic emission signals were obtained during the battery tab production process. The cumulative number of punching operations, the type of mold material, and the trend of punching force are quantified and weighted to obtain equipment status information.

[0006] According to some embodiments of this application, the step of analyzing the characteristics in the production line data and combining the influence of environmental parameters on micro-defects to obtain the potential risk index of micro-defects in the battery tab includes: For the acoustic emission signals contained in the production line data, a fast Fourier transform is performed on the acoustic emission signals to identify defect patterns related to micron-level burrs or local stress concentrations. Based on the identified defect patterns, feature analysis and correlation calculations are performed by combining the welding parameters and equipment status information corresponding to the production line data, and the influence of environmental parameters on micro-defects is coupled to obtain the micro-defect potential risk index.

[0007] According to some embodiments of this application, the step of performing feature analysis and correlation calculation based on the identified defect pattern, combined with the welding parameters and equipment status information corresponding to the production line data, and coupling the influence of environmental parameters on micro-defects, to obtain a micro-defect potential risk index includes: Based on the defect pattern, feature values ​​related to micron-scale burrs or localized stress concentrations are extracted from the acoustic emission signal. The influence factor of the environmental parameters on micro-defects is obtained based on the environmental parameters. Each of the feature values, welding parameters, equipment status information, and influencing factors is assigned a corresponding weighting coefficient. The potential risk index of micro-defects is obtained by weighting and summing the corresponding weight coefficients, the feature values, the welding parameters, the equipment status information, and the influencing factors.

[0008] According to some embodiments of this application, the step of performing a fast Fourier transform on the acoustic emission signal to identify defect patterns related to micron-level burrs or localized stress concentrations includes: Perform a fast Fourier transform on the acoustic emission signal to analyze the energy distribution of the acoustic emission signal within a preset frequency range; Calculate the root mean square value of the acoustic emission signal; Based on the energy distribution, the root mean square value, and the preset energy threshold, identify and count instantaneous impact events exceeding the preset energy threshold; Based on the instantaneous impact event, defect patterns associated with micron-level burrs or localized stress concentrations are identified.

[0009] According to some embodiments of this application, the step of generating process parameter adjustment suggestions for preventing defects based on the micro-defect potential risk index, combined with the environmental parameters and the equipment status information, includes: When the potential risk index of micro-defects shows an upward trend and exceeds the preset defect alarm threshold, the analysis results are obtained by combining the potential risk index of micro-defects, the environmental parameters, and the equipment status information. When the analysis results indicate that defects are concentrated on the parting surface and molding edge, the main causes of micro-defects are determined to be mold wear and increased burr risk, and potential stress concentration risk in the welding area. When the analysis results characterize the stress accumulation at the locations of geometric abrupt changes in the weld and the enrichment locations of micro-defects, it is determined that the main cause of the micro-defects is the potential stress concentration risk in the weld area; Based on the main causes of the microscopic defects, recommendations for adjusting process parameters to prevent defects are generated.

[0010] According to some embodiments of this application, generating process parameter adjustment recommendations for defect prevention based on the primary cause of the microscopic defects includes: When the main cause of the micro-defects is characterized as mold wear and increased burr risk, process parameter adjustment recommendations are generated to prevent the defects. These recommendations include reducing the rising slope of the punching pressure curve and / or reducing the punching speed. When the main cause of the micro-defect is characterized to indicate a potential stress concentration risk in the welded area, process parameter adjustment suggestions are generated to prevent the defect. These suggestions include increasing welding energy and / or extending welding time.

[0011] According to some embodiments of this application, the step of simulating the proposed process parameter adjustment and evaluating its effectiveness to obtain an evaluation result includes: Obtain the material properties, geometric structure, and physical model of the battery tabs and battery assembly process; Based on the material properties, the geometry, and the physical model of the battery assembly process, the proposed process parameter adjustment was simulated, and simulation results were obtained. The effects of adjusting process parameters on the microstructure of the battery tabs during production, downstream assembly performance, and initial electrochemical performance were predicted, and the prediction results were obtained. The effectiveness of the proposed process parameter adjustment is evaluated based on the simulation results and the prediction results, and the evaluation results are obtained.

[0012] According to some embodiments of this application, the step of flexibly adjusting the process parameters of the production equipment based on the evaluation results includes: When the evaluation result indicates that the process parameter adjustment suggestion is effective, the process parameters of the production equipment are flexibly adjusted in an online non-stop progressive adjustment manner according to the preset step size. The flexible adjustment is a multi-equipment collaborative adaptive fine adjustment, including modifying the pressure setting value and punching speed of the punching machine, or the energy output parameters of the welding machine. When the evaluation result indicates that the process parameter adjustment suggestion is invalid, the process parameter adjustment suggestion is regenerated until the evaluation result indicates that the process parameter adjustment suggestion is valid, and the process parameters of the production equipment are flexibly adjusted according to the preset step size.

[0013] Secondly, this application also discloses a performance evaluation system based on battery tab production data analysis, comprising: The acquisition module is used to acquire production line data and environmental parameters during the battery tab production process. The production line data includes process parameters and equipment status information. The analysis module is used to analyze the features in the production line data and, in combination with the influence of the environmental parameters on micro-defects, obtain the potential risk index of micro-defects of the battery tabs, wherein the features include at least the features of the operating process parameters. The generation module is used to generate process parameter adjustment suggestions for preventing defects based on the micro-defect potential risk index, combined with the environmental parameters and the equipment status information. An evaluation module is used to simulate the proposed process parameter adjustment and evaluate its effectiveness to obtain evaluation results. The adjustment module is used to flexibly adjust the process parameters of the production equipment based on the evaluation results.

[0014] The technical solution according to the embodiments of this application has at least the following beneficial effects: This application provides a performance evaluation method based on battery tab production data analysis. This application can effectively integrate multi-source heterogeneous data, including production line data (process parameters, equipment status information) and environmental parameters, overcoming the limitations of traditional methods in handling massive and complex data. Through in-depth mining of high-dimensional data such as acoustic emission signals, defect patterns related to micron-level burrs or local stress concentrations can be identified, thereby revealing deep-seated microscopic physical characteristics closely related to subsequent processes, solving the problem that existing technologies cannot accurately evaluate the microscopic performance of products. This application introduces a microscopic defect potential risk index to achieve early warning of defect precursors. Before microscopic defects form, through in-depth interpretation of multi-source information, potential defect precursors can be identified, thereby providing a basis for preventive adjustments and avoiding the passive situation of remediation only after defects occur. Furthermore, this application can generate targeted process parameter adjustment suggestions based on the potential risks and specific causes of defects, and verify their effectiveness through simulation, avoiding production risks caused by blind adjustments. Ultimately, by flexibly adjusting the production equipment online without stopping the machine, intelligent and adaptive optimization of the production process was achieved, preventing the risks of deformation, alignment deviations, and abnormal electrochemical performance of the battery tabs during subsequent battery assembly from the outset. In summary, the method of this application can significantly improve the production quality and consistency of battery tabs, reduce the defect rate, and improve the overall performance and long-term reliability of the battery.

[0015] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0016] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0017] Figure 1 A flowchart illustrating a performance evaluation method based on battery tab production data analysis, provided as an embodiment of this application; Figure 2 This is a schematic diagram of a performance evaluation system based on battery tab production data analysis, provided as an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical methods, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] It should be noted that the meaning of "multiple" (or "more than") in the description of the embodiments of this application refers to two or more, and "greater than," "less than," "exceeding," etc. are understood to exclude the number itself, while "above," "below," "within," etc. are understood to include the number itself. If "first," "second," etc. are used in the description, they are only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0020] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: the existence of a alone, the existence of b alone, the existence of c alone, the simultaneous existence of a and b, the simultaneous existence of a and c, the simultaneous existence of b and c, or the simultaneous existence of a, b, and c, where a, b, and c can be single or multiple.

[0021] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0022] The performance evaluation method based on battery tab production data analysis provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms; the software can be an application that implements the performance evaluation method based on battery tab production data analysis, but is not limited to the above forms.

[0023] The embodiments of this application can be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside in local and remote computer storage media, including storage devices.

[0024] See Figure 1 , Figure 1 This is a flowchart illustrating a performance evaluation method based on battery tab production data analysis, provided in one embodiment of this application. The performance evaluation method based on battery tab production data analysis provided in this embodiment includes, but is not limited to, steps S110 to S150, which are described below.

[0025] Step S110: Obtain production line data and environmental parameters during the battery tab production process. The production line data includes process parameters and equipment status information. Step S120: Analyze the features in the production line data and combine them with the influence of environmental parameters on micro-defects to obtain the potential risk index of micro-defects of the battery tabs. The features include at least the features of the operating process parameters. Step S130: Based on the potential risk index of micro-defects, combined with environmental parameters and equipment status information, generate process parameter adjustment suggestions for preventing defects; Step S140: Simulate the proposed process parameter adjustment and evaluate its effectiveness to obtain the evaluation results; Step S150: Based on the evaluation results, flexibly adjust the process parameters of the production equipment.

[0026] It should be noted that "battery tabs" refer to the thin metal sheets in lithium-ion batteries used to connect the internal electrodes of the cell to the external circuitry; their quality directly affects the battery's conductivity and safety. "Production line data" encompasses all quantifiable information during the production process, including "process parameters" (such as punching force, welding current, and speed) and "equipment status information" (such as mold wear and equipment uptime). "Environmental parameters" refer to external conditions within the production workshop, such as temperature, humidity, and air cleanliness, that may affect product quality. The "microscopic defect potential risk index" is a quantitative indicator used to assess the likelihood of defects in the battery tabs at the microscopic level (such as burrs and stress concentration). "Process parameter adjustment recommendations" are specific operational instructions proposed to optimize the production process based on risk assessment results, such as adjusting punching pressure and welding energy. "Simulation" refers to predicting the effects of process parameter adjustments through mathematical models and computer simulations. "Flexible adjustment" emphasizes that production equipment can make small, rapid, and adaptive adjustments to process parameters based on assessment results, rather than simply shutting down or making drastic modifications.

[0027] In one embodiment, it is first necessary to acquire production line data and environmental parameters during the battery tab production process. Production line data can be acquired by deploying various sensors on the production line. For example, current sensors, voltage sensors, pressure sensors, and speed sensors can be used to collect process parameters at the punching and welding stations in real time. Equipment status information can be acquired through the equipment's built-in diagnostic system or additional sensors, such as recording the cumulative number of punching operations and the type of mold material. Environmental parameters can be acquired by installing temperature and humidity sensors, air cleanliness sensors, etc., in the production workshop. These sensors can periodically collect data and transmit it to the central data processing unit. After acquiring the production line data and environmental parameters, the characteristics in the production line data need to be analyzed, and the impact of environmental parameters on microscopic defects needs to be considered to obtain the potential risk index of microscopic defects in the battery tabs. Various data analysis techniques can be used when analyzing the characteristics in the production line data. For example, statistical analysis can be performed on the collected process parameters to calculate their mean, variance, peak value, and other statistical characteristics. For equipment status information, trend analysis can be performed, for example, analyzing the trend of mold wear over time. When considering the impact of environmental parameters on microscopic defects, a correlation model between environmental parameters and microscopic defects can be established. For example, historical data analysis reveals that high temperature and high humidity environments may increase the risk of electrode surface oxidation or stress concentration. Ultimately, by comprehensively analyzing these characteristics and effects, a quantitative microscopic defect potential risk index can be calculated.

[0028] In one embodiment, based on a micro-defect potential risk index, combined with environmental parameters and equipment status information, process parameter adjustment suggestions for defect prevention are generated. When the micro-defect potential risk index reaches or exceeds a preset threshold, the system triggers an early warning. At this point, further analysis of the specific reasons for the increased risk is required. For example, if the increase in the risk index is related to increased mold wear, it may be necessary to adjust the punching pressure or punching speed. If the increase in the risk index is related to fluctuations in welding parameters, it may be necessary to adjust the welding energy or welding time. When generating process parameter adjustment suggestions, a rule-based expert system or a machine learning model can be used to automatically generate the optimal adjustment scheme based on historical data and empirical knowledge. Subsequently, the process parameter adjustment suggestions are simulated, and their effectiveness is evaluated to obtain the evaluation results. The simulation process can be implemented by establishing a digital twin model of the battery tab production process. This model can simulate the punching and welding processes of the tab under different process parameters and predict the micro-characteristics of the tab (such as burr height and residual stress distribution) and its impact on downstream assembly and electrochemical performance. For example, the change in burr height at the tab edge after adjusting the punching pressure can be simulated. Simulation allows for the rapid verification of the effectiveness of process parameter adjustment recommendations without actual changes to the production line, avoiding production losses caused by blind adjustments. Finally, based on the evaluation results, the process parameters of the production equipment are flexibly adjusted. If the simulation evaluation results indicate that the process parameter adjustment recommendations are effective, they can be applied to the actual production equipment. Flexible adjustment means that the adjustment process is gradual, with small steps, and can adaptively correct itself based on real-time feedback from the production line. For example, the pressure setpoint or cutting speed of the punching machine can be gradually modified in preset steps, or the energy output parameters of the welding machine can be adjusted. This flexible adjustment method minimizes the impact on production stability and ensures a smooth transition during the adjustment process. If the evaluation results indicate that the process parameter adjustment recommendations are ineffective, new process parameter adjustment recommendations need to be re-analyzed and generated until an effective solution is found.

[0029] It should be noted that this application generates process parameter adjustment suggestions for defect prevention and verifies them through simulation, ultimately achieving flexible adjustment of production equipment and forming a closed-loop quality control system. This flexible adjustment mechanism enables the production line to adaptively optimize based on real-time data and evaluation results, thereby preventing the risk of electrode deformation, alignment deviations, and abnormal electrochemical performance in the early stages of cell assembly from the outset. This proactive prevention and adaptive adjustment capability significantly improves the production quality and consistency of battery electrodes, providing a solid guarantee for the long-term reliability of power batteries.

[0030] Specifically, the aforementioned acquisition of production line data and environmental parameters during the battery tab production process includes: To obtain the temperature, humidity, and air cleanliness of the production workshop during the battery tab production process; Environmental parameters are obtained based on temperature, humidity, and air cleanliness; Acoustic emission signals from the punching station and welding parameters from the welding station during the battery tab production process are obtained. The welding parameters include amplitude and energy. The process parameters are obtained based on the acoustic emission signal and welding parameters; The cumulative number of punching operations, mold material type, and punching force variation trend extracted from acoustic emission signals were obtained during the battery tab production process. The cumulative number of punching operations, die material type, and punching force variation trend are quantified and weighted to obtain equipment status information.

[0031] The acquisition of temperature, humidity, and air cleanliness in the production workshop aims to comprehensively monitor key factors affecting the battery tab production environment. These environmental factors have direct or indirect impacts on material properties, equipment operational stability, and the formation of micro-defects. Acoustic emission signals can sensitively reflect transient events such as microcracks and plastic deformation generated during the punching process, providing real-time monitoring data for punching quality. Welding parameters, such as amplitude and energy, are key factors affecting weld quality and weld microstructure. The cumulative number of punching cycles of the die is directly related to its wear level, while the die material type determines its inherent properties and lifespan. The punching force variation trend extracted from acoustic emission signals can reflect the stress and wear state of the die during the punching process in real time. Quantifying and weighting these data yields comprehensive equipment status information reflecting the equipment's operating status and potential failure risks. Quantification unifies different types of data into comparable values, while weighted calculation assigns different weights based on the importance of each factor's impact on equipment status, thereby more accurately assessing equipment status. By acquiring data on temperature, humidity, and air cleanliness in the production workshop, the impact of environmental factors on the battery tab production process can be accurately captured, providing crucial environmental background information for subsequent analysis of potential risks related to micro-defects. Simultaneously, by collecting acoustic emission signals from the punching station and welding parameters (including amplitude and energy) from the welding station, key physical events and energy inputs in the production process can be reflected in real-time and dynamically. This data is essential for identifying process anomalies directly related to micro-defects. Furthermore, by acquiring the cumulative number of punching operations, die material type, and punching force trends, and performing quantitative weighted calculations, the wear and health of equipment, particularly the die, can be systematically assessed, providing a quantitative basis for equipment status information. These detailed data acquisition methods work together to ensure the comprehensiveness and accuracy of the input data, providing solid data support for subsequent micro-defect potential risk index analysis, process parameter adjustment recommendations, and simulation evaluation.

[0032] In response, this application further proposes the following steps for obtaining the potential risk index of micro-defects in battery tabs by analyzing the characteristics in the production line data and combining them with the influence of environmental parameters on micro-defects: For the acoustic emission signals contained in the production line data, a fast Fourier transform is performed on the acoustic emission signals to identify defect patterns related to micron-level burrs or local stress concentrations. Based on the identified defect patterns, feature analysis and correlation calculations are performed by combining the welding parameters and equipment status information corresponding to the production line data, and the influence of environmental parameters on micro-defects are coupled to obtain the potential risk index of micro-defects.

[0033] Specifically, the acoustic emission signals acquired from the production line data are processed using Fast Fourier Transform (FFT). FFT is a mathematical method that converts time-domain signals into frequency-domain signals, aiming to reveal the energy distribution of different frequency components within the signal. By analyzing the characteristics of the acoustic emission signals in the frequency domain, specific defect modes associated with micron-level burrs or localized stress concentrations can be effectively identified. Welding parameters, such as amplitude and energy, directly affect weld quality and stress distribution within the tabs; equipment status information, such as the cumulative number of punching operations for the die, the die material type, and the trend of punching force extracted from the acoustic emission signals, reflects equipment wear and processing accuracy. Correlation analysis of these parameters with defect modes allows for a deeper understanding of defect formation mechanisms. Environmental parameters, such as temperature, humidity, and air cleanliness in the production workshop, may indirectly or directly exacerbate the formation or development of microscopic defects by affecting material properties, equipment stability, or contaminant adhesion. For example, high humidity environments may accelerate die corrosion, thereby increasing the risk of burrs. This application's solution, by introducing Fast Fourier Transform (FFT) analysis of acoustic emission signals, can transform minute impact events or energy fluctuations that are difficult to detect in the time domain into identifiable defect patterns in the frequency domain. This frequency domain analysis method makes it possible to identify hidden defects such as micron-sized burrs or localized stress concentrations at an early stage, overcoming the limitation of traditional methods that may miss key information due to signal complexity. Furthermore, by performing multi-dimensional and in-depth feature analysis and correlation calculations with these identified defect patterns and welding parameters, equipment status information, and environmental parameters, this solution can reveal the complex causal relationships behind defect formation. For example, specific high-frequency components in the acoustic emission signal may indicate the generation of burrs. When this signal coincides with an excessively high cumulative punching count in the die, abnormal punching force trends, and a high-humidity environment, it can be more accurately determined that the root cause of the burrs lies in the synergistic effect of die wear and environmental factors.

[0034] In some embodiments, it is assumed that acoustic emission signals are continuously collected by an acoustic emission sensor at the punching station of the battery tab. When the die begins to show slight wear, the minute friction and material fracture generated during the punching process will produce high-frequency transient impacts in the acoustic emission signals. At this time, performing a fast Fourier transform on the collected acoustic emission signals reveals abnormal energy peaks or energy distribution changes in a preset high-frequency range (e.g., 50kHz-200kHz), which are identified as defect modes related to micron-level burrs. Simultaneously, the system records that the cumulative number of punching operations for the die is approaching its design life limit, and the punching force shows slight fluctuations. Furthermore, the humidity sensor in the production workshop indicates that the current humidity is higher than normal. Based on this information—the burr defect mode identified by the acoustic emission signals, the equipment status information of the die wear, and the high humidity environmental parameters—the system uses a preset correlation calculation model to weight and sum these factors, thereby calculating a high potential risk index for microscopic defects. The upward trend of the index and its exceeding of the preset threshold clearly indicate that the battery tabs are about to face the risk of burr defects, which may be accompanied by local stress concentration, thus providing a timely and strong basis for subsequent process adjustments.

[0035] Specifically, based on the identified defect patterns, feature analysis and correlation calculations are performed by combining the welding parameters and equipment status information corresponding to the production line data, and the influence of environmental parameters on micro-defects are coupled to obtain a micro-defect potential risk index, which can be further implemented in the following ways: Based on the defect mode, feature values ​​related to micron-scale burrs or local stress concentrations are extracted from the acoustic emission signal. The influence factors of environmental parameters on micro-defects are obtained based on environmental parameters. Preset corresponding weight coefficients for characteristic values, welding parameters, equipment status information, and influencing factors; The potential risk index of micro-defects is obtained by weighting and summing the corresponding weight coefficients, eigenvalues, welding parameters, equipment status information and influencing factors.

[0036] After identifying specific defect patterns, numerical indicators directly related to these defect patterns are further quantified and extracted from the original acoustic emission signals. These features can include peak amplitude, energy, duration, rise time, and ring count of the acoustic emission signal. These indicators directly reflect the intensity of micron-level burr formation or the degree of local stress concentration. Extracting these features provides quantitative input for subsequent risk assessment. Environmental parameters such as temperature, humidity, and air cleanliness in the production workshop are transformed into one or more quantified influencing factors. For example, higher humidity may increase the risk of material oxidation, and lower air cleanliness may lead to dust adhesion, both of which may exacerbate the formation or worsening of micro-defects. Influencing factors can be empirical values, calculated values ​​based on physical models, or values ​​predicted by machine learning models. Different levels of importance are assigned to the above input data. These weighting coefficients can be set based on expert experience, historical data analysis, or optimization algorithms. If historical data shows that welding parameters have the most significant impact on micro-defects, a higher weighting coefficient can be assigned; if equipment condition information (such as mold wear) plays a decisive role in burr formation, its weighting coefficient will also be increased accordingly. By pre-setting weighting coefficients, it can be ensured that each factor is considered according to its true impact during comprehensive evaluation. This involves multiplying each of the aforementioned quantitative indicators by its corresponding weighting coefficient, then summing all the multiplications to calculate a comprehensive, quantitative micro-defect potential risk index. This weighted summation method integrates data from multiple dimensions into a single risk indicator, making the risk assessment results more representative and operable. Through this technical solution, a refined and quantitative assessment of the potential risk of micro-defects in battery tabs can be achieved. Compared to qualitative judgments based solely on defect patterns, this solution significantly improves the accuracy and reliability of risk assessment by introducing multi-source data (feature values, welding parameters, equipment status information, and environmental impact factors) and performing weighted summation. This comprehensive assessment method can identify potential micro-defect risks earlier and more accurately, providing stronger data support for subsequent process parameter adjustments, thereby effectively preventing defects and improving the production quality and consistency of battery tabs.

[0037] In this regard, this application further proposes the following steps for performing a fast Fourier transform on the acoustic emission signal to identify defect modes related to micron-level burrs or local stress concentrations: Perform a fast Fourier transform on the acoustic emission signal to analyze the energy distribution of the acoustic emission signal within a preset frequency range; Calculate the root mean square value of the acoustic emission signal; Based on energy distribution, root mean square value, and preset energy threshold, identify and statistically analyze instantaneous impact events exceeding the preset energy threshold; Identify defect patterns associated with micron-level burrs or localized stress concentrations based on instantaneous impact events.

[0038] Specifically, acoustic emission signals refer to transient elastic wave signals released by materials during deformation or fracture, carrying rich information about changes in the material's internal microstructure. Fast Fourier Transform (FFT) is a mathematical method that converts time-domain signals into frequency-domain signals. By performing FFT on acoustic emission signals, their energy distribution at different frequencies can be analyzed, revealing frequency characteristics related to specific defect types. For example, micron-sized burrs or localized stress concentrations typically exhibit abnormal energy concentration in specific high-frequency bands of the acoustic emission signal. The preset frequency range refers to a frequency interval determined based on experience or experimental data, related to the defect patterns of micron-sized burrs or localized stress concentrations that may occur during battery electrode manufacturing. By analyzing the energy distribution within this preset frequency range, signal characteristics related to defects can be effectively focused on, eliminating interference from irrelevant noise. The root mean square (RMS) value is a commonly used indicator for measuring signal strength or energy; calculating the RMS value of an acoustic emission signal reflects the overall activity level of the signal. When microscopic defects occur within the material (such as burr formation or stress concentration), it is usually accompanied by a significant increase in the intensity of the acoustic emission signal, which is reflected in the RMS value. A preset energy threshold is a key parameter used to distinguish between normal and abnormal signals. Transient impact events refer to short-duration events in acoustic emission signals where the energy suddenly increases and exceeds the preset energy threshold. These transient impact events are often directly related to microscopic defect behaviors such as the propagation of microcracks within materials, particle shedding, or localized stress release. By identifying and statistically analyzing these transient impact events, the frequency and intensity of defect occurrence can be quantified. Therefore, based on the characteristics of the identified transient impact events (e.g., their frequency components, duration, amplitude, etc.), specific defect patterns related to micron-sized burrs or localized stress concentrations can be further identified. For example, high-frequency, short-duration, high-energy impact events may indicate burr formation, while events with slightly longer durations and energy distribution in a specific mid-frequency band may be related to localized stress concentrations.

[0039] In one embodiment, by performing multi-dimensional analysis of the acoustic emission signal, the time-domain signal is first converted into a frequency-domain signal using a Fast Fourier Transform (FFT), thereby capturing the specific frequency energy distribution characteristics related to microscopic defects. Simultaneously, by combining the root mean square (RMS) value with the quantification of the overall signal strength, the activity level of acoustic emission can be comprehensively determined. When the energy distribution of the acoustic emission signal becomes abnormal within a preset frequency range, and the signal strength indicated by its RMS value exceeds a preset energy threshold, a transient impact event can be identified.

[0040] In this regard, this application further proposes the following steps for generating the above-mentioned process parameter adjustment suggestions for preventing defects: When the potential risk index of micro-defects shows an upward trend and exceeds the preset defect alarm threshold, the analysis results are obtained by combining the potential risk index of micro-defects, environmental parameters and equipment status information. When the analysis results indicate that the defects are concentrated on the parting surface and the molding edge, the main causes of the micro defects are mold wear and increased risk of burrs, and potential stress concentration risk in the welding area. When the analysis results characterize the stress accumulation at the locations of geometric abrupt changes in the weld and the locations of micro-defect enrichment, it is determined that the main cause of the micro-defects is the potential stress concentration risk in the weld area. Based on the main causes of microscopic defects, recommendations for adjusting process parameters to prevent defects are generated.

[0041] Specifically, the system continuously monitors changes in the potential risk index of micro-defects. Once this index not only continues to rise but also exceeds a pre-set safety limit, a defect alarm mechanism is triggered. At this point, the system will conduct in-depth analysis by comprehensively considering the current potential risk index of micro-defects, real-time environmental parameters, and equipment status information to obtain preliminary analysis results regarding the nature and location of the defects. The analysis results indicate that defects are concentrated on the parting surface and forming edge. This means that through comprehensive analysis of production line data and environmental parameters, it was found that micro-defects mainly appear in the punching parting surface or forming edge area of ​​the battery tabs. This phenomenon usually indicates that the mold may be worn, leading to a decrease in punching quality and increasing the risk of burr formation; it may also suggest potential stress concentration risks in the welding area at these specific locations. Analysis results show that defects are mainly concentrated at locations where the weld geometry changes drastically, or that the number of micro-defects increases significantly in certain specific areas, and these locations are accompanied by stress concentration. This usually indicates that the welding process parameters may be inappropriate, leading to excessive local stress during the welding process, thus causing micro-defects.

[0042] In this regard, this application further proposes the following steps for generating process parameter adjustment suggestions for defect prevention based on the main causes of microscopic defects: When the main cause of micro-defects is characterized by mold wear and increased burr risk, process parameter adjustment recommendations are generated to prevent defects. These recommendations include reducing the rising slope of the punching pressure curve and / or reducing the punching speed. When the main cause of micro-defects is characterized to indicate a potential risk of stress concentration in the welded area, process parameter adjustment recommendations are generated to prevent the defects. These recommendations include increasing welding energy and / or extending welding time.

[0043] Specifically, when system analysis indicates that the main cause of micro-defects is mold wear and increased burr risk, the generated process parameter adjustment suggestions will focus on optimizing the punching process. "Reducing the slope of the punching pressure curve" means slowing down the rate at which the punching force rises from its initial value to its maximum value during the punching process. This helps reduce the instantaneous impact between the mold and the material, thereby mitigating mold wear and reducing the risk of burr formation on material edges due to rapid punching. Simultaneously, "reducing the punching speed" means decreasing the stroke of the punching head or die per unit time, which also reduces impact and friction during the punching process, further suppressing burr formation and extending mold life. On the other hand, when the system determines that the main cause of micro-defects is the potential stress concentration risk in the weld area, the generated process parameter adjustment suggestions will focus on optimizing the welding process. "Increasing welding energy" means increasing the energy input to the weld area by the welding equipment per unit time. This helps ensure sufficient weld fusion, improves the internal structure of the weld, effectively disperses stress, and reduces stress concentration caused by insufficient welding or localized overheating. "Extending welding time" refers to increasing the duration for which the welding equipment applies energy to the welding area. This can also promote the uniform formation and stress release of the weld, further reduce the risk of stress concentration in the welding area, and improve the overall strength and reliability of the weld.

[0044] In one embodiment, when increased die wear and burr risk are identified, reducing the slope of the punching pressure curve and / or reducing the punching speed can effectively reduce mechanical impact and friction during the punching process, directly addressing the root cause of die wear and suppressing burr formation. This targeted adjustment can improve punching quality at a physical level and reduce microscopic defects at material edges. When potential stress concentration risks are identified in the welding area, increasing welding energy and / or extending welding time can optimize heat input and melting state during the welding process, promoting uniform weld formation and effective release of internal stress. This adjustment helps improve the microstructure of the weld, avoiding potential defects caused by localized stress concentration, thereby improving the overall performance and reliability of the battery tabs. Therefore, the solution of this application ensures that the generated process parameter adjustment suggestions can directly and effectively address the root cause of defects, avoiding blind or ineffective adjustments.

[0045] In some embodiments, assuming that during the production of battery tabs, through analysis of production line data and environmental parameters, the system identifies an upward trend in the potential risk index of micro-defects, and the analysis results characterize that defects are concentrated at the parting surface and forming edges. Further, the system determines that the main cause of micro-defects is mold wear and increased burr risk. At this point, this application will generate process parameter adjustment suggestions for defect prevention, specifically including reducing the rising slope of the punching pressure curve, for example, adjusting the rising slope from 50 MPa per millisecond to 30 MPa per millisecond, while simultaneously reducing the punching speed from 100 mm / s to 80 mm / s. Through these adjustments, the impact force of the punching process is effectively buffered, the mold wear rate is slowed down, thereby significantly reducing the generation of burrs at the edges of the battery tabs. As another specific implementation, assuming that the system analysis results characterize stress accumulation at weld geometry abrupt change locations and micro-defect enrichment locations, the main cause of micro-defects is determined to be the potential stress concentration risk in the welding area. In this context, this application will generate recommendations for adjusting process parameters to prevent defects, such as increasing welding energy from 100 joules to 120 joules and extending welding time from 50 milliseconds to 60 milliseconds. By increasing energy and extending welding time, the weld area can obtain more sufficient heat input and a longer melting time, allowing the weld metal to diffuse and solidify more uniformly, effectively releasing internal stress, thereby avoiding microcracks or fatigue failure caused by stress concentration, and improving the welding quality and long-term reliability of the battery tabs.

[0046] The above-mentioned process parameter adjustment suggestions were simulated, and the effectiveness of the process parameter adjustment suggestions was evaluated. The evaluation results include: Obtain the material properties, geometry, and physical model of the battery tabs and battery assembly process; Based on the physical model of material properties, geometry, and battery assembly process, simulations were performed to propose adjustments to process parameters, and simulation results were obtained. The effects of adjusting process parameters on the microstructure of the battery tabs during production, downstream assembly performance, and initial electrochemical performance were predicted, and the prediction results were obtained. The effectiveness of the proposed process parameter adjustments is evaluated based on the simulation and prediction results, and the evaluation results are obtained.

[0047] Specifically, obtaining the material properties of battery tabs refers to collecting data on the mechanical properties (such as yield strength, tensile strength, and elastic modulus), thermal properties (such as thermal conductivity and specific heat capacity), and electrical properties (such as resistivity) of the materials used in the tabs (e.g., aluminum, nickel). Geometric structure refers to detailed information such as the size, shape, thickness, and edge contour of the tabs. The physical model of the battery assembly process can be understood as a mathematical or simulation model describing the force, heat, and electrical physical effects on the battery tabs during subsequent assembly processes (such as stacking, winding, welding, and encapsulation). Its purpose is to simulate the stress deformation, thermal stress distribution, and contact state with other components of the tabs during assembly. Based on the aforementioned material properties, geometric structure, and the physical model of the battery assembly process, simulations can be performed to suggest adjustments to process parameters. Finite element analysis (FEA) software can be used to simulate the stress distribution, deformation, and temperature field changes inside the tabs after adjusting punching or welding parameters, thereby obtaining simulation results. By employing data analysis, machine learning models, or expert systems, and based on simulation results and historical data, this study infers the impact of process adjustments on microscopic features such as tab surface roughness, burr formation, grain structure, and internal defects; the impact on tab performance in subsequent battery assembly stages (e.g., compatibility with separators, positive and negative electrode materials, welding quality, stacking precision); and the impact on initial electrochemical performance such as capacity, internal resistance, and energy density during the first charge-discharge cycle of the battery. This yields predictive results. Simulation results provide detailed data on the physical processes, while predictive results correlate these physical changes with actual performance indicators. By comparing simulation and predictive data before and after adjustments, it is possible to quantitatively assess whether the proposed process parameter adjustments can effectively reduce defect risks, improve product performance, and avoid introducing new problems. This application integrates physical models of material properties, geometry, and battery assembly processes for simulation, and further predicts the impact of adjustments on tab microscopic characteristics, downstream assembly performance, and initial electrochemical performance, making the evaluation results more comprehensive, in-depth, and forward-looking. This not only effectively avoids potential quality problems or performance degradation caused by one-sided evaluation, but also provides more solid data support and decision-making basis for the flexible adjustment of production equipment, thereby ensuring the effectiveness and safety of the adjustment plan, and ultimately improving the overall production quality of battery tabs and the reliability of battery products.

[0048] In this regard, this application further proposes steps for flexibly adjusting the process parameters of production equipment based on the evaluation results, including: When the evaluation results indicate that the process parameter adjustment suggestions are effective, the process parameters of the production equipment are flexibly adjusted in an online, non-stop, progressive manner according to the preset step size. The flexible adjustment is a multi-equipment collaborative adaptive fine-tuning, including modifying the pressure setting value and punching speed of the punching machine, or the energy output parameters of the welding machine. If the evaluation result indicates that the process parameter adjustment suggestion is invalid, a new process parameter adjustment suggestion is generated until the evaluation result indicates that the process parameter adjustment suggestion is valid. Then, the process parameters of the production equipment are flexibly adjusted according to the preset step size.

[0049] Specifically, the "preset step size" refers to the minimum increment or decrement for each adjustment when adjusting process parameters. Its purpose is to ensure the smoothness and controllability of the adjustment process, avoiding new production problems caused by large adjustments. The preset step size can be set based on historical data, equipment characteristics, or expert experience to ensure precise adjustments. "Online non-stop progressive calibration" refers to gradually and incrementally adjusting process parameters without stopping production equipment. "Flexible adjustment to multi-equipment collaborative adaptive fine-tuning" can be understood as the system coordinating synchronous or asynchronous minor adjustments to the parameters of multiple production devices when the process parameters to be adjusted involve multiple production devices, based on the overall production line's operating status and objectives. Adjustments to the pressure setpoint and cutting speed of the punching machine may require coordination with the energy output parameters of the welding machine to ensure optimization of the entire production process. This collaborative adjustment better adapts to changes in the production environment, achieving global optimization. In practical applications, when the evaluation results show that the process parameter adjustment suggestions are effective, the system will gradually modify the pressure setting or punching speed of the punching machine according to a preset step size, such as 0.1% per minute, and monitor production data in real time to ensure that the adjustment effect meets expectations. Furthermore, when the evaluation results indicate that the process parameter adjustment suggestions are invalid, the system will not immediately apply the suggestions, but will trigger a mechanism to regenerate process parameter adjustment suggestions.

[0050] In one embodiment, by introducing a refined processing and iterative optimization mechanism for the evaluation results, the potential production interruptions and inefficiencies caused by process parameter adjustments in the aforementioned basic scheme are effectively addressed. Specifically, when a process parameter adjustment suggestion is evaluated as valid, an online, non-stop, gradual calibration method is adopted, combined with preset step sizes and multi-device collaborative adaptive fine-tuning, ensuring a smooth, continuous adjustment process with minimal impact on production. This gradual adjustment method allows the system to monitor the adjustment effect in real time during production and make fine-tuning adjustments, thereby avoiding the risks associated with large-scale adjustments made at once. Furthermore, when a process parameter adjustment suggestion is evaluated as invalid, the system can intelligently regenerate new process parameter adjustment suggestions instead of blindly applying invalid solutions. This iterative optimization mechanism ensures that only verified and valid process parameter adjustment suggestions are actually applied to production equipment, thereby avoiding potential production accidents or quality problems and improving the success rate and efficiency of adjustments.

[0051] See Figure 2 , Figure 2A schematic diagram of a performance evaluation system based on battery tab production data analysis, provided as an embodiment of this application. The performance evaluation system 200 based on battery tab production data analysis includes: The acquisition module 210 is used to acquire production line data and environmental parameters during the battery tab production process. The production line data includes process parameters and equipment status information. Analysis module 220 is used to analyze the features in the production line data and combine the influence of environmental parameters on micro defects to obtain the potential risk index of micro defects of battery tabs. The features include at least the features of operating process parameters. The generation module 230 is used to generate process parameter adjustment suggestions for preventing defects based on the potential risk index of micro defects, combined with environmental parameters and equipment status information. Evaluation module 240 is used to simulate the process parameter adjustment suggestions, evaluate the effectiveness of the process parameter adjustment suggestions, and obtain evaluation results; The adjustment module 250 is used to flexibly adjust the process parameters of the production equipment based on the evaluation results.

[0052] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0053] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0054] The above provides a detailed description of the preferred embodiments of this application. However, this application is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined in this application.

Claims

1. A performance evaluation method based on battery tab production data analysis, characterized in that, include: Acquire production line data and environmental parameters during the battery tab production process, wherein the production line data includes process parameters and equipment status information; By analyzing the characteristics in the production line data and combining them with the influence of the environmental parameters on micro-defects, the potential risk index of micro-defects of the battery tabs is obtained, wherein the characteristics include at least the characteristics of the operating process parameters. Based on the micro-defect potential risk index, combined with the environmental parameters and the equipment status information, process parameter adjustment suggestions for preventing defects are generated. The proposed process parameter adjustment is simulated, and its effectiveness is evaluated to obtain the evaluation results. Based on the evaluation results, the process parameters of the production equipment are flexibly adjusted.

2. The method according to claim 1, characterized in that, The acquisition of production line data and environmental parameters during the battery tab production process includes: To obtain the temperature, humidity, and air cleanliness of the production workshop during the battery tab production process; The environmental parameters are obtained based on the temperature, humidity, and air cleanliness. Acquire acoustic emission signals from the punching station and welding parameters from the welding station during the battery tab production process, wherein the welding parameters include amplitude and energy; The process parameters are obtained based on the acoustic emission signal and the welding parameters; The cumulative number of punching operations, mold material type, and punching force variation trend extracted from acoustic emission signals were obtained during the battery tab production process. The cumulative number of punching operations, the type of mold material, and the trend of punching force are quantified and weighted to obtain equipment status information.

3. The method according to claim 2, characterized in that, The analysis of the characteristics in the production line data, combined with the influence of environmental parameters on microscopic defects, yields a potential risk index for microscopic defects in the battery tabs, including: For the acoustic emission signals contained in the production line data, a fast Fourier transform is performed on the acoustic emission signals to identify defect patterns related to micron-level burrs or local stress concentrations. Based on the identified defect patterns, feature analysis and correlation calculations are performed by combining the welding parameters and equipment status information corresponding to the production line data, and the influence of environmental parameters on micro-defects is coupled to obtain the micro-defect potential risk index.

4. The method according to claim 3, characterized in that, The process involves analyzing and correlating the identified defect patterns with the welding parameters and equipment status information corresponding to the production line data, and coupling the influence of environmental parameters on microscopic defects to obtain a microscopic defect potential risk index, including: Based on the defect pattern, feature values ​​related to micron-scale burrs or localized stress concentrations are extracted from the acoustic emission signal. The influence factor of the environmental parameters on micro-defects is obtained based on the environmental parameters. Each of the feature values, welding parameters, equipment status information, and influencing factors is assigned a corresponding weighting coefficient. The potential risk index of micro-defects is obtained by weighting and summing the corresponding weight coefficients, the feature values, the welding parameters, the equipment status information, and the influencing factors.

5. The method according to claim 3, characterized in that, The step of performing a fast Fourier transform on the acoustic emission signal to identify defect patterns related to micron-level burrs or localized stress concentrations includes: Perform a fast Fourier transform on the acoustic emission signal to analyze the energy distribution of the acoustic emission signal within a preset frequency range; Calculate the root mean square value of the acoustic emission signal; Based on the energy distribution, the root mean square value, and the preset energy threshold, identify and count instantaneous impact events exceeding the preset energy threshold; Based on the instantaneous impact event, defect patterns associated with micron-level burrs or localized stress concentrations are identified.

6. The method according to claim 1, characterized in that, The step of generating process parameter adjustment suggestions for defect prevention based on the micro-defect potential risk index, combined with the environmental parameters and the equipment status information, includes: When the potential risk index of micro-defects shows an upward trend and exceeds the preset defect alarm threshold, the analysis results are obtained by combining the potential risk index of micro-defects, the environmental parameters, and the equipment status information. When the analysis results indicate that defects are concentrated on the parting surface and molding edge, the main causes of micro-defects are determined to be mold wear and increased burr risk, and potential stress concentration risk in the welding area. When the analysis results characterize the stress accumulation at the locations of geometric abrupt changes in the weld and the enrichment locations of micro-defects, it is determined that the main cause of the micro-defects is the potential stress concentration risk in the weld area; Based on the main causes of the microscopic defects, recommendations for adjusting process parameters to prevent defects are generated.

7. The method according to claim 6, characterized in that, The step of generating process parameter adjustment recommendations for defect prevention based on the main causes of the microscopic defects includes: When the main cause of the micro-defects is characterized as mold wear and increased burr risk, process parameter adjustment recommendations are generated to prevent the defects. These recommendations include reducing the rising slope of the punching pressure curve and / or reducing the punching speed. When the main cause of the micro-defect is characterized to indicate a potential stress concentration risk in the welded area, process parameter adjustment suggestions are generated to prevent the defect. These suggestions include increasing welding energy and / or extending welding time.

8. The method according to claim 1, characterized in that, The process parameter adjustment suggestions are simulated, and the effectiveness of the suggestions is evaluated to obtain evaluation results, including: Obtain the material properties, geometric structure, and physical model of the battery tabs and battery assembly process; Based on the material properties, the geometry, and the physical model of the battery assembly process, the proposed process parameter adjustment was simulated, and simulation results were obtained. The effects of adjusting process parameters on the microstructure of the battery tabs during production, downstream assembly performance, and initial electrochemical performance were predicted, and the prediction results were obtained. The effectiveness of the proposed process parameter adjustment is evaluated based on the simulation results and the prediction results, and the evaluation results are obtained.

9. The method according to claim 1, characterized in that, The step of flexibly adjusting the process parameters of the production equipment based on the evaluation results includes: When the evaluation result indicates that the process parameter adjustment suggestion is effective, the process parameters of the production equipment are flexibly adjusted in an online non-stop progressive adjustment manner according to the preset step size. The flexible adjustment is a multi-equipment collaborative adaptive fine adjustment, including modifying the pressure setting value and punching speed of the punching machine, or the energy output parameters of the welding machine. When the evaluation result indicates that the process parameter adjustment suggestion is invalid, the process parameter adjustment suggestion is regenerated until the evaluation result indicates that the process parameter adjustment suggestion is valid, and the process parameters of the production equipment are flexibly adjusted according to the preset step size.

10. A performance evaluation system based on battery tab production data analysis, characterized in that, include: The acquisition module is used to acquire production line data and environmental parameters during the battery tab production process. The production line data includes process parameters and equipment status information. The analysis module is used to analyze the features in the production line data and, in combination with the influence of the environmental parameters on micro-defects, obtain the potential risk index of micro-defects of the battery tabs, wherein the features include at least the features of the operating process parameters. The generation module is used to generate process parameter adjustment suggestions for preventing defects based on the micro-defect potential risk index, combined with the environmental parameters and the equipment status information. An evaluation module is used to simulate the proposed process parameter adjustment and evaluate its effectiveness to obtain evaluation results. The adjustment module is used to flexibly adjust the process parameters of the production equipment based on the evaluation results.

Images