Battery capacity performance test method and device and storage medium

Abstract

The invention discloses a battery capacity performance testing method and device and a storage medium, and relates to the technical field of battery capacity performance testing. By constructing a dynamic load model and a multi-load test protocol and combining a high-precision data acquisition and filtering algorithm, adaptive data analysis and a machine learning regression model, the problems of difficulty in balancing precision and efficiency, large data acquisition error, fixed test protocol and the like in the traditional battery test are solved; by dynamically adjusting test parameters and environmental conditions, complex working conditions of the battery in actual use are accurately simulated, meanwhile, dynamic updating and optimization of a test protocol are achieved, the test precision, the data reliability and the test efficiency are remarkably improved, and a comprehensive, efficient and high-adaptability solution is provided for battery performance evaluation and health management.

Description

Technical Field

[0001] The present invention relates to the technical field of battery capacity performance testing, and specifically to a battery capacity performance testing method, device, and storage medium. Background Art

[0002] During the battery capacity performance testing process, there is a significant technical contradiction in the existing methods: it is difficult to achieve a balance between testing accuracy and testing efficiency; traditional testing methods usually adopt a single load or fixed load mode. Although the operation is simple, it cannot accurately simulate the complex working conditions of the battery in actual use, resulting in a large deviation between the test results and the true performance. Especially in the evaluation of battery performance degradation, single-load testing is difficult to capture the specific performance of the battery at different usage stages, such as the discharge characteristics of the battery in a low-power state or the instantaneous response ability under high load.

[0003] Another technical problem is the insufficient relevance between the test environment and the test results. The battery may face various environmental conditions in actual applications, such as temperature changes, humidity fluctuations, and different charge and discharge rates. However, traditional testing methods often conduct tests under constant environments and cannot dynamically adjust test parameters to adapt to different environmental conditions, resulting in the lack of adaptability of the test results to actual application scenarios. Summary of the Invention

[0004] The purpose of the present invention is to provide a battery capacity performance testing method, device, and storage medium. Through a dynamic load model, high-precision data acquisition and analysis, and machine learning algorithms, the balance between battery testing accuracy and efficiency is achieved, the test protocol is optimized, and the reliability and adaptability of battery performance evaluation are significantly improved.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present application provides a battery capacity performance testing method, including the following steps:

[0007] Obtain the load demand data of the battery at different usage stages, including the discharge characteristics in a low-power state and the instantaneous response ability under high load, construct a dynamic load model, and design a multi-load test protocol according to the dynamic load model to simulate the complex working conditions of the battery in actual use, covering different discharge rates and load changes;

[0008] During the test, real-time collect the voltage, current, and temperature data of the battery, use high-precision sensors and filtering algorithms to reduce data acquisition errors; adjust the temperature, humidity, and charge and discharge rates of the test environment through preset environmental condition parameters to simulate the performance of the battery in different application scenarios;

[0009] Among them, when the test environment temperature is lower than the preset threshold, the low-temperature compensation algorithm is started to correct the capacity attenuation data of the battery in the low-temperature environment.

[0010] The adaptive data analysis algorithm is adopted to dynamically adjust the test parameters according to the real-time collected battery performance data, optimize the accuracy and efficiency of the test process, analyze the battery capacity attenuation trend through the regression model in the machine learning algorithm, and predict the specific performance of the battery at different usage stages.

[0011] According to the prediction results, a battery performance evaluation report is generated, including the discharge characteristics in the low-power state, the instantaneous response ability under high load, and the environmental adaptability analysis. The evaluation report is combined with the dynamic load model to update the test protocol.

[0012] Furthermore, the load demand data of the battery at different usage stages are obtained, including the discharge characteristics in the low-power state and the instantaneous response ability under high load, and a dynamic load model is constructed, specifically including: obtaining the voltage value and current value of the battery in different states through the battery management system, and recording the time value as a time stamp.

[0013] For the low-power state, the changes in voltage value and current value during the discharge process are collected, and the discharge amount data is calculated. For the high-load state, the changes in instantaneous current value and voltage value are collected, and the response value data is calculated.

[0014] The collected voltage value, current value, discharge amount, response value are associated with the time value to generate a characteristic value data set, and then the linear regression algorithm is used to fit the characteristic value data set to obtain the discharge characteristic curve and the instantaneous response curve.

[0015] According to the discharge characteristic curve and the instantaneous response curve, a neural network algorithm is used to construct a dynamic load model. When the model accuracy does not reach the preset threshold, the support vector machine algorithm is used to optimize the model.

[0016] Furthermore, according to the dynamic load model, a multi-load test protocol is designed to simulate the complex working conditions of the battery in actual use, covering different discharge rates and load changes, specifically including:

[0017] Obtain the historical operation data of the battery in the actual application scenario, extract the load change parameters and discharge rate parameters, establish a dynamic load model, and according to the dynamic load model, set multiple test scenarios, each scenario includes at least three load change cycles, and determine the load change amount and discharge rate value of each cycle.

[0018] Using the random forest algorithm, simulate the test scenario, adjust the load change parameters and discharge rate parameters, generate a multi-load test protocol, and execute the multi-load test protocol in the simulated scenario to collect the performance data of the battery under different load changes and discharge rates, including voltage, current, and temperature parameters;

[0019] Use the support vector machine algorithm to analyze the collected performance data, judge the performance of the battery under different complex working conditions, identify abnormal working conditions, and optimize the parameter settings in the dynamic load model according to the performance analysis results, and adjust the corresponding relationship between the load change amount and the discharge rate value;

[0020] Integrate the optimized dynamic load model with the multi-load test protocol to generate a complete test plan covering the actual usage scenario.

[0021] Furthermore, during the test process, the voltage, current, and temperature data of the battery are collected in real time, and high-precision sensors and filtering algorithms are used to reduce the data collection error, specifically including:

[0022] During the battery test process, the voltage, current, and temperature data are obtained in real time through high-precision sensors, and the collected data is processed according to the preset filtering algorithm to obtain the denoised voltage, current, and temperature data;

[0023] Use the Kalman filtering algorithm to further process the denoised voltage, current, and temperature data to obtain the smoothed voltage, current, and temperature data, calculate the power data of the battery according to the smoothed voltage and current data, and judge the working state of the battery in combination with the temperature data;

[0024] Among them, when the working state of the battery is within the abnormal range, trigger the alarm mechanism and record the abnormal data;

[0025] According to the recorded abnormal data and historical data, use the support vector machine algorithm to evaluate and predict the health state of the battery, and then use the linear regression algorithm to predict the remaining life of the battery to obtain the remaining service life of the battery, and store the working state, health state, and remaining service life data of the battery in the database.

[0026] Furthermore, through the preset environmental condition parameters, adjust the temperature, humidity, and charge and discharge rate of the test environment to simulate the performance of the battery in different application scenarios, specifically including:

[0027] Obtain the preset temperature value, humidity value, charge rate, and discharge rate as the basic parameters of the environmental conditions, and generate a dynamic adjustment plan for the test environment according to the temperature value, humidity value, charge rate, and discharge rate.

[0028] Adopt a dynamic adjustment scheme to adjust the environmental values of the test environment to obtain the target test conditions, and under the target test conditions, run the charge and discharge test of the battery to obtain the test values of the battery;

[0029] According to the test values, combined with the preset scenario values, calculate the performance values of the battery. When the performance values meet the preset thresholds, determine the applicability of the battery in specific application scenarios;

[0030] Generate the simulation results of the battery in different application scenarios through the mapping relationship between the performance values and the scenario values.

[0031] Furthermore, adopt an adaptive data analysis algorithm to dynamically adjust the test parameters according to the real-time collected battery performance data, and optimize the accuracy and efficiency of the test process, specifically including:

[0032] Obtain the battery performance data and transmit it to the data processing module for feature extraction. Adopt an adaptive algorithm to analyze the battery performance characteristics, establish a performance evaluation model, and judge the data fluctuation trend;

[0033] When the data fluctuation exceeds the preset threshold, start the dynamic adjustment mechanism, calculate the optimal test parameters, adjust the operating state of the test equipment according to the optimal test parameters, and obtain new battery performance data;

[0034] Input the new data into the performance evaluation model to judge whether the test accuracy reaches the preset standard. When the test accuracy does not meet the standard, update the parameters of the adaptive algorithm, recalculate the optimal test parameters until the test efficiency and accuracy reach the optimal balance.

[0035] Furthermore, through the regression model in the machine learning algorithm, analyze the battery capacity attenuation trend and predict the specific performance of the battery at different usage stages, specifically including:

[0036] Obtain the historical capacity data of the battery at different usage stages, perform data cleaning and preprocessing, and adopt a feature extraction method to extract the key feature parameters of battery attenuation from the preprocessed data;

[0037] According to the extracted feature parameters, construct two machine learning algorithms, namely the linear regression model and the random forest regression model. When the battery capacity data has non-linear characteristics, use the random forest regression model for training, otherwise use the linear regression model for training;

[0038] Predict the battery capacity through the trained regression model to obtain the capacity prediction value in the future usage stage, determine the remaining service life of the battery according to the capacity prediction value, and output the battery performance evaluation report.

[0039] Further, according to the prediction results, a battery performance evaluation report is generated, including discharge characteristics in the low battery state, instantaneous response ability under high load, and environmental adaptability analysis. The evaluation report is combined with the dynamic load model to update the test protocol, specifically including:

[0040] Obtain the real-time operation data of the battery, extract the voltage and current parameters in the low battery state, and calculate the discharge characteristic indicators through a preset discharge model;

[0041] Based on the current change curve under high load conditions, use time series analysis methods to judge the stability and fluctuation range of the instantaneous response ability. For different environmental temperature and humidity conditions, establish a multi-dimensional data matrix, and evaluate the comprehensive score of environmental adaptability through principal component analysis methods;

[0042] Integrate the evaluation results of discharge characteristics, response ability, and adaptability to generate a battery performance evaluation report, form a structured data storage, extract the load change characteristic parameters from the dynamic load model, and calculate the matching degree with the performance indicators in the evaluation report;

[0043] When the matching degree is lower than the preset threshold, use a regression algorithm to optimize the parameter settings of the test protocol, improve the fit between the model and the measured data. After updating the test protocol, write the new parameter configuration into the test system to complete the test protocol update process.

[0044] A battery capacity performance test device includes a processor, a memory, and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the above-mentioned battery capacity performance test method is implemented.

[0045] A storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned battery capacity performance test method is implemented.

[0046] The beneficial effects of the present invention are:

[0047] Through the design of the dynamic load model and the multi-load test protocol, the present invention solves the technical problem that it is difficult to balance the test accuracy and efficiency in traditional test methods. By obtaining the load demand data of the battery at different usage stages, including the discharge characteristics in the low battery state and the instantaneous response ability under high load, a dynamic load model is constructed, and a multi-load test protocol is designed to simulate the complex working conditions of the battery in actual use; combined with the random forest algorithm and neural network to optimize the model accuracy, ensuring that the test protocol can accurately reflect the true performance of the battery under complex working conditions; not only improving the test accuracy, but also enhancing the test efficiency by dynamically adjusting the test parameters, achieving the optimal balance between accuracy and efficiency;

[0048] Through high-precision sensors and filtering algorithms, combined with adaptive data analysis algorithms, the problems of large data acquisition errors and insufficient monitoring of abnormal working conditions in traditional tests are solved. During the test, high-precision sensors are used to collect voltage, current, and temperature data in real time, and the Kalman filtering algorithm is used to denoise and smooth the data. Combining support vector machines and linear regression algorithms to evaluate the battery health state and remaining life, and by dynamically adjusting the temperature, humidity, and charge-discharge rate of the test environment, simulating the performance of the battery in different application scenarios, ensuring the reliability and adaptability of the test results; significantly improving the reliability of data acquisition and analysis, providing more accurate data support for battery performance evaluation;

[0049] By combining the battery performance evaluation report with the dynamic load model, the dynamic update and optimization of the test protocol are realized, solving the problem that the test protocol is fixed in traditional test methods and difficult to adapt to the actual working conditions of the battery. Generate a battery performance evaluation report containing low-power discharge characteristics, high-load instantaneous response ability, and environmental adaptability analysis according to the prediction results, and optimize the parameter settings of the test protocol through regression algorithms to ensure that the test protocol highly matches the actual working conditions. When the matching degree between the evaluation result and the model is lower than the preset threshold, automatically update the test protocol and write it into the test system to form a closed-loop optimization process; not only improving the adaptability and accuracy of the test protocol, but also providing a dynamically optimized test plan for the health management of the battery. Brief Description of the Drawings

[0050] For better understanding and implementation, the technical solutions of the present application will be described in detail below with reference to the accompanying drawings.

[0051] Figure 1 It is a schematic flowchart of a battery capacity performance test method provided by the present application;

[0052] Figure 2 It is a schematic flowchart of a battery capacity performance test method provided by the present application for obtaining load demand data of the battery at different usage stages;

[0053] Figure 3 It is a schematic flowchart of reducing data acquisition errors of a battery capacity performance test method provided by the present application. Detailed Description of the Invention

[0054] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, exemplary embodiments will be described in detail herein, and their examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of methods and systems consistent with some aspects of the present application as detailed in the appended claims.

[0055] The terms used in the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0056] The following will detail the specific implementation manners, features, and effects of the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0057] Please refer to Figures 1 - 3 , this embodiment provides a method for testing battery capacity performance, including the following steps:

[0058] S1. Obtain the load demand data of the battery at different usage stages, including the discharge characteristics in the low battery state and the instantaneous response ability under high load conditions, construct a dynamic load model, and design a multi-load test protocol according to the dynamic load model to simulate the complex working conditions of the battery in actual use, covering different discharge rates and load changes;

[0059] Further, obtaining the load demand data of the battery at different usage stages, including the discharge characteristics in the low battery state and the instantaneous response ability under high load conditions, and constructing a dynamic load model specifically includes: S11. Obtain the voltage value and current value of the battery in different states through the battery management system, and record the time value as a time stamp;

[0060] S12. For the low battery state, collect the changes in voltage value and current value during the discharge process, calculate the discharge amount data, and for the high load state, collect the changes in instantaneous current value and voltage value, and calculate the response value data;

[0061] S13. Associate the collected voltage value, current value, discharge amount, response value with the time value to generate a characteristic value data set, and then use the linear regression algorithm to fit the characteristic value data set to obtain the discharge characteristic curve and the instantaneous response curve;

[0062] S14. According to the discharge characteristic curve and the instantaneous response curve, a dynamic load model is constructed using a neural network algorithm. When the model accuracy does not reach the preset threshold, a support vector machine algorithm is used to optimize the model.

[0063] Among them, the construction process of the dynamic load model includes: based on the voltage, current, discharge capacity, and response value data of the battery at different usage stages, a linear regression algorithm is used to fit the discharge characteristic curve and the instantaneous response curve to determine the initial model parameters; when constructing the dynamic load model through a neural network algorithm, a three-layer fully connected network structure is adopted, the input layer is voltage, current, temperature, and timestamp data, the number of hidden layer nodes is 64, the activation function is ReLU, and the output layer is the load prediction value; finally, when the model accuracy does not reach the preset threshold (such as 95%), a support vector machine algorithm is used for optimization, the kernel function is selected as the radial basis function (RBF), the regularization parameter C is set to 1.0, the gamma value is 0.1, and the hyperparameters are adjusted through cross-validation to ensure that the model accuracy meets the requirements.

[0064] Specifically, by constructing a dynamic load model, the load demand data of the battery at different usage stages can be accurately obtained, including the low-power discharge characteristics and the high-load instantaneous response ability. The linear regression and neural network algorithms are used to fit the characteristic curves and establish the model, and at the same time, the support vector machine is used to optimize the model accuracy, effectively solving the technical problems of low accuracy, inability to simulate complex working conditions, and lack of environmental adaptability of traditional testing methods, significantly improving the accuracy and practicality of battery performance testing, and achieving the balance of testing accuracy and efficiency.

[0065] Furthermore, according to the dynamic load model, a multi-load test protocol is designed to simulate the complex working conditions of the battery in actual use, covering different discharge rates and load changes, specifically including:

[0066] Obtain the historical operation data of the battery in the actual application scenario, extract the load change parameters and discharge rate parameters, establish a dynamic load model, and according to the dynamic load model, set multiple test scenarios, each scenario includes at least three load change cycles, and determine the load change amount and discharge rate value of each cycle;

[0067] Adopt the random forest algorithm to simulate the test scenarios, adjust the load change parameters and discharge rate parameters, generate a multi-load test protocol, and execute the multi-load test protocol in the simulated scenarios to collect the performance data of the battery under different load changes and discharge rates, including voltage, current, and temperature parameters;

[0068] Among them, in the random forest algorithm, the number of trees is set to 100, the maximum depth is 10, the feature selection criterion is the Gini coefficient, and the hyperparameters are optimized through grid search to determine the optimal model parameters. Then, in the test scenario, the load change parameters and discharge rate parameters are adjusted to generate a multi-load test protocol. Next, these protocols are executed in the simulation environment to collect the performance data of the battery under different load changes and discharge rates, including voltage, current, and temperature parameters.

[0069] Using the support vector machine algorithm, analyze the collected performance data to judge the performance of the battery under different complex working conditions, identify abnormal working conditions, and according to the performance analysis results, optimize the parameter settings in the dynamic load model and adjust the corresponding relationship between the load change amount and the discharge rate value;

[0070] Fuse the optimized dynamic load model with the multi-load test protocol to generate a complete test plan covering the actual usage scenario, ensuring that the test protocol can accurately reflect the true performance of the battery under complex working conditions.

[0071] Specifically, through the design of the multi-load test protocol based on the dynamic load model, the technical problem that the traditional battery test method cannot accurately simulate complex working conditions is solved. The multi-load test protocol is generated using the random forest algorithm, and the load change and discharge rate parameters are adjusted to simulate the performance of the battery under different working conditions; the collected performance data is analyzed using the support vector machine algorithm to identify abnormal working conditions and optimize the model parameters; finally, the optimized dynamic load model is fused with the test protocol to generate a complete test plan covering the actual usage scenario, ensuring that the test results can accurately reflect the true performance of the battery under complex working conditions; significantly improving the test accuracy and efficiency and enhancing the adaptability of the test results to actual applications.

[0072] S2. During the test process, the voltage, current, and temperature data of the battery are collected in real time, and high-precision sensors and filtering algorithms are used to reduce the data acquisition error; through the preset environmental condition parameters, the temperature, humidity, and charge and discharge rate of the test environment are adjusted to simulate the performance of the battery in different application scenarios;

[0073] Among them, when the test environment temperature is lower than the preset threshold, the low-temperature compensation algorithm is started to correct the capacity attenuation data of the battery in the low-temperature environment;

[0074] It should be noted that the low-temperature compensation algorithm is a key technology to ensure the performance and accuracy of the battery in a low-temperature environment. When the test environment temperature is lower than the preset threshold, the low-temperature compensation algorithm will monitor the current temperature of the battery in real time through a temperature sensor and correct the capacity attenuation data of the battery according to the preset compensation model. Specifically, this algorithm can establish a mapping relationship between temperature and battery performance through methods such as polynomial fitting or neural networks, so as to calculate the compensation parameters that need to be adjusted. For example, the BP neural network algorithm can be used to train the neural network to predict the performance change of the battery in a low-temperature environment and adjust the test parameters in real time; in addition, in order to improve the accuracy and response speed of compensation, a PID control system can also be combined to ensure that the heating element can respond quickly and maintain the battery within an appropriate working temperature range. Through these measures, the low-temperature compensation algorithm can effectively correct the capacity attenuation data of the battery in a low-temperature environment and ensure the accuracy and reliability of the test results.

[0075] Furthermore, during the test process, the voltage, current, and temperature data of the battery are collected in real time, and high-precision sensors and filtering algorithms are used to reduce the data acquisition error, specifically including:

[0076] S21. During the battery test process, the voltage, current, and temperature data are obtained in real time through high-precision sensors, and the collected data are processed according to the preset filtering algorithm to obtain the denoised voltage, current, and temperature data;

[0077] S22. The Kalman filtering algorithm is used to further process the denoised voltage, current, and temperature data to obtain the smoothed voltage, current, and temperature data. The power data of the battery are calculated according to the smoothed voltage and current data, and the working state of the battery is judged in combination with the temperature data;

[0078] Among them, when the working state of the battery is within the abnormal range, the alarm mechanism is triggered and the abnormal data are recorded;

[0079] S23. According to the recorded abnormal data and historical data, the support vector machine algorithm is used to evaluate and predict the health state of the battery, and then the linear regression algorithm is used to predict the remaining life of the battery to obtain the remaining service life of the battery. The working state, health state, and remaining service life data of the battery are stored in the database for subsequent analysis and decision-making.

[0080] It should be noted that in the Kalman filtering algorithm, the state vector includes voltage, current, and temperature, the observation vector is the original data collected by the sensor, and the state transition matrix and observation matrix are calibrated through experimental data; in the linear regression algorithm, the least squares method is used to fit the discharge characteristic curve, and the objective function is the minimization of the sum of squared errors.

[0081] Further, by means of preset environmental condition parameters, adjust the temperature, humidity and charge-discharge rate of the test environment to simulate the performance of the battery in different application scenarios, specifically including:

[0082] Obtain the preset temperature value, humidity value, charge rate and discharge rate as the basic parameters of the environmental conditions, and generate a dynamic adjustment plan for the test environment according to the temperature value, humidity value, charge rate and discharge rate.

[0083] Adopt the dynamic adjustment plan to adjust the environmental values of the test environment to obtain the target test conditions, and under the target test conditions, conduct the charge-discharge test of the battery to obtain the test values of the battery;

[0084] According to the test values and in combination with the preset scenario values, calculate the performance values of the battery. When the performance values meet the preset thresholds, determine the applicability of the battery in specific application scenarios;

[0085] Generate the simulation results of the battery in different application scenarios through the mapping relationship between the performance values and the scenario values.

[0086] Specifically, the voltage, current and temperature data of the battery are collected and processed in real time through high-precision sensors and filtering algorithms, effectively reducing the data acquisition error and improving the data quality. The Kalman filtering algorithm is used to further smooth the data and monitor the working state of the battery in real time. Once an anomaly is detected, an alarm is triggered and the data is recorded. Based on the anomaly data and historical data, in combination with the support vector machine and linear regression algorithms, the health state and remaining life of the battery are evaluated and predicted, and the results are stored in the database to provide support for subsequent analysis and decision-making; in addition, by dynamically adjusting the temperature, humidity and charge-discharge rate of the test environment, the performance of the battery in different application scenarios is simulated to ensure the accuracy and applicability of the test results. It solves the problems of low data acquisition accuracy, inability to monitor anomalies in real time and lack of environmental adaptability in traditional tests, and significantly improves the reliability and practicality of battery tests.

[0087] S3. Adopt an adaptive data analysis algorithm to dynamically adjust the test parameters according to the real-time collected battery performance data, optimize the accuracy and efficiency of the test process, and analyze the battery capacity attenuation trend through a regression model in the machine learning algorithm to predict the specific performance of the battery at different usage stages.

[0088] Further, adopt an adaptive data analysis algorithm to dynamically adjust the test parameters according to the real-time collected battery performance data, optimize the accuracy and efficiency of the test process, specifically including:

[0089] Obtain the battery performance data and transmit it to the data processing module for feature extraction, analyze the battery performance characteristics by using an adaptive algorithm, establish a performance evaluation model, and judge the data fluctuation trend;

[0090] When the data fluctuation exceeds the preset threshold, the dynamic adjustment mechanism is activated to calculate the optimal test parameters, adjust the operating state of the test equipment according to the optimal test parameters, and obtain new battery performance data;

[0091] Input the new data into the performance evaluation model to determine whether the test accuracy reaches the preset standard. When the test accuracy does not meet the standard, update the parameters of the adaptive algorithm and recalculate the optimal test parameters until the test efficiency and accuracy reach the optimal balance.

[0092] Specifically, through the adaptive data analysis algorithm and the machine learning regression model, the technical problems of difficult balance between accuracy and efficiency in traditional battery testing and inaccurate prediction of battery capacity attenuation are solved. The adaptive algorithm can dynamically adjust the test parameters according to the real-time collected battery performance data, monitor the data fluctuation in real time through feature extraction and performance evaluation model. When the fluctuation exceeds the threshold, it automatically calculates the optimal test parameters and adjusts the operating state of the test equipment, which not only improves the test accuracy, but also maximizes the test efficiency through continuous optimization.

[0093] Furthermore, through the regression model in the machine learning algorithm, analyze the trend of battery capacity attenuation and predict the specific performance of the battery at different usage stages, specifically including:

[0094] Obtain the historical capacity data of the battery at different usage stages, perform data cleaning and preprocessing, and use the feature extraction method to extract the key feature parameters of battery attenuation from the preprocessed data;

[0095] According to the extracted feature parameters, construct two machine learning algorithms, the linear regression model and the random forest regression model. When the battery capacity data has non-linear characteristics, use the random forest regression model for training, otherwise use the linear regression model for training;

[0096] Predict the battery capacity through the trained regression model to obtain the capacity prediction value in the future usage stage, determine the remaining service life of the battery according to the capacity prediction value, and output the battery performance evaluation report.

[0097] Specifically, through the linear regression and random forest regression models in machine learning, analyze and predict the trend of battery capacity attenuation, and can accurately predict the performance of the battery at different usage stages. Extract the key feature parameters according to the historical capacity data of the battery, and select the appropriate regression model for training according to the linear or non-linear characteristics of the data, so as to accurately predict the remaining service life of the battery and output the performance evaluation report. This data-driven prediction method significantly improves the accuracy and reliability of battery performance evaluation, and provides strong support for the optimal design and health management of the battery.

[0098] S4. Generate a battery performance evaluation report based on the prediction results, including discharge characteristics in low battery state, instantaneous response ability under high load, and environmental adaptability analysis. Combine the evaluation report with the dynamic load model to update the test protocol, further improving the accuracy and reliability of the battery capacity performance test.

[0099] Furthermore, based on the prediction results, generate a battery performance evaluation report, including discharge characteristics in low battery state, instantaneous response ability under high load, and environmental adaptability analysis. Combine the evaluation report with the dynamic load model to update the test protocol, specifically including:

[0100] Obtain the real-time operation data of the battery, extract the voltage and current parameters in the low battery state, and calculate the discharge characteristic indicators through a preset discharge model;

[0101] Based on the current change curve under high load conditions, use time series analysis methods to judge the stability and fluctuation range of the instantaneous response ability. For different environmental temperature and humidity conditions, establish a multi-dimensional data matrix, and evaluate the comprehensive score of environmental adaptability through principal component analysis methods;

[0102] Integrate the evaluation results of discharge characteristics, response ability, and adaptability to generate a battery performance evaluation report, form a structured data storage, extract the load change characteristic parameters from the dynamic load model, and calculate the matching degree with the performance indicators in the evaluation report;

[0103] When the matching degree is lower than the preset threshold, use a regression algorithm to optimize the parameter settings of the test protocol, improve the fit between the model and the measured data. After updating the test protocol, write the new parameter configuration into the test system to complete the test protocol update process.

[0104] Specifically, by integrating the battery performance evaluation report with the dynamic load model, a comprehensive analysis of the battery performance and dynamic update of the test protocol are realized, solving the technical problems of incomplete performance evaluation and difficulty in adapting the test protocol to the actual working conditions of the battery in traditional test methods.

[0105] A battery capacity performance test device includes a processor, a memory, and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the above-mentioned battery capacity performance test method is implemented.

[0106] A storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned battery capacity performance test method is implemented.

[0107] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments by using the technical content disclosed above without departing from the technical solution of the present invention. However, as long as it does not depart from the technical solution content of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for testing the battery capacity performance, characterized in that: It includes the following steps: Obtain the load demand data of the battery at different usage stages, including the discharge characteristics in the low battery state and the instantaneous response ability under high load conditions, construct a dynamic load model, and design a multi-load test protocol according to the dynamic load model to simulate the complex working conditions of the battery in actual use, covering different discharge rates and load changes; During the test, collect the voltage, current, and temperature data of the battery in real time, and use high-precision sensors and filtering algorithms to reduce the data collection error; adjust the temperature, humidity, and charge-discharge rate of the test environment through the preset environmental condition parameters to simulate the performance of the battery in different application scenarios; Among them, when the test environment temperature is lower than the preset threshold, start the low-temperature compensation algorithm to correct the capacity attenuation data of the battery in the low-temperature environment; Adopt an adaptive data analysis algorithm to dynamically adjust the test parameters according to the real-time collected battery performance data, optimize the accuracy and efficiency of the test process, and analyze the battery capacity attenuation trend through the regression model in the machine learning algorithm to predict the specific performance of the battery at different usage stages; According to the prediction results, generate a battery performance evaluation report, including the discharge characteristics in the low battery state, the instantaneous response ability under high load, and the environmental adaptability analysis, and combine the evaluation report with the dynamic load model to update the test protocol.

2. The battery capacity performance testing method according to claim 1, wherein: Obtain the load demand data of the battery at different usage stages, including the discharge characteristics in the low battery state and the instantaneous response ability under high load conditions, construct a dynamic load model, specifically including: obtain the voltage value and current value of the battery in different states through the battery management system, and record the time value as the time stamp; For the low battery state, collect the changes in voltage value and current value during the discharge process, calculate the discharge amount data, and for the high load state, collect the changes in instantaneous current value and voltage value, and calculate the response value data; Associate the collected voltage value, current value, discharge amount, response value with the time value to generate a characteristic value data set, and then use the linear regression algorithm to fit the characteristic value data set to obtain the discharge characteristic curve and the instantaneous response curve; According to the discharge characteristic curve and the instantaneous response curve, use the neural network algorithm to construct a dynamic load model. When the model accuracy does not reach the preset threshold, use the support vector machine algorithm to optimize the model.

3. A method for testing the battery capacity performance according to claim 1, characterized in that: According to the dynamic load model, design a multi-load test protocol to simulate the complex working conditions of the battery in actual use, covering different discharge rates and load changes, specifically including: Obtain the historical operation data of the battery in the actual application scenario, extract the load change parameters and discharge rate parameters, establish a dynamic load model, and according to the dynamic load model, set multiple test scenarios, each scenario includes at least three load change cycles, and determine the load change amount and discharge rate value of each cycle; Adopt the random forest algorithm to simulate the test scenario, adjust the load change parameters and discharge rate parameters, generate a multi-load test protocol, and execute the multi-load test protocol in the simulated scenario to collect the performance data of the battery under different load changes and discharge rates, including voltage, current, and temperature parameters; Using the support vector machine algorithm, analyze the collected performance data, judge the performance of the battery under different complex working conditions, identify abnormal working conditions, and according to the performance analysis results, optimize the parameter settings in the dynamic load model and adjust the corresponding relationship between the load change amount and the discharge rate value; Integrate the optimized dynamic load model with the multi-load test protocol to generate a complete test plan covering the actual usage scenarios.

4. A method for testing the battery capacity performance according to claim 1, characterized in that: During the test process, collect the voltage, current, and temperature data of the battery in real time, and use high-precision sensors and filtering algorithms to reduce the data collection error, specifically including: During the battery test, obtain the voltage, current, and temperature data in real time through high-precision sensors, and process the collected data according to the preset filtering algorithm to obtain the denoised voltage, current, and temperature data; Use the Kalman filtering algorithm to further process the denoised voltage, current, and temperature data to obtain the smoothed voltage, current, and temperature data. Calculate the power data of the battery based on the smoothed voltage and current data, and judge the working state of the battery in combination with the temperature data; Among them, when the working state of the battery is within the abnormal range, trigger the alarm mechanism and record the abnormal data; According to the recorded abnormal data and historical data, use the support vector machine algorithm to evaluate and predict the health state of the battery, and then predict the remaining life of the battery through the linear regression algorithm to obtain the remaining service life of the battery. Store the working state, health state, and remaining service life data of the battery in the database.

5. A method for testing the battery capacity performance according to claim 1, characterized in that: Adjust the temperature, humidity, and charge-discharge rate of the test environment through the preset environmental condition parameters to simulate the performance of the battery in different application scenarios, specifically including: Obtain the preset temperature value, humidity value, charge rate, and discharge rate as the basic parameters of the environmental conditions, and generate a dynamic adjustment plan for the test environment according to the temperature value, humidity value, charge rate, and discharge rate; Adopt the dynamic adjustment plan to adjust the environmental value of the test environment to obtain the target test conditions, and under the target test conditions, run the charge-discharge test of the battery to obtain the test value of the battery; According to the test value, combine the preset scenario value to calculate the performance value of the battery. When the performance value meets the preset threshold, determine the applicability of the battery in a specific application scenario; Generate the simulation results of the battery in different application scenarios through the mapping relationship between the performance value and the scenario value.

6. A method for testing battery capacity performance according to claim 1, characterized in that: Adopt the adaptive data analysis algorithm to dynamically adjust the test parameters according to the real-time collected battery performance data, and optimize the accuracy and efficiency of the test process, specifically including: Obtain the battery performance data and transmit it to the data processing module for feature extraction. Use the adaptive algorithm to analyze the battery performance characteristics, establish a performance evaluation model, and judge the data fluctuation trend; When the data fluctuation exceeds the preset threshold, start the dynamic adjustment mechanism, calculate the optimal test parameters, adjust the operating state of the test equipment according to the optimal test parameters, and obtain the new battery performance data; Input the new data into the performance evaluation model to judge whether the test accuracy reaches the preset standard. When the test accuracy does not meet the standard, update the parameters of the adaptive algorithm, recalculate the optimal test parameters until the test efficiency and accuracy reach the optimal balance.

7. A method for testing the battery capacity performance according to claim 1, characterized in that: Analyze the battery capacity attenuation trend through the regression model in the machine learning algorithm, and predict the specific performance of the battery at different usage stages, specifically including: Obtain the historical capacity data of the battery at different usage stages, perform data cleaning and preprocessing, and use feature extraction methods to extract the key feature parameters of battery attenuation from the preprocessed data; According to the extracted feature parameters, construct two machine learning algorithms, namely the linear regression model and the random forest regression model. When the battery capacity data has non-linear characteristics, use the random forest regression model for training, otherwise use the linear regression model for training; Predict the battery capacity through the trained regression model to obtain the capacity prediction value in the future usage stage, determine the remaining service life of the battery according to the capacity prediction value, and output the battery performance evaluation report.

8. A method for testing battery capacity performance according to claim 1, characterized in that: Generate a battery performance evaluation report based on the prediction results, including the discharge characteristics under low battery conditions, the instantaneous response ability under high load, and the environmental adaptability analysis. Combine the evaluation report with the dynamic load model to update the test protocol, specifically including: Obtain the real-time operation data of the battery, extract the voltage and current parameters under low battery conditions, and calculate the discharge characteristic indicators through a preset discharge model; Based on the current change curve under high load conditions, use the time series analysis method to judge the stability and fluctuation range of the instantaneous response ability. For different environmental temperature and humidity conditions, establish a multi-dimensional data matrix, and evaluate the comprehensive score of environmental adaptability through the principal component analysis method; Integrate the discharge characteristics, response ability, and adaptability evaluation results to generate a battery performance evaluation report, form a structured data storage, extract the load change feature parameters from the dynamic load model, and calculate the matching degree with the performance indicators in the evaluation report; When the matching degree is lower than the preset threshold, use the regression algorithm to optimize the parameter settings of the test protocol, improve the fit between the model and the measured data. After updating the test protocol, write the new parameter configuration into the test system to complete the test protocol update process.

9. A battery capacity performance testing device, characterized in that: Including a processor, a memory, and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the battery capacity performance test method described in claims 1-8 above is implemented.

10. A storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, the battery capacity performance test method described in claims 1-8 above is implemented.

Images