Lithium ion battery cycle performance improvement method based on multi-feature analysis

Abstract

The invention relates to the technical field of battery management, and particularly discloses a lithium ion battery cycle performance improving method based on multi-feature analysis. Key parameters of capacity, internal resistance, charge and discharge efficiency and temperature fluctuation of a battery are monitored in real time; according to the method, the electrolyte decomposition risk can be accurately evaluated and early warning can be provided by utilizing the advanced algorithms such as dynamic time warping, Kalman filtering, fast Fourier transform and Haar wavelet transform to calculate corresponding characteristic values and combining a gradient boosting decision-making tree and a machine learning model of a support vector machine, and once the potential risk is detected, the risk of electrolyte decomposition can be accurately evaluated and early warning can be provided. The system automatically starts the PID controller to precisely regulate and control the charging and discharging process and the temperature, it is ensured that the battery operates under the optimal condition, the comprehensive monitoring and regulation and control mechanism effectively prevents potential safety hazards such as electrolyte decomposition, the service life of the battery is remarkably prolonged, and the overall safety of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery management, and in particular to a method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis. Background Art

[0002] With the rapid development of renewable energy and electric vehicle industries, lithium-ion batteries have been widely used as an efficient and environmentally friendly energy storage device. However, lithium-ion batteries will face problems such as capacity decay, increased internal resistance and electrolyte decomposition during long-term use, which directly affect the cycle performance and service life of the battery. Especially under complex working conditions, the working environment (such as temperature fluctuations) and operation mode (such as charging and discharging efficiency) of the battery have a significant impact on the battery health state. Therefore, how to extend the battery life and improve its safety and reliability through effective monitoring and management methods has become the focus of current research. Traditional battery management systems (BMS) usually rely on simple threshold alarm mechanisms and cannot comprehensively and accurately evaluate the battery health state and its changing trends.

[0003] The prior art has the following deficiencies:

[0004] Most traditional methods use fixed thresholds to determine whether the battery is in normal working condition. This method is difficult to capture subtle changes in the battery's health status and can easily lead to misjudgment or missed judgment. Secondly, existing technologies perform poorly when dealing with complex and changeable operating conditions. For example, the impact of temperature fluctuations and changes in charge and discharge efficiency on battery health has not been fully considered and quantified. In addition, existing systems generally do not have predictive maintenance functions and cannot provide early warning of potential risks, which often lags maintenance measures and increases the probability of battery failure. Finally, most existing solutions lack intelligent data analysis tools and cannot effectively use advanced technologies such as machine learning to improve the overall performance of battery management systems. These shortcomings limit the effectiveness of battery management systems in practical applications, and there is an urgent need for a more intelligent and accurate method to solve the above problems. Summary of the invention

[0005] The object of the present invention is to provide a method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis to solve the above-mentioned problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis comprises the following steps:

[0008] S1: During the battery monitoring cycle, the capacity and internal resistance change of the battery are monitored and analyzed in real time, and whether the electrolyte is decomposed is determined based on the monitoring and analysis results;

[0009] S2: According to the evaluation results, the charge and discharge efficiency and temperature fluctuation degree of the battery during the monitoring period are obtained in real time, and the influence of the charge and discharge efficiency and temperature fluctuation degree on the decomposition of the electrolyte is analyzed;

[0010] S3: Based on the impact analysis results, the battery’s charge and discharge efficiency and temperature are regulated in real time to improve the battery’s cycle performance.

[0011] As a further solution of the present invention: the step of determining whether the electrolyte has decomposed specifically includes:

[0012] During the battery monitoring cycle, the battery capacity data and internal resistance data are obtained in real time according to the time series. The battery capacity characteristic value and the battery internal resistance characteristic value are calculated according to the degree of change of the battery capacity data and the internal resistance data, and the battery capacity characteristic value and the battery internal resistance characteristic value are used as the input of the machine learning model. The output of the model is the decomposition score. It is determined whether the decomposition score is greater than or equal to the preset threshold. If so, the electrolyte of the corresponding battery is decomposed. If not, the electrolyte of the corresponding battery is not decomposed.

[0013] As a further solution of the present invention: the process of obtaining the battery capacity characteristic value is:

[0014] Collect the real-time battery capacity data of the battery during the monitoring period to form a time series, and select a reference battery time series as the capacity change pattern under the healthy state;

[0015] Construct a local distance matrix to store the distance between each pair of corresponding points in the target sequence and the reference sequence, which is obtained by calculating the square of the difference between the two points;

[0016] Initialize a cumulative distance moment of the same size and with the same starting value; for the first row of the cumulative distance matrix, each element is obtained by adding the cumulative distance of the same column of the previous row to the current local distance; for the first column of the cumulative distance matrix, each element is obtained by adding the cumulative distance of the same row of the previous column to the current local distance, and the remaining positions are obtained by adding the local distance of the current position to the cumulative distance of the position with the smallest cumulative distance among the three adjacent positions to its left, above, and above the left; starting from the lower right corner of the cumulative distance matrix, trace back to the upper left corner along the direction that minimizes the cumulative distance, so as to determine an optimal alignment path connecting the starting point and the end point. The final battery capacity eigenvalue is obtained by calculating the average value of all cumulative distances on the optimal alignment path.

[0017] As a further solution of the present invention: the process of obtaining the characteristic value of the battery internal resistance is:

[0018] The initial state estimate is set to the battery internal resistance value measured for the first time, and an initial error covariance matrix is ​​set. At each time step, the internal resistance value at the current moment is predicted based on the state estimate value of the previous step, and the prediction error covariance matrix is ​​updated at the same time to obtain the battery internal resistance at the current moment, which is recorded as the actual measurement value. The Kalman gain is calculated based on the predicted value and the actual measurement value, and the state estimate is updated. At the same time, the error covariance matrix is ​​updated. The prediction and update steps are repeated until the end of the monitoring period to obtain a series of smoothed internal resistance estimates. The standard deviation of these smoothed internal resistance values ​​is calculated as the battery internal resistance eigenvalue.

[0019] As a further solution of the present invention: the process of establishing the machine learning model is:

[0020] The battery capacity characteristic value and the battery internal resistance characteristic value of the battery within the monitoring period are obtained, and the battery capacity characteristic value and the battery internal resistance characteristic value are constructed into a comprehensive characteristic vector as the input of the machine learning model. The machine learning model is trained with minimizing the error between the predicted decomposition score and the actual decomposition score of the battery as the training goal. The machine learning model is trained using historical battery data, and the decomposition score of the battery is output according to the trained machine learning model. The machine learning model is a gradient boosting decision tree.

[0021] As a further solution of the present invention: the analysis of the influence of the charge-discharge efficiency and the temperature fluctuation on the decomposition of the electrolyte specifically includes:

[0022] During the monitoring period of the battery, the charge and discharge efficiency data and temperature data are acquired in real time according to the time series. According to the fluctuation amplitude of the charge and discharge efficiency and the temperature, the charge and discharge efficiency characteristic value and the temperature fluctuation characteristic value are calculated respectively. According to the charge and discharge efficiency characteristic value and the temperature fluctuation characteristic value, the influence factor is calculated. The influence factor is compared with the preset threshold value to determine whether the influence factor is greater than or equal to the preset threshold value. If so, a serious impact is produced; if not, a slight impact is produced.

[0023] As a further solution of the present invention: the process of obtaining the characteristic value of the charge and discharge efficiency is:

[0024] During the monitoring period of the battery, the charge and discharge efficiency data are acquired in real time according to the time series, and the time domain signal is converted into the frequency domain signal by applying the fast Fourier transform to the time series data of the charge and discharge efficiency data. The cutoff frequency is selected, and the cutoff frequency is used to distinguish important low-frequency components from relatively unimportant high-frequency components. The sum of the energies of all frequency components below the cutoff frequency is calculated; the proportion of low-frequency energy to total energy is calculated to obtain the characteristic value of the charge and discharge efficiency.

[0025] As a further solution of the present invention: the process of obtaining the temperature fluctuation characteristic value is:

[0026] During the monitoring period of the battery, the temperature data of the battery is acquired in real time according to the time series, and the temperature data is subjected to Haar wavelet transform to decompose the temperature data of the battery into an approximate coefficient and a detail coefficient, wherein the approximate coefficient is obtained by calculating the average value of adjacent data points, and the detail coefficient is obtained by calculating the difference of adjacent data points;

[0027] For each layer’s detail coefficient set, sum the squares of all its coefficients to get the energy value of the corresponding layer;

[0028] The energy value of each layer detail coefficient is multiplied by the corresponding preset weight and then summed to obtain the final temperature fluctuation characteristic value.

[0029] As a further solution of the present invention: the process of obtaining the impact factor is:

[0030] Obtaining a charge and discharge efficiency characteristic value and a temperature fluctuation characteristic value of the battery, and preparing a set of historical data, including charge and discharge efficiency characteristic values, temperature fluctuation characteristic values ​​of multiple samples, and corresponding electrolyte decomposition labels, wherein the electrolyte decomposition labels include: electrolyte decomposition occurs and electrolyte does not decompose;

[0031] Use support vector machines to train historical data sets. For classification tasks, select a linear kernel to map input features to a high-dimensional space and find the optimal hyperplane to distinguish samples of different categories. For regression tasks, use a support vector regression model to predict the continuous value of the decomposition degree. During the training process, cross-validation is used to optimize model parameters including regularization parameters and kernel function parameters.

[0032] The trained support vector machine model is used to predict the electrolyte decomposition influencing factor to determine whether the influencing factor is greater than or equal to the preset threshold. If so, it is recorded as a severe impact, otherwise, it is recorded as a slight impact.

[0033] As a further solution of the present invention: the real-time regulation of the charging and discharging efficiency and temperature of the battery according to the impact degree analysis result specifically includes:

[0034] Based on the serious impact, the PID controller is started to dynamically adjust the working state of the battery. For the charging and discharging efficiency, the PID controller controls the charging and discharging efficiency according to the deviation between the current efficiency and the target efficiency. For temperature control, the PID controller controls the power output of the cooling or heating device according to the deviation between the current temperature and the target temperature, so that the battery temperature is quickly stabilized within a safe range.

[0035] Beneficial effects of the present invention:

[0036] (1) The present invention realizes accurate assessment of battery health status by real-time monitoring of key parameters such as capacity, internal resistance, charge and discharge efficiency and temperature fluctuation of lithium-ion batteries, and using advanced algorithms such as dynamic time warping, Kalman filtering, fast Fourier transform and Haar wavelet transform to calculate corresponding eigenvalues. Combined with machine learning models such as gradient boosting decision tree and support vector machine, the present invention can accurately predict the risk of electrolyte decomposition and provide early warning to ensure that measures can be taken when potential risks first appear. Once the decomposition risk is detected to exceed the preset threshold, the system automatically activates the PID controller to accurately control the charge and discharge process and temperature, optimize the charging current or voltage and the working parameters of the cooling / heating device to maintain the battery under optimal working conditions. This multi-level and intelligent monitoring and control mechanism not only effectively prevents safety hazards such as electrolyte decomposition, significantly prolongs the battery life, but also greatly improves the overall safety and reliability of the system. In addition, by analyzing the influencing factors of charge and discharge efficiency and temperature fluctuation, the present invention provides solid data support for the formulation of more scientific and reasonable battery management strategies, further enhancing battery performance and economic benefits. This innovative solution embodies the all-round battery health management concept from data collection, feature extraction, risk assessment to intelligent regulation, laying an important foundation for the realization of efficient, safe and long-life lithium-ion battery applications.

[0037] (2) The present invention uses gradient boosting decision trees and support vector machine advanced machine learning models to comprehensively evaluate the risk of electrolyte decomposition based on multi-dimensional eigenvalues ​​(including eigenvalues ​​of key parameters such as battery capacity, internal resistance, charge and discharge efficiency, and temperature fluctuation). These models can more accurately capture the subtle changes in battery health status through deep learning and pattern recognition technology, and provide reliable predictions of future health status, thereby achieving early warning of potential failures. In particular, by analyzing the influencing factors of charge and discharge efficiency and temperature fluctuation, the present invention can not only identify the key factors affecting battery performance degradation, but also quantify their impact, providing a scientific basis for maintenance personnel to take preventive measures in advance. This data-driven approach significantly improves the efficiency and accuracy of battery management, making it possible to optimize battery management and maintenance strategies. In addition, the present invention lays a solid foundation for building an intelligent and automated battery management system. Through real-time monitoring and dynamic control mechanisms, it ensures that the battery always operates in the optimal state, greatly improving the overall cycle performance and economic benefits of the battery. Ultimately, this innovative solution not only extends the service life of the battery, but also reduces maintenance costs, enhances the reliability and safety of the system, and promotes the development of battery health management technology to a new level. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below in conjunction with the accompanying drawings.

[0039] Figure 1 It is a flowchart of the specific steps of a method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1 As shown, the present invention is a method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis, comprising the following steps:

[0042] S1: During the battery monitoring cycle, the capacity and internal resistance change of the battery are monitored and analyzed in real time, and whether the electrolyte is decomposed is determined based on the monitoring and analysis results;

[0043] S2: According to the evaluation results, the charge and discharge efficiency and temperature fluctuation degree of the battery during the monitoring period are obtained in real time, and the influence of the charge and discharge efficiency and temperature fluctuation degree on the decomposition of the electrolyte is analyzed;

[0044] S3: Based on the impact analysis results, the battery’s charge and discharge efficiency and temperature are regulated in real time to improve the battery’s cycle performance.

[0045] In S1, during the monitoring period of the battery, the capacity and internal resistance change degree of the battery are monitored and analyzed in real time, and whether the electrolyte is decomposed is determined according to the monitoring and analysis results, which specifically includes: during the monitoring period of the battery, the capacity data and internal resistance data of the battery are acquired in real time according to the time series, and the battery capacity characteristic value and the battery internal resistance characteristic value are calculated according to the change degree of the battery capacity data and the internal resistance data, and the battery capacity characteristic value and the battery internal resistance characteristic value are used as the input of the machine learning model. The output of the model is the decomposition score, and it is determined whether the decomposition score is greater than or equal to a preset threshold value. If so, the electrolyte of the corresponding battery is decomposed, and if not, the electrolyte of the corresponding battery is decomposed;

[0046] The process of obtaining the battery capacity characteristic value is as follows:

[0047] Collect the real-time battery capacity data of the battery during the monitoring period to form a time series, and select a time series of a reference battery as the capacity change pattern under a healthy or ideal state;

[0048] Construct a local distance matrix to store the distance between each pair of corresponding points in the target sequence and the reference sequence. For each element in the matrix, the distance is obtained by calculating the square of the difference between the two points.

[0049] Initialize a cumulative distance moment of the same size and with the same starting value; for the first row of the cumulative distance matrix, each element is obtained by adding the cumulative distance of the same column of the previous row to the current local distance; for the first column of the cumulative distance matrix, each element is obtained by adding the cumulative distance of the same row of the previous column to the current local distance. For the remaining positions, the value is obtained by adding the local distance of the current position to the cumulative distance of the position with the smallest cumulative distance among the three adjacent positions to its left, above, and above the left; starting from the lower right corner of the cumulative distance matrix, trace back to the upper left corner in the direction that minimizes the cumulative distance, so as to determine an optimal alignment path connecting the starting point and the end point. The points on this path represent how the most similar parts of the two sequences match each other. The final battery capacity characteristic value is obtained by calculating the average value of all cumulative distances on the optimal alignment path;

[0050] The process of obtaining the battery internal resistance characteristic value is as follows:

[0051] The initial state estimate is set to the battery internal resistance value measured for the first time, and a larger initial error covariance matrix is ​​set to reflect the uncertainty of the initial estimate. At each time step, the internal resistance value at the current moment is predicted based on the state estimate value of the previous step, and the prediction error covariance matrix is ​​updated to reflect the uncertainty of the prediction value. The battery internal resistance at the current moment is obtained and recorded as the actual measurement value. The Kalman gain is calculated based on the predicted value and the actual measurement value. The formula Update the state estimate and the error covariance matrix at the same time, repeat the prediction and update steps until the monitoring period ends, and obtain a series of smoothed internal resistance estimates. Calculate the standard deviation of these smoothed internal resistance values ​​as the battery internal resistance characteristic value;

[0052] in, Indicates time steps, Indicates The updated state estimate for time steps is Indicates that based on The state estimation value of time steps predicts the internal resistance value at the current moment. Indicates The Kalman gain of time steps is Indicates The actual measured value of the time step;

[0053] The process of establishing the machine learning model is as follows:

[0054] Obtaining the battery capacity characteristic value and the battery internal resistance characteristic value of the battery during the monitoring period, constructing the battery capacity characteristic value and the battery internal resistance characteristic value into a comprehensive characteristic vector as the input of the machine learning model, taking minimizing the error between the predicted decomposition score and the actual decomposition score of the battery as the training goal, training the machine learning model, using historical battery data to train the machine learning model, and outputting the decomposition score of the battery according to the trained machine learning model, wherein the machine learning model is a gradient boosting decision tree;

[0055] It should be noted that the calculated battery decomposition score is used to determine whether the battery electrolyte has decomposed, so as to improve the overall cycle performance of the lithium-ion battery. This method can not only accurately capture the changing trend of the battery health status, but also provide an important basis for predicting the future health status of the battery.

[0056] In S2, according to the evaluation results, the charge and discharge efficiency and temperature fluctuation degree of the battery during the monitoring period are obtained in real time, and the influence of the charge and discharge efficiency and temperature fluctuation degree on the decomposition of the electrolyte is analyzed, including:

[0057] During the monitoring period of the battery, the charge and discharge efficiency data and the temperature data are acquired in real time according to the time series, and the charge and discharge efficiency characteristic value and the temperature fluctuation characteristic value are calculated according to the fluctuation amplitude of the charge and discharge efficiency and the temperature, and the influence factor is calculated according to the charge and discharge efficiency characteristic value and the temperature fluctuation characteristic value, and the influence factor is compared with the preset threshold value to determine whether the influence factor is greater than or equal to the preset threshold value, and if so, a serious influence is generated, and if not, a slight influence is generated;

[0058] The process of obtaining the characteristic value of the charge and discharge efficiency is as follows:

[0059] During the monitoring period of the battery, the charge and discharge efficiency data are acquired in real time according to the time series, the time domain signal is converted into the frequency domain signal by applying the fast Fourier transform to the time series data of the charge and discharge efficiency data, the cutoff frequency is selected, and the cutoff frequency is used to distinguish important low-frequency components from relatively unimportant high-frequency components, and the energy sum of all frequency components below the cutoff frequency is calculated; the proportion of low-frequency energy to total energy is calculated to obtain the charge and discharge efficiency characteristic value;

[0060] The energy calculation expression is: in, Represents low-frequency energy, Indicates A low-frequency component, represents the total number of low-frequency components, It represents the frequency domain representation of the charge and discharge efficiency data after fast Fourier transformation;

[0061] The process of obtaining the temperature fluctuation characteristic value is as follows:

[0062] During the monitoring period of the battery, the temperature data of the battery is acquired in real time according to the time series, and the temperature data is subjected to Haar wavelet transform to decompose the temperature data of the battery into an approximate coefficient and a detail coefficient, wherein the approximate coefficient is obtained by calculating the average value of adjacent data points, and the detail coefficient is obtained by calculating the difference of adjacent data points;

[0063] For each layer of detail coefficients obtained by Haar wavelet transform, the energy value is calculated. Specifically, for a set of detail coefficients of a certain layer, the squares of all its coefficients are summed to obtain the energy value of the corresponding layer.

[0064] The energy value of each layer reflects the fluctuation amplitude of the signal corresponding to the layer. The energy value of the low-frequency layer reflects the fluctuation on a long time scale, and the energy value of the high-frequency layer reflects the fluctuation on a short time scale.

[0065] The energy value of each layer detail coefficient is multiplied by the corresponding preset weight and then summed to obtain the final temperature fluctuation characteristic value;

[0066] The process of obtaining the impact factor is as follows:

[0067] Obtaining a charge and discharge efficiency characteristic value and a temperature fluctuation characteristic value of the battery, and preparing a set of historical data, including charge and discharge efficiency characteristic values, temperature fluctuation characteristic values ​​of multiple samples, and corresponding electrolyte decomposition labels, wherein the electrolyte decomposition labels include: electrolyte decomposition occurs and electrolyte does not decompose;

[0068] Use support vector machines to train historical data sets. For classification tasks, select linear kernels to map input features to high-dimensional space and find the optimal hyperplane to distinguish samples of different categories. For regression tasks, use support vector regression models to predict continuous values ​​of the degree of decomposition. During the training process, cross-validation is used to optimize model parameters including regularization parameters and kernel function parameters to improve the generalization ability of the model.

[0069] In the trained support vector machine model, the importance of the charge and discharge efficiency eigenvalues ​​and the temperature fluctuation eigenvalues ​​to the prediction results of electrolyte decomposition is analyzed.

[0070] For new test samples, the trained support vector machine model is used to predict the electrolyte decomposition influencing factor based on its charge and discharge efficiency characteristic value and temperature fluctuation characteristic value, and to determine whether the influencing factor is greater than or equal to the preset threshold. If so, it is recorded as a serious impact, otherwise, it is recorded as a minor impact.

[0071] In S3, according to the impact analysis results, the battery charging and discharging efficiency and temperature are adjusted in real time to improve the battery cycle performance, including:

[0072] Based on the serious impact, the PID controller is started to dynamically adjust the working state of the battery. For the charge and discharge efficiency, the PID controller controls the charge and discharge efficiency according to the deviation between the current efficiency and the target efficiency, adjusts the charge and discharge current or voltage, and optimizes the charge and discharge process to improve efficiency and reduce heat generation; for temperature control, the PID controller controls the power output of the cooling or heating device according to the deviation between the current temperature and the target temperature, so that the battery temperature quickly stabilizes within a safe range. The PID controller quickly responds to deviations through proportional terms, eliminates steady-state errors through integral terms, and suppresses excessive fluctuations through differential terms, thereby achieving accurate and stable control effects. This process ensures that the battery operates in an efficient and safe state, effectively prevents the risk of electrolyte decomposition, extends battery life and improves its reliability.

[0073] The working principle of the present invention is: the capacity and internal resistance data of the battery are acquired and analyzed in real time during the monitoring period, the characteristic value of the battery capacity is calculated by dynamic time warping, the characteristic value of the battery internal resistance is obtained by Kalman filtering, and these characteristic values ​​are input into the gradient boosting decision tree model, and the decomposition score is output to determine whether the electrolyte is decomposed. Secondly, for the charge and discharge efficiency and temperature fluctuation, the fast Fourier transform and the Haar wavelet transform are used to calculate the characteristic value of the charge and discharge efficiency and the characteristic value of the temperature fluctuation respectively, and then the support vector machine model is used to evaluate the influence of these characteristics on the decomposition of the electrolyte to determine whether there is a serious impact. Finally, according to the results of the impact degree analysis, the PID controller is started to regulate the charge and discharge efficiency and temperature of the battery in real time: for the charge and discharge efficiency, the PID controller adjusts the charge and discharge current or voltage, optimizes the charge and discharge process to improve efficiency and reduce heat generation; for temperature, the PID controller controls the power output of the cooling or heating device to stabilize the battery temperature within a safe range. Through the three functions of proportion, integration and differentiation, the PID controller achieves accurate and stable regulation effect, ensures that the battery operates in an efficient and safe state, effectively prevents the risk of electrolyte decomposition, prolongs the battery life and improves its reliability. This comprehensive solution can not only accurately capture the changing trends of the battery's health status, but also provide an important basis for predicting the battery's future health status, thereby comprehensively improving the cycle performance of lithium-ion batteries.

[0074] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0075] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0076] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0077] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0078] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. A method for improving the cycle performance of lithium-ion batteries based on multi-feature analysis, characterized in that: The following steps are involved: S1: During the battery monitoring cycle, the capacity and internal resistance change of the battery are monitored and analyzed in real time, and whether the electrolyte is decomposed is determined based on the monitoring and analysis results; S2: According to the evaluation results, the charge and discharge efficiency and temperature fluctuation degree of the battery during the monitoring period are obtained in real time, and the influence of the charge and discharge efficiency and temperature fluctuation degree on the decomposition of the electrolyte is analyzed; S3: Based on the impact analysis results, the battery’s charge and discharge efficiency and temperature are regulated in real time to improve the battery’s cycle performance.

2. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 1, characterized in that: The determining whether the electrolyte has decomposed specifically includes: During the battery monitoring cycle, the battery capacity data and internal resistance data are obtained in real time according to the time series. The battery capacity characteristic value and the battery internal resistance characteristic value are calculated according to the degree of change of the battery capacity data and the internal resistance data, and the battery capacity characteristic value and the battery internal resistance characteristic value are used as the input of the machine learning model. The output of the model is the decomposition score. It is determined whether the decomposition score is greater than or equal to the preset threshold. If so, the electrolyte of the corresponding battery is decomposed. If not, the electrolyte of the corresponding battery is not decomposed.

3. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 2, characterized in that: The process of obtaining the battery capacity characteristic value is as follows: Collect the real-time battery capacity data of the battery during the monitoring period to form a time series, and select a reference battery time series as the capacity change pattern under the healthy state; Construct a local distance matrix to store the distance between each pair of corresponding points in the target sequence and the reference sequence, which is obtained by calculating the square of the difference between the two points; Initialize a cumulative distance moment of the same size and with the same starting value; for the first row of the cumulative distance matrix, each element is obtained by adding the cumulative distance of the same column of the previous row to the current local distance; for the first column of the cumulative distance matrix, each element is obtained by adding the cumulative distance of the same row of the previous column to the current local distance, and the remaining positions are obtained by adding the local distance of the current position to the cumulative distance of the position with the smallest cumulative distance among the three adjacent positions to its left, above, and above the left; starting from the lower right corner of the cumulative distance matrix, trace back to the upper left corner along the direction that minimizes the cumulative distance, so as to determine an optimal alignment path connecting the starting point and the end point. The final battery capacity eigenvalue is obtained by calculating the average value of all cumulative distances on the optimal alignment path.

4. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 2, characterized in that: The process of obtaining the battery internal resistance characteristic value is as follows: The initial state estimate is set to the battery internal resistance value measured for the first time, and an initial error covariance matrix is ​​set. At each time step, the internal resistance value at the current moment is predicted based on the state estimate value of the previous step, and the prediction error covariance matrix is ​​updated at the same time to obtain the battery internal resistance at the current moment, which is recorded as the actual measurement value. The Kalman gain is calculated based on the predicted value and the actual measurement value, and the state estimate is updated. At the same time, the error covariance matrix is ​​updated. The prediction and update steps are repeated until the end of the monitoring period to obtain a series of smoothed internal resistance estimates. The standard deviation of these smoothed internal resistance values ​​is calculated as the battery internal resistance eigenvalue.

5. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 2, characterized in that: The process of establishing the machine learning model is as follows: The battery capacity characteristic value and the battery internal resistance characteristic value of the battery within the monitoring period are obtained, and the battery capacity characteristic value and the battery internal resistance characteristic value are constructed into a comprehensive characteristic vector as the input of the machine learning model. The machine learning model is trained with minimizing the error between the predicted decomposition score and the actual decomposition score of the battery as the training goal. The machine learning model is trained using historical battery data, and the decomposition score of the battery is output according to the trained machine learning model. The machine learning model is a gradient boosting decision tree.

6. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 1, characterized in that: The analysis of the influence of the charge-discharge efficiency and the temperature fluctuation on the decomposition of the electrolyte specifically includes: During the monitoring period of the battery, the charge and discharge efficiency data and temperature data are acquired in real time according to the time series. According to the fluctuation amplitude of the charge and discharge efficiency and the temperature, the charge and discharge efficiency characteristic value and the temperature fluctuation characteristic value are calculated respectively. According to the charge and discharge efficiency characteristic value and the temperature fluctuation characteristic value, the influence factor is calculated. The influence factor is compared with the preset threshold value to determine whether the influence factor is greater than or equal to the preset threshold value. If so, a serious impact is produced; if not, a slight impact is produced.

7. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 6, characterized in that: The process of obtaining the characteristic value of the charge and discharge efficiency is as follows: During the monitoring period of the battery, the charge and discharge efficiency data are acquired in real time according to the time series, and the time domain signal is converted into the frequency domain signal by applying the fast Fourier transform to the time series data of the charge and discharge efficiency data. The cutoff frequency is selected, and the cutoff frequency is used to distinguish important low-frequency components from relatively unimportant high-frequency components. The sum of the energies of all frequency components below the cutoff frequency is calculated; the proportion of low-frequency energy to total energy is calculated to obtain the characteristic value of the charge and discharge efficiency.

8. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 6, characterized in that: The process of obtaining the temperature fluctuation characteristic value is as follows: During the monitoring period of the battery, the temperature data of the battery is acquired in real time according to the time series, and the temperature data is subjected to Haar wavelet transform to decompose the temperature data of the battery into an approximate coefficient and a detail coefficient, wherein the approximate coefficient is obtained by calculating the average value of adjacent data points, and the detail coefficient is obtained by calculating the difference of adjacent data points; For each layer’s detail coefficient set, sum the squares of all its coefficients to get the energy value of the corresponding layer; The energy value of each layer detail coefficient is multiplied by the corresponding preset weight and then summed to obtain the final temperature fluctuation characteristic value.

9. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 6, characterized in that: The process of obtaining the impact factor is as follows: Obtaining a charge and discharge efficiency characteristic value and a temperature fluctuation characteristic value of the battery, and preparing a set of historical data, including charge and discharge efficiency characteristic values, temperature fluctuation characteristic values ​​of multiple samples, and corresponding electrolyte decomposition labels, wherein the electrolyte decomposition labels include: electrolyte decomposition occurs and electrolyte does not decompose; Use support vector machines to train historical data sets. For classification tasks, select a linear kernel to map input features to a high-dimensional space and find the optimal hyperplane to distinguish samples of different categories. For regression tasks, use a support vector regression model to predict the continuous value of the decomposition degree. During the training process, cross-validation is used to optimize model parameters including regularization parameters and kernel function parameters. The trained support vector machine model is used to predict the electrolyte decomposition influencing factor to determine whether the influencing factor is greater than or equal to the preset threshold. If so, it is recorded as a severe impact, otherwise, it is recorded as a slight impact.

10. The method for improving the cycle performance of a lithium-ion battery based on multi-feature analysis according to claim 1, characterized in that: According to the impact degree analysis result, the charging and discharging efficiency and temperature of the battery are controlled in real time, specifically including: Based on the serious impact, the PID controller is started to dynamically adjust the working state of the battery. For the charging and discharging efficiency, the PID controller controls the charging and discharging efficiency according to the deviation between the current efficiency and the target efficiency. For temperature control, the PID controller controls the power output of the cooling or heating device according to the deviation between the current temperature and the target temperature, so that the battery temperature is quickly stabilized within a safe range.

Images