Lithium battery charging and discharging management method and system based on data analysis

Abstract

The invention provides a lithium battery charging and discharging management method and system based on data analysis, and the method comprises the steps: carrying out the nonlinear compensation processing of an internal resistance original data sequence of a lithium battery according to a temperature coefficient dynamic change sequence, generating a temperature compensation internal resistance change rate sequence, processing the temperature compensation internal resistance change rate sequence through a self-adaptive state estimation algorithm, and obtaining a lithium battery charging and discharging management result. According to the method, a corrected charge state estimation sequence is generated, and then a charge-discharge speed decision matrix is determined according to the corrected charge state estimation sequence and a predicted health state grade sequence of the lithium battery, so that an optimal charge-discharge speed decision is made according to the real state of the battery, and an optimal battery charge-discharge regulation and control strategy is obtained. The intelligent regulation and control of the charging and discharging speed are realized by combining multi-dimensional control parameters and deeply analyzing the mutual relation among the parameters, and the lithium battery can be protected while quick charging is pursued.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of lithium battery charging and discharging, and particularly relates to a lithium battery charging and discharging management method and system based on data analysis. BACKGROUND

[0002] As a core component of modern energy storage technology, lithium batteries play a decisive role in key application fields such as electric vehicles, energy storage systems and portable electronic devices. With the increasing urgency of energy transformation demand, the charging and discharging management technology of lithium batteries has become an important technical bottleneck affecting the development of the entire industry. The current lithium battery charging and discharging management method generally has the problem of insufficient control accuracy. Most systems only rely on a single or a few parameters for simple threshold control, and cannot adapt to the complex and variable actual working condition requirements.

[0003] These traditional methods often show response lag and inaccurate control defects when facing the dynamic changes of battery state, and it is difficult to find the best balance point between battery performance and service life. The fundamental challenge of lithium battery charging and discharging management lies in the complex coupling relationship between multiple key control parameters. The change of battery temperature coefficient will directly affect the accurate measurement of internal resistance change rate. When the battery works in different temperature environments, the internal electrochemical reaction rate changes, resulting in nonlinear change characteristics of internal resistance. The fluctuation of internal resistance change rate further affects the accurate assessment of state of charge and state of health, because internal resistance is an important indicator reflecting the internal state of the battery, and its measurement error will be amplified in the state estimation process. The inaccuracy of state of charge and state of health assessment ultimately leads to deviation in charging and discharging speed control decision, and the system cannot develop the optimal current control strategy according to the real state of the battery, so as to pursue fast charging while possibly damaging the battery life, or to protect the battery at the expense of charging efficiency.

[0004] Therefore, how to build a precise management system that can comprehensively consider the battery temperature coefficient, internal resistance change rate, state of charge, state of health and other multi-dimensional control parameters, and realize intelligent regulation and control of charging and discharging speed through deep analysis of the mutual relationship between parameters, has become a key problem in the development of lithium battery charging and discharging management technology. SUMMARY

[0005] The present application provides a lithium battery charging and discharging management method and system based on data analysis to solve the problem that the existing technology may damage the battery life while pursuing fast charging or sacrifice the charging efficiency in the process of protecting the battery, realize the optimal current control strategy according to the real state of the battery, combine multi-dimensional control parameters, and realize intelligent regulation and control of charging and discharging speed through deep analysis of the mutual relationship between parameters.

[0006] The present application provides a lithium battery charging and discharging management method based on data analysis, which is executed by a computer and comprises:

[0007] determining a temperature coefficient dynamic change sequence based on real-time temperature data of the lithium battery, wherein the temperature coefficient dynamic change sequence is obtained based on a temperature peak value, a temperature average value and a temperature change rate sequence of the real-time temperature data;

[0008] performing nonlinear compensation processing on an internal resistance original data sequence of the lithium battery based on a temperature coefficient dynamic change sequence corresponding to a reference internal resistance correction parameter table, to generate a temperature compensation internal resistance change rate sequence;

[0009] generating a corrected state of charge estimation sequence based on the temperature compensation internal resistance change rate sequence using an adaptive state estimation algorithm;

[0010] inputting the corrected state of charge estimation sequence and preset battery cycle number data into a health state evaluation model to determine a health state grade sequence of the lithium battery, wherein the health state evaluation model is obtained by training a training set of state of charge data and charging and discharging cycle number data;

[0011] generating a charging and discharging speed decision matrix based on the corrected state of charge estimation sequence and the health state grade sequence;

[0012] determining a charging mode required by the lithium battery based on the charging and discharging speed decision matrix;

[0013] The charging mode is used for regulating and controlling the charging and discharging speed of the lithium battery, and the charging mode includes a fast charging mode and a standard charging mode.

[0014] The lithium battery charging and discharging management method based on data analysis provided by the application further comprises:

[0015] using a real-time feedback control mechanism to monitor real-time current change data and temperature response data in the charging and discharging process;

[0016] dynamically adjusting charging speed set values and discharging speed set values in the charging and discharging speed decision matrix based on the current change data and the temperature response data to generate an optimized control parameter sequence;

[0017] updating the running state of the charging and discharging equipment in real time based on the optimized control parameter sequence to determine updated running state data;

[0018] If the running state data does not meet preset stable conditions, a new optimized control parameter sequence is determined based on the current change data and the temperature response data;

[0019] The new optimized control parameter sequence is used to update the charging and discharging speed decision matrix.

[0020] The lithium battery charge-discharge management method based on data analysis provided by the application further comprises:

[0021] Based on the temperature coefficient dynamic change sequence, the temperature compensation internal resistance change rate sequence, the corrected state of charge estimation sequence and the health state grade sequence, a weighted fusion algorithm is applied to determine a comprehensive evaluation index sequence of the battery state.

[0022] Based on the comprehensive evaluation index sequence and the preset performance and life average threshold of the lithium battery, a personalized charge-discharge management scheme sequence is generated.

[0023] Based on the charge-discharge management scheme sequence, the control strategy parameters are updated, wherein the control strategy parameters at least include the charge-discharge speed decision matrix, the optimization control parameter sequence, the charging mode, the battery cycle number data or the internal resistance original data sequence.

[0024] The lithium battery charge-discharge management method based on data analysis provided by the application, the internal resistance reference correction parameter table corresponding to the temperature coefficient dynamic change sequence is used to perform nonlinear compensation processing on the internal resistance original data sequence of the lithium battery to generate a temperature compensation internal resistance change rate sequence, which comprises:

[0025] The internal resistance reference correction parameter table is used to perform nonlinear compensation on the internal resistance original data sequence of the lithium battery to obtain a preliminary compensation data sequence.

[0026] If the temperature data influence in the preliminary compensation data sequence exceeds a preset threshold, a temperature compensation data sequence is generated based on the preliminary compensation data sequence and the environmental temperature data.

[0027] Based on the temperature compensation data sequence, the internal resistance change rate of the lithium battery is calculated to determine an internal resistance change rate sequence.

[0028] Key feature points are extracted from the internal resistance change rate sequence, and a support vector regression algorithm is used to predict the internal resistance change trend of the lithium battery to obtain an internal resistance change trend sequence.

[0029] The internal resistance change trend sequence is calculated using a sliding window method to calculate the local change rate mean of the lithium battery to obtain a smooth internal resistance change rate sequence.

[0030] Based on the smooth internal resistance change rate sequence, a time series analysis method is used to detect and remove abnormal change points to generate the temperature compensation internal resistance change rate sequence.

[0031] According to the lithium battery charge and discharge management method based on data analysis provided by the application, the adaptive state estimation algorithm is adopted based on the temperature compensation internal resistance change rate sequence to generate a corrected state of charge estimation sequence, which comprises:

[0032] The temperature sensor data and the voltage current history data sequence are acquired, and the Kalman filter algorithm is adopted to smooth the temperature compensation internal resistance change rate sequence based on the temperature sensor data and the voltage current history data sequence, so as to obtain a smoothed internal resistance change rate sequence.

[0033] The temperature compensation model is preset, and the temperature compensation is performed on the smoothed internal resistance change rate sequence to obtain a temperature compensation internal resistance change rate sequence.

[0034] The particle filter algorithm is adopted to obtain the battery state of the lithium battery in combination with the temperature compensation internal resistance change rate sequence and the voltage current history data sequence, so as to obtain an initial state of charge sequence.

[0035] If the change rate of the initial state of charge sequence exceeds a preset threshold value, the initial state of charge sequence is adjusted by the error compensation algorithm to generate a corrected state of charge estimation sequence.

[0036] According to the lithium battery charge and discharge management method based on data analysis provided by the application, the corrected state of charge estimation sequence and the preset battery cycle number data are input into a health state evaluation model to determine a health state grade sequence of the lithium battery, which comprises:

[0037] The corrected state of charge sequence and the battery cycle number data are integrated into a unified data set to obtain a preliminarily processed battery state data set.

[0038] Based on the preliminarily processed battery state data set, a support vector machine model is adopted to extract features thereof to determine a preliminary characteristic value sequence of capacity attenuation, wherein the preliminary characteristic value sequence of capacity attenuation is used to represent the correlation between the state of charge and the cycle number of the lithium battery.

[0039] Based on the preliminary characteristic value sequence of capacity attenuation, a dynamic change sequence of an internal aging index is calculated in combination with a pre-established aging index calculation rule to obtain a quantitative result of the aging index.

[0040] Based on the quantitative result of the aging index, an abnormality is marked to determine the abnormal distribution of the aging index.

[0041] Based on the abnormal distribution of the aging index and the preliminary characteristic value sequence of capacity attenuation, a preset health state evaluation model is adopted for comprehensive calculation to obtain a health state grade sequence.

[0042] The application provides a lithium battery charge-discharge management method based on data analysis.

[0043] The modified state of charge estimation sequence and the health state grade sequence are input into the lithium battery, and real-time state data of the lithium battery is extracted to obtain state sequence data;

[0044] Based on the state sequence data, an intelligent current control algorithm is used to obtain the state of charge and the health state of the lithium battery;

[0045] The state of charge and the health state are classified by using a support vector machine algorithm to obtain a classification feature vector;

[0046] Based on the classification feature vector, an initial speed decision matrix is generated by using a logistic regression model in combination with preset state of charge threshold values and health state threshold values;

[0047] If the variance of the candidate values in the initial speed decision matrix is lower than a preset threshold value, the initial speed decision matrix is smoothed by using a linear interpolation method to generate the charge-discharge speed decision matrix.

[0048] The application further provides a lithium battery charge-discharge management system based on data analysis.

[0049] The first analysis module is used for determining a temperature coefficient dynamic change sequence based on real-time temperature data of the lithium battery, wherein the temperature coefficient dynamic change sequence is obtained based on a temperature peak value, a temperature average value and a temperature change rate sequence of the real-time temperature data;

[0050] The second analysis module is used for performing nonlinear compensation processing on an internal resistance original data sequence of the lithium battery based on a temperature compensation internal resistance change rate sequence corresponding to a reference correction parameter table of the internal resistance of the lithium battery;

[0051] The third analysis module is used for generating a modified state of charge estimation sequence based on the temperature compensation internal resistance change rate sequence by using an adaptive state estimation algorithm;

[0052] The fourth analysis module is used for inputting the modified state of charge estimation sequence and preset battery cycle number data into a health state evaluation model to determine a health state grade sequence of the lithium battery, wherein the health state evaluation model is obtained by training a training set of a state of charge data set and a charge-discharge cycle number data set;

[0053] a fifth analysis module configured to generate a charging and discharging speed decision matrix based on the corrected state of charge estimation sequence and the health state level sequence;

[0054] a sixth analysis module configured to determine a charging mode required by the lithium battery based on the charging and discharging speed decision matrix;

[0055] The charging mode is used for regulating the charging and discharging speed of the lithium battery, and the charging mode includes a fast charging mode and a standard charging mode.

[0056] The application further provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the lithium battery charging and discharging management method based on data analysis according to any one of the above when executing the program.

[0057] The application further provides a non-transitory computer readable storage medium having a computer program stored thereon, and the computer program is executable on a processor to implement the lithium battery charging and discharging management method based on data analysis according to any one of the above.

[0058] The application provides a lithium battery charging and discharging management method and system based on data analysis, which performs nonlinear compensation processing on an internal resistance original data sequence of a lithium battery according to a temperature coefficient dynamic change sequence to generate a temperature compensation internal resistance change rate sequence, processes the temperature compensation internal resistance change rate sequence by using an adaptive state estimation algorithm to generate a corrected state of charge estimation sequence, and then determines a charging and discharging speed decision matrix according to the corrected state of charge estimation sequence and a predicted health state level sequence of the lithium battery, so as to make an optimal charging and discharging speed decision according to the real state of the battery, obtain an optimal battery charging and discharging regulation strategy, realize intelligent regulation and control of the charging and discharging speed by combining multiple control parameters and performing deep analysis on the mutual relationship between the parameters, and achieve fast charging while protecting the lithium battery. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 is one of flowcharts of the lithium battery charging and discharging management method based on data analysis provided by the application;

[0060] Figure 2 is another flowchart of the lithium battery charging and discharging management method based on data analysis provided by the application;

[0061] Figure 3 is a third flowchart of the lithium battery charging and discharging management method based on data analysis provided by the application;

[0062] Figure 4Fig. 4 is a fourth flowchart of a lithium battery charging and discharging management method based on data analysis according to an embodiment of the present application;

[0063] Figure 5 Fig. 5 is a fifth flowchart of a lithium battery charging and discharging management method based on data analysis according to an embodiment of the present application;

[0064] Figure 6 Fig. 6 is a sixth flowchart of a lithium battery charging and discharging management method based on data analysis according to an embodiment of the present application;

[0065] Figure 7 Fig. 7 is a seventh flowchart of a lithium battery charging and discharging management method based on data analysis according to an embodiment of the present application;

[0066] Figure 8 Fig. 8 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0068] With reference to Figure 1 The present embodiment provides a lithium battery charging and discharging management method based on data analysis, comprising the following steps:

[0069] In step 100, a temperature coefficient dynamic change sequence is determined based on real-time temperature data of the lithium battery, wherein the temperature coefficient dynamic change sequence is obtained based on a temperature peak value, a temperature average value and a temperature change rate sequence of the real-time temperature data;

[0070] Real-time temperature data and historical temperature curves are obtained from a lithium battery sensor. Based on the real-time temperature data and the historical temperature data, a temperature peak value, a temperature average value and a temperature change rate sequence of the lithium battery are extracted. A time series analysis method is used to determine the collection frequency and integrity of the real-time temperature data, and a standardized temperature data set is obtained. According to the standardized temperature data set, a peak value detection algorithm is used to extract a temperature peak value sequence. According to the standardized temperature data set, a temperature average value within a preset time window is calculated, and an average value sequence is obtained. From the temperature peak value sequence and the average value sequence, a ratio of a temperature difference value and a time interval of adjacent time points is calculated, and a temperature change rate sequence is obtained.

[0071] The temperature peak value sequence, the average value sequence and the change rate sequence constitute a to-be-processed temperature matrix, and then the principal component analysis algorithm is used to process the to-be-processed temperature matrix, the purpose being to extract key information from the multi-dimensional temperature feature sequence and extract the main feature vector in the to-be-processed temperature matrix to obtain a multi-parameter coupling feature set. Based on the multi-parameter coupling feature set, a temperature coefficient dynamic change sequence is determined. On the one hand, the multi-parameter coupling feature set can be directly used as the temperature coefficient dynamic change sequence, and on the other hand, a feature sequence obtained after smoothing processing of the multi-parameter coupling feature set can also be used as the temperature coefficient dynamic change sequence. Specifically, if the deviation of the multi-parameter coupling feature set from the preset threshold exceeds a specified range, the Kalman filtering algorithm is used to perform smoothing processing on the multi-parameter coupling feature set to obtain the temperature coefficient dynamic change sequence.

[0072] In step 200, based on the temperature coefficient dynamic change sequence corresponding to the internal resistance reference correction parameter table, the internal resistance original data sequence of the lithium battery is subjected to nonlinear compensation processing to generate a temperature compensation internal resistance change rate sequence.

[0073] The internal resistance reference correction parameter table is determined based on the temperature coefficient dynamic change sequence, and the temperature compensation internal resistance change rate sequence records the law of the change of the battery internal resistance with time under different temperature conditions.

[0074] The determination method of the internal resistance reference correction parameter table is as follows: first, the reaction rate constant is calculated according to the absolute temperature of the temperature coefficient dynamic change sequence and the preset gas constant to obtain a reaction rate sequence, wherein the method for calculating the reaction rate sequence can refer to the Arrhenius equation. The temperature feature value in the reaction rate sequence is extracted, the correlation degree with the temperature coefficient sequence is calculated, and the internal resistance correction factor is obtained, wherein the temperature feature value in the reaction rate sequence includes temperature sensitivity characteristics, reaction kinetics state characteristics, safety warning characteristics or aging correlation characteristics. If the correlation degree is lower than a preset threshold, the gas constant is adjusted, and the reaction rate sequence is recalculated. Then, according to the internal resistance correction factor, the initial internal resistance reference parameter table is generated in combination with the battery internal resistance value. The initial internal resistance reference parameter table contains the mapping relationship between the temperature coefficient and the internal resistance correction factor. The parameter pairs are extracted from the initial internal resistance reference parameter table, and the least square method is used to optimize the parameter pairs to obtain the optimized internal resistance correction parameter. According to the optimized internal resistance correction parameter, the initial internal resistance reference parameter table is updated to generate the internal resistance reference correction parameter table.

[0075] The original data sequence of the internal resistance of the lithium battery is measured by using a high-frequency pulse injection method, controlling external interference and humidity. Specifically, a high-frequency pulse injection method is used to generate a pulse signal, and a stable frequency pulse signal is output by a preset signal generator to obtain initial pulse data. Then, the initial pulse data is preprocessed by a digital filter to suppress external interference and humidity effects, and filtered pulse data is obtained. According to the filtered pulse data, if the signal amplitude of the filtered pulse data exceeds a preset threshold, the signal frequency characteristics thereof are extracted by a fast Fourier transform algorithm, and the signal frequency characteristics are used to represent the frequency response characteristics of the battery internal resistance. According to the signal frequency characteristics, the original value of the battery internal resistance is calculated by an impedance calculation formula. From the original value of the battery internal resistance, a sliding window method is used to smooth the original value of the battery internal resistance to generate a continuous internal resistance original data sequence. The internal resistance original data sequence is obtained, and the internal resistance original data sequence is nonlinearly compensated by using reference correction parameters in a reference correction parameter table in combination with environmental temperature data to generate a temperature-compensated internal resistance change rate sequence.

[0076] Step 300, based on the temperature-compensated internal resistance change rate sequence, an adaptive state estimation algorithm is used to generate a corrected state of charge estimation sequence;

[0077] The adaptive state estimation algorithm is used to correct the state of charge of the battery in real time according to the temperature-compensated internal resistance change rate sequence, so as to significantly improve the accuracy of battery state monitoring. Specifically, the core principle of the adaptive state estimation algorithm is to dynamically analyze the temperature-compensated internal resistance change trend by dynamically fusing the internal resistance change data, the temperature-compensated internal resistance data, and the state of charge data, and to construct a nonlinear state of charge correction model. That is, the adaptive state estimation algorithm can construct a nonlinear dynamic change relationship between the internal resistance change and the state of charge, correct the state of charge of the battery, and improve the estimation accuracy of the state of charge. Therefore, the adaptive state estimation algorithm establishes a dynamic correlation between the battery internal resistance and the state of charge of the lithium battery, and fully considers the influence of temperature change on the relationship between the two, so as to correct the state of charge of the lithium battery under the internal resistance change rate by using the temperature-compensated internal resistance change rate sequence, and obtain a corrected state of charge estimation sequence. The corrected state of charge estimation sequence is used to represent the percentage of the current remaining capacity of the lithium battery, and reflects the proportion of the available energy of the lithium battery at a certain moment to the total energy of its fully charged state. The correction method of the state of charge by using the adaptive state estimation algorithm in the embodiment can dynamically analyze the temperature-compensated internal resistance change trend and realize noise adaptation, which significantly improves the robustness of the state estimation of the lithium battery.

[0078] Step 400, input the corrected state of charge estimation sequence and the preset battery cycle number data into a health state evaluation model to determine a health state grade sequence of the lithium battery, wherein the health state evaluation model is obtained by training a training set of a state of charge data set and a charge-discharge cycle number data set;

[0079] According to the corrected state of charge sequence, a sliding window method is used to analyze the change trend to obtain a battery state change trend. Through a preset battery health model, the battery health degree is calculated by combining the battery state change trend and the voltage and current historical sequence to obtain a health degree index. Time series analysis is used to predict the future battery state according to the health degree index and the corrected state of charge sequence to obtain a predicted state sequence.

[0080] By obtaining the corrected state of charge sequence from the monitoring system and the pre-stored battery cycle number data, a unified data set is integrated to obtain a preliminarily processed battery state data set. According to the preliminarily processed battery state data set and the battery cycle number data, a support vector machine model is used to extract features of the battery state data set, analyze the correlation between the state of charge and the cycle number, determine a preliminary characteristic value sequence of capacity attenuation and a quantitative result of the aging index. Then, the preliminary characteristic value sequence of capacity attenuation and the quantitative result of the aging index are input into a health state evaluation model, and a preset health state evaluation model is used for comprehensive calculation to obtain a health state grade sequence of the lithium battery. The health state evaluation model is obtained by training a training set of the state of charge data set and the charge-discharge cycle number data set.

[0081] Step 500, generate a charge-discharge speed decision matrix based on the corrected state of charge estimation sequence and the health state grade sequence;

[0082] In the lithium battery management system, the generation of the charge-discharge speed decision matrix is an intelligent and dynamic decision-making process, which is based on two key input parameters: the corrected state of charge estimation sequence and the health state grade sequence of the battery. This decision matrix is essentially a multi-dimensional query table that provides the optimal charge-discharge rate guidance for the system under different state of charge and health state combination conditions.

[0083] First, the modified state of charge estimation sequence, which has been temperature compensated and dynamically calibrated, is analyzed to accurately reflect the current true state of charge of the battery. At the same time, the state of health grade sequence provides the long-term state of health evaluation results of the battery, for example, the battery life can be divided into multiple grades (such as A grade representing good state of health, and E grade representing serious aging). By cross-referencing these two key parameters, a two-dimensional decision space is established, in which the horizontal axis represents the state of charge estimation interval, and the vertical axis represents the state of health grade. Therefore, by inputting the modified state of charge estimation sequence and the state of health grade sequence of the lithium battery into the two-dimensional decision space, the strategy decision scheme for charging and discharging is predicted, and a charging and discharging speed decision matrix is generated

[0084] In each intersection unit of state of charge and state of health grade, the system will preset the corresponding charging and discharging speed strategy. For example, when the battery is in the medium state of charge interval (30%-70%) and the state of health grade is rated as good (A grade or B grade), the system allows a higher charging and discharging rate; when the state of charge is close to full or empty, or the state of health grade shows that the battery has obviously aged, the system will automatically limit the charging and discharging speed to protect the battery. This decision matrix also considers dynamic adjustment of real-time working conditions, such as automatically adjusting the charging and discharging speed threshold of all units to a lower value in a high-temperature environment.

[0085] Step 600, based on the charging and discharging speed decision matrix, determine the charging mode required by the lithium battery;

[0086] The charging mode is used to regulate the charging and discharging speed of the lithium battery, and the charging mode includes a fast charging mode and a standard charging mode.

[0087] The fast charging mode includes a fast charging mode parameter sequence, and the standard charging mode includes a standard mode parameter sequence. According to the charging and discharging speed decision matrix, it is judged whether the state of charge is higher than a preset high state of charge threshold. If yes, the fast charging mode is selected, and a fast charging mode parameter sequence is generated. The fast charging mode parameter sequence is used to charge and discharge the lithium battery according to the fast charging mode. If the state of charge is lower than the preset high state of charge threshold, the standard charging mode is selected, and a standard charging mode parameter sequence is generated through a parameter mapping table. The standard charging mode parameter sequence is used to charge and discharge the lithium battery according to the standard charging mode. The fast charging mode parameter sequence or the standard charging mode parameter sequence is transmitted to the charging controller through the battery management system, so that the charging controller charges and discharges the lithium battery according to the corresponding parameters.

[0088] The application provides a lithium battery charging and discharging management method based on data analysis, which comprises the following steps: performing nonlinear compensation processing on an original data sequence of the internal resistance of a lithium battery according to a temperature coefficient dynamic change sequence, generating a temperature compensation internal resistance change rate sequence, processing the temperature compensation internal resistance change rate sequence through an adaptive state estimation algorithm, generating a corrected state of charge estimation sequence, and determining a charging and discharging speed decision matrix according to the corrected state of charge estimation sequence and a predicted health state grade sequence of the lithium battery, so as to realize optimal charging and discharging speed decision according to the real state of the battery, obtain optimal battery charging and discharging regulation and control strategy, realize intelligent regulation and control of the charging and discharging speed through deep analysis of the mutual relationship between multi-dimensional control parameters, and achieve protection of the lithium battery while pursuing fast charging.

[0089] In one embodiment, referring to Figure 2 , it also comprises:

[0090] Step 700, a real-time feedback control mechanism is adopted to monitor real-time current change data and temperature response data in the charging and discharging process;

[0091] Step 800, based on the current change data and the temperature response data, the charging speed setting value and the discharging speed setting value in the charging and discharging speed decision matrix are dynamically adjusted to generate an optimized control parameter sequence;

[0092] Step 900, based on the optimized control parameter sequence, the running state of the charging and discharging equipment is updated in real time to determine updated running state data;

[0093] Step 1000, if the running state data does not meet preset stable conditions, a new optimized control parameter sequence is determined based on the current change data and the temperature response data;

[0094] The new optimized control parameter sequence is used to update the charging and discharging speed decision matrix.

[0095] The current change data and temperature response data in the charging and discharging process are collected in real time by a sensor device to obtain an initial monitoring data set, and the initial monitoring data set includes the current change data and the temperature response data. According to the initial monitoring data set, the current change data and the temperature response data are detected for abnormalities by using a preset threshold range, and if it is detected that the initial monitoring data set exceeds the threshold range, the initial monitoring data set is marked as an abnormal data point, and an abnormal data distribution feature is determined. According to the abnormal data distribution feature, abnormal state information of the charging and discharging process corresponding to the abnormal data is obtained, the support vector machine algorithm is used to classify the abnormal state information, and it is determined whether the current charging and discharging process has a potential risk. If it is determined that the current charging and discharging process has a potential risk, the charging speed setting value and the discharging speed setting value in the decision matrix are dynamically adjusted to obtain an optimized control parameter sequence. The running state of the charging and discharging device is updated in real time by using the optimized control parameter sequence, updated running data is obtained, and it is determined whether the running state meets a preset stable condition. If the running state does not meet the preset stable condition, new optimized control parameter sequences are generated again based on the current change data and the temperature response data, and the charging and discharging setting values in the charging and discharging speed decision matrix are updated according to the new optimized control parameter sequences.

[0096] Specifically, the charging and discharging process is optimized through a real-time feedback control mechanism, the current and temperature data need to be collected, the charging and discharging speed setting values in the decision matrix are dynamically adjusted, and the optimized control parameter sequence is generated. First, high-precision sensors are used to collect the current (unit: ampere, range 0-50 A) and temperature (unit: Celsius, range 20-60℃) data in the battery charging and discharging process at a frequency of 100 Hz, for example, the current value sequence is [10.5, 11.2, 10.8] A, and the temperature sequence is [25.3, 26.1, 27.0]℃. Then, the current change rate (ΔI / Δt) and the temperature rise rate (ΔT / Δt) are analyzed. If ΔI / Δt>2A / s or ΔT / Δt>0.5℃ / s, it indicates that the battery is at high load or overheating risk, and the charging and discharging speed needs to be reduced. Based on this, a decision matrix is constructed, the matrix dimension is 3x3, including the charging speed (low: 1C, medium: 2C, high: 3C) and the discharging speed (low: 0.5C, medium: 1C, high: 2C), and the initial setting value is medium speed (charging 2C, discharging 1C). Through a fuzzy logic control algorithm, the matrix is adjusted according to the current change rate and the temperature rise rate. For example, when ΔT / Δt=0.6℃ / s, the fuzzy rule reduces the charging speed from 2C to 1C, and the discharging speed remains 1C, and the adjusted control parameter sequence is output: [1C, 1C]. Wherein, C represents the capacity value of the battery under standard conditions, and "C" in the charging and discharging speed is the rate, which represents the ratio of the current to the battery capacity, and in the charging and discharging speed, it represents the rate of charging and discharging.

[0097] In an embodiment, refer to Figure 3 Further comprising:

[0098] Step 1100, based on the temperature coefficient dynamic change sequence, the temperature compensation internal resistance change rate sequence, the corrected state of charge estimation sequence and the health state level sequence, applying a weighted fusion algorithm to determine a comprehensive evaluation index sequence of the battery state;

[0099] Step 1200, based on the comprehensive evaluation index sequence and the preset performance and life average threshold of the lithium battery, generating a personalized charging and discharging management scheme sequence;

[0100] Step 1300, based on the charging and discharging management scheme sequence, updating the control strategy parameters, wherein the control strategy parameters at least include the charging and discharging speed decision matrix, the optimization control parameter sequence, the charging mode, the battery cycle count data or the internal resistance original data sequence.

[0101] First, four key parameter sequences are collected: temperature coefficient dynamic change sequence, temperature compensation internal resistance change rate sequence, corrected state of charge estimation sequence and health state level sequence. These parameters reflect the environmental adaptability, internal characteristics, real-time power state and long-term health of the battery. The system uses a weighted fusion algorithm to dynamically adjust the weight proportion of each parameter according to the current working condition, and finally generates a comprehensive evaluation index sequence between 0 and 1. This index comprehensively represents the instantaneous state of the battery, and the higher the value, the better the state. After generating the comprehensive evaluation index sequence, combined with the user's preset performance and life average threshold, a personalized charging and discharging management scheme sequence is developed. The system divides the battery state into multiple interval levels, each interval corresponding to a different management strategy. For example, when the comprehensive evaluation index is high, a performance priority strategy can be used to allow a larger charging and discharging current; when the index is low, a life priority strategy is switched to limit the charging and discharging range to prolong the battery life. These strategies will form an ordered scheme sequence to guide subsequent charging and discharging operations. Then the specific strategy update work is performed. The system dynamically adjusts multiple parameters of the control system according to the charging and discharging management scheme. These parameters include the charging and discharging speed decision matrix, the optimization control parameter sequence, the charging mode selection, the battery cycle count data and the internal resistance original data sequence. By continuously updating these parameters, the system can achieve adaptive control to ensure that the battery can obtain the optimal management strategy under various working conditions.

[0102] Take the battery management system of an electric vehicle as an example. One day at noon, the vehicle is preparing for fast charging in a 35℃ high-temperature environment. The system detects that the current temperature coefficient is 0.8 (decreased compared to the standard temperature), the temperature-compensated internal resistance increases by 20%, the corrected state of charge is 65%, and the battery health state rating is B level (health degree 85%). Through weighted calculation, the current comprehensive evaluation index is 0.78, which belongs to good condition. According to the "balancing mode" threshold preset by the vehicle owner, the system decides to use a medium-intensity charging strategy: use 0.5 times the pulse charging method, set the upper limit of the state of charge to 85%, and closely monitor the temperature change. If the temperature exceeds 40℃, the charging current will be automatically reduced. The system updates the following control parameters: change the charging mode from standard constant current to pulse charging; adjust the charging and discharging speed decision matrix to use a more conservative current setting under high-temperature conditions; record the initial internal resistance data of this charging for subsequent health state analysis; and update the battery cycle count counter.

[0103] The embodiments of the present application comprehensively consider various indicators, apply a weighted fusion algorithm to calculate a comprehensive evaluation index of the battery state, generate a personalized charging and discharging management scheme accordingly, and form a closed-loop adaptive management process. Through the cooperative work of the above steps, both the charging speed and the temperature rise of the battery are effectively controlled under high-temperature conditions, the service life of the lithium battery is effectively improved, the balance between performance and service life is achieved, the charging and discharging efficiency is optimized, the balance between battery performance and service life is achieved, and a new technical scheme is provided for intelligent management of lithium batteries.

[0104] In one embodiment, referring to Figure 4 , the internal resistance original data sequence of the lithium battery is subjected to nonlinear compensation processing based on the internal resistance reference correction parameter table corresponding to the temperature coefficient dynamic change sequence, to generate a temperature-compensated internal resistance change rate sequence, including:

[0105] Step 201, the internal resistance original data sequence of the lithium battery is subjected to nonlinear compensation based on the internal resistance reference correction parameter table, to obtain a preliminary compensation data sequence;

[0106] Step 202, if the temperature data influence in the preliminary compensation data sequence exceeds a preset threshold, a temperature compensation data sequence is generated based on the preliminary compensation data sequence and environmental temperature data;

[0107] Step 203, based on the temperature compensation data sequence, the internal resistance change rate of the lithium battery is calculated to determine an internal resistance change rate sequence;

[0108] Step 204, key feature points are extracted from the internal resistance change rate sequence, a support vector regression algorithm is used to predict the internal resistance change trend of the lithium battery, and an internal resistance change trend sequence is obtained;

[0109] Step 205, for the internal resistance change trend sequence, a sliding window method is used to calculate the local change rate mean of the lithium battery, and a smooth internal resistance change rate sequence is obtained;

[0110] Step 206, based on the smooth internal resistance change rate sequence, a time series analysis method is used to detect and remove abnormal change points, and a temperature compensation internal resistance change rate sequence is generated.

[0111] The internal resistance original data sequence of the lithium battery is compensated by the reference correction parameter in the preset internal resistance reference correction parameter table, and a preliminary compensation data sequence is obtained. If the temperature influence of the preliminary compensation data sequence exceeds the preset threshold, a temperature influence compensation model is used in combination with the environmental temperature data to generate a temperature compensation data sequence.

[0112] According to the internal resistance value at the last time point and the current time point in the temperature compensation data sequence, the internal resistance change rate is calculated, and an internal resistance change rate sequence is generated. Key feature points are extracted from the internal resistance change rate sequence, a support vector regression algorithm is used to predict the internal resistance change trend, and an internal resistance change trend sequence is obtained. For the internal resistance change trend sequence, a sliding window method is used to calculate the local change rate mean, and a smooth internal resistance change rate sequence is generated. Through the smooth internal resistance change rate sequence, a time series analysis method is used to detect abnormal change points, and a temperature compensation internal resistance change rate sequence is generated. The calculation formula of the internal resistance change rate r is as follows:

[0113]

[0114] Wherein, r is the internal resistance change rate in the internal resistance change rate sequence, R k is the temperature compensated internal resistance value at the kth time point, R k―1 is the temperature compensated internal resistance value at the k-1th time point, t k is the timestamp at the kth time point, t k―1 is the timestamp at the k-1th time point.

[0115] In this embodiment, a multi-level compensation mechanism is established, and through the synergistic effect of internal resistance correction, temperature compensation and abnormality removal, the data quality is significantly improved. Secondly, the traditional compensation processing and trend prediction are organically combined to form a complete analysis chain from data cleaning to state prediction. Moreover, a variety of adaptive processing methods are used, including dynamic threshold, variable window, etc., so that the system can intelligently cope with different working conditions. Finally, the combination of support vector regression and time series analysis not only ensures the prediction accuracy, but also enhances the robustness of the algorithm, so that through the established lithium battery internal resistance data intelligent processing flow, through multi-level compensation and trend analysis, the internal resistance characteristics are accurately described and reliably predicted.

[0116] In an embodiment, referring to Figure 5 , the adaptive state estimation algorithm is used to generate a corrected state of charge estimation sequence based on the temperature-compensated internal resistance change rate sequence, including:

[0117] In step 301, temperature sensor data and voltage and current historical data sequences are obtained, and the Kalman filter algorithm is used to smooth the temperature-compensated internal resistance change rate sequence based on the temperature sensor data and the voltage and current historical data sequences, to obtain a smoothed internal resistance change rate sequence.

[0118] In step 302, a preset temperature compensation model is used to perform temperature compensation on the smoothed internal resistance change rate sequence, to obtain a temperature-compensated internal resistance change rate sequence.

[0119] In step 303, the particle filter algorithm is used to obtain the state of the lithium battery in combination with the temperature-compensated internal resistance change rate sequence and the voltage and current historical data sequence, to obtain an initial state of charge sequence.

[0120] In step 304, if the change rate of the initial state of charge sequence exceeds a preset threshold, an error compensation algorithm is used to adjust the initial state of charge sequence, to generate a corrected state of charge estimation sequence.

[0121] The temperature sensor data and voltage and current collection data are obtained, the Kalman filter algorithm is used to smooth the internal resistance change rate sequence, to generate a smoothed internal resistance change rate sequence. A preset temperature compensation model is used to perform temperature compensation on the smoothed internal resistance change rate sequence, to obtain a temperature-compensated internal resistance change rate sequence. The particle filter algorithm is used to estimate the state of the battery in combination with the temperature-compensated internal resistance change rate sequence and the voltage and current historical data sequence, to obtain an initial state of charge sequence. If the change rate of the initial state of charge sequence exceeds a preset threshold, an error compensation algorithm is used to adjust the estimation parameter, to obtain a corrected state of charge sequence.

[0122] Specifically, to achieve the processing of the temperature-compensated internal resistance change rate sequence and the voltage and current historical data sequence by the adaptive state estimation algorithm to analyze the battery state and generate the corrected state of charge estimation sequence, the following specific implementation method can be used. Assuming that the battery management system collects the internal resistance change rate sequence at a temperature of 25°C as [0.002, 0.003, 0.0025, 0.004] Ω / s, the voltage sequence as [3.7, 3.68, 3.65, 3.6] V, and the current sequence as [1.0, 1.2, 1.1, 0.9] A. First, the internal resistance change rate is temperature-compensated, and the compensated internal resistance change rate sequence is calculated as [0.00203, 0.003045, 0.0025375, 0.00406] Ω / s. Then, the Kalman filter algorithm is used to process the voltage and current historical data to construct a state space model. Through iterative updating, the state of charge sequence is estimated as [0.85, 0.849, 0.848, 0.847]. By analyzing the internal resistance change rate, it is found that 0.00406 exceeds the threshold range of [0.001, 0.0035] Ω / s, triggering the error compensation mechanism. The error compensation uses the least squares method to optimize the battery state of charge estimation, combines the voltage residual error, adjusts the state of charge to minimize the residual error, and obtains the corrected state of charge sequence as [0.851, 0.8495, 0.8482, 0.8473]. Finally, through the mapping relationship between the battery state of charge sequence and the battery health state, the battery state is evaluated, and the battery health state is calculated as 99.71%, indicating that the battery state is good.

[0123] The embodiment proposes an advanced lithium battery state estimation process, which realizes high-precision dynamic estimation of the battery internal resistance and state of charge through multi-stage data processing and intelligent algorithm fusion. The innovation of this series of steps lies in three aspects: first, the two algorithms of Kalman filter and particle filter with their own advantages are organically combined, the former guarantees the quality of data preprocessing, and the latter provides strong state estimation capability. Second, the temperature compensation model is no longer a simple linear correction, but considers the performance evolution of the battery throughout its life cycle, realizing true adaptive compensation. Finally, the dynamic threshold design and error compensation mechanism constitute a double guarantee, enabling the system to automatically identify and correct abnormal estimation, significantly improving the robustness of state estimation.

[0124] In one embodiment, referring to Figure 6 , the method further comprises:

[0125] Step 401, integrating the corrected state of charge sequence and the battery cycle number data into a unified data set to obtain a preliminarily processed battery state data set;

[0126] In step 402, based on the preliminary processed battery state data set, a support vector machine model is used to extract features, and a preliminary feature value sequence of capacity attenuation is determined, wherein the preliminary feature value sequence of capacity attenuation is used to represent the correlation between the state of charge and the cycle number of the lithium battery.

[0127] In step 403, based on the preliminary feature value sequence of capacity attenuation, a pre-established aging index calculation rule is combined to calculate a dynamic change sequence of the internal aging index, and a quantitative result of the aging index is obtained.

[0128] In step 404, based on the quantitative result of the aging index, an abnormality is marked, and an abnormal distribution of the aging index is determined.

[0129] In step 405, based on the abnormal distribution of the aging index and the preliminary feature value sequence of capacity attenuation, a preset health state evaluation model is used for comprehensive calculation to obtain a health state grade sequence.

[0130] By obtaining the corrected state of charge sequence from the monitoring system and the pre-stored battery cycle number data, a unified data set is integrated to obtain a preliminary processed battery state data set. According to the preliminary processed battery state data set, a support vector machine model is used to extract features, and the correlation between the state of charge and the cycle number is analyzed to determine a preliminary feature value sequence of capacity attenuation. Through the preliminary feature value sequence of capacity attenuation, a pre-established aging index calculation rule is combined to calculate a dynamic change sequence of the internal aging index, and a quantitative result of the aging index is obtained. For the quantitative result of the aging index, if the aging index exceeds the preset threshold range, an abnormality is marked, and the corresponding cycle number interval is recorded to determine the abnormal distribution of the aging index.

[0131] According to the abnormal distribution of the aging index, a preset health state evaluation model is combined with the preliminary feature value sequence of capacity attenuation to perform comprehensive calculation to obtain a battery health state grade sequence. Further, through the battery health state grade sequence, trend comparison and analysis can also be performed in combination with historical cycle number data, and if the trend deviates from the preset normal range, the battery health state grade sequence is corrected again to determine a final battery health state grade sequence. The health state evaluation model is obtained by training a training set of the state of charge data set and the charge and discharge cycle number data set.

[0132] The embodiment proposes a complete lithium battery health state evaluation process, realizes precise evaluation and abnormal detection of battery aging state through multi-source data fusion and intelligent analysis. The embodiment analyzes the evolution data of the state of charge and the cycle number, breaks through the limitation of separately viewing the two types of data, and discovers many new aging characteristics. Secondly, a dynamically configurable aging index calculation rule engine is developed, which supports flexible adjustment of evaluation strategies according to different battery chemical systems (such as NMC and LFP). And a multi-level abnormal detection system is established, which can identify sudden failures and progressive degradation at the same time.

[0133] In one embodiment, referring to Figure 7 , the method comprises:

[0134] Step 501, input the modified state of charge estimation sequence and the health state level sequence into the lithium battery, and extract the real-time state data of the lithium battery to obtain state sequence data;

[0135] Step 502, based on the state sequence data, an intelligent current control algorithm is used to obtain the state of charge and the health state of the lithium battery;

[0136] Step 503, the support vector machine algorithm is used to classify the features of the state of charge and the health state to obtain a classification feature vector;

[0137] Step 504, based on the classification feature vector, combining the preset state of charge threshold and health state threshold, an initial speed decision matrix is generated through a logistic regression model;

[0138] Step 505, if the variance of the candidate value in the initial speed decision matrix is lower than the preset threshold, the initial speed decision matrix is smoothed through a linear interpolation method to obtain the charging and discharging speed decision matrix.

[0139] The state sequence data is obtained by inputting the corrected state of charge estimation sequence and the health state level sequence into the lithium battery, extracting real-time state data from the battery management system, and obtaining the state sequence data. If the state sequence data is complete and conforms to the preset format, the state of charge and the health state of the lithium battery are estimated by the intelligent current control algorithm, and the state of charge and the health state of the lithium battery are obtained. The calculation principle of the intelligent current control algorithm is as follows: in the lithium battery management system, the intelligent current control algorithm dynamically adjusts the charging and discharging strategy by analyzing the state sequence data of the battery in real time, so as to accurately estimate the state of charge and the health state of the lithium battery, and to realize the maximum charging and discharging efficiency under the premise of ensuring the safety and life of the battery. The state sequence data can include dynamic parameters such as voltage, current, temperature, and internal resistance, for example, the state sequence data can be electrical parameters, temperature data, internal resistance data, and historical cycle data. The intelligent current control algorithm is a multi-objective optimization algorithm, which optimizes the charging time, battery damage index (life), energy efficiency and other target parameters of the battery by inputting multi-dimensional time sequence data, and predicts the optimal state of charge and health state.

[0140] Then, the support vector machine algorithm is used to classify the state of charge and the health state to obtain the classification feature vector. According to the classification feature vector, the preset state of charge threshold and the health state threshold are combined, and the candidate value of the charging and discharging speed is calculated by the logistic regression model to generate an initial speed decision matrix. If the variance of the candidate value in the initial speed decision matrix is lower than the preset threshold, the matrix is smoothed by the linear interpolation method to obtain the charging and discharging speed decision matrix.

[0141] For example, in the test of a certain type of power battery, the system automatically adjusts the charging current from 1.5A to 1.2A after identifying that the battery enters the "high state of charge- rapid aging" state, which reduces the capacity decay rate in this state by 40%, and only increases the charging time by 8%. This intelligent trade-off decision fully reflects the excellent performance of the system in multi-objective optimization, and provides an innovative solution for the safe and efficient use of lithium batteries.

[0142] This embodiment constructs a complete intelligent decision system for charging and discharging speed of lithium battery, realizes precise control and adaptive adjustment of charging and discharging strategy through multi-algorithm cooperation and dynamic optimization. Through the closed-loop linkage mechanism of state evaluation and control strategy generation, the system can continuously learn and improve from the actual control effect. Secondly, a hybrid decision architecture integrating data-driven and model-driven is developed, which has the development ability of machine learning and the interpretability of physical model. Moreover, a matrix optimization algorithm considering the dynamic response of the battery is designed, which avoids the common strategy jump problem in traditional methods.

[0143] The lithium battery charging and discharging management system based on data analysis provided by the present application is described below. The lithium battery charging and discharging management system based on data analysis described below can be referred to in correspondence with the lithium battery charging and discharging management method based on data analysis described above.

[0144] The present application also provides a lithium battery charging and discharging management system based on data analysis, comprising:

[0145] The first analysis module is configured to determine a temperature coefficient dynamic change sequence based on real-time temperature data of the lithium battery, wherein the temperature coefficient dynamic change sequence is obtained based on a temperature peak value, a temperature average value and a temperature change rate sequence of the real-time temperature data;

[0146] The second analysis module is configured to perform nonlinear compensation processing on an internal resistance original data sequence of the lithium battery based on a temperature coefficient dynamic change sequence corresponding to the internal resistance reference correction parameter table, to generate a temperature compensation internal resistance change rate sequence;

[0147] The third analysis module is configured to generate a corrected state of charge estimation sequence based on the temperature compensation internal resistance change rate sequence using an adaptive state estimation algorithm;

[0148] The fourth analysis module is configured to input the corrected state of charge estimation sequence and preset battery cycle number data into a health state evaluation model to determine a health state grade sequence of the lithium battery, wherein the health state evaluation model is obtained by training a training set of state of charge data set and charging and discharging cycle number data set;

[0149] The fifth analysis module is configured to generate a charging and discharging speed decision matrix based on the corrected state of charge estimation sequence and the health state grade sequence;

[0150] The sixth analysis module is configured to determine a charging mode required by the lithium battery based on the charging and discharging speed decision matrix;

[0151] The charging mode is used to regulate and control the charging and discharging speed of the lithium battery, and the charging mode includes a fast charging mode and a standard charging mode.

[0152] Figure 8 An example of an electronic device entity structure schematic diagram is shown as Figure 8As shown, the electronic device can include a processor 810, a communications interface 820, a memory 830, and a communications bus 840, wherein the processor 810, the communications interface 820, and the memory 830 complete mutual communication through the communications bus 840. The processor 810 can invoke a logical instruction in the memory 830 to execute the lithium battery charging and discharging management method based on data analysis.

[0153] In addition, the logical instruction in the memory 830 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0154] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the lithium battery charging and discharging management method based on data analysis provided by the above-mentioned methods.

[0155] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement it without creative labor.

[0156] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0157] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A lithium battery charge and discharge management method based on data analysis, characterized in that, Executed by a computer, including: Based on real-time temperature data of lithium batteries, a dynamic change sequence of temperature coefficient is determined, wherein the dynamic change sequence of temperature coefficient is obtained based on the temperature peak, temperature average and temperature change rate sequence of the real-time temperature data. Based on the internal resistance reference correction parameter table corresponding to the temperature coefficient dynamic change sequence, the original internal resistance data sequence of the lithium battery is subjected to nonlinear compensation processing to generate a temperature-compensated internal resistance change rate sequence. Based on the temperature-compensated internal resistance change rate sequence, an adaptive state estimation algorithm is used to generate a corrected state of charge estimation sequence. The corrected state of charge estimation sequence and the preset battery cycle count data are input into the health status assessment model to determine the health status level sequence of the lithium battery. The health status assessment model is trained based on the training set of the state of charge dataset and the charge-discharge cycle count dataset. Based on the corrected state of charge estimation sequence and the health status level sequence, a charge / discharge rate decision matrix is ​​generated; Based on the charge / discharge rate decision matrix, the required charging mode for the lithium battery is determined. The charging mode is used to regulate the charging and discharging speed of the lithium battery, and the charging mode includes a fast charging mode and a standard charging mode.

2. The lithium battery charge and discharge management method based on data analysis according to claim 1, characterized in that, Also includes: A real-time feedback control mechanism is adopted to monitor real-time current changes and temperature response data during the charging and discharging process; Based on the current change data and the temperature response data, the charging speed setpoint and discharging speed setpoint in the charging and discharging speed decision matrix are dynamically adjusted to generate an optimized control parameter sequence. Based on the optimized control parameter sequence, the operating status of the charging and discharging equipment is updated in real time, and the updated operating status data is determined. If the operating status data does not meet the preset stability conditions, a new optimized control parameter sequence is determined based on the current change data and the temperature response data. The new optimized control parameter sequence is used to update the charge / discharge speed decision matrix.

3. The lithium battery charge and discharge management method based on data analysis according to claim 2, characterized in that, Also includes: Based on the dynamic change sequence of the temperature coefficient, the change rate sequence of the temperature-compensated internal resistance, the corrected state of charge estimation sequence, and the health status level sequence, a weighted fusion algorithm is applied to determine the comprehensive evaluation index sequence of the battery status. Based on the comprehensive evaluation index sequence and the preset average performance life threshold of the lithium battery, a personalized charge and discharge management scheme sequence is generated. Based on the charge and discharge management scheme sequence, the control strategy parameters are updated, wherein the control strategy parameters include at least the charge and discharge speed decision matrix, the optimized control parameter sequence, the charging mode, the battery cycle count data, or the original internal resistance data sequence.

4. The lithium battery charge and discharge management method based on data analysis according to claim 1, characterized in that, The internal resistance reference correction parameter table based on the dynamic change sequence of the temperature coefficient is used to perform nonlinear compensation processing on the original internal resistance data sequence of the lithium battery to generate a temperature-compensated internal resistance change rate sequence, including: The original internal resistance data sequence of the lithium battery is nonlinearly compensated using the internal resistance reference correction parameter table to obtain a preliminary compensated data sequence. If the influence of temperature data in the preliminary compensation data sequence exceeds a preset threshold, a temperature compensation data sequence is generated based on the preliminary compensation data sequence and the ambient temperature data. Based on the temperature compensation data sequence, the internal resistance change rate of the lithium battery is calculated, and the internal resistance change rate sequence is determined. Key feature points are extracted from the internal resistance change rate sequence, and the support vector regression algorithm is used to predict the internal resistance change trend of the lithium battery, thus obtaining the internal resistance change trend sequence. For the internal resistance change trend sequence, the sliding window method is used to calculate the mean local change rate of the lithium battery, and a smooth internal resistance change rate sequence is obtained. Based on the smoothed internal resistance change rate sequence, a time series analysis method is used to detect and remove abnormal change points to generate the temperature-compensated internal resistance change rate sequence.

5. The lithium battery charge and discharge management method based on data analysis according to claim 1, characterized in that, The step of generating a corrected state-of-charge estimation sequence based on the temperature-compensated internal resistance change rate sequence using an adaptive state estimation algorithm includes: Acquire temperature sensor data and historical voltage and current data sequences, and based on the temperature sensor data and the historical voltage and current data sequences, use the Kalman filter algorithm to smooth the temperature-compensated internal resistance change rate sequence to obtain a smoothed internal resistance change rate sequence. By using a preset temperature compensation model, the smoothed internal resistance change rate sequence is temperature compensated to obtain a temperature-compensated internal resistance change rate sequence. Using a particle filter algorithm, combined with the temperature-compensated internal resistance change rate sequence and the voltage and current historical data sequence, the battery state of the lithium battery is obtained, and the initial state of charge sequence is obtained. If the rate of change of the initial state of charge sequence exceeds a preset threshold, the initial state of charge sequence is adjusted by an error compensation algorithm to generate a corrected state of charge estimation sequence.

6. The lithium battery charge and discharge management method based on data analysis according to claim 1, characterized in that, The step of inputting the corrected state of charge estimation sequence and preset battery cycle count data into the health status assessment model to determine the health status level sequence of the lithium battery includes: The corrected state of charge sequence and the battery cycle count data are integrated into a unified dataset to obtain a pre-processed battery state dataset. Based on the pre-processed battery state dataset, a support vector machine model is used to extract features from it to determine the preliminary feature value sequence of capacity decay, wherein the preliminary feature value sequence of capacity decay is used to characterize the correlation between the state of charge and the number of cycles of the lithium battery. Based on the preliminary characteristic value sequence of capacity decay, combined with the pre-established aging index calculation rules, the dynamic change sequence of internal aging index is calculated, and the quantitative result of aging index is obtained. Based on the quantitative results of the aging index, anomalies are marked to determine the abnormal distribution of the aging index. Based on the abnormal distribution of the aging indicators and the preliminary characteristic value sequence of the capacity decay, a health status level sequence is obtained by comprehensive calculation using a preset health status assessment model.

7. The lithium battery charge and discharge management method based on data analysis according to claim 1, characterized in that, The step of generating a charge / discharge rate decision matrix based on the corrected state of charge estimation sequence and the health state level sequence includes: The corrected state of charge estimation sequence and health status level sequence are input into the lithium battery, and the real-time state data of the lithium battery is extracted to obtain state sequence data; Based on the state sequence data, an intelligent current control algorithm is used to obtain the state of charge and health status of the lithium battery. The state of charge and the state of health are classified using the support vector machine algorithm to obtain a classification feature vector. Based on the classification feature vector, combined with the preset state of charge threshold and health state threshold, an initial velocity decision matrix is ​​generated through a logistic regression model. If the variance of the candidate values ​​in the initial velocity decision matrix is ​​lower than a preset threshold, the initial velocity decision matrix is ​​smoothed by a linear interpolation method to generate the charge / discharge velocity decision matrix.

8. A lithium battery charging and discharging management system based on data analysis, characterized in that, include: The first analysis module is used to determine the dynamic change sequence of the temperature coefficient based on the real-time temperature data of the lithium battery, wherein the dynamic change sequence of the temperature coefficient is obtained based on the temperature peak, temperature average and temperature change rate sequence of the real-time temperature data. The second analysis module is used to perform nonlinear compensation processing on the original internal resistance data sequence of the lithium battery based on the internal resistance benchmark correction parameter table corresponding to the dynamic change sequence of the temperature coefficient, and generate a temperature-compensated internal resistance change rate sequence. The third analysis module is used to generate a corrected state of charge estimation sequence based on the temperature-compensated internal resistance change rate sequence and an adaptive state estimation algorithm. The fourth analysis module is used to input the corrected state of charge estimation sequence and the preset battery cycle count data into the health status assessment model to determine the health status level sequence of the lithium battery. The health status assessment model is trained based on the training set of the state of charge dataset and the charge-discharge cycle count dataset. The fifth analysis module is used to generate a charge / discharge rate decision matrix based on the corrected state of charge estimation sequence and the health status level sequence. The sixth analysis module is used to determine the required charging mode for the lithium battery based on the charging and discharging speed decision matrix. The charging mode is used to regulate the charging and discharging speed of the lithium battery, and the charging mode includes a fast charging mode and a standard charging mode.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the lithium battery charge and discharge management method based on data analysis as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the lithium battery charge and discharge management method based on data analysis as described in any one of claims 1 to 7.

Images