Intelligent battery management system and method for charging electric vehicle

Abstract

The invention provides an intelligent battery management system and method for electric vehicle charging, and relates to the technical field of intelligent battery management, working condition parameters of a target electric vehicle battery are collected, and battery impedance multi-mode sensing is performed on the target electric vehicle battery according to the working condition parameters to obtain a multi-source heterogeneous parameter set; acquiring historical charging data, performing inferior electricity prediction on the target electric vehicle battery according to the multi-source heterogeneous parameter set and the historical charging data to obtain a battery class loss set, and determining an inferior loss response according to the battery class loss set; determining an inferior electricity index through the inferior damage response, and performing intelligent charging management on the target electric vehicle battery according to the inferior electricity index and a preset charging strategy to obtain a charging strategy; and the target electric vehicle battery is intelligently charged according to the charging strategy, and intelligent charging strategy management is completed. According to the invention, the deterioration state of the rechargeable battery of the automobile can be accurately identified, and the charging safety and efficiency are improved.

Description

Technical Field

[0001] This application relates to the field of battery intelligent management technology, and more specifically, to a battery intelligent management system and method for charging electric vehicles. Background Technology

[0002] In existing technologies, Battery Management Systems (BMS) are widely used in electric vehicles, primarily for monitoring and controlling key operating parameters such as battery voltage, current, and temperature to ensure safe battery operation. Traditional charging management methods often employ fixed threshold strategies, such as constant current-constant voltage (CC-CV) charging, or simple control based on voltage and SOC (state of charge). In recent years, with advancements in sensor technology and data processing capabilities, some research has begun to introduce impedance spectroscopy analysis, battery capacity estimation, and internal resistance measurement to obtain more comprehensive battery state information. Simultaneously, multi-source data fusion and machine learning-based battery state prediction methods are gradually being applied to battery state of health (SOH) assessment and lifetime prediction, providing support for more refined charging management. Furthermore, some technologies attempt to build charging strategy models to dynamically adjust charging process parameters according to different battery states, achieving preliminary intelligent charging control. These technologies collectively drive the evolution of battery management from rule-driven to data-driven and model-driven approaches.

[0003] Current technologies for electric vehicle battery charging management generally suffer from several drawbacks. Firstly, they rely on limited methods for battery status identification, limiting them to basic parameters such as voltage, current, or temperature. This fails to comprehensively reflect the battery's actual health level. Secondly, they lack effective mechanisms for predicting degradation trends, making it impossible to anticipate battery degradation during charging based on historical data and current conditions. Thirdly, charging strategies typically employ fixed or coarse rules, failing to adapt to individual and dynamic adjustments based on the battery's current health status. Finally, the lack of proactive intervention and control measures for potential risks during charging easily leads to safety and lifespan issues such as overcharging, thermal runaway, or accelerated aging. These problems directly limit the safety and charging efficiency of battery systems. Therefore, achieving accurate identification of automotive battery degradation status and improving charging safety and efficiency has become a significant challenge for the industry. Summary of the Invention

[0004] This application provides a battery intelligent management system and method for electric vehicle charging, which can accurately identify the deterioration state of the vehicle battery and improve charging safety and efficiency.

[0005] In a first aspect, this application provides a battery intelligent management method for charging electric vehicles, the battery intelligent management method comprising the following steps:

[0006] The operating parameters of the target electric vehicle battery during charging are collected, and the battery impedance multimodal sensing of the target electric vehicle battery is performed based on the operating parameters to obtain a multi-source heterogeneous parameter set of the target electric vehicle battery.

[0007] Historical charging data of the target electric vehicle battery is obtained. Based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, the battery degradation prediction under charging conditions is performed to obtain the battery damage set of the target electric vehicle battery during charging. Based on the battery damage set, the degradation response of the target electric vehicle battery during charging is determined.

[0008] The poor battery index of the target electric vehicle battery during the charging process is determined by the poor battery response. Based on the poor battery index and the preset charging strategy, the target electric vehicle battery is screened for a strategy to obtain a charging strategy for intelligent charging of the target electric vehicle battery.

[0009] The target electric vehicle battery is intelligently charged according to the charging strategy, thus completing the intelligent charging strategy management.

[0010] In this embodiment, collecting the operating parameters of the target electric vehicle battery during charging specifically includes:

[0011] The charging current, terminal voltage, battery temperature, and AC impedance spectrum of the target electric vehicle battery during the charging process are collected.

[0012] The charging current, the terminal voltage, the battery temperature, and the AC impedance spectrum are used as the operating parameters of the target electric vehicle battery during charging.

[0013] In this embodiment, based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, the battery degradation prediction of the target electric vehicle battery under charging conditions is performed, and the battery degradation set of the target electric vehicle battery under charging conditions specifically includes:

[0014] The degradation of the target electric vehicle battery is predicted by using the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, thereby obtaining the degradation factor for each degradation category.

[0015] The battery damage set of the target electric vehicle battery during charging is determined based on the degradation factors of each degradation category.

[0016] In this embodiment, determining the deterioration response of the target electric vehicle battery during charging based on the battery damage set specifically includes:

[0017] A damage matrix for the target electric vehicle battery is constructed based on the battery damage set and preset damage thresholds.

[0018] The target electric vehicle battery is scored based on the aforementioned defect matrix, and then each defect score is obtained.

[0019] The degradation response of the target electric vehicle battery during the charging process is determined by all degradation scores.

[0020] In this embodiment, determining the degradation index of the target electric vehicle battery during the charging process through the degradation response specifically includes:

[0021] The initial degradation profile of the target electric vehicle battery during the charging process is determined by the battery loss set of the target electric vehicle battery during charging.

[0022] The defective response is subjected to a defective correction mapping to obtain the defective correction coefficient;

[0023] The battery degradation index of the target electric vehicle battery during the charging process is determined based on the preliminary degradation score and the degradation correction coefficient.

[0024] In this embodiment, the target electric vehicle battery is intelligently charged using the poor battery index and a preset charging strategy. The intelligent charging strategy for the target electric vehicle battery is obtained by matching and mapping the poor battery index and the preset charging strategy.

[0025] In this embodiment, the charging strategy includes: a poor power index and a constant current stage current correction result.

[0026] Secondly, this application provides a battery intelligent management system for charging electric vehicles, used to execute a battery intelligent management method for charging electric vehicles, the battery intelligent management system for charging electric vehicles comprising:

[0027] The data acquisition module collects the operating parameters of the target electric vehicle battery during charging, and performs multi-modal sensing of battery impedance based on the operating parameters to obtain a multi-source heterogeneous parameter set of the target electric vehicle battery.

[0028] The degradation response module acquires historical charging data of the target electric vehicle battery, performs degradation prediction on the target electric vehicle battery under charging conditions based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, obtains the battery damage set of the target electric vehicle battery during charging, and determines the degradation response of the target electric vehicle battery during charging based on the battery damage set.

[0029] The intelligent strategy module determines the battery degradation index of the target electric vehicle battery during the charging process through the degradation response, performs strategy screening on the target electric vehicle battery based on the battery degradation index and the preset charging strategy, and then obtains a charging strategy for intelligent charging of the target electric vehicle battery.

[0030] The strategy execution module performs intelligent charging operations on the target electric vehicle battery according to the charging strategy, thereby completing the intelligent charging strategy management.

[0031] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described intelligent battery management method for charging electric vehicles.

[0032] Fourthly, this application provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned intelligent battery management method for charging electric vehicles.

[0033] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0034] The system collects operating parameters of the target electric vehicle battery during charging, performs multi-modal sensing of battery impedance based on these parameters, and obtains a multi-source heterogeneous parameter set for the target electric vehicle battery. It also acquires historical charging data of the target electric vehicle battery, performs battery degradation prediction based on the multi-source heterogeneous parameter set and the historical charging data, and obtains a battery damage set during charging. The system then determines the battery degradation response during charging based on this set. Finally, it determines the battery degradation index during charging based on the degradation response, performs strategy screening based on the index and a preset charging strategy, and obtains a smart charging strategy for the target electric vehicle battery. The system then performs smart charging operations according to the charging strategy, completing the smart charging strategy management.

[0035] Therefore, this application firstly, by combining multimodal signal processing and impedance sensing algorithms with real-time operating parameters of the target electric vehicle battery during charging, a multi-source heterogeneous parameter set containing thermal, electrical, and chemical information is constructed. This enables deep perception and comprehensive characterization of the battery state, providing more accurate and reliable data support for subsequent degradation prediction and intelligent charging strategy formulation. Secondly, by integrating the historical charging behavior of the target electric vehicle battery with current multi-source heterogeneous operating parameters, a multi-dimensional battery degradation prediction model is established. This effectively uncovers key degradation characteristics of the battery during charging, quantifies and forms a battery damage set, and further constructs the degradation... The loss response not only enhances the predictability and accuracy of battery degradation risk but also enables dynamic assessment of battery health under complex operating conditions, providing a reliable foundation for risk perception and control of subsequent intelligent charging strategies. Then, by analyzing battery loss sets, a unified battery health index is constructed, and this index is matched and mapped with a preset charging strategy library to obtain charging strategies. Finally, by applying the matched charging strategies to the actual charging process, the charging current is dynamically controlled, achieving closed-loop intelligent control throughout the entire process. Key parameters are continuously adjusted and protected according to the strategy settings, effectively avoiding risks such as overcharging and excessive temperature rise, thus improving charging safety and energy efficiency.

[0036] In summary, the technical solution adopted in this application can accurately identify the deterioration state of automotive rechargeable batteries, thereby improving charging safety and efficiency. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is an exemplary flowchart of a battery intelligent management method for charging electric vehicles provided in this application;

[0039] Figure 2 This is an exemplary flowchart of obtaining the battery class loss set of the target electric vehicle battery during charging, according to the present application.

[0040] Figure 3 This is an exemplary flowchart for determining the degraded battery index of a target electric vehicle battery during the charging process, based on the information provided in this application.

[0041] Figure 4This is a module structure diagram of a battery intelligent management system for electric vehicle charging provided in this application;

[0042] Figure 5 This is a schematic diagram of the structure of a computer device for implementing a battery intelligent management method for charging electric vehicles, according to the present application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] This application provides a battery intelligent management system and method for electric vehicle charging. The core of the system involves collecting operating parameters of the target electric vehicle battery during charging; performing multi-modal sensing of battery impedance based on these parameters to obtain a multi-source heterogeneous parameter set for the target electric vehicle battery; acquiring historical charging data of the target electric vehicle battery; predicting battery degradation under charging conditions based on the multi-source heterogeneous parameter set and the historical charging data to obtain a battery damage set during charging; determining the battery degradation response during charging based on the battery damage set; determining the battery degradation index during charging based on the degradation response; selecting a strategy for intelligent charging of the target electric vehicle battery based on the degradation index and a preset charging strategy; and performing intelligent charging operations on the target electric vehicle battery according to the charging strategy to complete intelligent charging strategy management. This solution enables accurate identification of the battery degradation state, improving charging safety and efficiency.

[0045] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown in the figure, this is an exemplary flowchart of a battery intelligent management method for charging an electric vehicle according to this embodiment of the present application. The battery intelligent management method includes the following steps:

[0046] In step S1, the operating parameters of the target electric vehicle battery during charging are collected, and the battery impedance multimodal sensing of the target electric vehicle battery is performed based on the operating parameters to obtain the multi-source heterogeneous parameter set of the target electric vehicle battery.

[0047] In this embodiment, collecting the operating parameters of the target electric vehicle battery during charging specifically includes:

[0048] The charging current, terminal voltage, battery temperature, and AC impedance spectrum of the target electric vehicle battery during the charging process are collected.

[0049] The charging current, the terminal voltage, the battery temperature, and the AC impedance spectrum are used as the operating parameters of the target electric vehicle battery during charging.

[0050] In practical implementation, firstly, the charging current, terminal voltage, battery temperature, and AC impedance spectrum of the target electric vehicle battery during the charging process can be collected. Specifically, the charging current of the target electric vehicle battery can be collected using a precision Hall current sensor, the terminal voltage of the target electric vehicle battery can be obtained using an analog-to-digital converter interface, the temperature of the target electric vehicle battery casing can be measured using a surface-mount thermistor, and an AC impedance testing module (such as an EIS measurement unit) can be used to apply a small-amplitude sinusoidal excitation signal and measure the response during the charging interval or constant voltage stage to extract the AC impedance spectrum. Then, the charging current, the terminal voltage, the battery temperature, and the AC impedance spectrum can be used as the operating parameters of the target electric vehicle battery during charging.

[0051] In this embodiment, the battery impedance of the target electric vehicle battery is sensed in a multi-modal manner based on the operating parameters to obtain a multi-source heterogeneous parameter set of the target electric vehicle battery. Specifically, impedance response data can be obtained from the AC impedance spectrum in the operating parameters, a Nyquist curve can be fitted, and impedance spectrum features can be extracted, such as the current internal resistance and current reactance of the target electric vehicle battery. Then, the time-domain signal of the target electric vehicle battery can be extracted, such as the average voltage during the constant current stage and the current temperature curve of the target electric vehicle battery. Finally, the current internal resistance, current reactance, average voltage during the current constant current stage, and temperature rise rate of the target electric vehicle battery can be used as set elements to organize a state parameter set, thereby using this state parameter set as the multi-source heterogeneous parameter set of the target electric vehicle battery.

[0052] It should be noted that by collecting key operating parameters such as current, voltage, temperature and AC impedance in real time during the charging process of the target electric vehicle battery, and combining multimodal signal processing and impedance sensing algorithms, a multi-source heterogeneous parameter set containing thermal, electrical and chemical information is constructed. This enables a deep perception and comprehensive characterization of the battery state, providing more accurate and reliable data support for subsequent degradation prediction and intelligent charging strategy formulation.

[0053] In step S2, historical charging data of the target electric vehicle battery is obtained. Based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, the battery degradation prediction under charging conditions is performed to obtain the battery damage set of the target electric vehicle battery during charging. Based on the battery damage set, the degradation response of the target electric vehicle battery during charging is determined.

[0054] In practice, the historical charging data of the target electric vehicle battery can be obtained through the battery management system. The historical charging information of the target electric vehicle battery is used as the historical charging data of the target electric vehicle battery. The historical charging data includes: initial battery capacity, initial battery internal resistance, initial battery reactance, average voltage during the historical constant current stage, and battery capacity during the last charge.

[0055] Preferably, in this embodiment, reference Figure 2 As shown, this figure is an exemplary flowchart of obtaining the battery class loss set of the target electric vehicle battery during charging in an embodiment of this application. In this embodiment, the battery class loss set of the target electric vehicle battery during charging is obtained by predicting the battery's poor performance based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data. This can be achieved through the following steps:

[0056] In step S21, the degradation of the target electric vehicle battery is predicted by using the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, thereby obtaining the degradation factor for each degradation category.

[0057] In step S22, the battery damage set of the target electric vehicle battery during charging is determined based on the degradation factor of each degradation category.

[0058] In specific implementation, firstly, the degradation of the target electric vehicle battery is predicted using the multi-source heterogeneous parameter set and the historical charging data, thereby obtaining the degradation factors for each degradation category. Specifically, the capacity decay index can be obtained by subtracting the current battery capacity from the initial battery capacity and dividing the result by the initial battery capacity. Similarly, the internal resistance growth factor can be obtained by subtracting the initial internal resistance from the current internal resistance and dividing the result by the initial internal resistance. The temperature rise rate of the current target electric vehicle battery can be used as the temperature rise rate coefficient. Finally, the initial voltage plateau can be selected by taking the historical average voltage during the constant current phase and the current average voltage during the constant current phase as the current voltage plateau; the difference between the current voltage plateau and the initial voltage plateau can be subtracted from the current voltage plateau and divided by the initial voltage plateau. The initial internal resistance and initial reactance of the target electric vehicle battery at the time of manufacture can be extracted, squared, summed, and the square root of the sum can be used as the initial impedance magnitude of the target electric vehicle battery. Then, the current impedance magnitude is obtained based on the current internal resistance and current reactance of the target electric vehicle battery. The initial impedance magnitude is then subtracted from the current impedance magnitude, and the result is divided by the initial impedance magnitude to obtain the impedance spectrum change factor. The capacity decay index of the target electric vehicle battery is used as the degradation factor for the capacity decay category, the internal resistance growth factor as the degradation factor for the internal resistance growth category, the temperature rise rate coefficient as the degradation factor for the temperature category, the voltage plateau offset factor as the degradation factor for the voltage offset category, and the impedance spectrum change factor as the degradation factor for the impedance category, thus obtaining the degradation factors for each degradation category.

[0059] It should be noted that the capacity decay index is an index describing the effective capacity decay of the target electric vehicle battery during use; the internal resistance growth factor is an index describing the increase in the internal resistance of the battery with the increase of the usage period during charging and discharging; the temperature rise rate coefficient is a coefficient reflecting the rate at which energy loss inside the battery is converted into heat energy; the voltage plateau shift factor is an index measuring the degree of displacement of the stable voltage range of the battery during charging and discharging; and the impedance spectrum change factor is an index measuring the degree of change between the impedance spectrum of the target electric vehicle battery in a specified frequency range and its impedance spectrum under reference conditions.

[0060] In addition, in specific implementation, the battery class loss set of the target electric vehicle battery during charging is determined based on the degradation factors of each degradation category. That is, the degradation factors of each degradation category can be normalized respectively, and the results of the normalization process can be used as set elements and merged into the battery class loss set of the target electric vehicle battery during charging.

[0061] In this embodiment, determining the poor performance response of the target electric vehicle battery during charging based on the battery damage set can be achieved through the following steps:

[0062] A damage matrix for the target electric vehicle battery is constructed based on the battery damage set and preset damage thresholds.

[0063] The target electric vehicle battery is scored based on the aforementioned defect matrix, and then each defect score is obtained.

[0064] The degradation response of the target electric vehicle battery during the charging process is determined by all degradation scores.

[0065] In specific implementation, firstly, a degradation matrix of the target electric vehicle battery can be constructed based on the battery degradation set and preset degradation thresholds. Specifically, the degradation thresholds can be preset based on experimental data analysis, and each degradation factor in the battery degradation set can be subtracted from its corresponding degradation threshold. The result is used as a matrix element of the degradation matrix of the target electric vehicle battery. A result less than 0 is recorded as 0, indicating that the degradation factor is in a normal state. All matrix elements are then combined into a one-dimensional matrix, which is used as the degradation matrix of the target electric vehicle battery. Next, the degradation of the target electric vehicle battery can be scored based on the degradation matrix, thus obtaining various degradation scores. Specifically, the degradation scores for each degradation category can be preset based on expert experience. Weights are assigned to the matrix elements, which are then multiplied by their respective degradation weights. The results are used as degradation scores for the target electric vehicle battery, and the output results are as follows: {capacity decay score, internal resistance growth score, temperature rise rate score, voltage plateau shift score, impedance spectrum change score}. It should be noted that the degradation score refers to the degree of influence of the degradation category on the target electric vehicle battery. Finally, the degradation response of the target electric vehicle battery during the charging process can be determined by all degradation scores. That is, degradation scores with a value of 0 can be removed, and all remaining non-zero degradation scores can be combined into a data set. The resulting data set is used as the degradation response of the target electric vehicle battery. It should be noted that the degradation response refers to the set of all degradation scores that pose a degradation risk to the target electric vehicle battery.

[0066] It should be noted that by integrating the historical charging behavior of the target electric vehicle battery with the current multi-source heterogeneous operating parameters, a multi-dimensional battery degradation prediction model can be established. This model can effectively uncover key degradation characteristics of the battery during the charging process, quantify multiple battery damage sets including capacity decay, internal resistance growth, voltage plateau shift, and abnormal temperature rise rate, and further construct a battery degradation response evaluation matrix. This not only enhances the predictability and accuracy of battery degradation risk but also enables dynamic assessment of battery health status under complex operating conditions, providing a reliable foundation for risk perception and control of subsequent intelligent charging strategies.

[0067] In step S3, the battery degradation index of the target electric vehicle battery during the charging process is determined by the degradation response. Based on the battery degradation index and the preset charging strategy, the target electric vehicle battery is selected for strategy screening, thereby obtaining a charging strategy for intelligent charging of the target electric vehicle battery.

[0068] Preferably, in this embodiment, reference Figure 3 As shown, this figure is an exemplary flowchart for determining the degradation index of a target electric vehicle battery during the charging process in an embodiment of this application. The determination of the degradation index of the target electric vehicle battery during the charging process through the degradation response in this embodiment can be achieved using the following steps:

[0069] In step S31, the initial degradation of the target electric vehicle battery during the charging process is determined by the battery damage set of the target electric vehicle battery during charging.

[0070] In step S32, the defective response is subjected to defective correction mapping to obtain defective correction coefficients;

[0071] In step S33, the battery degradation index of the target electric vehicle battery during the charging process is determined based on the preliminary degradation score and the degradation correction coefficient.

[0072] In specific implementation, firstly, the initial degradation score of the target electric vehicle battery during charging can be determined by the battery damage set during charging. That is, corresponding degradation factors can be selected from the battery damage set of the target electric vehicle battery based on the degradation score in the degradation response. Each selected degradation factor is then normalized, and each normalized degradation factor is multiplied by its corresponding degradation weight and summed. The sum is used as the initial degradation score of the target electric vehicle battery during charging. It should be noted that the initial degradation score refers to a preliminary degradation rating of the target electric vehicle battery. Next, the degradation response can be modified by a degradation correction mapping to obtain degradation correction coefficients. That is, the degradation scores in the degradation response can be summed, and the result can be calculated using an exponential correction function. The result is used as the degradation correction coefficient, where the exponential correction function can be expressed by the following formula:

[0073]

[0074] in, Indicates the damage correction factor; This represents the summation of various degradation scores. The degradation correction coefficient is a nonlinear dynamic adjustment factor introduced based on the initial degradation score to improve the robustness of the evaluation results to nonlinear degradation trends. Finally, the degradation index of the target electric vehicle battery during the charging process can be determined based on the initial degradation score and the degradation correction coefficient. That is, the initial degradation score can be multiplied by the degradation correction coefficient, and the result can be multiplied by 100 to obtain the degradation index of the target electric vehicle battery during the charging process. The degradation index is an index that reflects the degree of performance degradation risk that the battery may experience during the current charging process.

[0075] In this embodiment, intelligent charging management of the target electric vehicle battery is achieved through the battery degradation index and a preset charging strategy. The intelligent charging strategy for the target electric vehicle battery is obtained by matching and mapping the battery degradation index and the preset charging strategy. In specific implementation, the battery degradation index can be matched with the preset charging strategy. For example: battery degradation index 0-20, normal charging; battery degradation index 21-40, constant current stage current limit reduced by 20%; battery degradation index 41-60, constant current stage current limit reduced by 50%; battery degradation index 61-80, constant current stage current limit reduced by 70%; battery degradation index 81-100, fast charging prohibited, trickle charging only with a prompt. Based on the matching result, the battery degradation index is converted into a corresponding charging strategy, thus obtaining the intelligent charging strategy for the target electric vehicle battery. The charging strategy includes the battery degradation index and the constant current stage current correction result.

[0076] It should be noted that by analyzing the battery damage set, a unified index for measuring battery health is constructed. This index is then dynamically matched and mapped with a preset charging strategy library to form an adaptive intelligent charging strategy for different health levels. This achieves risk perception, decision optimization, and control linkage during the charging process, and can accurately adjust the charging current parameters. This effectively suppresses the spread of battery degradation, reduces the risk of thermal runaway and overcharging, and improves charging efficiency and system response capabilities.

[0077] In step S4, the target electric vehicle battery is intelligently charged according to the charging strategy to complete the intelligent charging strategy management.

[0078] In specific implementation, intelligent charging operations are performed on the target electric vehicle battery according to the charging strategy to complete intelligent charging strategy management. Specifically, the charging strategy can be converted into charging settings, such as: for a battery index of 0~20, normal charging is converted into setting the current to full output; for a battery index of 21~40, the upper limit of the constant current stage is reduced by 20%, which is converted into setting the current to full output current multiplied by 0.8; for a battery index of 41~60, the upper limit of the constant current stage is reduced by 50%, which is converted into setting the current to full output current multiplied by 0.5; for a battery index of 61~80, the upper limit of the constant current stage is reduced by 70%, which is converted into setting the current to full output current multiplied by 0.3; for a battery index of 81~100, fast charging is prohibited, only trickle charging is used and a prompt is issued, which is converted into setting the current to trickle output and issuing a prompt sound, thereby completing intelligent charging strategy management.

[0079] It should be noted that by applying the matched charging strategy parameter set to the actual charging process, the charging current is dynamically controlled to achieve closed-loop intelligent regulation throughout the entire process. The system monitors the battery response status in real time during the charging process and continuously adjusts and protects key parameters according to the strategy settings, effectively avoiding risks such as overcharging and excessive temperature rise, and improving the safety and energy efficiency of charging.

[0080] Therefore, this application firstly, by combining multimodal signal processing and impedance sensing algorithms with real-time operating parameters of the target electric vehicle battery during charging, a multi-source heterogeneous parameter set containing thermal, electrical, and chemical information is constructed. This enables deep perception and comprehensive characterization of the battery state, providing more accurate and reliable data support for subsequent degradation prediction and intelligent charging strategy formulation. Secondly, by integrating the historical charging behavior of the target electric vehicle battery with current multi-source heterogeneous operating parameters, a multi-dimensional battery degradation prediction model is established. This effectively uncovers key degradation characteristics of the battery during charging, quantifies and forms a battery damage set, and further constructs the degradation... The loss response not only enhances the predictability and accuracy of battery degradation risk but also enables dynamic assessment of battery health under complex operating conditions, providing a reliable foundation for risk perception and control of subsequent intelligent charging strategies. Then, by analyzing battery loss sets, a unified battery health index is constructed, and this index is matched and mapped with a preset charging strategy library to obtain charging strategies. Finally, by applying the matched charging strategies to the actual charging process, the charging current is dynamically controlled, achieving closed-loop intelligent control throughout the entire process. Key parameters are continuously adjusted and protected according to the strategy settings, effectively avoiding risks such as overcharging and excessive temperature rise, thus improving charging safety and energy efficiency.

[0081] In summary, the technical solution adopted in this application can accurately identify the deterioration state of automotive rechargeable batteries, thereby improving charging safety and efficiency.

[0082] Example 2: This application provides a reference for a battery intelligent management system for electric vehicle charging. Figure 4 As shown, this figure is a module structure diagram of the battery intelligent management method according to this embodiment of the present application. The battery intelligent management method includes:

[0083] The data acquisition module 100 acquires the operating parameters of the target electric vehicle battery during charging, and performs multi-modal sensing of battery impedance based on the operating parameters to obtain a multi-source heterogeneous parameter set of the target electric vehicle battery.

[0084] The degradation response module 200 acquires historical charging data of the target electric vehicle battery, performs degradation prediction on the target electric vehicle battery under charging conditions based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, obtains the battery damage set of the target electric vehicle battery during charging, and determines the degradation response of the target electric vehicle battery during charging based on the battery damage set.

[0085] The intelligent strategy module 300 determines the battery degradation index of the target electric vehicle battery during the charging process through the degradation response, performs strategy screening on the target electric vehicle battery according to the battery degradation index and the preset charging strategy, and then obtains a charging strategy for intelligent charging of the target electric vehicle battery.

[0086] The strategy execution module 400 performs intelligent charging operations on the target electric vehicle battery according to the charging strategy, thereby completing intelligent charging strategy management.

[0087] The foregoing has detailed an example of a battery intelligent management system and method for charging electric vehicles provided in the embodiments of this application. It is understood that the corresponding apparatus, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0088] In embodiment three, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described intelligent battery management method for electric vehicle charging.

[0089] In this embodiment, reference Figure 5 The dashed lines in the figure indicate that the unit or module is optional. This figure is a schematic diagram of the structure of a computer device for a battery intelligent management system for electric vehicle charging according to an embodiment of this application. The above-described battery intelligent management method for electric vehicle charging in the above embodiment can be... Figure 5 The computer device shown is used to implement this, and the computer device includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device may be a terminal device, a server or a chip.

[0090] Processor 501 can be a general-purpose processor or a special-purpose processor. For example, processor 501 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 505 to realize signal input (reception) and output (transmission).

[0091] For example, the computer device may be a chip, and the communication unit 505 may be the input and / or output circuit of the chip, or the communication unit 505 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0092] For example, the computer device may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0093] The computer device may include one or more memories 502 storing a program 504. The program 504 can be executed by a processor 501 to generate instructions 503, causing the processor 501 to perform the methods described in the above method embodiments according to the instructions 503. Optionally, the memory 502 may also store data (such as a target audit model). Optionally, the processor 501 may also read data stored in the memory 502, which may be stored at the same storage address as the program 504, or the data may be stored at a different storage address than the program 504.

[0094] The processor 501 and memory 502 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0095] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in processor 501. Processor 501 can be a central processing unit, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other programmable logic device, such as discrete gate, transistor logic device, or discrete hardware component.

[0096] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] In embodiment four, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described intelligent battery management method for electric vehicle charging.

[0098] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0099] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A battery intelligent management method for electric vehicle charging, characterized in that, The management method includes the following steps: The operating parameters of the target electric vehicle battery during charging are collected, and the battery impedance multimodal sensing of the target electric vehicle battery is performed based on the operating parameters to obtain a multi-source heterogeneous parameter set of the target electric vehicle battery. Historical charging data of the target electric vehicle battery is obtained. Based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, the battery degradation prediction under charging conditions is performed to obtain the battery damage set of the target electric vehicle battery during charging. Based on the battery damage set, the degradation response of the target electric vehicle battery during charging is determined. The poor battery index of the target electric vehicle battery during the charging process is determined by the poor battery response. Based on the poor battery index and the preset charging strategy, the target electric vehicle battery is screened for a strategy to obtain a charging strategy for intelligent charging of the target electric vehicle battery. The target electric vehicle battery is intelligently charged according to the charging strategy, thus completing the intelligent charging strategy management.

2. The intelligent battery management method for electric vehicle charging as described in claim 1, characterized in that, The specific operating parameters of the target electric vehicle battery during charging include: The charging current, terminal voltage, battery temperature, and AC impedance spectrum of the target electric vehicle battery during the charging process are collected. The charging current, the terminal voltage, the battery temperature, and the AC impedance spectrum are used as the operating parameters of the target electric vehicle battery during charging.

3. The intelligent battery management method for electric vehicle charging as described in claim 1, characterized in that, Based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, the battery degradation prediction under charging conditions is performed on the target electric vehicle battery, resulting in a battery degradation set specifically including: The degradation of the target electric vehicle battery is predicted by using the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, thereby obtaining the degradation factor for each degradation category. The battery damage set of the target electric vehicle battery during charging is determined based on the degradation factors of each degradation category.

4. The intelligent battery management method for electric vehicle charging as described in claim 1, characterized in that, Determining the degraded response of the target electric vehicle battery during charging based on the aforementioned battery damage set specifically includes: A damage matrix for the target electric vehicle battery is constructed based on the battery damage set and preset damage thresholds. The target electric vehicle battery is scored based on the aforementioned defect matrix, and then each defect score is obtained. The degradation response of the target electric vehicle battery during the charging process is determined by all degradation scores.

5. The intelligent battery management method for electric vehicle charging as described in claim 1, characterized in that, The determination of the battery degradation index of the target electric vehicle battery during the charging process through the degradation response specifically includes: The initial degradation of the target electric vehicle battery during the charging process is determined by the battery damage set of the target electric vehicle battery. The defective response is subjected to a defective correction mapping to obtain defective correction coefficients; The battery degradation index of the target electric vehicle battery during the charging process is determined based on the preliminary degradation score and the degradation correction coefficient.

6. The intelligent battery management method for electric vehicle charging as described in claim 1, characterized in that, The strategy screening of the target electric vehicle battery by matching and mapping the battery deterioration index and the preset charging strategy is to obtain a charging strategy for intelligent charging of the target electric vehicle battery.

7. The intelligent battery management method for electric vehicle charging as described in claim 1, characterized in that, The charging strategy includes: correction operations for the poor power index and the constant current stage current.

8. A battery intelligent management system for charging electric vehicles, used to execute a battery intelligent management method for charging electric vehicles as described in any one of claims 1 to 7, characterized in that, The battery intelligent management system for charging electric vehicles includes: The data acquisition module collects the operating parameters of the target electric vehicle battery during charging, and performs multi-modal sensing of battery impedance based on the operating parameters to obtain a multi-source heterogeneous parameter set of the target electric vehicle battery. The degradation response module acquires historical charging data of the target electric vehicle battery, performs degradation prediction on the target electric vehicle battery under charging conditions based on the multi-source heterogeneous parameter set of the target electric vehicle battery and the historical charging data, obtains the battery damage set of the target electric vehicle battery during charging, and determines the degradation response of the target electric vehicle battery during charging based on the battery damage set. The intelligent strategy module determines the battery degradation index of the target electric vehicle battery during the charging process through the degradation response, performs strategy screening on the target electric vehicle battery based on the battery degradation index and the preset charging strategy, and then obtains a charging strategy for intelligent charging of the target electric vehicle battery. The strategy execution module performs intelligent charging operations on the target electric vehicle battery according to the charging strategy, thereby completing the intelligent charging strategy management.

9. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that the computer device performs a battery intelligent management method for charging an electric vehicle according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement a battery intelligent management method for charging an electric vehicle as described in any one of claims 1 to 7.

Images