New energy battery intelligent maintenance method based on charging pile and medium

Abstract

The invention relates to the field of new energy battery management, in particular to a new energy battery intelligent maintenance method based on a charging pile and a medium. The method comprises the steps of obtaining data of a battery through a charging pile; uploading the data to a cloud database, and matching an optimal charging parameter interval of the batteries of the same model under historical working conditions; based on a matching result, extracting voltage-current curve morphological characteristics, analyzing relevance among long sequence parameters, and generating an optimal target current value considering both the charging efficiency and the battery health; and when the voltage deviation of the battery exceeds a dynamic equalization threshold value, performing dynamic equalization charging control through a charging pile communication interface according to the optimal target current value. The core contradiction that the charging speed and the service life of the battery cannot be collaboratively optimized in the prior art is effectively solved, each time of charging can adapt to the current battery state and respond to the voltage deviation in time, the aging trend can be prevented based on historical health data, and finally the service life of the battery is remarkably prolonged while the charging efficiency is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of new energy battery management, and in particular to a method and medium for intelligent maintenance of new energy batteries based on charging piles. Background Art

[0002] With the increasing popularity of new energy vehicles, the performance degradation of power batteries, as core components, has become increasingly prominent. Batteries inevitably experience capacity decay and increased internal resistance during the charge and discharge cycle. This process is significantly affected by charging strategies—particularly the high current surge and temperature rise effects of fast charging, which accelerate the aging of electrode materials. Currently, the industry generally relies on onboard battery management systems (BMS) for charge and discharge control. However, the local computing power of BMSs is limited, and they can only implement simple balancing strategies based on basic parameters such as battery cell voltage and temperature.

[0003] A few existing solutions attempt to optimize charging strategies through cloud-based platforms, but these approaches suffer from fundamental limitations: First, they rely on battery test data from laboratory environments and fail to integrate multi-dimensional operating condition data from real-world vehicle operations (such as dynamic current fluctuations and ambient temperature transients). Second, they lack the ability to deeply mine real-time data collected from charging piles, effectively generating only static charging curves and failing to dynamically modify control instructions during the charging process. The most fundamental flaw lies in the inability of existing technologies to integrate and analyze the multi-source heterogeneous data—such as real-time current, voltage, and temperature—available from charging piles with the historical battery degradation characteristics to achieve dynamic, balanced control that balances immediate charging efficiency with long-term health maintenance. This results in the charging process either sacrificing speed for battery life or accelerating battery aging in pursuit of speed, a persistent struggle to strike a balance between these two. Summary of the Invention

[0004] In order to solve the problem that the existing technology cannot link the real-time current, voltage, temperature and other multi-source heterogeneous data obtained by the charging pile with the historical battery attenuation characteristics for analysis, the present application provides a new energy battery intelligent maintenance method and medium based on the charging pile. The method provided in the present application includes the following steps: When charging new energy batteries, the real-time charging current, power, voltage, external ambient temperature and internal core temperature data of the battery are obtained through the charging pile; Uploading the data to a cloud database to match the optimal charging parameter range for batteries of the same model under historical operating conditions, using a multi-dimensional parameter matching matrix constructed by combining historical battery operating data and aging test results; Based on the matching results, the voltage-current curve morphology characteristics are extracted and the correlation between long sequence parameters is analyzed to generate the optimal target current value that takes into account both charging efficiency and battery health. When the voltage deviation of the battery exceeds a dynamic balancing threshold, dynamic balancing charging control is performed through the charging pile communication interface according to the optimal target current value.

[0005] Specifically, the multi-dimensional parameter matching matrix constructed by combining the battery historical operation data and aging test results includes: Based on the battery's charge and discharge cycle number, capacity attenuation rate, and internal resistance change data, a two-dimensional parameter plane is constructed with current as the horizontal axis and voltage as the vertical axis. In the two-dimensional parameter plane, the temperature dimension is superimposed to form a three-dimensional parameter space; Based on the battery aging test results, the safety boundary surfaces under different SOH health states are marked in the three-dimensional parameter space; The optimal charging parameter interval is located in the overlapping area between the safety boundary surface and the maximum charging efficiency isosurface.

[0006] Specifically, the method for generating an optimal target current value that takes into account both charging efficiency and battery health includes: A convolutional neural network is used to extract the local impulse response slope of the voltage-current curve and the voltage platform fluctuation variance during the constant current phase. The self-attention mechanism of the Transformer model is used to establish long-sequence parameter associations. The long-sequence parameter associations include the cross-influence weight of the ambient temperature sequence and the SOC change rate, and the constraint coefficient of the historical capacity decay trend on the current maximum allowable current. The outputs of the convolutional neural network and the Transformer model are integrated to solve the optimal current value through the objective function, which is: in, or For charging efficiency, ΔT is the temperature rise, SOH For health status, α 、 β 、 c is the weighting coefficient, and α + β + c =1; The objective function is optimized under constraints using a gradient descent method, wherein the constraints include voltage constraints, temperature constraints, and SOH health state constraints.

[0007] Specifically, the method further includes, when performing the dynamic balanced charging control, adjusting a dynamic balanced threshold according to the SOC state of charge, wherein the dynamic balanced threshold adjustment includes: When the SOC state of charge is less than 20%, the balancing threshold is relaxed to ±5%; When 20%≤the SOC≤95%, the balancing threshold is limited to ±2%; When the SOC state of charge is greater than 95%, the balancing threshold is limited to less than 1%.

[0008] Specifically, the method further includes, when performing the dynamic balanced charging control, correcting the optimal target current value, wherein the correction includes: For batteries whose SOH health status is lower than the health threshold, reduce their balancing current and satisfy the formula: , in, I bal represents the adjusted target current value, k is the proportional coefficient used to prevent overcharging, | I opt −I real ∣ represents the absolute deviation between the target current and the actual current, and the target current is the optimal target current value. SOH i is the battery's SOH state of health value.

[0009] Specifically, the method further includes: After executing dynamic balanced charging control, real-time battery response data is collected; Calculate actual charging efficiency or actual and prediction efficiency or pred Deviation Δ or ; When Δ or >Δ or max When the voltage-current curve characteristics are re-extracted, the historical data in the parameter matching matrix is ​​updated, and the optimal target current value is regenerated to establish the feedback coefficient , used to correct the target current value in the next control cycle, where the upper limit of the charging efficiency deviation allowed by the preset system.

[0010] In addition to the above content, the present application also includes a computer-readable storage medium, which stores a computer program. The computer program can be executed by at least one processor to implement the method described in the above content.

[0011] This application has the following technical effects: The present invention collects battery operation data in real time through the charging pile and uploads it to the cloud, intelligently integrates historical operating conditions and aging characteristics to generate the optimal charging strategy, and dynamically adjusts the balancing current during the charging process, effectively solving the core contradiction of the existing technology that cannot coordinately optimize the charging speed and battery life. Each charge can adapt to the current battery status and respond to voltage deviations in a timely manner, and can preventively suppress aging trends based on historical health data, ultimately significantly extending the battery life while ensuring charging efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] By reading the detailed description below with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding numbers represent the same or corresponding parts.

[0013] Figure 1 This is a flow chart of an intelligent maintenance method for new energy batteries based on charging piles in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0015] To address the issue of battery degradation, real-time testing is required during battery charging, particularly for the SOC (State of Charge) and SOH (State of Health). Conventional battery SOC and SOH testing typically requires obtaining the required data in a laboratory through the vehicle's BMS system. However, this embodiment, based on a data acquisition layer integrated into the charging pile, directly obtains a high-precision raw data stream through sensors and their communication modules during the charging process, with a sampling frequency of up to 1,000 times per second. This data serves as the data foundation for the battery's "digital twin."

[0016] In this embodiment, the acquired data includes: real-time charging current, power, voltage, external ambient temperature and internal core temperature, such as Figure 1 As shown, the steps of the new energy battery intelligent maintenance method based on these data include: Uploading the data to a cloud database to match the optimal charging parameter range for batteries of the same model under historical operating conditions, using a multi-dimensional parameter matching matrix constructed by combining historical battery operating data and aging test results; Based on the matching results, the voltage-current curve morphology characteristics are extracted and the correlation between long sequence parameters is analyzed to generate the optimal target current value that takes into account both charging efficiency and battery health. When the voltage deviation of the battery exceeds a dynamic balancing threshold, dynamic balancing charging control is performed through the charging pile communication interface according to the optimal target current value.

[0017] In this embodiment, a multidimensional parameter matching matrix uses the number of charge and discharge cycles, capacity decay rate, and internal resistance change data from 100,000 sets of historical charge and discharge cycle data to construct a two-dimensional parameter plane with current as the horizontal axis and voltage as the vertical axis. The temperature dimension is then superimposed to form a three-dimensional parameter space. For example, the safety boundary surface of a ternary lithium battery after 500 cycles at 25°C shows that a charge current exceeding 120A will trigger lithium plating risk. The current lower limit corresponding to the maximum charge efficiency isosurface (η>95%) is 80A. The overlapping area of ​​these two constitutes the optimal current range [80A, 120A] for this operating condition.

[0018] After the matching is completed, the system extracts the morphological characteristics of the voltage-current curve of the current charging process. In this embodiment, instead of using the simple slope calculation of the traditional BMS, a convolutional neural network is used to extract the local pulse response slope of the voltage-current curve and the voltage platform fluctuation variance during the constant current phase. The self-attention mechanism of the Transformer model is used to establish long-sequence parameter associations. The long-sequence parameter associations include the cross-influence weight of the ambient temperature sequence and the SOC change rate, and the constraint coefficient of the historical capacity decay trend on the current maximum allowable current. The outputs of the convolutional neural network and the Transformer model are integrated to solve the optimal current value through the objective function, which is: in, or For charging efficiency, ΔT is the temperature rise, SOH For health status, α 、 β 、 c is the weighting coefficient, and α + β + c =1; The objective function is optimized under constraints using a gradient descent method, wherein the constraints include voltage constraints, temperature constraints, and SOH health state constraints.

[0019] When the system detects that the voltage deviation of a single cell in the battery pack exceeds the dynamic balancing threshold, the core control action of claim 1 is immediately triggered. During the control process, the threshold is dynamically adjusted based on the SOC state of charge. When the SOC state of charge is <20%, it is in the deep discharge stage and the balancing threshold is relaxed to ±5% to avoid excessive balancing under low power conditions causing charging interruption; when 20% ≤ the SOC state of charge ≤ 95%, the balancing threshold is limited to ±2%; when the SOC state of charge is >95%, the balancing threshold is limited to <1%.

[0020] When performing the dynamic balanced charging control, the optimal target current value needs to be corrected, and the correction includes: For batteries whose SOH health status is lower than the health threshold, reduce their balancing current and satisfy the formula: , in, I bal represents the adjusted target current value, k is the proportional coefficient used to prevent overcharging, | I opt −I real ∣ represents the absolute deviation between the target current and the actual current, and the target current is the optimal target current value. SOH i is the battery's SOH state of health value.

[0021] After executing dynamic balancing control, the system starts a multi-source data fusion verification mechanism to collect battery response data in real time; Calculate actual charging efficiency or actual and prediction efficiency or pred Deviation Δ or ; When Δ or >Δ or max When the voltage-current curve characteristics are re-extracted, the historical data in the parameter matching matrix is ​​updated, and the optimal target current value is regenerated to establish the feedback coefficient , used to correct the target current value in the next control cycle, where the upper limit of the charging efficiency deviation allowed by the preset system.

[0022] By continuously collecting battery data from different regions, vehicle models, and years of use, a closed-loop control system was established, encompassing data collection, feature extraction, decision optimization, and execution feedback. After 200 consecutive fast-charging cycles, the battery capacity retention rate using this solution was significantly improved compared to traditional BMS management solutions, while charging time was significantly shortened, effectively resolving the conflict between battery health and charging efficiency in fast-charging scenarios.

[0023] In addition to the above, the system of this embodiment also has an application layer, which converts the SOC state of charge and SOH state of health into reports and dynamic curves for output. The SOH state of health can also serve as a guide for determining whether the battery needs repair. The SOH threshold for repair varies depending on the battery type. For example, the threshold for lithium-ion batteries is SOH ≤ 80% of rated capacity; the threshold for lead-acid batteries is SOH ≤ 50% of rated capacity, at which point it can be considered severe sulfation or plate corrosion; and the threshold for nickel-metal hydride batteries is SOH ≤ 70% of rated capacity. In addition, the need for repair can be determined by phenomena such as increased internal resistance, abnormal charging voltage, excessive self-discharge rate, abnormal temperature characteristics, and physical damage. It should be noted that due to differences in material properties, aging mechanisms, and failure modes, the repair strategies for different types of batteries are not exactly the same. This embodiment provides the core differences and comparative analysis of different types of batteries in the table below.

[0024] Core differences and comparative analysis of different battery types Obviously, the embodiments described above are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0025] It should be understood that when the terms "first," "second," etc. are used in the claims, specification, and drawings of this application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "comprise" and "comprising" used in the specification and claims of this application indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

Claims

1. A new energy battery intelligent maintenance method based on charging piles, characterized in that: The method comprises: When charging new energy batteries, the real-time charging current, power, voltage, external ambient temperature and internal core temperature data of the battery are obtained through the charging pile; Uploading the data to a cloud database to match the optimal charging parameter range for batteries of the same model under historical operating conditions, using a multi-dimensional parameter matching matrix constructed by combining historical battery operating data and aging test results; Based on the matching results, the voltage-current curve morphology characteristics are extracted and the correlation between long sequence parameters is analyzed to generate the optimal target current value that takes into account both charging efficiency and battery health. When the voltage deviation of the battery exceeds a dynamic balancing threshold, dynamic balancing charging control is performed through the charging pile communication interface according to the optimal target current value.

2. The method according to claim 1, characterized in that The multi-dimensional parameter matching matrix constructed by combining the battery historical operation data and aging test results includes: Based on the battery's charge and discharge cycle number, capacity attenuation rate, and internal resistance change data, a two-dimensional parameter plane is constructed with current as the horizontal axis and voltage as the vertical axis. In the two-dimensional parameter plane, the temperature dimension is superimposed to form a three-dimensional parameter space; Based on the battery aging test results, the safety boundary surfaces under different SOH health states are marked in the three-dimensional parameter space; The optimal charging parameter interval is located in the overlapping area between the safety boundary surface and the maximum charging efficiency isosurface.

3. The method according to claim 1, characterized in that The method for generating an optimal target current value taking into account both charging efficiency and battery health includes: A convolutional neural network is used to extract the local impulse response slope of the voltage-current curve and the voltage platform fluctuation variance during the constant current phase. The self-attention mechanism of the Transformer model is used to establish long-sequence parameter associations. The long-sequence parameter associations include the cross-influence weight of the ambient temperature sequence and the SOC change rate, and the constraint coefficient of the historical capacity decay trend on the current maximum allowable current. The outputs of the convolutional neural network and the Transformer model are integrated to solve the optimal current value through the objective function, which is: in, η For charging efficiency, ΔT is the temperature rise, SOH For health status, α 、 β 、 γ is the weighting coefficient, and α + β + γ =1; The objective function is optimized under constraints using a gradient descent method, wherein the constraints include voltage constraints, temperature constraints, and SOH health state constraints.

4. The method according to claim 1, wherein The method further includes, when performing the dynamic balanced charging control, adjusting a dynamic balanced threshold value according to the SOC state of charge, wherein the dynamic balanced threshold value adjustment includes: When the SOC state of charge is less than 20%, the balancing threshold is relaxed to ±5%; When 20%≤the SOC≤95%, the balancing threshold is limited to ±2%; When the SOC state of charge is greater than 95%, the balancing threshold is limited to less than 1%.

5. The method according to claim 1, wherein The method further includes, when performing the dynamic balanced charging control, correcting the optimal target current value, wherein the correction includes: For batteries whose SOH health status is lower than the health threshold, reduce their balancing current and satisfy the formula: ， in, I bal represents the adjusted target current value, k is the proportional coefficient used to prevent overcharging, | I opt −I real ∣ represents the absolute deviation between the target current and the actual current, and the target current is the optimal target current value. SOH i is the battery's SOH state of health value.

6. The method according to claim 1, wherein The method further comprises: After executing dynamic balanced charging control, real-time battery response data is collected; Calculate actual charging efficiency η actual and prediction efficiency η pred Deviation Δ η ; When Δ η > Δ η max When the voltage-current curve characteristics are re-extracted, the historical data in the parameter matching matrix is ​​updated, and the optimal target current value is regenerated to establish the feedback coefficient , used to correct the target current value in the next control cycle, where the upper limit of the charging efficiency deviation allowed by the preset system.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which can be executed by at least one processor to implement the method according to any one of claims 1 to 6.

Images