Charging condition extraction method, battery management system, electronic device and storage medium

Abstract

The present application provides a charging condition extraction method, a battery management system, an electronic device and a storage medium. The charging condition extraction method includes: screening the charging condition data to obtain floating charge data; obtaining a split point from the floating charge data, and determining the normal charging condition and the floating charge condition of the vehicle according to the split point. The present application obtains a split point from the floating charge data, distinguishes the normal charging condition and the floating charge condition according to the split point, prevents the floating charge time from being too long or insufficient, optimizes the charging strategy, and improves the performance and life of the battery.

Description

Technical Field

[0001] The present application relates to the field of charging technology, and in particular to a charging condition extraction method, a battery management system, an electronic device and a storage medium. Background Art

[0002] With the popularity of electric and hybrid vehicles, the management and maintenance of vehicle batteries have become increasingly important. Vehicle batteries need to maintain a proper state of charge in daily use to ensure their normal operation and extend their service life. Float charging is a common battery maintenance method that can maintain the battery at a full charge state and prevent deep discharge by maintaining the battery at an appropriate float charge voltage.

[0003] However, excessively high floating charge voltage or long floating charge state may have a negative impact on the battery. Excessive floating charge voltage will cause the battery to overcharge, which will accelerate the hydrolysis reaction inside the battery and produce gas. These gases will cause the battery to lose water and increase internal pressure, ultimately affecting the battery capacity and life. Therefore, controlling the floating charge time is crucial to the health of the battery. Existing battery management systems (BMS) are usually unable to accurately distinguish between normal charging and floating charge processes, resulting in a less than optimized charging strategy.

[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention

[0005] The present application provides a charging condition extraction method, a battery management system, an electronic device and a storage medium to solve the problem of being unable to accurately distinguish between normal charging and floating charging.

[0006] In a first aspect, the present application provides a charging condition extraction method, the method comprising:

[0007] Filter the charging condition data to obtain the floating charge data;

[0008] The split point is obtained from the floating charge data, and the normal charging condition and the floating charge condition are determined according to the split point.

[0009] In one embodiment, a split point is obtained from the floating charge data, and a normal charging condition and a floating charge condition are determined according to the split point, specifically including:

[0010] Divide the data within the first preset time from the start of the floating charge data into N parts according to the time series;

[0011] Obtain the maximum voltage value Vmax1, Vmax2, ... VmaxN in each part of the data;

[0012] The maximum value of the maximum voltage value of each part of the data is obtained as the split voltage Vmaxi, Vmaxi=max{Vmax1, Vmax2...VmaxN};

[0013] The time corresponding to the split voltage is obtained as the split time point, the charging data before the split time point is the normal charging condition, and the charging data after the split time point is the floating charging condition, wherein the split voltage is within the preset voltage range.

[0014] In one embodiment, the method further comprises:

[0015] Get the starting voltage of floating charge data;

[0016] If the starting voltage is within the preset voltage range, the floating charge data is determined to be a floating charge condition.

[0017] In one embodiment, a split point is obtained from the floating charge data, and a normal charging condition and a floating charge condition are determined according to the split point, specifically including:

[0018] Acquire unit charging data, where the unit charging data is data acquired continuously in the floating charge data and the time interval is less than the second preset time;

[0019] Divide the data within the first preset time from the start of the unit charging data into N parts according to the time series;

[0020] Obtain the maximum voltage value Vmax1, Vmax2, ... VmaxN in each part of the data;

[0021] The maximum value of the maximum voltage value of each part of the data is obtained as the split voltage Vmaxi, Vmaxi=max{Vmax1, Vmax2...VmaxN};

[0022] The time corresponding to the split voltage is obtained as the split time point, the charging data before the split time point is the normal charging condition, and the charging data after the split time point is the floating charging condition, wherein the split voltage is within the preset voltage range.

[0023] In one embodiment, after filtering the charging condition data to obtain the floating charge data, the method further includes:

[0024] Reduce the dimension of floating charge data;

[0025] Smoothing is performed on the floating charge data after dimension reduction.

[0026] In one of the embodiments, the charging condition data is filtered according to the first preset condition to obtain the floating charge data;

[0027] The first preset condition is to select, from the charging condition data, continuous charging data in which the DC working mode is in a step-down state and the intelligent charging state is displayed as non-intelligent charging.

[0028] In one embodiment, the method further comprises:

[0029] Screening the processed charging condition data according to a second preset condition to obtain intelligent charging data, and determining an intelligent charging condition according to the intelligent charging data;

[0030] The second preset condition is to select the DC working mode as the buck state and the smart charging state as the continuous charging data in the smart charging in the charging condition data.

[0031] In one embodiment, the method includes:

[0032] Acquire multiple sets of intelligent charging data, each set of intelligent charging data is time-continuous data with a time interval less than a second preset time;

[0033] wherein the time interval between the i-th group of intelligent charging data and the i-1-th group of intelligent charging data is greater than a third preset time;

[0034] The charging time, charging depth, battery charging initial charge state and charging temperature difference of each set of intelligent charging data are calculated, and the battery state is determined based on the calculation results.

[0035] In a second aspect, the present application provides a battery management system, including: a memory, a processor;

[0036] Memory stores computer-executable instructions;

[0037] The processor executes the computer-executable instructions stored in the memory, so that the processor performs any of the above-mentioned charging condition extraction methods.

[0038] In a third aspect, the present application provides an electronic device, comprising the above-mentioned battery management system.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement any of the above-mentioned charging condition extraction methods.

[0040] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements any of the above-mentioned charging condition extraction methods when executed by a processor.

[0041] The present application provides a charging condition extraction method, which includes: screening charging condition data to obtain floating charge data; obtaining a split point from the floating charge data, and determining the normal charging condition and floating charge condition of the vehicle according to the split point. The present application obtains a split point from the floating charge data, distinguishes the normal charging condition and the floating charge condition according to the split point, prevents the floating charge time from being too long or insufficient, optimizes the charging strategy, and improves the performance and life of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] Figure 1 A flowchart of a charging condition extraction method provided in an embodiment of the present application;

[0044] Figure 2 A flowchart of a charging condition extraction method provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram for distinguishing between a normal charging condition and a floating charging condition provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of unit charging data provided by an embodiment of the present application;

[0047] Figure 5 A schematic diagram of a unit charging data dimensionality reduction process provided by an embodiment of the present application;

[0048] Figure 6 A schematic diagram of unit charging data after smoothing provided by an embodiment of the present application;

[0049] Figure 7 A structural schematic diagram of a battery management system is provided for one embodiment of the present application.

[0050] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0051] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0052] Let me first briefly introduce the technical issues. Float charging is a common battery maintenance method. By maintaining the battery at an appropriate float charge voltage, the battery can be kept fully charged and prevented from deep discharge. However, too high a float charge voltage or a long period of float charge may have a negative impact on the battery. Too high a float charge voltage will cause the battery to overcharge, which will accelerate the hydrolysis reaction inside the battery and produce gas. These gases will cause the battery to lose water and increase internal pressure, ultimately affecting the battery's capacity and life.

[0053] Based on the above problems, Figure 1 As shown, Figure 1 This is a flowchart of a charging condition extraction method provided in an embodiment of the present application. The present application provides a charging condition extraction method, which includes the following steps:

[0054] Step S102: Filter the charging condition data to obtain floating charge data.

[0055] Specifically, the charging condition data of the vehicle is filtered out from the real vehicle data in the server or big data platform to ensure the accuracy and completeness of the data. The filtering field is marked with "starting battery signal data" or "charging condition data". Different platforms have different markings. The data can also be marked as other fields. This application does not limit it, but all represent the charging condition data of the battery. The real vehicle data can be collected by the battery management system (BMS), the on-board diagnostic system, the charging pile, the GPS module and the communication module.

[0056] The actual vehicle data includes the battery operating data, including charging operating data, battery storage data and discharge operating data. Charging operating data includes intelligent charging data, normal charging data, floating charging data, cycle DOD (Deep of Discharge) and cycle SOC (State of Charge); battery storage data includes storage time and static data (i.e. parking power consumption and parking time); discharge operating data includes battery discharge time and discharge depth.

[0057] After acquiring the charging condition data, the present application processes the data, including but not limited to: data cleaning, data formatting and data synchronization; data cleaning is to remove noise and outliers to ensure the accuracy of the data; data formatting is to unify the formatting of data from different sources for subsequent processing; data synchronization is to time align data with different timestamps to ensure data consistency.

[0058] Step S104: obtaining a split point from the floating charge data, and determining a normal charging condition and a floating charge condition according to the split point.

[0059] Specifically, normal charging conditions and floating charging conditions are generally a continuous process, which often occurs in the process from powering on to driving. Therefore, we distinguish the normal charging conditions and floating charging conditions of the vehicle after processing and analyzing the floating charging data, optimize the charging strategy, and avoid excessive or insufficient floating charging time.

[0060] The present application obtains a split point from the float charge data, and uses the split point to distinguish the normal charging condition and the float charge condition from the float charge data, thereby preventing the float charge time from being too long or insufficient, optimizing the charging strategy, and improving the performance and life of the battery.

[0061] In one embodiment, step S104 specifically includes the following steps: Figure 2 As shown, Figure 2 A flowchart of a charging condition extraction method provided in an embodiment of the present application:

[0062] Step S202, dividing the data within the first preset time from the start of the floating charge data into N parts according to the time series;

[0063] Optionally, the first preset time is the time for reaching the floating charge state after normal power-on, which can be set according to actual conditions. In the embodiment provided in this application, the first preset time is 15 minutes.

[0064] Step S204, obtaining the maximum voltage value Vmax1, Vmax2, ..., VmaxN in each part of the data;

[0065] Step S206, obtaining the maximum value of the maximum voltage values ​​of each part of the data as the split voltage Vmaxi, Vmaxi=max{Vmax1, Vmax2...VmaxN};

[0066] Step S208, the time corresponding to the split voltage is obtained as the split time point, the charging data before the split time point is the normal charging condition, and the charging data after the split time point is the floating charging condition, wherein the split voltage is within the preset voltage range.

[0067] Optionally, the preset voltage range is 13.7 V-13.8 V. The present application can extract the normal charging condition and floating charging condition of a single vehicle through the above method, and can also extract the normal charging condition and floating charging condition of all vehicles in batches according to the above method.

[0068] In one embodiment, if Figure 3 As shown, Figure 3 A schematic diagram for distinguishing between normal power replenishment conditions and floating charging conditions provided in an embodiment of the present application. The battery is in a normal power replenishment condition within the third preset time after power-on, and the total voltage of the battery reaches 13.7V-13.8V, which is a floating charging condition. Optionally, the third preset time is 15 minutes. Therefore, the floating charge data (i.e., the process from point A to point C) is divided into two data intervals, namely the first part and the second part, by binary division according to the time series, and the time period of each part is 7.5 minutes. The maximum voltage value of the first part and the second part (i.e. Figure 6 Point P and point Q in the figure) to obtain the maximum value of the two maximum voltage values, that is, the split voltage Vmaxi=max(V p 、V Q ), if Vp>V Q , and Vp is within the preset voltage range, the battery reaches the floating charge state in the first part, then the split voltage of the floating charge data is Vp, and the time corresponding to obtaining Vp is the split time point, that is, the charging data before the split time point is that the vehicle is in a normal charging condition, and the charging data after the split time point is that the vehicle is in a floating charge condition, that is, AP is a normal charging condition, and PC is a floating charge condition. Figure 6 Medium V Q >Vp, and V Q Within the preset voltage range, the battery reaches a floating charge state in the second part, that is, AQ is a normal charging condition, and QC is a floating charge condition.

[0069] The present application screens out floating charge data from the charging condition data, and distinguishes normal charging conditions and floating charge conditions from the floating charge data, thereby preventing the floating charge time from being too long or insufficient, optimizing the charging strategy, and improving the performance and life of the battery.

[0070] In one embodiment, step S104 includes: acquiring unit charging data, where the unit charging data is data acquired continuously in the floating charge data and the time interval is less than a second preset time;

[0071] Divide the data within the first preset time from the start of the unit charging data into N parts according to the time series;

[0072] Obtain the maximum voltage value Vmax1, Vmax2, ... VmaxN in each part of the data;

[0073] The maximum value among the maximum voltage values ​​of each part of the data is obtained as the split voltage Vmaxi, Vmaxi=max{Vmax1, Vmax2...VmaxN}.

[0074] The time corresponding to the split voltage is obtained as the split time point. The charging data before the split time point indicates that the vehicle is in a normal charging condition, and the charging data after the split time point indicates that the vehicle is in a floating charging condition, wherein the split voltage is within a preset voltage range.

[0075] Specifically, Figure 4 As shown, Figure 4 A schematic diagram of unit charging data provided in an embodiment of the present application. The horizontal axis is time, the vertical axis is the total voltage collected during the battery charging process, the unit charging data is the smallest charging unit including the normal charging condition and the floating charging condition, and the unit charging data is a set of floating charging data with continuous time and a time interval less than the second preset time. In the embodiment of the present application, the second preset time is set to 3 seconds, and the second preset time can be set according to the actual situation, and this application does not limit it.

[0076] Optionally, the method further includes the following steps: reducing the dimension of the unit charging data; and smoothing the unit charging data after the dimension reduction.

[0077] Specifically, the unit charging data is reduced in dimension to remove redundant and irrelevant features, thereby improving the performance and accuracy of the model. The data dimensionality reduction operation can reduce the consumption of computing resources and improve operating efficiency. Figure 5 As shown, Figure 5 Schematic diagram of the unit charging data dimensionality reduction processing provided in one embodiment of the present application. Secondly, the unit charging data after dimensionality reduction is smoothed. Optionally, the SG filtering algorithm is used to reduce the noise of the unit charging data after dimensionality reduction to obtain a smoothed data table. The filtering algorithm is used for smoothing, which is equivalent to extracting Figure 5 The characteristics of the data in the , adjust the appropriate parameters, such as Figure 6 As shown, Figure 6 A schematic diagram of unit charging data after smoothing provided by an embodiment of the present application.

[0078] The present application obtains unit charging data having normal power replenishment data and floating charging data, and processes the unit charging data to remove redundant and irrelevant features, thereby improving the accuracy of distinguishing normal power replenishment conditions from floating charging conditions and reducing the consumption of computing resources.

[0079] In one embodiment, the method further comprises the following steps:

[0080] The starting voltage of the floating charge data is obtained; if the starting voltage is within a preset voltage range, it is determined that the floating charge data is a floating charge condition.

[0081] Optionally, the preset voltage range is 13.7 V-13.8 V. Specifically, the starting voltage of the floating charge data is obtained, and if the starting voltage of the floating charge data is already within the range of 13.7 V-13.8 V, it is considered that the battery has reached the floating charge state, that is, the floating charge data is the floating charge data of the battery, which belongs to the floating charge condition.

[0082] In one embodiment, after step S102, the method further includes the following steps:

[0083] Reduce the dimension of floating charge data;

[0084] Smoothing is performed on the floating charge data after dimension reduction.

[0085] Specifically, the floating charge data is reduced in dimension to remove redundant and irrelevant features, thereby improving the performance and accuracy of the model. The data reduction operation can reduce the consumption of computing resources and improve the operation efficiency. Secondly, the unit charging data after dimension reduction is smoothed. Optionally, the SG filtering algorithm is used to reduce the noise of the unit charging data after dimension reduction to obtain a smoothed data table, and the filtering algorithm is used to smooth the data. Figure 5 , Figure 6 The data processing method shown.

[0086] In one of the embodiments, the charging condition data is filtered according to the first preset condition to obtain the floating charge data;

[0087] The first preset condition is to select, from the charging condition data, continuous charging data in which the DC working mode is in a step-down state and the intelligent charging state is displayed as non-intelligent charging.

[0088] Specifically, the battery management system (BMS) monitors the status of the battery, including information such as voltage, current, temperature and state of charge (SOC). Therefore, we can collect the field "DC working mode" in the charging condition data to obtain the data of the vehicle in DC working mode, and then judge the start-up battery switch status through the DC working mode. When the DC working mode is "off state", the battery is in storage or discharge state, which can be understood as supplying power to the load; when the DC working mode is "step-down state", it means that the battery is in charging state.

[0089] Since both the smart charging state and the floating charging state are displayed as "step-down state" in the DC working mode of the charging condition data, the smart charging state is displayed as non-smart charging, which means that the data with the smart charging state as smart charging is filtered out, and the remaining data is the data in the floating charging state, that is, the floating charging data. We can thus distinguish the normal charging condition and the floating charging condition of the vehicle from the floating charging data.

[0090] In one of the embodiments, detailed data of the initial and terminal total pressure, start time, end time, initial terminal single cell voltage, initial terminal temperature, vehicle operation status, plug connection status, etc. corresponding to normal charging conditions and floating charging conditions are obtained, and the starting SOC of the battery charging and other information are estimated according to the SOC-OCV test of the lithium iron phosphate system. The SOC-OCV test is a battery testing method used to determine the charge state of the battery.

[0091] In one embodiment, the method further comprises:

[0092] The processed charging condition data is screened according to the second preset condition to obtain intelligent charging data, and it is determined that the vehicle is in the intelligent charging condition according to the intelligent charging data.

[0093] In one of the embodiments, the second preset condition is to filter out the DC working mode in the charging condition data as the buck state and the smart charging state is displayed as continuous charging data in the smart charging.

[0094] Specifically, smart charging is one of the charging conditions. Based on the number of times and time that smart charging is turned on, we can preliminarily judge whether the battery is abnormal or has a reduced lifespan. Therefore, we also extract the smart charging condition of the battery when extracting the charging condition. The smart charging condition screening selects the smart charging state as "smart charging" and the DC working mode as "step-down state".

[0095] In one embodiment, the method includes:

[0096] Acquire multiple sets of intelligent charging data, each set of intelligent charging data is continuous in time, and the time interval is less than the second preset time;

[0097] wherein the time interval between the i-th group of intelligent charging data and the i-1-th group of intelligent charging data is greater than a third preset time;

[0098] The charging time, charging depth, battery charging initial charge state and charging temperature difference of each set of intelligent charging data are calculated, and the battery state is determined based on the calculation results.

[0099] Specifically, in this embodiment, the second preset time is 3 seconds, and the third preset time is 10 seconds. The data with continuous acquisition time and time interval less than 3s is a group of intelligent charging data. Considering that the original data may contain dropped frame data, the time interval between the i-th group of intelligent charging data and the i-1-th group of intelligent charging data is greater than the third preset time, and the time interval between the upper and lower frame data is greater than 10s, which is a new group of intelligent charging data. For example: the time interval between the last frame of the first group of intelligent charging data and the first frame of the second group of intelligent charging data is greater than 10s. This application can obtain multiple groups of intelligent charging data according to the above-mentioned charging condition extraction method, calculate the charging time, charging depth, battery charging initial charge state and charging temperature difference of each group of intelligent charging data, and determine the battery state of the vehicle according to the calculation results.

[0100] This application can extract all intelligent charging conditions, normal charging conditions and floating charging conditions of a vehicle according to the above-mentioned charging condition extraction method, and can also extract intelligent charging conditions, normal charging conditions and floating charging conditions for batch vehicles, as shown in Table 1. This application can prevent the floating charging time from being too long or insufficient, optimize the charging strategy, and improve the performance and life of the battery through intelligent charging conditions, normal charging conditions and floating charging conditions; secondly, the battery status and life can be determined through intelligent charging conditions, normal charging conditions and floating charging conditions.

[0101] Table 1 is an extracted charging condition table provided in an embodiment of the present application.

[0102]

[0103] like Figure 7 As shown, Figure 7 A schematic diagram of a battery management system is provided for an embodiment of the present application. The present application provides a battery management system 500, including: a memory 502, a processor 501;

[0104] Memory stores computer-executable instructions;

[0105] The processor executes the computer-executable instructions stored in the memory, so that the processor performs any of the above-mentioned charging condition extraction methods.

[0106] The present application provides an electronic device, comprising the above-mentioned battery management system.

[0107] Electronic devices are smart terminals with battery devices, including but not limited to mobile phones and new energy vehicles.

[0108] The present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement any of the above-mentioned charging condition extraction methods.

[0109] The present application provides a computer program product, including a computer program, which implements any of the above-mentioned charging condition extraction methods when executed by a processor.

[0110] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0111] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A charging condition extraction method, characterized in that: The method comprises: Filter the charging condition data to obtain the floating charge data; Obtaining a split point from the floating charge data, and determining a normal charging condition and a floating charge condition according to the split point; The step of obtaining a split point from the floating charge data and determining a normal charging condition and a floating charge condition according to the split point specifically includes: Acquire data divided into N parts according to time series from the float charge data; Obtain the maximum voltage value Vmax1, Vmax2, ... VmaxN in each part of the data; The maximum value of the maximum voltage value of each part of the data is obtained as the split voltage Vmaxi, Vmaxi=max{Vmax1, Vmax2...VmaxN}; The time corresponding to the split voltage is obtained as the split time point, the charging data before the split time point is the normal charging condition, and the charging data after the split time point is the floating charging condition, wherein the split voltage is within the preset voltage range.

2. The charging condition extraction method according to claim 1, characterized in that: Obtaining data divided into N parts according to time series from the float charge data, specifically including: The data within the first preset time from the start of the floating charge data is divided into N parts according to the time series.

3. The charging condition extraction method according to claim 1, characterized in that: Obtaining data divided into N parts according to time series from the float charge data, specifically including: Acquire unit charging data, wherein the unit charging data is data acquired continuously in the floating charge data and the time interval is less than a second preset time; The data within the first preset time from the start of the unit charging data is divided into N parts according to a time sequence.

4. The charging condition extraction method according to claim 1, characterized in that: The method further comprises: Acquire the starting voltage of the floating charge data; If the starting voltage is within a preset voltage range, the floating charge data is determined to be a floating charge condition.

5. The charging condition extraction method according to claim 1, characterized in that: After filtering the charging condition data to obtain the floating charge data, the method further includes: Performing dimension reduction on the float charge data; The floating charge data after dimension reduction is smoothed.

6. The charging condition extraction method according to claim 1, characterized in that: Filter the charging condition data according to a first preset condition to obtain the floating charge data; The first preset condition is to select continuous charging data in which the DC working mode is in a step-down state and the intelligent charging state is displayed as non-intelligent charging from the charging condition data.

7. The charging condition extraction method according to claim 1, characterized in that: The method further comprises: Filtering the processed charging condition data according to a second preset condition to obtain intelligent charging data, and determining an intelligent charging condition according to the intelligent charging data; The second preset condition is to select, from the charging condition data, a DC working mode that is in a step-down state and a smart charging state that is displayed as continuous charging data in smart charging.

8. The charging condition extraction method according to claim 7, characterized in that: The method comprises: Acquire multiple groups of intelligent charging data, each group of the intelligent charging data is time-continuous data with a time interval less than a second preset time; wherein the time interval between the i-th group of intelligent charging data and the i-1-th group of intelligent charging data is greater than a third preset time; The charging time, charging depth, battery charging initial charge state and charging temperature difference of each set of intelligent charging data are calculated, and the battery state is determined based on the calculation results.

9. A battery management system, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the charging condition extraction method as described in any one of claims 1-8.

10. An electronic device, characterized in that: Comprising the battery management system as claimed in claim 9.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the charging condition extraction method according to any one of claims 1 to 8.

12. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the charging condition extraction method described in any one of claims 1 to 8.

Images