Training method, device, electronic device and storage medium for self-discharge monitoring model

Abstract

The present disclosure proposes a training method, device, electronic device and storage medium for a self-discharge monitoring model, which relates to the field of battery management technology. The method comprises: obtaining a plurality of training samples, wherein each of the training samples comprises a labeled self-discharge level and a plurality of state-of-charge outlier feature reference values; inputting the plurality of state-of-charge outlier feature reference values ​​into an initial model to obtain a predicted self-discharge level output by the initial model; and modifying the initial model according to the difference between the predicted self-discharge level and the labeled self-discharge level to generate a self-discharge monitoring model. The present disclosure generates a self-discharge monitoring model capable of grading the degree of self-discharge of a battery through training, which not only ensures accurate identification of the self-discharge of the battery, but also realizes determination of the level of self-discharge of the battery based on the severity of the self-discharge of the battery.

Description

Technical Field

[0001] The present disclosure relates to the field of battery management technology, and in particular to a training method, device, electronic device and storage medium for a self-discharge monitoring model. Background Art

[0002] Electric vehicles use batteries as their power source. When a short circuit occurs inside a battery during use, the positive and negative electrodes will overlap to generate a short circuit current, which will lead to the self-discharge of the battery. At present, the monitoring method for battery self-discharge can only determine whether the battery self-discharge is abnormal. However, different degrees of battery self-discharge may bring different consequences, such as reduced vehicle range, insufficient power performance, and even serious safety hazards. Therefore, it is of great significance to study how to quickly and accurately identify the severity of battery self-discharge. Summary of the invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0004] The first embodiment of the present disclosure provides a training method for a self-discharge monitoring model, including:

[0005] Acquire a plurality of training samples, wherein each of the training samples comprises a labeled self-discharge level and a plurality of state-of-charge outlier feature reference values, and the labeled self-discharge level is determined from the self-discharge level;

[0006] Inputting a plurality of the state of charge outlier characteristic reference values ​​into an initial model to obtain a predicted self-discharge level output by the initial model, wherein the predicted self-discharge level is determined from the self-discharge levels after the initial model analyzes the plurality of the state of charge outlier characteristic reference values;

[0007] The initial model is modified according to the difference between the predicted self-discharge level and the marked self-discharge level to generate a self-discharge monitoring model.

[0008] A second aspect of the present disclosure provides a method for monitoring battery self-discharge, comprising:

[0009] Obtain voltage monitoring data and current monitoring data of each battery cell;

[0010] Determining the state of charge of each of the battery cells in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data;

[0011] Determine, according to the state of charge of each battery cell in each reference time period, an outlier feature of the state of charge of each battery cell in each reference time period;

[0012] All of the state-of-charge outlier features of each of the battery cells are input into a self-discharge monitoring model to determine a self-discharge level of each of the battery cells.

[0013] The third aspect of the present disclosure provides a training device for a self-discharge monitoring model, including:

[0014] A first acquisition module is used to acquire a plurality of training samples, wherein each of the training samples includes a labeled self-discharge level and a plurality of state of charge outlier feature reference values, and the labeled self-discharge level is determined from the self-discharge level;

[0015] A second acquisition module, configured to input a plurality of the state of charge outlier characteristic reference values ​​into an initial model to obtain a predicted self-discharge level output by the initial model, wherein the predicted self-discharge level is determined from the self-discharge level after the initial model analyzes the plurality of the state of charge outlier characteristic reference values;

[0016] A generating module is used to modify the initial model according to the difference between the predicted self-discharge level and the marked self-discharge level to generate the self-discharge monitoring model.

[0017] A fourth aspect of the present disclosure provides a battery self-discharge monitoring device, comprising:

[0018] A first acquisition module, used to acquire voltage monitoring data and current monitoring data of each battery cell;

[0019] A first determination module, configured to determine the state of charge of each of the battery cells in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data;

[0020] A second determination module, configured to determine, according to the state of charge of each battery cell in each reference time period, an outlier feature of the state of charge of each battery cell in each reference time period;

[0021] The third determination module is used to input all the state of charge outlier features of each battery cell into a self-discharge monitoring model to determine the self-discharge level of each battery cell.

[0022] The fifth aspect embodiment of the present disclosure proposes an electronic device, comprising: a memory, a processor, and computer instructions stored in the memory and executable on the processor. When the processor executes the instructions, it implements the method proposed in the first aspect embodiment or the second aspect embodiment of the present disclosure.

[0023] A sixth aspect embodiment of the present disclosure proposes a vehicle, comprising the electronic device proposed in the fifth aspect embodiment of the present disclosure.

[0024] The seventh aspect embodiment of the present disclosure proposes a non-temporary computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, they implement the method proposed in the first aspect embodiment or the second aspect embodiment of the present disclosure.

[0025] The eighth aspect embodiment of the present disclosure proposes a computer program product. When the instruction processor in the computer program product executes, the method proposed in the first aspect embodiment or the second aspect embodiment of the present disclosure is executed.

[0026] The training method, device, computer equipment and storage medium of the self-discharge monitoring model provided by the present disclosure have the following beneficial effects:

[0027] First, multiple training samples are obtained, wherein each training sample includes a labeled self-discharge level and multiple state of charge outlier feature reference values; then, multiple state of charge outlier feature reference values ​​are input into the initial model to obtain the predicted self-discharge level output by the initial model; finally, according to the difference between the predicted self-discharge level and the labeled self-discharge level, the initial model is corrected to generate a self-discharge monitoring model. The present invention trains and generates a self-discharge monitoring model that can classify the degree of self-discharge of the battery based on the state of charge outlier features of the battery training samples, realizes accurate identification of the self-discharge of the battery through the self-discharge monitoring model, and can determine the self-discharge level of the battery according to the severity of the battery self-discharge, providing support and basis for taking different countermeasures based on the level of battery self-discharge.

[0028] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0030] Figure 1 A flowchart of a method for training a self-discharge monitoring model provided by an embodiment of the present disclosure;

[0031] Figure 2 A flowchart of a method for training a self-discharge monitoring model provided by another embodiment of the present disclosure;

[0032] Figure 3 A change curve of training samples corresponding to different self-discharge levels provided by an embodiment of the present disclosure;

[0033] Figure 4 A flowchart of a method for monitoring battery self-discharge provided by an embodiment of the present disclosure;

[0034] Figure 5 A schematic flow chart of a method for monitoring battery self-discharge provided by another embodiment of the present disclosure;

[0035] Figure 6 A schematic diagram of a battery SOC_OCV experience curve provided by an embodiment of the present disclosure;

[0036] Figure 7 A schematic diagram of the structure of a training device for a self-discharge monitoring model provided by an embodiment of the present disclosure;

[0037] Figure 8 A schematic diagram of the structure of a battery self-discharge monitoring device provided by an embodiment of the present disclosure;

[0038] Fig. 9 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0039] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0040] The following describes the training method, device, electronic device and storage medium of the self-discharge monitoring model of the embodiments of the present disclosure with reference to the accompanying drawings.

[0041] Figure 1 A flowchart of a method for training a self-discharge monitoring model provided in an embodiment of the present disclosure.

[0042] The embodiment of the present disclosure takes the training method of the self-discharge monitoring model being configured in a training device of the self-discharge monitoring model as an example. The training device of the self-discharge monitoring model can be applied to any vehicle-mounted device, cloud device, or other hardware device with various operating systems, touch screens, and / or display screens, so that the device can perform the training function of the self-discharge monitoring model.

[0043] like Figure 1 As shown, the training method of the self-discharge monitoring model may include the following steps:

[0044] Step 101 : obtaining a plurality of training samples, wherein each training sample includes a labeled self-discharge level and a plurality of state of charge outlier feature reference values, and the labeled self-discharge level is determined from the self-discharge level.

[0045] It should be noted that the self-discharge level of the battery can represent the severity of the self-discharge of the battery. The specific division method of the self-discharge level can be determined according to actual needs.

[0046] For example, it can be divided into normal, severe and not severe. Or, it can be divided into level 0, level 1, level 2, level 3, etc. Among them, level 0 represents normal battery self-discharge. As the level increases, it indicates that the degree of battery self-discharge is getting more and more serious.

[0047] It should be noted that the electric vehicle power battery may include a plurality of battery cells, each of which corresponds to a state of charge (SOC), ie, the remaining power of the battery.

[0048] When there is a short circuit point inside a battery cell, the positive and negative electrodes overlap to generate a short circuit current. As time goes by, the remaining power gradually decreases, that is, the SOC decreases, and the battery voltage decreases at the same time. The state of charge outlier feature can be any type of value that can characterize the difference in the state of charge of each battery cell.

[0049] For example, the state of charge of each battery cell in a certain period of time is SOC1, SOC2, ..., SOC n Where n is the number of battery cells. The average state of charge of each battery cell =(SOC1+SOC2+…+SOC n ) / n, the outlier characteristics of the state of charge of each battery cell can be:

[0050] Alternatively, the states of charge of each battery cell in a certain reference period are SOC1, SOC2, ..., SOC n The median state of charge of each battery cell during the reference period is SOC i The outlier characteristics of the state of charge of each battery cell are: ΔSOC1 = SOC1-SOC i , ΔSOC2=SOC2-SOC i , ..., ΔSOC n =SOC n -SOC i .

[0051] It should be noted that the above examples are only illustrative and cannot be used as a limitation on the outlier characteristics of the state of charge in the embodiments of the present disclosure.

[0052] In the disclosed embodiment, each training sample includes a labeled self-discharge level and multiple state-of-charge outlier feature reference values. Among them, multiple state-of-charge outlier feature reference values ​​form a data sequence. The number of state-of-charge outlier feature reference values ​​contained in each training sample can be determined according to the number of reference time periods. In other words, each state-of-charge outlier feature reference value in the training sample corresponds to a reference time period.

[0053] For example, the reference period is 6 hours long, and 7 days includes 28 reference periods, namely 0:00 to 6:00, 6:00 to 12:00, 12:00 to 18:00, and 18:00 to 24:00. Then each training sample can include 28 sequentially arranged outlier feature reference values ​​of the state of charge.

[0054] It is understandable that the change trend of the state of charge outlier feature of the battery cell within a certain period of time can characterize the severity of the battery self-discharge. Therefore, according to the numerical values ​​of multiple state of charge outlier feature reference values ​​in each training sample, the labeled self-discharge level corresponding to each training sample can be determined from the self-discharge level.

[0055] For example, the self-discharge level is divided into 0 to 5. For a certain training sample, the state of charge outlier feature reference values ​​it contains are 0, 0.8, 0.4, 0.7, ..., 1.1, and the corresponding annotated self-discharge level can be 0. For another training sample, the state of charge outlier feature reference values ​​it contains are -3.8, -2.3, -3.2, ..., -1.5, and the corresponding annotated self-discharge level can be 1.

[0056] It should be noted that the above examples are only for illustration and cannot be used as limitations on the reference values ​​of the state of charge outlier characteristics and the annotated self-discharge levels in the embodiments of the present disclosure.

[0057] Step 102, inputting a plurality of state of charge outlier characteristic reference values ​​into an initial model to obtain a predicted self-discharge level output by the initial model, wherein the predicted self-discharge level is determined from the self-discharge level after the initial model analyzes the plurality of state of charge outlier characteristic reference values.

[0058] Among them, the initial model can be any type of pre-built machine learning model, such as an Xgboost (Extreme Gradient Boosting) model, etc., which is not limited in this disclosure.

[0059] Specifically, the initial model can analyze multiple input state-of-charge outlier feature reference values ​​based on pre-set model parameters to determine the severity of battery self-discharge and convert it into a predicted self-discharge level output.

[0060] For example, the initial model may determine a level from pre-set self-discharge levels as the predicted self-discharge level according to the numerical values ​​of multiple state of charge outlier feature reference values ​​and the changing trends of each state of charge outlier feature reference value over time.

[0061] Step 103 , modifying the initial model according to the difference between the predicted self-discharge level and the marked self-discharge level to generate a self-discharge monitoring model.

[0062] In the initial stage, the predicted self-discharge level output by the initial model may be significantly different from the labeled self-discharge level. As the training progresses, the initial model is continuously modified until the difference between the predicted self-discharge level and the labeled self-discharge level meets the requirements.

[0063] For example, the Xgboost model can be used to continuously generate new decision trees to fit the residuals of the previous decision tree training results, and the prediction results of each tree are added together to obtain the final result until the difference between the predicted self-discharge level and the labeled self-discharge level meets the requirements.

[0064] In the embodiment of the present disclosure, a plurality of training samples are first obtained, wherein each training sample includes a labeled self-discharge level and a plurality of state of charge outlier feature reference values; then the plurality of state of charge outlier feature reference values ​​are input into the initial model to obtain the predicted self-discharge level output by the initial model; finally, the initial model is modified according to the difference between the predicted self-discharge level and the labeled self-discharge level to generate a self-discharge monitoring model. The present disclosure trains a self-discharge monitoring model capable of grading the degree of self-discharge of the battery based on the outlier feature of the state of charge of the battery, realizes accurate identification of the self-discharge of the battery based on the self-discharge monitoring model, and at the same time determines the level of self-discharge of the battery according to the severity of the self-discharge of the battery, providing support and basis for taking different countermeasures based on the level of self-discharge of the battery.

[0065] It is understandable that training samples are an important factor affecting the accuracy and reliability of model prediction results. However, in real scenarios, severe battery self-discharge may not be common. Therefore, the number of training samples generated based on real data is limited. In one possible implementation, a large number of training samples can be obtained by constructing training data. Figure 2 The above process is further explained.

[0066] Figure 2 FIG. 1 is a flow chart of a method for training a self-discharge monitoring model provided by another embodiment of the present disclosure. Figure 2 As shown, the training method of the self-discharge monitoring model may include the following steps:

[0067] Step 201, determine a first numerical range and a second numerical range corresponding to each self-discharge level, wherein the first numerical range is a numerical range of the state of charge outlier characteristic within a set period, and the second numerical range is a numerical range of a rate of change of the state of charge outlier characteristic within a set period.

[0068] It should be noted that the battery self-discharge level can be characterized by the change trend of the outlier characteristics of the state of charge of the battery cell within a set period.

[0069] The duration of the set cycle can be set according to actual needs, for example, 7 days, 10 days or 20 days, etc., which is not limited in the present disclosure.

[0070] Furthermore, the set period can be divided into a plurality of reference time periods according to the duration, wherein the duration of the reference time period can be determined according to the duration of the set period.

[0071] For example, if the set period is 7 days, each day can be divided into 4 reference periods, and the set period can be divided into 28 reference periods.

[0072] Alternatively, if the set period is 20 days, each day can be divided into one reference period, and the set period can be divided into 20 reference periods.

[0073] The first value range corresponding to each self-discharge level may be determined according to the state of charge outlier characteristics within a set period, and the second value range corresponding to each self-discharge level may be determined according to the rate of change of the state of charge outlier characteristics within a set period.

[0074] Furthermore, the first numerical range and the second numerical range may be used simultaneously as two indicators for determining the battery self-discharge level.

[0075] For example, when the battery self-discharge level is level 0, the first numerical range may be (-1, 1) and the second numerical range may be (-0.1, 0.1). When the battery self-discharge level is level 1, the first numerical range may be (-4, -1) and the second numerical range may be (-0.5, -0.1).

[0076] It should be noted that the above examples are merely illustrative and cannot be used as limitations on the first numerical range and the second numerical range corresponding to each self-discharge level in the embodiments of the present disclosure.

[0077] In addition, the first numerical range and the second numerical range corresponding to each battery self-discharge level may be independent of each other or may have an intersection, which is not limited in the present disclosure.

[0078] Step 202: Generate a plurality of initial sample curves corresponding to each self-discharge level according to the first numerical range and the second numerical range; wherein the initial sample curve is a curve of change of the outlier characteristic of the state of charge within a set period.

[0079] It can be understood that since the first numerical range represents the state of charge outlier characteristics within the set period, and the second numerical range represents the rate of change of the state of charge outlier characteristics within the set period, for each self-discharge level, two values ​​can be arbitrarily selected from the corresponding first numerical range as the state of charge outlier characteristics at the initial moment and the end moment of the set period, respectively, while ensuring that the rate of change of the state of charge outlier characteristics within the set period is within the corresponding second numerical range, thereby generating an initial sample curve.

[0080] Specifically, the horizontal axis of the coordinate system where the initial sample curve is located is time, and the vertical axis is the charge state outlier feature. The time corresponding to the starting point of the initial sample curve is the initial moment of the set period, and the time corresponding to the end point of the initial sample curve is the end time of the set period. The charge state outlier features corresponding to the starting point and the end point of the initial sample curve are two values ​​arbitrarily selected from the first value range, and the slope of the initial sample curve is within the second value range.

[0081] Step 203 : determining initial values ​​of outlier characteristics of the state of charge in a plurality of reference time periods within a set period according to the initial sample curve.

[0082] Among them, since the starting point coordinates, the end point coordinates and the slope of the initial sample curve are known, the outlier characteristics of the state of charge at any time within the set period can be determined.

[0083] Specifically, multiple sample points can be selected on the initial sample curve according to the length of the reference period in the set cycle, and each sample point corresponds to a reference period. The initial value of the state of charge outlier feature corresponding to each reference period can be determined according to the initial sample curve.

[0084] Step 204 : Generate a corresponding random number for each initial value of the state of charge outlier feature.

[0085] Step 205 : adding each state of charge outlier feature initial value to the corresponding random number to obtain a state of charge outlier feature reference value corresponding to each reference time period.

[0086] It should be noted that in real scenarios, the outlier characteristics of the state of charge of battery cells at different time periods are usually fluctuating and irregular.

[0087] Therefore, in order to make the state of charge outlier feature corresponding to each reference time period closer to the true value, a random number can be generated for each state of charge outlier feature initial value, and each state of charge outlier feature initial value can be added to the corresponding random number to obtain the state of charge outlier feature reference value corresponding to each reference time period.

[0088] The numerical range of the random number can be set according to actual needs, for example, it can be 0 to 0.1, or it can be 0 to 0.5, etc., which is not limited in the present disclosure.

[0089] Step 206 , obtaining true values ​​of outlier characteristics of the state of charge of a plurality of battery cells with normal self-discharge in a plurality of reference time periods of a set cycle.

[0090] It is understandable that in the field scenario, most battery cells self-discharge normally, and only a few battery cells may self-discharge abnormally. Therefore, the true value of the state of charge of a large number of battery cells with normal self-discharge in multiple reference time periods of a set cycle can be obtained.

[0091] Furthermore, according to the true value of the state of charge, the true value of the outlier characteristic of the state of charge of the battery cell in multiple reference time periods of a set cycle can be determined.

[0092] Among them, the specific implementation method of obtaining the true value of the state of charge outlier feature can refer to the detailed description of obtaining the state of charge outlier feature in other embodiments of the present disclosure, and will not be repeated here.

[0093] Step 207 : adding each state of charge outlier feature reference value to the state of charge outlier feature true value of the corresponding time period to update the state of charge outlier feature reference value.

[0094] It should be noted that in real scenarios, the state of charge outlier characteristics of battery cells with normal self-discharge often fluctuate around zero.

[0095] In order to further improve the authenticity of the state of charge outlier feature reference value corresponding to each reference time period, each state of charge outlier feature reference value can be added to the state of charge outlier feature true value of the corresponding time period to make its change characteristics closer to the real data.

[0096] Step 208 : obtaining annotated self-discharge levels corresponding to a plurality of state of charge outlier feature reference values ​​to generate training samples.

[0097] Among them, according to the numerical value of the state of charge outlier feature reference value in each reference time period within the set period and the change rate of the state of charge outlier feature within the set period, the labeled self-discharge level corresponding to each training sample can be determined.

[0098] In some embodiments, Figure 3As shown, the set period can be 20 days, and the duration of each reference period in the set period is 1 day. The self-discharge level is divided into 0-6 levels, where level 0 represents normal self-discharge of the battery cell. Level 1 represents the weakest self-discharge of the battery cell. As the level increases, the change in the outlier characteristics of the state of charge becomes larger and larger, indicating that the self-discharge of the battery cell is becoming more and more serious.

[0099] It should be noted that in the disclosed embodiment, the real monitoring data of the battery cells can be used to construct training samples of normal battery self-discharge, and the above method can be used to construct training samples of abnormal battery self-discharge. By randomly sampling the training samples, the number of training samples corresponding to each self-discharge level is kept balanced.

[0100] Step 209 : inputting a plurality of state of charge outlier characteristic reference values ​​into the initial model to obtain a predicted self-discharge level output by the initial model.

[0101] Step 210 , modifying the initial model according to the difference between the predicted self-discharge level and the marked self-discharge level to generate a self-discharge monitoring model.

[0102] The specific implementation of step 209 to step 210 may refer to the detailed description of other embodiments of the present disclosure and will not be repeated here.

[0103] In the disclosed embodiment, firstly, a large number of training samples are generated by constructing data based on the self-discharge level classification rules, and then the historical monitoring data is used to generate real data of normal battery self-discharge, and the constructed training samples are corrected, which not only ensures the data volume of the model training samples, but also improves the accuracy and reliability of the monitoring model prediction results.

[0104] Figure 4 A schematic flow chart of a method for monitoring battery self-discharge provided in an embodiment of the present disclosure.

[0105] The embodiment of the present disclosure takes the method for monitoring battery self-discharge as an example in which the method is configured in a battery self-discharge monitoring device. The battery self-discharge monitoring device can be applied to any vehicle-mounted device, cloud device, or other hardware device with various operating systems, touch screens, and / or display screens, so that the device can perform the battery self-discharge monitoring function.

[0106] like Figure 4 As shown, the battery self-discharge monitoring method may include the following steps:

[0107] Step 401, obtaining voltage monitoring data and current monitoring data of each battery cell.

[0108] It should be noted that the power battery of an electric vehicle is composed of a plurality of battery cells electrically connected. For example, a power battery may include 96 battery cells.

[0109] It is understandable that in order to ensure the reliable operation of the battery and extend the service life of the battery, the voltage and current of each battery cell can be monitored to maintain and manage the battery.

[0110] The current monitoring data of each battery cell connected in series is the same, and the voltage monitoring data of the battery cell may be different due to individual differences. The voltage monitoring data is the voltage value of each battery cell at any time, and the current monitoring data is the current value of each battery cell at any time.

[0111] Step 402 , determining the state of charge of each battery cell in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data.

[0112] It should be noted that the battery state of charge (SOC) is the remaining power of the battery. When there is a short circuit point inside the battery, the positive and negative electrodes overlap to generate a short circuit current. As time accumulates, the remaining power gradually decreases, that is, the SOC decreases, and the battery voltage decreases at the same time.

[0113] Therefore, based on the voltage monitoring data and current monitoring data of each battery cell, the state of charge of each battery cell at the corresponding moment can be determined. Among them, the decrease of the state of charge SOC, that is, the integral of the short-circuit current and time, is currently the most accurate indicator for measuring battery self-discharge.

[0114] It is understandable that the battery self-discharge situation may not change much in a short period of time. However, as time accumulates, the change trend of the battery self-discharge will gradually become obvious.

[0115] Therefore, the self-discharge of the battery can be evaluated based on the state of charge of the battery in multiple reference time periods, thereby achieving the evaluation of the self-discharge of the battery by combining real-time data and historical data to improve the accuracy of the evaluation.

[0116] The number and duration of the reference time periods should be consistent with the reference time period corresponding to each training sample. Each reference time period corresponds to a state of charge, and multiple reference time periods can form a fixed duration.

[0117] For example, if the reference period is 6 hours, 7 days may include 28 reference periods, namely 0:00 to 6:00, 6:00 to 12:00, 12:00 to 18:00, and 18:00 to 24:00. Alternatively, if the reference period is 1 day, 20 days may include 20 reference periods.

[0118] It should be noted that the monitoring of the battery self-discharge can be repeated at a set time to achieve continuous monitoring of the battery.

[0119] For example, the self-discharge of the battery may be monitored once a day, or the self-discharge of the battery may be monitored once every 12 hours, which is not limited in the present disclosure.

[0120] Each time the self-discharge of the battery is monitored, the self-discharge of the battery can be evaluated based on the real-time state of charge and historical state of charge of each battery cell.

[0121] For example, when the self-discharge of the battery is monitored every day and the reference period is 6 hours, the state of charge of the battery cell in the 4 reference periods of the day can be obtained as the real-time state of charge; at the same time, the state of charge of the battery cell in the 24 reference periods of the previous 6 days can be obtained as the historical state of charge. Then, the self-discharge of the battery is evaluated based on the state of charge of the 28 reference periods in 7 days.

[0122] In the disclosed embodiment, the historical state of charge can be determined based on the historical monitoring data stored on the cloud device, and the real-time state of charge can be determined based on the real-time monitoring data of the vehicle-side device. The disclosed embodiment combines real-time data with historical data to evaluate the battery self-discharge, thereby ensuring the timeliness of battery self-discharge monitoring.

[0123] It should be noted that the above examples are merely illustrative and cannot be used as limitations on the reference time period, etc. in the embodiments of the present disclosure.

[0124] Step 403 : determining the outlier feature of the state of charge of each battery cell in each reference time period according to the state of charge of each battery cell in each reference time period.

[0125] The method of determining the state of charge outlier feature of each battery cell in each reference period should be consistent with the state of charge outlier feature corresponding to each training sample.

[0126] For example, the state of charge of each battery cell in a certain period of time is SOC1, SOC2, ..., SOC n Where n is the number of battery cells. The average state of charge of each battery cell =(SOC1+SOC2+…+SOC n ) / n, the outlier characteristics of the state of charge of each battery cell can be:

[0127] Alternatively, the states of charge of each battery cell in a certain reference period are SOC1, SOC2, ..., SOC n The median state of charge of each battery cell during the reference period is SOC i The outlier characteristics of the state of charge of each battery cell are: ΔSOC1 = SOC1-SOC i , ΔSOC2=SOC2-SOC i , ..., ΔSOC n =SOC n -SOC i .

[0128] It should be noted that the above examples are merely illustrative and cannot be used as limitations on the outlier characteristics of the state of charge in the embodiments of the present disclosure.

[0129] In step 404 , all state of charge outlier features of each battery cell are input into a self-discharge monitoring model to determine a self-discharge level of each battery cell.

[0130] It can be understood that the changing trend of the outlier characteristics of the state of charge of a battery cell within a certain period of time can represent the severity of the battery self-discharge.

[0131] Therefore, the self-discharge monitoring model can be used to analyze the outlier characteristics of the state of charge of the battery cell to determine the self-discharge level of the battery cell.

[0132] For example, the self-discharge level of the battery cell may be normal, severe or not severe, or may be level 0, level 1, level 2 or level 3, etc.

[0133] Among them, the specific implementation of the self-discharge monitoring model can refer to the detailed description of other embodiments of the present disclosure, and will not be repeated here.

[0134] In the disclosed embodiment, the voltage monitoring data and current monitoring data of each battery cell are first obtained; then, the state of charge of each battery cell in multiple reference time periods is determined based on the voltage monitoring data and the current monitoring data; then, the state of charge outlier characteristics of each battery cell in each reference time period are determined based on the state of charge of each battery cell in each reference time period; finally, all the state of charge outlier characteristics of each battery cell are input into the self-discharge monitoring model to determine the self-discharge level of each battery cell. Based on the outlier characteristics of the state of charge of the battery in a set period, the disclosed method monitors the self-discharge level of the battery through the self-discharge monitoring model, realizes accurate identification of the severity of battery self-discharge, and provides support and basis for taking different countermeasures based on the risk level of battery self-discharge.

[0135] Figure 5FIG. 1 is a flow chart of a method for monitoring battery self-discharge provided by another embodiment of the present disclosure. Figure 5 As shown, the battery self-discharge monitoring method may include the following steps:

[0136] Step 501, obtaining voltage monitoring data and current monitoring data of each battery cell.

[0137] The specific implementation of step 201 may refer to the detailed description of other embodiments of the present disclosure and will not be repeated here.

[0138] Step 502 , determining a target time period in which the current monitoring data is within a set range within each reference time period.

[0139] It is understandable that when the electric vehicle is in a driving state, the battery current is significantly greater than the current when the electric vehicle is in a stationary state. Therefore, the period of time when the electric vehicle is in a stationary state can be determined based on the battery current monitoring data, and the corresponding state of charge can be determined based on the battery voltage in the stationary state, so as to improve the accuracy and reliability of battery self-discharge monitoring.

[0140] Specifically, a target period in which the current monitoring data is within a set range can be selected from each reference period. The specific implementation of the reference period can refer to the detailed description of other embodiments of the present disclosure, which will not be repeated here.

[0141] The setting range of the current monitoring data can be determined according to actual needs. For example, the setting range can be 0 to 10 amps, or the setting range can be 0 to 5 amps, which is not limited in the present disclosure.

[0142] In addition to the value of the current monitoring data, the target period can also be determined in combination with the duration. For example, the period in which the battery current monitoring data is within the set range for more than 1 hour is the target period.

[0143] Step 503 , determining the state of charge of each battery cell in a reference period according to the voltage monitoring data of each battery cell in the target period and the mapping relationship between the battery state of charge and the open circuit voltage.

[0144] It is understandable that the current data and voltage data of the battery cell at each moment correspond one to one. That is, after the target period is determined according to the current monitoring data, the voltage monitoring data of the target period can be obtained.

[0145] It should be noted that the terminal voltage of the battery in the open circuit state is called the open circuit voltage (OCV). The battery state of charge and the open circuit voltage have a certain mapping relationship, which can be characterized by the SOC_OCV empirical curve, such as Figure 6shown.

[0146] Therefore, the state of charge SOC within the target period can be obtained based on the voltage monitoring data of the battery cell within the target period and the SOC_OCV experience curve that represents the mapping relationship between the battery state of charge and the open circuit voltage.

[0147] It should be noted that when the duration of the reference period is long, it may include multiple target periods. For example, when the duration of the reference period is 1 day, the target period may include 0:00 to 8:00, 12:00 to 14:00, etc.

[0148] Therefore, when determining the state of charge of a battery cell within a reference period, different approaches may be used as needed.

[0149] For example, a target period within the reference period may be selected, and the state of charge at a certain moment within the target period may be used as the state of charge of the battery cell in the reference period.

[0150] Alternatively, each target period within the reference period may be sampled, and the average value of the state of charge of all sampling points may be used as the state of charge of the battery cell in the reference period.

[0151] It should be noted that the above examples are merely illustrative and cannot be used as a limitation on the charge state of the battery cells in the reference period in the embodiments of the present disclosure.

[0152] Step 504 : determining a reference state of charge according to the median of the states of charge of all battery cells in a reference period of time.

[0153] The reference state of charge can be used as a comparison benchmark to determine the difference in the state of charge between the battery cells. By comparing the state of charge corresponding to each battery cell with the reference state of charge, the difference between the two can be determined.

[0154] In the embodiment of the present disclosure, the median of the states of charge of all battery cells in the reference time period may be used as the reference state of charge.

[0155] For example, the states of charge of each battery cell in a certain reference period are SOC1, SOC2, ..., SOC n . SOC1, SOC2, ..., SOC n Arrange the values ​​in order, and the number in the middle is the reference state of charge. If there is an even number of battery cells, the average of the two middle values ​​can be taken as the reference state of charge.

[0156] Step 505 : determining an outlier feature of the state of charge of each battery cell in the reference time period according to a difference between the state of charge of each battery cell in the reference time period and a reference state of charge.

[0157] The state of charge outlier feature can characterize the difference between the states of charge of each battery cell. In the embodiment of the present disclosure, the difference between the state of charge corresponding to each battery cell and the reference state of charge can be used as the state of charge outlier feature of each battery cell.

[0158] For example, the states of charge of each battery cell in a certain reference period are SOC1, SOC2, ..., SOC n The outlier characteristics of the state of charge of each battery cell are: ΔSOC1 = SOC1-SOC i , ΔSOC2=SOC2-SOC i , ..., ΔSOC n =SOC n -SOC i Among them, SOC i is the reference state of charge.

[0159] Step 506 : Input all the state of charge outlier features of each battery cell into the self-discharge monitoring model to determine the self-discharge level of each battery cell.

[0160] The specific implementation of step 506 may refer to the detailed description of other embodiments of the present disclosure and will not be repeated here.

[0161] In the disclosed embodiment, the voltage monitoring data and current monitoring data of each battery cell are first obtained, and then a target time period is screened from a reference time period according to the current monitoring data of the battery cell, and the corresponding state of charge is obtained based on the voltage monitoring data of the target time period; then, the state of charge outlier characteristics of the battery cell in multiple reference time periods are determined according to the state of charge; finally, the self-discharge level of the battery is monitored through a self-discharge monitoring model according to the state of charge outlier characteristics of the battery in multiple reference time periods, which not only improves the timeliness and accuracy of the battery self-discharge monitoring, but also realizes the classification of the severity of the battery self-discharge, and provides support and basis for taking different countermeasures based on the battery self-discharge level.

[0162] In order to implement the above embodiments, the present disclosure also proposes a training device for a self-discharge monitoring model.

[0163] Figure 7 A schematic diagram of the structure of a training device for a self-discharge monitoring model provided in an embodiment of the present disclosure.

[0164] like Figure 7 As shown, the training device 100 of the self-discharge monitoring model may include: a first acquisition module 110 , a second acquisition module 120 , and a generation module 130 .

[0165] The first acquisition module 110 is used to acquire a plurality of training samples, wherein each training sample includes a labeled self-discharge level and a plurality of state of charge outlier feature reference values, and the labeled self-discharge level is determined from the self-discharge level;

[0166] A second acquisition module 120, for inputting a plurality of state of charge outlier characteristic reference values ​​into an initial model to obtain a predicted self-discharge level output by the initial model, wherein the predicted self-discharge level is determined from the self-discharge level after the initial model analyzes the plurality of state of charge outlier characteristic reference values;

[0167] The generating module 130 is used to modify the initial model according to the difference between the predicted self-discharge level and the marked self-discharge level to generate a self-discharge monitoring model.

[0168] In a possible implementation, the first acquisition module includes:

[0169] A first determination unit is used to determine a first numerical range and a second numerical range corresponding to each self-discharge level, wherein the first numerical range is a numerical range of the state of charge outlier characteristic within a set period, and the second numerical range is a numerical range of a rate of change of the state of charge outlier characteristic within the set period;

[0170] A first generating unit is used to generate a plurality of initial sample curves corresponding to each self-discharge level according to the first numerical range and the second numerical range; wherein the initial sample curve is a curve of change of the outlier characteristic of the state of charge within a set period;

[0171] A second determination unit, configured to determine initial values ​​of outlier characteristics of the state of charge for a plurality of reference time periods within a set period according to the initial sample curve;

[0172] A second generating unit is used to generate a corresponding random number for each initial value of the state of charge outlier feature;

[0173] A first acquisition unit is used to add each state of charge outlier feature initial value to the corresponding random number to obtain a state of charge outlier feature reference value corresponding to each reference time period;

[0174] The second acquisition unit is used to acquire the annotated self-discharge levels corresponding to a plurality of state of charge outlier feature reference values ​​to generate training samples.

[0175] In a possible implementation, the first acquisition module further includes:

[0176] A third acquisition unit is used to acquire the true values ​​of the outlier characteristics of the state of charge of multiple battery cells with normal self-discharge in multiple reference time periods of a set cycle;

[0177] The updating unit is used to add each state of charge outlier feature reference value to the state of charge outlier feature true value of the corresponding time period to update the state of charge outlier feature reference value.

[0178] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can be referred to the above method embodiments, and will not be repeated here.

[0179] The training device of the self-discharge monitoring model of the embodiment of the present disclosure first obtains multiple training samples, wherein each training sample includes a labeled self-discharge level and multiple state of charge outlier feature reference values; then the multiple state of charge outlier feature reference values ​​are input into the initial model to obtain the predicted self-discharge level output by the initial model; finally, according to the difference between the predicted self-discharge level and the labeled self-discharge level, the initial model is corrected to generate a self-discharge monitoring model. The present disclosure trains and generates a self-discharge monitoring model that can classify the degree of self-discharge of the battery based on the outlier feature of the state of charge of the battery, realizes accurate identification of the battery self-discharge situation based on the self-discharge monitoring model, and at the same time determines the level of battery self-discharge according to the severity of battery self-discharge, providing support and basis for taking different countermeasures based on the level of battery self-discharge.

[0180] In order to implement the above embodiments, the present disclosure also provides a battery self-discharge monitoring device.

[0181] Figure 8 A schematic diagram of the structure of a battery self-discharge monitoring device provided in an embodiment of the present disclosure.

[0182] like Figure 8 As shown, the battery self-discharge monitoring device 200 may include: a first acquisition module 210 , a first determination module 220 , a second determination module 230 , and a third determination module 240 .

[0183] The first acquisition module 210 is used to acquire voltage monitoring data and current monitoring data of each battery cell;

[0184] A first determination module 220, for determining the state of charge of each battery cell in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data;

[0185] A second determination module 230, configured to determine, according to the state of charge of each battery cell in each reference time period, an outlier feature of the state of charge of each battery cell in each reference time period;

[0186] The third determination module 240 is used to input all the state of charge outlier features of each battery cell into the self-discharge monitoring model to determine the self-discharge level of each battery cell.

[0187] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can be referred to the above method embodiments, and will not be repeated here.

[0188] In a possible implementation manner, the first determining module is used to:

[0189] Determine a target period in each reference period when the current monitoring data is within a set range;

[0190] The state of charge of each battery cell in the reference period is determined according to the voltage monitoring data of each battery cell in the target period and the mapping relationship between the battery state of charge and the open circuit voltage.

[0191] In a possible implementation manner, the second determining module is used to:

[0192] Determine a reference state of charge according to the median of the states of charge of all battery cells in a reference period;

[0193] According to the difference between the state of charge of each battery cell in the reference period and the reference state of charge, an outlier feature of the state of charge of each battery cell in the reference period is determined.

[0194] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can be referred to the above method embodiments, and will not be repeated here.

[0195] The battery self-discharge monitoring device of the disclosed embodiment first obtains the voltage monitoring data and the current monitoring data of each battery cell, then selects the target time period from the reference time period according to the current monitoring data of the battery cell, and obtains the corresponding state of charge based on the voltage monitoring data of the target time period; then determines the outlier characteristics of the state of charge of the battery cell in multiple reference time periods according to the state of charge; finally, based on the outlier characteristics of the state of charge of the battery in multiple reference time periods, the self-discharge level of the battery is monitored through a self-discharge monitoring model, which not only improves the timeliness and accuracy of the battery self-discharge monitoring, but also realizes the classification of the severity of the battery self-discharge, and provides support and basis for taking different countermeasures based on the battery self-discharge level.

[0196] Fig. 9 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Fig. 9 The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0197] like Fig. 9As shown, the electronic device 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .

[0198] The processing component 902 generally controls the overall operation of the electronic device 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.

[0199] The memory 904 is configured to store various types of data to support operations on the electronic device 900. Examples of such data include instructions for any application or method operating on the electronic device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0200] The power supply component 906 provides power to the various components of the electronic device 900. The power supply component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 900.

[0201] The multimedia component 908 includes a touch display screen that provides an output interface between the electronic device 900 and the user. In some embodiments, the touch display screen may include a liquid crystal display (LCD) and a touch panel (TP). The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front camera and / or a rear camera. When the electronic device 900 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0202] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), and when the electronic device 900 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 904 or sent via the communication component 916.

[0203] In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.

[0204] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0205] The sensor assembly 914 includes one or more sensors for providing various aspects of status assessment for the electronic device 900. For example, the sensor assembly 914 can detect the open / closed state of the electronic device 900, the relative positioning of components, such as the display and keypad of the electronic device 900, and the sensor assembly 914 can also detect the position change of the electronic device 900 or a component of the electronic device 900, the presence or absence of user contact with the electronic device 900, the orientation or acceleration / deceleration of the electronic device 900, and the temperature change of the electronic device 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 914 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0206] The communication component 916 is configured to facilitate wired or wireless communication between the electronic device 900 and other devices. The electronic device 900 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 916 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 916 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0207] In an exemplary embodiment, the electronic device 900 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0208] In an exemplary embodiment, a vehicle is also provided, comprising the electronic device as proposed in the above embodiment.

[0209] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, and the above instructions can be executed by the processor 920 of the electronic device 900 to complete the above method. Optionally, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0210] In an exemplary embodiment, a computer program product is also provided, comprising a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0211] The technical solution disclosed in the present invention first obtains multiple training samples, wherein each training sample includes a labeled self-discharge level and multiple state of charge outlier feature reference values; then the multiple state of charge outlier feature reference values ​​are input into the initial model to obtain the predicted self-discharge level output by the initial model; finally, the initial model is corrected according to the difference between the predicted self-discharge level and the labeled self-discharge level to generate a self-discharge monitoring model. The present invention trains and generates a self-discharge monitoring model that can classify the degree of self-discharge of the battery based on the outlier features of the state of charge of the battery, realizes accurate identification of the battery self-discharge situation based on the self-discharge monitoring model, and at the same time determines the level of battery self-discharge according to the severity of the battery self-discharge, providing support and basis for taking different countermeasures based on the level of battery self-discharge.

[0212] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0213] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0214] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.

[0215] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0216] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0217] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0218] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0219] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. A training method for a self-discharge monitoring model, characterized in that: include: Acquire a plurality of training samples, wherein each of the training samples comprises a labeled self-discharge level and a plurality of state-of-charge outlier feature reference values, and the labeled self-discharge level is determined from the self-discharge level; Inputting a plurality of the state of charge outlier characteristic reference values ​​into an initial model to obtain a predicted self-discharge level output by the initial model, wherein the predicted self-discharge level is determined from the self-discharge levels after the initial model analyzes the plurality of the state of charge outlier characteristic reference values; According to the difference between the predicted self-discharge level and the marked self-discharge level, the initial model is modified to generate a self-discharge monitoring model; The obtaining of multiple training samples comprises: Determine a first numerical range and a second numerical range corresponding to each of the self-discharge levels, wherein the first numerical range is a numerical range of the state of charge outlier characteristic within a set period, and the second numerical range is a numerical range of a rate of change of the state of charge outlier characteristic within the set period; According to the first numerical range and the second numerical range, a plurality of initial sample curves corresponding to each of the self-discharge levels are generated; wherein the initial sample curve is a curve of changes in the outlier characteristic of the state of charge within the set period; Determining initial values ​​of outlier characteristics of the state of charge for a plurality of reference time periods within the set period according to the initial sample curve; Generate a corresponding random number for each of the initial values ​​of the state of charge outlier feature; Adding each of the initial values ​​of the state of charge outlier feature to the corresponding random number to obtain the reference value of the state of charge outlier feature corresponding to each of the reference time periods; The annotated self-discharge levels corresponding to a plurality of the state of charge outlier feature reference values ​​are obtained to generate the training samples.

2. The method according to claim 1, characterized in that Before obtaining the annotated self-discharge levels corresponding to the plurality of state of charge outlier feature reference values, the method further includes: Obtaining true values ​​of outlier characteristics of the state of charge of a plurality of battery cells with normal self-discharge in a plurality of reference time periods of the set cycle; Each of the state of charge outlier feature reference values ​​is added to the state of charge outlier feature true value of the corresponding time period to update the state of charge outlier feature reference value.

3. A method for monitoring battery self-discharge, characterized in that: include: Obtain voltage monitoring data and current monitoring data of each battery cell; Determining the state of charge of each of the battery cells in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data; Determine, according to the state of charge of each battery cell in each reference time period, an outlier feature of the state of charge of each battery cell in each reference time period; Inputting all the state-of-charge outlier features of each of the battery cells into a self-discharge monitoring model to determine a self-discharge level of each of the battery cells; The step of determining the state of charge of each of the battery cells in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data includes: Determine a target time period in which the current monitoring data is within a set range within each reference time period; The state of charge of each battery cell in the reference time period is determined according to the voltage monitoring data of each battery cell in the target time period and the mapping relationship between the state of charge and the open circuit voltage.

4. The method according to claim 3, characterized in that The step of determining the outlier feature of the state of charge of each battery cell in each reference time period according to the state of charge of each battery cell in each reference time period comprises: Determining a reference state of charge according to a median of the states of charge of all the battery cells in the reference time period; The outlier feature of the state of charge of each battery cell in the reference time period is determined according to the difference between the state of charge of each battery cell in the reference time period and the reference state of charge.

5. A training device for a self-discharge monitoring model, characterized in that: include: A first acquisition module is used to acquire a plurality of training samples, wherein each of the training samples includes a labeled self-discharge level and a plurality of state of charge outlier feature reference values, and the labeled self-discharge level is determined from the self-discharge level; A second acquisition module is used to input the plurality of state of charge outlier characteristic reference values ​​into an initial model to obtain a predicted self-discharge level output by the initial model, wherein the predicted self-discharge level is determined from the self-discharge level after the initial model analyzes the plurality of state of charge outlier characteristic reference values; A generating module, configured to modify the initial model according to a difference between the predicted self-discharge level and the marked self-discharge level, so as to generate the self-discharge monitoring model; The obtaining of multiple training samples comprises: Determine a first numerical range and a second numerical range corresponding to each of the self-discharge levels, wherein the first numerical range is a numerical range of the state of charge outlier characteristic within a set period, and the second numerical range is a numerical range of a rate of change of the state of charge outlier characteristic within the set period; According to the first numerical range and the second numerical range, a plurality of initial sample curves corresponding to each of the self-discharge levels are generated; wherein the initial sample curve is a curve of changes in the outlier characteristic of the state of charge within the set period; Determining initial values ​​of outlier characteristics of the state of charge for a plurality of reference time periods within the set period according to the initial sample curve; Generate a corresponding random number for each of the initial values ​​of the state of charge outlier feature; Adding each of the initial values ​​of the state of charge outlier feature to the corresponding random number to obtain the reference value of the state of charge outlier feature corresponding to each of the reference time periods; The annotated self-discharge levels corresponding to a plurality of the state of charge outlier feature reference values ​​are obtained to generate the training samples.

6. A battery self-discharge monitoring device, characterized in that: include: A first acquisition module, used to acquire voltage monitoring data and current monitoring data of each battery cell; A first determination module, configured to determine the state of charge of each of the battery cells in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data; A second determination module, configured to determine, according to the state of charge of each battery cell in each reference time period, an outlier feature of the state of charge of each battery cell in each reference time period; A third determination module, configured to input all the state of charge outlier features of each of the battery cells into a self-discharge monitoring model to determine a self-discharge level of each of the battery cells; The step of determining the state of charge of each of the battery cells in a plurality of reference time periods according to the voltage monitoring data and the current monitoring data includes: Determine a target time period in which the current monitoring data is within a set range within each reference time period; The state of charge of each battery cell in the reference time period is determined according to the voltage monitoring data of each battery cell in the target time period and the mapping relationship between the state of charge and the open circuit voltage.

7. An electronic device, characterized in that: The method comprises a memory, a processor and computer instructions stored in the memory and executable on the processor, wherein when the processor executes the instructions, the method according to any one of claims 1 to 4 is implemented.

8. A vehicle, characterized in that: Comprising the electronic device as claimed in claim 7.

9. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 4 is implemented.

10. A computer program product, characterized in that The method comprises computer instructions which, when executed by a processor, implement the method according to any one of claims 1 to 4.

Images