A power battery safety early warning method and device and a vehicle

Abstract

The application provides a power battery safety early warning method and device and an automobile. The method comprises the following steps: obtaining operation data of a power battery of the automobile; obtaining a voltage increment of a charging process of the power battery of the automobile according to the operation data; calculating an average increment value according to the voltage increment of the charging process; calculating a characteristic value according to the voltage increment of the charging process and the average increment value; and performing early warning on the power battery of the automobile according to the characteristic value. The scheme of the application can identify an abnormal single body in advance, actively take measures, and reduce the proportion of thermal runaway of an electric vehicle.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle technology, and in particular to a power battery safety early warning method, device, and vehicle. Background Technology

[0002] With the increasing sales of new energy vehicles, thermal runaway incidents are also on the rise, highlighting battery safety issues. There is an urgent need for power battery safety early warning systems to identify anomalies before thermal runaway occurs and take timely measures to mitigate the risk. Currently, there are no such early warning devices on the market. Most vehicles report faults through the BMS (Battery Management System), but these faults may not pose a safety risk, only a potential performance degradation. BMS fault alarms are only reported when a certain threshold is reached, lacking flexibility and prone to false alarms. Summary of the Invention

[0003] This invention provides a method, device, and vehicle for early warning of power battery safety, which can identify abnormal cells in advance and take proactive measures to reduce the proportion of thermal runaway in electric vehicles on the market.

[0004] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0005] Obtain operational data of the vehicle's power battery;

[0006] Based on the aforementioned operating data, the voltage increment during the charging process of the vehicle's power battery is obtained;

[0007] Calculate the average increment based on the voltage increment during the charging process;

[0008] Calculate the characteristic value based on the voltage increment during the charging process and the average value of the increment;

[0009] Based on the aforementioned characteristic values, an early warning is issued for the vehicle's power battery.

[0010] Optionally, based on the operational data, the voltage increment of the vehicle's power battery during each charging process is obtained, including:

[0011] The operational data is subjected to abnormal data removal processing to obtain preprocessed data;

[0012] Based on the preprocessed data, the voltage increment of the vehicle's power battery during each charging process is obtained.

[0013] Optionally, based on the preprocessed data, the voltage increment of the vehicle's power battery for each charging process is obtained, including:

[0014] Based on the voltage difference between the nth frame and the 1st frame in the preprocessed data, the voltage increment of the vehicle power battery for each charging process is obtained, where n is a preset positive integer.

[0015] Optionally, based on the voltage increment during the charging process, the average increment is calculated, including:

[0016] Calculate the average value ΔV of the voltage increment of the power battery. avg ;

[0017] Where, ΔV m ΔV represents the voltage increment during the charging process. avg The value is the incremental average, and M is the number of individual battery cells involved in the calculation.

[0018] Optionally, based on the voltage increment during the charging process and the average value of the increment, a characteristic value is calculated, including:

[0019] The absolute value of the difference between the voltage increment during the charging process and the average value of the increment is determined as the characteristic value.

[0020] Optionally, based on the aforementioned characteristic value, a warning is issued for the vehicle's power battery, including:

[0021] When the feature value is greater than a preset value, the feature value is compared with a first preset threshold to obtain a first comparison result;

[0022] Based on the first comparison result, an early warning is issued for the vehicle's power battery.

[0023] Optionally, based on the aforementioned characteristic value, a warning is issued for the vehicle's power battery, including:

[0024] When the feature value is less than a preset value, the feature value is compared with multiple second preset thresholds to obtain multiple second comparison results;

[0025] Based on multiple second comparison results, an early warning is issued for the vehicle's power battery.

[0026] The present invention also provides a power battery safety warning device, comprising:

[0027] The acquisition module is used to acquire the operating data of the vehicle's power battery;

[0028] The processing module is used to obtain the voltage increment of the vehicle power battery during the charging process based on the operating data; calculate the average increment based on the voltage increment; calculate the characteristic value based on the voltage increment and the average increment; and issue an early warning for the vehicle power battery based on the characteristic value.

[0029] The present invention also provides a vehicle including the power battery safety warning device as described above.

[0030] The present invention also provides a computer-readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described above.

[0031] The above-described solution of the present invention has at least the following beneficial effects:

[0032] The above-described solution of the present invention acquires the operating data of the vehicle's power battery; obtains the voltage increment during the charging process of the vehicle's power battery based on the operating data; calculates the average increment based on the voltage increment; calculates a characteristic value based on the voltage increment and the average increment; and provides an early warning for the vehicle's power battery based on the characteristic value. This allows for the early identification of abnormal cells and proactive measures to reduce the proportion of thermal runaway in electric vehicles. Attached Figure Description

[0033] Figure 1 This is a flowchart of a power battery safety early warning method provided in an embodiment of the present invention;

[0034] Figure 2 This is a schematic flowchart of a power battery safety early warning method, which is a specific example of the present invention.

[0035] Figure 3 This is a schematic diagram of feature values ​​for a specific example of the present invention;

[0036] Figure 4 This is a schematic diagram of a power battery safety warning device provided in an embodiment of the present invention. Detailed Implementation

[0037] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0038] like Figure 1 As shown, an embodiment of the present invention proposes a power battery safety early warning method, including:

[0039] Step 11: Obtain the operating data of the vehicle's power battery;

[0040] Step 12: Based on the operating data, obtain the voltage increment during the charging process of the vehicle's power battery;

[0041] Step 13: Calculate the average increment based on the voltage increment during the charging process;

[0042] Step 14: Calculate the characteristic value based on the voltage increment during the charging process and the average value of the increment;

[0043] Step 15: Issue an early warning for the vehicle's power battery based on the aforementioned characteristic values.

[0044] In this embodiment, the operating data of the vehicle's power battery is acquired; based on the operating data, the voltage increment during the charging process of the vehicle's power battery is obtained; based on the voltage increment during the charging process, an average increment value is calculated; based on the voltage increment during the charging process and the average increment value, a characteristic value is calculated; and based on the characteristic value, an early warning is issued for the vehicle's power battery. This allows for the early identification of abnormal cells, reducing the proportion of thermal runaway in electric vehicles.

[0045] In an optional embodiment of the present invention, the operating data of the vehicle power battery includes: voltage data of each frame of a battery cell or parallel unit during vehicle operation and charging; wherein, in the battery system, a cell or parallel unit generally exists as the smallest unit, a cell refers to a single battery cell without any additional components, and a parallel unit is composed of multiple single cells connected and combined through other components. Target data segments are extracted from the power battery operating data: this operating process includes the charging process (the charging process is generally observed using vehicle status indicators, selecting data from the charging indicator code; if there is no status standard, changes in current and SOC can be referenced; as time increases, if current is present, SOC shows a continuous increase, indicating a charging state). Each charging process needs to be saved independently for subsequent staged calculations. The time interval between two adjacent frames of voltage data is 1 second, 5 seconds, and 10 seconds.

[0046] In an optional embodiment of the present invention, step 12 may include:

[0047] Step 121: Perform abnormal data removal processing on the running data to obtain preprocessed data:

[0048] In practice, data such as null values, zero values, or multiple battery cells or parallel units exceeding the normal range of relevant characteristic parameters in the operational data will be removed. During vehicle operation, some abnormal data values ​​may appear due to data upload or wiring harness acquisition, such as null values, zero values, or multiple battery cells or parallel units exceeding the normal range of relevant characteristic parameters (these fixed values ​​vary depending on the parameters of each car manufacturer and model). For example, if at the same time, the voltage of 1 / 3 of the total number of individual cells or parallel units is 6.25V, and then returns to normal, then 6.25V is considered an abnormal value (this value is not unique because the battery management system strategies differ for different car models).

[0049] Step 122: Based on the preprocessed data, obtain the voltage increment ΔV of the vehicle's power battery for each charging process. m ;

[0050] In specific implementation, the voltage increment ΔV of the vehicle's power battery for each charging process is obtained based on the voltage difference between the nth frame and the 1st frame in the preprocessed data. m n is a preset positive integer. Specifically, through ΔV m =V m,n -V1, obtains the voltage increment of the vehicle's power battery during each charging process;

[0051] Where m is the number of a single or parallel unit; n is the time point, n is greater than or equal to 2; ΔV m For voltage increment; V m,n V1 represents the voltage value of battery number m in frame n; V2 represents the voltage value in frame 1.

[0052] In this embodiment, for the same single unit or parallel unit, the voltage difference between the nth frame and the 1st frame is calculated, i.e.: ΔV1=V 1第n帧 -V 1第1帧 ΔV2=V 2第n帧 -V 2第1帧 , ......, ΔV m =V m第n帧 -V m第1帧 (1...m: represents the number of a single unit or parallel unit; n: time, its value is ≥2). In order to make the voltage increment of each single unit or parallel unit comparable, this step uses the voltage of the first frame as the reference throughout the charging process to make the voltage increment of each single unit or parallel unit comparable.

[0053] In an optional embodiment of the present invention, step 13 includes:

[0054] Step 131: Calculate the average increment ΔV based on the voltage increment ΔVm during the charging process. avg ;

[0055] Specifically, through The average value ΔV of the voltage increment of the power battery is calculated. avg ;

[0056] Where, ΔV m ΔV represents the voltage increment during the charging process. avg The value is the incremental average, and M is the number of individual battery cells involved in the calculation.

[0057] In an optional embodiment of the present invention, step 14 includes:

[0058] Step 141: Calculate the characteristic value based on the voltage increment during the charging process and the average value of the increment:

[0059] Step 142: Determine the absolute value of the difference between the voltage increment during the charging process and the average value of the increment as a characteristic value.

[0060] Specifically, through δ=|ΔV m -ΔV avg | Calculate the absolute value of the difference between the voltage increment of each individual or parallel unit and the average increment at the same time to obtain the characteristic value;

[0061] Where, ΔV m ΔV represents the voltage increment during the charging process. avg δ is the incremental average value, and δ is the characteristic value.

[0062] In this embodiment, the incremental average value is selected as the benchmark value to ensure that each feature value is comparable.

[0063] The comparison is made with the characteristic value δ at the same moment, so there is no need to consider the selection range of SOC. More complete data can be obtained, and it is easier to identify abnormal single units or parallel units. As long as the data is not abnormal, the characteristic value of its charging process can be calculated.

[0064] In an optional embodiment of the present invention, step 15 may include:

[0065] Step 151: When the feature value is greater than a preset value, the feature value is compared with a first preset threshold to obtain a first comparison result;

[0066] Step 152: Based on the first comparison result, issue a warning for the vehicle's power battery.

[0067] In specific implementation, a single threshold setting is used. The first preset threshold is mainly set for abnormal vehicles with a large characteristic value (δ). Based on the battery's inherent properties and the vehicle's operating conditions, a threshold for a single process is set. For example, for new models or private vehicles, where user operating conditions are relatively stable and mileage is short, combined with the battery properties of the vehicle, the characteristic value (δ) threshold can be set relatively small, such as 50mV. If the calculated vehicle is an older model or a ride-hailing vehicle, where user operating conditions are more severe and mileage is longer, then the characteristic value (δ) threshold can be set according to different risk levels based on the specific circumstances of the vehicle. For example, low risk can be set to δ≤100mV, medium risk to 100mV<δ≤150mV, and high risk to δ≥150mV. In this case, multiple individual cells or parallel units may be identified as having potential safety risks, which provides a more comprehensive early warning of abnormal individual cells and allows for immediate action. In an optional embodiment of the present invention, step 15 may include:

[0068] Step 153: When the feature value is less than a preset value, the feature value is compared with multiple second preset thresholds to obtain multiple second comparison results;

[0069] Step 154: Based on multiple second comparison results, issue a warning for the vehicle's power battery.

[0070] In practice, multiple threshold comparisons are performed. This threshold setting primarily targets abnormal vehicles where the characteristic value (δ) changes little and cannot be detected by threshold settings calculated in a single charging process. However, it does not rule out the possibility of self-discharge in such cases. The method involves repeating data cleaning, extraction, and calculation steps 1-5. Each individual or parallel unit's calculated characteristic value (δ) is used as a sub-threshold, and the changing trend of multiple sub-thresholds is compared. This is done by using the increasing trend of multiple individual characteristic values ​​(δ) and classifying them into sudden increase and gradual increase types. Sudden increase type: This refers to a significant increase in the characteristic value of the subsequent charging process compared to the previous one. For example, comparing the characteristic value (δ) thresholds of three consecutive charging processes, if the sub-threshold calculated in each charging process increases compared to the previous sub-threshold with an increase ≥30mV, it is considered to meet the sudden increase characteristic. Gradual increase type: Comparing the characteristic value (δ) thresholds of six consecutive charging processes, if the sub-threshold calculated in each charging process increases compared to the previous sub-threshold with an increase [10mV, 30mV), it is considered to meet the gradual increase characteristic.

[0071] The above embodiments of the present invention, by calculating specific data during the operation of the power battery, employ a simple model method that does not require extensive calculations of complex formulas, and can identify abnormal cells in advance, take proactive measures, and reduce the proportion of thermal runaway in electric vehicles.

[0072] like Figure 2 The diagram shows the specific implementation flow of the above method, including:

[0073] Step 21: Extract the target data segment from the power battery operating data:

[0074] time <![CDATA[Monomer voltage V1]]> <![CDATA[Monomer voltage V2]]> <![CDATA[Single - cell voltage V3]]> <![CDATA[Monomer voltage V4]]> <![CDATA[Monomer voltage V5]]> Frame 1 4.012 4.012 4.012 4.012 4.012 Frame 2 4.013 4.013 4.013 4.018 4.013 Frame 3 4.014 4.014 4.014 4.028 4.014 Frame 4 4.015 4.015 4.015 4.033 4.015 Frame 5 4.016 4.016 4.016 4.038 4.016

[0075] The first column represents time, and columns 2-6 represent the individual unit voltage in volts (V).

[0076] Step 22, Remove outlier data:

[0077] During vehicle operation, some abnormal data values ​​may appear due to data upload or wiring harness collection, such as null values, 0 or multiple battery cells or parallel units exceeding the normal range of relevant characteristic parameters (since the parameters of each car manufacturer and each model are different, this fixed value is also different).

[0078] For example, if at the same time, the voltage of 1 / 3 of the individual or parallel units reaches 6.25V and then returns to normal, then 6.25V is an abnormal value (this value is not unique because the battery management system strategies of different models are different).

[0079] Step 23, calculate the voltage increment for each charging process:

[0080] For example, for frame 2

[0081] △V1=(4.013-4.012)*1000=1mV, △V2=(4.013-4.012)*1000=1mV,

[0082] △V3=(4.013-4.012)*1000=1mV, △V4=(4.018-4.012)*1000=6m,

[0083] △V5=(4.013-4.012)*1000=1mV.

[0084] The following table shows all the voltage increments from the operating data:

[0085] time <![CDATA[△V1]]> <![CDATA[△V2]]> <![CDATA[△V3]]> <![CDATA[△V4]]> <![CDATA[△V5]]> Frame 1 0 0 0 0 0 Frame 2 1 1 1 6 1 Frame 3 2 2 2 16 2 Frame 4 3 3 3 21 3 Frame 5 4 4 4 26 4

[0086] The first column represents time, and columns 2-6 represent voltage increments in mV.

[0087] Step 24, calculate the incremental average:

[0088] For example, for frame 2: ΔV avg = (1+1+1+6+1)mV / 5 = 2mV.

[0089] The following table shows the average of all incremental data during the operation:

[0090] time <![CDATA[△V1]]> <![CDATA[△V2]]> <![CDATA[△V3]]> <![CDATA[△V4]]> <![CDATA[△V5]]> <![CDATA[ΔV avg ]]> Frame 1 0 0 0 0 0 0 Frame 2 1 1 1 6 1 2 Frame 3 2 2 2 16 2 4.8 Frame 4 3 3 3 21 3 6.6 Frame 5 4 4 4 26 4 8.4

[0091] The first column represents time, columns 2-6 represent voltage increments, and column 7 represents the average increment, all in mV.

[0092] Step 25, Calculate the eigenvalues:

[0093] For example, for frame 2: δ1=|1-2|=1mV, δ2=|1-2|=1mV, δ3=|1-2|=1mV, δ4=|6-2|=4mV, δ5=|1-2|=1mV.

[0094] The following table and diagram illustrate all the feature values ​​of the running data:

[0095] time <![CDATA[δ1]]> <![CDATA[δ2]]> <![CDATA[δ3]]> <![CDATA[δ4]]> <![CDATA[δ5]]> Frame 1 0 0 0 0 0 Frame 2 1 1 1 4 1 Frame 3 2.8 2.8 2.8 11.2 2.8 Frame 4 3.6 3.6 3.6 14.4 3.6 Frame 5 4.4 4.4 4.4 17.6 4.4

[0096] The first column represents time, and columns 2-6 represent feature values ​​in mV.

[0097] like Figure 3 As shown, V4 exhibits a significant voltage deviation compared to the other cells, while the characteristic values ​​of the other cells are not significantly different. Therefore, V4 is an abnormal cell.

[0098] Step 26, Set the feature value threshold:

[0099] Warnings are issued based on single-time anomaly identification: for new car models or privately owned vehicles, it is recommended to recharge at 20-30mV; for 30-50mV, the module should be replaced.

[0100] For older vehicle models or ride-hailing vehicles, low risk can be set as δ≤100mV, medium risk as 100mV<δ≤150mV, and high risk as δ≥150mV. The measures are to charge the battery for low risk and replace the module for medium and high risk.

[0101] Warnings are issued based on multiple threshold comparisons: Examples of sudden increases: For instance, the characteristic value of V4 is 17.6mV in this calculation, 50mV in the second charge, and 80mV in the third charge. Such a sudden increase in characteristic value is classified as a sudden increase risk.

[0102] Example of a gradually increasing risk: Six charging cycles were selected. For instance, in this calculation, the characteristic value of V4 was 17.6mV. The characteristic value of V4 was 28mV in the second charge, 38mV in the third, 48mV in the fourth, 58mV in the fifth, and 68mV in the sixth. This gradual increase in characteristic value is classified as a gradually increasing risk. For both types of risks, module replacement is recommended.

[0103] The power battery safety early warning method described in the above embodiments of the present invention has a simple early warning model, good effect, and low computational resource consumption. The model can be fully embedded into devices such as battery safety diagnostic instruments, and safety early warning tests can be carried out simultaneously during customer maintenance visits. If an abnormal vehicle is detected through early warning, different handling measures can be taken immediately to avoid repeated appointments to the store, improving customer experience while ensuring vehicle safety. The model can be deployed on a cloud monitoring platform to realize cloud-based early warning. Reporting to after-sales service according to different early warning levels and taking timely handling measures can improve the safety of new energy vehicles, greatly save accident costs, obtain good brand benefits, significantly enhance user confidence, and improve product competitiveness.

[0104] like Figure 4 As shown, this embodiment of the invention also provides a power battery safety warning device 40, comprising:

[0105] The acquisition module 41 is used to acquire the operating data of the vehicle's power battery;

[0106] The processing module 42 is used to obtain the voltage increment of the vehicle power battery during the charging process based on the operating data; calculate the average increment based on the voltage increment; calculate the characteristic value based on the voltage increment and the average increment; and issue an early warning to the vehicle power battery based on the characteristic value.

[0107] Optionally, when the processing module 42 obtains the voltage increment of the vehicle's power battery for each charging process based on the operating data, it is specifically used for:

[0108] The operational data is subjected to abnormal data removal processing to obtain preprocessed data;

[0109] Based on the preprocessed data, the voltage increment of the vehicle's power battery during each charging process is obtained.

[0110] Optionally, when the processing module 42 obtains the voltage increment of each charging process of the vehicle's power battery based on the preprocessed data, it is specifically used for:

[0111] Based on the voltage difference between the nth frame and the 1st frame in the preprocessed data, the voltage increment of the vehicle power battery for each charging process is obtained, where n is a preset positive integer.

[0112] Optionally, the processing module 42 is used to calculate the incremental average value based on the voltage increment during the charging process, specifically for:

[0113] Calculate the average value ΔV of the voltage increment of the power battery. avg ;

[0114] Where, ΔV m ΔV represents the voltage increment during the charging process. avg The value is the incremental average, and M is the number of individual battery cells involved in the calculation.

[0115] Optionally, when the processing module 42 calculates the feature value based on the voltage increment during the charging process and the average increment, it is specifically used for:

[0116] The absolute value of the difference between the voltage increment during the charging process and the average value of the increment is determined as the characteristic value.

[0117] Optionally, when the processing module 42 is used to issue a warning for the vehicle's power battery based on the feature value, it is specifically used for:

[0118] When the feature value is greater than a preset value, the feature value is compared with a first preset threshold to obtain a first comparison result;

[0119] Based on the first comparison result, an early warning is issued for the vehicle's power battery.

[0120] Optionally, when the processing module 42 is used to issue a warning for the vehicle's power battery based on the feature value, it is specifically used for:

[0121] When the feature value is less than a preset value, the feature value is compared with multiple second preset thresholds to obtain multiple second comparison results;

[0122] Based on multiple second comparison results, an early warning is issued for the vehicle's power battery.

[0123] It should be noted that this device is the same as the method described above. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0124] This invention also provides a vehicle, including the power battery safety warning device described above. The warning device is for a vehicle power battery. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0125] This invention also provides a computer-readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the method described above. All implementations in the above method embodiments are applicable to this embodiment and achieve the same technical effects.

[0126] In embodiments of the present invention, operational data of a vehicle's power battery is acquired; based on the operational data, the voltage increment during the charging process of the vehicle's power battery is obtained; based on the voltage increment during the charging process, an average increment value is calculated; based on the voltage increment during the charging process and the average increment value, a characteristic value is calculated; and based on the characteristic value, an early warning is issued for the vehicle's power battery. This allows for the early identification of abnormal cells, enabling proactive measures to reduce the proportion of thermal runaway in electric vehicles.

[0127] The power battery safety early warning method of the present invention has a simple model, does not require a large number of complex formula calculations, occupies less computing resources, and has good effect. The model can be fully embedded into devices such as battery safety diagnostic instruments, and safety early warning tests can be carried out at the same time as customers come to the store for maintenance. If an abnormal vehicle is detected through early warning detection, different handling measures can be taken immediately to avoid repeated appointments to the store, improve the customer experience and ensure vehicle safety.

[0128] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for early warning of power battery safety, characterized in that, include: Acquire the operating data of the vehicle's power battery; the operating data includes: voltage data of each battery cell or parallel unit during vehicle operation and charging. Based on the operational data, the voltage increment of the vehicle power battery during the charging process is obtained, including: performing abnormal data removal processing on the operational data to obtain preprocessed data; obtaining the voltage increment of the vehicle power battery for each charging process based on the preprocessed data; the abnormal data removal processing includes: removing null values, zero values, or data in the operational data that exceed the normal range of relevant characteristic parameters for multiple battery cells or parallel units; for the same battery cell or parallel unit in each charging process, using the voltage of the first frame of the charging process as a reference, calculating the voltage difference between the nth frame and the first frame in the charging process, and using this as the voltage increment of the charging process, where n≥2 is a preset positive integer; Calculate the average increment based on the voltage increment during the charging process, including: Calculate the average value of the voltage increment of the power battery. ; where ΔV m This represents the voltage increment during the charging process. This is the incremental average value, where M is the number of individual battery cells involved in the calculation of the power battery. Calculating a characteristic value based on the voltage increment during the charging process and the average increment includes: determining the absolute value of the difference between the voltage increment during the charging process and the average increment as the characteristic value; The method for issuing a warning for the vehicle power battery based on the characteristic value includes: when the characteristic value is greater than a preset value, comparing the characteristic value with a first preset threshold to obtain a first comparison result; issuing a warning for the vehicle power battery based on the first comparison result; when the characteristic value is less than a preset value, comparing the characteristic value with multiple second preset thresholds to obtain multiple second comparison results; and issuing a warning for the vehicle power battery based on the multiple second comparison results, specifically: taking the characteristic value calculated for each individual cell or parallel unit each time as a sub-threshold, comparing the changing trend of multiple sub-thresholds, and if the characteristic value of three consecutive charging processes increases and the single increase is ≥30mV, the second comparison result is determined to be a sudden increase anomaly; if the characteristic value of six consecutive charging processes increases and the single increase is [10mV, 30mV), the second comparison result is determined to be a slow increase anomaly.

2. A power battery safety early warning device, characterized in that, include: An acquisition module is used to acquire operational data of the vehicle's power battery; the operational data includes: voltage data of each battery cell or parallel unit during vehicle operation and charging; a processing module is used to obtain the voltage increment of the vehicle's power battery during the charging process based on the operational data; calculate the average increment based on the voltage increment; calculate a feature value based on the voltage increment and the average increment; and provide an early warning for the vehicle's power battery based on the feature value; The method for obtaining the voltage increment of the vehicle power battery during the charging process based on the operating data includes: performing abnormal data removal processing on the operating data to obtain preprocessed data; obtaining the voltage increment of the vehicle power battery for each charging process based on the preprocessed data; the abnormal data removal processing includes: removing null values, zero values, or data in the operating data that exceed the normal range of relevant characteristic parameters for multiple battery cells or parallel units; for the same battery cell or parallel unit in each charging process, using the voltage of the first frame of the charging process as a reference, calculating the voltage difference between the nth frame and the first frame in the charging process, and using this difference as the voltage increment of the charging process, where n≥2 is a preset positive integer; Calculate the average increment based on the voltage increment during the charging process, including: Calculate the average value of the voltage increment of the power battery. ; where ΔV m This represents the voltage increment during the charging process. This is the incremental average value, where M is the number of individual battery cells involved in the calculation of the power battery. Calculating a characteristic value based on the voltage increment during the charging process and the average increment includes: determining the absolute value of the difference between the voltage increment during the charging process and the average increment as the characteristic value; The method for issuing a warning for the vehicle power battery based on the characteristic value includes: when the characteristic value is greater than a preset value, comparing the characteristic value with a first preset threshold to obtain a first comparison result; issuing a warning for the vehicle power battery based on the first comparison result; when the characteristic value is less than a preset value, comparing the characteristic value with multiple second preset thresholds to obtain multiple second comparison results; and issuing a warning for the vehicle power battery based on the multiple second comparison results, specifically: taking the characteristic value calculated for each individual cell or parallel unit each time as a sub-threshold, comparing the changing trend of multiple sub-thresholds, and if the characteristic value of three consecutive charging processes increases and the single increase is ≥30mV, the second comparison result is determined to be a sudden increase anomaly; if the characteristic value of six consecutive charging processes increases and the single increase is [10mV, 30mV), the second comparison result is determined to be a slow increase anomaly.

3. A car, characterized in that, Includes the power battery safety warning device as described in claim 2.

4. A computer-readable storage medium, characterized in that, A program or instructions are stored on the readable storage medium, which, when executed by a processor, implement the steps of the method as described in claim 1.

Images