Method and device for early warning of thermal runaway of power battery

Abstract

The application relates to the technical field of battery management, in particular to a power battery thermal runaway early warning method and device, wherein the method comprises the following steps: acquiring battery charging data of a vehicle; calculating an actual health state of a power battery of the vehicle according to the battery charging data, and calculating an overcurrent ratio of the power battery according to the actual health state; calculating the probability of an abnormal charging segment based on a pre-constructed abnormal probability identification model, and giving a power battery thermal runaway early warning prompt to a user when the probability is greater than a preset early warning threshold. According to the application, the actual health state of the power battery of the vehicle and the overcurrent ratio are calculated, the probability of the abnormal charging segment is calculated based on the pre-constructed abnormal probability identification model, and the power battery thermal runaway early warning prompt is given when the probability is greater than the early warning threshold, so that the real-time performance of the power battery thermal runaway early warning is effectively improved, and the robustness and stability of the power battery are improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of battery management, in particular to a power battery thermal runaway early warning method and device. BACKGROUND

[0002] In the related art, such as CN116176350A, the detected signals can be sent to a judgment module to calculate the rate of change of voltage with time and the rate of change of temperature with time, and when the battery reaches a thermal runaway early warning condition in the current state, a vehicle end alarm is given, and an entire vehicle thermal runaway early warning signal is fed back to a cloud data platform. Through collection and processing of battery temperature, single cell voltage and smoke concentration, a plurality of parameter conditions are set to comprehensively judge the battery thermal runaway state and give graded alarms.

[0003] However, in the related art, the collection and processing of battery temperature, single cell voltage and smoke concentration result in low accuracy when facing real random working conditions, reduce the real-time performance of power battery thermal runaway early warning, and reduce the robustness and stability of the power battery, which needs to be solved urgently. SUMMARY

[0004] The present application is based on the following problems and realizations of the inventors:

[0005] With the popularity of new energy vehicles and the increasing requirements of users on new energy vehicles, in order to solve the range anxiety and charging time anxiety of users on new energy vehicles, the energy of power battery packs is higher and higher, and the charging time is shorter and shorter. High energy of power batteries means that more battery cells are needed for each battery pack, and shorter charging time requires greater charging power. However, high-power charging can accelerate the aging and lithium precipitation of lithium batteries, and aging and lithium precipitation are one of the main causes of thermal runaway of lithium batteries.

[0006] When designing battery packs, lithium battery manufacturers will adjust the charging power as the battery ages. The adjustment of charging power is usually strongly related to the state of health SOH (State of Health) of the battery. The vehicle-mounted BMS (Battery Management System) calculates the current SOH value of the vehicle. However, due to the limitations of hardware conditions, the vehicle cannot store a large amount of data, and the SOH is closely related to the battery management system strategy. To ensure its accuracy, the conditions for triggering the vehicle to update the SOH value are very strict, which may cause the vehicle to not update the SOH value in time, resulting in a large error between the estimated SOH of the battery management system and the real battery state, causing the battery to actually decay but the charging power not to be adjusted in time, thereby indirectly increasing the charging power of the battery, accelerating the aging of the battery, and posing a safety risk.

[0007] The application provides a power battery thermal runaway early warning method and device to solve the problem of low accuracy when facing real random working conditions, reduced real-time power battery thermal runaway early warning, and reduced robustness and stability of the power battery by collecting and processing battery temperature, single cell voltage and smoke concentration in the related art.

[0008] The first aspect of the application provides a power battery thermal runaway early warning method, including the following steps: obtaining battery charging data of a vehicle; calculating the actual health state of the power battery of the vehicle according to the battery charging data, and calculating the overcurrent ratio of the power battery according to the actual health state; calculating the probability of an abnormal charging segment based on a pre-constructed abnormal probability identification model, and giving a power battery thermal runaway early warning prompt to a user when the probability is greater than a preset early warning threshold.

[0009] According to the above technical means, the application embodiment can calculate the actual health state and overcurrent ratio of the power battery of the vehicle, calculate the probability of an abnormal charging segment based on a pre-constructed abnormal probability identification model, and give a power battery thermal runaway early warning prompt when the probability is greater than a preset early warning threshold, effectively improving the real-time power battery thermal runaway early warning, and improving the robustness and stability of the power battery.

[0010] Optionally, in an embodiment of the application, the pre-constructed abnormal probability identification model is trained by testing the damage degree of the battery under different charging rates and extracting at least one charging feature of the battery with a damage degree greater than a preset damage value from the test results.

[0011] According to the above technical means, the application embodiment can pre-construct an abnormal probability identification model, effectively improving the robustness of the power battery thermal runaway early warning.

[0012] Optionally, in an embodiment of the application, the actual health state of the power battery of the vehicle is calculated according to the battery charging data, including: based on the battery charging data, taking the single cell voltage, the temperature corresponding to the single cell and the current of the first row of the charging segment, and the single cell voltage, the temperature corresponding to the single cell and the current of any row; calculating the actual single cell voltage curve at the initial time and the end time respectively, to calculate the first state of charge corresponding to the first row and the second state of charge corresponding to the any row in the charging SOC-OCV curve; calculating the actual health state of the power battery according to the single cell voltage, the temperature corresponding to the single cell and the current of the first row, and the single cell voltage, the temperature corresponding to the single cell and the current of the any row, and the first state of charge and the second state of charge.

[0013] According to the technical means, the application can calculate the actual health state of the power battery according to the battery charging data and the charging segment, and effectively improve the real-time and accuracy of the early warning.

[0014] Optionally, in an embodiment of the application, the calculating the over-current ratio of the power battery according to the actual health state comprises: determining a theoretical current of the power battery according to the actual health state; and calculating the over-current ratio according to the actual current of the power battery and the theoretical current.

[0015] According to the technical means, the application can calculate the over-current ratio according to the actual current and the theoretical current of the power battery, and effectively improve the real-time of the early warning.

[0016] Optionally, in an embodiment of the application, the calculating the probability of the abnormal charging segment based on the pre-constructed abnormal probability identification model comprises: obtaining a median of the over-current ratio in each charging segment according to the over-current ratio; obtaining an input vector according to the median and the charging times, inputting the input vector into the abnormal probability identification model, and outputting the probability of the abnormal charging segment.

[0017] According to the technical means, the application can obtain an input vector according to the median of the over-current ratio in each charging segment and the charging times, input the input vector into the abnormal probability identification model, and obtain the probability of the abnormal charging segment, which effectively improves the robustness of the early warning and the safety of the vehicle.

[0018] The second aspect of the application provides a power battery thermal runaway early warning device, comprising: an acquisition module configured to acquire battery charging data of a vehicle; a calculation module configured to calculate an actual health state of a power battery of the vehicle according to the battery charging data, and calculate an over-current ratio of the power battery according to the actual health state; and a warning module configured to calculate a probability of an abnormal charging segment based on a pre-constructed abnormal probability identification model, and give a power battery thermal runaway early warning prompt to a user when the probability is greater than a preset early warning threshold.

[0019] Optionally, in an embodiment of the application, the pre-constructed abnormal probability identification model is trained by testing the damage degree of the battery under different charging rates and extracting at least one charging feature of the battery whose damage degree is greater than a preset damage value in the test results.

[0020] Optionally, in an embodiment of the present application, the calculating module comprises: an obtaining unit, configured to obtain the cell voltage, the temperature corresponding to the cell and the current of the first row of the charging segment and the cell voltage, the temperature corresponding to the cell and the current of any row based on the battery charging data; a first calculating unit, configured to calculate the actual cell voltage curve at the initial time and the end time respectively, to calculate the initial true first state of charge corresponding to the first row and the second state of charge corresponding to the any row in the charging SOC-OCV curve; and a second calculating unit, configured to calculate the actual health state of the power battery according to the cell voltage, the temperature corresponding to the cell and the current of the first row, the cell voltage, the temperature corresponding to the cell and the current of the any row and the first state of charge and the second state of charge.

[0021] Optionally, in an embodiment of the present application, the calculating module comprises: a first determining unit, configured to determine the theoretical current of the power battery according to the actual health state; and a third calculating unit, configured to calculate the overcurrent ratio according to the actual current of the power battery and the theoretical current.

[0022] Optionally, in an embodiment of the present application, the early warning module comprises: a second determining unit, configured to obtain the median of the overcurrent ratio in each charging segment according to the overcurrent ratio; and an output unit, configured to obtain an input vector according to the median and the charging times, input the input vector into the abnormal probability identification model, and output the probability of the abnormal charging segment.

[0023] An embodiment of the third aspect of the present application provides a vehicle, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the early warning method of power battery thermal runaway as described in the above embodiments.

[0024] An embodiment of the fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the early warning method of power battery thermal runaway as described above.

[0025] The present application has the following beneficial effects:

[0026] (1) The embodiments of the present application can calculate the actual health state of the power battery according to the battery charging data and the charging segment, and effectively improve the real-time performance and accuracy of the early warning.

[0027] (2) The embodiment of the present application can obtain an input vector according to the median of the overcurrent ratio in each charging segment and the charging frequency, input the input vector into an abnormal probability identification model, to obtain the probability of the abnormal charging segment, effectively improving the robustness of the early warning, and improving the safety of the vehicle.

[0028] (3) The embodiment of the present application can calculate the probability of the abnormal charging segment according to the calculation of the actual health state of the power battery of the vehicle and the overcurrent ratio, and based on the pre-constructed abnormal probability identification model, and when the probability is greater than the early warning threshold, the early warning prompt of the power battery thermal runaway is issued, effectively improving the real-time of the power battery thermal runaway early warning, and improving the robustness and stability of the power battery.

[0029] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0030] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0031] Figure 1 A flow chart of a power battery thermal runaway early warning method according to an embodiment of the present application is provided;

[0032] Figure 2 A schematic diagram of the principle of power battery thermal runaway early warning of an embodiment of the present application is provided;

[0033] Figure 3 A schematic diagram of the structure of a power battery thermal runaway early warning device according to an embodiment of the present application is provided;

[0034] Figure 4 A schematic diagram of the structure of a vehicle according to an embodiment of the present application is provided.

[0035] Among them, 10-power battery thermal runaway early warning device; 100-acquisition module, 200-computation module and 300-early warning module; 401-memory, 402-processor 403-communication interface. DETAILED DESCRIPTION

[0036] The embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0037] A method and device for early warning of thermal runaway of a power battery are described below with reference to the accompanying drawings. In view of the problem in the prior art that the accuracy is low when facing real random working conditions, the real-time performance of early warning of thermal runaway of a power battery is reduced, and the robustness and stability of the power battery are reduced, the present application provides a method for early warning of thermal runaway of a power battery. In the method, the actual health status of the power battery of the vehicle can be calculated according to the battery charging data, and the overcurrent ratio of the power battery can be calculated. Based on a pre-constructed abnormal probability identification model, the probability of an abnormal charging segment is calculated, and when the probability is greater than a preset early warning threshold, the user is prompted for early warning of thermal runaway of the power battery, thereby effectively improving the real-time performance of early warning of thermal runaway of the power battery, and improving the robustness and stability of the power battery. Thus, the problem in the prior art that the accuracy is low when facing real random working conditions, the real-time performance of early warning of thermal runaway of a power battery is reduced, and the robustness and stability of the power battery are reduced, etc. are solved.

[0038] Specifically, Figure 1 A flowchart of a method for early warning of thermal runaway of a power battery provided by the present application is shown.

[0039] As Figure 1 shown, the method for early warning of thermal runaway of a power battery includes the following steps:

[0040] In step S101, battery charging data of a vehicle is obtained.

[0041] It can be understood that the battery charging data of the vehicle can be obtained by the present application, for example, the time, temperature, single cell voltage, charging current and charging capacity during battery charging can be obtained, thereby effectively improving the executability of early warning of thermal runaway of a power battery.

[0042] In step S102, the actual health status of the power battery of the vehicle is calculated according to the battery charging data, and the overcurrent ratio of the power battery is calculated according to the actual health status.

[0043] It can be understood that the actual health status of the power battery of the vehicle can be calculated according to the battery charging data, and the overcurrent ratio of the power battery can be calculated according to the actual health status by the present application, thereby effectively improving the accuracy of early warning.

[0044] In one embodiment of this application, calculating the actual health state of the vehicle's power battery based on battery charging data includes: taking the cell voltage, temperature, and current of the first row of the charging segment and the cell voltage, temperature, and current of any row based on the battery charging data; calculating the actual cell voltage curves at the initial and final times respectively, so as to calculate the initial true first state of charge corresponding to the first row and the second state of charge corresponding to any row in the charging SOC-OCV curve; and calculating the actual health state of the power battery based on the cell voltage, temperature, and current of the first row and the cell voltage, temperature, and current of any row, as well as the first and second states of charge.

[0045] For example, embodiments of this application can acquire charging data for each vehicle from cloud data, calculate the charging capacity for each charge using the ampere-hour integration method, and employ a discrete data integration method. Assume there are h rows of charging data, and record the charging time as t1, t2, ..., t... h The currents are denoted as I1, I2, ..., I h The amount of electricity charged is:

[0046]

[0047] Where h represents the number of rows of charging data, I i t represents the charging current. i Indicates charging time.

[0048] Next, in this embodiment of the application, the first row of the charging segment can be used to obtain the individual cell voltage V1, the corresponding temperature T1, and the current I1, and the h-th row of the individual cell voltage V h Temperature T corresponding to the single unit h and current I h Using the charging SOC-OCV curves and battery internal resistance R tested in the following steps, calculate the actual single-cell OCV1 = V1 - I1 × R1 and OCV at the beginning and end, respectively. h =V h -I h ×R h Then use OCV1 and OCV h The initial true SOC1 and SOC are calculated using interpolation in the charging SOC-OCV curve. h The specific formula is as follows:

[0049] SOC h =(OCV) h -V2) / (V1-V2)×(S1-S2)+S2

[0050] Wherein, V1, V2, S1, S2 respectively represent the value in the charging SOC-OCV curve, S1 and V1, S2 and V2 correspond respectively, and V1≤OCV h ≤V2.

[0051] In addition, the monomer battery can be charged in the capacity of:

[0052] Q m =Q1 / (SOC h -SOC1)

[0053] Therefore, the current battery health status of the whole package is calculated, that is:

[0054] SOH= min(Q m ) / Q r ×100%

[0055] Wherein, Q r represents the theoretical rated capacity of the power battery.

[0056] By calculating the actual health status of the power battery, the real-time and accuracy of the early warning are effectively improved.

[0057] Optionally, in an embodiment of the present application, the overcurrent ratio of the power battery is calculated according to the actual health status, comprising: determining the theoretical current of the power battery according to the actual health status; calculating the overcurrent ratio according to the actual current and the theoretical current of the power battery.

[0058] In the actual execution process, the present application embodiment can obtain the cloud each time charging data of each vehicle, wherein the actual current is I1, and the theoretical current is calculated as:

[0059] I0=I×SOH

[0060] Therefore, the overcurrent ratio is calculated:

[0061] P I =I1 / I0-1

[0062] Wherein, when I1 I =0.

[0063] By calculating the overcurrent ratio according to the actual current and the theoretical current of the power battery, the real-time of the early warning is effectively improved.

[0064] In step S103, based on the pre-constructed abnormal probability identification model, the probability of the abnormal charging segment is calculated, and when the probability is greater than the preset early warning threshold, the user is prompted for the early warning of the power battery thermal runaway.

[0065] It can be understood that the embodiments of the present application can calculate the probability of the abnormal charging segment based on the pre-constructed abnormal probability identification model in the following steps, and when the probability is greater than the early warning threshold, the user is prompted for the thermal runaway of the power battery, for example, the power battery thermal runaway early warning prompt of the instrument panel pop-up window, and the alarm sound is emitted in the vehicle, thereby effectively improving the real-time and robustness of the early warning, and improving the safety and reliability of the vehicle, meeting the user's demand for using the vehicle.

[0066] It should be noted that the preset early warning threshold is set by a person skilled in the art according to the actual situation, which is not limited here.

[0067] Optionally, in an embodiment of the present application, the pre-constructed abnormal probability identification model is trained by testing the damage degree of the battery under different charging rates, and extracting at least one charging feature of the battery whose damage degree is greater than the preset damage value in the test results.

[0068] For example, the embodiments of the present application can test the charging SOC-OCV curve of the battery at different temperatures using the same new battery, and calculate the value R(SOC, T, I) of the battery resistance under different SOC, different temperature and different current.

[0069] Firstly, the embodiments of the present application can take x batteries, use the fast charging mode to perform working condition charging and discharging cycle on the batteries, the charging current is always consistent with the initial one, and each charging is sorted by time, and the serial number is marked as 1, 2, …, a in turn. SOH0 is measured and calculated in real time during the test, and when SOH0 is 90%, 80%, 70%, …, respectively, part of the batteries are taken out for disassembly analysis, and the batteries with more serious lithium precipitation are selected.

[0070] Then, the charging data of the selected battery with more serious lithium precipitation is obtained, wherein the actual current of the battery is I, and the calculated theoretical current is:

[0071] I0=I×SOH

[0072] Secondly, the overcurrent ratio is calculated according to the current I and I0:

[0073] P I =I / I0-1

[0074] Wherein, when I I

[0075] Divide SOC into 10 segments [0, 10], [10, 20], …, [90, 100], take the charging data of each time, and calculate the mean or median of the overcurrent ratio P I Ikj ​​wherein k represents the kth charge, and j represents each SOC segment, and j≤m.

[0076] Finally, according to all the overcurrent data of the selected lithium precipitation serious batteries, an n x 11 matrix is obtained, wherein each row is a charge of a battery, and the column is the characteristic value containing the overcurrent proportion P Ikj and the charge number k, the matrix is input into the XGBoost model for training, thereby effectively improving the robustness of the early warning.

[0077] Optionally, in an embodiment of the present application, based on the pre-constructed abnormal probability identification model, the probability of the abnormal charging segment is calculated, including: obtaining the median of the overcurrent proportion in each charging segment according to the overcurrent proportion; obtaining an input vector according to the median and the number of charges; inputting the input vector into the abnormal probability identification model to output the probability of the abnormal charging segment.

[0078] For example, the SOC can be divided into 10 segments [0, 10], [10, 20],..., [90, 100] in the embodiment of the present application, and the charging data of each time is obtained from the cloud, and the average or median of the overcurrent proportion P I of each SOC segment is calculated. Ikj wherein k represents the kth charge, and j represents each SOC segment, and j≤m.

[0079] Next, P Ikj and the number of charges k are combined into a vector, and then the vector is input into the pre-constructed abnormal probability identification model, the label output by the model is recorded, and the number of abnormal charging labels b accumulated by each vehicle is counted, and the probability of the abnormal charging segment is calculated, that is:

[0080] P=b / a×100%

[0081] Furthermore, the probability of the abnormal charging segment, i.e. the probability of the vehicle failure, can set a threshold value for the probability P, and after reaching the threshold value, the vehicle is warned, thereby effectively improving the robustness of the early warning and improving the safety of the vehicle.

[0082] For example, as Figure 2As shown, it is a principle diagram of power battery thermal runaway early warning of one embodiment of the application. First, the embodiment of the application can obtain the battery charging data of the vehicle through the battery management system and upload it to the cloud. Then, the battery charging data of the vehicle can be obtained from the cloud, the actual health status of the power battery of the vehicle is calculated according to the battery charging data, and the overcurrent ratio of the power battery is calculated according to the actual health status. Secondly, an abnormal probability identification model is constructed offline. Finally, the vehicle can calculate the probability of abnormal charging segment based on the battery charging data, and when the probability is greater than the preset warning threshold, the user is prompted for power battery thermal runaway early warning. The warning information can be sent to the vehicle end or after-sales, effectively improving the real-time performance of power battery thermal runaway early warning, and improving the robustness and stability of the power battery.

[0083] The power battery thermal runaway early warning method according to the embodiment of the application can calculate the actual health status of the power battery of the vehicle according to the battery charging data, calculate the overcurrent ratio of the power battery, calculate the probability of abnormal charging segment based on the pre-constructed abnormal probability identification model, and prompt the user for power battery thermal runaway early warning when the probability is greater than the preset warning threshold. The real-time performance of power battery thermal runaway early warning is effectively improved, and the robustness and stability of the power battery are improved. Thus, the problems in the related art that the accuracy is low when facing real random working conditions, the real-time performance of power battery thermal runaway early warning is reduced, and the robustness and stability of the power battery are reduced are solved.

[0084] Secondly, the power battery thermal runaway early warning device according to the embodiment of the application is described with reference to the accompanying drawings.

[0085] Figure 3 It is a block diagram of the power battery thermal runaway early warning device of the embodiment of the application.

[0086] As Figure 3 shown, the power battery thermal runaway early warning device 10 includes an acquisition module 100, a calculation module 200, and a warning module 300.

[0087] Specifically, the acquisition module 100 is configured to acquire the battery charging data of the vehicle.

[0088] The calculation module 200 is configured to calculate the actual health status of the power battery of the vehicle according to the battery charging data, and calculate the overcurrent ratio of the power battery according to the actual health status.

[0089] The warning module 300 is configured to calculate the probability of abnormal charging segment based on the pre-constructed abnormal probability identification model, and prompt the user for power battery thermal runaway early warning when the probability is greater than the preset warning threshold.

[0090] Optionally, in an embodiment of the present application, the pre-constructed abnormal probability identification model is trained by testing the damage degree of the battery under different charging rates and extracting at least one charging feature of the battery whose damage degree is greater than a preset damage value in the test result.

[0091] Optionally, in an embodiment of the present application, the calculation module 200 comprises an acquisition unit, a first calculation unit and a second calculation unit.

[0092] The acquisition unit is configured to acquire the cell voltage, the temperature corresponding to the cell and the current of the first row of the charging segment and the cell voltage, the temperature corresponding to the cell and the current of any row based on the battery charging data.

[0093] The first calculation unit is configured to calculate the actual cell voltage curve at the initial time and the end time respectively, so as to calculate the initial true first state of charge corresponding to the first row and the second state of charge corresponding to any row in the charging SOC-OCV curve.

[0094] The second calculation unit is configured to calculate the actual health state of the power battery according to the cell voltage, the temperature corresponding to the cell and the current of the first row, the cell voltage, the temperature corresponding to the cell and the current of any row, and the first state of charge and the second state of charge.

[0095] Optionally, in an embodiment of the present application, the calculation module 200 comprises a first determination unit and a third calculation unit.

[0096] The first determination unit is configured to determine the theoretical current of the power battery according to the actual health state.

[0097] The third calculation unit is configured to calculate the overcurrent ratio according to the actual current and the theoretical current of the power battery.

[0098] Optionally, in an embodiment of the present application, the early warning module 300 comprises a second determination unit and an output unit.

[0099] The second determination unit is configured to obtain the median of the overcurrent ratio in each charging segment according to the overcurrent ratio.

[0100] The output unit is configured to obtain an input vector according to the median and the number of charges, input the input vector into the abnormal probability identification model, and output the probability of the abnormal charging segment.

[0101] It should be noted that the foregoing explanation and description of the embodiment of the power battery thermal runaway early warning method also apply to the power battery thermal runaway early warning device of this embodiment, which will not be described here again.

[0102] The early warning device for thermal runaway of a power battery provided by the embodiment of the present application can calculate the actual health state of the power battery of the vehicle according to the battery charging data, calculate the overcurrent ratio of the power battery, calculate the probability of an abnormal charging segment based on a pre-constructed abnormal probability identification model, and give a pre-warning prompt for the user when the probability is greater than a preset pre-warning threshold, thereby effectively improving the real-time performance of the early warning for thermal runaway of the power battery and improving the robustness and stability of the power battery. In this way, the problems in the prior art that the accuracy is low when facing real random working conditions due to the collection and processing of the battery temperature, the single battery voltage and the smoke concentration, the real-time performance of the early warning for thermal runaway of the power battery is reduced, and the robustness and stability of the power battery are reduced are solved.

[0103] Figure 4 The vehicle structure schematic diagram provided by the embodiment of the present application. The vehicle can include:

[0104] The memory 401, the processor 402 and the computer program stored in the memory 401 and executable on the processor 402.

[0105] The processor 402 implements the early warning method for thermal runaway of the power battery provided in the above embodiment when executing the program.

[0106] Further, the vehicle further includes:

[0107] The communication interface 403 is used for communication between the memory 401 and the processor 402.

[0108] The memory 401 is used for storing the computer program executable on the processor 402.

[0109] The memory 401 can include a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0110] If the memory 401, the processor 402 and the communication interface 403 are independently implemented, the communication interface 403, the memory 401 and the processor 402 can be connected with each other through a bus and complete the communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 4Only one bus or only one type of bus can exist, however.

[0111] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can complete the communication with each other through an internal interface.

[0112] The processor 402 can be a central processing unit (CPU) or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0113] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the power battery thermal runaway early warning method.

[0114] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or N embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present application and the features of the different embodiments or examples without contradiction.

[0115] In addition, the terms "first", "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0116] Any processes or methods described in the flowcharts or otherwise described herein can be understood as representing a module, segment, or portion of code that includes one or N steps for implementing the specified logical functions or processes. The scope of a preferred embodiment of the present application encompasses combinations of one or more steps of the described processes, even if not explicitly described in the above description, and further includes the performance of functional equivalents thereof, which are understood to be within the scope of the present application.

[0117] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a product of the manufacturing and / or processing, and can be a machine-readable storage medium (alternatively, the medium can be a machine-readable signal medium). The computer-readable medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber (optical), and a portable compact disc read-only memory (CDROM). Note that the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the medium is a suitable medium with the program printed on the medium. The computer-readable medium can be a non-transitory computer-readable medium. The term "non-transitory" can also mean "not entirely transitory" or "not entirely non-transitory." Thus, a non-transitory computer-readable medium does not necessarily mean a medium that is completely non-transitory in its entirety.

[0118] It should be understood that aspects of the present application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, the N steps or processes can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, and in another embodiment, any of the following technologies, or combinations thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0119] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0120] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0121] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A method for early warning of thermal runaway in a power battery, characterized in that, Includes the following steps: Obtain vehicle battery charging data; The actual health status of the vehicle's power battery is calculated based on the battery charging data, and the overcurrent ratio of the power battery is calculated based on the actual health status. as well as Based on a pre-built anomaly probability identification model, the probability of an abnormal charging segment is calculated, and when the probability is greater than a preset warning threshold, a warning prompt for thermal runaway of the power battery is given to the user. The calculation of the probability of abnormal charging segments based on the pre-built anomaly probability identification model includes: The median of the overcurrent ratio in each charging segment is obtained based on the overcurrent ratio. An input vector is obtained based on the median and the number of charging cycles. This input vector is then fed into the anomaly probability identification model, which outputs the probability of the abnormal charging segment.

2. The method according to claim 1, characterized in that, The pre-built anomaly probability identification model is trained by testing the damage level of batteries at different charging rates and extracting at least one charging feature of batteries with damage levels greater than a preset damage value from the test results.

3. The method according to claim 1, characterized in that, The step of calculating the actual health status of the vehicle's power battery based on the battery charging data includes: Based on the battery charging data, the individual cell voltage, temperature, and current of the first row of the charging segment are taken, as well as the individual cell voltage, temperature, and current of any row. The actual single-cell voltage curves at the initial and final times are calculated respectively to calculate the initial true first state of charge corresponding to the first row and the second state of charge corresponding to any row in the charging SOC-OCV curve; The actual health status of the power battery is calculated based on the individual cell voltage, corresponding temperature and current in the first row, and the individual cell voltage, corresponding temperature and current in any row, as well as the first state of charge and the second state of charge.

4. The method according to claim 1, characterized in that, The calculation of the overcurrent ratio of the power battery based on the actual health status includes: The theoretical current of the power battery is determined based on the actual health status. The overcurrent ratio is calculated based on the actual current and the theoretical current of the power battery.

5. A warning device for thermal runaway of a power battery, characterized in that, include: The acquisition module is used to acquire vehicle battery charging data; The calculation module is used to calculate the actual health status of the vehicle's power battery based on the battery charging data, and to calculate the overcurrent ratio of the power battery based on the actual health status. as well as The early warning module is used to calculate the probability of abnormal charging segments based on a pre-built abnormal probability identification model, and to provide the user with an early warning prompt of power battery thermal runaway when the probability is greater than a preset early warning threshold. The calculation of the probability of abnormal charging segments based on the pre-built anomaly probability identification model includes: The median of the overcurrent ratio in each charging segment is obtained based on the overcurrent ratio. An input vector is obtained based on the median and the number of charging cycles. This input vector is then fed into the anomaly probability identification model, which outputs the probability of the abnormal charging segment.

6. The apparatus according to claim 5, characterized in that, The pre-built anomaly probability identification model is trained by testing the damage level of batteries at different charging rates and extracting at least one charging feature of batteries with damage levels greater than a preset damage value from the test results.

7. The apparatus according to claim 5, characterized in that, The computing module includes: The acquisition unit is used to acquire, based on the battery charging data, the individual cell voltage, the temperature of the individual cell, and the current of the first row of the charging segment, and the individual cell voltage, the temperature of the individual cell, and the current of any row. The first calculation unit is used to calculate the actual single-cell voltage curves at the initial time and at the end time, respectively, so as to calculate the initial true first state of charge corresponding to the first row and the second state of charge corresponding to any row in the charging SOC-OCV curve. The second calculation unit is used to calculate the actual health status of the power battery based on the cell voltage, temperature and current of the cell in the first row, and the cell voltage, temperature and current of the cell in any row, as well as the first state of charge and the second state of charge.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the early warning method for thermal runaway of a power battery as described in any one of claims 1-4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the early warning method for thermal runaway of the power battery as described in any one of claims 1-4.

Images