Vehicle battery system fault early warning method and device and electronic equipment

Abstract

The invention provides a vehicle battery system fault early warning method and device and electronic equipment, and the method comprises the steps: obtaining the 24-hour monitoring data of each single cell in a vehicle battery system, and extracting the target charging data of each single cell in the battery system from the 24-hour monitoring data after the vehicle is parked and powered off; for any single cell, circulating for multiple times based on the Thevenin model of the single cell, and according to the target charging data, applying a least square method to obtain the internal resistance of each single cell; clustering the internal resistance of each single cell in the vehicle battery system obtained for multiple times, and obtaining the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value; and determining whether each single cell is abnormal or not according to the internal resistance classification result of each single cell and the deviation degree from the reference resistance value. Through the above mode, the method can achieve the precise positioning of a fault single cell, achieves the recognition and early warning of a cell with the internal resistance abnormally increased, and improves the operation safety of a vehicle.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery systems, and in particular relates to a vehicle battery system fault warning method, device and electronic equipment. Background Art

[0002] With the current development of world science and technology and the transformation of energy structure, lithium-ion (Li-ion) batteries play an irreplaceable and key role in electric vehicles and energy storage power stations.

[0003] Currently, the more common battery system is composed of thousands or even tens of thousands of battery cells connected in series and parallel internally and externally. Therefore, if any of the cells has capacity decay, or the SOC is too high or too low, the available power of the battery system will be significantly reduced. Therefore, accurately identifying any faulty cell in the battery system and performing related maintenance and repair work is a necessary prerequisite for ensuring the long-term stable operation of the battery system.

[0004] In recent years, due to the rapid development of the number of electric vehicles and energy storage products, fault warning methods for battery system safety have received extensive attention and research. These methods can be divided into three categories according to different principles: empirical models, mechanism models, and data models. The empirical model mainly estimates and compares the battery state based on the collected direct data such as battery voltage, current, temperature, etc. Its main feature is that the model is simple and easy to calculate, but often leads to large errors due to different working conditions. The mechanism model mainly uses an equivalent circuit model to quantify the electrochemical reaction. This method is often a complex calculation process of the battery mechanism, and the battery cell characteristics need to be studied in the early stage, so the calculation accuracy is relatively high. However, since traditional mechanism models often require a large amount of data storage and calculation, they cannot be well applied in industrial products. For data model methods, such as the common feature parameter engineering combined with neural networks to train the model in large quantities, and a large amount of data needs to be provided in the early stage to continuously train the model, the actual application is difficult and is only suitable as a supplementary method for the early warning system. With the rapid development of electrification, lithium iron phosphate batteries are widely favored by the market due to their high safety, low cost, and long life, but this also poses a great challenge to battery safety warning work. Lithium iron phosphate has a very long voltage platform area within the operating voltage range, and the battery voltage has no obvious characteristic changes within this platform. Therefore, it is impossible to accurately identify the battery system status based on the voltage value collected by the system. Summary of the invention

[0005] The present invention provides a vehicle battery system fault early warning method, device and electronic equipment, which solve the problem that the existing voltage value collected by the system cannot accurately identify the battery system status.

[0006] Based on the above purpose, the present invention proposes a vehicle battery system fault warning method, including: obtaining 24h monitoring data of each single cell in the vehicle battery system, and extracting the target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24h monitoring data; for any single cell, applying the least squares method based on the Thevenin model of the single cell according to the target charging data for multiple cycles to obtain the internal resistance of each single cell; clustering the internal resistance of each single cell in the vehicle battery system obtained multiple times, obtaining the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value; determining whether each single cell is abnormal according to the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value.

[0007] Optionally, the target charging data of each single cell in the battery system after the vehicle is parked and powered off is extracted from the 24h monitoring data, including: recording the vehicle data throughout its life cycle; judging the vehicle speed, the current, the charging status and the charging time of each single cell based on the recorded vehicle data, and identifying the time period that meets the charging duration, charging capacity and meets the vehicle charging status; extracting the voltage, current and temperature data of all single cells in the time period from the 24h monitoring data to obtain the target charging data.

[0008] Optionally, before the cycle multiple times of applying the least squares method based on the Thevenin model of the single cell to obtain the internal resistance of each single cell according to the target charging data, includes: obtaining the Thevenin first-order model based on the equivalent circuit model of the single cell, the Thevenin first-order model including: a single cell body, a first resistor connected to the positive electrode of the single cell body, a second resistor and a first capacitor connected in parallel, one end of the second resistor and the first capacitor is connected to the first resistor, and the other end is the positive output end of the single cell, and the negative electrode of the single cell body is the negative output end.

[0009] Optionally, the method of applying the least squares method based on the target charging data to the Thevenin model of the single cell in a cycle multiple times obtains the internal resistance of each single cell, including: applying the least squares method based on the target charging data to obtain the first resistance, the second resistance and the first capacitance in the Thevenin model in a cycle multiple times, and determining the obtained first resistance as the internal resistance of the single cell.

[0010] Optionally, the internal resistance of each single cell in the vehicle battery system obtained multiple times is clustered to obtain the internal resistance classification result of each single cell and the degree of deviation from a reference resistance value, including: determining a reference resistance value characterizing normal internal resistance based on multiple internal resistances of each single cell in the vehicle battery system obtained; clustering the multiple internal resistances of each single cell using a clustering method to divide all the single cells in the vehicle battery system into three categories: cells with large internal resistance, cells with slightly large internal resistance, and cells with normal internal resistance, and determining the degree of deviation of the internal resistance of each single cell from the reference resistance value.

[0011] Optionally, the clustering methods include: kmeans clustering algorithm, FCM clustering algorithm, decision tree, support vector machine, random forest, and logistic regression.

[0012] Optionally, the method of determining whether each single cell is abnormal based on the internal resistance classification result of each single cell and the degree of deviation from a reference internal resistance includes: if the internal resistance classification result of any single cell belongs to a category with a larger internal resistance, and the degree of deviation of the internal resistance of the single cell from the reference internal resistance is greater than a first reference value, then determining that the single cell is abnormal.

[0013] Based on the same inventive concept, the present invention also proposes a vehicle battery system fault warning device, including: a data acquisition unit, used to acquire 24-hour monitoring data of each single cell in the vehicle battery system, and extract the target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24-hour monitoring data; an internal resistance calculation unit, used to obtain the internal resistance of each single cell for any single cell, based on the Thevenin model of the single cell, according to the target charging data by applying the least squares method for multiple cycles; a clustering unit, used to cluster the internal resistance of each single cell in the vehicle battery system acquired multiple times, and obtain the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value; a fault detection unit, used to determine whether each single cell is abnormal according to the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value.

[0014] Based on the same inventive concept, the present invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the vehicle battery system fault warning method as described above is implemented.

[0015] Based on the same inventive concept, the present invention also proposes a computer storage medium, in which at least one executable instruction is stored, and the executable instruction enables a processor to execute the vehicle battery system fault warning method as described above.

[0016] From the above, it can be seen that the beneficial effects of the technical solution provided by the present invention are: a vehicle battery system fault warning method, device and electronic equipment provided by the present invention, the method includes: obtaining 24h monitoring data of each single cell in the vehicle battery system, and extracting the target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24h monitoring data; for any single cell, the least squares method is applied based on the Thevenin model of the single cell according to the target charging data to obtain the internal resistance of each single cell in a cycle for multiple times; the internal resistance of each single cell in the vehicle battery system obtained multiple times is clustered to obtain the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value; according to the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value, it is determined whether each single cell is abnormal, and the faulty single cell can be accurately located, and the cell with abnormally increased internal resistance can be identified and warned, thereby improving the safety of vehicle operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic diagram of a vehicle battery system fault warning method according to an embodiment of the present invention;

[0019] Figure 2 is a structural schematic diagram of a Thevenin first-order model of any single cell in an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of the relationship between OCV and SOC of any single cell in an embodiment of the present invention;

[0021] Figure 4 It is a schematic diagram of clustering results of each single cell of an embodiment of the present invention;

[0022] Figure 5 A schematic diagram of the structure of a vehicle battery system fault warning device according to an embodiment of the present invention;

[0023] Figure 6 Schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0025] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present invention do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0026] The embodiment of the present invention implements a vehicle battery system fault warning method, such as Figure 1 As shown, the vehicle battery system fault warning method includes:

[0027] Step S11: Acquire 24-hour monitoring data of each single cell in the vehicle battery system, and extract target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24-hour monitoring data.

[0028] Optionally, the vehicle data is recorded throughout its life cycle; based on the recorded vehicle data, the vehicle speed, current of each battery cell, charging status and charging time are judged, and the time period that meets the charging time, charging power and vehicle charging status is identified; the voltage, current and temperature data of all battery cells within the time period are extracted from the 24h monitoring data to obtain the target charging data. This time period is the stable charging time period of the vehicle battery system.

[0029] Since the Yunzhitong data platform records the vehicle data throughout its life cycle, the data file contains rich and detailed vehicle status. The embodiment of the present invention extracts the available data after slicing from a large number of vehicle data. By judging the current, vehicle speed, charging status, and charging time, the internal resistance warning data that meets the conditions of charging time, charging power, and vehicle charging status can be identified, and the 24h monitoring data after power-off can be continuously extracted. After the time period is identified, the voltage, current, and temperature of all single cells in this time period are extracted and cleaned. The selection of charging time and charging depth is related to the electrochemical characteristics of the batteries used in different vehicles and is not a fixed parameter. For example, some vehicles are charged from 50% to 90%, and some vehicles are charged from 60% to 90%. The vehicle charging status is issued by the battery management system (BMS), and the BMS will determine whether the current vehicle is in a stable charging state.

[0030] Step S12: for any single cell, the internal resistance of each single cell is obtained by applying the least square method based on the Thevenin model of the single cell according to the target charging data in a cycle for multiple times.

[0031] In the embodiment of the present invention, before step S12, the Thevenin first-order model is obtained based on the equivalent circuit model of the single cell. Figure 2 As shown, the Thevenin first-order model includes: a single cell body, a first resistor R0 connected to the positive electrode of the single cell body, a second resistor R1 and a first capacitor C1 connected in parallel, one end of the second resistor R1 and the first capacitor C1 is connected to the first resistor R0, and the other end is the positive output end of the single cell, and the negative electrode of the single cell body is the negative output end. The first resistor R0 is the ohmic resistance of the single cell, the second resistor R1 is the polarization resistance of the single cell, and the first capacitor C1 is the ohmic capacitance of the single cell.

[0032] In the embodiment of the present invention, a performance test is performed on a single cell of known capacity, including an open circuit voltage test at different temperatures and battery state of charge (SOC), a battery feature database is obtained, an open circuit voltage model is established, and the relationship between the actual open circuit voltage (OCV) and the single cell SOC is characterized. The model fitting curve is compared with the actual test OCV. Figure 3 shown.

[0033] Perform Hybrid Pulse Power Characteristic (HPPC) cycle tests on battery cells of known capacity under different temperature environments (T1, T2, T3...) to obtain voltage, current and other data during the test. Extract the HPPC data obtained in the test, extract the current and temperature data in the test result data according to the test requirements of different SOCs and different temperatures in the test outline, and calculate the real SOC value at the same time. Slice the extracted data and calculate according to the characteristic values ​​of current mutation and voltage mutation in the test, and you can get the ohmic resistance and polarization resistance values ​​under different temperatures and SOCs. The DC internal resistance under different temperatures, SOCs, and corresponding times can be obtained through the following relationship:

[0034] DCR(T, SOC, t)=(U1-U0) / (I1-I0)

[0035] Among them, DCR represents the DC internal resistance of the battery cell, U1 and I1 are the voltage and current values ​​corresponding to the response time in the HPPC specification, and U0 and I0 are the voltage and current values ​​at the initial moment of the test.

[0036] In step S12, optionally, the least square method is applied multiple times in a cycle according to the target charging data to obtain the first resistance, the second resistance and the first capacitance in the Thevenin model, and the obtained first resistance is determined as the internal resistance of the single cell.

[0037] Through the equivalent circuit model (ECM), two equations are listed, which are

[0038] ECM(U L )=U ocv -IR1-U P

[0039] Ud p / dt=Function(τ,I,U,R1,C1)

[0040] The above two equations are solved simultaneously, and after S (Laplace) transformation, R0, R1, C1, τ are finally expressed with measurable data, where τ is the time constant, τ=R1C1, which is related to the electrochemical reaction characteristics during the battery charging and discharging process.

[0041] The parameters are identified by the least square method with the forgetting factor ff. The sliced ​​HPPC test data are respectively substituted into the above relationship for parameter calculation to obtain R0, R1, and C1 after parameter identification. The calculation steps of the least square method with the forgetting factor are as follows:

[0042] (1) Initialize the matrix RCR(k) and the covariance matrix P(k);

[0043] (2) Calculate the RCR(k+1) at the next moment;

[0044] (3) Calculate the relative error e(k+1);

[0045] (4) Calculate the gain matrix K(k+1);

[0046] (5) Calculate the covariance matrix P(k+1);

[0047] (6) looping steps 2-5;

[0048] (7) Identify parameters R0, R1, C1.

[0049] The least square method (also known as the least square method) is a mathematical optimization technique. The best function matching of the data is found by minimizing the sum of squares of the errors. The least square method can be used to easily obtain unknown data and minimize the sum of squares of the errors between the obtained data and the actual data. In the process of algorithm implementation, the sum of squares of the difference between the actual value and the fitting function is minimized as much as possible to achieve the purpose of the best fitting effect.

[0050] Step S13: clustering the internal resistances of the battery cells in the vehicle battery system obtained multiple times, and obtaining the classification results of the internal resistances of the battery cells and the degree of deviation from the reference resistance value.

[0051] Optionally, first determine a reference resistance value characterizing normal internal resistance based on multiple internal resistances of each single cell in the vehicle battery system. The reference resistance value can be set as needed, or the median value of multiple internal resistances of each single cell can be taken, which is not specifically limited here. Then, a clustering method is applied to cluster the multiple internal resistances of each single cell, and all the single cells in the vehicle battery system are divided into three categories: cells with large internal resistance, cells with slightly large internal resistance, and cells with normal internal resistance, and the degree of deviation of the internal resistance of each single cell from the reference resistance is determined. Clustering methods include: kmeans clustering algorithm, FCM (Fuzzy C-means) clustering algorithm, decision tree, support vector machine, random forest, and logistic regression.

[0052] Step S14: determining whether each single cell is abnormal according to the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value.

[0053] If the internal resistance classification result of any single cell belongs to a category with a large internal resistance, and the internal resistance of the single cell deviates from the reference internal resistance by more than a first reference value, it is determined that the single cell is abnormal. Figure 4As shown, the single cells in the vehicle battery system are divided into three categories: 1, 2, and 3, where the first category is a collection of single cells with normal internal resistance, the second category is a collection of single cells with slightly larger internal resistance, and the third category is a collection of single cells with larger internal resistance. The degree of deviation is in μΩ. Figure 4 The internal resistance classification results of the single cells numbered 12 and 24 belong to the third category, and the deviation between the internal resistance and the reference internal resistance is greater than the first reference value, and it is determined that the two single cells numbered 12 and 24 are abnormal. The first reference value can be set as needed and is not specifically limited here.

[0054] The vehicle battery system fault warning method of the embodiment of the present invention calculates the internal resistance of all single cells in the battery system and accurately locates the faulty single cells; the update frequency is high to meet the actual use conditions of buses. When the vehicle returns to the depot after charging and then shuts down, it can also be monitored 24 hours a day to complete the safety warning of the vehicle at the cell level. Since the working conditions after charging are consistent, the embodiment of the present invention significantly improves the accuracy of the battery system fault warning;

[0055] The vehicle battery system fault warning method of the embodiment of the present invention does not require additional detection equipment, and the equivalent circuit model has strong applicability. Different from the real-time calculation method of SOC and SOH under driving state, the embodiment of the present invention identifies and extracts data that meets the internal resistance warning calculation conditions based on the data monitored by the cloud platform 24h, which can greatly reduce the amount of data calculation, can be used on the original vehicle terminal, and can also be applied to BMS, vehicle terminal, cloud platform, etc.

[0056] In summary, the vehicle battery system fault warning method of the embodiment of the present invention obtains 24h monitoring data of each single cell in the vehicle battery system, and extracts the target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24h monitoring data; for any single cell, the least squares method is applied based on the Thevenin model of the single cell according to the target charging data for multiple cycles to obtain the internal resistance of each single cell; the internal resistance of each single cell in the vehicle battery system obtained multiple times is clustered to obtain the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value; whether each single cell is abnormal is determined according to the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value, so as to accurately locate the faulty single cell, identify and warn the cell with abnormally increased internal resistance, and improve the safety of vehicle operation.

[0057] The above specific embodiments of the present invention are described. In some cases, the actions or steps recorded in the embodiments of the present invention can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0058] The embodiment of the present invention also provides a vehicle battery system fault warning device, such as Figure 4 As shown, the vehicle battery system fault warning device includes: a data acquisition unit, an internal resistance calculation unit, a clustering unit and a fault detection unit.

[0059] A data acquisition unit, used to acquire 24h monitoring data of each single cell in the vehicle battery system, and extract target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24h monitoring data;

[0060] An internal resistance calculation unit, used for obtaining the internal resistance of each single cell by applying a least square method based on the Thevenin model of the single cell according to the target charging data for multiple cycles;

[0061] A clustering unit, used to cluster the internal resistance of each single cell in the vehicle battery system obtained multiple times, and obtain the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value;

[0062] The fault detection unit is used to determine whether each single cell is abnormal based on the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value.

[0063] For the convenience of description, the above device is described in terms of functions and is divided into various units and described separately. Of course, when implementing the embodiment of the present invention, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0064] The device of the above embodiment is applied to the corresponding method in the above embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0065] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the above embodiments is implemented.

[0066] An embodiment of the present invention provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the method described in any of the above embodiments.

[0067] Figure 6 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 601, a memory 602, an input / output interface 603, a communication interface 604, and a bus 605. The processor 601, the memory 602, the input / output interface 603, and the communication interface 604 are connected to each other in communication within the device through the bus 605.

[0068] The processor 601 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided by the method embodiment of the present invention.

[0069] The memory 602 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 602 can store an operating system and other application programs. When the technical solution provided by the method embodiment of the present invention is implemented by software or firmware, the relevant program code is stored in the memory 602 and called and executed by the processor 601.

[0070] The input / output interface 603 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0071] The communication interface 604 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0072] The bus 605 includes a path for transmitting information between various components of the device (eg, the processor 601 , the memory 602 , the input / output interface 603 , and the communication interface 604 ).

[0073] It should be noted that, although the above device only shows the processor 601, the memory 602, the input / output interface 603, the communication interface 604 and the bus 605, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present invention, and does not necessarily include all the components shown in the figure.

[0074] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0075] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the scope of protection of this disclosure.

Claims

1. A vehicle battery system fault early warning method, characterized in that: The battery system failure early warning method comprises: Acquire 24h monitoring data of each single cell in the vehicle battery system, and extract target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24h monitoring data; For any single cell, the internal resistance of each single cell is obtained by applying the least square method based on the Thevenin model of the single cell according to the target charging data for multiple cycles; Clustering the internal resistance of each single cell in the vehicle battery system obtained multiple times, obtaining the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value; Whether each battery cell is abnormal is determined based on the internal resistance classification result of each battery cell and the degree of deviation from the reference resistance value.

2. The vehicle battery system fault early warning method according to claim 1, characterized in that: The target charging data of each single cell in the battery system after the vehicle is parked and powered off is extracted from the 24h monitoring data, including: The vehicle data is recorded throughout its life cycle; According to the recorded vehicle data, the vehicle speed, the current of each battery cell, the charging state and the charging time are judged, and the time period that meets the charging time, charging amount and meets the vehicle charging state is identified; The voltage, current and temperature data of all single cells within the time period are extracted from the 24h monitoring data to obtain target charging data.

3. The vehicle battery system fault warning method according to claim 1, characterized in that: Before the cyclic multiple times of applying the least square method based on the Thevenin model of the single cell to obtain the internal resistance of each single cell according to the target charging data, the method includes: A Thevenin first-order model is obtained based on an equivalent circuit model of a single cell, wherein the Thevenin first-order model includes: a single cell body, a first resistor connected to the positive electrode of the single cell body, a second resistor and a first capacitor connected in parallel, wherein one end of the second resistor and the first capacitor is connected to the first resistor, and the other end is the positive output end of the single cell, and the negative electrode of the single cell body is the negative output end.

4. The vehicle battery system fault early warning method according to claim 3, characterized in that: The cycle is repeated multiple times based on the Thevenin model of the single cell and the least square method is applied according to the target charging data to obtain the internal resistance of each single cell, including: The first resistance, the second resistance and the first capacitance in the Thevenin model are obtained by applying the least square method according to the target charging data in a cycle for multiple times, and the obtained first resistance is determined as the internal resistance of the single cell.

5. The vehicle battery system fault early warning method according to claim 1, characterized in that: The step of clustering the internal resistances of the battery cells in the vehicle battery system obtained multiple times to obtain the internal resistance classification results of the battery cells and the degree of deviation from the reference resistance value includes: Determine a reference resistance value representing a normal internal resistance based on multiple internal resistances of each single cell in the vehicle battery system; A clustering method is applied to cluster multiple internal resistances of each single cell, and all single cells in the vehicle battery system are divided into three categories: cells with large internal resistance, cells with slightly large internal resistance, and cells with normal internal resistance. The degree of deviation of the internal resistance of each single cell from the reference resistance is determined.

6. The vehicle battery system fault warning method according to claim 5, characterized in that: The clustering methods include: kmeans clustering algorithm, FCM clustering algorithm, decision tree, support vector machine, random forest, and logistic regression.

7. The vehicle battery system fault warning method according to claim 1, characterized in that: The step of determining whether each single cell is abnormal according to the internal resistance classification result of each single cell and the degree of deviation from the reference internal resistance includes: If the internal resistance classification result of any single cell belongs to a category with a larger internal resistance, and the internal resistance of the single cell deviates from the reference internal resistance by more than a first reference value, it is determined that the single cell is abnormal.

8. A vehicle battery system fault warning device, characterized in that: The vehicle battery system failure warning device comprises: A data acquisition unit, used to acquire 24h monitoring data of each single cell in the vehicle battery system, and extract target charging data of each single cell in the battery system after the vehicle is parked and powered off from the 24h monitoring data; An internal resistance calculation unit, used for obtaining the internal resistance of each single cell by applying a least square method based on the Thevenin model of the single cell according to the target charging data for multiple cycles; A clustering unit, used to cluster the internal resistance of each single cell in the vehicle battery system obtained multiple times, and obtain the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value; The fault detection unit is used to determine whether each single cell is abnormal based on the internal resistance classification result of each single cell and the degree of deviation from the reference resistance value.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images