Battery fault detection method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a battery fault detection method and device, equipment and a storage medium. Relates to the technical field of battery detection, and the method comprises the steps: responding to a fault detection instruction of a battery, obtaining a feature vector of each cell in the battery, the feature vector being a vector which is determined according to a resistance parameter and a reactance parameter and is used for representing the internal electrical characteristics of the cell; and if the feature vectors of the battery cells are outlier vectors, determining that the battery state of the battery is a fault state. The method is used for improving the accuracy of battery fault identification.

Description

Technical Field

[0001] This application relates to the field of battery testing technology, and in particular to a method, apparatus, device and storage medium for detecting battery faults. Background Technology

[0002] As the core power source for new energy vehicles, the health of lithium-ion batteries directly impacts the vehicle's range, power performance, and safety. To ensure normal battery operation, traditional battery management systems (BMS) typically rely on monitoring conventional parameters such as voltage, temperature, and current.

[0003] However, in practical applications, vehicles inevitably encounter various mechanical stresses, such as severe vibrations and bottom scrapes, which can lead to internal battery damage (such as separator rupture or electrode micro-short circuits). Because traditional BMS systems rely solely on monitoring routine parameters, they may still classify a damaged battery as being in normal operating condition, resulting in low accuracy in identifying battery faults. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for detecting battery faults, in order to improve the accuracy of battery fault identification.

[0005] In a first aspect, embodiments of this application provide a method for detecting battery faults, including:

[0006] In response to a battery fault detection command, a feature vector of each cell in the battery is obtained. The feature vector is a vector used to characterize the internal electrical characteristics of the cell, determined based on resistance parameters and reactance parameters.

[0007] If a cell's feature vector is an outlier, then the battery's state is determined to be faulty.

[0008] In one possible implementation, the method further includes:

[0009] The feature vector of each battery cell is normalized to obtain at least one target vector;

[0010] The at least one target vector is subjected to mean processing to obtain a mean vector;

[0011] For any target vector, if the vector distance between the target vector and the mean vector is greater than a preset distance, then the target vector is determined to be an outlier vector.

[0012] In one possible implementation, the method further includes:

[0013] If no cell's feature vector is an outlier, then the feature vectors of the cells in the battery are discretized to obtain the degree of dispersion of each cell's feature vector.

[0014] The battery state is determined based on the discreteness corresponding to the feature vector of each cell.

[0015] In one possible implementation, determining the battery state based on the discreteness corresponding to the feature vector of each cell includes:

[0016] If the discreteness corresponding to the feature vector of each cell is less than the first discreteness threshold, then the battery state is determined to be healthy.

[0017] If, in the discreteness corresponding to the feature vector of each cell, there exists a target discreteness that is greater than the first discreteness threshold and less than or equal to the second discreteness threshold, then the battery state is determined to be a warning state; the first discreteness threshold is less than the second discreteness threshold.

[0018] In one possible implementation, the fault detection command is triggered in any of the following ways:

[0019] The vehicle acceleration is greater than or equal to a preset acceleration threshold.

[0020] The change in the vehicle's suspension height within a preset time period is greater than or equal to a suspension height change threshold.

[0021] The trajectory of the flying stone was identified from the image data captured by the vehicle-mounted camera.

[0022] The abnormal noise frequency detected in the microphone in the vehicle is lower than a first preset frequency or higher than a second preset frequency; the first preset frequency is lower than the second preset frequency.

[0023] The system detected that the user selected the battery fault detection control on the human-computer interaction interface.

[0024] The user-inputted voice command for battery fault detection was detected.

[0025] In one possible implementation, obtaining the feature vector of each cell in the battery includes:

[0026] For any given battery cell, obtain the resistance and reactance parameters of the battery cell;

[0027] The electrical characteristic parameters of the battery cell are calculated based on the resistance parameters and the reactance parameters; the electrical characteristic parameters include at least one of the following: impedance amplitude, impedance phase, internal temperature of the battery cell, remaining charge of the battery cell, equivalent resistance, equivalent capacitance, and equivalent inductance;

[0028] The relaxation time distribution (DRT) analysis is performed on the resistance parameter and the reactance parameter to determine the relaxation parameter of the cell. The relaxation parameter includes at least one relaxation time and the resistance corresponding to each relaxation time.

[0029] The eigenvector is determined to include at least one of the following: the resistance parameter, the reactance parameter, the electrical characteristic parameter, and the relaxation parameter.

[0030] In one possible implementation, calculating the electrical characteristic parameters of the battery cell based on the resistance parameter and the reactance parameter includes:

[0031] The impedance amplitude is obtained by processing the resistance parameter and the reactance parameter using the amplitude calculation formula.

[0032] The impedance phase is obtained by processing the resistance parameters and the reactance parameters using the phase calculation formula.

[0033] The internal temperature of the battery cell is obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset temperature function.

[0034] The remaining charge of the battery cell is obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset charge function.

[0035] By using a preset equivalent circuit model, the resistance parameters and the reactance parameters are fitted to obtain the equivalent resistance, the equivalent capacitance, and the equivalent inductance.

[0036] Secondly, embodiments of this application provide a battery fault detection device, comprising:

[0037] The acquisition module is used to acquire the feature vector of each cell in the battery in response to the battery fault detection command. The feature vector is a vector used to characterize the internal electrical characteristics of the cell, which is determined based on the resistance parameter and reactance parameter.

[0038] The processing module is used to determine the battery state as faulty if there is a cell whose feature vector is an outlier vector.

[0039] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0040] The memory stores computer-executed instructions;

[0041] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0042] Fourthly, embodiments of this application provide a vehicle, including: a vehicle body and electronic equipment as described in the third aspect.

[0043] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0044] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0045] The battery fault detection method, apparatus, device, and storage medium provided in this application include, in response to a battery fault detection command, acquiring the feature vector of each cell in the battery; if any cell's feature vector is an outlier, then the battery state is determined to be a fault state. The feature vector is a vector characterizing the internal electrical characteristics of the cell, determined based on resistance and reactance parameters. By acquiring the feature vectors characterizing the internal electrical characteristics of the cell and identifying outliers, the accuracy of battery fault identification can be improved. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0047] Figure 1 A schematic diagram illustrating the application scenarios provided in the embodiments of this application;

[0048] Figure 2 A flowchart illustrating an embodiment of the battery fault detection method provided in this application;

[0049] Figure 3 A schematic flowchart of Embodiment 2 of the battery fault detection method provided in this application;

[0050] Figure 4 A schematic diagram of the electrochemical impedance spectroscopy testing system provided in the embodiments of this application;

[0051] Figure 5 A schematic diagram of a second-order RC equivalent circuit provided in an embodiment of this application;

[0052] Figure 6 A schematic diagram of relaxation time distribution provided in an embodiment of this application;

[0053] Figure 7A schematic diagram of the Mahalanobis distance distribution provided in the embodiments of this application;

[0054] Figure 8 A flowchart illustrating Embodiment 3 of the battery fault detection method provided in this application;

[0055] Figure 9 A flowchart illustrating an example of a battery fault detection method provided in this application.

[0056] Figure 10 A schematic diagram of the structure of the battery fault detection device provided in the embodiments of this application;

[0057] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0058] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0059] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0060] First, let me explain the terms used in this application:

[0061] Impedance: In AC circuits, impedance is a complex number used to describe the total opposition of the circuit to alternating current. The real part of impedance corresponds to the resistance parameter, representing the portion of electrical energy consumed in the circuit; the imaginary part of impedance corresponds to the reactance parameter, representing the phase difference caused by inductance and capacitance in the circuit.

[0062] Electrochemical impedance spectroscopy (EIS) is an important experimental analytical technique used to study the dynamic behavior and interfacial properties of electrochemical systems, such as batteries.

[0063] Equivalent circuit model: By using a set of idealized circuit elements (such as resistors, capacitors, inductors, voltage sources, and current sources), the behavior of a real circuit or system is simulated and described, enabling a simpler way to understand and predict the electrical characteristics of the system.

[0064] Distribution of Relaxation Times (DRT): A technique used to study the kinetic processes in electrochemical systems. DRT analysis transforms electrochemical impedance spectroscopy (EIS) data into relaxation time distributions to reveal the time constants and relative intensities of different physical and chemical processes within the system.

[0065] Fourier analysis: According to Fourier analysis, any periodic signal can be decomposed into a superposition of a series of sine waves with different frequencies, amplitudes and phases.

[0066] Figure 1 This is a schematic diagram illustrating an application scenario provided in an embodiment of this application. Please refer to [link / reference]. Figure 1 The vehicle can be equipped with a battery controller and a battery. When the battery controller receives a fault detection command from the battery, it can monitor the battery's conventional parameters such as voltage, temperature, and current to determine whether the battery is faulty.

[0067] In related technologies, during actual vehicle operation, vehicles often encounter various mechanical stresses such as severe vibrations and collisions. These mechanical stresses may cause localized damage to the internal structure of the battery, such as micro-tears in the lithium-ion battery separator or localized compression deformation between the positive and negative electrode plates.

[0068] Such localized damage is often highly insidious in its initial stages, potentially causing only minor abnormal changes in current, voltage, or temperature within the battery, far below the safety thresholds set by traditional BMS systems based on conventional parameters such as voltage, temperature, and current. The BMS system may misclassify a faulty battery as normal, thus reducing the accuracy of fault identification.

[0069] To address the aforementioned problems, the inventors considered analyzing feature vectors characterizing the internal electrical properties of battery cells to accurately identify battery faults. Based on this, after numerous experiments, the inventors discovered that the feature vector of each battery cell can be obtained upon responding to a battery fault detection command. This feature vector, determined based on resistance and reactance parameters, characterizes the internal electrical properties of the cell. If a cell's feature vector is identified as an outlier, it indicates that the cell's electrical properties are significantly different from the normal state, thus confirming a battery fault. Based on this, this application proposes a battery fault detection method to improve the accuracy of battery fault identification.

[0070] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0071] Figure 2 This is a flowchart illustrating an embodiment of the battery fault detection method provided in this application. Please refer to [link / reference]. Figure 2 The method includes:

[0072] S201. In response to the battery fault detection command, obtain the feature vector of each cell in the battery.

[0073] The execution subject of this application embodiment can be an electronic device or a battery fault detection device installed in an electronic device. The battery fault detection device can be implemented through software or a combination of software and hardware. The battery fault detection device can be a processor in the electronic device. For ease of understanding, the technical solution of this application will be described below using a battery controller as an example. It should be understood that the battery controller is essentially a hardware carrier that executes the functions of the BMS system and is responsible for the task of detecting battery faults.

[0074] In this step, the battery controller can respond to the battery's fault detection command and obtain the feature vector of each cell in the battery. The feature vector is a vector determined based on resistance and reactance parameters to characterize the internal electrical properties of the cell.

[0075] Optionally, for any given cell, its resistance and reactance parameters can be obtained. In specific implementations, the battery controller, in response to a battery fault detection command, controls an excitation source to generate a pulse current that acts on the cell. Under the influence of this pulse current, the cell generates a response voltage. By performing a discrete Fourier transform on the response voltage and the pulse current, the resistance and reactance parameters of each cell can be obtained. The resistance parameters can be represented by the symbol... It can be indicated that reactance parameters can be expressed using symbols. express.

[0076] In one alternative implementation, the pulsed current generated by the excitation source can be a sinusoidal signal with a wide frequency range, containing sinusoidal signal waves with various frequency components in the frequency domain. Therefore, the resistance parameters at different frequencies can be adopted using { , … } represents the pulse current, where the subscripts f1, f2, and fm are used to represent different frequencies of the pulse current; the reactance parameters at different frequencies can be represented by { , … }express.

[0077] Furthermore, the electrical characteristic parameters of the battery cell can be calculated using resistance and reactance parameters. These electrical characteristic parameters may include at least one of the following: impedance magnitude, impedance phase, internal temperature of the battery cell, remaining charge of the battery cell, equivalent resistance, equivalent capacitance, and equivalent inductance. The impedance magnitude can be represented by the symbol... The impedance phase can be represented by the symbol This indicates that the internal temperature of the battery cell can be represented by the symbol IT, the remaining charge of the battery cell can be represented by the symbol SOC, and the equivalent resistance can be represented by the symbol... The equivalent inductance can be represented by the symbol express.

[0078] Similarly, the impedance amplitude at different frequencies can be expressed as { , … The impedance phase at different frequencies can be represented by {} , … }express.

[0079] It should be noted that since the number and specific parameter values ​​of equivalent resistance, equivalent capacitance, and equivalent inductance are usually determined based on the structure of the specific equivalent circuit model, to maintain consistency and clarity when describing these components, the following can be used: , … } represents the parameter values ​​of different equivalent resistances in the equivalent circuit model, and the subscript m indicates the number of equivalent resistances in the circuit; it can be represented by { , … } represents the parameter values ​​of different equivalent capacitors in the equivalent circuit model, and the subscript n indicates the number of equivalent capacitors in the circuit; it can be represented by { , … } represents the parameter values ​​of different equivalent inductances in the equivalent circuit model, and the subscript is used. This indicates the number of equivalent inductors in the circuit.

[0080] For example, the equivalent circuit model can include three equivalent resistors, with parameter values ​​as follows: , ,as well as The equivalent circuit model can include two equivalent capacitors, with parameter values ​​as follows: and The equivalent circuit model can include two equivalent inductors, with parameter values ​​as follows: and .

[0081] For ease of understanding, , , , , , , The symbols represent the corresponding equivalent elements and the parameter values ​​of those elements, respectively.

[0082] Furthermore, relaxation time distribution (DRT) analysis can be performed on the resistance and reactance parameters to determine the cell's relaxation parameters. These relaxation parameters include at least one relaxation time and the resistance corresponding to each relaxation time. The relaxation parameters can be represented by symbols... express.

[0083] It should be noted that during DRT analysis, the resistance parameters (real part) and reactance parameters (imaginary part) at a single frequency cannot provide information about the relaxation time. To identify different relaxation processes in the system, it is necessary to analyze the resistance parameters across the entire frequency range. , … } and reactance parameters { , … By fitting the resistance and reactance parameters across the entire frequency range, multiple relaxation times and their corresponding resistances within the battery cell can be obtained. Specifically, this can be achieved using { , … } represents the relaxation parameter of the battery cell across the entire frequency range, subscript} , … The time corresponding to the peak value (resistance) of different relaxation times; , … For different resistance values.

[0084] Optionally, the characteristic vector of the battery cell can be determined based on at least one of the resistance parameter, reactance parameter, electrical characteristic parameter, and relaxation parameter.

[0085] For example, a battery may contain 100 cells. The battery controller can, in response to a battery fault detection command, acquire the feature vectors of the 100 cells. For instance, the feature vector X1 of cell 1 could be [...]. , , , The feature vector X2 of cell 2 can be [IT1, SOC1]. , , , [IT2, SOC2], where the subscripts f1 and f2 in the vector indicate that the excitation source emits two pulse currents of different frequencies.

[0086] S202. If there exists a cell whose feature vector is an outlier, then the battery state is determined to be a fault state.

[0087] In this step, outlier detection can be performed on the feature vector of each cell to determine whether there is an outlier vector in the feature vector of each cell. If there is an outlier vector in the feature vector of a cell, the battery state is determined to be faulty.

[0088] Optionally, the criterion for identifying outlier vectors can be a mean-based approach. First, the mean of all feature vectors in the battery cells is calculated, resulting in a mean vector. Then, the vector distance between each feature vector and the mean vector is calculated. If the vector distance between a feature vector and the mean vector is greater than a preset distance, then that feature vector is considered an outlier. The mean vector can be represented by a symbol... express.

[0089] In one specific implementation, the preset distance can be set according to actual needs. For example, in this process, the preset distance can be set to 3σ (standard deviation), that is, if the vector distance between the feature vector and the mean vector is greater than three times the standard deviation, then the feature vector is considered an outlier vector.

[0090] In one alternative implementation, 3σ is a global criterion for judging multi-dimensional data in the comprehensive feature vector, rather than a single-dimensional standard deviation.

[0091] For example, in 100 battery cells, there exists a feature vector X1 and a mean vector for cell 1. If the vector distance is greater than three times the standard deviation, then the feature vector X1 of cell 1 can be determined to be an outlier vector, and the battery state can be determined to be a fault state.

[0092] In this embodiment, in response to a battery fault detection command, the feature vector of each cell in the battery can be obtained. If the feature vector of a cell is an outlier, the battery state is determined to be a fault state. The feature vector is a vector characterizing the internal electrical characteristics of the cell, determined based on resistance and reactance parameters. In this process, feature vectors characterizing the internal electrical characteristics of the cell can be established based on resistance and reactance parameters, and outlier analysis can be used for fault detection, enabling more accurate identification of abnormal cell behavior and improving the accuracy of battery fault detection.

[0093] exist Figure 2 Based on the illustrated embodiment, the following, in conjunction with Figure 3The detection methods for the aforementioned battery faults will be further explained in detail.

[0094] Figure 3 This is a flowchart illustrating Embodiment Two of the battery fault detection method provided in this application. Please refer to... Figure 3 The method may include:

[0095] S301, in response to a battery fault detection command, obtains the resistance and reactance parameters of any given cell.

[0096] In this step, when the battery controller receives a fault detection command from the battery, it can respond to the fault detection command and obtain the resistance and reactance parameters of any cell in the battery.

[0097] In one alternative implementation, the fault detection command can be triggered in any of the following ways:

[0098] Method (1): The vehicle acceleration is greater than or equal to the preset acceleration threshold.

[0099] Optionally, the preset acceleration can be pre-calibrated. The pre-calibrated acceleration can be the acceleration in the vehicle's forward direction, or the acceleration in any of the X, Y, or Z axes of the vehicle coordinate system. For example, the pre-calibrated acceleration is the acceleration in the vehicle's forward direction, and the preset acceleration threshold is 5 times the gravitational acceleration (5g).

[0100] For example, if the vehicle's acceleration in the forward direction is 6g during driving, which is greater than the preset acceleration threshold of 5g, a fault detection command can be triggered.

[0101] Method (2): The change in vehicle suspension height within a preset time period is greater than or equal to the suspension height change threshold.

[0102] The preset duration and suspension height change threshold can be pre-calibrated. For example, the preset duration is 5 milliseconds (ms), and the preset suspension height change threshold is 5 centimeters (cm).

[0103] For example, if the vehicle's suspension height changes by 6cm within 5 milliseconds, which is greater than the suspension height change threshold of 5cm, a fault detection command can be triggered.

[0104] Method (3): Identify the trajectory of the flying stone from the image data collected by the vehicle-mounted camera.

[0105] In one alternative implementation, a pre-trained visual detection model can be used to process image data captured by the vehicle-mounted camera. If a flying stone trajectory is detected, a fault detection command is triggered. The visual detection model can be obtained by training a neural network model using historical image data captured by the vehicle-mounted camera.

[0106] Method (4): The abnormal noise frequency of the microphone in the vehicle is detected to be less than the first preset frequency or greater than the second preset frequency; the first preset frequency is less than the second preset frequency.

[0107] The first and second preset frequencies can be pre-calibrated. For example, the first preset frequency is 2000 Hz and the second preset frequency is 8000 Hz.

[0108] For example, if the frequency of the microphone in the vehicle is detected to be 1000Hz, which is less than the first preset frequency of 2000Hz, a fault detection command can be triggered while the vehicle is in motion.

[0109] Method (5): Detects the user's selection of the battery fault detection control on the human-computer interaction interface.

[0110] For example, a fault detection command can be triggered in response to a user's selection of a battery fault detection control on the vehicle's human-machine interface (such as the instrument panel or central control screen).

[0111] For example, a user's terminal device, such as a smartphone, can run a battery fault detection application (APP). This application can be used to trigger a fault detection command over the network when the user selects a battery fault detection control through a remote mobile APP.

[0112] Method (6): Detects user-inputted voice command for battery fault detection.

[0113] For example, users can trigger fault detection commands by inputting voice commands. The input voice command could be something like, "Please perform a battery fault detection."

[0114] Optional. The resistance and reactance parameters of the battery cell can be obtained through electrochemical impedance spectroscopy (EIS) testing.

[0115] Figure 4 A schematic diagram of the electrochemical impedance spectroscopy testing system provided in this application embodiment. Please refer to... Figure 4The battery controller can send a trigger command to the excitation source to perform pulse current excitation and a test command to the cell monitoring controller (CMC) to perform EIS testing. The pulse current generated by the excitation source acts on the battery cells. The battery cells form a response voltage under the action of the pulse current. The CMC measures the pulse current and response voltage, and performs a Discrete Fourier Transform (DFT) to obtain the resistance and reactance parameters of each cell, and sends these resistance and reactance parameters to the battery controller.

[0116] In one alternative implementation, the battery controller can directly acquire the resistance and reactance parameters of each cell. Specifically, the battery controller can send a trigger command to an excitation source to initiate pulse current excitation. The pulse current generated by the excitation source acts on the battery cells, causing them to generate a response voltage. The battery controller can directly measure this pulse current and response voltage, and calculate the resistance and reactance parameters of each cell by performing a discrete Fourier transform.

[0117] Optionally, the excitation source can be designed to send multiple pulse currents of different frequencies upon receiving a trigger command. This capability allows the battery controller to utilize the advantages of multiple frequencies simultaneously within an operating cycle, thereby improving battery monitoring and management efficiency.

[0118] For example, when the excitation source receives a trigger command, it can send pulse currents with three different frequencies. These pulse currents act on the battery cells, causing the cells to generate a response voltage. The CMC measures the pulse currents and response voltages and performs a Discrete Fourier Transform to obtain the resistance parameters. , , } and reactance parameters { , , }, f1, f2, and f3 are used to represent three different frequencies of the pulse current; for example, the resistance parameters of cell 1 are { , , }, the reactance parameter is { , , }

[0119] S302. Calculate the electrical characteristic parameters of the battery cell based on the resistance and reactance parameters.

[0120] In this step, the battery controller can calculate the electrical characteristic parameters of the battery cell based on the resistance and reactance parameters at different frequencies. The electrical characteristic parameters may include at least one of the following: impedance amplitude, impedance phase, internal temperature of the battery cell, remaining charge of the battery cell, equivalent resistance, equivalent capacitance, and equivalent inductance.

[0121] In one optional implementation, the impedance amplitude can be obtained by processing the resistance and reactance parameters using an amplitude calculation formula. The amplitude calculation formula can be as shown in formula (1):

[0122] Formula (1)

[0123] For example, the resistance parameter { can be obtained using formula (1) { , , } and reactance parameters { , , The impedance amplitude is obtained by processing the data. , , }; For example, the impedance amplitude of cell 1 is { , , }

[0124] In one alternative implementation, the impedance phase can be obtained by processing the resistance and reactance parameters using a phase calculation formula. The phase calculation formula can be as shown in formula (2):

[0125] Formula (2)

[0126] For example, the resistance parameter { can be obtained using formula (2) { , , } and reactance parameters { , , } is processed to obtain the impedance phase { , , }; For example, the impedance phase of cell 1 is { , , }

[0127] In one optional implementation, the internal temperature of the battery cell can be obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset temperature function. The internal temperature of the battery cell refers to the temperature value obtained by calculating the resistance parameters, reactance parameters, impedance amplitude, and impedance phase at multiple frequencies. The preset temperature function can be as shown in formula (3):

[0128] Formula (3)

[0129] Formula (3) is an algebraic equation, and the coefficients in the algebraic equation can be fitted by the least squares method.

[0130] For example, the resistance parameter { can be obtained using formula (3). , , }, Reactance parameters { , , Impedance amplitude { , , } and impedance phase { , , The internal temperature IT of the battery cell is obtained by processing the cells; for example, the internal temperature of battery cell 1 is IT1.

[0131] In one optional implementation, the remaining battery capacity is obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset charge function. The remaining battery capacity refers to the value obtained by calculating the remaining battery capacity at multiple frequencies using the resistance parameters, reactance parameters, impedance amplitude, and impedance phase. The preset charge function can be as shown in formula (4):

[0132] Formula (4)

[0133] Similarly, formula (4) is an algebraic equation, and the coefficients in the algebraic equation can be fitted by the least squares method.

[0134] For example, the resistance parameter { can be obtained using formula (4) { , , }, Reactance parameters { , , Impedance amplitude { , , } and impedance phase { , , The remaining charge (SOC) of the battery cell is obtained by processing the cells; for example, the remaining charge of battery cell 1 is SOC1.

[0135] In one optional implementation, a preset equivalent circuit model is used to fit the resistance and reactance parameters to obtain equivalent resistance, equivalent capacitance, and equivalent inductance. Specifically, the preset equivalent circuit model can be applied to the measured impedance spectrum data (including resistance and reactance parameters). Optimization algorithms, such as nonlinear least squares or genetic algorithms, are used to continuously adjust the parameter values ​​in the model (i.e., the values ​​of equivalent resistance, equivalent capacitance, and equivalent inductance) to minimize the error between the impedance spectrum data calculated by the preset equivalent circuit model and the actually measured impedance spectrum data.

[0136] It should be noted that if the preset equivalent circuit model only includes resistance and capacitance, but not inductance, then when fitting the resistance and reactance parameters, the result may only include the equivalent resistance and equivalent capacitance, but not the equivalent inductance.

[0137] Figure 5 This is a schematic diagram of a second-order RC equivalent circuit provided in an embodiment of this application. Please refer to... Figure 5 It consists of a resistor and two RC network structures connected in series, and the resistor parameters { , , } and reactance parameters { , , By performing fitting, the equivalent resistance can be obtained. Equivalent resistance Equivalent resistance Equivalent capacitance Equivalent capacitance Where I represents the pulse current; This indicates the port voltage of the battery cell that can be directly measured. This represents the response voltage.

[0138] In an alternative implementation, the pre-defined equivalent circuit model can also incorporate a Warburg element to more accurately simulate diffusion confinement. Therefore, by fitting the resistance and reactance parameters, the resulting electrical characteristic parameters can also include the specific values ​​of the Warburg element.

[0139] For example, the preset equivalent circuit model can consist of a third-order RC circuit and Warburg elements. Specifically, it can consist of a resistor R0, three RC network structures (R1 / C1, R2 / C2, R3 / C3), and Warburg elements connected in series.

[0140] For example, by pre-setting a second-order RC equivalent circuit model, the resistance parameters { , , } and reactance parameters { , , The equivalent resistance is obtained by fitting the data. Equivalent resistance Equivalent resistance Equivalent capacitance Equivalent capacitance For example, the equivalent resistance of cell 1 is { , , }, equivalent contents are { , }

[0141] S303. Perform relaxation time distribution (DRT) analysis on the resistance and reactance parameters to determine the relaxation parameters of the battery cell. The relaxation parameters include at least one relaxation time and the resistance corresponding to each relaxation time.

[0142] In this step, the battery controller can use relaxation time distribution (DRT) analysis to resolve the resistance and reactance parameters in the frequency domain in the time domain, thereby separating and resolving highly overlapping electrochemical processes and determining the cell's relaxation parameters. The relaxation parameters include at least one relaxation time and the resistance corresponding to each relaxation time.

[0143] Figure 6 This is a schematic diagram of a relaxation time distribution provided for an embodiment of this application. Please refer to... Figure 6 The graph illustrates the time required for different relaxation processes within the battery cell (such as lithium-ion movement and chemical reactions), represented by the relaxation time τ on the horizontal axis, and the magnitude of the impact of each relaxation process on the total internal resistance of the cell (the area of ​​the characteristic peak). Each characteristic peak represents a relaxation process; the larger the area of ​​the characteristic peak, the greater the resistance (R) caused by the corresponding relaxation process, and the more significant the impact on the cell's performance. For ease of understanding, the maximum value of the characteristic peak is used to represent the magnitude of the impact of each relaxation process on the total internal resistance of the cell.

[0144] For example, for the resistance parameter { , , } and reactance parameters { , , By performing relaxation time distribution (DRT) analysis, relaxation parameters can be obtained. For example, Figure 6 The relaxation parameters of cell 1 are shown, including { , }

[0145] S304. Determine that the eigenvector includes at least one of the following: resistance parameter, reactance parameter, electrical characteristic parameter, and relaxation parameter.

[0146] In this step, the characteristic vector of the battery cell can be determined based on at least one of the obtained resistance parameters, reactance parameters, electrical characteristic parameters, and relaxation parameters.

[0147] Optionally, the parameter dimensions included in the feature vector can be preset according to actual needs. For example, the feature vector may only include resistance parameters and reactance parameters; or, the feature vector may only include electrical characteristic parameters; or the feature vector may only include resistance parameters, reactance parameters, and relaxation parameters.

[0148] For example, the feature vector of each cell in the battery can be determined to include resistance parameters, reactance parameters, and electrochemical characteristic parameters such as the cell's internal temperature and remaining charge. Among these, the feature vector X1 of cell 1 can be [ , , , The feature vector X2 of [IT1, SOC1] and cell 2 can be [ , , , IT2, SOC2).

[0149] S305. Normalize the feature vector of each cell to obtain at least one target vector.

[0150] Optionally, the feature vector of each cell can be normalized to adjust the values ​​of different features to the same scale, enabling more effective comparison and analysis. Normalization can include min-max normalization and Z-score standardization.

[0151] For example, the feature vectors of 100 battery cells can be normalized to obtain the target vector for each battery cell.

[0152] S306. Perform mean processing on at least one target vector to obtain a mean vector.

[0153] For example, the mean vector can be obtained by averaging 100 target vectors. .

[0154] S307. For any target vector, if the vector distance between the target vector and the mean vector is greater than a preset distance, then the target vector is determined to be an outlier vector.

[0155] Optionally, the vector distance can be the Mahalanobis distance between two vectors. The formula for calculating the Mahalanobis distance is shown in formula (5):

[0156] Formula (5)

[0157] In formula (5), the subscript i is the cell number; X is the target vector of the cell; It is the inverse of the covariance matrix; It is a vector ( The transpose of ).

[0158] Figure 7 This is a schematic diagram of the Mahalanobis distance distribution provided in an embodiment of this application. Please refer to... Figure 7 The diagram shows the locations of 10 battery cells. After normalizing the feature vector X1 of cell 1, the target vector can be obtained. (Point A), based on the target vector With mean vector If the Mahalanobis distance (to the origin O) is greater than 3σ, the target vector can be determined. Let be an outlier vector. Here, σ can take the value 1.

[0159] S308. Based on the fact that the feature vector of the battery cell is an outlier vector, the battery state is determined to be a fault state.

[0160] For example, based on the existence of the target vector of cell 1 The outlier vector indicates that the battery state is a fault state.

[0161] In this embodiment, the battery controller can respond to a battery fault detection command, acquire the resistance and reactance parameters of the battery cells, and calculate the electrical characteristic parameters and relaxation parameters of the cells accordingly. The feature vector of a battery cell can be composed of at least one of the resistance, reactance, electrical characteristic, and relaxation parameters. Normalizing the feature vector of each cell generates a target vector. Furthermore, the target vector can be averaged to obtain a mean vector. If a target vector deviates from the mean vector by a preset distance, the target vector is identified as an outlier. If a cell's feature vector is an outlier, the battery can be determined to be in a fault state. In the above process, by acquiring and analyzing multiple parameters (such as resistance, reactance, electrical characteristic, and relaxation parameters), the state of the battery cells can be more comprehensively reflected, thereby improving the accuracy of battery fault detection.

[0162] Furthermore, the battery fault detection method provided in this application, through normalization and outlier analysis of the cell feature vector, can identify abnormal cells in the early stages of a fault, preventing the fault from escalating and thus improving battery safety. In addition, by setting multiple triggering methods for fault detection commands, battery fault detection can be performed flexibly, allowing the vehicle to initiate the detection process based on different conditions (such as impact from flying stones or severe vibration) and user needs, thereby improving the overall safety and reliability of the vehicle.

[0163] Figure 8 This is a flowchart illustrating Embodiment 3 of the battery fault detection method provided in this application. Please refer to... Figure 8 Based on any of the above embodiments, the battery fault detection method further includes:

[0164] S801. If there is no outlier eigenvector of a cell, then perform discrete analysis on the eigenvectors of the cells in the battery to obtain the discreteness of the eigenvector of each cell.

[0165] In this step, when the feature vector of a cell that does not exist is determined to be an outlier, the feature vector of the cells in the battery can be discretized to determine the degree of deviation of the feature vector of each cell from the mean vector, and thus obtain the discreteness of the feature vector of each cell.

[0166] In one specific implementation, the magnitude of the dispersion can be represented by the Mahalanobis distance between vectors.

[0167] For example, it can be based on the target vector With mean vector The Mahalanobis distance D1 is 1.8σ, and the discreteness of the feature vector X1 is determined to be 1.8σ; it can be determined based on the target vector. With mean vector The Mahalanobis distance D2 is 0.5σ, and the discreteness of the eigenvector X2 is determined to be 1.5σ.

[0168] S802. Determine the battery state based on the discreteness corresponding to the feature vector of each cell.

[0169] In this step, the battery state can be determined based on the discreteness corresponding to the feature vector of each cell.

[0170] The battery status can include healthy status, warning status, and fault status.

[0171] In one optional implementation, if the discreteness corresponding to the feature vector of each cell is less than the first discreteness threshold, then the battery state is determined to be healthy.

[0172] If, in the discreteness corresponding to the feature vector of each cell, there exists a target discreteness that is greater than the first discreteness threshold and less than or equal to the second discreteness threshold, then the battery state is determined to be a warning state; the first discreteness threshold is less than the second discreteness threshold.

[0173] Optionally, the first and second dispersion thresholds can be set according to actual needs, and the second preset distance is less than the preset distance in the above embodiment. For example, the first dispersion threshold can be set to σ, and the second dispersion threshold can be set to 2σ.

[0174] For example, if a battery consists of 100 cells, and the discreteness of the feature vector of each cell is less than σ, then the battery state can be determined to be healthy.

[0175] For example, if a battery consists of 100 cells, and cell 2 has a dispersion of 1.5σ, which is greater than the first dispersion threshold σ and less than the second dispersion threshold 2σ, then the battery state can be determined to be a warning state. Here, 1.5σ is the target dispersion that is greater than the first dispersion threshold σ and less than the second dispersion threshold 2σ.

[0176] In one alternative implementation, when the battery status is determined, corresponding feedback can also be provided to the user based on the different battery statuses.

[0177] For example, when the battery status is determined to be in a warning state, a first alert message can be sent to the user's terminal device. For instance, the first alert message could remind the user to pay attention to battery usage and suggest reducing high-load usage.

[0178] For example, when the battery is determined to be faulty, a second notification message can be sent to the user's terminal device. For instance, the second notification message could be: "The battery is faulty; please have it repaired promptly."

[0179] In an optional implementation, when the battery state is not a fault state, the overall damage level of the battery can also be judged by the distribution entropy. The formula for calculating the distribution entropy is shown in formula (6):

[0180] Formula (6)

[0181] In formula (6), D is the Mahalanobis distance of the battery cell; P(D) is the probability of the Mahalanobis distance D occurring, which can be obtained through data statistics.

[0182] By calculating the distribution entropy of all battery cells, the overall degree of damage to the battery can be determined. Distribution entropy provides a method for quantifying the consistency of the battery's internal state; a higher distribution entropy usually indicates greater variation in cell state, suggesting potential damage or performance degradation. By comparing the determined degree of damage with the distribution entropy of a normal battery, the current health status of the battery can be assessed. If the current battery's distribution entropy is significantly higher than that of a normal battery, it indicates that the battery has undergone a certain degree of damage or degradation, requiring further attention and possible maintenance measures.

[0183] In this embodiment, when the feature vector of a cell is determined to be an outlier, a discrete analysis can be performed on the feature vectors of the cells in the battery to obtain the dispersion of the feature vector of each cell. Based on the dispersion of the feature vector of each cell, the battery state can be determined. In the above process, by calculating the dispersion of the feature vector of each cell, subtle differences between cells can be obtained, potential performance problems or early damage can be identified more accurately, thereby providing a more reliable battery state assessment.

[0184] Figure 9 This is a flowchart illustrating an example of a battery fault detection method provided in this application. Please refer to... Figure 9 ,include:

[0185] S901, multimodal triggering.

[0186] Fault detection commands can be triggered by the vehicle's acceleration being greater than or equal to a preset acceleration threshold, the change in the vehicle's suspension height within a preset time period being greater than or equal to a suspension height change threshold, or by detecting a user-inputted voice command for battery fault detection.

[0187] S902, Electrochemical Impedance Spectroscopy Testing and Data Processing.

[0188] Optionally, resistance and reactance parameters can be obtained through electrochemical impedance spectroscopy. Data processing of the resistance and reactance parameters yields electrical characteristic parameters and relaxation parameters. Electrical characteristic parameters may include at least one of the following: impedance amplitude, impedance phase, internal cell temperature, remaining charge in the cell, equivalent resistance, equivalent capacitance, and equivalent inductance.

[0189] S903, Damage Feature Extraction.

[0190] Optionally, the feature vector may include at least one of the following damage features: resistance parameter, reactance parameter, electrical characteristic parameter, and relaxation parameter.

[0191] S904. Diagnosis and display of damage severity.

[0192] For example, the battery status can be determined to be faulty based on the outlier vectors of existing battery cells. Then, a "Battery faulty, please repair promptly" message can be sent to the user's terminal device. Optionally, the "Battery faulty, please repair promptly" message can also be displayed through the vehicle's human-machine interface to provide multi-faceted reminders to the user.

[0193] The battery fault detection method provided in this application is an example. The specific execution process can be found in the technical solution shown in the above method embodiments. The implementation principle and beneficial effects are similar, and will not be repeated here.

[0194] Figure 10 This is a schematic diagram of the battery fault detection device provided in an embodiment of this application. Please refer to... Figure 10 The battery fault detection device 10 includes:

[0195] The acquisition module 11 is used to acquire the feature vector of each cell in the battery in response to the battery fault detection command. The feature vector is a vector used to characterize the internal electrical characteristics of the cell, which is determined based on the resistance parameter and reactance parameter.

[0196] The processing module 12 is used to determine the battery state as faulty if there is a feature vector of a battery cell that is an outlier vector.

[0197] The battery fault detection device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0198] In one possible implementation, the processing module 12 is further configured to:

[0199] The feature vector of each battery cell is normalized to obtain at least one target vector;

[0200] The at least one target vector is subjected to mean processing to obtain a mean vector;

[0201] For any target vector, if the vector distance between the target vector and the mean vector is greater than a preset distance, then the target vector is determined to be an outlier vector.

[0202] In one possible implementation, the processing module 12 is further configured to:

[0203] If no cell's feature vector is an outlier, then the feature vectors of the cells in the battery are discretized to obtain the degree of dispersion of each cell's feature vector.

[0204] The battery state is determined based on the discreteness corresponding to the feature vector of each cell.

[0205] In one possible implementation, the processing module 12 is specifically used for:

[0206] If the discreteness corresponding to the feature vector of each cell is less than the first discreteness threshold, then the battery state is determined to be healthy.

[0207] If, in the discreteness corresponding to the feature vector of each cell, there exists a target discreteness that is greater than the first discreteness threshold and less than or equal to the second discreteness threshold, then the battery state is determined to be a warning state; the first discreteness threshold is less than the second discreteness threshold.

[0208] In one possible implementation, the fault detection command is triggered in any of the following ways:

[0209] The vehicle acceleration is greater than or equal to a preset acceleration threshold.

[0210] The change in the vehicle's suspension height within a preset time period is greater than or equal to a suspension height change threshold.

[0211] The trajectory of the flying stone was identified from the image data captured by the vehicle-mounted camera.

[0212] The abnormal noise frequency detected in the microphone in the vehicle is lower than a first preset frequency or higher than a second preset frequency; the first preset frequency is lower than the second preset frequency.

[0213] The system detected that the user selected the battery fault detection control on the human-computer interaction interface.

[0214] The user-inputted voice command for battery fault detection was detected.

[0215] In one possible implementation, the acquisition module 11 is specifically used for:

[0216] For any given battery cell, obtain the resistance and reactance parameters of the battery cell;

[0217] The electrical characteristic parameters of the battery cell are calculated based on the resistance parameters and the reactance parameters; the electrical characteristic parameters include at least one of the following: impedance amplitude, impedance phase, internal temperature of the battery cell, remaining charge of the battery cell, equivalent resistance, equivalent capacitance, and equivalent inductance;

[0218] The relaxation time distribution (DRT) analysis is performed on the resistance parameter and the reactance parameter to determine the relaxation parameter of the cell. The relaxation parameter includes at least one relaxation time and the resistance corresponding to each relaxation time.

[0219] The eigenvector is determined to include at least one of the following: the resistance parameter, the reactance parameter, the electrical characteristic parameter, and the relaxation parameter.

[0220] In one possible implementation, the acquisition module 11 is specifically used for:

[0221] The impedance amplitude is obtained by processing the resistance parameter and the reactance parameter using the amplitude calculation formula.

[0222] The impedance phase is obtained by processing the resistance parameters and the reactance parameters using the phase calculation formula.

[0223] The internal temperature of the battery cell is obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset temperature function.

[0224] The remaining charge of the battery cell is obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset charge function.

[0225] By using a preset equivalent circuit model, the resistance parameters and the reactance parameters are fitted to obtain the equivalent resistance, the equivalent capacitance, and the equivalent inductance.

[0226] The battery fault detection device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0227] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Please refer to... Figure 11 The electronic device 20 may include at least one processor 21 and a memory 22. Optionally, the electronic device 20 may also include a communication component 23. The processor 21, the memory 22, and the communication component 23 are connected via a bus 24.

[0228] In the specific implementation process, at least one processor 21 executes computer execution instructions stored in memory 22, causing at least one processor 21 to perform the above-described method.

[0229] The specific implementation process of processor 21 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0230] The electronic device provided in this application embodiment can be a battery controller, or other controllers in the vehicle that can effectively manage and monitor the battery status, such as a vehicle controller, a cockpit domain controller, etc. This solution does not limit the scope of the application.

[0231] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0232] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0233] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0234] This application embodiment also provides a vehicle, including a vehicle body and, as shown in the example, Figure 11 The electronic device shown enables intelligent detection of battery faults through the coordinated operation of its processor, memory, and communication components.

[0235] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0236] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0237] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0238] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0239] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0240] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0241] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0242] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0243] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0244] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for detecting battery faults, characterized in that, include: In response to a battery fault detection command, a feature vector of each cell in the battery is obtained. The feature vector is a vector used to characterize the internal electrical characteristics of the cell, determined based on resistance parameters and reactance parameters. If a cell's feature vector is an outlier, then the battery's state is determined to be faulty.

2. The method according to claim 1, characterized in that, The method further includes: The feature vector of each battery cell is normalized to obtain at least one target vector; The at least one target vector is subjected to mean processing to obtain a mean vector; For any target vector, if the vector distance between the target vector and the mean vector is greater than a preset distance, then the target vector is determined to be an outlier vector.

3. The method according to claim 1 or 2, characterized in that, The method further includes: If no cell's feature vector is an outlier, then the feature vectors of the cells in the battery are discretized to obtain the degree of dispersion of each cell's feature vector. The battery state is determined based on the discreteness corresponding to the feature vector of each cell.

4. The method according to claim 3, characterized in that, Determining the battery state based on the discreteness corresponding to the feature vector of each cell includes: If the discreteness corresponding to the feature vector of each cell is less than the first discreteness threshold, then the battery state is determined to be healthy. If, in the discreteness corresponding to the feature vector of each cell, there exists a target discreteness that is greater than the first discreteness threshold and less than or equal to the second discreteness threshold, then the battery state is determined to be a warning state; the first discreteness threshold is less than the second discreteness threshold.

5. The method according to claim 1 or 2, characterized in that, The fault detection command is triggered in any of the following ways: The vehicle acceleration is greater than or equal to a preset acceleration threshold. The change in the vehicle's suspension height within a preset time period is greater than or equal to a suspension height change threshold. The trajectory of the flying stone was identified from the image data captured by the vehicle-mounted camera. The abnormal noise frequency detected in the microphone in the vehicle is lower than a first preset frequency or higher than a second preset frequency; the first preset frequency is lower than the second preset frequency. The system detected that the user selected the battery fault detection control on the human-computer interaction interface. The user-inputted voice command for battery fault detection was detected.

6. The method according to claim 1 or 2, characterized in that, The step of obtaining the feature vector of each cell in the battery includes: For any given battery cell, obtain the resistance and reactance parameters of the battery cell; The electrical characteristic parameters of the battery cell are calculated based on the resistance parameters and the reactance parameters; the electrical characteristic parameters include at least one of the following: impedance amplitude, impedance phase, internal temperature of the battery cell, remaining charge of the battery cell, equivalent resistance, equivalent capacitance, and equivalent inductance; The relaxation time distribution (DRT) analysis is performed on the resistance parameter and the reactance parameter to determine the relaxation parameter of the cell. The relaxation parameter includes at least one relaxation time and the resistance corresponding to each relaxation time. The eigenvector is determined to include at least one of the following: the resistance parameter, the reactance parameter, the electrical characteristic parameter, and the relaxation parameter.

7. The method according to claim 6, characterized in that, The calculation of the electrical characteristic parameters of the battery cell based on the resistance parameters and the reactance parameters includes: The impedance amplitude is obtained by processing the resistance parameter and the reactance parameter using the amplitude calculation formula. The impedance phase is obtained by processing the resistance parameters and the reactance parameters using the phase calculation formula. The internal temperature of the battery cell is obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset temperature function. The remaining charge of the battery cell is obtained by processing the resistance parameters, reactance parameters, impedance amplitude, and impedance phase using a preset charge function. By using a preset equivalent circuit model, the resistance parameters and the reactance parameters are fitted to obtain the equivalent resistance, the equivalent capacitance, and the equivalent inductance.

8. A battery fault detection device, characterized in that, include: The acquisition module is used to acquire the feature vector of each cell in the battery in response to the battery fault detection command. The feature vector is a vector used to characterize the internal electrical characteristics of the cell, which is determined based on the resistance parameter and reactance parameter. The processing module is used to determine the battery state as faulty if there is a cell whose feature vector is an outlier vector.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A vehicle, characterized in that, include: The vehicle body, and the electronic device as described in claim 9.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images