Detection method, electronic equipment and storage medium

Abstract

According to the detection method, the electronic equipment and the storage medium provided by the invention, the first state data of the battery and the second state data of the battery core in the battery are acquired under the condition that the residual capacity of the battery of the vehicle is smaller than the preset capacity threshold value; under the condition that the battery of the vehicle is charged, third state data of the battery in the charging process and fourth state data of a battery cell in the battery are obtained; and inputting the first state data, the second state data, the third state data and the fourth state data into a neural network model to at least determine the target parameter of each battery cell, so that the target parameters of the battery cells can be determined, and the accuracy and reliability of battery detection are effectively improved.

Description

Technical Field

[0001] This application belongs to the field of vehicle inspection technology, and in particular relates to an inspection method, electronic equipment and storage medium. Background Technology

[0002] In the maintenance of new energy vehicles, diagnostic tools interact with the Battery Management System (BMS) via the On-Board Diagnostics (OBD) diagnostic port to obtain battery data and assess battery status. However, existing diagnostic methods have significant drawbacks. Diagnostic tools can only obtain the State of Health (SOH) at the battery pack level, failing to acquire key parameters such as the SOH or internal resistance of individual cells, making it impossible to locate faulty cells. Obtaining cell-level data requires either relying on expensive laboratory equipment, necessitating the transport of the vehicle to the lab, which is time-consuming and labor-intensive, or offline disassembly of the battery pack, which is a destructive operation and further increases cost and difficulty. Summary of the Invention

[0003] In view of this, embodiments of this application provide a detection method, electronic device, and storage medium that can determine the target parameters of a battery cell, thereby effectively improving the accuracy and reliability of battery detection.

[0004] In a first aspect, embodiments of this application provide a detection method, including: When the remaining capacity of the vehicle's battery is less than a preset capacity threshold, the first state data of the battery and the second state data of the cells in the battery are acquired. While the battery of the vehicle is being charged, third state data of the battery during the charging process and fourth state data of the cells in the battery are acquired. The first state data, the second state data, the third state data, and the fourth state data are input into the neural network model to determine at least the target parameters of each battery cell; The battery is tested based on the target parameters of each cell.

[0005] In some embodiments, the target parameter includes: available capacity, and the detection of the battery based on the target parameters of each cell includes: The health status of each cell is determined based on its available capacity and corresponding rated capacity. The battery cells are tested based on the health status of each cell. If the health status of a target cell is lower than the health status threshold, the target cell is determined to be abnormal.

[0006] In some embodiments, the target parameter includes: internal resistance, and the detection of the battery based on the target parameters of each cell includes: The differences between each cell are determined based on the internal resistance of each cell and the corresponding theoretical internal resistance. Each battery cell is tested based on its differences. If the difference of a target battery cell is greater than a difference threshold, the target battery cell is determined to be abnormal.

[0007] In some embodiments, the detection of the battery based on target parameters of each cell includes: Determine the degree of consistency among the target parameters of each battery cell; The battery is tested based on the degree of consistency. If the degree of consistency is less than the degree of consistency threshold, the battery is determined to be normal. If the degree of consistency is greater than or equal to the degree of consistency threshold, the battery is determined to be abnormal.

[0008] In some embodiments, the method further includes: In the event of an anomaly in the target battery cell, the location of the target battery cell is determined; Output the location of the target battery cell.

[0009] In some embodiments, the method further includes: Output suggested information.

[0010] In some embodiments, inputting the first state data, the second state data, the third state data, and the fourth state data into a neural network model to at least determine the target parameters of each battery cell includes: The first state data, the second state data, the third state data, and the fourth state data are input into a neural network model to determine the target parameters of each cell and the target parameters of the battery. The method further includes: determining the health status of the battery based on target parameters of the battery; The battery is tested based on its health status.

[0011] In some embodiments, the method further includes: The first state data, the second state data, the third state data, and the fourth state data are preprocessed, and the preprocessing includes outlier handling and missing value handling.

[0012] Secondly, embodiments of this application provide a detection device, comprising: The first acquisition module is used to acquire first state data of the battery and second state data of the battery cells when the remaining capacity of the vehicle's battery is less than a preset capacity threshold. The second acquisition module is used to acquire the third state data of the battery during the charging process and the fourth state data of the battery cells when the battery of the vehicle is being charged. The input module is used to input the first state data, the second state data, the third state data, and the fourth state data into the neural network model to at least determine the target parameters of each cell; The detection module is used to detect the battery based on the target parameters of each cell.

[0013] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any of the above-mentioned embodiments.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0015] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the electronic device to execute any of the methods described above.

[0016] The beneficial effects of the embodiments in this application compared with the prior art are: This application provides a detection method that, when the remaining capacity of a vehicle's battery is less than a preset capacity threshold, acquires first state data of the battery and second state data of the battery cells; when the vehicle's battery is being charged, acquires third state data of the battery during the charging process and fourth state data of the battery cells; and inputs the first state data, second state data, third state data, and fourth state data into a neural network model to determine at least the target parameters of each cell, thereby effectively improving the accuracy and reliability of battery detection. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic diagram illustrating the implementation process of a detection method provided for the purposes of this application; Figure 2 This is a schematic diagram of the structure of a detection device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0020] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0021] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once detected," or "in response to detection."

[0023] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0025] Based on the problems in related technologies, this application provides a detection method that can be applied to electronic devices, including: mobile phones, tablets, wearable devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), diagnostic instruments, etc. This application does not impose any restrictions on the specific type of electronic device. Figure 1 A schematic diagram illustrating the implementation flow of a detection method provided for the purposes of this application is shown below. Figure 1 As shown, the detection methods include: Step S101: When the remaining capacity of the vehicle's battery is less than a preset capacity threshold, acquire the first state data of the battery and the second state data of the cells in the battery.

[0026] In this embodiment, the vehicle battery refers to the energy storage device that provides power to the vehicle, commonly including lithium-ion batteries. Remaining capacity represents the amount of electricity the battery can currently store and release, usually expressed as a percentage (SOC, State of Charge). For example, 50% SOC means the battery currently has 50% of its rated capacity remaining. A preset capacity threshold is a pre-defined capacity value used to determine the battery's state. When the remaining battery capacity is less than this threshold, the battery is considered to be in a low-charge state, and relevant data is acquired for analysis. For example, the preset capacity threshold can be set to 30% SOC; when the remaining battery capacity is detected to be below 30%, subsequent data acquisition operations are triggered. First-state data refers to data about the overall battery state acquired when the remaining battery capacity is less than the preset capacity threshold, including but not limited to the battery's total voltage, total current, and battery temperature. This data reflects the battery's basic performance in the current low-charge state. A battery cell is the basic building block of a battery. Multiple cells are connected in series or parallel to form a battery pack, and the performance of the cells directly affects the overall performance of the battery pack. The second state data is the data about the state of each cell in the battery, such as cell voltage and cell temperature, obtained when the remaining capacity of the battery is less than a preset capacity threshold. By analyzing this data, we can understand the health status and performance differences of each cell.

[0027] In this embodiment, a battery management system (BMS) equipped on the vehicle can be used. This system can monitor various parameters of the battery in real time. First-state data such as the total voltage, total current, and battery temperature of the battery, as well as second-state data such as the individual cell voltage and individual cell temperature of each cell, can be collected from the BMS.

[0028] In this embodiment of the application, data is acquired when the battery is in a low charge state, which can capture the performance of the battery under a specific working state. At this time, the chemical reactions and physical characteristics inside the battery are different from those under normal charge state. The acquired data can provide an important basis for subsequent analysis of the battery's health status and help to discover potential problems of the battery when the charge is low, such as the risk of over-discharge of the cell and changes in the battery's internal resistance.

[0029] Step S102: While the vehicle's battery is being charged, acquire the third state data of the battery during the charging process and the fourth state data of the battery cells.

[0030] In this embodiment, the charging process refers to the process of replenishing the vehicle battery with electrical energy. During this process, the battery's charge gradually increases, and its parameters such as voltage, current, and temperature change. The third state data refers to data about the overall state of the battery acquired during the charging process, such as the cumulative charge amount, the battery voltage change curve over time, and battery temperature changes. This data helps to understand the battery's performance during charging. The fourth state data refers to data about the state of individual cells within the battery acquired during the charging process, such as changes in individual cell voltage and temperature.

[0031] In this embodiment, after the vehicle is connected to the charging device and charging begins, the charging process of the battery is continuously monitored. The BMS can use built-in sensors and data acquisition modules to record, at preset time intervals, the cumulative charging amount, the battery voltage change curve over time, the battery temperature change, and other third-state data, as well as the individual cell voltage change and individual cell temperature change during the charging process, and other fourth-state data, so that the electronic devices can obtain relevant data from the BMS.

[0032] In this embodiment, the charging process is a crucial stage for battery performance recovery and adjustment. Acquiring data during the charging process allows for a comprehensive understanding of the battery's performance during charging. For example, by analyzing the voltage change curve during charging, it is possible to determine the battery's charging efficiency and whether there are any charging anomalies. By monitoring the temperature changes of the battery cells, it is possible to promptly detect whether the cells are overheating during charging, thus preventing battery performance degradation or safety accidents caused by overheating.

[0033] Step S103: Input the first state data, the second state data, the third state data, and the fourth state data into the neural network model to at least determine the target parameters of each cell.

[0034] In this embodiment, the neural network model is a computational model that simulates the structure of neurons in the human brain, possessing powerful data processing and analysis capabilities. It can automatically learn features and patterns from input data and make predictions and classifications based on the learned knowledge. The neural network model is used to determine the target parameters for each battery cell based on the acquired battery and cell state data. Target parameters refer to key parameters obtained through neural network model analysis that reflect the cell's performance and health status, such as available capacity and internal resistance.

[0035] In this embodiment, a large amount of historical data can be collected, including battery and cell state data under different conditions and corresponding actual target parameters. This data is divided into training, validation, and test sets. A suitable neural network structure is selected, such as a multilayer perceptron, convolutional neural network, or recurrent neural network. In this embodiment, the neural network structure is a multilayer perceptron, which consists of an input layer, multiple hidden layers, and an output layer. The neural network model is trained using the training set, and the connection weights between neurons are continuously adjusted through backpropagation to minimize the error between the model's output and the actual target parameters. During training, a validation set is used to monitor the model's performance and prevent overfitting.

[0036] In this embodiment, the collected four types of state data are organized and preprocessed to remove noise and outliers. The processed data is then input into a pre-trained neural network model. The neural network model extracts and analyzes features from the input data through internal neuron connections and weight adjustments, ultimately outputting the target parameters of each battery cell, such as available capacity and internal resistance.

[0037] In this embodiment, the neural network model possesses powerful nonlinear mapping and adaptive learning capabilities, enabling it to extract key information from complex data and accurately determine the target parameters of the battery cell. Compared to traditional parameter calculation methods, the neural network model can better handle noise and uncertainty in the data, improving the accuracy and reliability of parameter determination. Accurately obtaining the target parameters of the battery cell provides a more precise basis for subsequent battery testing.

[0038] Step S104: The battery is tested based on the target parameters of each cell.

[0039] In this embodiment, the battery is tested using corresponding detection algorithms and standards based on the target parameters of each cell determined by the neural network model, such as available capacity and internal resistance. For example, the state of health (SOH) of the cell is calculated by comparing its available capacity with its rated capacity; the performance change of the cell is evaluated by comparing its internal resistance with its theoretical internal resistance; and the consistency between the target parameters of each cell can be analyzed to determine whether the performance of the cells in the battery pack is balanced.

[0040] The method provided in this application, based on target parameters of the battery cells, can comprehensively and accurately assess the health status and performance of the battery. It can promptly detect abnormal battery cells, such as those with excessively rapid capacity decay or increased internal resistance, providing a scientific basis for battery maintenance and replacement. Simultaneously, by analyzing the consistency between battery cells, the overall performance of the battery pack can be evaluated, avoiding performance degradation and safety hazards caused by cell inconsistencies, extending battery life, and improving vehicle safety and reliability.

[0041] In some embodiments, the target parameter includes: available capacity, and step S104 may include: Step S1041: Determine the health status of each cell based on its available capacity and corresponding rated capacity.

[0042] In this embodiment, rated capacity refers to the amount of electricity that a battery cell can store and release under standard conditions (such as specific temperature and discharge current), as designed. It is an important performance indicator of the battery cell and is usually determined at the factory. State of Health (SOH) measures the degree of degradation of a battery cell's current performance relative to its initial performance, and is generally expressed as a percentage. For example, a battery cell with a state of health of 90% means that its current performance is 90% of its initial performance.

[0043] In this embodiment, the health status of the battery cell is calculated using a formula: SOH=C 可用 / C 额定 ×100%, where C 可用 It is the usable capacity of the battery cell, C 额定 This refers to the rated capacity of the battery cell. For example, if a battery cell has a rated capacity of 50Ah and its usable capacity is tested to be 45Ah, then the state of health (SOH) of the battery cell is 45 / 50 × 100% = 90%.

[0044] Step S1042: The battery cells are tested based on the health status of each cell. If the health status of a target cell is lower than the health status threshold, the target cell is determined to be abnormal.

[0045] In this embodiment, the health status threshold is a pre-set threshold used to determine whether a battery cell is abnormal. When the health status of a battery cell is lower than this threshold, the cell is considered abnormal. For example, the health status threshold can be set to 80%. When a battery cell's health status is detected to be lower than 80%, the cell is determined to be abnormal. The target battery cells are those in the battery pack whose health status is lower than the health status threshold. These cells may have problems such as performance degradation and aging, and require special attention and handling.

[0046] In this embodiment, the calculated health status of each battery cell is compared with a pre-set health status threshold using a comparison algorithm. For example, a conditional statement is set in the program. When the health status of a battery cell is less than the health status threshold, the cell is marked as a target cell and determined to be abnormal. For example, if the health status threshold is 80%, and the health status of a certain battery cell is 75%, then the cell is determined to be a target cell and is abnormal.

[0047] The method provided in this application determines the health status of a battery cell by calculating the ratio of its usable capacity to its rated capacity. This method accurately quantifies the degree of performance degradation of the cell relative to its initial state, avoiding subjective judgment and providing objective and accurate data for subsequent cell testing and maintenance. By comparing the health status of the cell with a preset health status threshold, abnormal cells can be quickly and accurately identified. When the health status of a cell falls below the threshold, it indicates that the cell's performance can no longer meet normal usage requirements, potentially posing safety hazards or affecting the overall performance of the battery pack.

[0048] In this embodiment, after accurately detecting an abnormal cell, corresponding measures can be taken, such as replacing the abnormal cell or performing equalization maintenance on the battery pack. This ensures the performance consistency of each cell within the battery pack, helps improve the overall performance and safety of the battery pack, and reduces battery pack failures and safety accidents caused by differences in cell performance. For example, in a battery pack composed of multiple cells, if there is an abnormal cell with a low health status, this cell may experience excessive current or voltage during the charging and discharging process, leading to overheating, short circuits, and other problems, thus affecting the safety of the entire battery pack. By promptly detecting and handling abnormal cells, this situation can be avoided, improving the reliability and lifespan of the battery pack.

[0049] In some embodiments, the target parameter includes: internal resistance, and step S104 includes: Step S1043: Determine the differences between each cell based on its internal resistance and the corresponding theoretical internal resistance.

[0050] In this embodiment, internal resistance refers to the resistance encountered by the current flowing through the battery cell during charging and discharging. The magnitude of internal resistance affects the battery cell's charging and discharging efficiency, heat generation, and other performance indicators. For example, a battery cell with higher internal resistance generates more heat during charging and discharging, leading to increased energy loss. The theoretical internal resistance is a value calculated based on the battery cell's design parameters and material properties under standard conditions (such as specific temperature, charging and discharging current, and cell state). It serves as a reference value for the battery cell's internal resistance under ideal conditions and is used for comparison with the internal resistance obtained through actual measurement. The difference refers to the difference between the actual internal resistance of each battery cell and its corresponding theoretical internal resistance. This difference reflects the degree of deviation of the actual internal resistance from the theoretical internal resistance and can indicate changes in the battery cell's performance.

[0051] In this embodiment, the theoretical internal resistance value of each battery cell can be obtained from the cell design document or database. The difference between the actual internal resistance and the theoretical internal resistance is calculated to determine the variation of each cell. The calculation formula is: Variation = Actual Internal Resistance - Theoretical Internal Resistance. For example, if the actual internal resistance of a battery cell is 5mΩ and its theoretical internal resistance is 4mΩ, then the variation of that cell is 5 - 4 = 1mΩ.

[0052] Step S1044: Detect each battery cell based on the differences between each battery cell, wherein if the difference between the target battery cell and the target battery cell is greater than the difference threshold, the target battery cell is determined to be abnormal.

[0053] In this embodiment, the difference threshold is a pre-set critical value used to determine whether a battery cell is abnormal. When the difference between the cell's internal resistance and its theoretical internal resistance exceeds this threshold, the cell is considered abnormal. For example, the difference threshold can be set to 10% of the theoretical internal resistance. If the difference between the actual and theoretical internal resistance exceeds this percentage, the cell is determined to be abnormal. The target cells are those in the battery pack whose internal resistance differs from the theoretical internal resistance by more than the difference threshold. These cells may have performance degradation, aging, or manufacturing defects, and require special attention and handling.

[0054] In this embodiment, the difference between the calculated internal resistance of each battery cell and its theoretical internal resistance is compared with a pre-set difference threshold. A conditional judgment method can be used, for example, by setting a judgment statement in the detection program. When the difference is greater than the difference threshold, the battery cell is marked as a target battery cell and determined to be abnormal. For example, the difference threshold is set to 15% of the theoretical internal resistance. If the theoretical internal resistance of a battery cell is 4mΩ, the difference threshold can be 0.6mΩ. If the difference is greater than the difference threshold, the battery cell is determined to be a target battery cell and is abnormal.

[0055] The method provided in this application, by comparing the actual internal resistance of a battery cell with its theoretical internal resistance and calculating the difference, can accurately detect changes in the cell's internal resistance. Changes in internal resistance often reflect changes in the cell's internal structure and electrochemical reactions, such as the degradation of electrode materials and the decomposition of the electrolyte. This precise identification helps to gain a deeper understanding of the cell's performance degradation mechanisms. Comparing the difference between the cell's internal resistance and its theoretical internal resistance with a difference threshold allows for the rapid and accurate screening of abnormal cells. When the difference exceeds the threshold, it indicates that the cell's actual internal resistance deviates from the normal range, potentially indicating performance problems or safety hazards. Timely identification of these abnormal cells helps prevent the entire battery pack from failing due to a single cell's problem. After accurately detecting cells with abnormal internal resistance, corresponding measures can be taken, such as replacing the abnormal cells or performing equalization maintenance on the battery pack, thereby ensuring the performance consistency of each cell within the battery pack. This helps improve the overall performance and safety of the battery pack, reducing battery pack failures and safety accidents caused by differences in cell performance.

[0056] In some embodiments, step S104 may further include: Step S1045: Determine the degree of consistency between the target parameters of each cell.

[0057] In this embodiment, target parameters are key indicators used to evaluate cell performance, such as available capacity, internal resistance, and voltage. These parameters reflect the characteristics of the cell in different aspects. For example, available capacity reflects the cell's energy storage capacity, internal resistance reflects the resistance during charging and discharging, and voltage is related to the cell's state of charge and performance stability. Consistency refers to the degree of closeness or similarity between the target parameters of each cell in the battery pack. High consistency indicates that the performance of each cell is relatively similar, while low consistency indicates significant performance differences between cells. For example, if the available capacity of the cell is used as the target parameter, high consistency means that the available capacities of each cell in the battery pack differ very little.

[0058] In this embodiment, firstly, suitable target parameters, such as available capacity or internal resistance, are selected. Then, statistical indicators of these available capacities or internal resistances are calculated to measure the degree of consistency. The degree of consistency can be determined by calculating the standard deviation; the smaller the standard deviation, the closer the voltage values ​​of each cell are, and the higher the degree of consistency.

[0059] Step S1046: The battery is tested based on the consistency level, wherein if the consistency level is less than the consistency level threshold, the battery is determined to be normal, and if the consistency level is greater than or equal to the consistency level threshold, the battery is determined to be abnormal.

[0060] In this embodiment, the consistency threshold is a pre-set critical value used to determine whether the battery is abnormal. When the consistency of the target parameters of the battery cell is compared with this threshold, the state of the battery can be determined. This threshold is determined comprehensively based on factors such as battery design requirements, usage scenarios, and safety standards.

[0061] In this embodiment, the calculated consistency level (such as standard deviation or range) is compared with a pre-set consistency level threshold. For example, if standard deviation is used as a measure of consistency level, a consistency level threshold is set. Conditional statements are used to implement the comparison logic in the program. If the calculated standard deviation is less than the consistency level threshold, the battery is determined to be normal; if the standard deviation is greater than or equal to the consistency level threshold, the battery is determined to be abnormal.

[0062] The method provided in this application, by detecting the consistency of target parameters of battery cells, can detect potential problems before obvious battery pack failures occur. When the consistency deteriorates, it means that the performance of some cells differs significantly from other cells. This may be due to cell aging, manufacturing defects, or damage during use. Early detection of these problems allows for timely intervention, such as maintenance or replacement of abnormal cells, preventing further deterioration. The performance stability of a battery pack depends on the consistency of performance among individual cells. When the consistency of target parameters of the cells is high, the battery pack can distribute current and voltage more evenly during charging and discharging, reducing problems such as local overcharging and over-discharging caused by differences in cell performance. This improves the overall performance stability and lifespan of the battery pack. Inconsistent cell performance may lead to safety hazards such as local overheating and short circuits during charging and discharging. By detecting the consistency and promptly identifying anomalies, these safety hazards can be avoided. When the consistency is greater than or equal to a threshold, a battery abnormality is determined, prompting timely measures to eliminate potential safety risks.

[0063] In some embodiments, after step S104, the method further includes: Step S105: If there is an abnormality in the target battery cell, determine the location of the target battery cell.

[0064] In this embodiment, the location refers to the specific physical coordinates or identification information of the target cell within the battery pack. Typically, the cell's location can be accurately described using methods such as row and column numbering, specific coding, or spatial coordinates, depending on the battery pack's structural design.

[0065] In this embodiment, row and column numbering or specific encoding can be used to obtain the location of each battery cell, and then an association table of cell number, parameter information, and location identifier can be created. When an abnormal battery cell is detected, the corresponding location identifier is looked up in the association table using the cell number.

[0066] Step S106: Output the position of the target battery cell.

[0067] In this embodiment, the location information of the abnormal battery cell can be displayed in text or graphics. For example, it can be displayed as a list, such as "Abnormal battery cell number: SN12345, location: R2C3"; or the location of the abnormal battery cell can be highlighted based on the graphical interface of the battery pack.

[0068] In some embodiments, the location information of abnormal cells and related detection parameters can be recorded in a database for subsequent querying and analysis.

[0069] In some embodiments, a detailed test report can be generated based on the recorded data. The report includes information such as the location of the abnormal cell, the abnormal parameters, and the test time, providing a reference for repair and maintenance.

[0070] In large battery packs, there are numerous cells. Without accurate location information, maintenance personnel would need to spend a significant amount of time inspecting each cell individually to pinpoint the fault. This method, however, can quickly locate abnormal cells, greatly shortening troubleshooting time and improving maintenance efficiency. Quickly and accurately locating abnormal cells avoids unnecessary interference and damage to other healthy cells. Simultaneously, it reduces the time and manpower costs for maintenance personnel during fault location, thereby lowering overall maintenance costs. Timely detection and location of abnormal cells can prevent chain reactions caused by them, such as overheating and short circuits, thus preventing more serious battery pack failures and enhancing the safety and reliability of the battery pack.

[0071] In some embodiments, while step S106 is being performed, the method further includes: Step S107: Output suggestion information.

[0072] In this embodiment, the suggested information may include one or more of the following: maintenance suggestions, inspection suggestions, operational adjustment suggestions, and preventative suggestions. Maintenance suggestions provide specific repair operation guidance for the abnormal condition of the target cell, such as replacing the cell or repairing it (e.g., resoldering connection points). Inspection suggestions prompt the inspection of other components or systems related to the target cell, such as checking whether the battery module connection lines are loose or whether the relevant parameter settings of the battery management system are correct. Operational adjustment suggestions provide recommendations for adjusting the battery pack's operating parameters based on the target cell's abnormality, such as reducing the charging current or adjusting the discharge cutoff voltage, to prevent further deterioration of the abnormality. Preventative suggestions provide preventative measures to prevent similar cell abnormalities from recurring, such as improving the battery pack's heat dissipation environment and performing regular cell balancing maintenance.

[0073] In this embodiment, various abnormal cell conditions and their corresponding suggestions can be collected and organized to form a rule base. Rules can be expressed in "if-then" form, such as "If the cell voltage is too low and the internal resistance is normal, then it is recommended to check if the charging circuit is normal and appropriately extend the charging time." When an abnormality is detected in a target cell, the abnormality is matched with the rules in the rule base to find the most suitable condition, thereby outputting corresponding suggestions. For example, when a cell voltage is detected to be below the normal threshold and the internal resistance is within the normal range, the suggestion "check if the charging circuit is normal and appropriately extend the charging time" is output through rule matching.

[0074] The method provided in this application provides clear operational guidance to maintenance personnel by outputting suggested information, avoiding blind attempts due to lack of experience or knowledge, thereby improving maintenance efficiency. At the same time, accurate suggestions help to thoroughly resolve cell malfunctions and improve maintenance quality.

[0075] In some embodiments, step S103 includes: Step S1031: Input the first state data, the second state data, the third state data, and the fourth state data into the neural network model to determine the target parameters of each cell and the target parameters of the battery.

[0076] In this embodiment of the application, the target parameters for the battery can be the overall capacity of the battery pack, energy efficiency, charging and discharging power, etc.

[0077] In some embodiments, the method further includes: Step S108: Determine the health status of the battery based on the target parameters of the battery.

[0078] In this embodiment, an evaluation model is established based on the relationship between the battery's target parameters and its health status. For example, experiments and data analysis can reveal that the ratio of the battery's actual capacity to its brand-new capacity can serve as an important indicator of its health status. That is, SOH = (Actual Capacity / Rated Capacity) × 100%. Alternatively, multiple target parameters can be considered comprehensively, using weighted averages or other combined methods to establish a more accurate health status evaluation model. For example, considering factors such as battery capacity, internal resistance, and energy efficiency, a corresponding weight is assigned to each factor, and the health status is determined by calculating a weighted sum. The battery's target parameters are substituted into the health status evaluation model to calculate the battery's health status. For example, if the battery's actual capacity is 80 Ah and its brand-new capacity is 100 Ah, then according to the above capacity ratio calculation method, the battery's health status is 80%.

[0079] Step S109: Detect the battery based on its health status.

[0080] In this embodiment, different health status thresholds are set according to the application scenario and requirements of the battery. For example, in electric vehicles, to ensure safe driving and performance, it may be set that when the battery health status is below 80%, the user needs to be reminded to perform battery maintenance or replacement; when the health status is below 60%, high-speed driving or high-power charging and discharging is prohibited. The battery health status is monitored in real time and compared with the set thresholds. If the battery health status falls below a certain threshold, the system issues a corresponding warning signal. The warning method can be an audio prompt, a warning message displayed on the screen, or a message sent to the user's mobile device via wireless communication. Based on the trend of health status changes, the remaining battery life is predicted, providing the user with more comprehensive battery status information so that the user can reasonably arrange the battery usage and maintenance plan.

[0081] The method provided in this application utilizes a neural network model that can automatically learn the complex relationships between various state data. This avoids the simplification assumptions and linear approximations that may exist in traditional methods. Through extensive data training, the neural network can more accurately estimate the target parameters of the battery cell and battery, providing a more reliable foundation for subsequent health status assessment and detection. By setting reasonable thresholds based on accurate health status and performing real-time detection and early warning, potential battery problems can be identified promptly, preventing safety accidents and equipment damage caused by battery failure. Simultaneously, early warning provides users with sufficient time for battery maintenance or replacement, extending battery life and reducing operating costs.

[0082] In some embodiments, prior to step S103, the method further includes: Step S1: Preprocess the first state data, the second state data, the third state data, and the fourth state data. The preprocessing includes outlier handling and missing value handling.

[0083] In this embodiment, outliers are data points that deviate significantly from the normal range, which may be caused by sensor malfunction, measurement error, or transient interference, such as sudden voltage jumps or abnormal temperature fluctuations. Missing values ​​are data omissions caused by sensor malfunction, communication interruption, or data recording errors during data acquisition, manifested as empty or invalid values ​​in the data sequence.

[0084] In this embodiment, outliers can be corrected by methods such as median filtering and moving average filtering, and supplemented by methods such as linear interpolation, spline interpolation, or prediction filling based on historical data to ensure the integrity and continuity of the data.

[0085] In some embodiments, parameters such as the theoretical capacity and theoretical internal resistance of the battery can be calculated using an electrochemical model.

[0086] In some embodiments, the SOH and internal resistance of the vehicle's battery are output, and the SOH and internal resistance of each cell are displayed using a bar chart.

[0087] The method provided in this application enables non-destructive testing without disassembling the battery pack. It can accurately calculate the state of health (SOH) or internal resistance of each cell, breaking the limitations of traditional battery health monitoring which is confined to the battery pack level. This expands the user's focus on battery faults and performance to the more refined cell level. Users can quickly locate the specific location of battery faults, accurately identify abnormal cells, and receive detailed repair suggestions based on different results. Locating the faulty cell eliminates the need to replace the entire battery pack, saving users costs. Battery health status analysis can be performed without disassembling the battery pack, saving time and effort.

[0088] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0089] According to the foregoing embodiments, this application provides a detection device. The various modules and units included in the device can be implemented by a processor in a computer device; of course, they can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0090] This application provides a detection device. Figure 2 This is a schematic diagram of the structure of a detection device provided in an embodiment of this application, as shown below. Figure 2 As shown, the detection device 200 includes: The first acquisition module 201 is used to acquire first state data of the battery and second state data of the battery cells when the remaining capacity of the vehicle's battery is less than a preset capacity threshold. The second acquisition module 202 is used to acquire the third state data of the battery during the charging process and the fourth state data of the battery cells when the battery of the vehicle is being charged. Input module 203 is used to input the first state data, the second state data, the third state data and the fourth state data into the neural network model to at least determine the target parameters of each cell; The detection module 204 is used to detect the battery based on the target parameters of each cell.

[0091] In some embodiments, the target parameter includes: available capacity, and the detection module 204 includes: The first determining unit is used to determine the health status of each cell based on its available capacity and corresponding rated capacity. The first detection unit is used to detect the cells of the battery based on the health status of each cell, wherein if the health status of a target cell is less than a health status threshold, the target cell is determined to be abnormal.

[0092] In some embodiments, the target parameter includes: internal resistance; the detection module 204 includes: The second determining unit is used to determine the differences between each cell based on the internal resistance of each cell and the corresponding theoretical internal resistance. The second detection unit is used to detect each battery cell based on the differences between each battery cell, wherein if the difference between the target battery cell and the target battery cell is greater than the difference threshold, the target battery cell is determined to be abnormal.

[0093] In some embodiments, the detection module 204 includes: The third determining unit is used to determine the degree of consistency between the target parameters of each cell; The third detection unit is used to detect the battery based on the consistency level, wherein if the consistency level is less than the consistency level threshold, the battery is determined to be normal, and if the consistency level is greater than or equal to the consistency level threshold, the battery is determined to be abnormal.

[0094] In some embodiments, the detection device 200 further includes: The first determining module is used to determine the location of the target battery cell in the event of an anomaly in the target battery cell; The first output module is used to output the position of the target battery cell.

[0095] In some embodiments, the detection device 200 further includes: The second output module is used to output suggestion information.

[0096] In some embodiments, inputting the first state data, the second state data, the third state data, and the fourth state data into a neural network model to at least determine the target parameters of each battery cell includes: The first state data, the second state data, the third state data, and the fourth state data are input into a neural network model to determine the target parameters of each cell and the target parameters of the battery. In some embodiments, the detection device 200 further includes: The second determining module is used to determine the health status of the battery based on the target parameters of the battery. The second detection module is used to detect the battery based on its health status.

[0097] In some embodiments, the detection device 200 further includes: The preprocessing module is used to preprocess the first state data, the second state data, the third state data, and the fourth state data. The preprocessing includes outlier handling and missing value handling.

[0098] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0099] In addition, the detection device described above can be a software unit, a hardware unit, or a combination of software and hardware. It can also be integrated into electronic devices as an independent component, or exist as an independent terminal device.

[0100] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0101] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 3 in this embodiment may include: at least one processor 30 ( Figure 3Only one processor 30, memory 31, and computer program 32 stored in memory 31 and executable on at least one processor 30 are shown. When the processor 30 executes the computer program 32, it implements the steps in any of the above method embodiments, or the processor 30 executes the computer program 32 to implement the functions of each module / unit in the above device or system embodiments.

[0102] For example, computer program 32 may be divided into one or more modules / units, one or more of which are stored in memory 31 and executed by processor 30 to complete this application. One or more modules / units may be a series of computer program 32 instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.

[0103] This application also provides a computer-readable storage medium storing a computer program 32, which, when executed by a processor 30, implements the steps described in the above-described method embodiments.

[0104] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0105] If the integrated unit 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, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program 32 instructing related hardware. The computer program 32 can be stored in a computer-readable storage medium, and when executed by the processor 30, it can implement the steps of the various method embodiments described above. The computer program 32 includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code to a terminal, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, a computer-readable medium cannot be an electrical carrier signal or a telecommunication signal.

[0106] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0107] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0108] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and 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 through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0109] 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.

[0110] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method of detection, characterized in that, The method comprises: obtaining first state data of a battery of a vehicle and second state data of an electric cell in the battery when a remaining capacity of the battery is less than a preset capacity threshold; obtaining third state data of the battery and fourth state data of the electric cell in the battery when the battery is charged; inputting the first state data, the second state data, the third state data and the fourth state data into a neural network model to determine at least a target parameter of each electric cell; detecting the battery based on the target parameter of each electric cell.

2. The method of claim 1, wherein, The target parameter comprises an available capacity, and the detecting the battery based on the target parameter of each electric cell comprises: determining a health state of each electric cell based on the available capacity and a corresponding rated capacity of each electric cell; detecting the electric cell of the battery based on the health state of each electric cell, wherein it is determined that a target electric cell is abnormal when the health state of the target electric cell is less than a health state threshold.

3. The method of claim 1, wherein, The target parameter comprises an internal resistance, and the detecting the battery based on the target parameter of each electric cell comprises: determining a corresponding difference of each electric cell based on the internal resistance and a corresponding theoretical internal resistance of each electric cell; detecting each electric cell based on the corresponding difference of each electric cell, wherein it is determined that a target electric cell is abnormal when the corresponding difference of the target electric cell is greater than a difference threshold.

4. The method of claim 1, wherein, The detecting the battery based on the target parameter of each electric cell comprises: determining a consistency degree between the target parameters of each electric cell; detecting the battery based on the consistency degree, wherein it is determined that the battery is normal when the consistency degree is less than a consistency degree threshold, and it is determined that the battery is abnormal when the consistency degree is greater than or equal to the consistency degree threshold.

5. The method according to any one of claims 2 to 3, characterized in that, The method further comprises: determining a location of a target electric cell when the target electric cell is abnormal; outputting the location of the target electric cell.

6. The method of claim 5, wherein, The method further comprises: outputting suggestion information.

7. The method of claim 1, wherein, The inputting the first state data, the second state data, the third state data and the fourth state data into the neural network model to determine at least the target parameter of each electric cell comprises: inputting the first state data, the second state data, the third state data and the fourth state data into the neural network model to determine the target parameter of each electric cell and a target parameter of the battery; The method further comprises determining a health state of the battery based on the target parameter of the battery; detecting the battery based on the health state of the battery.

8. The method of claim 1, wherein, The method further comprises: preprocessing the first state data, the second state data, the third state data and the fourth state data, wherein the preprocessing comprises outlier processing and missing value processing.

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, The processor executes the computer program to implement the method of any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the method of any one of claims 1 to 8.

Images