Power battery fault alarm method and device, vehicle and medium

Abstract

The invention provides a power battery fault alarm method and device, a vehicle and a medium, and the method comprises the steps: determining the actual voltage difference of a power battery at the current moment according to the voltage data of a plurality of battery cells in the power battery at the current moment; determining an expected voltage difference of the power battery at the current moment according to the battery state data of the power battery at the current moment; and if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet a preset condition, outputting a power battery fault alarm signal. In the embodiment of the invention, the expected pressure difference is determined according to the battery state data at the current moment, then the power battery is diagnosed according to the expected pressure difference at the current moment and the actual pressure difference, and if the preset condition is met, the power battery fault alarm signal is output. Therefore, the power battery can be diagnosed based on the expected voltage differences corresponding to different battery states, false alarm or missing alarm of the power battery fault is avoided to a certain extent, and the diagnosis requirement of the power battery is basically met.

Description

Technical Field

[0001] This application relates to the field of electric vehicle technology, and in particular to a power battery fault alarm method, device, vehicle and medium. Background Technology

[0002] The power batteries in new energy vehicles are typically composed of multiple cells. Due to differences in manufacturing processes, material properties, operating temperature, and aging levels, different cells may exhibit different states. If the voltage difference between different cells is too large, it may limit the usable capacity and power output of the power battery, and may also lead to overcharging or over-discharging, affecting the health of the power battery.

[0003] To promptly detect problems with power batteries and ensure their stable operation, related technologies can diagnose the state of power batteries based on their voltage difference. Specifically, voltage data from each cell in the power battery can be collected, and the voltage difference between the two cells with the highest and lowest voltages can be calculated, i.e., the voltage difference of the power battery. By comparing the voltage difference of the power battery with a preset voltage difference threshold, it can be determined whether there is an abnormality in the power battery.

[0004] However, the voltage difference and the reasonable voltage difference of a power battery are not constant values, but are closely related to the battery state (e.g., state of charge, battery power, battery temperature, and battery health). Under different battery states, the actual voltage difference and the reasonable voltage difference of the power battery are different. Diagnosing the power battery based on a constant preset voltage difference threshold may lead to false alarms or missed faults, making it difficult to meet the diagnostic needs of power batteries.

[0005] It should be noted that the information disclosed in the background section of this application is intended only to enhance the understanding of the general background of this application, and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] This application provides a method, device, vehicle, and medium for alarming power battery faults, which helps to solve the problem of false alarms or missed alarms for power battery faults.

[0007] In a first aspect, embodiments of this application provide a method for alarming a power battery fault, including: Based on the voltage data of multiple cells in the power battery at the current moment, the actual voltage difference of the power battery at the current moment is determined. The actual voltage difference is the voltage difference between the cell with the highest voltage and the cell with the lowest voltage among the multiple cells. Based on the current battery state data of the power battery, determine the expected voltage difference of the power battery at the current moment; If the actual pressure difference at the current moment and the expected pressure difference at the current moment meet the preset conditions, a power battery fault alarm signal will be output.

[0008] In some possible implementations, the step of outputting a power battery fault alarm signal if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet a preset condition includes: If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the voltage data of multiple cells in the power battery at the current moment meet the preset conditions, then a power battery fault alarm signal is output.

[0009] In some possible implementations, the step of outputting a power battery fault alarm signal if the actual voltage difference at the current moment, the expected voltage difference at the current moment, and the voltage data of multiple cells in the power battery at the current moment meet preset conditions includes: Based on the voltage data of multiple cells in the power battery at the current moment, a first auxiliary feature is determined at the current moment. The first auxiliary feature is used to characterize the voltage dispersion of the multiple cells. If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the first auxiliary feature at the current moment meet the preset conditions, then a power battery fault alarm signal is output.

[0010] In some possible implementations, the step of outputting a power battery fault alarm signal if the actual voltage difference at the current moment, the expected voltage difference at the current moment, and the voltage data of multiple cells in the power battery at the current moment meet preset conditions includes: Based on the voltage data of multiple cells in the power battery at the current moment and the average voltage of each cell in the multiple cells within a first preset time interval, a second auxiliary feature is determined at the current moment. The second auxiliary feature is used to characterize the voltage fluctuation of the multiple cells. If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the second auxiliary feature at the current moment meet the preset conditions, then a power battery fault alarm signal is output.

[0011] In some possible implementations, determining the desired voltage difference of the power battery at the current moment based on the battery state data of the power battery at the current moment includes: The battery state data of the power battery at the current moment is input into the expected voltage prediction model, and the expected voltage difference of the power battery at the current moment is output. The expected voltage prediction model is a model trained with a preset dataset. The preset dataset includes multiple sets of battery state data and multiple actual voltage differences corresponding to the multiple sets of battery state data.

[0012] In some possible implementations, the step of outputting a power battery fault alarm signal if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet a preset condition includes: If the differential pressure deviations at multiple times within a second preset time interval including the current time meet preset conditions, a power battery fault alarm signal is output, wherein the differential pressure deviation is the difference between the actual differential pressure and the expected differential pressure.

[0013] In some possible implementations, after outputting a power battery fault alarm signal if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet a preset condition, the method further includes: If the actual voltage difference at the current moment and the expected voltage difference at the current moment meet the preset conditions, the information of the faulty battery cell is output. The faulty battery cell is the battery cell with the highest voltage and the battery cell with the lowest voltage among the multiple battery cells at the current moment.

[0014] Secondly, embodiments of this application also provide a power battery fault alarm device, comprising: The actual voltage difference acquisition module is used to determine the actual voltage difference of the power battery at the current moment based on the voltage data of multiple cells in the power battery at the current moment. The actual voltage difference is the voltage difference between the cell with the highest voltage and the cell with the lowest voltage among the multiple cells. The desired pressure difference acquisition module is used to determine the desired pressure difference of the power battery at the current moment based on the battery state data of the power battery at the current moment. The fault alarm module is used to output a power battery fault alarm signal if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet preset conditions.

[0015] Thirdly, embodiments of this application also provide a vehicle, including: A controller configured to perform the method described in any one of the first aspects.

[0016] Fourthly, embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the method described in any one of the first aspects.

[0017] In this embodiment, the expected voltage difference at the current moment is determined based on the battery state data. Then, the power battery is diagnosed based on the expected voltage difference and the actual voltage difference. If the actual voltage difference and the expected voltage difference at the current moment meet preset conditions, a power battery fault alarm signal is output. In this way, the power battery can be diagnosed based on the expected voltage difference corresponding to different battery states, which to some extent avoids false alarms or missed alarms for power battery faults and basically meets the diagnostic needs of power batteries. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments 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.

[0019] Figure 1 This is a structural diagram illustrating an application scenario provided in an embodiment of this application. Figure 2 A flowchart illustrating a power battery fault alarm method provided in an embodiment of this application; Figure 3 A schematic diagram of a differential pressure deviation provided in an embodiment of this application; Figure 4 A schematic diagram of a multi-level threshold provided in an embodiment of this application; Figure 5 A flowchart illustrating another power battery fault alarm method provided in this application embodiment; Figure 6 A flowchart illustrating another power battery fault alarm method provided in this application embodiment; Figure 7 A schematic diagram of differential pressure fluctuation provided for an embodiment of this application; Figure 8 This is a schematic diagram of the structure of a power battery fault alarm device provided in an embodiment of this application; Figure 9 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Detailed Implementation

[0020] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0021] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0022] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0024] The power batteries in new energy vehicles are typically composed of multiple cells. Due to differences in manufacturing processes, material properties, operating temperature, and aging levels, different cells may exhibit different states. If the voltage difference between different cells is too large, it may limit the usable capacity and power output of the power battery, and may also lead to overcharging or over-discharging, affecting the health of the power battery.

[0025] To promptly identify problems with power batteries and ensure their stable operation, relevant technologies utilize a Battery Management System (BMS) to diagnose the state of the power battery.

[0026] See Figure 1 This is a structural diagram illustrating an application scenario provided in an embodiment of this application, such as... Figure 1 As shown, the vehicle 100 includes a power battery 101 and a battery management system 102. The battery management system 102 can collect the voltage data of each cell in the power battery 101, calculate the voltage difference between the two cells with the highest and lowest voltages, i.e., the voltage difference of the power battery, and determine whether there is an abnormality in the power battery by comparing the voltage difference of the power battery with a preset voltage difference threshold.

[0027] However, the voltage difference and the reasonable voltage difference of a power battery are not constant values, but are closely related to the battery state (e.g., state of charge, battery power, battery temperature, and battery health). Under different battery states, the actual voltage difference and the reasonable voltage difference of the power battery are different. Using a constant preset voltage difference threshold for power battery diagnosis may lead to false alarms or missed alarms for power battery faults, making it difficult to meet the diagnostic needs of power batteries.

[0028] In view of this, embodiments of this application provide a method for alarming power battery faults, which helps to solve the problem of false alarms or missed alarms for power battery faults. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0029] It should be pointed out that, as Figure 1 The application scenario shown is merely an exemplary one. Those skilled in the art can apply the method provided in this application embodiment to other application scenarios according to actual conditions, such as applying it to the vehicle control unit (VCU) that communicates with the battery management system via a controller area network (CAN) bus. This application embodiment does not impose specific limitations on specific application scenarios.

[0030] See Figure 2 This is a flowchart illustrating a power battery fault alarm method provided in an embodiment of this application, which can be applied to, for example... Figure 1 The application scenarios shown are as follows: Figure 2 As shown, the method specifically includes the following steps.

[0031] S201: Determine the actual voltage difference of the power battery at the current moment based on the voltage data of multiple cells in the power battery at the current moment.

[0032] The actual voltage difference is the voltage difference between the cell with the highest voltage and the cell with the lowest voltage among multiple cells.

[0033] In this embodiment of the application, the terminal device connected to the power battery can receive or acquire the voltage data of multiple cells in the power battery at the current moment, and determine the actual voltage difference of the power battery at the current moment based on the voltage data of the multiple cells at the current moment.

[0034] The voltage data of multiple cells at the current moment typically refers to the real-time voltage information corresponding to some or all of the cells in the power battery under the current battery state. That is to say, multiple cells can refer to all the cells in the power battery, or it can refer to a preset number of cells in the power battery. Those skilled in the art can set the number and selection of multiple cells according to actual diagnostic needs, and the embodiments of this application do not impose specific limitations in this regard.

[0035] Specifically, the terminal equipment connected to the power battery may include BMS and / or VCU. The terminal equipment can collect or receive the current voltage data of multiple cells in the power battery through CAN bus or wireless communication.

[0036] Optionally, the voltage data of multiple cells at the current moment can be packaged into data frames for transmission at a preset fixed frequency. Each data frame can contain the voltage data of multiple cells at the current moment, and can also include cell information such as the cell number.

[0037] In this way, after obtaining the current voltage data of multiple cells in the power battery, the actual voltage difference of the power battery at that moment can be determined based on the current voltage data of multiple cells. The actual voltage difference of the power battery at that moment is determined by calculating the voltage difference between the cell with the highest voltage and the cell with the lowest voltage among the multiple cells at that moment.

[0038] S202: Determine the expected voltage difference of the power battery at the current moment based on the battery state data of the power battery at the current moment.

[0039] In this embodiment of the application, the terminal device connected to the power battery can receive or acquire the battery status data of the power battery at the current moment. The battery status data of the power battery at the current moment is typically a set of parameters characterizing the overall operating state of the power battery at that moment. Specifically, the battery status data typically includes the power battery's state of charge, battery power, battery temperature, and state of health (SOH), etc.

[0040] Similarly, terminal devices connected to the power battery typically include a BMS and / or VCU. Furthermore, these terminal devices can collect the current battery status data via a CAN network bus or wireless communication module. For example, the current battery status data, along with the current voltage data of multiple battery cells, can be packaged into a data frame for transmission at a preset fixed frequency. Each data frame contains not only cell voltage data and related cell information, but also current battery status data such as state of charge, battery power, battery temperature, and battery health status, facilitating synchronous acquisition and subsequent retrieval by the terminal device.

[0041] Understandably, after obtaining the current state data of the power battery, the expected voltage difference of the power battery at that moment can be determined based on the current state data. The expected voltage difference reflects the reasonable voltage difference between multiple cells in the corresponding battery state at the current moment, and its value will be dynamically adjusted as the battery state data changes.

[0042] Specifically, the expected voltage difference of the power battery at the current moment can be determined in various ways. For example, the expected voltage difference can be determined through statistical induction. By statistically summarizing and analyzing the historical operating data of the power battery under different battery states, a correspondence between battery state data and expected voltage difference is established. When the battery state data at the current moment is obtained, the terminal device can query the preset correspondence table to find the expected voltage difference at the current moment corresponding to the current battery state data.

[0043] In some possible implementations, the current battery state data of the power battery is input into the expected voltage prediction model, and the expected voltage difference of the power battery at the current moment is output. The expected voltage prediction model is a model trained on a preset dataset, which includes multiple sets of battery state data and multiple actual voltage differences corresponding to the multiple sets of battery state data.

[0044] It is understood that the trained expected voltage prediction model can receive the current battery state data of the power battery as input and output an expected voltage difference that is more consistent with the battery state data, so as to meet the core requirement of dynamically determining the expected voltage difference and improving the accuracy of fault diagnosis in the embodiments of this application.

[0045] Specifically, the preset dataset typically includes multiple sets of battery status data and multiple actual pressure differences corresponding to the multiple sets of battery status data, i.e. multiple data pairs. Each data pair includes battery status data and the pressure difference corresponding to the battery status data. The multiple data pairs can be data pairs collected during the actual operation of one or more power batteries.

[0046] For example, multiple sets of data pairs can be collected during the actual operation of power batteries in various health states as components of a preset dataset. A power battery in a healthy state can be a newly manufactured power battery or a power battery confirmed to be fault-free after testing. Alternatively, multiple sets of battery status data and multiple actual pressure differences corresponding to these sets of battery status data can be collected during the actual operation of one or more power batteries. Based on preset conditions, the collected data pairs can be filtered; for example, data pairs with pressure differences lower than a preset safe pressure difference threshold can be selected as components of the preset dataset. Of course, based on the battery health status of each power battery among multiple power batteries, power batteries with a battery health status above a preset battery health status threshold (e.g., 95%) can be selected, and multiple sets of data pairs can be collected during the actual operation of the selected power batteries as components of the preset dataset.

[0047] Optionally, the collected data pairs can undergo pre-defined data processing to obtain the constituent data of a pre-defined dataset. Similarly, data pairs can be collected through a terminal device connected to the power battery, and pre-defined data processing can be performed on the collected data pairs to ensure the accuracy and robustness of model training.

[0048] Specifically, the pre-defined data processing typically includes data fusion processing, time-series alignment processing, data cleaning processing, and credibility verification processing. Among these, data fusion processing can merge data from different power batteries into a unified dataset; time-series alignment processing can align multiple sets of battery state data and multiple actual pressure differences corresponding to the multiple sets of battery state data into data pairs based on the collection timestamp; and data cleaning processing can remove data that exceeds extreme ranges, as well as invalid or failed data, to form a standardized training dataset.

[0049] It is understandable that training the expected voltage prediction model with a pre-set dataset can enable the expected voltage prediction model to fit the mapping relationship between battery state data and expected voltage difference, and output a more matching expected voltage difference.

[0050] Specifically, a training dataset for supervised learning can be determined based on a pre-defined dataset. Multiple sets of battery state data from the training dataset are extracted as input feature vectors and used as model input. Multiple actual pressure differences corresponding to these sets of battery state data are used as target values ​​for the model to learn and predict. An appropriate regression algorithm can be used to train the model. For example, gradient boosting decision tree algorithms can be employed. These algorithms effectively handle nonlinear relationships between input features and achieve high prediction accuracy, making them suitable for the prediction needs of this scenario.

[0051] During model training, the model parameters can be optimized by minimizing the residual (e.g., mean squared error) between the predicted voltage drop output by the model and the actual voltage drop corresponding to the training set. This improves the model's prediction accuracy for voltage drops under different battery states. A validation dataset can also be determined based on a pre-defined dataset. The prediction performance of the expected voltage prediction model is then validated against this dataset. If the deviation between the predicted voltage drop output by the model and the actual voltage drop corresponding to the validation set is within a pre-defined reasonable range (i.e., the model's prediction accuracy meets the pre-defined requirements), then model training is complete, resulting in an expected voltage prediction model suitable for practical applications. If the deviation exceeds the pre-defined reasonable range, the process returns to adjust the pre-defined data processing parameters or model training parameters, and data processing and model training are repeated until the model's prediction accuracy meets the pre-defined requirements.

[0052] Of course, those skilled in the art can also choose other methods to determine the expected voltage difference of the power battery at the current moment, depending on the actual situation. For example, a mapping relationship can be established between various battery state data such as state of charge, battery power, battery temperature, and battery health status and the cell voltage difference, and a corresponding weight coefficient can be assigned to each parameter according to the difference in importance of the various battery state data to the cell voltage difference. After obtaining the battery state data at the current moment, the voltage difference contribution of each parameter is calculated through the corresponding mapping relationship, and then the voltage difference contribution of each parameter is weighted and summed with the corresponding weight coefficient. The result obtained is the expected voltage difference of the power battery at the current moment.

[0053] S203: If the actual pressure difference at the current moment and the expected pressure difference at the current moment meet the preset conditions, then output a power battery fault alarm signal.

[0054] In this embodiment of the application, the power battery can be diagnosed by judging whether the actual pressure difference at the current moment and the expected pressure difference at the current moment meet the preset conditions. If the actual pressure difference at the current moment and the expected pressure difference at the current moment meet the preset conditions, it can be considered that the actual pressure difference of the power battery at the current moment is too large and the power battery has a fault, and then the power battery fault alarm signal is output.

[0055] Optionally, if the actual pressure difference at the current moment is greater than the expected pressure difference at the current moment, and the pressure difference deviation at the current moment, that is, the difference between the actual pressure difference at the current moment and the expected pressure difference at the current moment, is greater than the preset pressure difference deviation threshold, then a power battery fault alarm signal is output.

[0056] Understandably, the expected voltage difference at the current moment is determined based on the battery state data. Then, the power battery is diagnosed based on the expected voltage difference and the actual voltage difference. If the actual voltage difference and the expected voltage difference at the current moment meet preset conditions, a power battery fault alarm signal is output. In this way, the power battery can be diagnosed based on the expected voltage difference corresponding to different battery states, which to some extent avoids false alarms or missed alarms for power battery faults and basically meets the diagnostic needs of power batteries.

[0057] In some possible implementations, if the differential pressure deviations at multiple times within a second preset time interval including the current time meet preset conditions, a power battery fault alarm signal is output.

[0058] The differential pressure deviation is usually the difference between the actual differential pressure and the expected differential pressure.

[0059] In this embodiment, the second preset time interval is typically a time range set to capture the trend of differential pressure deviation changes over a period of time and avoid interference from instantaneous fluctuations. The length of the second preset time interval can be set according to actual diagnostic needs; for example, it can be set to 1 second, or it can be set to the duration corresponding to an interval of 5 consecutive data frames. The temporal relationship between the second preset time interval and the current moment can be set according to actual diagnostic needs; for example, the current moment can be the start point, end point, or a point on the second preset time interval. This embodiment does not impose specific limitations on the length of the second preset time interval or the temporal relationship between the current moment and the second preset time interval.

[0060] Furthermore, the sampling times selected within the second preset time interval can be the times corresponding to multiple consecutive data frames or the times corresponding to discrete data frames. This application embodiment does not impose specific restrictions on the number of sampling times or their distribution within the second preset time interval.

[0061] In this embodiment, the power battery can be diagnosed by determining whether the differential pressure deviation at multiple moments within a second preset time interval including the current moment meets a preset condition. If the differential pressure deviation at multiple moments within the second preset time interval including the current moment meets the preset condition, the power battery can be considered to have a fault, and a power battery fault alarm signal will be output. It is understood that by analyzing the differential pressure deviation at multiple moments within the second preset time interval including the current moment, false alarms caused by instantaneous voltage fluctuations or abnormal single data acquisition can be effectively avoided, further improving the stability and accuracy of power battery fault diagnosis.

[0062] Optionally, if the differential pressure deviation at multiple times within a second preset time interval including the current time is greater than a preset differential pressure deviation threshold, a power battery fault alarm signal is output. See [link to relevant documentation]. Figure 3 This is a schematic diagram of a differential pressure deviation provided in an embodiment of this application, as shown below. Figure 3 As shown, the blue solid line represents the actual pressure difference at different times, the green dashed line represents the expected pressure difference at different times, and the filled part represents the pressure difference deviation at different times. When the current time is T1, the second preset time interval can be the interval corresponding to T1 to T2. If the pressure difference deviation at multiple times within the second preset time interval is greater than the preset pressure difference deviation threshold, a power battery fault alarm signal will be output.

[0063] Optionally, at least one preset differential pressure deviation threshold is determined based on the preset dataset, and the preset condition is determined based on the at least one preset differential pressure deviation threshold.

[0064] In this embodiment, multiple sets of battery state data from a preset dataset can be input into the expected differential pressure prediction model to obtain the expected differential pressure corresponding to the multiple sets of battery state data. Based on the multiple actual differential pressures corresponding to the multiple sets of battery state data and the expected differential pressure, multiple differential pressure deviations are determined. Then, based on the multiple differential pressure deviations, at least one preset differential pressure deviation threshold is determined.

[0065] In this way, by statistically analyzing a large number of differential pressure deviations, statistical data reflecting the range of differential pressure deviations under normal conditions can be obtained, and a threshold can be set based on this, so that the preset differential pressure deviation threshold matches the actual operating characteristics of the power battery.

[0066] See Figure 4 This is a schematic diagram illustrating a preset differential pressure deviation threshold provided in an embodiment of this application, as shown below. Figure 4 As shown, the distribution of multiple differential pressure deviations obtained through the expected differential pressure prediction model is approximately a normal distribution, and an anomaly detection algorithm can be used to determine at least one preset differential pressure deviation threshold. Specifically, the standard deviations of multiple differential pressure deviations can be determined, and a preset differential pressure deviation threshold is set based on the sum of the average value of the differential pressure deviations and the standard deviations of a preset multiple. For example, based on the average value and 2 times the standard deviation, 9.85mV is determined as the first preset differential pressure deviation threshold; based on the average value and 3 times the standard deviation, 14.78mV is determined as the second preset differential pressure deviation threshold; and based on the average value and 4 times the standard deviation, 19.70mV is determined as the third preset differential pressure deviation threshold.

[0067] It should be pointed out that, as Figure 4 The example shown is merely an exemplary preset differential pressure deviation threshold. Those skilled in the art may set more or fewer preset differential pressure deviation thresholds (at least one) or set larger or smaller preset differential pressure deviation thresholds according to actual needs. This application embodiment does not impose specific limitations in this regard.

[0068] After determining at least one preset differential pressure deviation threshold, a corresponding preset condition can be determined based on the at least one preset differential pressure deviation threshold. For example, when the number of preset differential pressure deviation thresholds is one, the preset condition can be set to the condition that the differential pressure deviations of multiple consecutive moments within a second preset time interval including the current moment are all greater than the preset differential pressure deviation threshold.

[0069] When there are multiple preset differential pressure deviation thresholds, different fault alarm levels can be divided according to the magnitude of each preset differential pressure deviation threshold, and corresponding preset conditions can be matched to trigger different levels of power battery fault alarm signals.

[0070] In this way, multi-level alarms for power battery faults are achieved through multiple preset differential pressure deviation thresholds. This allows for accurate reflection of the power battery's fault state level based on the severity of the differential pressure deviation. Furthermore, differentiated handling measures can be implemented based on different alarm levels, improving the targeting and timeliness of fault handling. Simultaneously, by combining differential pressure deviation judgment conditions at continuous moments within a second preset time interval, false alarms caused by instantaneous fluctuations can be effectively avoided while achieving tiered alarms, better meeting the diagnostic and maintenance needs throughout the entire lifecycle of the power battery.

[0071] In some possible implementations, if the actual voltage difference at the current moment and the expected voltage difference at the current moment meet the preset conditions, the information of the faulty cell is output. The faulty cell is the cell with the highest voltage and the cell with the lowest voltage among the multiple cells at the current moment.

[0072] In this embodiment, the terminal device connected to the power battery can obtain information about the cell with the highest voltage and the cell with the lowest voltage at the current moment, including the cell number, the cell's location identifier in the power battery, and other information uniquely corresponding to the cell. After outputting the power battery fault alarm signal, information about the faulty cell can also be output. The output method can be consistent with the transmission method of the power battery fault alarm signal, such as simultaneously displaying the power battery fault alarm prompt and the relevant information about the faulty cell on the vehicle-mounted display device. This embodiment does not impose specific limitations on the specific output method of the faulty cell information. In this way, cells with abnormal voltage differences in the power battery can be located, improving the efficiency of power battery fault repair.

[0073] In some possible implementations, if the actual voltage difference at the current moment, the expected voltage difference at the current moment, and the voltage data of multiple cells in the power battery at the current moment meet preset conditions, then a power battery fault alarm signal is output.

[0074] In this embodiment, fault diagnosis of the power battery can also be performed based on the current voltage data of multiple cells in the power battery. Specifically, preset conditions for diagnosing power battery faults can be set based on the actual voltage difference at the current moment, the expected voltage difference at the current moment, and the current voltage data of multiple cells in the power battery, thereby improving the comprehensiveness and accuracy of fault judgment.

[0075] For example, if the actual pressure difference at the current moment is greater than the expected pressure difference at the current moment, the difference between the actual pressure difference at the current moment and the expected pressure difference is greater than the preset pressure difference deviation threshold, and among the voltage data of multiple cells in the power battery at the current moment, the voltage of the cell with the highest voltage exceeds the preset maximum voltage threshold, or the voltage of the cell with the lowest voltage is lower than the preset minimum voltage threshold, then a power battery fault alarm signal is output.

[0076] Understandably, by introducing the current voltage data of multiple cells as the basis for fault judgment, false alarms can be avoided, further improving the accuracy and practicality of power battery fault diagnosis and better meeting the fault diagnosis needs of power batteries.

[0077] See Figure 5 This is a flowchart illustrating another power battery fault alarm method provided in an embodiment of this application, as shown below. Figure 5 As shown, in Figure 2 Based on the method shown, step S203 may specifically include the following steps.

[0078] S501: Determine the first auxiliary feature at the current moment based on the voltage data of multiple cells in the power battery at the current moment.

[0079] The first auxiliary feature is used to characterize the voltage dispersion of multiple cells.

[0080] It is understandable that a first auxiliary feature can be calculated based on the current voltage data of multiple cells in a power battery to characterize the voltage dispersion of the multiple cells. For example, the first auxiliary feature can be the standard deviation of the voltage of the multiple cells at the current moment, or it can be other parameters or combinations of parameters that can be used to characterize the voltage dispersion of the multiple cells, such as voltage range and voltage variance.

[0081] Optional, according to the formula: Determine the first auxiliary feature at the current time, where, Let N be the first auxiliary feature at time t, and N be the number of battery cells. Let be the voltage of the i-th cell out of N cells at time t. Let be the average voltage value of N cells at time t.

[0082] S502: If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the first auxiliary characteristic at the current moment meet the preset conditions, then output a power battery fault alarm signal.

[0083] In this embodiment of the application, based on the diagnostic requirements of the power battery, preset conditions can be set by combining the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the first auxiliary feature at the current moment. Through the coordinated judgment of the three, the fault diagnosis of the power battery can be realized, and the fault state of the power battery can be determined.

[0084] Optionally, if the actual pressure difference at the current moment is greater than the expected pressure difference at the current moment, the difference between the actual pressure difference at the current moment and the expected pressure difference is greater than the preset pressure difference deviation threshold, and the first auxiliary feature at the current moment is greater than the preset auxiliary feature threshold, then a power battery fault alarm signal is output.

[0085] Of course, diagnostic input features can also be determined based on the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the first auxiliary feature at the current moment. The diagnostic input features are then input into the fault judgment model, and a power battery fault alarm signal is output based on the output of the fault judgment model.

[0086] It is understandable that by introducing a first auxiliary feature that characterizes the degree of dispersion of cell voltage as a judgment criterion, abnormal states of cell voltage distribution can be accurately captured, further improving the accuracy and reliability of power battery fault diagnosis and better adapting to the actual diagnostic needs of power batteries.

[0087] See Figure 6 This is a flowchart illustrating another power battery fault alarm method provided in an embodiment of this application, as shown below. Figure 6 As shown, in Figure 2 Based on the method shown, step S203 may specifically include the following steps.

[0088] S601: Determine the second auxiliary feature at the current moment based on the voltage data of multiple cells in the power battery at the current moment and the average voltage of each cell in the multiple cells within a first preset time interval.

[0089] The second auxiliary feature is used to characterize the voltage fluctuation of multiple cells.

[0090] It is understood that, based on the current voltage data of multiple cells in a power battery, and the average voltage of each cell within a first preset time interval, a second auxiliary feature for characterizing the degree of voltage fluctuation of the cells can be calculated. For example, the second auxiliary feature may be the absolute value of the difference between the current voltage data of each cell and the average voltage of that cell within the first preset time interval, or it may be other parameters or combinations of parameters that can be used to characterize the degree of voltage fluctuation of the cells, such as the rate of voltage change.

[0091] See Figure 7 This is a schematic diagram of differential pressure fluctuation provided in an embodiment of this application, as shown below. Figure 7 As shown in Figure A, if the voltage of any cell experiences a sudden change, that cell can be considered an abnormal cell. Figure 7 As shown in B, a second auxiliary feature for characterizing the degree of voltage fluctuation of a battery cell can be calculated based on the current voltage data of multiple cells in the power battery and the average voltage of each cell within a first preset time interval.

[0092] Optional, according to the formula: Determine the second auxiliary feature at the current time, where, Here, W represents the second auxiliary feature at time t, W is the duration of the first preset time interval, and N is the number of battery cells. Let be the average voltage of the i-th cell at time t. Let be the voltage of the i-th cell at time t.

[0093] S602: If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the second auxiliary characteristic at the current moment meet the preset conditions, then output a power battery fault alarm signal.

[0094] In this embodiment of the application, based on the diagnostic requirements of the power battery, preset conditions can be set by combining the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the second auxiliary feature at the current moment. Through the coordinated judgment of the three, the power battery can be diagnosed and the fault state of the power battery can be determined.

[0095] Optionally, if the actual pressure difference at the current moment is greater than the expected pressure difference at the current moment, the difference between the actual pressure difference at the current moment and the expected pressure difference is greater than the preset pressure difference deviation threshold, and the second auxiliary feature at the current moment is greater than the preset auxiliary feature threshold, then a power battery fault alarm signal is output.

[0096] Of course, the diagnostic input features can also be determined based on the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the second auxiliary feature at the current moment. The diagnostic input features are then input into the fault judgment model, and the power battery fault alarm signal is output based on the output result of the fault judgment model.

[0097] By introducing a second auxiliary feature that characterizes the degree of cell voltage fluctuation as a judgment criterion, the abnormal state of cell voltage fluctuation over time can be accurately captured, further improving the accuracy and reliability of power battery fault diagnosis and better adapting to the actual diagnostic needs of power batteries.

[0098] Optionally, based on the voltage data of multiple cells in the power battery at the current moment, a first auxiliary feature is determined for the current moment. The first auxiliary feature is used to characterize the voltage dispersion of the multiple cells. Based on the voltage data of multiple cells in the power battery at the current moment and the average voltage of each cell in the multiple cells within a first preset time interval, a second auxiliary feature is determined for the current moment. The second auxiliary feature is used to characterize the voltage fluctuation of the multiple cells. If the actual voltage difference at the current moment, the expected voltage difference at the current moment, the first auxiliary feature at the current moment, and the second auxiliary feature at the current moment meet preset conditions, a power battery fault alarm signal is output.

[0099] Specifically, the actual pressure difference at the current moment, the expected pressure difference at the current moment, the first auxiliary feature at the current moment, and the second auxiliary feature at the current moment can be used to determine the diagnostic input features. The diagnostic input features are then input into the fault judgment model, and a power battery fault alarm signal is output based on the output of the fault judgment model.

[0100] Of course, those skilled in the art can also add other judgment criteria to the judgment criteria provided in the embodiments of this application to perform power battery diagnosis according to actual needs. For example, power battery diagnosis can also be performed based on the current battery status data. The diagnostic input features are determined according to the above judgment criteria, the diagnostic input features are input into the fault judgment model, and the power battery fault alarm signal is output according to the output result of the fault judgment model.

[0101] Corresponding to the above embodiments, this application also provides a power battery fault alarm device, see [link to relevant documentation]. Figure 8 This is a schematic diagram of the structure of a power battery fault alarm device provided in an embodiment of this application. Figure 8 As shown, the power battery fault alarm device 800 includes an actual differential pressure acquisition module 801, a desired differential pressure acquisition module 802, and a fault alarm module 803.

[0102] The actual voltage difference acquisition module 801 is used to determine the actual voltage difference of the power battery at the current moment based on the voltage data of multiple cells in the power battery at the current moment. The actual voltage difference is the voltage difference between the cell with the highest voltage and the cell with the lowest voltage among the multiple cells. The expected pressure difference acquisition module 802 is used to determine the expected pressure difference of the power battery at the current moment based on the battery state data of the power battery at the current moment. The fault alarm module 803 is used to output a power battery fault alarm signal if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet the preset conditions.

[0103] For details regarding the embodiments of this application, please refer to the description of the above method embodiments. For the sake of brevity, these details will not be repeated here.

[0104] Corresponding to the above embodiments, this application also provides a vehicle, see [link to previous embodiment]. Figure 9 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Figure 9 As shown, vehicle 900 includes controller 901, which is configured to perform the method described in any of the method embodiments.

[0105] For details regarding the embodiments of this application, please refer to the description of the above method embodiments. For the sake of brevity, these details will not be repeated here.

[0106] Corresponding to the above embodiments, this application also provides a computer-readable storage medium, wherein the computer-readable storage medium may store a program, and when the program runs, it can control the device where the computer-readable storage medium is located to execute some or all of the steps in the above method embodiments. In specific implementation, the computer-readable storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0107] For details regarding the embodiments of this application, please refer to the description of the above method embodiments. For the sake of brevity, these details will not be repeated here.

[0108] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0109] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. 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.

[0110] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the above-described apparatus, controller, and computer storage medium can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0111] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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 described in the various embodiments of this application. 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.

[0112] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for alarming faults in a power battery, characterized in that, include: Based on the voltage data of multiple cells in the power battery at the current moment, the actual voltage difference of the power battery at the current moment is determined. The actual voltage difference is the voltage difference between the cell with the highest voltage and the cell with the lowest voltage among the multiple cells. Based on the current battery state data of the power battery, determine the expected voltage difference of the power battery at the current moment; If the actual pressure difference at the current moment and the expected pressure difference at the current moment meet the preset conditions, a power battery fault alarm signal will be output.

2. The method according to claim 1, characterized in that, If the actual pressure difference at the current moment and the expected pressure difference at the current moment meet a preset condition, a power battery fault alarm signal is output, including: If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the voltage data of multiple cells in the power battery at the current moment meet the preset conditions, then a power battery fault alarm signal is output.

3. The method according to claim 2, characterized in that, If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the voltage data of multiple cells in the power battery at the current moment meet preset conditions, then a power battery fault alarm signal is output, including: Based on the voltage data of multiple cells in the power battery at the current moment, a first auxiliary feature is determined at the current moment. The first auxiliary feature is used to characterize the voltage dispersion of the multiple cells. If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the first auxiliary feature at the current moment meet the preset conditions, then a power battery fault alarm signal is output.

4. The method according to claim 2, characterized in that, If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the voltage data of multiple cells in the power battery at the current moment meet preset conditions, then a power battery fault alarm signal is output, including: Based on the voltage data of multiple cells in the power battery at the current moment and the average voltage of each cell in the multiple cells within a first preset time interval, a second auxiliary feature is determined at the current moment. The second auxiliary feature is used to characterize the voltage fluctuation of the multiple cells. If the actual pressure difference at the current moment, the expected pressure difference at the current moment, and the second auxiliary feature at the current moment meet the preset conditions, then a power battery fault alarm signal is output.

5. The method according to claim 1, characterized in that, Determining the desired voltage difference of the power battery at the current moment based on the battery state data of the power battery at the current moment includes: The battery state data of the power battery at the current moment is input into the expected voltage prediction model, and the expected voltage difference of the power battery at the current moment is output. The expected voltage prediction model is a model trained with a preset dataset. The preset dataset includes multiple sets of battery state data and multiple actual voltage differences corresponding to the multiple sets of battery state data.

6. The method according to claim 1, characterized in that, If the actual pressure difference at the current moment and the expected pressure difference at the current moment meet a preset condition, a power battery fault alarm signal is output, including: If the differential pressure deviations at multiple times within a second preset time interval including the current time meet preset conditions, a power battery fault alarm signal is output, wherein the differential pressure deviation is the difference between the actual differential pressure and the expected differential pressure.

7. The method according to claim 1, characterized in that, After outputting a power battery fault alarm signal if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet a preset condition, the method further includes: If the actual voltage difference at the current moment and the expected voltage difference at the current moment meet the preset conditions, the information of the faulty battery cell is output. The faulty battery cell is the battery cell with the highest voltage and the battery cell with the lowest voltage among the multiple battery cells at the current moment.

8. A power battery fault alarm device, characterized in that, include: The actual voltage difference acquisition module is used to determine the actual voltage difference of the power battery at the current moment based on the voltage data of multiple cells in the power battery at the current moment. The actual voltage difference is the voltage difference between the cell with the highest voltage and the cell with the lowest voltage among the multiple cells. The desired pressure difference acquisition module is used to determine the desired pressure difference of the power battery at the current moment based on the battery state data of the power battery at the current moment. The fault alarm module is used to output a power battery fault alarm signal if the actual pressure difference at the current moment and the expected pressure difference at the current moment meet preset conditions.

9. A vehicle, characterized in that, include: A controller configured to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 7.

Images