A vehicle and a method, apparatus for detecting self-discharge of a battery pack of the vehicle

Abstract

A vehicle and a method, apparatus for detecting self-discharge of a battery pack of the vehicle are described. The method includes obtaining recorded data of the battery pack; determining a set of associated recorded data based on the recorded data, wherein the set of associated recorded data is associated with last recorded data before the vehicle enters hibernation and first recorded data after the vehicle wakes up; determining a self-discharge value of each battery in the battery pack based at least in part on the set of associated recorded data; storing a set of specified feature data of a single battery with a largest self-discharge value in the battery pack to create a profile; inputting the set of specified feature data in the profile into a detection function model to generate a self-discharge detection result of the battery pack. The application also includes an apparatus for detecting self-discharge of a battery pack of a vehicle, a vehicle comprising the apparatus and the battery pack, and numerous other aspects.

Description

Technical Field

[0001] This invention relates to the field of vehicle battery technology, and more specifically to a method and apparatus for detecting the self-discharge of a vehicle's battery pack. Background Technology

[0002] With the popularization of new energy vehicles, battery self-discharge has become an increasingly important concern. Self-discharge not only affects battery lifespan, leading to battery degradation, performance decline, and vehicle thermal runaway, but can even cause safety issues. Therefore, online rapid identification and early warning of abnormal battery self-discharge are of great significance. However, traditional self-discharge detection methods are time-consuming, inefficient, and easily affected by external factors. In existing technologies, methods that calculate battery voltage dispersion through large amounts of data are affected by factors such as voltage sampling and battery internal resistance, increasing errors. Furthermore, experience and knowledge from fault analysis indicate that most internal battery errors cause high self-discharge when the vehicle is parked at a high state of charge (SOC).

[0003] Real-time monitoring (RTM) data collection is a data collection activity conducted according to GB / T 32960 requirements. Whenever a vehicle is awakened (driving, charging), it collects high-voltage battery-related data for battery electric vehicles (BEVs) / plug-in hybrid electric vehicles (PHEVs) and transmits it to the cloud at 30-second intervals. With data analysis focusing on battery self-discharge, RTM data has been recognized as an important resource. However, directly calculating battery voltage statistics (such as deviation and standard deviation) involves a massive amount of data, requiring significant data processing resources and resulting in low efficiency. Furthermore, current RTM data structures do not differentiate between data collected before the vehicle enters sleep mode and data collected after the vehicle is awakened, leading to low accuracy.

[0004] This application proposes a vehicle and a method and apparatus for detecting the self-discharge of the vehicle's battery pack, which can efficiently and accurately detect and predict the self-discharge results of the vehicle's battery pack. Summary of the Invention

[0005] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not an exhaustive summary of all conceived aspects, nor is it intended to identify the key or decisive elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed descriptions that follow.

[0006] To address the aforementioned problems, this invention proposes a vehicle and a method and apparatus for detecting the self-discharge of the vehicle's battery pack.

[0007] In one aspect, this application describes a method for detecting the self-discharge of a vehicle's battery pack, comprising: acquiring recorded data of the battery pack; determining an associated record dataset based on the recorded data, wherein the associated record dataset is associated with the last recorded data before the vehicle enters hibernation and the first recorded data after the vehicle wakes up; determining the self-discharge value of each battery in the battery pack based at least in part on the associated record dataset; storing a specified feature dataset of a single battery in the battery pack with the maximum self-discharge value to create a configuration file; and inputting the specified feature dataset from the configuration file into a detection function model to generate a self-discharge detection result for the battery pack.

[0008] Preferably, determining the associated record dataset includes: in response to the difference in timestamps between two consecutive records being greater than a specified time threshold: identifying the record with the earlier time among the two records as the last record before the vehicle enters hibernation, and setting the first Boolean label of the last record to 1 and the second Boolean label to 0; identifying the record with the later time among the two records as the first record after the vehicle wakes up, and setting the first Boolean label and the second Boolean label of the first record to 1; setting the first Boolean label and the second Boolean label of the remaining data to 0; and creating the associated record dataset by setting all records with the first Boolean label to 1.

[0009] Preferably, determining the self-discharge value of each battery in the battery pack based at least in part on the associated record dataset includes: calculating the self-discharge value of each battery using the difference between the cell voltage of the last recorded data and the cell voltage of the first recorded data in the associated record dataset; and the method further includes: identifying a single battery in the battery pack with the maximum self-discharge value, and setting a third Boolean class label indicating the maximum self-discharge value of that battery to 1.

[0010] Preferably, storing the specified feature dataset includes storing the specified feature dataset in the record dataset whose third Boolean class label is set to 1. The specified feature dataset includes: the collection timestamp of the specified feature data, cumulative mileage, total battery voltage, state of charge (SOC), maximum self-discharge value, second maximum self-discharge value, battery identifier ID corresponding to the maximum self-discharge value, and the difference between the maximum self-discharge value and the second maximum self-discharge value.

[0011] Preferably, creating the configuration file includes storing the specified feature dataset for a predetermined time period.

[0012] Preferably, the detection function model includes at least one of the following: a first function model associated with continuous self-discharge cell ID checking; or a second function model associated with significant high self-discharge value checking; or a third function model associated with large cell voltage deviation detection of the battery pack.

[0013] Preferably, determining the self-discharge detection result of the battery pack includes: generating the detection function model based at least in part on the first functional model, the second functional model, and the third functional model, wherein each functional model has an associated weighting factor; and determining that the self-discharge detection result of the corresponding individual battery has a potential fault in response to the output of the detection function model exceeding a specified threshold.

[0014] On the other hand, this application describes an apparatus for detecting the self-discharge of a vehicle's battery pack, comprising: a data acquisition module for acquiring recorded data of the battery pack; a processing module for determining an associated record dataset based on the recorded data, wherein the associated record dataset is associated with the last recorded data before the vehicle enters hibernation and the first recorded data after the vehicle wakes up; determining the self-discharge value of each battery in the battery pack based at least in part on the associated record dataset; a storage module for storing a specified feature dataset of a single battery in the battery pack with the maximum self-discharge value to create a configuration file; and a detection module for inputting the specified feature dataset from the configuration file into a detection function model to generate a self-discharge detection result for the battery pack.

[0015] Preferably, the processing module determines the associated record dataset by: in response to the difference in timestamps between two consecutive records being greater than a specified time threshold: identifying the record data with the earlier time among the two records as the last record data before the vehicle enters hibernation, and setting the first Boolean label of the last record data to 1 and the second Boolean label to 0; identifying the record data with the later time among the two records as the first record data after the vehicle wakes up, and setting the first Boolean label and the second Boolean label of the first record data to 1; setting the first Boolean label and the second Boolean label of the remaining data to 0; and creating the associated record dataset by setting all records with the first Boolean label to 1.

[0016] Preferably, the processing module determines the self-discharge value of each battery in the battery pack by: calculating the self-discharge value of each battery using the difference between the cell voltage of the last recorded data and the cell voltage of the first recorded data in the associated record dataset; and the processing module is further configured to identify a single battery in the battery pack with the maximum self-discharge value, and set the third Boolean class label of that battery indicating the maximum self-discharge value to 1.

[0017] Preferably, the storage module stores the specified feature dataset by storing: the specified feature dataset in the record dataset whose third Boolean class label is set to 1, wherein the specified feature dataset includes: the collection timestamp of the specified feature data, cumulative mileage, total battery voltage, state of charge (SOC), maximum self-discharge value, second maximum self-discharge value, battery identifier ID corresponding to the maximum self-discharge value, and the difference between the maximum self-discharge value and the second maximum self-discharge value.

[0018] Preferably, the storage module creates the configuration file by storing the specified feature dataset for a predetermined time period.

[0019] Preferably, the detection function model includes at least one of the following: a first function model associated with continuous self-discharge cell ID checking; or a second function model associated with significant high self-discharge value checking; or a third function model associated with large cell voltage deviation detection of the battery pack.

[0020] Preferably, the detection module generates the self-discharge detection result of the battery pack by: generating the detection function model based at least in part on the first functional model, the second functional model, and the third functional model, wherein each functional model has an associated weighting factor; and determining that the self-discharge detection result of the corresponding individual battery has a potential fault in response to the output of the detection function model exceeding a specified threshold.

[0021] In another aspect, this application describes a vehicle comprising: a battery pack, and a device for detecting the self-discharge of the battery pack as described above.

[0022] In another aspect, this application describes a computer-readable storage medium having a computer program stored thereon, characterized in that the program is executed by a processor to implement the method for detecting the self-discharge of a battery pack as described above.

[0023] This synopsis is provided to introduce some concepts in a simplified form, which will be further described in the detailed description below. This synopsis is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. Other aspects, features, and / or advantages of the embodiments will be set forth in part in the description which follows, and will be apparent in part from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0024] To gain a detailed understanding of the manner in which the above-described features of the invention are employed, a more specific description of the above-briefly summarized content can be provided with reference to various embodiments, some of which are illustrated in the accompanying drawings. However, it should be noted that the drawings only illustrate certain typical aspects of the invention and should not be considered as limiting its scope, as this description may allow for other equivalent aspects. In the drawings, similar reference numerals are consistently used for similar purposes. It should be noted that the described drawings are merely schematic and non-limiting. In the drawings, the dimensions of some components may be enlarged and are not drawn to scale for illustrative purposes.

[0025] Figure 1 An example of a method for detecting the self-discharge of a vehicle's battery pack according to an embodiment of the present invention has been explained.

[0026] Figure 2 A schematic diagram illustrating data acquisition for analyzing the open-circuit voltage behavior of vehicle battery pack cells according to an embodiment of the present invention is provided.

[0027] Figure 3 The two types of battery cell self-discharge faults were explained.

[0028] Figures 4A to 4D A functional model supporting the detection of self-discharge of a vehicle's battery pack, according to an embodiment of the present invention, is explained.

[0029] Figure 5 A block diagram illustrating a device for detecting the self-discharge of a vehicle's battery pack, according to an embodiment of the present invention, is provided.

[0030] Figure 6 A block diagram of an exemplary computing device according to an embodiment of the present invention is shown, which is an example of a hardware device applicable to various aspects of the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the described exemplary embodiments. However, it will be apparent to those skilled in the art that the described embodiments can be practiced without some or all of these specific details. In other exemplary embodiments, well-known structures or processing steps have not been described in detail to avoid unnecessarily obscuring the concepts of this disclosure.

[0032] In this specification, unless otherwise stated, the term "A or B" as used herein refers to "A and B" and "A or B", and does not imply that A and B are exclusive.

[0033] Conventionally, factors such as voltage sampling and battery internal resistance can increase the detection error of high self-discharge caused by internal errors in lithium-ion batteries. Fault analysis experience and knowledge indicate that most internal battery errors lead to high self-discharge when the vehicle is parked at a high state of charge (SOC). Furthermore, as data analysis focuses on battery self-discharge, real-time monitoring (RTM) data has been recognized as an important resource. This data can collect and transmit the individual cell voltages of the entire high-voltage battery pack every 30 seconds, providing a basis for fault analysis of lithium-ion battery cells.

[0034] This application provides a database to generate vehicle profiles by setting specific tags and filtering RTM data before and after parking. This reflects whether any potential faulty batteries will affect the high-voltage battery pack or vehicle functionality in the near future, and can be verified through long-term curves of actual fault cases. The following is combined with... Figures 1 to 6 A detailed description is provided of a vehicle according to an embodiment of the present invention, as well as a method and apparatus for detecting the self-discharge of the vehicle's battery pack.

[0035] Figure 1 An example of a method 100 for detecting the self-discharge of a vehicle's battery pack according to an embodiment of the present invention has been explained.

[0036] In an embodiment of this application, method 100 may include step 105: acquiring recorded data of the vehicle's battery pack.

[0037] In the embodiments of this application, RTM data of the vehicle's battery pack can be obtained. RTM data is the collection of real-time operating data of new energy vehicles as required by national standard 32960. This collection includes key data tags such as basic vehicle information and high-voltage batteries, for example, collection timestamp, cumulative mileage, total battery voltage, SOC, total battery current, highest single-cell voltage, lowest single-cell voltage, cell voltage array, etc.

[0038] RTM data sampling is required during vehicle wake-up (driving, charging) with intervals not exceeding 30 seconds. For example, RTM data can collect and transmit the cell voltage of individual cells in the entire high-voltage battery pack every 30 seconds, providing a basis for fault analysis of lithium-ion battery cells. An example of RTM data is shown in Table 1 below:

[0039]

[0040] It should be understood that any other suitable battery pack may be used to record data without departing from the scope of this disclosure.

[0041] In embodiments of this application, method 100 may include step 110: determining an associated record dataset based on recorded data, wherein the associated record dataset is associated with the last recorded data before the vehicle entered hibernation and the first recorded data after the vehicle woke up. For example, the associated record dataset (which may also be referred to herein as a record data table or record database) may be formed by selecting only the data including the last record before the vehicle entered hibernation and the first record after the vehicle woke up.

[0042] In the embodiments of this application, the data acquisition time of RTM data can be filtered. For extremely large amounts of RTM data, directly calculating the dispersion and standard deviation of each cell would place high demands on system resources. Furthermore, since the battery is under load for most of the data acquisition time, the internal resistance of the cells will have a significant impact on the results, thus affecting the accuracy of self-discharge judgment. Therefore, the data acquisition time can be filtered, for example, by referring to... Figure 2 The data collection shown is for the analysis of the open-circuit voltage behavior of electric vehicle battery cells. Figure 2 The diagram 200 shows the changes in battery cell voltage under different vehicle conditions, along with the data acquisition points during these changes. For example, Figure 2 The diagram shows the vehicle's driving status (e.g., including 202a, 202b, 202c, 202d, etc.), charging status (e.g., including 204a, etc.), and parking status (e.g., including 206a, 206b, 206c, etc.). During the first parking status 206a and the third parking status 206c, because the parking time exceeds a time threshold (generally specified as 1.5 hours), the vehicle enters a sleep mode, and the battery cells can be depolarized to an open-circuit voltage state (e.g., ...). Figure 2 As shown in Figure 210), the above parking status is set as a high-quality data collection point (e.g., Figure 2 As shown in Figure 215); while in the second parking state 206b, because the short-term parking time is less than the time threshold (as shown in Figure 215), Figure 2 If (as shown in Figure 220), then data will not be collected under this parking state.

[0043] In embodiments of this application, a label can be set for each data record of the same vehicle in the RTM database to indicate that the specified data record is the last data record before the vehicle enters hibernation or the first data record after the vehicle wakes up. For example, a first Boolean label `label_stop_start` and a second Boolean label `label_start` can be set for each RTM data record. The label value is calculated by the difference between the timestamps `data_collection_time` between two consecutive data records. Once the label value is lower than a set time threshold, the first Boolean label `label_stop_start` is set to 1; otherwise, the first Boolean label `label_stop_start` is set to 0.

[0044] In embodiments of this application, taking into account the chemical and physical characteristics of the battery cell, a time threshold (e.g., a dormancy time threshold) can be specified as 1.5 hours. The dataset with first and second Boolean class labels (as shown in the boxes) is shown in Table 2, below, recording data collected from 00:38:33 on 2023-07-03 to 08:39:56 on 2023-07-03.

[0045]

[0046] In embodiments of this application, if the data is the first record after the vehicle wakes up, its second Boolean label_start is set to 1; otherwise, its second Boolean label_start is set to 0. In other words, determining the associated record dataset based on the recorded data can include performing the following actions in response to a timestamp difference between two consecutive records exceeding a specified time threshold: identifying the earlier record as the last record before the vehicle entered hibernation, and setting the first Boolean label of the last record to 1 and the second Boolean label to 0; identifying the later record as the first record after the vehicle wakes up, and setting the first Boolean label and the second Boolean label of the first record to 1; and setting the first Boolean label and the second Boolean label of the remaining data to 0. Additionally or alternatively, if the second Boolean label_start of the data is 1, the self-discharge and battery voltage diffusion of each battery in the high-voltage battery pack can be calculated, as described in more detail below.

[0047] In the embodiments of this application, a dataset of data records for all data with the first Boolean label `label_stop_start=1` is created as an associated record dataset, which also includes all data with the second Boolean label `label_start=1`. Table 3 below shows an example of an associated record dataset for a pure electric vehicle that includes only data from before parking and after starting, and which meets the sleep time threshold:

[0048]

[0049] In an embodiment of this application, method 100 may include step 115: determining the self-discharge value of each battery in the battery pack based at least in part on an associated record dataset.

[0050] In the embodiments of this application, if the second Boolean label_start of the data is 1, the self-discharge value of each battery can be calculated by the difference between the cell voltage of the last record before the vehicle enters hibernation and the cell voltage of the first record after the vehicle wakes up. When the data label_start is 1, i.e., at the start time, the voltage change of each cell relative to the parking time is calculated, and an array is created containing the voltage change elements of each cell. Table 4 below shows data examples of the voltage changes of each cell during parking for a certain pure electric vehicle from August 29, 2024 to September 2, 2024, with abnormal cell voltage changes marked in the boxes.

[0051]

[0052] In an embodiment of this application, method 100 may include step 120: storing a specified feature dataset of a single battery in the battery pack with the maximum self-discharge value to create a profile.

[0053] In the embodiments of this application, the calculated array of battery self-discharge values ​​can be compared to determine whether only one battery has the maximum self-discharge value.

[0054] In embodiments of this application, a third Boolean label, is_record_valid, can be set to indicate a valid record. This label is set to 1 (TRUE) if and only if the maximum self-discharge value of the cell is lower than the second maximum self-discharge value of the cell, and 0 (FALSE) otherwise, thereby further filtering out invalid data. For example, invalid data could be a situation where all batteries in the cell discharge as a whole, resulting in the maximum self-discharge value of the cell being equal to the second maximum self-discharge value of the cell, as described in more detail below.

[0055] In embodiments of this application, another data record table can be created as a long-term vehicle configuration file within a specified time (e.g., 30 days, 90 days, etc.) to record each dataset when the third Boolean class label is_record_valid.

[0056] In embodiments of this application, if the third Boolean class label is_record_valid = 1, necessary data can be stored, such as data collection timestamps, mileage, SOC, high-voltage battery current, and some other statistical values, including the maximum self-discharge value, the second largest self-discharge value, the maximum battery voltage in the battery pack, the battery identifier ID corresponding to the maximum self-discharge value, and the difference between the maximum self-discharge value and the second largest self-discharge value, etc. For example, if the third Boolean class label is_record_valid = 1 in specific data, the following specified feature dataset for this data is returned: collection time, cumulative mileage, total battery voltage, SOC, maximum battery self-discharge value, second largest battery self-discharge value (also known as the second largest self-discharge value), maximum self-discharge cell number, difference between the maximum and the second largest value, valid marker (is_record_valid), voltage value and number of the highest voltage cell, voltage value and number of the lowest voltage cell, voltage value and number of the second lowest voltage cell, etc. Table 5 below shows the dataset with the third Boolean class label is_record_valid set to 1, which includes the corresponding specified feature dataset. As shown in the box in Table 5, the maximum self-discharge value of cell ID 17 is lower than the second maximum self-discharge value, so its third Boolean label is_record_valid is set to 1 (true). The maximum self-discharge value of the other cells (e.g., cell IDs 1, 3, 2, etc.) is equal to the second maximum self-discharge value, so they are invalid data, and the third Boolean label is_record_valid is set to 0 (false).

[0057]

[0058] In embodiments of this application, method 100 may include step 125: inputting a specified feature dataset from a configuration file into a detection function model to generate self-discharge detection results for the battery pack. See the following reference... Figure 3 as well as Figures 4A to 4D More detailed description.

[0059] Figure 3 Figure 300 illustrates two types of cell self-discharge faults. Figures 4A to 4D A functional model supporting the detection of self-discharge of a vehicle's battery pack, according to an embodiment of the present invention, is explained.

[0060] like Figure 3As shown, the two fault modes of cell self-discharge include: slow self-discharge and sudden self-discharge. Figure 3 The diagram on the left shows how slow self-discharge causes a gradual and significant deviation in the cell voltage within the battery pack. Figure 3 The arrows in the figure represent the voltage of the failed battery cell, which gradually decreases over time. The dashed lines represent the voltage changes over time for the normal battery cell 305 and the failed battery cell 310, respectively. As can be seen from the figure, during on-board diagnostic testing (e.g., in...), Figure 3 (At the vertical line in the image), there is a significant voltage difference between the normal cell 305 and the failed cell 310. Figure 3 The diagram on the right shows a significant deviation in cell voltage within the battery pack caused by sudden self-discharge. Similarly, the arrow represents the voltage of the failed cell 305, which drops sharply over a short period. The dashed lines represent the voltage changes over time for the normal cell 305 and the failed cell 310, respectively. During on-board diagnostic testing (e.g., in...), Figure 3 (At the vertical line in the text), there is a significant voltage deviation between normal cell 305 and failed cell 310.

[0061] Both of these failure modes can affect the overall performance and reliability of the battery cell. According to the failure sample database, the failure modes of cell self-discharge can be roughly divided into the above two types. In order to realize the detection function to cover the above different cell failure modes, different sub-functional models are needed to realize fault detection.

[0062] In embodiments of this application, three different functional models can be created based on the configuration file, including: Figure 4A The first functional model F1 shown is used for continuous self-discharge cell number (cell ID) checking; Figure 4B The second functional model F2 shown is used for detecting significantly high self-discharge; and Figure 4C The third functional model F3 shown is used for detecting large cell voltage deviations in the battery pack.

[0063] In embodiments of this application, a first functional model associated with continuous self-discharge cell ID checking can detect whether a certain cell ID is continuously reported as the cell with the highest self-discharge, calculate a failure function and compare it with a first threshold, thereby determining whether the cell has a potential fault. Preferably, the cell ID with the highest self-discharge and the SOC in the configuration file can be input into the first functional model, and the probability of the cell ID having a potential fault can be calculated by taking the SOC into account through a recursive (filtering) function, so as to detect whether the cell ID is continuously reported as the cell with the highest self-discharge.

[0064] Specifically, the first functional model can be described as:

[0065] At time t:

[0066] Step 1: For cell_max_voltage_drop_id (maximum self-discharge cell number), compare the input at time t with the input at time t-1, and generate the intermediate variable cell_id_same (same cell number), which is also used as the input u of the filter function. t .

[0067] Step 2.1: When cell_id_same = 1, calculate k. t =soc * 0.01 * 0.5 + 0.5, resulting in k, which is between 0.5 and 1. t And calculate y t =k t (u t +y t-1 )

[0068] Step 2.2: When cell_id_same = 0, calculate k. t =0.5, and calculate y t =k t (u t +y t-1 )

[0069] Additionally, at time t1, i.e., when the input is the first data item in the dataset, the default values ​​are cell_id_same = u1 = 0 and y0 = 0.

[0070] The advantage of using the first functional model is that when a cell ID is continuously detected as the cell number with the highest self-discharge during high SOC shutdown, its y t It will quickly rise above the threshold, thus rapidly determining that the cell has a potential fault; when the cell ID is discontinuous, due to k t =0.5, its y t It will rebound quickly to avoid false alarms. Additional or replacement grounds can also be used; other Y-type grounds can be employed. t or k t The value is used to achieve the first functional model described above without departing from the scope of this application.

[0071] In embodiments of this application, a second functional model associated with a significant high self-discharge check can indicate whether a single battery has a self-discharge value larger than all other batteries, thereby detecting whether a particular cell exhibits a significant high self-discharge and determining whether the cell has a potential fault. For example, in the examples in Table 5 above, cell ID 17 experienced a 160mV self-discharge at 08:25:52 on August 30, 2024, while all other cells did not show a voltage drop. Preferably, the maximum self-discharge value and the second maximum value of the cell in the configuration file can be input into the second functional model to obtain the difference between the maximum value and the second maximum value. If this difference is higher than a second threshold (e.g., 30mV, etc.), a positive result is given, indicating that the cell has a potential fault.

[0072] Specifically, the second functional model can be described as:

[0073] Step 1: Input the array of cell voltage changes and take the minimum value, which is the maximum self-discharge value of the cell.

[0074] Step 2: Input the array of cell voltage changes and take the second minimum value, which is the second maximum value of cell self-discharge.

[0075] Step 3: Calculate the difference between the maximum value and the second maximum value, and compare it with the set second threshold of 30mV to determine the result.

[0076] In the embodiments of this application, the third functional model associated with the detection of large cell voltage deviations in the battery pack can verify whether the suspicious cells detected by the first or second functional model are causing excessive cell voltage deviations within the battery pack. It determines whether a cell is experiencing self-discharge by detecting whether the cell voltage deviation exceeds a set threshold. In the example shown in Table 6 below, the cell voltage deviation increased from 30mV to 190mV on 2024-08-30 at 08:25:52.

[0077]

[0078] Preferably, the cell voltage dataset in the configuration file can be input into the third functional model. If the maximum cell voltage value minus the minimum cell voltage value is greater than or equal to the third threshold, and the second minimum cell voltage value minus the minimum cell voltage value is greater than or equal to the fourth threshold, then a positive result is given: the cell voltage deviation in the battery pack is too large, and the cell has a potential fault.

[0079] Specifically, the third functional model can be described as:

[0080] Step 1: Input the cell voltage array, and take the maximum value, minimum value, and second minimum value;

[0081] Step 2: Calculate the maximum and minimum cell deviations, and the second minimum and minimum cell deviations;

[0082] Step 3: Compare the maximum and minimum cell deviations, and the second minimum and minimum cell deviations with the set thresholds. When the maximum and minimum cell deviations are greater than or equal to 50mV and the second minimum and minimum cell deviations are greater than or equal to 40mV, it is determined that the cell voltage deviations in the battery pack are too large.

[0083] In the embodiments of this application, such as Figure 4D As shown, a final detection functional model can be created, which is calculated by summing (SUM) the results of the three functional models (F1, F2, F3) mentioned above. Each functional model has a weighting factor (WF1, WF2, WF3) to determine whether a cell has a potential fault. A positive result (POSITIVE) is given if the threshold is exceeded (e.g., 0.6), and a negative result (NEGATIVE) is given otherwise. Preferably, the weighting factors can be determined by machine learning. Additionally or alternatively, the first weighting factor WF1 of the first functional model can be 0.35, the second weighting factor WF2 of the second functional model can be 0.4, and the third weighting factor WF3 of the third functional model can be 0.25.

[0084] Figure 5 A block diagram of a device 500 for detecting the self-discharge of a vehicle's battery pack, according to an embodiment of the present invention, is described.

[0085] like Figure 5 As shown, the device for detecting the self-discharge of a vehicle's battery pack according to this application may include a data acquisition module 505, a processing module 510, a storage module 515, and a detection module 520.

[0086] In embodiments of this application, the data acquisition module 505 can be used to acquire recorded data from the battery pack. For example, the data acquisition module 505 can acquire RTM data from the vehicle's battery pack. RTM data sampling is required during vehicle wake-up periods (driving, charging), with intervals not exceeding 30 seconds. For example, RTM data can be collected and transmitted every 30 seconds for the cell voltage of a single cell in the entire high-voltage battery pack, providing a basis for fault analysis of lithium-ion battery cells.

[0087] In embodiments of this application, processing module 510 can be used to determine an associated record dataset based on recorded data, wherein the associated record dataset is associated with the last recorded data before the vehicle enters hibernation and the first recorded data after the vehicle wakes up; and to determine the self-discharge value of each battery in the battery pack based at least in part on the associated record dataset. Preferably, processing module 510 determining the associated record dataset may include: in response to the difference in timestamps between two consecutive records being greater than a specified time threshold: identifying the earlier recorded data as the last recorded data before the vehicle enters hibernation, and setting a first Boolean class label of the last recorded data to 1 and a second Boolean class label to 0; identifying the later recorded data as the first recorded data after the vehicle wakes up, and setting a first Boolean class label and a second Boolean class label of the first recorded data to 1; setting the first Boolean class label and a second Boolean class label of the remaining data to 0; and creating an associated record dataset of records with all first Boolean class labels set to 1. Preferably, the processing module 510 determining the self-discharge value of each battery in the battery pack may include: calculating the self-discharge value of each battery using the difference between the cell voltage of the last recorded data and the cell voltage of the first recorded data in the associated record dataset; and the method further includes: identifying a single battery in the battery pack with the maximum self-discharge value, and setting the third Boolean class label of that battery indicating the maximum self-discharge value to 1.

[0088] In embodiments of this application, the storage module 515 can be used to store a specified feature dataset of a single battery in the battery pack with the maximum self-discharge value to create a configuration file. Preferably, the storage module 515 stores the specified feature dataset by storing a specified feature dataset from a record dataset with a third Boolean class label set to 1. The specified feature dataset includes: the collection timestamp of the specified feature data, cumulative mileage, total battery voltage, state of charge (SOC), maximum self-discharge value, second maximum self-discharge value, battery identifier ID corresponding to the maximum self-discharge value, and the difference between the maximum self-discharge value and the second maximum self-discharge value. Preferably, the storage module 515 creates the configuration file by storing the specified feature dataset within a predetermined time period.

[0089] In embodiments of this application, the detection module 520 can be used to input a specified feature dataset from a configuration file into a detection function model to generate self-discharge detection results for the battery pack. The detection function model may include at least one of the following: a first function model associated with continuous self-discharge cell ID checks; a second function model associated with checks for significantly high self-discharge values; or a third function model associated with detection of large cell voltage deviations in the battery pack. Preferably, the detection module 520 generates the self-discharge detection results for the battery pack by: generating the detection function model at least partially based on the first, second, and third function models, wherein each function model has an associated weighting factor; and determining that the self-discharge detection result of the corresponding individual battery has a potential fault in response to the output of the detection function model exceeding a specified threshold.

[0090] Figure 6 A block diagram of an exemplary computing device according to an embodiment of the present invention is shown, which is an example of a hardware device applicable to various aspects of the present invention. For example, the hardware device may be a vehicle or other means of transportation. Additionally or alternatively, the vehicle in this application may include a battery and the computing device (which may also be used as an on-board device).

[0091] refer to Figure 6 A computing device 600 will now be described as an example of a hardware device applicable to various aspects of the present invention. The computing device 600 can be any machine configured to perform processing and / or computation, and can be, but is not limited to, a workstation, server, desktop computer, laptop computer, tablet computer, personal digital processor, smartphone, in-vehicle computer, or any combination thereof. The various methods / apparatus / servers described above can be implemented wholly or at least partially by the computing device 600 or similar devices or systems.

[0092] The computing device 600 may include components that can be connected or communicated via one or more interfaces and a bus 602. For example, the computing device 600 may include a bus 602, one or more processors 604, one or more input devices 606, and one or more output devices 608. The one or more processors 604 may be any type of processor and may include, but are not limited to, one or more general-purpose processors and / or one or more dedicated processors (e.g., specialized processing chips). The input device 606 may be any type of device capable of inputting information to the computing device and may include, but is not limited to, a mouse, keyboard, touchscreen, microphone, and / or remote controller. The output device 608 may be any type of device capable of presenting information and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. The computing device 600 may also include or be connected to a non-transient storage device 610. The non-transient storage device can be any storage device that is non-transient and capable of data storage. This non-transient storage device may include, but is not limited to, disk drives, optical storage devices, solid-state drives, floppy disks, hard disks, magnetic tapes or any other magnetic media, optical discs or any other optical media, ROM (read-only memory), RAM (random access memory), cache memory, and / or any memory chip or magnetic tape cassette, and / or any other medium from which a computer can read data, instructions, and / or code. The non-transient storage device 610 may be detachable from an interface. The non-transient storage device 610 may have data / instructions / code for implementing the methods and steps described above. The computing device 600 may also include a communication device 612. The communication device 612 can be any type of device or system capable of communicating with internal devices and / or with a network, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication devices and / or chipsets, such as Bluetooth devices, IEEE 802.11 devices, WiFi devices, WiMax devices, cellular communication devices and / or similar devices.

[0093] When the computing device 600 is used as an in-vehicle device, it can also be connected to external devices (e.g., a GPS receiver, sensors for sensing different environmental data such as accelerometers, wheel speed sensors, gyroscopes, etc.). In this way, the computing device 600 can, for example, receive positioning data and sensor data indicating the vehicle's driving status. When the computing device 600 is used as an in-vehicle device, it can also be connected to other devices used to control the vehicle's driving and operation (e.g., engine system, windshield wipers, anti-lock braking system, etc.).

[0094] Furthermore, the non-transient storage device 610 may contain map information and software components, enabling the processor 604 to perform route guidance processing. Additionally, the output device 606 may include a display for showing a map, displaying vehicle location markers, and displaying images indicating the vehicle's driving status. The output device 606 may also include a speaker or headphone jack for audio guidance.

[0095] Bus 602 may include, but is not limited to, Industry Standard Architecture (ISA) bus, Microchannel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and PCI bus. In particular, for automotive devices, bus 602 may also include Controller Area Network (CAN) bus or other architectures designed for automotive applications.

[0096] The computing device 600 may also include a working memory 614, which may be any type of working memory capable of storing instructions and / or data that are conducive to the operation of the processor 604, and may include, but is not limited to, random access memory and / or read-only memory devices.

[0097] Software components may reside in working memory 614, including but not limited to operating system 616, one or more application programs 618, drivers, and / or other data and code. Instructions for implementing the above methods and steps may be contained in one or more application programs 618, and the modules / units / components of the aforementioned various devices / servers may be implemented by processor 604 reading and executing the instructions of one or more application programs 618.

[0098] The above describes a vehicle according to the present invention and a method and apparatus for detecting the self-discharge of the vehicle's battery pack. Compared with the prior art, the method of the present invention has at least the following advantages:

[0099] (1) Using a portion of the RTM data, the vehicle's battery self-discharge can be quickly identified and warned online, reducing the requirements for system processing resources and improving efficiency;

[0100] (2) Using specific tags to mark whether data records during parking are the last data record before the vehicle enters hibernation or the first data record after the vehicle wakes up, accurately detecting and predicting the self-discharge results of the vehicle battery pack; and

[0101] (3) The final detection function model includes three sub-function detection models, which cover the detection of two types of faults: slow self-discharge and sudden self-discharge of the cell.

[0102] Throughout this specification, reference has been made to "embodiments," meaning that a particular described feature, structure, or characteristic is included in at least one embodiment. Therefore, the use of these phrases may refer to more than one embodiment. Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0103] The various steps and modules of the methods and apparatus described above can be implemented in hardware, software, or a combination thereof. If implemented in hardware, the various illustrative steps, modules, and circuits described in connection with this disclosure can be implemented or executed using a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic components, hardware components, or any combination thereof. A general-purpose processor can be a processor, microprocessor, controller, microcontroller, or state machine, etc. If implemented in software, the various illustrative steps and modules described in connection with this disclosure can be stored as one or more instructions or codes on a computer-readable medium or transmitted. Software modules implementing the various operations of this disclosure can reside in a storage medium, such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, CD-ROM, cloud storage, etc. The storage medium can be coupled to a processor so that the processor can read and write information from / to the storage medium and execute corresponding program modules to implement the various steps of this disclosure. Moreover, software-based embodiments can be uploaded, downloaded, or remotely accessed through appropriate communication means. Such appropriate means of communication include, for example, the Internet, the World Wide Web, intranets, software applications, cables (including fiber optic cables), magnetic communication, electromagnetic communication (including RF microwave and infrared communication), electronic communication, or other such means of communication.

[0104] The numerical values ​​given in the various embodiments are merely examples and are not intended to limit the scope of the invention. Furthermore, as a whole, there are other components or steps not listed in the claims or specification of this invention. Moreover, a single name for a component does not preclude other names for that component.

[0105] It should also be noted that these embodiments may be described as processes depicted as flowcharts, flow diagrams, structure diagrams, or block diagrams. Although a flowchart may describe the operations as a sequential process, many of these operations can be executed in parallel or concurrently. Furthermore, the order of these operations can be rearranged.

[0106] The disclosed methods, apparatuses, and systems should not be limited in any way. Rather, this disclosure covers all novel and non-obvious features and aspects of the various disclosed embodiments (individually and in various combinations and sub-combinations of each other). The disclosed methods, apparatuses, and systems are not limited to any particular aspect or feature or combination thereof, and no disclosed embodiment is required to have any one or more specific advantages or to solve any particular or all technical problems.

[0107] This invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other modifications based on the teachings of this invention without departing from the spirit and scope of the claims. All of these modifications are within the scope of protection of this invention.

[0108] Those skilled in the art will recognize that these embodiments can be practiced without one or more specific details or using other methods, resources, materials, etc. In other cases, well-known structures, resources, or operations are not shown or described in detail merely for the purpose of observing obscure aspects of the embodiments.

[0109] While embodiments and applications have been described and illustrated, it should be understood that the embodiments are not limited to the precise configurations and resources described above. Various modifications, substitutions, and improvements that will be apparent to those skilled in the art may be made in the arrangement, operation, and details of the methods and systems disclosed herein without departing from the scope of the claimed embodiments.

[0110] As used herein, the terms “and,” “or,” and “and / or” may include a variety of meanings, which are also contemplated, at least in part, depending on the context in which such terms are used. Generally, “or,” when used to relate a list such as A, B, or C, is intended to mean A, B, and C (in the inclusive sense) and A, B, or C (in the exclusive sense). Additionally, the term “one or more” as used herein may be used to describe any feature, structure, or property in its singular form, or to describe multiple features, structures, or characteristics, or some other combination thereof. However, it should be noted that this is merely an illustrative example, and the claimed subject matter is not limited to this example.

[0111] While the features currently considered exemplary have been explained and described, those skilled in the art will understand that various other modifications can be made and equivalents can be substituted without departing from the claimed subject matter. Additionally, numerous modifications can be made to adapt a particular scenario to the teachings of the claimed subject matter without departing from the central concepts described herein.

Claims

1. A method for detecting the self-discharge of a vehicle's battery pack, comprising: Obtain the recorded data of the battery pack; Based on the recorded data, an associated record dataset is determined, wherein the associated record dataset is associated with the last recorded data before the vehicle entered hibernation and the first recorded data after the vehicle woke up; The self-discharge value of each battery in the battery pack is determined at least in part based on the associated record dataset; Store a specified feature dataset of the individual cells in the battery pack that have the maximum self-discharge value to create a configuration file; The specified feature dataset in the configuration file is input into the detection function model to generate the self-discharge detection results of the battery pack.

2. The method as described in claim 1, characterized in that, Determining the associated record dataset includes: The response is triggered when the difference between the timestamps of two consecutive records exceeds a specified time threshold. The earlier record of the two records is identified as the last record before the vehicle entered hibernation, and the first Boolean label of the last record is set to 1 and the second Boolean label is set to 0. The record with the later time among the two recorded data is identified as the first recorded data after the vehicle is woken up, and the first Boolean class label and the second Boolean class label of the first recorded data are set to 1; Set the first and second Boolean class labels of the remaining data to 0; and The dataset of records for which all first Boolean class labels are set to 1 is created as the associated record dataset.

3. The method as described in claim 1, characterized in that, Determining the self-discharge value of each battery in the battery pack includes: The self-discharge value of each battery is calculated using the difference between the cell voltage of the last recorded data and the cell voltage of the first recorded data in the associated record dataset. The method further includes: identifying a single battery in the battery pack with the maximum self-discharge value, and setting a third Boolean label indicating the maximum self-discharge value of that battery to 1.

4. The method as described in claim 3, characterized in that, The specified feature dataset includes: The specified feature dataset in the record dataset whose third Boolean class label is set to 1 is stored. The specified feature dataset includes: the collection timestamp of the specified feature data, the cumulative mileage, the total battery voltage, the state of charge (SOC), the maximum self-discharge value, the second maximum self-discharge value, the battery identifier ID corresponding to the maximum self-discharge value, and the difference between the maximum self-discharge value and the second maximum self-discharge value.

5. The method as described in claim 1, characterized in that, Creating the configuration file includes: The specified feature dataset is stored within a predetermined time period.

6. The method as described in claim 1, characterized in that, The detection function model includes at least one of the following: A first functional model, which is associated with continuous self-discharge cell ID checking; or A second functional model, which is associated with a significant high self-discharge value detection; or The third functional model is associated with the detection of large cell voltage deviations in the battery pack.

7. The method as described in claim 6, characterized in that, The self-discharge detection results of the battery pack include: The detection functional model is generated at least in part based on the first functional model, the second functional model, and the third functional model, wherein each functional model has an associated weighting factor; In response to the output of the detection function model exceeding a specified threshold, the self-discharge detection result of the corresponding individual battery is determined to indicate a potential fault.

8. A device for detecting the self-discharge of a vehicle's battery pack, comprising: The data acquisition module is used to acquire the recorded data of the battery pack; Processing module, which is used for Based on the recorded data, an associated record dataset is determined, wherein the associated record dataset is associated with the last recorded data before the vehicle entered hibernation and the first recorded data after the vehicle woke up; The self-discharge value of each battery in the battery pack is determined at least in part based on the associated record dataset; A storage module for storing a specified feature dataset of individual cells in the battery pack with the maximum self-discharge value to create a configuration file; as well as The detection module is used to input the specified feature dataset from the configuration file into the detection function model to generate the self-discharge detection results of the battery pack.

9. The apparatus as claimed in claim 8, characterized in that, The processing module determines that the associated record dataset includes: The response is triggered when the difference between the timestamps of two consecutive records exceeds a specified time threshold. The earlier record of the two records is identified as the last record before the vehicle entered hibernation, and the first Boolean label of the last record is set to 1 and the second Boolean label is set to 0. The record with the later time among the two recorded data is identified as the first recorded data after the vehicle is woken up, and the first Boolean class label and the second Boolean class label of the first recorded data are set to 1; Set the first and second Boolean class labels of the remaining data to 0; and The dataset of records for which all first Boolean class labels are set to 1 is created as the associated record dataset.

10. The apparatus as claimed in claim 8, characterized in that, The processing module determines the self-discharge value of each battery in the battery pack by including: The self-discharge value of each battery is calculated using the difference between the cell voltage of the last recorded data and the cell voltage of the first recorded data in the associated record dataset. Furthermore, the processing module is used to identify a single battery in the battery pack with the maximum self-discharge value, and to set the third Boolean label of that battery indicating the maximum self-discharge value to 1.

11. The apparatus as claimed in claim 10, characterized in that, The storage module stores the specified feature dataset, including: The specified feature dataset in the record dataset whose third Boolean class label is set to 1 is stored. The specified feature dataset includes: the collection timestamp of the specified feature data, the cumulative mileage, the total battery voltage, the state of charge (SOC), the maximum self-discharge value, the second maximum self-discharge value, the battery identifier ID corresponding to the maximum self-discharge value, and the difference between the maximum self-discharge value and the second maximum self-discharge value.

12. The apparatus as claimed in claim 8, characterized in that, The storage module creates the configuration file by: The specified feature dataset is stored within a predetermined time period.

13. The apparatus as claimed in claim 8, characterized in that, The detection function model includes at least one of the following: A first functional model, which is associated with continuous self-discharge cell ID checking; or A second functional model, which is associated with a significant high self-discharge value detection; or The third functional model is associated with the detection of large cell voltage deviations in the battery pack.

14. The apparatus as claimed in claim 13, characterized in that, The detection module generates the self-discharge detection results of the battery pack, including: The detection functional model is generated at least in part based on the first functional model, the second functional model, and the third functional model, wherein each functional model has an associated weighting factor; In response to the output of the detection function model exceeding a specified threshold, the self-discharge detection result of the corresponding individual battery is determined to indicate a potential fault.

15. A vehicle comprising: A battery pack, and a device for detecting the self-discharge of the battery pack as claimed in any one of claims 8-14.

Images