A voltage detection method, device, vehicle and storage medium

Abstract

The embodiment of the application discloses a voltage detection method, device, vehicle and storage medium, the method comprises: obtaining the data group of at least one time interval of target object;The data group includes the voltage of each battery cell contained by at least one battery pack of target object;According to the voltage of each battery cell contained by any battery pack contained in the data group of any time interval, the voltage of any battery pack in any time interval is obtained;The voltage of at least one battery pack in any time interval is clustered based on clustering algorithm, and a plurality of battery pack voltage clusters in any time interval are obtained;From the plurality of battery pack voltage clusters in at least one time interval, determine the suspected voltage outlier cluster and voltage outlier cluster;According to the number of suspected voltage outlier cluster and the number of voltage outlier cluster, determine whether the target object exists battery pack voltage outlier. The embodiment of the application can effectively detect the battery pack voltage, and ensure the efficient and safe operation of the battery system.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a voltage detection method, device, vehicle, and storage medium. Background Technology

[0002] With the rapid development of the new energy industry, batteries, as a core component of new energy sources, are gradually attracting consumer attention. While energy storage batteries offer advantages such as large capacity, high energy density, and long lifespan, their complex internal structure and manufacturing processes can lead to issues like excessively low or high voltage within the battery pack (Body Cell, BC). This can result in abnormal battery capacity and, in severe cases, even the risk of internal short circuits. Battery pack voltage outliers refer to significant differences or anomalies in the voltage of certain cells or individual cells within the battery pack compared to other cells. Therefore, effectively detecting battery pack voltage outliers is a problem that urgently needs to be solved. Summary of the Invention

[0003] This application provides a voltage detection method, device, vehicle, and storage medium that can effectively detect battery pack voltage and ensure the efficient and safe operation of the battery system.

[0004] In a first aspect, embodiments of this application provide a voltage detection method, the method comprising:

[0005] Acquire a data set for at least one time interval of the target object; the data set includes the voltage of each cell contained in at least one battery pack of the target object;

[0006] Based on the voltage of each cell in any battery pack contained in any data set within any time interval, the voltage of any battery pack in any time interval can be obtained.

[0007] Clustering algorithms are used to cluster the voltage of at least one battery pack in any time interval to obtain multiple battery pack voltage clusters in any time interval.

[0008] From multiple battery pack voltage clusters within at least one time interval, identify suspected voltage outliers and voltage outliers.

[0009] Based on the number of suspected voltage outlier clusters and the total number of voltage outlier clusters, determine whether the target object has battery pack voltage outliers.

[0010] Secondly, embodiments of this application provide a voltage detection device, which includes:

[0011] An acquisition unit is configured to acquire a data set of at least one time interval of a target object; the data set includes the voltage of each cell contained in at least one battery pack of the target object;

[0012] The processing unit is used to obtain the voltage of any battery pack in any time interval based on the voltage of each cell in any battery pack contained in a data set in any time interval.

[0013] The processing unit is also used to cluster the voltage of at least one battery pack in any time interval based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval.

[0014] The determination unit is used to identify suspected voltage outlier clusters and voltage outlier clusters from multiple battery pack voltage clusters over at least one time interval.

[0015] The determination unit is also used to determine whether the target object has a battery pack voltage outlier based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters.

[0016] In one embodiment, the method by which the determining unit determines voltage outlier clusters includes:

[0017] Obtain the first average voltage value of the voltage contained in the currently traversed suspected voltage outlier cluster, and the second average voltage value of each of the other suspected voltage outlier clusters in the at least one time interval besides the currently traversed suspected voltage outlier cluster.

[0018] Voltage outlier clusters are determined based on the first voltage mean and each of the second voltage means, until the traversal is complete.

[0019] In one embodiment, the determining unit determines voltage outlier clusters based on the first voltage mean and each of the second voltage means, until the traversal is complete, including:

[0020] If the absolute value of the difference between each second voltage mean and the first voltage mean is greater than the first preset voltage threshold, then the suspected voltage outlier cluster currently being traversed is identified as a voltage outlier cluster, until the traversal ends.

[0021] In one embodiment, the determining unit determines whether a target object has a battery pack voltage outlier based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, including:

[0022] If the ratio of the number of voltage outliers to the number of suspected voltage outliers is greater than a first preset ratio threshold, or if the difference between the number of voltage outliers and the number of other suspected voltage outliers (excluding voltage outliers) is greater than a preset number threshold, then it is determined that the target object has a battery pack voltage outlier.

[0023] In one embodiment, the acquisition unit is further configured to include:

[0024] Obtain object data of the target object; the object data of the target object includes the voltage of each cell in at least one battery pack of the target object during a historical time period;

[0025] The object data of the target object is divided to obtain at least one data group for the target object in at least one time interval.

[0026] In one embodiment, the object data further includes: the state of charge of each cell in at least one battery pack in the target object during the historical time period.

[0027] The processing unit divides the object data of the target object to obtain at least one data group of time interval of the target object, including: obtaining the voltage of each cell contained in the at least one battery pack at any time point from the object data;

[0028] From at least one voltage at any given time point, obtain the target voltage at that given time point; the target voltage is higher than the other voltages among the at least one voltage.

[0029] Obtain the target state of charge of the cell corresponding to the target voltage at any time point;

[0030] Based on the target voltage and the target state of charge, determine the target object data;

[0031] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0032] In one embodiment, the determining unit determines target object data based on the target voltage and the target state of charge, including:

[0033] If the target voltage is greater than the second preset voltage threshold and the target state of charge is greater than the second preset ratio threshold, then the object data at any time point in the object data is determined as the target object data.

[0034] In one embodiment, the object data further includes: the current of any cell in at least one battery pack in the target object during the historical time period;

[0035] The processing unit divides the object data of the target object to obtain at least one data group of time intervals of the target object, including: obtaining the current of any cell at any time point from the object data, and the current of any cell at k adjacent time points at any time point; k is a positive integer;

[0036] Based on the current at any given time point and the current at the k adjacent time points, determine the target object data;

[0037] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0038] In one embodiment, the determining unit determines target object data based on the current at any given time point and the currents at the k adjacent time points, including:

[0039] If the current at any given time point is less than a first preset current threshold, and the difference between the maximum and minimum currents among the currents at the adjacent k time points and the current at any given time point is less than a second preset current threshold, then the object data at any given time point in the object data is determined as the target object data.

[0040] In one embodiment, the processing unit clusters the voltages of at least one battery pack over any time interval based on a clustering algorithm, obtaining multiple battery pack voltage clusters over any time interval, including:

[0041] Based on the clustering algorithm, the voltage of at least one battery pack in any time interval is clustered to obtain multiple candidate battery pack voltage clusters;

[0042] If the number of multiple candidate battery pack voltage clusters is greater than a preset value, then the multiple candidate battery pack voltage clusters are clustered based on a clustering algorithm to obtain multiple clustered candidate battery pack voltage clusters.

[0043] If the number of candidate battery pack voltage clusters after multiple clustering is greater than a preset value, then the multiple candidate battery pack voltage clusters after multiple clustering will be used as multiple candidate battery pack voltage clusters, and the clustering algorithm will be triggered to cluster the multiple candidate battery pack voltage clusters to obtain multiple clustered candidate battery pack voltage clusters until the number of multiple clustered candidate battery pack voltage clusters is equal to the preset value.

[0044] Multiple candidate battery pack voltage clusters with a number equal to a preset value are determined as multiple battery pack voltage clusters in any time interval.

[0045] Thirdly, embodiments of this application provide a computer device, characterized in that the computer device includes a memory, a communication interface, and a processor, wherein the memory, the communication interface, and the processor are interconnected; the memory stores a computer program, and the processor calls the computer program stored in the memory to implement the method described in the first aspect.

[0046] Fourthly, embodiments of this application provide a vehicle, characterized in that the vehicle includes an automobile body and a processor, the processor being used to execute the method described in the first aspect.

[0047] Fifthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0048] In a sixth aspect, embodiments of this application provide a computer program product, which includes a computer program stored in a computer storage medium; a processor of a computer device reads the computer program from the computer storage medium and executes the computer program, causing the computer device to perform the voltage detection method described above.

[0049] In this embodiment, at least one time interval data set of the target object is obtained; the data set includes the voltage of each cell contained in at least one battery pack of the target object; based on the voltage of each cell contained in any battery pack contained in the data set of any time interval, the voltage of any battery pack in any time interval is obtained; the voltage of at least one battery pack in any time interval is clustered based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval; from the multiple battery pack voltage clusters in at least one time interval, suspected voltage outlier clusters and voltage outlier clusters are identified; based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, it is determined whether the target object has battery pack voltage outliers. After detecting the suspected voltage outlier clusters of the battery pack, the voltage outlier clusters are identified, which can effectively detect the battery pack voltage and ensure the efficient and safe operation of the battery system. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or the background art, the accompanying drawings used in the embodiments of this application or the background art will be described below.

[0051] Figure 1 This is a schematic diagram of the architecture of a voltage detection system provided in an embodiment of this application;

[0052] Figure 2 This is a schematic flowchart of a voltage detection method provided in an embodiment of this application;

[0053] Figure 3 This is a flowchart illustrating a clustering algorithm provided in an embodiment of this application;

[0054] Figure 4 This is a schematic diagram of another voltage detection method provided in an embodiment of this application;

[0055] Figure 5This is a schematic diagram of the structure of a voltage detection device provided in an embodiment of this application;

[0056] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0057] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0058] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0059] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, may be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or," "and / or," "including at least one of the following," etc., as used in this application, may be interpreted as inclusive, or mean any one or any combination thereof. For example, "including at least one of the following: A, B, C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Similarly, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Exceptions to this definition only occur when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0060] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0061] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0062] Please see Figure 1 , Figure 1 This is a schematic diagram of the architecture of a voltage detection system provided in an embodiment of this application. The target object can refer to a vehicle equipped with a battery or a photovoltaic system equipped with an energy storage battery.

[0063] For example, a data set for at least one time interval of the target object is obtained; the data set includes the voltage of each cell contained in at least one battery pack of the target object; based on the voltage of each cell contained in any battery pack contained in the data set for any time interval, the voltage of any battery pack in any time interval is obtained; the voltage of at least one battery pack in any time interval is clustered based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval; from the multiple battery pack voltage clusters in at least one time interval, suspected voltage outlier clusters and voltage outlier clusters are identified; based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, it is determined whether the target object has battery pack voltage outliers.

[0064] Optionally, after the original data of the target object is collected and uploaded to the cloud server, the processor can obtain the original data of the target object from the cloud, sort the original data by time, and obtain the object data of the target object.

[0065] Please see Figure 2 , Figure 2 This is a schematic flowchart of a voltage detection method provided in an embodiment of this application, as shown below. Figure 2 The voltage detection method shown includes, but is not limited to, steps S201-S205, wherein:

[0066] S201, Obtain at least one data set of the target object for at least one time interval.

[0067] In this embodiment, the target object may refer to a vehicle equipped with a battery or a photovoltaic system equipped with an energy storage battery. For example, the target object is a target vehicle. After the vehicle collects vehicle data, it is uploaded to a cloud server or a local server. The central processing unit (CPU) obtains at least one data set of the target object for at least one time interval.

[0068] In one implementation, the method further includes:

[0069] Obtain object data of the target object; the object data of the target object includes the voltage of each cell in at least one battery pack of the target object during a historical time period;

[0070] The object data of the target object is divided to obtain at least one data group for the target object in at least one time interval.

[0071] In this embodiment, the CPU divides the vehicle data to obtain at least one data group for the target vehicle within a time interval.

[0072] In one implementation, the object data further includes: the state of charge of each cell in at least one battery pack in the target object during the historical time period.

[0073] The step of dividing the object data of the target object to obtain at least one time interval data group of the target object includes: obtaining the voltage of each cell contained in the at least one battery pack at any time point from the object data;

[0074] From at least one voltage at any given time point, obtain the target voltage at that given time point; the target voltage is higher than the other voltages among the at least one voltage.

[0075] Obtain the target state of charge of the cell corresponding to the target voltage at any time point;

[0076] Based on the target voltage and the target state of charge, determine the target object data;

[0077] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0078] In this embodiment, the voltage of each cell in at least one battery pack at any given time is obtained from the vehicle data. From the at least one voltage at any given time, a target voltage at any given time is obtained. The target voltage is higher than the other voltages in the at least one voltage, i.e., the highest voltage. The state of charge (SOC) of the cell corresponding to the highest voltage is obtained, where the state of charge refers to the percentage of the amount of electricity stored in the battery relative to the total capacity. Based on the highest voltage and the state of charge of the highest voltage, target vehicle data is determined. The time-continuous target vehicle data in the vehicle data is determined as a data group of a time interval to obtain at least one data group of time intervals.

[0079] In one implementation, determining the target object data based on the target voltage and the target state of charge includes:

[0080] If the target voltage is greater than the second preset voltage threshold and the target state of charge is greater than the second preset ratio threshold, then the object data at any time point in the object data is determined as the target object data.

[0081] In this embodiment, if the highest voltage is greater than a second preset voltage threshold, for example, the second preset voltage threshold is 3V, if the highest voltage is greater than 3V, and the state of charge of the cell corresponding to the highest voltage is greater than a second preset ratio threshold, for example, the second preset ratio threshold is 60%, and the state of charge of the cell corresponding to the highest voltage is greater than 60%, then the vehicle data at any point in time in the vehicle data is determined as the target vehicle data.

[0082] In one implementation, the object data further includes: the current of any cell in at least one battery pack in the target object during the historical time period;

[0083] The step of dividing the object data of the target object to obtain at least one data group of time interval of the target object includes: obtaining the current of any cell at any time point from the object data, and the current of any cell at k adjacent time points at any time point; k is a positive integer;

[0084] Based on the current at any given time point and the current at the k adjacent time points, determine the target object data;

[0085] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0086] In this embodiment, the current of any battery cell at any given time point and the current of any battery cell at k adjacent time points at any given time point are obtained from the vehicle data; k is a positive integer; where the k time points can be the k time points before any given time point, the k time points after any given time point, or a total of k time points before and after any given time point. Based on the current at any given time point and the current at the k adjacent time points, target object data is determined; the time-continuous target object data in the object data is determined as a data group of a time interval to obtain at least one data group of a time interval.

[0087] In one implementation, determining the target object data based on the current at any given time point and the currents at the k adjacent time points includes:

[0088] If the current at any given time point is less than a first preset current threshold, and the difference between the maximum and minimum currents among the currents at the adjacent k time points and the current at any given time point is less than a second preset current threshold, then the object data at any given time point in the object data is determined as the target object data.

[0089] In this embodiment, if the current at any given time point is less than a first preset current threshold, and the difference between the maximum and minimum currents among the currents at any given time point and the current at any given time point is less than a second preset current threshold, then the vehicle data at any given time point in the vehicle data is determined as the target vehicle data. For example, if k is 4, the first preset current threshold is 0.2 amperes, and the second preset current threshold is 1 ampere, then the currents at any given time point and the currents at four adjacent time points are obtained. If the current at any given time point is less than 0.2 amperes, and the difference between the maximum and minimum currents among the currents at any given time point and the currents at four adjacent time points is less than 1 ampere, then the vehicle data at any given time point in the vehicle data is determined as the target vehicle data.

[0090] Optionally, the original vehicle data of the target vehicle can be obtained from a cloud-based big data platform, and the vehicle data can be preprocessed to obtain the vehicle data. For example, preprocessing can include deleting illegal data caused by hardware or software sampling failures, cloud communication failures, and parsing errors on the target vehicle side; reordering the data according to the data time; and retaining only one frame of data with the same data time. After preprocessing the original vehicle data, the vehicle data can be obtained.

[0091] S202: Based on the voltage of each cell in any battery pack contained in any data set within any time interval, obtain the voltage of any battery pack in any time interval.

[0092] In this embodiment, the voltage of the battery pack corresponding to each cell is determined by the voltage of each cell. For example, the battery pack includes a first cell, a second cell, and a third cell, and the voltage of the first cell is 2V, the voltage of the second cell is 3V, and the voltage of the third cell is 3V. Then the voltage of the battery pack is obtained by summing the cell voltages, which is 9V.

[0093] S203, cluster the voltage of at least one battery pack in any time interval based on the clustering algorithm to obtain multiple battery pack voltage clusters in any time interval.

[0094] In this embodiment, a clustering algorithm is used to cluster the voltage of at least one battery pack in any time interval to obtain multiple battery pack voltage clusters in any time interval.

[0095] In one implementation, a clustering algorithm is used to cluster the voltages of at least one battery pack over any time interval, resulting in multiple battery pack voltage clusters over that time interval, including:

[0096] Based on the clustering algorithm, the voltage of at least one battery pack in any time interval is clustered to obtain multiple candidate battery pack voltage clusters;

[0097] If the number of multiple candidate battery pack voltage clusters is greater than a preset value, then the multiple candidate battery pack voltage clusters are clustered based on a clustering algorithm to obtain multiple clustered candidate battery pack voltage clusters.

[0098] If the number of candidate battery pack voltage clusters after multiple clustering is greater than a preset value, then the multiple candidate battery pack voltage clusters after multiple clustering will be used as multiple candidate battery pack voltage clusters, and the clustering algorithm will be triggered to cluster the multiple candidate battery pack voltage clusters to obtain multiple clustered candidate battery pack voltage clusters until the number of multiple clustered candidate battery pack voltage clusters is equal to the preset value.

[0099] Multiple candidate battery pack voltage clusters with a number equal to a preset value are determined as multiple battery pack voltage clusters in any time interval.

[0100] In this embodiment, please refer to Figure 3 , Figure 3 This is a flowchart illustrating a clustering algorithm provided in an embodiment of this application.

[0101] S301, Input independent clusters.

[0102] The voltage data of a single battery pack within the vehicle data segment is input as a separate cluster.

[0103] S302, calculate the inter-cluster distance.

[0104] The inter-cluster distance can be calculated based on the voltage data characteristics of individual battery packs and the task requirements. Optional clustering algorithms include Single Linkage, Complete Linkage, Average Linkage, or Ward Linkage.

[0105] S303 aggregates the clusters corresponding to the shortest inter-cluster distance.

[0106] The voltage data of all battery packs in the cluster with the closest inter-cluster distance are aggregated to form a new cluster, resulting in multiple candidate battery pack voltage clusters.

[0107] S304, determine whether the clustering results meet the requirements.

[0108] Analyze whether the current clustering result meets the requirement, that is, the number of clusters N obtained by the final clustering. The value of N is not fixed, and it is generally 2 or 3. For example, if N is 2, the number of clusters obtained by the final clustering is 2, then the requirement is met, and the clustering algorithm stops. If the number of clusters obtained by the final clustering is greater than 2, then the requirement is not met, and the above step S302 is performed to calculate the inter-cluster distance. If the number of candidate battery group voltage clusters after multiple clustering is greater than the preset number 2, then the candidate battery group voltage clusters after multiple clustering are treated as multiple candidate battery group voltage clusters and the inter-cluster distance is calculated for further clustering until the number of candidate battery group voltage clusters obtained after multiple clustering is equal to the preset number 2.

[0109] S305 outputs the clusters after clustering is complete.

[0110] After clustering is completed, N preset battery pack voltage clusters are obtained for any time interval.

[0111] S204, from multiple battery pack voltage clusters in at least one time interval, identify suspected voltage outlier clusters and voltage outlier clusters.

[0112] In one implementation, the voltage outlier clusters are determined by:

[0113] Obtain the first average voltage value of the voltage contained in the currently traversed suspected voltage outlier cluster, and the second average voltage value of each of the other suspected voltage outlier clusters in the at least one time interval besides the currently traversed suspected voltage outlier cluster.

[0114] Voltage outlier clusters are determined based on the first voltage mean and each of the second voltage means, until the traversal is complete.

[0115] In this embodiment, after clustering, N preset battery pack voltage clusters are obtained. Among the N battery pack voltage clusters, the cluster with the fewest battery pack voltage data points is identified as a suspected outlier cluster. The suspected voltage outlier clusters are traversed over at least one time interval. A first voltage mean of the voltages contained in the currently traversed suspected voltage outlier cluster is obtained, along with a second voltage mean of each of the other suspected voltage outlier clusters in at least one time interval. Voltage outlier clusters are determined based on the first voltage mean and each of the second voltage means, until the traversal is complete.

[0116] In one implementation, determining voltage outlier clusters based on the first voltage mean and each of the second voltage means until the traversal is complete includes:

[0117] If the absolute value of the difference between each of the second voltage average values ​​and the first voltage average value is greater than the first preset voltage threshold, then the currently traversed suspected voltage outlier cluster is determined as a voltage outlier cluster, until the traversal ends.

[0118] In this embodiment, for example, the first preset voltage threshold is 0.5V. The average first voltage of the currently traversed suspected voltage outlier clusters is 4V, and the average second voltages are 5V, 5.2V, and 5.3V. The absolute values ​​of the differences between the average second voltages and the average first voltages are 1V, 1.2V, and 1.3V, respectively. Since the absolute values ​​of the differences between the average second voltages and the average first voltages are greater than the first preset voltage threshold, the currently traversed suspected voltage outlier clusters are determined to be voltage outlier clusters until the traversal ends. With the BC voltage data for each time interval already obtained, only the external parameter N (the number of clusters when clustering is complete) needs to be passed to the clustering algorithm to obtain the information of suspected voltage outlier clusters. It is not necessary to design a detection threshold based on the historical data of the detected battery, battery manufacturing process, battery model, etc. Therefore, this method is highly adaptive.

[0119] S205, Based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, determine whether the target object has a battery pack voltage outlier.

[0120] In one implementation, determining whether the target object has battery pack voltage outliers based on the number of suspected voltage outlier clusters and the total number of voltage outlier clusters includes:

[0121] If the ratio of the number of voltage outliers to the number of suspected voltage outliers is greater than a first preset ratio threshold, or if the difference between the number of voltage outliers and the number of other suspected voltage outliers (excluding voltage outliers) is greater than a preset number threshold, then it is determined that the target object has a battery pack voltage outlier.

[0122] In this embodiment, the target object can refer to a vehicle equipped with a battery or a photovoltaic system equipped with an energy storage battery. For example, the target object is a target vehicle. The number of identified voltage outliers and the number of suspected voltage outliers are obtained. For instance, if the first preset ratio threshold is 50%, the number of voltage outliers is 6, the number of suspected voltage outliers is 10, and the ratio of voltage outliers to suspected voltage outliers is 60%, which is greater than 50%, then the target vehicle is determined to have battery pack voltage outliers. Alternatively, if the preset number threshold is 10, the number of voltage outliers is 20, the number of suspected voltage outliers is 5, and the difference between the number of voltage outliers and suspected voltage outliers is 15, which is greater than the preset number of 10, then the target vehicle is determined to have battery pack voltage outliers. By adjusting the first preset ratio threshold or the preset number threshold, the width of the detection window can be adjusted, specifically adjusting the detection criteria for key targets.

[0123] In this embodiment, at least one time interval data set of the target object is obtained; the data set includes the voltage of each cell contained in at least one battery pack of the target object; based on the voltage of each cell contained in any battery pack contained in the data set of any time interval, the voltage of any battery pack in any time interval is obtained; the voltage of at least one battery pack in any time interval is clustered based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval; from the multiple battery pack voltage clusters in at least one time interval, suspected voltage outlier clusters and voltage outlier clusters are identified; based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, it is determined whether the target object has battery pack voltage outliers. After detecting suspected voltage outlier clusters of the battery pack, the voltage outlier clusters are identified, which can effectively detect the battery pack voltage and ensure the efficient and safe operation of the battery system.

[0124] Please see Figure 4 , Figure 4 This is a schematic flowchart of another voltage detection method provided in an embodiment of this application, as shown below. Figure 4 The voltage detection method shown includes, but is not limited to, steps S401-S406, wherein:

[0125] S401, Determine the charging / discharging state of the target object.

[0126] In this embodiment, the target object may refer to a vehicle equipped with a battery or a photovoltaic system equipped with an energy storage battery. For example, if the target object is a target vehicle, the charging and discharging status of the vehicle is first determined based on the vehicle data obtained from the cloud.

[0127] Optionally, the charging and discharging status of the vehicle can be determined using current data; for example, positive current usually indicates charging, and negative current indicates discharging. Zero current usually indicates that the battery is at rest, i.e., not charging or discharging.

[0128] Optionally, the charging and discharging status of the vehicle can be determined by voltage data; for example, a higher voltage may indicate charging, and a lower voltage may indicate discharging.

[0129] Optionally, the charging and discharging status of the vehicle can be determined by the state of charge (SCC). SCC refers to the ratio of the current amount of electricity stored in the battery to its total capacity, usually expressed as a percentage. If the SCC value increases, it indicates charging; if it decreases, it indicates discharging.

[0130] Optionally, the vehicle's charging / discharging status can be determined by its operating conditions; for example, if the vehicle is moving and the battery current is positive, the battery is likely discharging. If the vehicle is stationary and the current is positive, it may be charging.

[0131] Optionally, the charging and discharging status of a vehicle can be determined by comprehensively considering current, voltage, state of charge, and vehicle operating conditions.

[0132] S402, based on the charging and discharging state of the target object, divide the object data of the target object to obtain at least one data group for a time interval.

[0133] In this embodiment, optionally, if the target vehicle is in a charging state, the vehicle data of the target vehicle is divided based on the division method during charging to obtain at least one data group for a time interval.

[0134] In one implementation, the object data further includes: the state of charge of each cell in at least one battery pack in the target object during the historical time period.

[0135] The step of dividing the object data of the target object to obtain at least one time interval data group of the target object includes: obtaining the voltage of each cell contained in the at least one battery pack at any time point from the object data;

[0136] From at least one voltage at any given time point, obtain the target voltage at that given time point; the target voltage is higher than the other voltages among the at least one voltage.

[0137] Obtain the target state of charge of the cell corresponding to the target voltage at any time point;

[0138] Based on the target voltage and the target state of charge, determine the target object data;

[0139] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0140] In this embodiment, if the target vehicle is in a charging state, the voltage of each cell in at least one battery pack in the vehicle sequence data is obtained at any time point. From the at least one voltage at any time point, the target voltage at any time point is obtained. The target voltage is higher than the other voltages in the at least one voltage, i.e., the highest voltage. The SOC of the cell corresponding to the highest voltage is obtained. Based on the highest voltage and the SOC of the highest voltage, the target vehicle data is determined. The time-continuous target vehicle data in the vehicle data is determined as a data group of a time interval to obtain at least one data group of time intervals.

[0141] In one implementation, determining the target object data based on the target voltage and the target state of charge includes:

[0142] If the target voltage is greater than the second preset voltage threshold and the target state of charge is greater than the second preset ratio threshold, then the object data at any time point in the object data is determined as the target object data.

[0143] In this embodiment, if the highest voltage is greater than a second preset voltage threshold, for example, the second preset voltage threshold is 3V; if the highest voltage is greater than 3V; and the SOC of the cell corresponding to the highest voltage is greater than a second preset percentage threshold, for example, the second preset percentage threshold is 60%; and the state of charge of the cell corresponding to the highest voltage is greater than 60%, then the vehicle data at any point in time in the vehicle data is determined as the target vehicle data. The target vehicle data with continuous time in the vehicle data is determined as a data group for a time interval, so as to obtain at least one data group for a time interval, and this data group is a high-state charging segment. Extracting the high-state charging segment as a data group can eliminate the adverse effects of the lithium iron phosphate battery voltage characteristics on the voltage of the individual cell (IC). The lithium iron phosphate battery voltage characteristics refer to the plateau period during charging, during which the voltage difference of ICs with large SOC differences is not significant, making cluster analysis impossible. Conversely, during the high-state charging phase, the IC voltage is more significantly affected by the State of Charge (SOC), making it easier to obtain information about voltage changes caused by issues with the battery cell itself. Because resistance increases during high SOC charging, even small differences in resistance can have a substantial impact on the voltage. Selecting to tap the high-state charging point is precisely to avoid the adverse effects of the lithium iron phosphate battery's voltage characteristics on the IC voltage.

[0144] Optionally, if the target vehicle is in a discharged state, the vehicle data of the target vehicle is divided according to the division method during discharge to obtain at least one data group for a time interval.

[0145] In one implementation, the object data further includes: the current of any cell in at least one battery pack in the target object during the historical time period;

[0146] The step of dividing the object data of the target object to obtain at least one data group of time interval of the target object includes: obtaining the current of any cell at any time point from the object data, and the current of any cell at k adjacent time points at any time point; k is a positive integer;

[0147] Based on the current at any given time point and the current at the k adjacent time points, determine the target object data;

[0148] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0149] In this embodiment, if the target vehicle is in a discharged state, the current of any cell at any time point and the current of any cell at k adjacent time points at any time point are obtained from the vehicle data sequence; k is a positive integer; where the k time points can be the k time points before any time point, the k time points can be the k time points after any time point, or the k time points before and after any time point. Based on the current at any time point and the currents at the k adjacent time points, the target vehicle data is determined; the time-continuous target vehicle data in the vehicle data is determined as a data group of a time interval to obtain at least one data group of a time interval.

[0150] In one implementation, determining the target object data based on the current at any given time point and the currents at k adjacent time points includes:

[0151] If the current at any time point is less than the first preset current threshold, and the difference between the current at any of the adjacent k time points and the maximum and minimum currents at any time point is less than the second preset current threshold, then the object data at any time point in the object data is determined as the target object data.

[0152] In this embodiment, if the current at any given time point is less than a first preset current threshold, and the difference between the maximum and minimum currents among the currents at any given time point and the current at any given time point is less than a second preset current threshold, then the vehicle data at any given time point in the vehicle data is determined as the target vehicle data. For example, if k is 4, the first preset current threshold is 0.2 amperes, and the second preset current threshold is 1 ampere, then the currents at any given time point and the currents at four adjacent time points are obtained. If the current at any given time point is less than 0.2 amperes, and the difference between the maximum and minimum currents among the currents at any given time point and the currents at four adjacent time points is less than 1 ampere, then the vehicle data at any given time point in the vehicle data is determined as the target vehicle data.

[0153] S403: Based on the voltage of each cell in any battery pack contained in any data set within any time interval, obtain the voltage of any battery pack in any time interval.

[0154] Please refer to step S202 above for the specific steps of this embodiment; this step will not be repeated here.

[0155] S404, based on a clustering algorithm, cluster the voltage of at least one battery pack in any time interval to obtain multiple battery pack voltage clusters in any time interval.

[0156] Please refer to step S203 above for the specific steps of this embodiment; this step will not be repeated here.

[0157] S405, from multiple battery pack voltage clusters in at least one time interval, identify suspected voltage outliers and voltage outliers.

[0158] For the specific steps of this embodiment, please refer to step S204 above. This step will not be repeated here.

[0159] S406, Based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, determine whether the target object has a battery pack voltage outlier.

[0160] Please refer to step S205 above for the specific steps of this embodiment, which will not be repeated here.

[0161] In this embodiment, the charge / discharge state of the target object is determined. Based on the charge / discharge state of the target object, the object data of the target object is divided into at least one data group for a time interval. The voltage of any battery pack in any time interval is obtained based on the voltage of each cell in any battery pack contained in any data group for any time interval. A clustering algorithm is used to cluster the voltage of at least one battery pack in any time interval, resulting in multiple battery pack voltage clusters in any time interval. From these multiple battery pack voltage clusters in at least one time interval, suspected voltage outlier clusters and voltage outlier clusters are identified. Based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, it is determined whether the target object has any battery pack voltage outliers. By determining the charge / discharge state of the target object, and then acquiring the BC voltage data for the high-state charging segment and the steady-state discharging segment respectively, data from both the charging and discharging segments can be covered, thereby achieving all-weather detection of the cells. After detecting suspected voltage outlier clusters in the battery pack, the voltage outlier clusters are identified, effectively detecting the battery pack voltage and ensuring the efficient and safe operation of the battery system.

[0162] This application also provides a computer storage medium storing program instructions, which, when executed, are used to implement the corresponding methods described in the above embodiments.

[0163] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a voltage detection device provided in an embodiment of this application.

[0164] In one implementation of the voltage detection device according to an embodiment of this application, the voltage detection device includes the following structure:

[0165] The acquisition unit 501 is used to acquire a data set of at least one time interval of the target object; the data set includes the voltage of each cell contained in at least one battery pack of the target object;

[0166] The processing unit 502 is used to obtain the voltage of any battery pack in any time interval based on the voltage of each cell contained in any battery pack in a data set in any time interval.

[0167] The processing unit 502 is also used to cluster the voltage of at least one battery pack in any time interval based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval.

[0168] The determining unit 503 is used to determine suspected voltage outlier clusters and voltage outlier clusters from multiple battery pack voltage clusters in at least one time interval;

[0169] The determining unit 503 is also used to determine whether the target object has a battery pack voltage outlier based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters.

[0170] In one embodiment, the determination unit 503 determines voltage outlier clusters in the following manner:

[0171] Obtain the first average voltage value of the voltage contained in the currently traversed suspected voltage outlier cluster, and the second average voltage value of each of the other suspected voltage outlier clusters in the at least one time interval besides the currently traversed suspected voltage outlier cluster.

[0172] Voltage outlier clusters are determined based on the first voltage mean and each of the second voltage means, until the traversal is complete.

[0173] In one embodiment, the determining unit 503 determines voltage outlier clusters based on the first voltage mean and each of the second voltage means until the traversal is complete, including:

[0174] If the absolute value of the difference between each second voltage mean and the first voltage mean is greater than the first preset voltage threshold, then the suspected voltage outlier cluster currently being traversed is identified as a voltage outlier cluster, until the traversal ends.

[0175] In one embodiment, the determining unit 503 determines whether the target object has a battery pack voltage outlier based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, including:

[0176] If the ratio of the number of voltage outliers to the number of suspected voltage outliers is greater than a first preset ratio threshold, or if the difference between the number of voltage outliers and the number of other suspected voltage outliers (excluding voltage outliers) is greater than a preset number threshold, then the target vehicle is determined to have a battery pack voltage outlier.

[0177] In one embodiment, the acquisition unit 501 is further configured to include:

[0178] Obtain object data of the target object; the object data of the target object includes the voltage of each cell in at least one battery pack of the target object during a historical time period;

[0179] The object data of the target object is divided to obtain at least one data group for the target object in at least one time interval.

[0180] In one embodiment, the object data further includes: the state of charge of each cell in at least one battery pack in the target object during the historical time period.

[0181] The processing unit 502 divides the object data of the target object to obtain at least one time interval data group of the target object, including: obtaining the voltage of each cell contained in the at least one battery pack at any time point from the object data;

[0182] From at least one voltage at any given time point, obtain the target voltage at that given time point; the target voltage is higher than the other voltages among the at least one voltage.

[0183] Obtain the target state of charge of the cell corresponding to the target voltage at any time point;

[0184] Based on the target voltage and the target state of charge, determine the target object data;

[0185] The time-continuous target object data in the object data is determined into a data group for a time interval to obtain the data group for the at least one time interval. In one embodiment, the determining unit 503 determines the target object data based on the target voltage and the target state of charge, including:

[0186] If the target voltage is greater than the second preset voltage threshold and the target state of charge is greater than the second preset ratio threshold, then the object data at any time point in the object data is determined as the target object data.

[0187] In one embodiment, the object data further includes: the current of any cell in at least one battery pack in the target object during the historical time period;

[0188] The processing unit 502 divides the object data of the target object to obtain at least one data group of time interval of the target object, including: obtaining the current of any cell at any time point from the object data, and the current of any cell at k adjacent time points at any time point; k is a positive integer;

[0189] Based on the current at any given time point and the current at the adjacent k time points, the target object data is determined;

[0190] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0191] In one embodiment, the determining unit 503 determines target object data based on the current at any given time point and the currents at the adjacent k time points, including:

[0192] If the current at any given time point is less than a first preset current threshold, and the difference between the maximum and minimum currents among the currents at the adjacent k time points and the current at any given time point is less than a second preset current threshold, then the object data at any given time point in the object data is determined as the target object data.

[0193] In one embodiment, the processing unit 502 clusters the voltages of at least one battery pack in any time interval based on a clustering algorithm, obtaining multiple battery pack voltage clusters in any time interval, including:

[0194] Based on the clustering algorithm, the voltage of at least one battery pack in any time interval is clustered to obtain multiple candidate battery pack voltage clusters;

[0195] If the number of multiple candidate battery pack voltage clusters is greater than a preset value, then the multiple candidate battery pack voltage clusters are clustered based on a clustering algorithm to obtain multiple clustered candidate battery pack voltage clusters.

[0196] If the number of candidate battery pack voltage clusters after multiple clustering is greater than a preset value, then the multiple candidate battery pack voltage clusters after multiple clustering will be used as multiple candidate battery pack voltage clusters, and the clustering algorithm will be triggered to cluster the multiple candidate battery pack voltage clusters to obtain multiple clustered candidate battery pack voltage clusters until the number of multiple clustered candidate battery pack voltage clusters is equal to the preset value.

[0197] Multiple candidate battery pack voltage clusters with a number equal to a preset value are determined as multiple battery pack voltage clusters in any time interval.

[0198] In this embodiment, the acquisition unit 501 acquires a data set of at least one time interval of the target object; the data set includes the voltage of each cell contained in at least one battery pack of the target object; the processing unit 502 obtains the voltage of any battery pack in any time interval based on the voltage of each cell contained in any battery pack in any time interval of the data set of any time interval; the processing unit 502 clusters the voltage of at least one battery pack in any time interval based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval; the determination unit 503 determines suspected voltage outlier clusters and voltage outlier clusters from the multiple battery pack voltage clusters in at least one time interval; the determination unit 503 determines whether the target object has battery pack voltage outliers based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters. After detecting suspected voltage outlier clusters of the battery pack, the determination of voltage outlier clusters can effectively detect the battery pack voltage and ensure the efficient and safe operation of the battery system. See also Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. The computer device in this embodiment includes a power supply module and other structures. The computer device can run on a cloud server or a local server, and includes a processor 601, a memory 602, and a communication interface 603. The processor 601, the memory 602, and the communication interface 603 can exchange data, and the processor 601 implements the corresponding voltage detection method.

[0199] Memory 602 may include volatile memory, such as random-access memory (RAM); memory 602 may also include non-volatile memory, such as flash memory, solid-state drive (SSD), etc.; memory 602 may also include combinations of the above types of memory.

[0200] Processor 601 may be a central processing unit (CPU). Processor 601 may also be a combination of a CPU and a GPU. In a computer device, multiple CPUs and GPUs may be included as needed for corresponding voltage detection. In one embodiment, memory 602 is used to store program instructions. Processor 601 can invoke program instructions to implement the various methods described above in the embodiments of this application.

[0201] In a first possible implementation, the processor 601 of the computer device invokes program instructions stored in memory 602 to acquire a data set of at least one time interval of a target object; the data set includes the voltage of each cell contained in at least one battery pack of the target object; based on the voltage of each cell contained in any battery pack contained in the data set of any time interval, the voltage of any battery pack in any time interval is obtained; the voltage of the at least one battery pack in any time interval is clustered based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval; from the multiple battery pack voltage clusters in the at least one time interval, suspected voltage outlier clusters and voltage outlier clusters are identified; based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, it is determined whether the target object has battery pack voltage outliers. In one embodiment, the processor 601 may perform the following operations to determine voltage outlier clusters:

[0202] Obtain the first average voltage value of the voltage contained in the currently traversed suspected voltage outlier cluster, and the second average voltage value of each of the other suspected voltage outlier clusters in the at least one time interval besides the currently traversed suspected voltage outlier cluster.

[0203] Voltage outlier clusters are determined based on the first voltage mean and each of the second voltage means, until the traversal is complete.

[0204] In one embodiment, the processor 601 determines voltage outlier clusters based on the first voltage mean and each of the second voltage means until the traversal is complete, and may perform the following operations:

[0205] If the absolute value of the difference between each of the second voltage average values ​​and the first voltage average value is greater than the first preset voltage threshold, then the currently traversed suspected voltage outlier cluster is determined as a voltage outlier cluster, until the traversal ends.

[0206] In one embodiment, the processor 601 determines whether the target object has a battery pack voltage outlier based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, and may perform the following operations:

[0207] If the ratio of the number of voltage outliers to the number of suspected voltage outliers is greater than a first preset ratio threshold, or if the difference between the number of voltage outliers and the number of other suspected voltage outliers (excluding voltage outliers) is greater than a preset number threshold, then it is determined that the target object has a battery pack voltage outlier.

[0208] In one embodiment, the processor 601 may also perform the following operations:

[0209] Obtain object data of the target object; the object data of the target object includes the voltage of each cell in at least one battery pack of the target object during a historical time period;

[0210] The object data of the target object is divided to obtain at least one data group for the target object in at least one time interval.

[0211] In one embodiment, the object data further includes: the state of charge of each cell in at least one battery pack in the target object during the historical time period.

[0212] The processor 601 divides the object data of the target object to obtain at least one data group for at least one time interval of the target object, and can perform the following operations:

[0213] Obtain the voltage of each cell in the at least one battery pack at any point in time from the object data;

[0214] From at least one voltage at any given time point, obtain the target voltage at that given time point; the target voltage is higher than the other voltages among the at least one voltage.

[0215] Obtain the target state of charge of the cell corresponding to the target voltage at any time point;

[0216] Based on the target voltage and the target state of charge, determine the target object data;

[0217] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0218] In one embodiment, the processor 601 determines target object data based on the target voltage and the target state of charge, and may perform the following operations:

[0219] If the target voltage is greater than the second preset voltage threshold and the target state of charge is greater than the second preset ratio threshold, then the object data at any time point in the object data is determined as the target object data.

[0220] In one embodiment, the object data further includes: the current of any cell in at least one battery pack in the target object during the historical time period;

[0221] The processor 601 divides the object data of the target object to obtain at least one data group for at least one time interval of the target object, and can perform the following operations:

[0222] Obtain the current of any cell at any time point from the object data, and the current of any cell at k adjacent time points at any time point; k is a positive integer;

[0223] Based on the current at any given time point and the current at the k adjacent time points, determine the target object data;

[0224] The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

[0225] In one embodiment, determining the target object data based on the current at any given time point and the currents at the k adjacent time points can be performed by the following operation:

[0226] If the current at any given time point is less than a first preset current threshold, and the difference between the maximum and minimum currents among the currents at the adjacent k time points and the current at any given time point is less than a second preset current threshold, then the object data at any given time point in the object data is determined as the target object data.

[0227] In one embodiment, the processor 601 clusters the voltages of at least one battery pack in any time interval based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval, and can perform the following operations:

[0228] Based on the clustering algorithm, the voltage of at least one battery pack in any time interval is clustered to obtain multiple candidate battery pack voltage clusters;

[0229] If the number of multiple candidate battery pack voltage clusters is greater than a preset value, then the multiple candidate battery pack voltage clusters are clustered based on a clustering algorithm to obtain multiple clustered candidate battery pack voltage clusters.

[0230] If the number of candidate battery pack voltage clusters after multiple clustering is greater than a preset value, then the multiple candidate battery pack voltage clusters after multiple clustering will be used as multiple candidate battery pack voltage clusters, and the clustering algorithm will be triggered to cluster the multiple candidate battery pack voltage clusters to obtain multiple clustered candidate battery pack voltage clusters until the number of multiple clustered candidate battery pack voltage clusters is equal to the preset value.

[0231] Multiple candidate battery pack voltage clusters with a number equal to a preset value are determined as multiple battery pack voltage clusters in any time interval.

[0232] In this embodiment, the processor 601 acquires a data set for at least one time interval of the target object; the data set includes the voltage of each cell contained in at least one battery pack of the target object; based on the voltage of each cell contained in any battery pack in any time interval, the voltage of any battery pack in any time interval is obtained; the voltage of at least one battery pack in any time interval is clustered based on a clustering algorithm to obtain multiple battery pack voltage clusters in any time interval; from the multiple battery pack voltage clusters in at least one time interval, suspected voltage outlier clusters and voltage outlier clusters are identified; based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, it is determined whether the target object has battery pack voltage outliers. After detecting suspected voltage outlier clusters of the battery pack, the voltage outlier clusters are identified, which can effectively detect the battery pack voltage and ensure the efficient and safe operation of the battery system.

[0233] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0234] The above-disclosed embodiments are merely some of the embodiments of this application, and should not be construed as limiting the scope of this application. Those skilled in the art can understand that implementing all or part of the above embodiments and making equivalent changes in accordance with the claims of this application still fall within the scope of this invention.

Claims

1. A voltage detection method, characterized in that, include: Acquire a data set for at least one time interval of the target object; the data set includes the voltage of each cell contained in at least one battery pack of the target object; The voltage of any battery pack in any time interval is obtained based on the voltage of each cell in any battery pack contained in any data set in any time interval. Based on the clustering algorithm, the voltage of the at least one battery pack is clustered in any time interval to obtain multiple battery pack voltage clusters in any time interval. From multiple battery pack voltage clusters within the at least one time interval, identify suspected voltage outlier clusters and voltage outlier clusters; Based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters, it is determined whether the target object has a battery pack voltage outlier. The methods for determining the voltage outlier clusters include: Obtain the first average voltage value of the voltage contained in the currently traversed suspected voltage outlier cluster, and the second average voltage value of each of the other suspected voltage outlier clusters in the at least one time interval besides the currently traversed suspected voltage outlier cluster. Voltage outlier clusters are determined based on the first voltage mean and each of the second voltage means, until the traversal is complete.

2. The method as described in claim 1, characterized in that, The process of determining voltage outlier clusters based on the first voltage mean and each of the second voltage means, until the traversal is complete, includes: If the absolute value of the difference between each of the second voltage average values ​​and the first voltage average value is greater than the first preset voltage threshold, then the currently traversed suspected voltage outlier cluster is determined as a voltage outlier cluster, until the traversal ends.

3. The method as described in claim 1, characterized in that, The step of determining whether the target object has a battery pack voltage outlier based on the number of suspected voltage outlier clusters and the number of voltage outlier clusters includes: If the ratio of the number of voltage outliers to the number of suspected voltage outliers is greater than a first preset ratio threshold, or if the difference between the number of voltage outliers and the number of other suspected voltage outliers (excluding the voltage outlier) is greater than a preset number threshold, then it is determined that the target object has a battery pack voltage outlier.

4. The method as described in claim 1, characterized in that, The method further includes: Obtain object data of the target object; the object data of the target object includes the voltage of each cell in at least one battery pack of the target object during a historical time period; The object data of the target object is divided to obtain at least one data group for the target object in at least one time interval.

5. The method as described in claim 4, characterized in that, The object data also includes: the state of charge of each cell in at least one battery pack in the target object during the historical time period. The step of dividing the object data of the target object to obtain at least one time interval data group of the target object includes: obtaining the voltage of each cell contained in the at least one battery pack at any time point from the object data; From at least one voltage at any given time point, obtain the target voltage at that given time point; the target voltage is higher than the other voltages among the at least one voltage. Obtain the target state of charge of the cell corresponding to the target voltage at any time point; Based on the target voltage and the target state of charge, determine the target object data; The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

6. The method as described in claim 5, characterized in that, The process of determining target object data based on the target voltage and the target state of charge includes: If the target voltage is greater than the second preset voltage threshold and the target state of charge is greater than the second preset ratio threshold, then the object data at any time point in the object data is determined as the target object data.

7. The method as described in claim 4, characterized in that, The object data also includes: the current of any cell in at least one battery pack in the target object during the historical time period; The step of dividing the object data of the target object to obtain at least one data group of time interval of the target object includes: obtaining the current of any cell at any time point from the object data, and the current of any cell at k adjacent time points at any time point; k is a positive integer; Based on the current at any given time point and the current at the k adjacent time points, determine the target object data; The time-continuous target object data in the object data is determined as a data group of a time interval to obtain the data group of the at least one time interval.

8. The method as described in claim 7, characterized in that, The determination of target object data based on the current at any given time point and the currents at the k adjacent time points includes: If the current at any given time point is less than a first preset current threshold, and the difference between the maximum and minimum currents among the currents at the adjacent k time points and the current at any given time point is less than a second preset current threshold, then the object data at any given time point in the object data is determined as the target object data.

9. The method as described in claim 1, characterized in that, The method of clustering the voltage of the at least one battery pack in any time interval based on a clustering algorithm yields multiple battery pack voltage clusters in any time interval, including: Based on the clustering algorithm, the voltage of the at least one battery pack is clustered in any time interval to obtain multiple candidate battery pack voltage clusters; If the number of candidate battery pack voltage clusters is greater than a preset value, then the candidate battery pack voltage clusters are clustered based on the clustering algorithm to obtain multiple clustered candidate battery pack voltage clusters. If the number of candidate battery pack voltage clusters after multiple clustering is greater than the preset value, then the multiple candidate battery pack voltage clusters after multiple clustering are taken as multiple candidate battery pack voltage clusters, and the clustering of the multiple candidate battery pack voltage clusters based on the clustering algorithm is triggered to obtain multiple clustered candidate battery pack voltage clusters, until the number of multiple clustered candidate battery pack voltage clusters obtained is equal to the preset value. Multiple candidate battery pack voltage clusters with a number equal to the preset value are determined as multiple battery pack voltage clusters in any given time interval.

10. A computer device, characterized in that, The computer device includes a memory, a communication interface, and a processor, wherein the memory, the communication interface, and the processor are interconnected; the memory stores a computer program, and the processor calls the computer program stored in the memory to implement the method according to any one of claims 1 to 9.

11. A vehicle, characterized in that, The vehicle includes a vehicle body and a processor, the processor being configured to perform the method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 9.

Images