Battery SOC jump abnormality determination method and apparatus, electronic device, and storage medium

Abstract

A battery SOC jump abnormality determination method and apparatus, an electronic device, and a storage medium. The method comprises: on the basis of vehicle operation information and vehicle battery information uploaded in real time from a vehicle end, in combination with a pre-constructed battery SOC jump scenario database and a battery SOC jump feature database, detecting whether a vehicle battery is in an abnormal SOC jump state and detecting a target abnormal scenario for the abnormal SOC jump (S102); and, on the basis of the target abnormal scenario and the vehicle battery information, determining an SOC jump abnormality type for the vehicle battery (S103). In this way, after receiving the vehicle operation information and the vehicle battery information transmitted from the vehicle end, the cloud end promptly determines, by means of the pre-established battery SOC jump scenario database and battery SOC jump feature database, the target abnormal scenario for the abnormal SOC jump of the vehicle battery, and determines the SOC jump abnormality type of the vehicle battery in a targeted manner, thereby helping to improve the efficiency and accuracy of SOC jump type determination.

Description

Methods, devices, electronic equipment, and storage media for determining abnormal battery SOC switching.

[0001] Cross-reference to related applications

[0002] This disclosure claims priority to Chinese Patent Application No. 202410658991.6, filed on May 27, 2024, entitled "Method, Apparatus, Electronic Device and Storage Medium for Determining Battery SOC Jump Anomaly", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of automotive power battery technology, and in particular to methods, apparatus, electronic devices and storage media for determining abnormal battery SOC fluctuations. Background Technology

[0004] With the development of technology, new energy vehicles are gradually entering users' lives. The power battery is the core component of electric vehicles and is related to the safety of vehicle use. In order to ensure the driving safety of the vehicle, it is necessary to analyze and predict the battery data in real time.

[0005] Among them, the State of Charge (SOC) of a power battery is one of the key indicators for measuring battery capacity and is crucial for battery management and performance. During daily operation, various factors can cause a deviation between the SOC calculated by the Battery Management System (BMS) and the actual SOC of the battery. When this deviation reaches a certain level, corrections are necessary. These corrections are reflected in the instrumentation or cloud-based system as SOC fluctuations.

[0006] In related technologies, the determination of the cause of SOC transition still adopts a unified judgment standard, which requires a lot of time to accurately determine the cause and type of SOC transition, resulting in low efficiency and accuracy in determining the type of SOC transition.

[0007] Summary of the Invention

[0008] In view of this, the purpose of this disclosure is to provide a method, device, electronic device and storage medium for determining battery SOC jump anomalies. After receiving vehicle operation information and vehicle battery information sent by the vehicle terminal in the cloud, the system promptly identifies the target abnormal scenario of the vehicle battery's SOC jump anomaly through a pre-established battery SOC jump scenario database and battery SOC jump feature database, and specifically determines the type of vehicle battery SOC jump anomaly for the target abnormal scenario, which helps to improve the efficiency and accuracy of SOC jump type judgment.

[0009] In a first aspect, an optional embodiment of this disclosure provides a method for determining abnormal battery SOC fluctuations, applied in the cloud; the determination method includes:

[0010] Receive real-time vehicle operation information and vehicle battery information uploaded by the vehicle terminal;

[0011] Based on the vehicle operation information and vehicle battery information, combined with the pre-built battery SOC jump scenario database and battery SOC jump feature database, the system detects whether the vehicle battery is in an abnormal SOC jump situation, and the target abnormal scenario in which the SOC jump is abnormal.

[0012] Based on the target abnormal scenario and the vehicle battery information, the SOC jump abnormality type of the vehicle battery is determined.

[0013] In one optional implementation, the battery SOC jump scenario database includes multiple SOC jump types, and each SOC jump type includes at least one SOC jump scenario; the battery SOC jump feature database includes multiple SOC jump types, and each SOC jump type includes at least one SOC jump scenario, and each SOC jump scenario corresponds to specific battery data features and operating data features.

[0014] The SOC transition scenario includes at least one of the following:

[0015] Scenarios with full charge jump within accuracy range, scenarios with full charge jump outside accuracy range, scenarios with jump before resting time is reached, scenarios with jump after resting time is reached, scenarios with jump before resting time is reached, and scenarios with jump after resting time is reached.

[0016] In one optional implementation, detecting whether the vehicle battery at the vehicle end is experiencing an abnormal SOC jump includes:

[0017] Based on the mileage and running time information in the vehicle operation information, and combined with the SOC information in the vehicle battery information, the target SOC transition scenario and target SOC transition type are determined.

[0018] Based on the abnormal transition information corresponding to the target SOC transition type under the target SOC transition type, detect whether the vehicle battery at the vehicle end is in a state of abnormal SOC transition.

[0019] In one alternative implementation, the abnormal transition scenario includes at least one of the following:

[0020] Scenarios with sudden changes in accuracy after full charge, scenarios with sudden changes before the resting time is reached, scenarios with sudden changes before the threshold is reached, and scenarios with data loss.

[0021] In one optional implementation, when the target abnormal scenario is the precision external full charge jump scenario, determining the SOC jump abnormality type of the vehicle battery based on the target abnormal scenario and the vehicle battery information includes:

[0022] Based on the vehicle battery information, the time of the current SOC jump is determined, and a first target time that meets preset statistical conditions before the jump time is determined; wherein, the first target time is the time corresponding to when the battery is fully charged or the time corresponding to when the SOC correction condition is reached.

[0023] Based on the vehicle battery information, calculate the SOC deviation of the vehicle battery for each charge-discharge cycle within the target time period from the first target time to the jump time;

[0024] If the SOC deviation is greater than the first deviation threshold, the SOC jump anomaly type of the vehicle battery is determined to be the insufficient accuracy jump type.

[0025] In one optional implementation, calculating the SOC deviation of the vehicle battery for each charge-discharge cycle within the target time period from the first target time to the transition time, based on the vehicle battery information, includes:

[0026] Based on the vehicle battery information, calculate the total charge and discharge capacity of the vehicle battery within the target time period;

[0027] Based on the total charge / discharge capacity and the rated capacity of the vehicle battery, determine the number of charge / discharge cycles within the target time period;

[0028] For each charge-discharge cycle, the SOC deviation of that charge-discharge cycle is determined based on the number of charge-discharge cycles and the number of SOC jumps of the vehicle battery within the target time period.

[0029] In an optional implementation, when the target abnormal scenario is the scenario of a sudden change in SOC before the resting time is reached or the scenario of a sudden change in resting time before the threshold is reached, determining the SOC change abnormality type of the vehicle battery based on the target abnormal scenario and the vehicle battery information includes:

[0030] Based on the vehicle battery information, determine the current SOC transition time and a second target time within a preset time threshold before the transition time.

[0031] Based on the vehicle battery information, the first cell voltage corresponding to the transition time, the second cell voltage corresponding to the second target time, the first SOC value corresponding to the transition time, and the second SOC value corresponding to the second target time are determined.

[0032] The target voltage difference is determined based on the voltage of the first cell and the voltage of the second cell.

[0033] Based on the first SOC value and the calculated actual SOC value of the vehicle battery, a first SOC difference is determined, and based on the second SOC value and the actual SOC value, a second SOC difference is determined.

[0034] If the target voltage difference is greater than a preset voltage difference threshold, and the absolute value of the first SOC difference is less than the first SOC threshold, and the absolute value of the second SOC difference is greater than the first SOC threshold, then the SOC jump anomaly type of the vehicle battery is determined to be the BMS threshold anomaly jump type.

[0035] In one optional implementation, the determining method further includes:

[0036] If the target voltage difference is less than or equal to a preset voltage difference threshold, or the absolute value of the first SOC difference is greater than or equal to the first SOC threshold, or the absolute value of the second SOC difference is less than or equal to the second SOC threshold, the SOC jump anomaly type of the vehicle battery is determined to be a data loss anomaly type.

[0037] In one alternative implementation, the battery SOC jump scenario database is constructed through the following steps:

[0038] Acquire multiple SOC transition data within a preset time period, and determine multiple SOC transition scenarios and the transition type of each SOC transition scenario;

[0039] For each SOC transition scenario, determine whether the transition scenario is an abnormal transition scenario, and generate the abnormal transition information corresponding to the SOC transition scenario;

[0040] The battery SOC transition scenario database is generated by combining SOC transition scenarios belonging to the same transition type with the corresponding abnormal transition information set.

[0041] In one alternative implementation, the battery SOC jump characteristic database is constructed through the following steps:

[0042] Based on the battery SOC jump scenario database, initial data features are constructed;

[0043] Based on the initial data features, cluster analysis is performed on the acquired multiple SOC jump data to determine the SOC jump scenario classification results;

[0044] Based on the SOC jump scenario classification results, the data feature thresholds corresponding to each data feature are adjusted, and abnormal data features are deleted to construct the battery SOC jump feature database.

[0045] The data feature threshold is set based on the SOC accuracy of the vehicle battery and the BMS threshold.

[0046] In an optional implementation, after determining the SOC jump anomaly type of the vehicle battery based on the target anomaly scenario and the vehicle battery information, the determination method further includes:

[0047] Based on the aforementioned SOC jump anomaly type, the vehicle-side SOC algorithm is corrected.

[0048] Secondly, an optional embodiment of this disclosure also provides a device for determining abnormal battery SOC fluctuations, applied in the cloud; the device includes:

[0049] The information receiving module is used to receive real-time vehicle operation information and vehicle battery information uploaded by the vehicle terminal.

[0050] The jump scenario determination module is used to detect whether the vehicle battery is in a state of SOC jump abnormality, and the target abnormal scenario in which SOC jump abnormality occurs, based on the vehicle operation information and vehicle battery information, combined with the pre-built battery SOC jump scenario database and battery SOC jump feature database.

[0051] The jump type determination module is used to determine the SOC jump anomaly type of the vehicle battery based on the target abnormal scenario and the vehicle battery information.

[0052] Thirdly, an optional embodiment of this disclosure also provides an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for determining a battery SOC jump abnormality as described in any of the first aspects.

[0053] Fourthly, an optional embodiment of this disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for determining a battery SOC jump anomaly as described in any of the first aspects.

[0054] The battery SOC jump anomaly determination method, apparatus, electronic device, and storage medium provided in this disclosure receive real-time vehicle operation information and vehicle battery information uploaded by the vehicle terminal; based on the vehicle operation information and vehicle battery information, combined with a pre-built battery SOC jump scenario database and battery SOC jump feature database, it detects whether the vehicle battery is experiencing an SOC jump anomaly, and identifies the target anomaly scenario; based on the target anomaly scenario and the vehicle battery information, it determines the SOC jump anomaly type of the vehicle battery. Thus, after receiving the vehicle operation information and vehicle battery information from the vehicle terminal in the cloud, the target anomaly scenario of the vehicle battery's SOC jump anomaly is promptly determined using the pre-built battery SOC jump scenario database and battery SOC jump feature database, and the SOC jump anomaly type of the vehicle battery is determined specifically for the target anomaly scenario, which helps improve the efficiency and accuracy of SOC jump type judgment.

[0055] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0056] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 is a flowchart of a method for determining battery SOC jump anomaly according to an optional embodiment of this disclosure;

[0058] Figure 2 is a schematic diagram of one of the structures of a battery SOC jump abnormality determination device provided in an optional embodiment of this disclosure;

[0059] Figure 3 is a second schematic diagram of a device for determining abnormal battery SOC switching provided in an optional embodiment of this disclosure;

[0060] Figure 4 is a schematic diagram of the structure of an electronic device provided in an optional embodiment of this disclosure. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. Based on the embodiments of this disclosure, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this disclosure.

[0062] First, the applicable scenarios of this disclosure are introduced. This disclosure can be applied to the field of automotive power battery technology.

[0063] With the development of technology, new energy vehicles are gradually entering users' lives. The power battery is the core component of electric vehicles and is related to the safety of vehicle use. In order to ensure the driving safety of the vehicle, it is necessary to analyze and predict the battery data in real time.

[0064] Among them, the State of Charge (SOC) of a power battery is one of the key indicators for measuring battery capacity and is crucial for battery management and performance. During daily operation, various factors can cause a deviation between the SOC calculated by the Battery Management System (BMS) and the actual SOC of the battery. When this deviation reaches a certain level, corrections are necessary. These corrections are reflected in the instrumentation or cloud-based system as SOC fluctuations.

[0065] In related technologies, the determination of the cause of SOC transition still adopts a unified judgment standard, which requires a lot of time to accurately determine the cause and type of SOC transition, resulting in low efficiency and accuracy in determining the type of SOC transition.

[0066] Based on this, the present disclosure provides a method for determining abnormal battery SOC transitions, so as to improve the efficiency and accuracy of SOC transition type judgment.

[0067] Please refer to Figure 1, which is a flowchart of a method for determining battery SOC jump anomalies according to an optional embodiment of this disclosure. As shown in Figure 1, the method for determining battery SOC jump anomalies according to an optional embodiment of this disclosure includes:

[0068] S101: Receives real-time vehicle operation information and vehicle battery information uploaded by the vehicle terminal.

[0069] S102. Based on the vehicle operation information and vehicle battery information, combined with the pre-built battery SOC jump scenario database and battery SOC jump feature database, detect whether the vehicle battery at the vehicle end is in a SOC jump abnormal situation, and the target abnormal scenario in which the SOC jump abnormality occurs.

[0070] S103. Based on the target abnormal scenario and the vehicle battery information, determine the SOC jump abnormality type of the vehicle battery.

[0071] This disclosure provides a method for determining abnormal SOC transitions in a battery. After receiving vehicle operation information and vehicle battery information from the vehicle terminal in the cloud, the method promptly identifies the target abnormal scenario of the vehicle battery's SOC transition by using a pre-established battery SOC transition scenario database and battery SOC transition feature database. The method then specifically determines the type of SOC transition abnormality for the target abnormal scenario, which helps improve the efficiency and accuracy of SOC transition type judgment.

[0072] The exemplary steps of the embodiments of this disclosure are described below:

[0073] S101: Receives real-time vehicle operation information and vehicle battery information uploaded by the vehicle terminal.

[0074] In one optional implementation of this disclosure, vehicle operation information and vehicle battery information can be uploaded to the cloud in real time via a wireless network, and the cloud can analyze the data.

[0075] In one optional implementation, the vehicle in question can be a new energy vehicle, and the collected vehicle battery information can be specific to the battery installed in the vehicle, including battery information during vehicle operation or charging. Specifically, the collection of vehicle operation information can be performed during vehicle travel and charging.

[0076] In one alternative implementation, the cloud can analyze the vehicle battery status based on the vehicle operation information and vehicle battery information uploaded by the vehicle in real time.

[0077] In one optional implementation, the vehicle can send vehicle operation information and vehicle battery information to the cloud at a preset time frequency. The time frequency can be set according to measurement needs and network transmission speed. When the vehicle uploads vehicle operation information and vehicle battery information, it will also upload the corresponding timestamp information simultaneously so that the cloud can perform data analysis based on the time information.

[0078] Among them, vehicle operation information includes vehicle mileage information, and vehicle battery information includes data such as current, cell temperature, cell voltage, and SOC during vehicle operation (driving, charging, etc.).

[0079] In this embodiment, the judgment is based on the abnormal SOC state of the battery. SOC (State of charge) reflects the remaining capacity of the battery and is numerically defined as the ratio of remaining capacity to the total battery capacity, usually expressed as a percentage. Its value ranges from 0 to 1. When SOC = 0, it indicates that the battery is fully discharged; when SOC = 1, it indicates that the battery is fully charged.

[0080] Among them, the State of Charge (SOC) of a power battery is one of the key indicators for measuring battery capacity and is crucial for battery management and performance. During daily operation, various factors can cause a deviation between the SOC calculated by the Battery Management System (BMS) and the actual SOC of the battery. When this deviation reaches a certain level, corrections are necessary. These corrections are reflected in the instrumentation or cloud-based system as SOC fluctuations.

[0081] SOC fluctuation refers to an abnormal change in the displayed state of charge (SOC) value of a battery. This phenomenon can be caused by various reasons, including but not limited to SOC calculation program malfunctions, battery pack failures, high-voltage distribution box failures, and battery manager failures. In new energy vehicles, if an SOC fluctuation is detected, the actual SOC value of the battery should first be estimated to determine if it is caused by a program malfunction. If it is a program malfunction, the SOC value displayed on the instrument panel should be calibrated based on the actual SOC value; if it is not a program malfunction, engineers need to analyze historical data to determine whether it is caused by a fault in the battery itself or other hardware.

[0082] Furthermore, after obtaining the vehicle operation information and vehicle battery information uploaded in real time from the vehicle in the cloud, the system will analyze whether the vehicle's SOC status changes abnormally and the reasons for such abnormal changes based on the vehicle operation information and vehicle battery information.

[0083] S102. Based on the vehicle operation information and vehicle battery information, combined with the pre-built battery SOC jump scenario database and battery SOC jump feature database, detect whether the vehicle battery at the vehicle end is in a SOC jump abnormal situation, and the target abnormal scenario in which the SOC jump abnormality occurs.

[0084] In this embodiment of the disclosure, a battery SOC jump scenario database and a battery SOC jump feature database need to be constructed based on historical SOC anomaly data and corresponding data features. The cloud analyzes whether there is an SOC jump anomaly in the vehicle battery and the cause of the anomaly based on the vehicle operation information and vehicle battery information received from the vehicle end, combined with the battery SOC jump scenario database and the battery SOC jump feature database.

[0085] In one optional implementation, a battery SOC jump scenario database and a battery SOC jump feature database need to be pre-constructed based on historical SOC anomaly data and corresponding data characteristics, and stored in the cloud. When analyzing data uploaded in real time from the vehicle, the databases are compared to these databases to further reduce the need to retrieve the databases again and improve the efficiency of determining the vehicle's SOC jump type.

[0086] The following sections will describe the construction process of the battery SOC jump scenario database and the battery SOC jump feature database.

[0087] Specifically, the battery SOC jump scenario database is constructed through the following steps:

[0088] a1: Obtain multiple SOC transition data within a preset time period, and determine multiple SOC transition scenarios and the transition type of each SOC transition scenario.

[0089] a2: For each SOC transition scenario, determine whether the transition scenario is an abnormal transition scenario, and generate the abnormal transition information corresponding to the SOC transition scenario.

[0090] a3: Generate the battery SOC transition scenario database by combining SOC transition scenarios belonging to the same transition type with the corresponding abnormal transition information set.

[0091] In one optional implementation, the preset time period can be the time from when the vehicle is put into use after production, and the multiple SOC jump data obtained can be SOC jump data of the same model at different time points, or SOC jump data of multiple different models in the same time period.

[0092] Furthermore, after acquiring multiple SOC transition data, it is necessary to analyze these multiple SOC data to determine multiple SOC transition scenarios and the transition type of each SOC transition scenario. For each SOC transition scenario, it is necessary to determine whether the current SOC transition scenario is an abnormal transition scenario and generate corresponding abnormal transition information. After clustering SOC transition scenarios belonging to the same transition type and their corresponding abnormal transition information, a battery SOC transition scenario database is generated.

[0093] In one alternative implementation, the SOC transition scenario includes at least one of the following:

[0094] Scenarios with full charge jump within accuracy range, scenarios with full charge jump outside accuracy range, scenarios with jump before resting time is reached, scenarios with jump after resting time is reached, scenarios with jump before resting time is reached, and scenarios with jump after resting time is reached.

[0095] The abnormal transition scenarios include at least one of the following:

[0096] Scenarios with sudden changes in accuracy after full charge, scenarios with sudden changes before the resting time is reached, scenarios with sudden changes before the threshold is reached, and scenarios with data loss.

[0097] Meanwhile, multiple SOC transition types include at least one of the following:

[0098] Category 1: Full charge jump, Category 2: Non-static jump, Category 3: Static jump, Category 4: Data problem.

[0099] In one possible implementation, the full charge jump category includes full charge jump scenarios within the accuracy range and full charge jump scenarios outside the accuracy range; the non-static jump category includes jump scenarios before the static time is reached; the static jump category includes static jump scenarios reaching the threshold and static jump scenarios not reaching the threshold; and the data problem category includes data loss scenarios.

[0100] For example, the database of battery SOC transition scenarios is stored in tabular form.

[0101] Please refer to Table 1, which is a data table of battery SOC transition scenarios. As shown in Table 1, it includes multiple SOC transition types, each of which includes at least one SOC transition scenario, as well as abnormal transition information corresponding to each SOC transition scenario.

[0102] Table 1 Data Table of Battery SOC Jump Scenarios

[0103] Furthermore, after constructing the battery SOC transition scenario database, based on the multiple SOC transition types included in the database and at least one SOC transition scenario under each SOC transition type, the data characteristics under each SOC transition scenario can be analyzed, thereby constructing a battery SOC transition feature database.

[0104] Specifically, the battery SOC jump feature database is constructed through the following steps:

[0105] b1: Based on the battery SOC jump scenario database, construct initial data features.

[0106] b2: Based on the initial data features, perform cluster analysis on the acquired multiple SOC jump data to determine the SOC jump scenario classification results.

[0107] b3: Based on the SOC jump scenario classification results, adjust the data feature thresholds corresponding to each data feature, delete abnormal data features, and then construct the battery SOC jump feature database.

[0108] In this embodiment of the disclosure, based on the constructed battery SOC jump scenario database, multiple SOC jump types and at least one SOC jump scenario included under each SOC jump type are determined. Then, based on the initial data features under each SOC jump scenario and based on the acquired multiple SOC jump data, cluster analysis is performed to determine the SOC jump scenario classification result. At the same time, abnormal data that does not meet the conditions in the data features are deleted, and a battery SOC jump feature database is constructed.

[0109] Abnormal data that does not meet the criteria may include data that is obviously erroneous.

[0110] Specifically, data features may include time difference, mileage information, SOC values, etc.

[0111] For example, the battery SOC jump feature database is stored in tabular form.

[0112] Please refer to Table 2, which is a data table of battery SOC transition characteristics. As shown in Table 2, it includes multiple SOC transition types, each of which includes at least one SOC transition scenario, as well as the data characteristics corresponding to each SOC transition scenario.

[0113] Table 2 Battery SOC Jump Characteristics Data Table

[0114] The data feature thresholds (a*, b*) are set based on the SOC accuracy of the vehicle battery and the thresholds initially set by the BMS.

[0115] The mileage difference refers to the difference in mileage between the current frame and the previous frame when a SOC transition occurs. For example, if the current frame that has a transition corresponds to a mileage of 5000 kilometers and the previous frame that has a transition corresponds to a mileage of 4900 kilometers, then the current mileage difference is 100 kilometers.

[0116] Furthermore, after receiving the vehicle operation information and vehicle battery information uploaded by the vehicle terminal in the cloud, the system compares the vehicle operation information and vehicle battery information with the data features in the battery SOC jump feature database to determine the jump type and jump scenario of the current vehicle battery. Then, based on the battery SOC jump scenario database, it determines whether the current vehicle jump scenario belongs to the target abnormal scenario.

[0117] Specifically, the step "detecting whether the vehicle battery at the vehicle end is in a state of abnormal SOC transition" includes:

[0118] c1: Based on the mileage and running time information in the vehicle operation information, and combined with the SOC information in the vehicle battery information, determine the target SOC transition scenario and the target SOC transition type.

[0119] c2: Based on the abnormal transition information corresponding to the target SOC transition type under the target SOC transition type, detect whether the vehicle battery at the vehicle end is in a state of abnormal SOC transition.

[0120] In one optional implementation, the target SOC transition scenario of the current vehicle is determined by combining the battery SOC transition feature database, the mileage information in the vehicle operation information uploaded in real time by the vehicle terminal, and the SOC information in the vehicle battery information, along with the corresponding time information. Then, based on the battery SOC transition scenario database, it is determined whether the current target SOC transition scenario is an abnormal SOC transition scenario.

[0121] For example, if the current mileage difference is determined to be 0 based on the mileage information in the vehicle operation information, and the SOC information in the vehicle battery information shows that the current SOC = 100 and the time difference is less than 5 minutes, and the SOC value of the previous frame obtained based on the timestamp is less than or equal to a preset threshold, then according to the battery SOC jump feature database, it can be known that the current vehicle battery belongs to the jump scenario of precision external full charge jump, and according to the battery SOC jump scenario database, it can be known that the precision external full charge jump scenario is an abnormal jump scenario. That is, it can be determined whether the vehicle battery at the vehicle end is in an abnormal SOC jump.

[0122] Furthermore, once it is determined that the current vehicle battery is in a state of SOC abnormality, the abnormal transition type that caused the current vehicle battery SOC transition abnormality can be determined based on the target abnormal scenario of the current vehicle battery. Then, the vehicle battery can be diagnosed and repaired according to the abnormal transition type, and the SOC algorithm can be modified at the same time.

[0123] S103. Based on the target abnormal scenario and the vehicle battery information, determine the SOC jump abnormality type of the vehicle battery.

[0124] In the embodiments disclosed herein, the methods for determining the SOC jump anomaly type differ for different SOC anomaly scenarios. The specific methods for determining the SOC jump anomaly type will be described below for different anomaly jump types.

[0125] Firstly, when the target abnormal scenario is the aforementioned full-charge jump scenario, the step "determine the SOC jump anomaly type of the vehicle battery based on the target abnormal scenario and the vehicle battery information" includes:

[0126] d1: Based on the vehicle battery information, determine the current SOC jump time and the first target time that meets the preset statistical conditions before the jump time; wherein, the first target time is the time corresponding to when the battery is fully charged or the time corresponding to when the SOC correction condition is reached.

[0127] d2: Based on the vehicle battery information, calculate the SOC deviation of the vehicle battery for each charge-discharge cycle within the target time period from the first target time to the jump time.

[0128] d3: If the SOC deviation is greater than the first deviation threshold, the SOC jump anomaly type of the vehicle battery is determined to be the insufficient accuracy jump type.

[0129] In this embodiment of the disclosure, for the scenario of full charge jump in precision external, it is necessary to pre-determine the jump time of the current SOC jump, and then determine the first target time when the battery is fully charged or when the SOC correction condition is reached based on the historical vehicle battery information uploaded by the vehicle terminal.

[0130] Furthermore, based on the vehicle battery information, the SOC deviation of the vehicle battery for each charge-discharge cycle within the target time period from the first target time to the transition time is calculated.

[0131] One method for calculating the SOC deviation for each charge-discharge cycle is to first determine the number of cycles included in the target time period from the first target time to the transition time of the vehicle battery, and then perform the calculation.

[0132] Specifically, the step "based on the vehicle battery information, calculate the SOC deviation of the vehicle battery for each charge-discharge cycle within the target time period from the first target time to the transition time" includes:

[0133] e1: Based on the vehicle battery information, calculate the total charge and discharge capacity of the vehicle battery within the target time period.

[0134] e2: Based on the total charge / discharge capacity and the rated capacity of the vehicle battery, determine the number of charge / discharge cycles within the target time period.

[0135] e3: For each charge-discharge cycle, the SOC deviation of that charge-discharge cycle is determined based on the number of charge-discharge cycles and the number of SOC jumps of the vehicle battery within the target time period.

[0136] In one alternative implementation, the total charge and discharge capacity C1 of the vehicle battery within the target time period can be calculated based on the ampere-hour integral; alternatively, the total charge and discharge capacity C1 of the vehicle battery within the target time period can be calculated based on other SOC calculation methods.

[0137] Among the various SOC estimation methods, there are: open-circuit voltage method, ampere-hour integration method, internal resistance method, neural network method, and Kalman filter method. The open-circuit voltage method requires predicting the open-circuit voltage, necessitating a long period of static storage of the battery pack. The internal resistance method faces difficulties in estimating internal resistance and is also difficult to implement in hardware. Neural network and Kalman filter methods are not advantageous due to the difficulty in system setup and high cost when applied in battery management systems. Therefore, compared to the open-circuit voltage method, internal resistance method, neural network method, and Kalman filter method, ampere-hour integration is simpler. In conclusion, ampere-hour integration is the preferred method for SOC estimation.

[0138] Specifically, the ampere-hour integration method is the most commonly used method for SOC estimation. If the initial charging / discharging state is denoted as SOC0, then the SOC of the current state is:

[0139] Where SOC is the current SOC, SOC0 is the initial state of charging and discharging, C0 is the rated capacity of the vehicle battery, I is the charging and discharging current of the vehicle battery, η is the charging and discharging efficiency, and t is the charging and discharging time.

[0140] Furthermore, the number of charge / discharge cycles within the target time period can be determined based on the total charge / discharge capacity and the rated capacity of the vehicle battery; specifically, the number of charge / discharge cycles within the target time period can be determined using the following formula:

[0141] Where L is the number of charge-discharge cycles within the target time period; C1 is the total capacity within the target time period; and C0 is the rated capacity of the vehicle battery.

[0142] Furthermore, after determining the number of charge-discharge cycles within the target time period, the SOC deviation of the charge-discharge cycle can be determined based on the number of charge-discharge cycles and the number of SOC jumps of the vehicle battery within the target time period. Specifically, the SOC deviation of the charge-discharge cycle can be determined using the following formula:

[0143] Where L is the number of charge-discharge cycles within the target time period; ΔSOC0 is the SOC deviation of the charge-discharge cycle; and a is the number of SOC jumps.

[0144] In one alternative implementation, if the calculated SOC deviation is determined to be greater than a first deviation threshold, then the SOC jump anomaly type of the vehicle battery is determined to be an insufficient accuracy jump type.

[0145] The first deviation threshold can be set according to the battery type of the vehicle battery or the vehicle's operating parameters, for example, the first deviation threshold can be set to 3.

[0146] Secondly, when the target abnormal scenario is the scenario of jumping before the resting time is reached or the scenario of jumping before the threshold is reached, the calculation type of the SOC jump abnormality type of the vehicle battery is consistent for both.

[0147] Specifically, the step "determining the SOC jump anomaly type of the vehicle battery based on the target abnormal scenario and the vehicle battery information" includes:

[0148] f1: Based on the vehicle battery information, determine the current SOC transition time and the second target time within a preset time threshold before the transition time.

[0149] f2: Based on the vehicle battery information, determine the first cell voltage corresponding to the transition time, the second cell voltage corresponding to the second target time, the first SOC value corresponding to the transition time, and the second SOC value corresponding to the second target time.

[0150] f3: Determine the target voltage difference based on the voltage of the first cell and the voltage of the second cell.

[0151] f4: Based on the first SOC value and the calculated actual SOC value of the vehicle battery, determine the first SOC difference, and based on the second SOC value and the actual SOC value, determine the second SOC difference.

[0152] f5: If the target voltage difference is greater than the preset voltage difference threshold, and the absolute value of the first SOC difference is less than the first SOC threshold, and the absolute value of the second SOC difference is greater than the first SOC threshold, then the SOC jump anomaly type of the vehicle battery is determined to be the BMS threshold anomaly jump type.

[0153] In this embodiment of the disclosure, after determining that there is a SOC transition anomaly, when the current SOC transition occurs, a second target time within a preset time threshold before the transition time is determined based on the current time.

[0154] The preset time threshold can be set to one hour, meaning that the time between the second target time and the current jump time is less than or equal to one hour.

[0155] Furthermore, based on the current vehicle battery information, the first cell voltage corresponding to the transition time and the first SOC value corresponding to the transition time are determined. bmsBased on historical battery information obtained within the historical time period, the second cell voltage corresponding to the second target time and the second SOC value corresponding to the second target time are determined. bms-pre The target voltage difference between the transition time and the second target time is calculated based on the first cell voltage corresponding to the transition time and the second cell voltage corresponding to the second target time.

[0156] In one alternative implementation, the actual SOC value of the vehicle battery can be calculated based on the obtained cell voltage and the OCV-SOC curve. calc-pre ); and then, based on the first SOC value and the calculated actual SOC value of the vehicle battery, the first SOC difference (SOC) is calculated. calc-pre -SOC bms Furthermore, based on the second SOC value and the calculated actual SOC value of the vehicle battery, the second SOC difference (SOC) is calculated. calc-pre -SOC bms-pre ).

[0157] Furthermore, if it is determined that the calculated target voltage difference is greater than the preset voltage difference threshold, and the absolute value of the first SOC difference is less than the first SOC threshold, while the absolute value of the second SOC difference is greater than the first SOC threshold, then the SOC jump anomaly type of the vehicle battery can be determined to be the BMS threshold anomaly jump type.

[0158] For example, the preset voltage difference threshold can be set to 50mV; the first SOC threshold can be set to 1%; and the second SOC threshold can be set to 5%.

[0159] That is, when the target voltage difference is greater than 50mV and |SOC calc-pre -SOC bms |<1%,|SOC calc-pre -SOC bms-pre When |>5%, the SOC jump anomaly type of the vehicle battery is determined to be the BMS threshold anomaly jump type.

[0160] In one alternative implementation, if the above conditions are not met, the SOC jump anomaly type of the vehicle battery is determined to be a data loss anomaly type.

[0161] Specifically, the determination method further includes:

[0162] g1: If the target voltage difference is less than or equal to a preset voltage difference threshold, or the absolute value of the first SOC difference is greater than or equal to the first SOC threshold, or the absolute value of the second SOC difference is less than or equal to the second SOC threshold, the SOC jump anomaly type of the vehicle battery is determined to be a data loss anomaly type.

[0163] In this embodiment of the disclosure, if it is determined that the target voltage difference is less than or equal to a preset voltage difference threshold, and the absolute value of the first SOC difference is greater than or equal to the first SOC threshold, or the absolute value of the second SOC difference is less than or equal to the second SOC threshold, then the SOC jump anomaly type of the vehicle battery is determined to be a data loss anomaly type.

[0164] For example, in the above example, when the target voltage difference is less than or equal to 50mV, or |SOC calc-pre -SOC bms |≥1%,|SOC calc-pre -SOC bms-pre When |≤5%, the SOC jump anomaly type of the vehicle battery is determined to be a data loss anomaly type.

[0165] Furthermore, if it is determined that the vehicle has an abnormal SOC jump, the vehicle side needs to be notified to correct the SOC algorithm to ensure the normal operation of the vehicle battery.

[0166] Specifically, after the step of "determining the SOC jump anomaly type of the vehicle battery based on the target abnormal scenario and the vehicle battery information", the determination method further includes:

[0167] h1: Based on the SOC jump anomaly type, correct the vehicle-side SOC algorithm.

[0168] In this embodiment of the disclosure, the SOC algorithm may be modified and an OTA upgrade may be performed based on the cloud-based determination result (SOC jump anomaly type).

[0169] OTA (Over-the-Air) updates are a technology that allows software updates to be downloaded and installed without a wired connection. In the automotive industry, OTA updates allow vehicles to receive and install updates via wireless networks, thereby improving vehicle performance and system functionality. This technology is primarily applicable to pure electric vehicles or models equipped with internet-connected in-vehicle infotainment systems.

[0170] In one optional implementation, the specific update method is that the cloud determines the SOC transition anomaly type based on the judgment result and sends the SOC transition anomaly type to the corresponding vehicle terminal. When the vehicle terminal is powered on again, it corrects the SOC algorithm to correct the existing SOC transition anomaly.

[0171] The method for determining battery SOC jump anomalies provided in this embodiment receives real-time vehicle operation information and vehicle battery information uploaded by the vehicle terminal; based on the vehicle operation information and vehicle battery information, combined with a pre-built battery SOC jump scenario database and a battery SOC jump feature database, it detects whether the vehicle battery is experiencing an SOC jump anomaly, and identifies the target anomaly scenario; based on the target anomaly scenario and the vehicle battery information, it determines the SOC jump anomaly type of the vehicle battery. In this way, after receiving the vehicle operation information and vehicle battery information sent by the vehicle terminal in the cloud, the target anomaly scenario of the vehicle battery's SOC jump anomaly is promptly determined using the pre-built battery SOC jump scenario database and battery SOC jump feature database, and the SOC jump anomaly type of the vehicle battery is determined specifically for the target anomaly scenario, which helps improve the efficiency and accuracy of SOC jump type judgment.

[0172] Based on the same inventive concept, this disclosure also provides a device for determining battery SOC jump abnormality corresponding to the method for determining battery SOC jump abnormality. Since the principle of the device in this disclosure for solving the problem is similar to the method for determining battery SOC jump abnormality described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0173] Please refer to Figures 2 and 3. Figure 2 is a schematic diagram of one of the structures of a battery SOC jump anomaly determination device provided in an optional embodiment of this disclosure, and Figure 3 is a schematic diagram of another of the structures of a battery SOC jump anomaly determination device provided in an optional embodiment of this disclosure. As shown in Figure 2, the determination device 200 includes:

[0174] The information receiving module 210 is used to receive vehicle operation information and vehicle battery information uploaded in real time by the vehicle terminal;

[0175] The jump scenario determination module 220 is used to detect whether the vehicle battery at the vehicle end is in a state of SOC jump abnormality, and the target abnormal scenario in which SOC jump abnormality is, based on the vehicle operation information and vehicle battery information, combined with the pre-built battery SOC jump scenario database and battery SOC jump feature database.

[0176] The jump type determination module 230 is used to determine the SOC jump anomaly type of the vehicle battery based on the target abnormal scenario and the vehicle battery information.

[0177] In an optional implementation, as shown in FIG3, the determining device 200 further includes a scene database construction module 240, which is used to construct the battery SOC transition scene database through the following steps:

[0178] Acquire multiple SOC transition data within a preset time period, and determine multiple SOC transition scenarios and the transition type of each SOC transition scenario;

[0179] For each SOC transition scenario, determine whether the transition scenario is an abnormal transition scenario, and generate the abnormal transition information corresponding to the SOC transition scenario;

[0180] The battery SOC transition scenario database is generated by combining SOC transition scenarios belonging to the same transition type with the corresponding abnormal transition information set.

[0181] In an optional implementation, as shown in FIG3, the determining device 200 further includes a feature database construction module 250, which is used to construct the battery SOC jump feature database through the following steps:

[0182] Based on the battery SOC jump scenario database, initial data features are constructed;

[0183] Based on the initial data features, cluster analysis is performed on the acquired multiple SOC jump data to determine the SOC jump scenario classification results;

[0184] Based on the SOC jump scenario classification results, the data feature thresholds corresponding to each data feature are adjusted, and abnormal data features are deleted to construct the battery SOC jump feature database.

[0185] The data feature threshold is set based on the SOC accuracy of the vehicle battery and the BMS threshold.

[0186] In an optional implementation, as shown in FIG3, the determining device 200 further includes an algorithm correction module 260, the algorithm correction module 260 being used for:

[0187] Based on the aforementioned SOC jump anomaly type, the vehicle-side SOC algorithm is corrected.

[0188] In one optional implementation, the battery SOC jump scenario database includes multiple SOC jump types, and each SOC jump type includes at least one SOC jump scenario; the battery SOC jump feature database includes multiple SOC jump types, and each SOC jump type includes at least one SOC jump scenario, and each SOC jump scenario corresponds to specific battery data features and operating data features.

[0189] The SOC transition scenario includes at least one of the following:

[0190] Scenarios with full charge jump within accuracy range, scenarios with full charge jump outside accuracy range, scenarios with jump before resting time is reached, scenarios with jump after resting time is reached, scenarios with jump before resting time is reached, and scenarios with jump after resting time is reached.

[0191] In an optional implementation, when the jump scenario determination module 220 detects whether the vehicle battery at the vehicle end is in a state of charge (SOC) jump abnormality, the jump scenario determination module 220 is used to:

[0192] Based on the mileage and running time information in the vehicle operation information, and combined with the SOC information in the vehicle battery information, the target SOC transition scenario and target SOC transition type are determined.

[0193] Based on the abnormal transition information corresponding to the target SOC transition type under the target SOC transition type, detect whether the vehicle battery at the vehicle end is in a state of abnormal SOC transition.

[0194] In one alternative implementation, the abnormal transition scenario includes at least one of the following:

[0195] Scenarios with sudden changes in accuracy after full charge, scenarios with sudden changes before the resting time is reached, scenarios with sudden changes before the threshold is reached, and scenarios with data loss.

[0196] In an optional implementation, when the target abnormal scenario is the precision external full charge jump scenario, the jump type determination module 230, when determining the SOC jump abnormality type of the vehicle battery based on the target abnormal scenario and the vehicle battery information, is used to:

[0197] Based on the vehicle battery information, the time of the current SOC jump is determined, and a first target time that meets preset statistical conditions before the jump time is determined; wherein, the first target time is the time corresponding to when the battery is fully charged or the time corresponding to when the SOC correction condition is reached.

[0198] Based on the vehicle battery information, calculate the SOC deviation of the vehicle battery for each charge-discharge cycle within the target time period from the first target time to the jump time;

[0199] If the SOC deviation is greater than the first deviation threshold, the SOC jump anomaly type of the vehicle battery is determined to be the insufficient accuracy jump type.

[0200] In an optional implementation, when the jump type determination module 230 calculates the SOC deviation of the vehicle battery for each charge-discharge cycle within the target time period from the first target time to the jump time based on the vehicle battery information, the jump type determination module 230 is used to:

[0201] Based on the vehicle battery information, calculate the total charge and discharge capacity of the vehicle battery within the target time period;

[0202] Based on the total charge / discharge capacity and the rated capacity of the vehicle battery, determine the number of charge / discharge cycles within the target time period;

[0203] For each charge-discharge cycle, the SOC deviation of that charge-discharge cycle is determined based on the number of charge-discharge cycles and the number of SOC jumps of the vehicle battery within the target time period.

[0204] In an optional implementation, when the target abnormal scenario is the scenario of a jump in load before the resting time is reached or the scenario of a jump in load before the threshold is reached, the jump type determination module 230, when used to determine the SOC jump abnormality type of the vehicle battery based on the target abnormal scenario and the vehicle battery information, is used to:

[0205] Based on the vehicle battery information, determine the current SOC transition time and a second target time within a preset time threshold before the transition time.

[0206] Based on the vehicle battery information, the first cell voltage corresponding to the transition time, the second cell voltage corresponding to the second target time, the first SOC value corresponding to the transition time, and the second SOC value corresponding to the second target time are determined.

[0207] The target voltage difference is determined based on the voltage of the first cell and the voltage of the second cell.

[0208] Based on the first SOC value and the calculated actual SOC value of the vehicle battery, a first SOC difference is determined, and based on the second SOC value and the actual SOC value, a second SOC difference is determined.

[0209] If the target voltage difference is greater than a preset voltage difference threshold, and the absolute value of the first SOC difference is less than the first SOC threshold, and the absolute value of the second SOC difference is greater than the first SOC threshold, then the SOC jump anomaly type of the vehicle battery is determined to be the BMS threshold anomaly jump type.

[0210] In an optional implementation, the transition type determination module 230 is further configured to:

[0211] If the target voltage difference is less than or equal to a preset voltage difference threshold, or the absolute value of the first SOC difference is greater than or equal to the first SOC threshold, or the absolute value of the second SOC difference is less than or equal to the second SOC threshold, the SOC jump anomaly type of the vehicle battery is determined to be a data loss anomaly type.

[0212] The battery SOC jump anomaly determination device provided in this embodiment receives real-time vehicle operation information and vehicle battery information uploaded by the vehicle terminal; based on the vehicle operation information and vehicle battery information, combined with a pre-built battery SOC jump scenario database and battery SOC jump feature database, it detects whether the vehicle battery is experiencing an SOC jump anomaly, and identifies the target anomaly scenario; based on the target anomaly scenario and the vehicle battery information, it determines the SOC jump anomaly type of the vehicle battery. Thus, after receiving the vehicle operation information and vehicle battery information from the vehicle terminal in the cloud, it promptly determines the target anomaly scenario of the vehicle battery's SOC jump anomaly through the pre-built battery SOC jump scenario database and battery SOC jump feature database, and specifically determines the SOC jump anomaly type of the vehicle battery for the target anomaly scenario, which helps improve the efficiency and accuracy of SOC jump type determination.

[0213] Please refer to Figure 4, which is a schematic diagram of the structure of an electronic device provided in an optional embodiment of this disclosure. As shown in Figure 4, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0214] The memory 420 stores machine-readable instructions that can be executed by the processor 410. When the electronic device 400 is running, the processor 410 and the memory 420 communicate via the bus 430. When the machine-readable instructions are executed by the processor 410, the steps of the method for determining the abnormal battery SOC transition as shown in the method embodiment of Figure 1 above can be executed. For specific implementation, please refer to the method embodiment, which will not be repeated here.

[0215] This disclosure also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it can execute the steps of the method for determining battery SOC jump abnormality as shown in the method embodiment of FIG1 above. For specific implementation, please refer to the method embodiment, which will not be repeated here.

[0216] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0217] In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0218] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0219] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0220] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to related technologies, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0221] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A method for determining abnormal battery SOC fluctuations, applied in the cloud; The determination method comprises: receiving vehicle operation information and vehicle battery information uploaded in real time by a vehicle terminal; based on the vehicle operation information and the vehicle battery information, combining a pre-constructed battery SOC jump scenario database and a battery SOC jump feature database, detecting whether the vehicle battery of the vehicle terminal is in an SOC jump abnormality situation, and a target abnormal scenario in the SOC jump abnormality situation; based on the target abnormal scenario and the vehicle battery information, determining the SOC jump abnormality type of the vehicle battery.

2. The method of determining battery SOC jump anomaly according to claim 1, wherein, The battery SOC jump scenario database includes a plurality of SOC jump types, and each SOC jump type includes at least one SOC jump scenario; the battery SOC jump feature database includes a plurality of SOC jump types, and each SOC jump type includes at least one SOC jump scenario, and each SOC jump scenario corresponds to specific battery data features and operation data features; The SOC jump scenario includes at least one of the following: precision-in full charge jump scenario, precision-out full charge jump scenario, non-static time jump scenario, threshold static jump scenario, non-threshold static jump scenario, and data loss scenario.

3. The method of determining a battery SOC jump anomaly according to claim 2, wherein, The detection of whether the vehicle battery of the vehicle terminal is in an SOC jump abnormality situation comprises: based on the mileage information and the running time information in the vehicle operation information, combining the SOC information in the vehicle battery information, determining the target SOC jump scenario and the target SOC jump type; based on the abnormal jump information corresponding to the target SOC jump type under the target SOC jump type, detecting whether the vehicle battery of the vehicle terminal is in an SOC jump abnormality situation.

4. The method of determining battery SOC jump anomaly according to claim 2, wherein, The abnormal jump scenario includes at least one of the following: precision-out full charge jump scenario, non-static time jump scenario, non-threshold static jump scenario, and data loss scenario.

5. The method of determining battery SOC jump anomaly according to claim 4, wherein, When the target abnormal scenario is the precision-out full charge jump scenario, the determination of the SOC jump abnormality type of the vehicle battery based on the target abnormal scenario and the vehicle battery information comprises: based on the vehicle battery information, determining a jump time at which the SOC jump occurs currently, and a first target time satisfying a preset statistical condition before the jump time; wherein the first target time is a time corresponding to full charging of the battery or a time corresponding to reaching an SOC correction condition; based on the vehicle battery information, calculating the SOC deviation of each charge and discharge cycle included in a target time period from the first target time to the jump time of the vehicle battery; if the SOC deviation is greater than a first deviation threshold, determining that the SOC jump abnormality type of the vehicle battery is a precision deficiency jump type.

6. The method of determining battery SOC jump anomaly according to claim 5, wherein, The calculation of the SOC deviation of each charge and discharge cycle included in the target time period from the first target time to the jump time of the vehicle battery based on the vehicle battery information comprises: based on the vehicle battery information, calculating the total capacity of the vehicle battery in the target time period; determining, based on the total charging and discharging capacity and the rated capacity of the vehicle battery, a number of charging and discharging cycles in the target time period; for each charging and discharging cycle, determining, based on the number of charging and discharging cycles and a number of SOC jumps of the vehicle battery in the target time period, an SOC deviation of the charging and discharging cycle.

7. The method of determining battery SOC jump anomaly according to claim 4, wherein, When the target abnormal scenario is the non-static time jump scenario or the non-threshold static jump scenario, the determining, based on the target abnormal scenario and the vehicle battery information, of the SOC jump abnormal type of the vehicle battery comprises: determining, based on the vehicle battery information, a jump time at which the SOC jump currently occurs, and a second target time within a preset time threshold before the jump time; determining, based on the vehicle battery information, a first cell voltage corresponding to the jump time, a second cell voltage corresponding to the second target time, a first SOC value corresponding to the jump time, and a second SOC value corresponding to the second target time; determining a target voltage difference based on the first cell voltage and the second cell voltage; determining a first SOC difference based on the first SOC value and an actual SOC value of the vehicle battery calculated, and determining a second SOC difference based on the second SOC value and the actual SOC value; if the target voltage difference is greater than a preset voltage difference threshold, the absolute value of the first SOC difference is less than a first SOC threshold, and the absolute value of the second SOC difference is greater than the first SOC threshold, determining that the SOC jump abnormal type of the vehicle battery is a BMS threshold abnormal jump type.

8. The method of determining battery SOC jump anomaly according to claim 7, wherein, The method for determining the battery SOC jump abnormality further comprises: if the target voltage difference is less than or equal to the preset voltage difference threshold, or the absolute value of the first SOC difference is greater than or equal to the first SOC threshold, or the absolute value of the second SOC difference is less than or equal to a second SOC threshold, determining that the SOC jump abnormal type of the vehicle battery is a data loss abnormal type.

9. The method of determining battery SOC jump anomaly according to claim 1, wherein, The battery SOC jump scenario database is constructed by the following steps: obtaining a plurality of SOC jump data in a preset time period, and determining a plurality of SOC jump scenarios and a jump type to which each SOC jump scenario belongs; for each SOC jump scenario, determining whether the jump scenario is an abnormal jump scenario, and generating abnormal jump information corresponding to the SOC jump scenario; collecting the SOC jump scenarios and the corresponding abnormal jump information belonging to the same jump type to generate the battery SOC jump scenario database.

10. The method of determining battery SOC jump anomaly according to claim 1, wherein, The battery SOC jump feature database is constructed by the following steps: constructing initial data features based on the battery SOC jump scenario database; performing clustering analysis on the obtained plurality of SOC jump data based on the initial data features to determine an SOC jump scenario classification result; after adjusting the data feature thresholds corresponding to each data feature based on the SOC jump scenario classification result and deleting abnormal data features, constructing the battery SOC jump feature database; and The data feature threshold is based on the SOC accuracy of the vehicle battery and a BMS threshold setting.

11. The method of determining battery SOC jump anomaly according to claim 1, wherein, After determining the SOC jump abnormal type of the vehicle battery based on the target abnormal scenario and the vehicle battery information, the battery SOC jump abnormality determination method further comprises: Based on the SOC jump abnormal type, the SOC algorithm of the vehicle end is corrected. 12.A device for determining battery SOC jump anomaly, applied to a cloud. The determination device comprises: An information receiving module configured to receive vehicle running information and vehicle battery information uploaded by the vehicle end in real time; A jump scenario determination module configured to detect whether the vehicle battery of the vehicle end is in an SOC jump abnormal condition based on the vehicle running information and vehicle battery information, in combination with a pre-constructed battery SOC jump scenario database and a battery SOC jump feature database, and determine a target abnormal scenario in which the vehicle battery is in an SOC jump abnormal condition; A jump type determination module configured to determine the SOC jump abnormal type of the vehicle battery based on the target abnormal scenario and the vehicle battery information.

13. An electronic device comprising: A processor, a storage medium, and a bus, the storage medium storing machine-readable instructions executable by the processor, when the electronic device is running, the processor and the storage medium communicate through the bus, the processor executes the machine-readable instructions to perform the steps of the battery SOC jump abnormality determination method according to any one of claims 1 to 11.

14. A computer-readable storage medium, the computer-readable storage medium storing a computer program, the computer program being executed by a processor to perform the steps of the battery SOC jump abnormality determination method according to any one of claims 1 to 11.

Images