Detection Method, Device, Medium and Prompt Terminal for Abnormal Charging of New Energy Equipment

Abstract

The present application discloses a detection method, device, medium and prompt terminal for abnormal charging of new energy equipment. First, the type of the new energy equipment to be detected is determined, and then multiple new energy equipment of this type are selected as analysis objects to obtain primary reference charging process data. The secondary reference charging process data is calculated based on the primary reference charging process data, and the secondary actual charging process data is calculated based on the primary actual charging process data. Finally, based on the correspondence between the secondary reference charging process data and time, an abnormal detection method is used to determine the safety threshold corresponding to the secondary reference charging process data. Since the safety threshold is obtained from the primary reference charging process data, which is real data, the obtained safety threshold can more accurately reflect the current charging state of the new energy equipment to be detected. Moreover, the secondary reference charging process data can reflect the dynamic development of variables, so the obtained safety threshold can identify charging abnormalities in a timely manner.

Description

Technical Field

[0001] The present application relates to the field of new energy technologies, and particularly to a method, device, medium, and prompting terminal for detecting abnormal charging of new energy devices. Background Art

[0002] The new energy devices mentioned in the present application are devices that provide kinetic energy through batteries. For example, a vehicle using a battery, hereinafter referred to as an electric vehicle. With the rapid development of new energy devices, the charging technology of batteries has received increasing attention, and the charging safety is the focus of attention.

[0003] In order to prevent charging accidents caused by factors such as too high battery temperature during the charging process of the battery, usually the manufacturer conducts test experiments on the battery, obtains the safety thresholds of various variables for safe charging of the battery through the test experiments, and writes them into the battery management system (BMS). During the charging process, the size relationship between the current parameters of the battery and the set safety thresholds is compared to determine whether there is an abnormality in the battery charging.

[0004] Obviously, the safety thresholds obtained through test experiments are usually fixed. However, as the battery performance changes, the corresponding thresholds are also constantly changing. If a fixed safety threshold is used as the abnormal judgment criterion, it will inevitably lead to inaccurate judgment results. In addition, the existing safety thresholds usually quantify a static feature, for example, the temperature of the power battery, without considering the dynamic development of variables, so it is impossible to identify charging abnormalities in a timely manner.

[0005] Therefore, it can be seen that in the process of charging new energy devices, how to accurately and timely identify charging abnormalities is an urgent problem for those skilled in the art to solve. Summary of the Invention

[0006] The purpose of the present application is to provide a method, device, medium, and prompting terminal for detecting abnormal charging of new energy devices, which are used to accurately and timely identify charging abnormalities during the charging process of new energy devices.

[0007] To solve the above technical problems, the present application provides a method for detecting abnormal charging of new energy devices, including:

[0008] Determine the type of the new energy device to be detected;

[0009] Select multiple new energy devices of the type as analysis objects;

[0010] Obtain the first reference charging process data that matches the analysis object within a preset time range, where the first reference charging process data is the data generated by the analysis object during the charging process;

[0011] Calculate the secondary reference charging process data corresponding to each variable for characterizing the variable change trend according to the primary reference charging process data;

[0012] Calculate the secondary actual charging process data corresponding to each variable for characterizing the variable change trend according to the primary actual charging process data of the new energy device to be detected; wherein, the primary actual charging process data is the data generated during the current charging process of the new energy device to be detected;

[0013] Based on the corresponding relationship between the secondary reference charging process data and time, use an anomaly detection method to determine the safety threshold corresponding to the secondary reference charging process data, and the safety threshold is used as a comparison object to compare with the secondary actual charging process data of the new energy device to be detected to determine whether the new energy device to be detected has abnormal charging.

[0014] Preferably, selecting multiple new energy devices of the type as analysis objects includes:

[0015] Select multiple new energy devices of the same region and / or the same vehicle age of the type as the analysis objects.

[0016] Preferably, the step of determining the safety threshold corresponding to the secondary reference charging process data by using an anomaly detection method based on the corresponding relationship between the secondary reference charging process data and time includes:

[0017] Use a statistical analysis method or a clustering analysis method to determine the safety threshold corresponding to each variable in the secondary reference charging process data.

[0018] Preferably, the statistical analysis method includes a normal distribution statistical method and a mean method, and the clustering analysis method includes a Gaussian mixture clustering method.

[0019] Preferably, the step of obtaining the primary reference charging process data of the analysis object that matches the analysis object within a preset time range includes:

[0020] Obtain multiple target charging orders of the analysis object that match the analysis object within a preset time range;

[0021] Extract the primary reference charging process data from each of the target charging orders.

[0022] Preferably, it further includes:

[0023] Determine the health status corresponding to the deviation degree between the secondary actual charging process data and the safety threshold according to the corresponding relationship between the preset deviation degree and the health status.

[0024] Preferably, determining the health condition corresponding to the deviation degree between the secondary actual charging process data and the safety threshold according to the preset corresponding relationship between the deviation degree and the health condition includes:

[0025] Obtain multiple historical charging orders of the new energy device to be detected within a predetermined time;

[0026] Obtain the primary historical charging process data from each of the historical charging orders;

[0027] Calculate the secondary historical charging process data corresponding to each variable for characterizing the variable change trend according to the primary historical charging process data;

[0028] Calculate the average value corresponding to each variable in the secondary historical charging process data as the actual average value;

[0029] Calculate the reference average value corresponding to each variable in the secondary reference charging process data within the predetermined time;

[0030] Determine the variable deviation degree between the actual average value and the safety threshold corresponding to the same variable;

[0031] Determine the actual health level corresponding to the variable deviation degree according to the preset corresponding relationship between the variable deviation degree and the health level.

[0032] Preferably, determining the health condition corresponding to the deviation degree between the secondary actual charging process data and the safety threshold according to the preset corresponding relationship between the deviation degree and the health condition includes:

[0033] Determine the actual score data of each variable in the secondary actual charging process data according to the preset scoring model corresponding to each variable;

[0034] Determine the actual health level corresponding to the actual score data according to the preset corresponding relationship between the score data and the health level;

[0035] Wherein, the establishment process of the scoring model includes the following steps:

[0036] Conduct interval division according to multiple interval ranges composed of the average value and variance corresponding to each variable in the secondary reference charging process data;

[0037] Establish the corresponding relationship between the deviation degree and the score data according to the deviation degree of the actual value of each variable from the critical value of the corresponding interval.

[0038] Preferably, after determining the safety threshold corresponding to the secondary reference charging process data by using the anomaly detection method based on the corresponding relationship between the secondary reference charging process data and time, it further includes:

[0039] Establish a safety file for the new energy device to be detected according to the corresponding relationship between the safety threshold, the identity information of the new energy device to be detected, and the charging start information.

[0040] Preferably, it further includes:

[0041] After obtaining the actual charging start information of the new energy device to be detected sent by the charging device, search for the corresponding safety threshold and the identity information of the new energy device to be detected from the safety file according to the actual charging start information;

[0042] Send the safety threshold to the charging device so that the charging device can determine that the new energy device to be detected has abnormal charging when it determines that the secondary actual charging process data exceeds the safety threshold or the original threshold output by the BMS.

[0043] To solve the above technical problems, the present application also provides a detection device for abnormal charging of a new energy device, including a memory for storing a computer program;

[0044] A processor for implementing the steps of the detection method for abnormal charging of a new energy device as described when executing the computer program.

[0045] To solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the detection method for abnormal charging of a new energy device as described are implemented.

[0046] To solve the above technical problems, the present application also provides a prompt terminal for abnormal charging of a new energy device, including:

[0047] A memory for storing a computer program;

[0048] A processor for implementing the following steps when executing the computer program:

[0049] Receive the detection result of abnormal charging of the new energy device to be detected;

[0050] Output a prompt message for abnormal charging;

[0051] Among them, the detection result of abnormal charging is obtained through the following steps:

[0052] Determine the type of the new energy device to be detected;

[0053] Select multiple new energy devices of the type as analysis objects;

[0054] Obtain the first reference charging process data of the analysis object that matches the analysis object within a preset time range, where the first reference charging process data is the data generated by the analysis object during the charging process;

[0055] Calculate the second reference charging process data corresponding to each variable for characterizing the variable change trend according to the first reference charging process data;

[0056] Calculate the second actual charging process data corresponding to each variable for characterizing the variable change trend according to the first actual charging process data of the new energy device to be detected; where the first actual charging process data is the data generated during the current charging process of the new energy device to be detected;

[0057] Based on the correspondence between the second reference charging process data and time, use an anomaly detection method to determine the safety threshold corresponding to the second reference charging process data. The safety threshold is used as a comparison object to compare with the second actual charging process data of the new energy device to be detected to determine that the new energy device to be detected has a charging anomaly, and generate the charging anomaly detection result.

[0058] The method for detecting charging anomalies of a new energy device provided by the embodiments of the present application first determines the type of the new energy device to be detected, then selects multiple new energy devices of this type as analysis objects, and then obtains the first reference charging process data of the analysis object that matches the analysis object within a preset time range. Calculate the second reference charging process data according to the first reference charging process data, and calculate the second actual charging process data according to the first actual charging process data of the new energy device to be detected. Finally, based on the correspondence between the second reference charging process data and time, use an anomaly detection method to determine the safety threshold corresponding to the second reference charging process data. The safety threshold is used as a comparison object to compare with the second actual charging process data of the new energy device to be detected to determine that the new energy device to be detected has a charging anomaly. It can be seen that when applied to this technical solution, the safety threshold is obtained from the first reference charging process data of new energy devices of the same type as the new energy device to be detected within a preset time range, and the first reference charging process data is real data, so the obtained safety threshold can more accurately reflect the current charging state of the new energy device to be detected. Compared with a fixed threshold, the safety threshold obtained by this technical solution can improve the accuracy of charging anomaly detection. Moreover, the second reference charging process data can reflect the dynamic development of variables, so the obtained safety threshold can quantify the dynamic development of variables and can identify charging anomalies in a timely manner.

[0059] In addition, the detection device, medium, and charging anomaly prompt terminal of the new energy device provided by the present application correspond to the above method and have the same effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] To more clearly illustrate the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0061] Figure 1 FIG.

[0062] Figure 2 is a structural diagram of a charging management system for an electric vehicle provided by an embodiment of the present application;

[0063] Figure 3 FIG.

[0064] Figure 4 is a schematic diagram of a normal distribution curve of the maximum temperature rise rate provided by an embodiment of the present application;

[0065] Figure 5 FIG.

[0066] Figure 6 is a schematic diagram of a normal distribution curve of the maximum temperature difference provided by an embodiment of the present application;

[0067] Figure 7 FIG.

[0068] Figure 8 is a structural diagram of a detection device for charging anomalies of new energy equipment provided by another embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present application.

[0070] The core of this application is to provide a method, device, medium, and prompt terminal for detecting abnormal charging of new energy devices. The new energy devices proposed in this application can be electric vehicles or other electric devices. Hereinafter, electric vehicles are taken as an example for illustration. The method for detecting abnormal charging of new energy devices mentioned in the embodiments of this application can be applied to a charging cloud platform or a charging device, and can also be a driverless vehicle management platform (applicable to driverless vehicles). Hereinafter, the method for detecting abnormal charging of new energy devices applied to a charging cloud platform is described. Among them, the charging cloud platform is communicatively connected to the charging device and is used to uniformly manage multiple charging devices. Usually, the charging cloud platform is implemented by multiple computers cooperating with each other to perform corresponding functions. There are usually two hardware composition methods for charging devices. One is that the charger and the charging terminal are integrated, with a relatively large volume, which is commonly seen in scenarios such as rapid charging in highway service areas. The other is that the charger and the charging terminal are separated. One charger can be communicatively connected to multiple charging terminals and is used to uniformly manage multiple charging terminals. Since the charger and the charging terminal are separated, the charging terminal has a relatively small volume, directly performs data interaction with the electric vehicle, and has relatively simple functions. Usually, the vehicle data obtained is sent to the corresponding charger, and the charger completes more complex data operations and then returns the operation results to the charging terminal. Figure 1 This is a structural diagram of a charging management system for an electric vehicle provided by an embodiment of the present application. As Figure 1 shown, the charging management system includes a charging cloud platform, and multiple charging devices communicatively connected to the charging cloud platform. The charging devices obtain relevant data of the electric vehicle, such as charging start information, and send the charging start information to the charging cloud platform. The charging cloud platform identifies the device model based on the charging start information, and then performs relevant calculations on the charging process data of other new energy devices of the same type as the device to obtain a safety threshold. It should be noted that Figure 1 this is just a specific application scenario and does not mean that the charging cloud platform must be used to detect abnormal charging of new energy devices.

[0071] The hardware usage scenarios corresponding to the method for detecting abnormal charging of new energy devices provided in this application are described above. The embodiments of the method for detecting abnormal charging of new energy devices are described below. To enable those skilled in the art to better understand the solution of this application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0072] Figure 2 This is a flowchart of a method for detecting abnormal charging of new energy devices provided by an embodiment of the present application. As Figure 2 shown, the method includes:

[0073] S10: Determine the type of the new energy device to be detected.

[0074] The new energy device to be detected mentioned in this embodiment is one of the new energy devices. The purpose of determining the type of the new energy device to be detected is to select multiple new energy devices of this type as analysis objects.

[0075] S11: Select multiple new energy devices of the type as analysis objects.

[0076] It should be noted that the analysis objects are at least devices of the same type as the new energy device to be detected. In this embodiment, the analysis objects can be of the same type as the new energy device to be detected, or can be of the same type as the new energy device to be detected + the same vehicle age, etc. The purpose of selecting multiple new energy devices of the same type as analysis objects is to ensure that the obtained reference charging process data can accurately reflect the charging state of the new energy device to be detected, making the detection result more accurate. As a preferred implementation, select multiple new energy devices of the same type, in the same region, and / or with the same vehicle age as analysis objects.

[0077] S12: Obtain the first reference charging process data that matches the analysis objects within a preset time range. The charging process data mentioned in this application is the data generated by any new energy device during the charging process. The charging process data is sourced from the charging cloud platform and charging equipment, including charging system data and charging data. The charging system data is mainly the data of charging piles / charging terminals, user data, and vehicle data stored in the cloud platform system that supports the charging service. The charging data is obtained by the charging equipment from the vehicle during the charging process (handshake stage, parameter configuration stage, charging stage, charging end). The first reference charging process data is the data generated by the analysis objects during the charging process. Both the first reference charging process data and the first actual charging process data mentioned below are types of charging process data, that is, the data generated by the new energy device during the charging process. Only for the purpose of distinction, the data generated by the new energy device to be detected during the current charging process is called the first actual charging process data, and the charging process data of new energy devices (analysis objects) of the same model as the new energy device to be detected is called the first reference charging process data for use as reference data.

[0078] Correspondingly, the first reference charging process data can be the charging process data of new energy devices of the same type as the new energy device to be detected, or can be the charging process data of new energy devices of the same type as the new energy device to be detected + the same vehicle age, etc. Taking electric vehicles as an example, the reference charging process data can be the data generated by the following new energy devices during the charging process:

[0079] (1) The same vehicle model + a certain past time period / the current moment;

[0080] (2) The same vehicle model + the same region (such as the same city) + a certain past time period / the current moment;

[0081] (3)Same vehicle model + same vehicle age + a certain past time period / current moment.

[0082] For example, if the type of the new energy device to be detected is BYD EV450, then multiple new energy devices of the same type can be selected as the analysis objects as follows: Obtain electric vehicles with a vehicle age of 2 years of BYD EV450 in Chengdu from October 1st to October 30th, 2020 as the analysis objects.

[0083] As a preferred embodiment, the primary reference charging process data includes the maximum temperature of the power battery, the minimum temperature of the power battery, the SOC of the power battery, the highest voltage of the single cell, the lowest voltage of the single cell, the number of the single cell with the highest voltage, the number of the highest temperature monitoring point, and the number of the lowest temperature monitoring point. It should be noted that the SOC of the power battery mentioned in this embodiment includes the SOC during normal charging and also the SOC at the time of abnormal termination due to imbalance. The SOC at the time of abnormal termination due to imbalance belongs to the charging process data. It's just that after the charging anomaly occurs, the SOC at the end of charging is analyzed in reverse. The SOC at the time of abnormal termination due to imbalance is the battery SOC when the power battery is abnormally terminated due to imbalance, and the abnormal termination reasons highly related to imbalance are that the voltage of the single cell of the new energy device reaches the target value and the power battery reaches the target SOC to terminate. In a specific embodiment, the more variables in the primary reference charging process data, the more accurate the charging anomaly detection result. On this basis, the secondary reference charging process data includes the maximum temperature difference of the power battery, the maximum voltage difference of the power battery, the highest temperature rise rate of the power battery, the maximum SOC change rate of the power battery, the maximum voltage change rate of the single cell, the Shannon entropy value of the number of the highest temperature monitoring point, the Shannon entropy value of the number of the lowest temperature monitoring point, and the Shannon entropy value of the number of the single cell with the highest voltage.

[0084] 1) The maximum temperature difference of the power battery

[0085] The temperature difference refers to the difference between the highest temperature and the lowest temperature of the battery at the same moment during the charging process, which is obtained from the maximum temperature and the minimum temperature of the power battery. The maximum temperature difference refers to the maximum value of the temperature difference during a single charging process.

[0086] 2) The maximum voltage difference of the power battery

[0087] The maximum voltage difference refers to the difference between the highest voltage of the single cell and the lowest voltage of the single cell after a single charging process ends.

[0088] 3) The highest temperature rise rate of the power battery

[0089] The temperature rise rate refers to the change in the maximum temperature of the battery during charging at a specific frequency (millisecond, second, minute). The maximum temperature rise rate refers to the maximum value of the temperature rise rate during a single charging process.

[0090] 4) The maximum SOC change rate of the power battery

[0091] The SOC change rate refers to the change rate of the SOC transmitted by the BMS during a single charging process at a specific frequency (millisecond, second, minute). The maximum SOC change rate refers to the maximum value of the SOC change rate during a single charging process.

[0092] 5) The maximum change rate of the voltage of a single cell

[0093] The change rate of the voltage of a single cell refers to the change in the maximum voltage of a single cell transmitted by the BMS during charging at a specific frequency (millisecond, second, minute). The maximum change rate of the voltage of a single cell refers to the maximum value of the change rate of the voltage of a single cell during a single charging process.

[0094] 6) The Shannon entropy value of the number of the highest temperature monitoring point

[0095] Based on the numbers of the highest temperature detection points obtained at a specific frequency (millisecond, second, minute) during a single charging process, the Shannon entropy value of the number of the highest temperature monitoring point is calculated by combining the Shannon entropy algorithm.

[0096] 7) The Shannon entropy value of the number of the lowest temperature monitoring point

[0097] Based on the numbers of the lowest temperature detection points obtained at a specific frequency (millisecond, second, minute) during a single charging process, the Shannon entropy value of the number of the lowest temperature monitoring point is calculated by combining the Shannon entropy algorithm.

[0098] 8) The Shannon entropy value of the number where the highest voltage of a single cell is located

[0099] Based on the numbers of the detection points of the highest voltage of a single cell obtained at a specific frequency (millisecond, second, minute) during a single charging process, the Shannon entropy value of the number where the highest voltage of a single cell is located is calculated by combining the Shannon entropy algorithm.

[0100] It can be understood that the Shannon entropy value can show the degree of dispersion of the numbers of the highest temperature monitoring point and the number where the highest voltage of a single cell is located during the charging process. The lower the degree of dispersion, the greater the possibility of charging anomalies.

[0101] In addition, the primary reference charging process data obtained in this step can be obtained online after obtaining the charging start information of the new energy to be detected, or it can be pre-stored in the local database and directly called from the local database after obtaining the charging start information of the new energy to be detected. It can be understood that if it is obtained online after obtaining the charging start information of the new energy to be detected, the primary reference charging process data can be historical data or real-time data. If it is directly called from the local database after obtaining the charging start information of the new energy to be detected, the primary reference charging process data is historical data.

[0102] S13: Calculate the secondary reference charging process data corresponding to each variable for characterizing the variable change trend based on the primary reference charging process data.

[0103] The secondary reference charging process data is obtained from the primary reference charging process data and is used to characterize the variable change trend, such as variable difference, gradient change, etc. It can be understood that the number of variables included in the primary reference charging process data and the number of variables included in the secondary reference charging process data can be the same or different, but the variable types must be different, which will be described in detail below.

[0104] S14: Calculate the secondary actual charging process data corresponding to each variable for characterizing the variable change trend based on the primary actual charging process data of the new energy device to be detected.

[0105] The primary actual charging process data is the data generated during the current charging process of the new energy device to be detected. The secondary actual charging process data is obtained from the primary actual charging process data and is used to characterize the variable change trend, such as variable difference, gradient change, dispersion degree, etc. It should be noted that the method of obtaining the secondary reference charging process data from the primary reference charging process data is the same as the method of obtaining the secondary actual charging process data from the primary actual charging process data. It can be understood that the number of variables included in the primary reference charging process data and the number of variables included in the secondary reference charging process data can be the same or different, but the variable types must be different, which will be described in detail below.

[0106] S15: Based on the correspondence between the secondary reference charging process data and time, use the anomaly detection method to determine the safety threshold corresponding to the secondary reference charging process data. The safety threshold is used as a comparison object to compare with the secondary actual charging process data of the new energy device to be detected to determine whether the new energy device to be detected has abnormal charging.

[0107] It should be noted that in this embodiment, the calculation method of the safety threshold is not limited, and statistical analysis methods or clustering analysis methods can be used to determine it. The safety threshold in this step and the existing fixed threshold obtained through experiments are both used to measure whether the charging is abnormal. However, the safety threshold in this step is obtained from the real data of new energy devices of the same type as the new energy device to be detected during the charging process, so it can truly reflect the charging status of the same type of devices.

[0108] During the charging process of the new energy device to be detected, it is divided into four stages: the handshake stage, the parameter configuration stage, the charging stage, and the charging end. The actual charging process data can be the data of one stage or all stages among the four stages. Since the safety threshold is determined based on the charging process data of new energy devices of the same model as the new energy device to be detected, it can be used as the detection standard for the abnormality of the new energy device to be detected. As long as the secondary actual charging process data exceeds the safety threshold, it is determined that the new energy device to be detected has abnormal charging.

[0109] The method for detecting abnormal charging of a new energy device provided in this embodiment is as follows: First, determine the type of the new energy device to be detected, then select multiple new energy devices of this type as the analysis objects, and then obtain the first reference charging process data of the analysis objects that matches the analysis objects within a preset time range. Calculate the second reference charging process data based on the first reference charging process data, and calculate the second actual charging process data based on the first actual charging process data of the new energy device to be detected. Finally, based on the correspondence between the second reference charging process data and time, use the anomaly detection method to determine the safety threshold corresponding to the second reference charging process data. The safety threshold is used as a comparison object to compare with the second actual charging process data of the new energy device to be detected to determine whether the new energy device to be detected has abnormal charging. It can be seen that applied to this technical solution, the safety threshold is obtained from the first reference charging process data of new energy devices of the same type as the new energy device to be detected within a preset time range, and the first reference charging process data is real data, so the obtained safety threshold can more accurately reflect the current charging status of the new energy device to be detected. Compared with the fixed threshold, the safety threshold obtained by this technical solution can improve the accuracy of charging anomaly detection. Moreover, the second reference charging process data can reflect the dynamic development of variables, so the obtained safety threshold can quantify the dynamic development of variables and can identify charging anomalies in a timely manner.

[0110] Based on the correspondence between the second reference charging process data and time in the above embodiment, using the anomaly detection method to determine the safety threshold corresponding to the second reference charging process data includes:

[0111] Determine the safety thresholds corresponding to each variable in the secondary reference charging process data using statistical analysis methods or clustering analysis methods. As a preferred implementation, the statistical analysis methods include normal distribution statistical methods and mean methods, and the clustering analysis methods include Gaussian mixture clustering methods. The corresponding methods are described in detail below.

[0112] 1. Determine the safety threshold corresponding to the highest temperature rise rate in the secondary reference charging process data using the normal distribution statistical method

[0113] (1) Select the secondary reference charging process data in the charging orders of the same type of new energy equipment as the equipment to be detected in the past 30 days as sample data;

[0114] (2) Obtain the temperature rise rate for each charging order;

[0115] (3) Calculate the average value μ and standard deviation σ of the highest temperature rise rate of all orders;

[0116] (4) According to the "3σ" principle of the normal distribution: the interval (μ - 3σ, μ + 3σ) is the actual possible value interval of the random variable X, and the probability that X falls outside this interval is less than three thousandths. In practical problems, generally, it is considered that such an event will not occur. If the variable exceeds this three thousandths, it is an abnormal point. Then the threshold of the highest temperature is μ + 3σ, that is, the highest temperature safety threshold. Figure 3 This is a schematic diagram of the normal distribution curve of the highest temperature rise rate provided by the embodiment of the present application. As Figure 3 shown, points A, B, C, and D are respectively the highest temperature rise rates of the new energy equipment to be detected. Among them, the highest temperature rise rates of points A and B are normal, and the highest temperature rise rates of points C and D are abnormal.

[0117] 2. Determine the safety threshold corresponding to the maximum temperature difference in multiple groups of secondary reference charging process data using the normal distribution statistical method

[0118] (1) Select the secondary reference charging process data in the charging orders of the same type of new energy equipment as the equipment to be detected in the past 30 days as sample data;

[0119] (2) Obtain the maximum temperature difference for each order;

[0120] (3) Calculate the average value μ and standard deviation σ of the maximum temperature difference of all orders;

[0121] (4) According to the "3σ" principle of the normal distribution: the interval (μ - 3σ, μ + 3σ) is the actual possible value range of the random variable X, and the probability that X falls outside this interval is less than three thousandths. In practical problems, generally, such an event is considered not to occur. If the variable exceeds this three thousandths, it is an outlier. Then the threshold of the highest temperature is μ + 3σ, that is, the highest temperature safety threshold. Figure 4 It is a schematic diagram of the normal distribution curve of the maximum temperature difference provided by the embodiment of the present application. As Figure 4 shown, points A, B, C, D, and E are respectively the maximum temperature differences of the new energy device to be detected. Among them, the maximum temperature difference of point A is normal, and the maximum temperature differences of points B, C, D, and E are abnormal.

[0122] Similarly, according to the above method, the safety thresholds of each variable in the secondary reference charging process data can be obtained, which will not be elaborated in this embodiment. Figure 5 It is a schematic diagram of the normal distribution curve of the maximum SOC change rate provided by the embodiment of the present application. As Figure 5 shown, points A, B, C, and D are respectively the maximum SOC change rates of the new energy device to be detected. Among them, the maximum SOC change rates of points A, B, and C are normal, and the maximum SOC change rate of point D is abnormal. Figure 6 It is a schematic diagram of the normal distribution curve of the maximum pressure difference provided by the embodiment of the present application. As Figure 6 shown, point A is the maximum pressure difference of the new energy device to be detected, and the maximum pressure difference of point A is abnormal.

[0123] 3. Use the Gaussian mixture clustering method to determine the safety threshold corresponding to the highest temperature rise rate in the secondary reference charging process data

[0124] (1) Select the charging orders of the new energy devices of the same type as the new energy device to be detected within 30 days as the sample data;

[0125] (2) For each order, obtain the increase value of the highest temperature per minute, and then obtain the maximum value of the highest temperature increase value of each order;

[0126] (3) With the determined hyperparameters (number of clusters = 3), establish a Gaussian mixture model of the highest temperature rise rate;

[0127] (4) Perform clustering calculation on the secondary actual charging process data through the obtained Gaussian mixture model. The clustering result has 3 categories. The first category is μ - 3σ, the third category is μ + 3σ, and the rest are the second category. If the probability of the third category is greater than 50%, it indicates that the secondary actual charging process data exceeds the safety threshold.

[0128] Furthermore, obtaining the primary reference charging process data of the analysis object that matches the analysis object within the preset time range includes:

[0129] Obtain multiple target charging orders that match the analysis object within a preset time range;

[0130] Extract the first reference charging process data from each target charging order.

[0131] For the charging cloud platform, during the charging process of new energy equipment, a charging order corresponding to this charging will be generated, and the charging order contains the first reference charging process data mentioned above. Therefore, the method of obtaining the first reference charging process data using the charging order is relatively simple and does not require additional hardware or additional occupation of device resources.

[0132] In the above embodiments, it is possible to determine whether the new energy equipment to be detected has a charging anomaly based on whether the second actual charging process data exceeds the safety threshold. On this basis, in this embodiment, according to the corresponding relationship between the preset deviation degree and the health status, the health status corresponding to the deviation degree between the second actual charging process data and the safety threshold is determined, so as to determine the actual health level and evaluate the new energy equipment to be detected from multiple aspects.

[0133] As a preferred implementation manner, determining the health status corresponding to the deviation degree between the second actual charging process data and the safety threshold according to the corresponding relationship between the preset deviation degree and the health status includes:

[0134] Obtain multiple historical charging orders of the new energy equipment to be detected within a predetermined time;

[0135] Obtain the first historical charging process data from each historical charging order;

[0136] Calculate the second historical charging process data corresponding to each variable for characterizing the variable change trend according to the first historical charging process data;

[0137] Calculate the average value corresponding to each variable in the second historical charging process data as the actual average value;

[0138] Calculate the reference average value corresponding to each variable in the second reference charging process data within a predetermined time;

[0139] Determine the variable deviation degree between the actual average value corresponding to the same variable and the safety threshold;

[0140] Determine the actual health level corresponding to the variable deviation degree according to the corresponding relationship between the preset variable deviation degree and the health level.

[0141] It should be noted that the method of obtaining the secondary historical charging process data from the primary historical charging process data is the same as the method of obtaining the secondary actual charging process data from the primary actual charging process data. The primary historical charging process data in this embodiment is also a type of charging process data, but it is the charging process data corresponding to the historical charging order. Since the historical charging order is the order of the new energy device to be detected itself, the historical charging process data is the real data of the new energy device to be detected. The actual average value obtained from these data is used as a health assessment of the new energy device to be detected. Similarly, the reference average value obtained from the primary reference charging process data is used as a reference standard. If the deviation degree between the actual average value and the reference average value is large, it indicates that the risk of becoming a high-risk device is high. It can be understood that the corresponding relationship between the variable deviation degree and the health level can be obtained according to empirical values or other calibration methods, which will not be elaborated in this embodiment.

[0142] In this embodiment, on the basis of identifying that the new energy device to be detected has abnormal charging, the health status of the new energy device to be detected can also be evaluated to realize the quantification of the health status. Through the actual health level, the user can understand the charging trend of the power battery in advance, improving the user experience.

[0143] Corresponding to the previous embodiment, in this embodiment, the health status of the new energy device to be detected is quantitatively evaluated by another method. First, a scoring model needs to be established. The establishment process of the scoring model includes the following steps:

[0144] Interval division is carried out according to multiple interval ranges composed of the average value and variance corresponding to each variable in the secondary reference charging process data. For example, when the variable is the maximum temperature difference, it is divided into three grades, namely good, medium and poor, and the intervals include: (0, μ), (μ, μ + 3σ), (μ + 3σ, ∞).

[0145] Establish the corresponding relationship between the degree of deviation and the score data based on the degree of deviation of the actual values of each variable from the critical values of the corresponding intervals. Among them, the critical values of the corresponding intervals are 0, μ, and μ + 3σ. In specific implementation, according to the data mining method, different levels are quantitatively scored. For example, for the maximum temperature difference, it is further corrected based on the Zscore method, and 3σ is used as the critical value for high-risk vehicles. The score data can be from 0 to 100. It can be understood that the degree of deviation of the actual value from the critical value of the corresponding interval and the score data are negatively correlated, that is, the greater the degree of deviation of the actual value from the critical value of the corresponding interval, the lower the score data, and the smaller the degree of deviation of the actual value from the critical value of the corresponding interval, the higher the score data. For example, if μ + 3σ is 60 points, (0, μ) is 100 points (good), then 60 points < (μ, μ + 3σ) < 100 points (medium), (μ + 3σ, ∞) < 60 points (poor). If the actual variable falls within (μ, μ + 3σ), then specific scores are obtained according to the degree of deviation from the critical values μ and μ + 3σ.

[0146] The assessment of the health status of the new energy device to be detected using the scoring model specifically includes:

[0147] Determine the actual score data of each variable in the secondary actual charging process data according to the scoring model corresponding to each variable set in advance;

[0148] Determine the actual health level corresponding to the actual score data according to the corresponding relationship between the score data set in advance and the health level.

[0149] It can be understood that the charging protection mechanism can be determined according to the actual situation. For example, if the new energy device to be detected is in a high-risk station such as an oil and gas station, then all charging devices in this area are controlled to limit the current; or only the charging device where the new energy device to be detected is located is controlled to limit the current. In addition, different SOC limits can also be set according to different scenarios, or the charging devices in a specified area (such as Chengdu) are controlled to limit the current, etc. This embodiment will not be elaborated further.

[0150] On the basis of the above embodiment, in order to facilitate subsequent unified data management, in this embodiment, after determining the safety threshold corresponding to the secondary reference charging process data, it further includes:

[0151] Establish a safety file for the new energy device to be detected according to the corresponding relationship between the safety threshold, the identity information of the new energy device to be detected, and the charging start information.

[0152] Furthermore, in order to reduce the amount of data calculation and improve the detection speed, after obtaining the actual charging start information of the new energy device to be detected sent by the charging device, search for the corresponding safety threshold and the identity information of the new energy device to be detected from the safety file according to the actual charging start information;

[0153] Send a safety threshold to the charging device so that when the charging device determines that the secondary actual charging process data exceeds the safety threshold or the original threshold output by the BMS, it determines that the charging of the new energy device to be detected is abnormal.

[0154] Since a safety file is established, after the charging cloud platform obtains the actual charging start information, it can find the corresponding safety threshold from the safety file and directly send it to the charging device, saving the time of online calculation. It can be understood that for the charging cloud platform, it can also calculate a new safety threshold based on the latest reference charging process data and judge the actual charging process data according to the new safety threshold. In this embodiment, the detection of charging anomalies by the charging device is increased, the protection on the charging cloud platform side and the charging device side is realized, the division of labor and cooperation between the big data layer and the device layer is realized, and the respective advantages are exerted. In addition, for the charging device, on the one hand, it receives the safety threshold sent by the charging cloud platform, and on the other hand, it also obtains the fixed threshold sent by the BMS, and uses the two thresholds to judge the primary actual charging process data and the secondary actual charging process data to prevent inaccurate detection results caused by the loss or inaccuracy of one of the thresholds during transmission.

[0155] In the above embodiment, the detection method for charging anomalies of new energy devices is described in detail. The present application also provides an embodiment corresponding to the detection device for charging anomalies of new energy devices. It should be noted that the present application describes the embodiments of the device part from two perspectives, one is from the perspective of functional modules, and the other is from the perspective of hardware structure.

[0156] Figure 7 This is a structural diagram of a detection device for charging anomalies of new energy devices provided by an embodiment of the present application. As Figure 7 shown, from the perspective of functional modules, the detection device for charging anomalies of new energy devices includes:

[0157] A first determination module 10, configured to determine the type of the new energy device to be detected;

[0158] A selection module 11, configured to select multiple new energy devices of the type as analysis objects;

[0159] An acquisition module 12, configured to acquire the primary reference charging process data that matches the analysis object within a preset time range, where the primary reference charging process data is the data generated by the analysis object during the charging process;

[0160] A first processing module 13, configured to calculate the secondary reference charging process data corresponding to each variable for characterizing the variable change trend according to the primary reference charging process data;

[0161] The second processing module 14 is configured to calculate secondary actual charging process data corresponding to each variable for characterizing the variable change trend according to the primary actual charging process data of the new energy device to be detected; wherein, the primary actual charging process data is the data generated during the current charging process of the new energy device to be detected.

[0162] The second determination module 15 is configured to determine a safety threshold corresponding to the secondary reference charging process data by using an anomaly detection method based on the correspondence between the secondary reference charging process data and time. The safety threshold is used as a comparison object to compare with the secondary actual charging process data of the new energy device to be detected to determine whether the new energy device to be detected has an abnormal charging.

[0163] Since the embodiments in the device part correspond to the embodiments in the method part, please refer to the description of the embodiments in the method part for the embodiments in the device part, and will not be elaborated here.

[0164] The detection device for abnormal charging of a new energy device provided in this embodiment first determines the type of the new energy device to be detected, then selects multiple new energy devices of this type as analysis objects, and then obtains the primary reference charging process data that matches the analysis objects within a preset time range. Calculate the secondary reference charging process data according to the primary reference charging process data, and calculate the secondary actual charging process data according to the primary actual charging process data of the new energy device to be detected. Finally, based on the correspondence between the secondary reference charging process data and time, use an anomaly detection method to determine the safety threshold corresponding to the secondary reference charging process data. The safety threshold is used as a comparison object to compare with the secondary actual charging process data of the new energy device to be detected to determine whether the new energy device to be detected has an abnormal charging. Thus, it can be seen that when applied to this technical solution, the safety threshold is obtained from the primary reference charging process data of new energy devices of the same type as the new energy device to be detected within a preset time range, and the primary reference charging process data is real data. Therefore, the obtained safety threshold can more accurately reflect the current charging state of the new energy device to be detected. Compared with a fixed threshold, the safety threshold obtained by this technical solution can improve the accuracy of abnormal charging detection. Moreover, the secondary reference charging process data can reflect the dynamic development of variables, so the obtained safety threshold can quantify the dynamic development of variables and can identify abnormal charging in a timely manner.

[0165] Figure 8 The structural diagram of the detection device for abnormal charging of a new energy device provided in another embodiment of the present application is shown in Figure 8 As shown, from the perspective of the hardware structure, the detection device for abnormal charging of a new energy device includes: a memory 20 for storing a computer program.

[0166] The processor 21 is configured to implement the steps of the detection method for abnormal charging of new energy devices as described in the above embodiments when executing a computer program.

[0167] The detection device for abnormal charging of new energy devices provided in this embodiment may include, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.

[0168] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one of the following hardware forms: DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may further include an AI (Artificial Intelligence) processor, which is used to process computational operations related to machine learning.

[0169] The memory 20 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 20 may further include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201. After the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the detection method for abnormal charging of new energy devices disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may further include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, primary reference charging process data, secondary reference charging process data, primary actual charging process data, secondary actual charging process data, etc.

[0170] In some embodiments, the detection device for abnormal charging of new energy devices may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0171] Those skilled in the art can understand that Figure 8 the structure shown in does not constitute a limitation on the detection device for abnormal charging of new energy devices, and may include more or fewer components than those shown in the figure.

[0172] The detection device for abnormal charging of new energy devices provided by the embodiments of the present application includes a memory and a processor. When the processor executes the program stored in the memory, the following method can be implemented: First, determine the type of the new energy device to be detected, then select multiple new energy devices of this type as analysis objects, and then obtain the primary reference charging process data that matches the analysis objects within a preset time range. Calculate the secondary reference charging process data based on the primary reference charging process data, and calculate the secondary actual charging process data based on the primary actual charging process data of the new energy device to be detected. Finally, based on the correspondence between the secondary reference charging process data and time, use an anomaly detection method to determine the safety threshold corresponding to the secondary reference charging process data. The safety threshold is used as a comparison object to compare with the secondary actual charging process data of the new energy device to be detected to determine whether the new energy device to be detected has abnormal charging. It can be seen that, applied to this technical solution, the safety threshold is obtained from the primary reference charging process data of new energy devices of the same type as the new energy device to be detected within a preset time range, and the primary reference charging process data is real data. Therefore, the obtained safety threshold can more accurately reflect the current charging state of the new energy device to be detected. Compared with a fixed threshold, the safety threshold obtained by this technical solution can improve the accuracy of charging anomaly detection. Moreover, the secondary reference charging process data can reflect the dynamic development of variables. Therefore, the obtained safety threshold can quantify the dynamic development of variables and can identify charging anomalies in a timely manner.

[0173] The present application also provides an embodiment corresponding to a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.

[0174] It can be understood that if the methods in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of this application, in essence, or the parts that contribute to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0175] Finally, this application also provides a prompt terminal for abnormal charging of new energy devices, including a memory for storing a computer program;

[0176] a processor for implementing the following steps when executing the computer program:

[0177] receiving the charging anomaly detection result of the new energy device to be detected;

[0178] outputting a charging anomaly prompt message.

[0179] Among them, the charging anomaly detection result is obtained through the following steps:

[0180] determining the type of the new energy device to be detected;

[0181] selecting multiple new energy devices of the same type as analysis objects;

[0182] obtaining the first reference charging process data that matches the analysis object within a preset time range, where the first reference charging process data is the data generated by the analysis object during the charging process;

[0183] calculating the second reference charging process data corresponding to each variable for characterizing the variable change trend according to the first reference charging process data;

[0184] calculating the second actual charging process data corresponding to each variable for characterizing the variable change trend according to the first actual charging process data of the new energy device to be detected; where the first actual charging process data is the data generated during the current charging process of the new energy device to be detected;

[0185] Based on the correspondence between the data of the secondary reference charging process and time, an anomaly detection method is used to determine the safety threshold corresponding to the data of the secondary reference charging process. The safety threshold is used as a comparison object to compare with the secondary actual charging process data of the new energy device to be detected, so as to determine that the charging of the new energy device to be detected is abnormal and generate a charging anomaly detection result.

[0186] It can be understood that the prompt terminal for charging anomalies of the new energy device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, desktop computers, etc. Usually, the charging anomaly detection result is obtained by the charging cloud platform or charging terminal mentioned above. These devices establish a communication connection with the prompt terminal, so that after obtaining the charging anomaly detection result, it is sent to the prompt terminal, and the prompt terminal receives and outputs the charging anomaly prompt information, so that the user can view it in time.

[0187] The above has introduced in detail the detection method, device, medium and prompt terminal for charging anomalies of the new energy device provided in this application. Each embodiment in the specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0188] It should also be noted that in this specification, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including an..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

Claims

1. A detection method for abnormal charging of a new energy device, characterized in that, Including: Determine the type of the new energy device to be detected; Select multiple new energy devices of the said type as analysis objects; Obtain the primary reference charging process data that matches the analysis objects within a preset time range, where the primary reference charging process data is the data generated by the analysis objects during the charging process; Calculate the secondary reference charging process data corresponding to each variable for characterizing the variable change trend based on the primary reference charging process data; among them, the secondary reference charging process data includes at least one of the following: the maximum temperature difference of the power battery, the maximum pressure difference of the power battery, the maximum temperature rise rate of the power battery, the maximum SOC change rate of the power battery, the maximum change rate of the single cell voltage, the Shannon entropy value of the highest temperature monitoring point number, the Shannon entropy value of the lowest temperature monitoring point number, the Shannon entropy value of the number where the single cell has the highest voltage; Calculate the secondary actual charging process data corresponding to each variable for characterizing the variable change trend based on the primary actual charging process data of the new energy device to be detected; where the primary actual charging process data is the data generated during the current charging process of the new energy device to be detected; Based on the corresponding relationship between the secondary reference charging process data and time, use statistical analysis methods or clustering analysis methods to determine the safety thresholds corresponding to each variable in the secondary reference charging process data, and the safety thresholds are used as comparison objects to compare with the secondary actual charging process data of the new energy device to be detected to determine whether the charging of the new energy device to be detected is abnormal.

2. The detection method according to claim 1, characterized in that, The step of selecting multiple new energy devices of the said type as analysis objects includes: Select multiple new energy devices of the same region and / or the same vehicle age of the said type as the analysis objects.

3. The detection method according to claim 1, characterized in that, The statistical analysis methods include normal distribution statistical methods and mean methods, and the clustering analysis methods include Gaussian mixture clustering methods.

4. The detection method according to claim 1, characterized in that, The step of obtaining the primary reference charging process data that matches the analysis objects within a preset time range includes: Obtain multiple target charging orders that match the analysis objects within a preset time range; Extract the primary reference charging process data from each of the target charging orders.

5. The detection method according to any one of claims 1 to 4, characterized in that, It also includes: Determine the health status corresponding to the deviation degree between the secondary actual charging process data and the safety threshold according to the corresponding relationship between the preset deviation degree and the health status.

6. The detection method according to claim 5, characterized in that, The step of determining the health status corresponding to the deviation degree between the secondary actual charging process data and the safety threshold according to the corresponding relationship between the preset deviation degree and the health status includes: Obtain multiple historical charging orders of the new energy device to be detected within a predetermined time; Obtain the primary historical charging process data from each of the historical charging orders; Calculate the secondary historical charging process data corresponding to each variable for characterizing the variable change trend based on the primary historical charging process data; Calculate the average value corresponding to each variable in the secondary historical charging process data as the actual average value; Calculate the reference average value corresponding to each variable in the secondary reference charging process data within the predetermined time; Determine the variable deviation degree between the actual average value corresponding to the same variable and the safety threshold; Determine the actual health level corresponding to the variable deviation degree according to the pre-set corresponding relationship between the variable deviation degree and the health level.

7. The detection method according to claim 5, characterized in that, The determining of the health condition corresponding to the deviation degree between the secondary actual charging process data and the safety threshold according to the pre-set corresponding relationship between the deviation degree and the health condition includes: Determine the actual score data of each variable in the secondary actual charging process data according to the pre-set scoring model corresponding to each variable; Determine the actual health level corresponding to the actual score data according to the pre-set corresponding relationship between the score data and the health level.

8. The detection method according to claim 7, characterized in that, The establishment process of the scoring model includes the following steps: Conduct interval division according to the multiple interval ranges composed of the average value and variance corresponding to each variable in the secondary reference charging process data; Establish the corresponding relationship between the deviation degree and the score data according to the deviation degree of the actual value of each variable from the critical value of the corresponding interval.

9. The detection method according to any one of claims 1 to 4, characterized in that, After determining the safety threshold corresponding to the secondary reference charging process data by using the anomaly detection method based on the corresponding relationship between the secondary reference charging process data and time, it further includes: Establish the safety file of the new energy device to be detected according to the corresponding relationship between the safety threshold, the identity information of the new energy device to be detected, and the charging start information.

10. According to the detection method described in claim 9, characterized in that, It further includes: After obtaining the actual charging start information of the new energy device to be detected sent by the charging device, search for the corresponding safety threshold and the identity information of the new energy device to be detected from the safety file according to the actual charging start information; Send the safety threshold to the charging device so that the charging device can determine that the new energy device to be detected has abnormal charging when it determines that the secondary actual charging process data exceeds the safety threshold or the original threshold output by the BMS.

11. A detection device for abnormal charging of a new energy device, characterized in that, It includes: The first determination module is used to determine the type of the new energy device to be detected; The selection module is used to select multiple new energy devices of the type as the analysis objects; The acquisition module is used to acquire the primary reference charging process data that matches the analysis object within a preset time range, and the primary reference charging process data is the data generated by the analysis object during the charging process; The first processing module is used to calculate the secondary reference charging process data corresponding to each variable for characterizing the variable change trend according to the primary reference charging process data; among them, the secondary reference charging process data includes at least one of the following: the maximum temperature difference of the power battery, the maximum voltage difference of the power battery, the maximum temperature rise rate of the power battery, the maximum SOC change rate of the power battery, the maximum change rate of the single cell voltage, the Shannon entropy value of the highest temperature monitoring point number, the Shannon entropy value of the lowest temperature monitoring point number, the Shannon entropy value of the single cell highest voltage location number; A second processing module, configured to calculate, according to the primary actual charging process data of the new energy device to be detected, secondary actual charging process data corresponding to each variable for characterizing the variable change trend; wherein, the primary actual charging process data is the data generated during the current charging process of the new energy device to be detected; A second determination module, configured to determine, based on the correspondence between the secondary reference charging process data and time, the safety threshold corresponding to each of the variables in the secondary reference charging process data by using a statistical analysis method or a clustering analysis method, where the safety threshold is used as a comparison object to be compared with the secondary actual charging process data of the new energy device to be detected to determine that the new energy device to be detected has an abnormal charging.

12. A detection device for abnormal charging of a new energy device, characterized in that, It includes a memory for storing a computer program; A processor, configured to implement the steps of the method for detecting abnormal charging of a new energy device according to any one of claims 1 to 10 when executing the computer program.

13. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for detecting abnormal charging of a new energy device according to any one of claims 1 to 10 are implemented.

14. A prompt terminal for abnormal charging of a new energy device, characterized in that, It includes: A memory for storing a computer program; A processor, configured to implement the following steps when executing the computer program: Receiving the charging anomaly detection result of the new energy device to be detected; Outputting a charging anomaly prompt message; Wherein, the charging anomaly detection result is obtained through the following steps: Determining the type of the new energy device to be detected; Selecting multiple new energy devices of the type as analysis objects; Obtaining the primary reference charging process data matching the analysis object within a preset time range, where the primary reference charging process data is the data generated during the charging process of the analysis object; Calculating, according to the primary reference charging process data, secondary reference charging process data corresponding to each variable for characterizing the variable change trend; wherein, the secondary reference charging process data includes at least one of the following: the maximum temperature difference of the power battery, the maximum voltage difference of the power battery, the maximum temperature rise rate of the power battery, the maximum SOC change rate of the power battery, the maximum change rate of the single cell voltage, the Shannon entropy value of the highest temperature monitoring point number, the Shannon entropy value of the lowest temperature monitoring point number, the Shannon entropy value of the number where the highest voltage of the single cell is located; Calculating, according to the primary actual charging process data of the new energy device to be detected, secondary actual charging process data corresponding to each variable for characterizing the variable change trend; wherein, the primary actual charging process data is the data generated during the current charging process of the new energy device to be detected; Based on the correspondence between the secondary reference charging process data and time, using a statistical analysis method or a clustering analysis method to determine the safety threshold corresponding to each of the variables in the secondary reference charging process data, where the safety threshold is used as a comparison object to be compared with the secondary actual charging process data of the new energy device to be detected to determine that the new energy device to be detected has an abnormal charging and generate the charging anomaly detection result.

Images