Method for determining abnormal vehicle, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a method for determining an abnormal vehicle, electronic equipment and a computer readable storage medium. The method comprises the steps of determining whether the rising amplitude of at least one parameter of a power battery meets an amplitude threshold condition or not according to multiple groups of data obtained in multiple charging processes of the power battery of the vehicle; processing first data of which the rising amplitude meets an amplitude threshold condition in the multiple groups of data, so as to determine a change trend of at least one parameter according to second data of which the rising amplitude meets a degree threshold condition in the first data; performing trend inspection on the change trend to determine whether the change trend meets a trend inspection condition or not; and determining the vehicle corresponding to the change trend as an abnormal vehicle in response to determining that the change trend meets the trend inspection condition. According to the method disclosed by the embodiment of the invention, the abnormal vehicle can be identified as early as possible, and the probability of occurrence of safety accidents is reduced.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of vehicle charging, and more particularly, to a method for determining an abnormal vehicle, an electronic device, and a computer-readable storage medium. Background Art

[0002] In recent years, the number of new energy vehicles has gradually increased. Since the power batteries of new energy vehicles will gradually age during use, and even worse, thermal runaway events will occur, causing significant personal and property losses, it is very important to detect and evaluate the safety status of the power batteries of new energy vehicles. In addition, except for vehicle manufacturers and battery manufacturers, other related companies (such as charging platform companies) or individuals currently have no effective method to evaluate the health status of vehicles based on the battery data and raw data reported by the vehicle. Summary of the invention

[0003] The first aspect of the present disclosure provides a method for determining an abnormal vehicle. The method includes: determining whether the increase amplitude of at least one parameter of the power battery meets the amplitude threshold condition according to multiple sets of data acquired during multiple charging processes of the power battery of the vehicle; processing the first data whose increase amplitude meets the amplitude threshold condition in the multiple sets of data, so as to determine the change trend of the at least one parameter according to the second data that meets the degree threshold condition in the first data; performing a trend test on the change trend to determine whether the change trend meets the trend test condition; and in response to determining that the change trend meets the trend test condition, determining the vehicle corresponding to the change trend as an abnormal vehicle.

[0004] The method of the embodiment of the present disclosure calculates the correlation of the rise in the time dimension, and then confirms the normal rise amplitude and degree of the battery model in the space dimension, that is, determines the amplitude threshold and degree threshold, so that the abnormal vehicle can be identified before the vehicle changes to a more serious state. In addition, the amplitude threshold and degree threshold according to the embodiment of the present disclosure are determined based on the data of the corresponding period of the same battery model, so as to eliminate the influence of seasons and regions on the parameter thresholds, making the vehicle identification result more reliable.

[0005] In some embodiments, before determining whether the rising amplitude of at least one parameter of the power battery meets the amplitude threshold condition, it also includes: preprocessing the data obtained from the charging pile to remove abnormal data; and clustering the preprocessed data to determine the type of battery based on the clustering processing results.

[0006] In some embodiments, the method also includes: determining from data from the charging pile whether the number of valid orders within a predetermined period exceeds a predetermined threshold; and in response to determining that the number of valid orders within the predetermined period exceeds the predetermined threshold, determining the increase range based on multiple sets of data within the predetermined period.

[0007] In some embodiments, determining the increase further includes: processing multiple groups of data related to a selected parameter of at least one parameter within a predetermined period to remove abnormal data from the multiple groups of data; sorting the processed multiple groups of data in chronological order of orders corresponding to the multiple groups of data; filtering the sorted multiple groups of data; and processing the filtered multiple groups of data to determine the increase.

[0008] In some embodiments, the method further includes: processing the filtered data of the plurality of groups of batteries meeting the type condition and within a predetermined time period to determine the amplitude threshold condition of the corresponding type of battery.

[0009] In some embodiments, the method further includes: processing a plurality of first data within a predetermined time period for a plurality of groups of batteries meeting the type condition to determine the degree threshold condition.

[0010] In some embodiments, determining whether the changing trend satisfies the trend verification condition includes: sorting the second data by time; processing the sorted second data to determine the trend of at least one parameter and the correlation of the trend; and determining whether the changing trend satisfies the trend verification condition based on the trend and the correlation of the trend.

[0011] The second aspect of the present disclosure provides an electronic device. The electronic device includes: at least one processing unit; and at least one memory, which is coupled to the at least one processing unit and stores machine executable instructions, and when the instructions are executed by the at least one processing unit, the device performs an action, and the action includes: determining whether the increase amplitude of at least one parameter of the power battery meets the amplitude threshold condition according to multiple sets of data acquired during multiple charging processes of the power battery of the vehicle; processing the first data whose increase amplitude meets the amplitude threshold condition in the multiple sets of data, so as to determine the change trend of the at least one parameter according to the second data that meets the degree threshold condition in the first data; performing a trend test on the change trend to determine whether the change trend meets the trend test condition; and in response to determining that the change trend meets the trend test condition, determining the vehicle corresponding to the change trend as an abnormal vehicle.

[0012] In some embodiments, before determining whether the rising amplitude of at least one parameter of the power battery meets the amplitude threshold condition, it also includes: preprocessing the data obtained from the charging pile to remove abnormal data; and clustering the preprocessed data to determine the type of battery based on the clustering processing results.

[0013] In some embodiments, the action also includes: determining from data from the charging pile whether the number of valid orders within a predetermined period exceeds a predetermined threshold; and in response to determining that the number of valid orders within the predetermined period exceeds the predetermined threshold, determining the increase range based on multiple sets of data within the predetermined period.

[0014] In some embodiments, determining the increase further includes: processing multiple groups of data related to a selected parameter of at least one parameter within a predetermined period to remove abnormal data from the multiple groups of data; sorting the processed multiple groups of data in chronological order of orders corresponding to the multiple groups of data; filtering the sorted multiple groups of data; and processing the filtered multiple groups of data to determine the increase.

[0015] In some embodiments, the actions further include: processing the filtered data of the plurality of groups of batteries meeting the type condition and within a predetermined time period to determine the amplitude threshold condition of the corresponding type of battery.

[0016] In some embodiments, the actions further include: processing a plurality of first data within a predetermined time period for a plurality of groups of batteries meeting the type condition to determine the degree threshold condition.

[0017] In some embodiments, determining whether the changing trend satisfies the trend verification condition includes: sorting the second data by time; processing the sorted second data to determine the trend of at least one parameter and the correlation of the trend; and determining whether the changing trend satisfies the trend verification condition based on the trend and the correlation of the trend.

[0018] The third aspect of the present disclosure provides a computer storage medium. A computer program product stored on the computer storage medium includes machine executable instructions, which, when executed, cause a machine to perform the steps of the method of the first aspect of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the present disclosure will become more apparent through a more detailed description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present disclosure.

[0020] Figure 1 A simplified schematic diagram showing an environment in which the method according to an embodiment of the present disclosure can be applied;

[0021] Figure 2 A schematic diagram showing the process of interaction between the vehicle and the cloud platform during charging;

[0022] Figure 3A schematic diagram of a process according to an embodiment of the present disclosure is shown;

[0023] Figure 4 A schematic diagram showing a change trend of the pressure difference determined by the method according to an embodiment of the present disclosure;

[0024] Figure 5 A flowchart showing a method for determining an abnormal vehicle according to an embodiment of the present disclosure; and

[0025] Figure 6 A schematic block diagram of an electronic device suitable for implementing an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0026] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0027] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0028] The principles of the present disclosure will be described below with reference to several example embodiments shown in the accompanying drawings. Although preferred embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that these embodiments are described only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way.

[0029] In addition, the term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of executing a subsequent action executed in response to the event or condition is not necessarily strongly related to the time when the event occurs or the condition is satisfied. For example, in some cases, the subsequent action may be executed immediately when the event occurs or the condition is satisfied; while in other cases, the subsequent action may be executed after a period of time after the event occurs or the condition is satisfied.

[0030] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects are subject to the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user knows and confirms. Accordingly, when implementing each embodiment of the present disclosure, the type, scope of use, usage scenario, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0031] As mentioned above, in order to prevent personal and property losses that may be caused by the aging of power batteries (hereinafter referred to as batteries), it is necessary to detect and evaluate the safety status of batteries in new energy vehicles. At present, the main method for judging the health of vehicle batteries is to establish a battery model for the battery, such as an equivalent circuit model, an electrochemical model, an artificial intelligence model, etc. Through preliminary experimental calibration, the initial parameters required for the battery model are calibrated. In addition, by real-time collection of battery data under various working conditions, combined with the previous calibration data, the battery health status (SOH), remaining service life (RUL), voltage fluctuations, internal resistance evolution and other data are calculated. Based on the above calculated data, the current true state of the battery is identified, and then the health status of the vehicle battery is evaluated.

[0032] For vehicle manufacturers or battery manufacturers, they can obtain the real-time and historical voltage, temperature, current, pressure and other data of the vehicle's power battery, establish more complex equivalent circuit models, electrochemical models and other models, calculate the battery's internal resistance, capacity, voltage fluctuations, temperature fluctuations and other characteristics, and then accurately monitor the battery status based on the above characteristics.

[0033] However, the above models have high requirements for data quality, frequency of data upload, final data volume, and accuracy of original test data. For other industries, it is impossible to obtain data that meets the above requirements. Although charging platform companies can detect abnormalities by detecting vehicle temperature, current, voltage, remaining power (SOC) and other indicators or parameters to identify abnormal vehicles, the detection needs to rely on vehicle classification (based on vehicle VIN for vehicle model identification), and can only identify situations with large parameter deviations. It is impossible to identify abnormal vehicles from the trend changes of vehicles, and it does not consider the impact of the current environment.

[0034] The inventor has fully considered the characteristics that the vehicle's power battery ages over time and the control ability of the battery management system (BMS) will also deteriorate accordingly, that is, as the vehicle battery gradually ages and the control ability of the BMS gradually deviates, the battery's temperature, voltage, internal resistance, capacity and other parameters will change with the change of usage time, for example, the temperature control ability is getting worse and worse, the balancing ability is gradually getting worse, the internal resistance is getting bigger and bigger, the voltage control ability is weakened, etc., and proposed a method according to the embodiment of the present disclosure, which can identify abnormal vehicles before the aging degree of the vehicle's battery is serious. For abnormal vehicles, the charging platform needs to take certain execution actions for these gradually deteriorating vehicles, including charging restrictions, charging prohibitions, prompting maintenance, etc., so as to reduce the occurrence of spontaneous combustion during charging in the station, thereby improving the safety and reliability of the battery during the charging process.

[0035] Figure 1 A schematic diagram of a charging station for charging an electric vehicle is shown in FIG. Figure 1 The ubiquitous power Internet of Things architecture system for the construction of the distribution network of the charging station 110 is shown in FIG. 1 , which includes a four-layer structure of a perception layer, a network layer, a platform layer, and an application layer. Through the perception layer and the network layer, the geographical location of the charging station 110, the charging demand of the vehicle, and other information can be obtained in real time, and the platform layer and the application layer use big data methods to analyze and process the real-time shared information, thereby managing the charging demand of the vehicle in real time. The perception layer, i.e., the data acquisition layer, generally refers to the collection of user data through the charging station 110. The network layer, i.e., the network transmission 120, can adopt wired transmission, wireless transmission or Bluetooth transmission, which is not limited in this disclosure, and is used to transmit user data. The platform layer, i.e., the data center layer, generally uses a server 130 for data storage, data analysis, etc., and is used to process data from the network layer. The application layer, i.e., the client layer, generally refers to the terminal 140, which can be a user or a device. This disclosure is not limited to this, and is used to receive information from the platform layer. The method according to the embodiment of the present disclosure can be executed by a server of the platform layer (hereinafter also referred to as a platform). In some alternative embodiments, the method according to the embodiments of the present disclosure may also be executed by a terminal 140 at the platform layer.

[0036] The perception layer is generally implemented by charging the vehicle using a charging pile (also referred to as a charger) of the charging station 110, but it should be understood that according to the solution of the embodiment of the present disclosure, the charging pile can charge the vehicle by wire, and can also charge the vehicle wirelessly (for example, using an electromagnetic field). It should be understood that the situation of charging by other methods is similar, and the present disclosure does not limit this, and will not be repeated in the following.

[0037] Each charging pile generally includes multiple (for example, two) charging guns 1101. The plug portion of the charging gun 1101 is used to be inserted into the socket of the electric vehicle to connect the electrical connection between the battery of the vehicle and the charging pile. During vehicle charging, the vehicle and the charging pile will communicate via messages. For example, the vehicle can send the required power demand to the charging pile according to its own conditions, and the charging pile can charge the vehicle's battery based on factors such as the required power and its own power output. Message communication between the vehicle and the charging pile is usually carried out at predetermined time intervals.

[0038] Specifically, according to the requirements of the relevant charging protocol, when a new energy vehicle is charging, the BMS will exchange information with the charger. The exchanged information includes battery capacity, battery type, power, current, voltage, temperature, SOC and other information. The charging pile uploads this information to the charging platform. The interaction process is as follows: Figure 2 shown.

[0039] The method of the disclosed embodiment is based on the above-mentioned interaction process. The platform clusters each vehicle based on the data of vehicle-pile interaction, and then calculates the relevant parameters. Based on the clustering results, the time dimension is used to calculate the correlation of the increase, and then the space dimension is used to confirm the normal increase amplitude and degree of the battery model, that is, to determine the amplitude threshold and degree threshold, so that the abnormal vehicle can be identified when the vehicle has not changed to a more serious state. In addition, it should be emphasized that the amplitude threshold and degree threshold according to the disclosed embodiment are determined based on the data of the corresponding period of the same battery model, so as to eliminate the influence of seasons and regions on the parameter thresholds, making the vehicle identification results more reliable.

[0040] Embodiments according to the present disclosure will be described below with reference to the accompanying drawings. Figure 3 A schematic diagram of a process for identifying an abnormal vehicle according to an embodiment of the present disclosure is shown. Figure 3 It can be seen that the method according to the embodiment of the present disclosure is mainly based on the historical charging data of the vehicle. After the data quality verification, on the one hand, according to the basic information of the battery, different models are clustered by clustering method to obtain the battery model library. That is to say, the battery model library includes a collection of multiple batteries and their data that are determined to be of the same type through clustering. On the other hand, relevant parameters such as relative temperature, temperature difference, pressure difference, internal resistance, etc. are extracted (these parameters are determined from the time domain dimension for the battery of a certain vehicle). Then, based on the battery model library, an abnormal threshold (including amplitude threshold and degree threshold) relative to the model is formulated. In other words, as mentioned above, the abnormal threshold is determined from the spatial domain dimension based on the battery model library. Finally, after the verification of the rising amplitude and degree, and then the trend test, the vehicle with the battery that meets the conditions is determined as an abnormal vehicle.

[0041] From the brief description above, it can be seen that the method according to the embodiment of the present disclosure mainly proposes an abnormal vehicle identification method based on the fusion of time domain and space domain. The parameters used in the method according to the embodiment of the present disclosure include but are not limited to: relative temperature, temperature difference, pressure difference, internal resistance, etc. The relative temperature represents the value of the maximum temperature reached by the single cell during the charging process minus the ambient temperature; the temperature difference represents the maximum difference between the highest single cell temperature and the lowest single cell temperature during the charging process; the pressure difference refers to the difference between the maximum voltage and the minimum voltage of the single cell after the charging is completed; the internal resistance refers to the value of the internal resistance of the entire battery pack during the vehicle charging process. These parameters can be determined from the interactive information between the BMS and the charging pile or by calculation.

[0042] Specifically, during the charging process of the vehicle, the platform will obtain the charging process data corresponding to the target vehicle. The charging process data may contain a variety of information, such as current, maximum cell temperature, battery capacity, battery rated voltage, maximum cell voltage, etc. At the same time, if the conditions are met, the platform can also issue special operating instructions to the charging pile. The charging pile outputs current and voltage according to the instructions, and stores the above data fed back by the BMS together with other normal interaction data in the cloud database for subsequent analysis.

[0043] By studying the data uploaded by the charging pile, it can be found that the data usually has some data quality problems that affect the subsequent analysis and processing. These data quality problems include, for example: abnormal data uploaded by the vehicle, abnormal data uploaded by the pile, abnormal data processed by the platform, etc. In response to the above data quality problems, the method according to the embodiment of the present disclosure will use a reasonable method to filter out the data before processing (i.e., data preprocessing). Methods for data preprocessing to remove abnormal data include but are not limited to: setting reasonable thresholds, removing data with abnormal voltage changes, removing data from some charging piles, supplementing some data based on specific mathematical relationships, and other methods.

[0044] After the preprocessing of the data uploaded by the charging pile is completed, all the preprocessed data of the target vehicle charging for a predetermined period (for example, not less than two months) is taken to cluster the different battery information to determine the type of battery. Clustering methods include, but are not limited to, K-means, density-based noise space clustering method (DBSCAN) and other methods. K-means refers to a clustering algorithm based on Euclidean distance, which believes that the closer the distance between two targets, the greater the similarity. DBSCAN, as the name suggests, is a density-based clustering algorithm. The set of samples connected by the maximum density derived from the density-reachable relationship is a category of the final clustering, or a cluster.

[0045] In order to further eliminate the unreliable impact of some orders on subsequent analysis and processing, the method according to the embodiment of the present disclosure can verify the validity of the order according to the number of orders in different periods, and only perform subsequent analysis and processing on the relevant data of the orders that are considered valid. For example, for the target vehicle, if the number of valid orders within two months is not less than 10, the number of valid orders within one month is not less than 5, and / or the number of valid orders within a week is not less than 3, the order of the target vehicle will be considered to be a valid order, and subsequent analysis and processing will be carried out. On the contrary, if the number of valid orders within two months is less than 10, the number of valid orders within a month is less than 5, and / or the number of valid orders within a week is less than 3, the order of the target vehicle is considered to be an invalid order, and no subsequent analysis and processing will be carried out.

[0046] Of course, it should be understood that the above examples of checking order validity based on the number of orders in different cycles are illustrative and are not intended to limit the scope of protection of the present disclosure. Depending on the circumstances, other cycles of any length and threshold numbers may be used, which will not be described separately below.

[0047] After the above preprocessing, the method according to the embodiment of the present disclosure will determine the relative temperature data, temperature difference data, pressure difference data and internal resistance data of all orders of the target vehicle during charging on that day, and the calculation formula is shown in the following equation group (1).

[0048]

[0049] Among them, max_temp represents the relative temperature of the battery; max_temp_diff represents the maximum temperature difference, bsd_voltage_diff represents the maximum voltage difference; r represents the internal resistance of the battery pack; environment_temperature represents the ambient temperature at the time of the charging order; bsm_max_temp represents the maximum temperature data of the single cell uploaded during the charging process; bsm_max_temp represents the maximum temperature data of the single cell uploaded during the charging process; bsm_min_temp represents the minimum temperature data of the single cell uploaded during the charging process; bsd_max_voltage represents the maximum voltage uploaded at the end of charging; bsd_min_voltage represents the minimum voltage uploaded at the end of charging; V n Indicates the voltage of the battery pack during charging; I n Indicates the current of the battery pack during charging.

[0050] For the calculation of the battery internal resistance, the method according to the embodiment of the present disclosure is to consider starting the calculation only when the current change exceeds the threshold. This is because if the current change exceeds the threshold, it is usually affected by factors including the change in the battery internal resistance, and when the battery internal resistance changes slightly, the current change often does not exceed the threshold. Therefore, by starting to calculate the battery internal resistance only when the current change exceeds the threshold, some invalid calculations can be avoided, thereby reducing the processor budget and improving the calculation speed.

[0051] After determining the relative temperature, temperature difference, pressure difference and internal resistance (if any) data of the battery, data authenticity verification and smooth filtering will be performed. Specifically, for the relative temperature, temperature difference, pressure difference and internal resistance data determined in the above steps, the above parameters of the single vehicle dimension (that is, the time domain dimension) are filtered and verified to remove outliers. In this process, the methods that can be used to remove outliers include but are not limited to: statistics, filtering or artificial intelligence methods. Taking statistics as an example of pressure difference filtering, the pressure difference in the orders of a predetermined period (for example, the past two months) in the single vehicle dimension is obtained, and then the mean and standard deviation of the pressure difference of the vehicle are calculated, and the Z score method is used to calculate the authenticity threshold of the battery model. The Z score is also called the standard score, which is the process of dividing the difference between a number and the mean by the standard deviation. In statistics, the standard score is the symbol number of the standard deviation of the value of an observation or data point above the mean of the observed value or measured value. The specific calculation formula is shown in the following equation group (2).

[0052]

[0053] Among them, avg refers to the operator for averaging the data; vol_diff i Indicates the pressure difference of the i-th order in ascending time order; avg_vol_diff is the average pressure difference; std_vol_diff is the standard deviation of the pressure difference; Z_score i It is the standard score in the Z-score algorithm.

[0054] According to the method of the embodiment of the present disclosure, the standard of abnormal data can be determined according to the value of the standard score. For example, in some embodiments, the standard for defining abnormal data can be Z_score i >3 or Z_score i <-3. That is, if Z_score i If the Z_score falls within the above range, it means that the data is abnormal and should be removed. i If the data does not fall within the above range, it means that the data is normal data and can be used for subsequent processing. Through this step, the authenticity verification of the data is completed.

[0055] In some embodiments, after the data has been verified as above, the method according to the embodiment of the present disclosure will sort the parameters according to the order time sequence, and then perform smooth filtering on different parameters respectively. The method of data smooth filtering includes but is not limited to: Gaussian filtering, mean filtering, weighted average filtering, etc.

[0056] After completing the above-mentioned authenticity verification and smooth filtering operations on the data, the platform will determine the increase range of each parameter. In some embodiments, the increase range of each parameter can be determined by first calculating the minimum value of the parameter after filtering within a predetermined period and the current parameter value, and subtracting the two as the increase range of the parameter. Taking the temperature difference parameter as an example, the calculation formula is shown in equation group (3).

[0057]

[0058] Where min_temp_diff represents the minimum value of the temperature difference after filtering; temp_diff n Indicates the current temperature difference level; temp_diff_range indicates the increase in temperature difference.

[0059] After determining the rising amplitude, the method according to the embodiment of the present disclosure processes the data after the data verification and preprocessing to determine the threshold of the amplitude (hereinafter referred to as the amplitude threshold) in the dimension of the spatial domain. The platform selects the value of the parameter that meets the predetermined condition (for example, greater than 0) as the threshold sample to determine the amplitude threshold. The method used to determine the amplitude threshold includes but is not limited to: statistics, expert experience or artificial intelligence and other methods.

[0060] This article uses a statistical method to give an example of determining the amplitude threshold of the temperature difference parameter. According to the battery model determined by clustering in the previous article, within the same battery model, the amplitude of the temperature difference is arranged from small to large. In some embodiments, according to the principle of the box plot, 75% can be used as the threshold of the temperature difference of the battery model. Vehicles that exceed the battery model threshold are subject to subsequent analysis and calculation, and if they do not exceed the threshold, the subsequent calculation is abandoned. The box plot (Box-plot), also known as the box-whisker plot, box plot or box-and-whisker plot, is a statistical chart used to display the dispersion of a set of data. The method of drawing a box plot is: first find the upper edge, lower edge, median and two quartiles of a set of data; then, connect the two quartiles to draw a box; then connect the upper edge and lower edge to the box, and the median is in the middle of the box.

[0061] For data (hereinafter referred to as first data) whose increase exceeds the amplitude threshold (that is, meets the amplitude threshold condition), the platform will calculate the current degree threshold of each parameter. The degree threshold is also determined from the dimension of the spatial domain. Specifically, the platform calculates the degree of the current parameter based on the full order of the day and the battery model determined in the previous article using methods such as statistics, expert thresholds, and artificial intelligence.

[0062] This article also uses the relative temperature to determine the degree threshold using a statistical method as an example. When determining the degree threshold, the platform determines the mean and standard deviation of the relative temperature of the same battery model on that day (predetermined time period), and uses the value exceeding the mean by a predetermined number (for example, 2) of standard deviations as the relative temperature degree threshold, and performs subsequent trend verification on the data in the first data that exceeds the degree threshold (hereinafter referred to as the second data).

[0063] It should be noted that the amplitude threshold and degree threshold determined from the spatial domain dimension are based on the charging data of the same battery model within a predetermined time period. The predetermined time period can be the full data of the day or the full data of any appropriate time period.

[0064] After determining the second data, the changing trend of the parameter will be determined according to the second data. In some embodiments, the platform will sort the second data again in chronological order, and then determine the trend of the parameter and the correlation of the trend. The determination method may include but is not limited to Cochran-Armitage trend test, Mann-Kendall trend test, Kendall's tau-b rank correlation and other methods. Cochran-Armitage test is a linear trend test, which is often used for data where the independent variable is an ordered categorical variable and the dependent variable is a binary categorical variable. It can be used to test whether there is a linear trend between the independent variable and the dependent variable. The Mann-Kendall trend test is suitable for analyzing time series data with a continuous growth or downward trend (monotonic trend). It is a non-parametric test that is applicable to all distributions (i.e., the data does not need to meet the assumption of normal distribution), but the data should have no serial correlation. Kendall's tau-b rank correlation coefficient represents a parameter used to reflect the correlation of categorical variables, and is applicable to situations where both categorical variables are ordered categories.

[0065] This article takes the Mann-Kendall trend test as an example. When the upward trend is significant and the correlation is large (for example, corresponding to a 95% confidence level), the vehicle is judged to be an abnormal vehicle after the above conditions are met. Figure 4 As shown, the pressure difference of the power battery of the vehicle gradually increases with time and meets the judgment of the above steps, so the vehicle is judged to be an abnormal vehicle.

[0066] From the above description, it can be seen that according to the embodiments of the present disclosure, it is judged whether there is an abnormality in the power battery of the vehicle from the dimensions of the time domain and the space domain respectively. Specifically, from the time domain dimension, the method can analyze the charging data of the vehicle within a predetermined period to determine the increase amplitude and degree of some parameters of the battery of the vehicle. From the spatial domain dimension, the method can analyze the charging data of the same battery model within a predetermined time period to determine the amplitude threshold and degree threshold, which are used to compare with the above amplitude and degree determined above, and finally use trend inspection to determine abnormal vehicles. For abnormal vehicles, the charging platform needs to take certain execution actions for these gradually deteriorating vehicles, including charging restrictions, charging prohibitions, prompts for maintenance, etc., so as to reduce the occurrence of spontaneous combustion during charging in the station, thereby improving the safety and reliability of the battery during the charging process. In this way, the influence of ambient temperature, etc. can be combined to identify vehicle abnormalities as early as possible and reduce the occurrence of safety accidents.

[0067] Figure 5 A flow chart of a method for determining an abnormal vehicle according to an embodiment of the present disclosure is shown. In some embodiments, the method 500 may be implemented by a server 130 or a platform or a control system of the charging station 110 itself or a processor of other appropriate devices that communicate with the charging station 110. For ease of understanding, the specific examples, numbers or values ​​mentioned in the following description are merely exemplary and are not intended to limit the scope of protection of the present disclosure.

[0068] like Figure 5 As shown, in box 510, the processor determines whether the increase amplitude of at least one parameter of the power battery meets the amplitude threshold condition based on multiple sets of data obtained during multiple charging processes of the power battery of the vehicle. Next, in box 520, the first data whose increase amplitude meets the amplitude threshold condition in the multiple sets of data is processed to determine the change trend of the at least one parameter based on the second data that meets the degree threshold condition in the first data.

[0069] In block 530 , the processor performs a trend check on the change trend to determine whether the change trend satisfies a trend check condition. Finally, in block 540 , in response to determining that the change trend satisfies the trend check condition, the processor determines the vehicle corresponding to the change trend as an abnormal vehicle.

[0070] In some embodiments, the processor may also pre-process the data acquired from the charging pile to remove abnormal data, and perform clustering processing on the pre-processed data to determine the type of battery according to the clustering processing result.

[0071] In some embodiments, the processor may also determine from the data from the charging pile whether the number of valid orders within a predetermined period exceeds a predetermined threshold. If the processor determines that the number of valid orders within a predetermined period exceeds the predetermined threshold, the increase is determined based on multiple sets of data within the predetermined period.

[0072] In some embodiments, the processor may further process multiple sets of data related to a selected parameter of at least one parameter within a predetermined period to remove abnormal data from the multiple sets of data. Then, the processor sorts the processed multiple sets of data in the time sequence of the orders corresponding to the multiple sets of data. Next, the processor filters the sorted multiple sets of data and processes the filtered multiple sets of data to determine the rise.

[0073] In some embodiments, the processor may further process multiple groups of filtered data within a predetermined time period of multiple groups of batteries that meet the type condition to determine the amplitude threshold condition of the corresponding type of battery.

[0074] In some embodiments, the processor may further process a plurality of first data within a predetermined time period of a plurality of battery groups meeting the type condition to determine the degree threshold condition.

[0075] In some embodiments, the processor sorts the second data by time and processes the sorted second data to determine the trend of at least one parameter and the correlation of the trend. Finally, the processor determines whether the change trend meets the trend test condition according to the trend and the correlation of the trend.

[0076] Figure 6 1 shows a schematic block diagram of an electronic device 600 suitable for implementing an embodiment of the present disclosure. The electronic device 600 may be the server 130 mentioned above that communicates with the charging station 110 or the control system of the charging station 110 itself or other appropriate devices. Figure 5 As shown, the electronic device 600 includes at least one processing unit and at least one memory, and at least one processing unit can use a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 602 or computer program instructions loaded from a storage unit to a random access memory (RAM) 603. In RAM 603, various programs and data required for device operation can also be stored. CPU 601, ROM 602 and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0077] Multiple components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, such as a touch screen, buttons, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0078] The various processes and processing described above, such as the processes mentioned above, can be performed by the processing unit 601. For example, in some embodiments, the processes 510, 520, 530 and 540 can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the CPU 601, one or more actions of the processes 510, 520, 530 and 540 described above can be performed.

[0079] Embodiments of the present disclosure relate to methods, electronic devices, and / or computer program products. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0080] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, (but not limited to) an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0081] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0082] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on the remote computer, or entirely on the remote computer or server 130. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0083] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0084] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0085] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0086] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0087] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining an abnormal vehicle, comprising: determining, based on multiple sets of data acquired during multiple charging processes of the power battery of the vehicle, whether an increase amplitude of at least one parameter of the power battery meets an amplitude threshold condition; Processing the first data in the plurality of data groups whose rising amplitude satisfies the amplitude threshold condition, so as to determine the change trend of the at least one parameter according to the second data in the first data that satisfies the degree threshold condition; Performing a trend test on the change trend to determine whether the change trend meets a trend test condition; as well as In response to determining that the change trend satisfies a trend verification condition, a vehicle corresponding to the change trend is determined to be an abnormal vehicle.

2. The method according to claim 1, before determining whether the increase amplitude of at least one parameter of the power battery meets the amplitude threshold condition, further comprises: Preprocess the data obtained from the charging pile to remove abnormal data; as well as The pre-processed data is clustered to determine the type of the battery according to the clustering result.

3. The method according to claim 2, further comprising Determining from the data from the charging pile whether the number of valid orders within a predetermined period exceeds a predetermined threshold; and In response to determining that the effective order volume within the predetermined period exceeds the predetermined threshold, the increase range is determined according to the multiple sets of data within the predetermined period.

4. The method according to claim 3, determining the rising amplitude further comprises: Processing a plurality of sets of data related to a selected parameter of the at least one parameter within the predetermined period to remove abnormal data from the plurality of sets of data; Sorting the processed multiple sets of data in the time sequence of the orders corresponding to the multiple sets of data; filtering the sorted plurality of groups of data; as well as The filtered sets of data are processed to determine the rise amplitude.

5. The method according to any one of claims 2 to 4, further comprising: The filtered data of the plurality of groups of batteries meeting the type condition and within a predetermined time period are processed to determine the amplitude threshold condition of the corresponding type of battery.

6. The method according to any one of claims 2 to 4, further comprising: A plurality of the first data of a plurality of battery groups meeting the type condition within a predetermined time period are processed to determine the degree threshold condition.

7. According to the method of any one of claims 2 to 4, determining whether the change trend satisfies a trend test condition comprises: sorting the second data by time; processing the sorted second data to determine the trend of the at least one parameter and a correlation of the trend; as well as Whether the change trend satisfies a trend test condition is determined according to the trend and the correlation of the trends.

8. An electronic device comprising: at least one processing unit; as well as at least one memory coupled to the at least one processing unit and storing machine-executable instructions, which, when executed by the at least one processing unit, cause the device to perform actions, the actions comprising: determining, based on multiple sets of data acquired during multiple charging processes of the power battery of the vehicle, whether an increase amplitude of at least one parameter of the power battery meets an amplitude threshold condition; Processing the first data in the plurality of data groups whose rising amplitude satisfies the amplitude threshold condition, so as to determine the change trend of the at least one parameter according to the second data in the first data that satisfies the degree threshold condition; Performing a trend test on the change trend to determine whether the change trend satisfies a trend test condition; and In response to determining that the change trend satisfies a trend verification condition, a vehicle corresponding to the change trend is determined to be an abnormal vehicle.

9. The electronic device according to claim 8, further comprising, before determining whether the rising amplitude of at least one parameter of the power battery meets the amplitude threshold condition: Preprocess the data obtained from the charging pile to remove abnormal data; as well as The pre-processed data is clustered to determine the type of the battery according to the clustering result.

10. The electronic device according to claim 9, wherein the actions further comprise: determining from the data from the charging pile whether the number of valid orders within a predetermined period exceeds a predetermined threshold; as well as In response to determining that the effective order volume within the predetermined period exceeds the predetermined threshold, the increase range is determined according to the multiple groups of data within the predetermined period.

11. The electronic device according to claim 10, wherein determining the rising amplitude further comprises: Processing a plurality of sets of data related to a selected parameter of the at least one parameter within the predetermined period to remove abnormal data from the plurality of sets of data; Sorting the processed multiple sets of data in the time sequence of the orders corresponding to the multiple sets of data; filtering the sorted plurality of groups of data; as well as The filtered sets of data are processed to determine the rise amplitude.

12. The electronic device according to any one of claims 9 to 11, further comprising: The filtered data of the plurality of groups of batteries meeting the type condition and within a predetermined time period are processed to determine the amplitude threshold condition of the corresponding type of battery.

13. The electronic device according to any one of claims 9 to 11, further comprising: A plurality of the first data of a plurality of battery groups meeting the type condition within a predetermined time period are processed to determine the degree threshold condition.

14. The electronic device according to any one of claims 9 to 11, wherein determining whether the change trend satisfies a trend verification condition comprises: sorting the second data by time; processing the sorted second data to determine the trend of the at least one parameter and a correlation of the trend; as well as Whether the change trend satisfies a trend test condition is determined according to the trend and the correlation of the trends.

15. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 7.

Images