Charging pile group fault detection method, system and device, medium and product

By acquiring charging behavior data of charging pile groups and judging anomalies using preset models, adjusting charging output parameters using random number perturbations, and identifying faults by combining charging status data, the problem of low efficiency and high cost of fault detection in charging pile groups has been solved, achieving efficient and accurate fault identification.

CN121973667APending Publication Date: 2026-05-05FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202610446922.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-07
Publication Date
2026-05-05

AI Technical Summary

Technical Problem

Existing fault detection methods for charging pile clusters are inefficient and costly. In particular, fault detection for charging pile clusters requires high-frequency visual data acquisition and active detection, which leads to excessive costs and difficulty in timely fault detection.

Method used

By acquiring charging behavior data of charging pile groups, using a preset normal charging behavior habit model to judge charging anomalies, and adjusting charging output parameters through random number perturbation requests, combined with charging status data to identify faults, a fault detection method combining real-time monitoring and active perturbation is adopted.

Benefits of technology

It significantly improves the sensitivity and accuracy of fault identification, ensures the timeliness of fault detection, and balances the cost and efficiency of fault detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121973667A_ABST
    Figure CN121973667A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of automobile charging piles, and discloses a charging pile group fault detection method, system and device, a medium and a product, and the method comprises the steps: obtaining the charging behavior data of a target charging pile group and a preset normal charging behavior habit model, and judging whether the target charging pile group is abnormal in charging or not; after it is judged that charging abnormity exists in the target charging pile group, responding to the random number disturbance request for each charging pile connected with the electric vehicle in the target charging pile group, generating a plurality of random numbers through the random number disturbance request, and adjusting charging output parameters of the charging piles according to the random numbers; and the charging state data, corresponding to the charging output parameters adjusted each time, of the electric vehicle in the charging stage are obtained, the fault condition of each charging pile is determined according to the charging output parameters adjusted each time and the charging state data, and therefore the fault detection cost and efficiency can be balanced while the fault detection timeliness can be guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging pile technology, and in particular to a method, system, equipment, medium, and product for detecting faults in a group of charging piles. Background Technology

[0002] A single market entity (such as a company) often manages a large number of charging piles. Currently, fault inspections of these charging pile groups are conducted manually. However, manual inspections are inefficient, and existing fault detection methods often target individual charging piles. While some methods exist for detecting faults in charging pile groups, they typically require frequent and individual fault detection, leading to high costs. For example, Chinese invention patent application CN121142201A requires visual data collection between charging piles to monitor cable connections before vehicle charging. This fault detection method, to ensure real-time fault detection, requires frequent visual data collection regardless of whether the vehicle is currently charging, resulting in high costs.

[0003] In addition, existing charging pile groups often only perform fault detection proactively. Proactive detection means that detection commands need to be issued and data needs to be collected proactively, which increases the maintenance cost of the detection platform and makes it difficult to detect charging pile faults in a timely manner. Summary of the Invention

[0004] In view of this, in order to solve the above-mentioned technical problems, the present invention provides a method, system, device, medium and product for detecting faults in charging pile groups.

[0005] The first aspect of this invention provides a method for detecting faults in a charging pile group, comprising:

[0006] The system acquires charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period. Based on the charging behavior data and a preset normal charging behavior habit model, it determines whether there is any charging abnormality in the target charging pile group.

[0007] After determining that there is a charging abnormality in the target charging pile group, for each charging pile in the target charging pile group that is connected to an electric vehicle, in response to the random number perturbation request, multiple random numbers are generated through the random number perturbation request, and the charging output parameters of the charging pile are adjusted according to each random number.

[0008] Obtain the charging status data of the electric vehicle during the charging phase corresponding to the adjusted charging output parameters each time, and determine the fault status of each charging pile based on the adjusted charging output parameters and the charging status data.

[0009] In one embodiment, the normal charging behavior habit model includes a first charging behavior habit model and a second charging behavior habit model; the first charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging time and battery remaining power SOC, and the second charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging power and the charging time period.

[0010] In one embodiment, the charging behavior data includes the charging time required for a single full charge of the electric vehicle, the charging power, the time period during which charging occurs, and the remaining battery charge (SOC) at the start of charging.

[0011] The step of determining whether there is a charging anomaly in the target charging pile group based on the charging behavior data and a preset normal charging behavior habit model includes:

[0012] The charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging are input into the first charging behavior habit model to obtain a first probability density value; the charging power and the charging time period are input into the second charging behavior habit model to obtain a second probability density value.

[0013] Based on the first probability density value and the second probability density value, determine whether the target charging pile group has any charging anomalies:

[0014] If the first probability density value is lower than a preset first threshold and / or the second probability density value is lower than a preset second threshold, then it is determined that the target charging pile group has a charging abnormality.

[0015] In one embodiment, the charging output parameters include the output supply voltage and the output supply current;

[0016] The step of generating multiple random numbers through the random number perturbation request and adjusting the charging output parameters of the charging pile according to each random number includes:

[0017] The charging pile uses a built-in random number generation module to generate multiple random numbers at preset time intervals.

[0018] For each random number, the preset voltage level and preset current level corresponding to the random number are found in a preset random number mapping table, and the output supply voltage and output supply current of the charging pile are adjusted according to the preset voltage level and preset current level. The preset random number mapping table includes multiple random numbers and the mapping relationship between the preset voltage level and preset current level corresponding to the random number, and the voltage difference between any two preset voltage levels corresponding to the random numbers is not less than a preset voltage threshold, and the current difference between any two preset current levels corresponding to the random numbers is not less than a preset current threshold.

[0019] In one embodiment, the charging status data includes the remaining time required for a full charge and the current battery temperature; determining the fault status of each charging station based on the adjusted charging output parameters and the charging status data includes:

[0020] Based on the charging output parameters after each adjustment, determine the charging voltage and charging current variation trends of the charging pile.

[0021] Based on the remaining time required for full charging corresponding to the adjusted charging output parameters and the current temperature of the battery, the charging efficiency change trend of the charging pile and the current temperature change trend of the battery are determined respectively.

[0022] By comparing the trend of charging efficiency change with the trend of charging voltage change, if it is determined that the trend of charging efficiency change is inconsistent with the trend of charging voltage change, then it is determined that the charging pile has a fault.

[0023] By comparing the current temperature change trend of the battery with the charging current change trend, if it is determined that the current temperature change trend of the battery is inconsistent with the charging current change trend, then the charging pile is determined to be faulty.

[0024] In one embodiment, the method further includes:

[0025] The charging power and the remaining battery charge (SOC) at the start of charging are obtained for each electric vehicle connected to the target charging pile group during the current detection period.

[0026] Multiple target electric vehicles are determined based on the charging power of each electric vehicle and the remaining battery charge (SOC) at the start of charging; wherein the difference between the charging power of any two target electric vehicles is less than a preset power difference threshold, and the difference between the remaining battery charge (SOC) at the start of charging is less than a preset SOC difference threshold.

[0027] Acquire charging status data for each of the target electric vehicles; wherein the charging status data includes the time required for a single full charge and the current temperature of the battery;

[0028] The time required for a single full charge and the current temperature of the battery are normalized, and the normalized time required for a single full charge and the normalized current temperature of the battery are weighted and fused to generate a comprehensive status score.

[0029] Take every two target electric vehicles among all the target electric vehicles as a comparison group, and calculate the difference between the comprehensive status scores of the two target electric vehicles in each comparison group as the comprehensive status score difference value of the comparison group;

[0030] The comparison groups are sorted in descending order according to the size of the difference in the comprehensive status score, and the charging piles corresponding to the comparison groups with a preset number of groups before sorting are taken as suspected fault charging piles.

[0031] Obtain the comprehensive status score difference value between each suspected faulty charging pile and other charging piles. If the comprehensive status score difference value between the suspected faulty charging pile and at least two other charging piles exceeds the preset score difference threshold, then the suspected faulty charging pile is determined to be a faulty charging pile.

[0032] Secondly, the present invention also provides a charging pile group fault detection system, comprising:

[0033] The charging anomaly detection module is used to acquire charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period, and to determine whether there is a charging anomaly in the target charging pile group based on the charging behavior data and a preset normal charging behavior habit model.

[0034] The charging parameter adjustment module is used to, after determining that there is a charging abnormality in the target charging pile group, generate multiple random numbers for each charging pile in the target charging pile group that is connected to an electric vehicle in response to a random number perturbation request, and adjust the charging output parameters of the charging pile according to each random number.

[0035] The fault detection module is used to acquire the charging status data of the electric vehicle during the charging phase corresponding to the adjusted charging output parameters each time, and to determine the fault status of each charging pile based on the adjusted charging output parameters and the charging status data.

[0036] Thirdly, the present invention also provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor causing the processor to perform the steps of the charging pile group fault detection method as described in the first aspect.

[0037] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the steps of the charging pile group fault detection method as described in the first aspect.

[0038] Fifthly, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein, when the program instructions are executed by a computer, the computer performs the steps of the charging pile group fault detection method as described in the first aspect.

[0039] As can be seen from the above technical solutions, this invention determines whether there is a charging anomaly in the target charging pile group by comparing the charging behavior data of the target charging pile group with a preset normal charging behavior habit model, thereby achieving real-time monitoring and response to the anomaly. After detecting a charging anomaly in the target charging pile group, multiple random numbers are generated through random number perturbation requests to adjust the charging output parameters of the charging piles, and the charging status data of the electric vehicle during the charging stage corresponding to the charging output parameters after each adjustment is obtained. By the response relationship between the charging status data and the charging output parameters, the dynamic response deviation of each charging pile during the charging output parameter adjustment process is accurately identified, thereby identifying the fault status of each charging pile. This application utilizes a fault detection method that combines real-time monitoring and active perturbation, which significantly improves the sensitivity and accuracy of fault identification, and can ensure the timeliness of fault detection while balancing the cost and efficiency of fault detection. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is an application environment diagram of a charging pile group fault detection method provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart of a charging pile group fault detection method provided in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the structure of a charging pile group fault detection system provided in an embodiment of the present invention;

[0044] Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0045] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] The charging pile group fault detection method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102 or placed on a cloud or other network server. Terminal 101 or server 102 executes a charging pile group fault detection method, including: acquiring charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period; determining whether there is a charging abnormality in the target charging pile group based on the charging behavior data and a preset normal charging behavior habit model; after determining that there is a charging abnormality in the target charging pile group, for each charging pile connected to an electric vehicle in the target charging pile group, in response to a random number perturbation request, generating multiple random numbers through the random number perturbation request, and adjusting the charging output parameters of the charging pile according to each random number; acquiring the charging status data of the electric vehicle during the charging phase corresponding to each adjusted charging output parameter; and determining the fault status of each charging pile based on the adjusted charging output parameters and the charging status data.

[0047] Terminal 101 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets.

[0048] Server 102 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0049] like Figure 2 As shown in the embodiment of this application, a method for detecting faults in a charging pile group is provided, which is applied to... Figure 1 Taking terminal 101 or server 102 as an example, the explanation includes the following steps S1 to S3. Wherein:

[0050] Step S1: Obtain charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period. Based on the charging behavior data and the preset normal charging behavior habit model, determine whether there is any charging abnormality in the target charging pile group.

[0051] A target charging pile group refers to a collection of charging piles that are centrally deployed within a specific geographical area or management unit and uniformly dispatched by the same system. Generally speaking, charging pile groups that can be clearly identified by substation division have homogeneous power supply characteristics such as power supply capacity, and user charging behavior in this area shows statistical stability.

[0052] The charging behavior data collected in this application specifically refers to the charging behavior data of electric vehicle users connected to all operational charging piles within the target charging pile group. This charging behavior data is a key data indicator that can effectively reflect and characterize users' real charging habits and preferences. It covers a wide range of dimensions, including the total duration of a single charging process, real-time power changes during the charging process, the initial state of charge (SOC) value of the vehicle at the start of charging, and the specific electricity consumption period during which the charging behavior occurs, among other parameters.

[0053] The normal charging behavior habit model is a statistical distribution model of normal charging behavior built based on massive historical charging behavior data. This model includes a first charging behavior habit model and a second charging behavior habit model. The first model is a two-dimensional normal distribution model built based on the probability density function of charging time and remaining battery charge (SOC). The second model is a two-dimensional normal distribution model built based on the probability density function of charging power and the charging time period.

[0054] The first charging behavior habit model uses charging time and remaining battery charge (SOC) as joint variables. It fits the historical data distribution through kernel density estimation to obtain its joint probability density function, thereby quantifying users' typical preferences for choosing charging duration under different SOCs. The second charging behavior habit model uses charging power and charging time period as joint variables. It uses the same kernel density estimation method to construct its joint probability density function to characterize the regularity of users choosing charging power at different times. The two models together constitute a multidimensional statistical representation of users' normal charging behavior, providing a high-confidence benchmark for anomaly detection.

[0055] Optionally, the process of constructing a normal charging behavior habit model includes:

[0056] 1) Obtain historical electric vehicle charging behavior data of the target charging pile group. The charging behavior data includes the single charging time, charging power, charging time period and battery SOC at the start of charging for each electric vehicle.

[0057] The charging time for a single charge may vary depending on the vehicle and the circumstances (e.g., different times of day). Some vehicles may only require temporary charging (e.g., during the day) and do not need to be fully charged before charging ends, resulting in a shorter charging time. Other vehicles require a full charge before charging ends (e.g., at night), resulting in a longer charging time. Similarly, electric vehicles often include both fast and slow charging options to achieve different charging power levels, and users can even freely set the charging power between fast charging (maximum charging power) and slow charging (minimum charging power).

[0058] Different charging times and charging power reflect the charging behavior of electric vehicles, which in turn reflect the charging habits and preferences of the vehicle's owner (i.e., the user).

[0059] For example, to ensure that the obtained charging behavior data reflects recent user charging behavior, historical electric vehicle charging behavior data within the most recent N time periods is obtained. For instance, N is 3 months, meaning historical electric vehicle charging behavior data within the most recent 3 months is obtained.

[0060] 2) Using historical electric vehicle charging behavior data, establish probability density functions of two-dimensional normal distributions with charging time and remaining battery charge (SOC) as variables, and probability density functions of two-dimensional normal distributions with charging power and charging time period as variables. The probability density function of the two-dimensional normal distribution with charging time and remaining battery charge (SOC) as variables is used as the first charging behavior habit model, and the probability density function of the two-dimensional normal distribution with charging power and charging time period as variables is used as the second charging behavior habit model.

[0061] Understandably, for most users, taking lithium-ion battery electric vehicles as an example, the battery's remaining State of Charge (SOC) will begin charging when it reaches 20%-30%. Charging time depends on the battery's capacity, but it generally falls within a normal range. For instance, most vehicles can theoretically be fully charged in 1-1.5 hours with fast charging and 6-12 hours with slow charging; in reality, charging typically ends in 6-8 hours. Based on actual user behavior and factors such as the battery capacity of most electric vehicles and the charging power of charging stations, the charging time and SOC behavior of electric vehicles follow a normal distribution, forming a two-dimensional normal distribution function.

[0062] Similarly, most users charge their electric vehicles at different times of the day. For example, at night (e.g., 10 PM to 7 AM), they typically use slow charging or lower charging power, meaning they charge at a power below a certain first charging power threshold. During the day (e.g., 12 PM to 2 PM), they typically use fast charging or higher charging power, meaning they charge at a power exceeding a certain second charging power threshold. Therefore, charging behavior based on charging power and charging time also conforms to a normal distribution, forming a two-dimensional normal distribution function.

[0063] For example, different charging stations have varying charging capacities, which can influence charging behavior to some extent. For instance, in areas with limited charging capacity, it may be difficult to find a charging opportunity, and people often fully charge the battery before stopping. Conversely, in areas with larger charging capacity, charging opportunities are readily available, and people tend to charge the battery to a certain level (e.g., 80% of the maximum battery capacity) before stopping, resulting in different probability density functions of a two-dimensional normal distribution. Therefore, by dividing charging stations into different target charging pile groups based on the charging station area, a corresponding two-dimensional normal distribution probability density function is established for each target charging pile group within each charging station area—that is, a normal charging behavior habit model.

[0064] After establishing a normal charging behavior habit model, since users' charging behavior habits for electric vehicles are inertial, the current charging behavior should also conform to the normal charging behavior habit model. It will not change the normal distribution law due to the problem of a single user's vehicle. This often means that some or even all of the charging piles in the charging pile group are malfunctioning, causing users to compete for normal charging piles, thus affecting the probability density function of the normal distribution. Or, the charging time of electric vehicles will generally be longer because the available charging power is reduced due to the malfunction of the charging pile. Or the charging start time will generally be changed to the evening or other specific time period (no longer electric vehicles charging all day long). Other changes in charging behavior will be reflected in the five parameters of the two-dimensional normal distribution (the mean, standard deviation and coefficient between the two variables), thus no longer conforming to the original probability density function of the normal distribution.

[0065] The charging behavior data of the target charging pile group during the current detection period is verified by using a normal charging behavior habit model. If the charging behavior data during the current detection period does not conform to the model, it is determined that there is an anomaly in the target charging pile group, and the faulty charging pile needs to be further located.

[0066] Step S2: After determining that there is a charging abnormality in the target charging pile group, for each charging pile in the target charging pile group that is connected to an electric vehicle, in response to the random number perturbation request, multiple random numbers are generated through the random number perturbation request, and the charging output parameters of the charging pile are adjusted according to each random number.

[0067] The random number perturbation request is an active detection mechanism triggered after determining that there is a charging anomaly in the target charging pile group. When a charging pile in the target charging pile group is physically connected and starts charging electric vehicles, multiple random numbers conforming to a normal distribution are generated through the random number perturbation request. The charging output parameters of the corresponding charging pile, including output voltage or current, are adjusted in turn, while the charging power to the electric vehicle remains unchanged. That is, the voltage increases and the current decreases accordingly, or the current increases and the voltage decreases accordingly, thereby eliminating the interference of changes in charging power and verifying whether the voltage / current regulation function of the charging pile is normal.

[0068] Step S3: Obtain the charging status data of the electric vehicle during the charging phase corresponding to the charging output parameters after each adjustment, and determine the fault status of each charging pile based on the charging output parameters and charging status data after each adjustment.

[0069] After each adjustment of the charging output parameters, the charging status data of the electric vehicle during the charging phase can be collected in real time. This data can be used to provide feedback on the consistency of the charging pile's response after the output parameters are adjusted, thereby identifying potential issues such as voltage / current regulation faults in the charging pile.

[0070] It should be noted that this application embodiment determines whether there is a charging anomaly in the target charging pile group by comparing the charging behavior data of the target charging pile group with a preset normal charging behavior habit model, thereby realizing real-time monitoring and response to the anomaly. After detecting a charging anomaly in the target charging pile group, multiple random numbers are generated through random number perturbation requests to adjust the charging output parameters of the charging piles, and the charging status data of the electric vehicle during the charging stage corresponding to the charging output parameters after each adjustment is obtained. By the response relationship between the charging status data and the charging output parameters, the dynamic response deviation of each charging pile during the charging output parameter adjustment process is accurately identified, thereby identifying the fault condition of each charging pile. This application utilizes a fault detection method that combines real-time monitoring and active perturbation, which significantly improves the sensitivity and accuracy of fault identification, and can ensure the timeliness of fault detection while balancing the cost and efficiency of fault detection.

[0071] In some embodiments, charging behavior data includes the charging time required for a single full charge of the electric vehicle, the charging power, the time period during which charging occurs, and the remaining battery charge (SOC) at the start of charging. The charging time required for a single full charge refers to the total time elapsed from the start of charging until the battery reaches 100% charge; the charging time period refers to the specific time during which the electric vehicle connects to the charging station and begins charging, such as during morning rush hour, midday, or off-peak hours at night; and the remaining battery charge (SOC) at the start of charging refers to the percentage of the battery's state of charge at the moment charging begins.

[0072] In this case, based on charging behavior data and a preset normal charging behavior habit model, it is determined whether the target charging pile group has charging abnormalities. This includes: inputting the charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging into a first charging behavior habit model to obtain a first probability density value; inputting the charging power and the charging time period into a second charging behavior habit model to obtain a second probability density value; and determining whether the target charging pile group has charging abnormalities based on the first and second probability density values: if the first probability density value is lower than a preset first threshold and / or the second probability density value is lower than a preset second threshold, then it is determined that the target charging pile group has charging abnormalities.

[0073] It should be noted that, in order to avoid model misjudgment due to insufficient sample size, this application needs to obtain charging behavior data of more than a certain number of vehicles (such as 100 vehicles) to ensure the statistical significance and generalization ability of the model training.

[0074] Optionally, the charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging are input into the first charging behavior habit model to obtain a first probability density value, which reflects the rationality of the current charging behavior distribution in the two-dimensional space of time and charge. Similarly, the charging power and the charging time period are input into the second model to obtain a second probability density value, which characterizes the normal matching degree of the power-time period combination.

[0075] Then, the first probability density value and the second probability density value are used to identify whether there is a charging abnormality in the target charging pile group. If either probability density value is lower than the corresponding threshold, it is determined that there is a charging abnormality in the target charging pile group. At the same time, this charging abnormality means that there is an abnormality in the target charging pile group, and it is necessary to further investigate whether the individual charging piles in the target charging pile group have malfunctioned.

[0076] In some embodiments, the charging output parameters include the output supply voltage and the output supply current. In this case, generating multiple random numbers through a random number perturbation request and adjusting the charging output parameters of the charging pile according to each random number includes: generating multiple random numbers at preset time intervals using a random number generation module built into the charging pile; finding the preset voltage level and preset current level corresponding to each random number in a preset random number mapping table, and adjusting the output supply voltage and output supply current of the charging pile according to the preset voltage level and preset current level; wherein the preset random number mapping table includes multiple random numbers and the mapping relationship between the preset voltage level and preset current level corresponding to the random numbers, and the voltage difference between the preset voltage levels corresponding to any two random numbers is not less than a preset voltage threshold, and the current difference between the preset current levels corresponding to any two random numbers is not less than a preset current threshold.

[0077] The random number generation module is embedded in the main control chip of the charging pile, or a group of charging piles can share a single random number generation module. After receiving a random number disturbance request, the random number generation module generates random numbers under the premise of following a normal distribution, ensuring that the disturbance has statistical stability and unpredictability.

[0078] Meanwhile, the random number mapping table contains multiple random numbers and their corresponding preset voltage and current levels. Each random number corresponds to a specific supply voltage or current, achieving a one-to-one mapping. To ensure the discreteness and safety of voltage and current disturbances, the voltage difference between any two preset voltage levels corresponding to random numbers is no less than a preset voltage threshold (e.g., 0.5V), and the current difference between any two preset current levels corresponding to random numbers is no less than a preset current threshold (e.g., 0.2A). This design avoids control ambiguity caused by parameters being too close between adjacent disturbance levels and ensures that the charging process remains within a safety margin during dynamic adjustments, providing highly discriminative verification samples for anomaly identification.

[0079] Optionally, a corresponding random number is generated every 0.01. The power supply voltage or current generated by each random number is maintained for a preset duration. After the preset duration ends, the charging pile resumes standard charging power to charge the electric vehicle.

[0080] In some embodiments, the charging status data includes the remaining time required for a full charge and the current temperature of the battery. Determining the fault status of each charging station based on the adjusted charging output parameters and the charging status data includes: determining the charging voltage and charging current trends of the charging station based on the adjusted charging output parameters; determining the charging efficiency and current battery temperature trends of the charging station based on the remaining time required for a full charge and the current battery temperature corresponding to the adjusted charging output parameters; comparing the consistency between the charging efficiency and charging voltage trends; if the charging efficiency and charging voltage trends are inconsistent, the charging station is determined to be faulty; comparing the consistency between the current battery temperature and charging current trends; if the current battery temperature and charging current trends are inconsistent, the charging station is determined to be faulty.

[0081] The charging voltage change trend is a real-time fluctuation sequence that appears as the preset voltage level corresponding to the random number is dynamically adjusted. For example, when the preset voltage level is increased, the charging voltage change trend should show an upward trend, and when the preset voltage level is decreased, it should show a downward trend. The charging current change trend is similar.

[0082] In addition, after each adjustment of the charging output parameters, corresponding to the current expected remaining time for full charge and the current battery temperature, if the current expected remaining time for full charge is shorter, it indicates higher charging efficiency, and the charging efficiency of the charging pile should show an upward trend; if the current expected remaining time for full charge is longer, it indicates lower charging efficiency, and the charging efficiency of the charging pile should show a downward trend; the same applies to the current battery temperature.

[0083] Since charging with a higher supply voltage results in faster charging while maintaining the same charging power, the expected remaining time to fully charge is shorter. Similarly, using a higher charging current while maintaining the same charging power will cause the battery to heat up and its temperature to rise. Therefore, this application compares the consistency between the trends in charging efficiency and charging voltage, as well as the consistency between the trends in current battery temperature and charging current.

[0084] Optionally, if the charging efficiency change trend is inconsistent with the charging voltage change trend, or the current battery temperature change trend is inconsistent with the charging current change trend, then the charging pile is determined to be faulty.

[0085] By configuring a random number generation module and using the random numbers generated by this module to form a corresponding supply voltage or current for charging electric vehicles, the charging voltage or current supplied to the vehicle is changed, thereby altering the electric vehicle's status data. If the change in the electric vehicle's status data matches the direction of change in the supply voltage or current, it means that the charging station has indeed generated a change in supply voltage or current and is supplying power normally, indicating that the current charging station is functioning correctly. Otherwise, it indicates that the current charging station is faulty. Therefore, through this process, by simply iterating through each charging station, it is possible to determine whether a specific charging station in a group is faulty.

[0086] Furthermore, to avoid misjudging aging charging pile hardware and slow charging as malfunctions, this application also performs cross-validation. Specifically, the method further includes: obtaining the charging power of each electric vehicle connected to the target charging pile group during the current detection period and the remaining battery charge (SOC) at the start of charging; determining multiple target electric vehicles based on the charging power and the remaining battery charge (SOC) at the start of charging; wherein the difference between the charging power of any two target electric vehicles is less than a preset power difference threshold, and the difference in the remaining battery charge (SOC) at the start of charging is less than a preset SOC difference threshold; obtaining charging status data for each target electric vehicle; wherein the charging status data includes the time required for a single full charge and the current battery temperature; and performing a cross-validation on the time required for a single full charge and the current battery temperature. The system is normalized, and the normalized time required for a single full charge and the normalized current battery temperature are weighted and fused to generate a comprehensive status score. Each pair of target electric vehicles is treated as a comparison group, and the difference between the comprehensive status scores of the two target electric vehicles within each comparison group is calculated as the comprehensive status score difference value for the comparison group. The comparison groups are sorted in descending order according to the magnitude of the comprehensive status score difference values, and the charging piles corresponding to the first preset number of comparison groups are selected as suspected fault charging piles. The comprehensive status score difference value between each suspected fault charging pile and other charging piles is obtained. If the comprehensive status score difference value between the suspected fault charging pile and at least two other charging piles exceeds a preset score difference threshold, the suspected fault charging pile is determined to be a faulty charging pile.

[0087] This application embodiment obtains charging status data of at least 3 charging piles of the target charging pile group for multiple target electric vehicles within a preset time period (such as one day). The charging status data includes the time required for a single full charge and the current temperature of the battery.

[0088] Then, after normalizing the time required for a single full charge and the current battery temperature, a weighted fusion is used to generate a comprehensive status score. Then, through multiple sets of comparative analysis of the difference values, abnormal fluctuations are accurately identified by traversing each set.

[0089] Optionally, the charging status data of any two target electric vehicles form a group. The comprehensive status score difference value of each group is iterated through, and the groups are sorted from largest to smallest according to the magnitude of the comprehensive status score difference value. The charging piles in the groups corresponding to the top few (e.g., the top-ranked) difference scores are identified as suspected faulty charging piles. If the comprehensive status score difference value between the suspected faulty charging pile and at least two other charging piles exceeds a preset score threshold, then the suspected faulty charging pile is determined to be faulty.

[0090] Understandably, since charging is performed on identical electric vehicles under the same conditions, theoretically, the difference in charging status data between any two charging stations is minimal, meaning the difference in their overall status scores is also minimal. When this difference exceeds a preset scoring threshold, it often indicates a fault in the charging station causing a change in charging efficiency. This change in charging efficiency will be reflected in the charging status data and thus accurately captured as an abnormal signal.

[0091] Based on the same inventive concept, this application also provides a charging pile group fault detection system for implementing the charging pile group fault detection method mentioned above.

[0092] The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more charging pile group fault detection system embodiments provided below can be found in the limitations of the charging pile group fault detection method above, and will not be repeated here.

[0093] like Figure 3 As shown in the figure, this application provides a charging pile group fault detection system, including: a charging anomaly judgment module 100, a charging parameter adjustment module 200, and a fault detection module 300. Wherein:

[0094] The charging anomaly judgment module 100 is used to acquire charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period, and to determine whether there is a charging anomaly in the target charging pile group based on the charging behavior data and the preset normal charging behavior habit model.

[0095] The charging parameter adjustment module 200 is used to, after determining that there is a charging abnormality in the target charging pile group, generate multiple random numbers in response to the random number perturbation request for each charging pile in the target charging pile group that is connected to an electric vehicle, and adjust the charging output parameters of the charging pile according to each random number.

[0096] The fault detection module 300 is used to acquire the charging status data of the electric vehicle during the charging stage corresponding to the adjusted charging output parameters each time, and to determine the fault status of each charging pile based on the adjusted charging output parameters and charging status data each time.

[0097] In some embodiments, the normal charging behavior habit model includes a first charging behavior habit model and a second charging behavior habit model; the first charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging time and battery remaining power SOC, and the second charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging power and the charging time period.

[0098] In some embodiments, charging behavior data includes the charging time required for a single full charge of the electric vehicle, the charging power, the time period during which charging takes place, and the remaining battery charge (SOC) at the start of charging.

[0099] The charging anomaly detection module 100 is used for:

[0100] The charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging are input into the first charging behavior habit model to obtain the first probability density value; the charging power and the charging time period are input into the second charging behavior habit model to obtain the second probability density value.

[0101] Based on the first probability density value and the second probability density value, determine whether there is any charging anomaly in the target charging pile group:

[0102] If the first probability density value is lower than the preset first threshold and / or the second probability density value is lower than the preset second threshold, then it is determined that there is a charging abnormality in the target charging pile group.

[0103] In some embodiments, the charging output parameters include the output supply voltage and the output supply current;

[0104] The charging parameter adjustment module 200 is used for:

[0105] The charging pile uses a built-in random number generation module to generate multiple random numbers at preset time intervals.

[0106] For each random number, the system finds the corresponding preset voltage and current levels in a preset random number mapping table, and adjusts the output voltage and current of the charging pile according to the preset voltage and current levels. The preset random number mapping table includes multiple random numbers and the mapping relationship between the preset voltage and current levels corresponding to the random numbers. The voltage difference between any two preset voltage levels corresponding to any two random numbers is not less than a preset voltage threshold, and the current difference between any two preset current levels corresponding to any two random numbers is not less than a preset current threshold.

[0107] In some embodiments, the fault detection module 300 is used for:

[0108] Based on the charging output parameters after each adjustment, determine the trends in charging voltage and charging current of the charging pile.

[0109] Based on the remaining time required for full charge and the current temperature of the battery corresponding to the adjusted charging output parameters, the charging efficiency trend of the charging pile and the current temperature trend of the battery are determined respectively.

[0110] By comparing the trends of charging efficiency and charging voltage, if the trends of charging efficiency and charging voltage are not consistent, it is determined that there is a fault in the charging pile.

[0111] By comparing the current temperature change trend of the battery with the charging current change trend, if it is determined that the current temperature change trend of the battery is inconsistent with the charging current change trend, it is determined that there is a fault in the charging pile.

[0112] In some embodiments, the system further includes: a cross-fault identification module, used for:

[0113] Obtain the charging power and the remaining battery charge (SOC) of each electric vehicle connected to the target charging pile group during the current detection period;

[0114] Based on the charging power of each electric vehicle and the remaining battery charge (SOC) at the start of charging, multiple target electric vehicles are determined; wherein, the difference between the charging power of any two target electric vehicles is less than a preset power difference threshold, and the difference between the remaining battery charge (SOC) at the start of charging is less than a preset SOC difference threshold.

[0115] Acquire charging status data for each target electric vehicle; the charging status data includes the time required for a single full charge and the current temperature of the battery;

[0116] The time required for a single full charge and the current temperature of the battery are normalized, and the normalized time required for a single full charge and the normalized current temperature of the battery are weighted and fused to generate a comprehensive status score.

[0117] For each pair of target electric vehicles among all target electric vehicles, a comparison group is formed. The difference between the comprehensive status scores of the two target electric vehicles in each comparison group is calculated as the comprehensive status score difference value of the comparison group.

[0118] The comparison groups are sorted in descending order according to the size of the difference in the comprehensive status score. The charging piles corresponding to the comparison groups with a preset number of groups before sorting are taken as suspected fault charging piles.

[0119] Obtain the comprehensive status score difference value between each suspected faulty charging pile and other charging piles. If the comprehensive status score difference value between the suspected faulty charging pile and at least two other charging piles exceeds the preset score difference threshold, the suspected faulty charging pile is determined to be a faulty charging pile.

[0120] like Figure 4 As shown, this application provides an electronic device 10, which includes a memory 20 and a processor 30. The memory 20 stores a computer program. When the computer program is executed by the processor 30, the processor 30 performs the following steps:

[0121] Acquire charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period, and determine whether there is any charging abnormality in the target charging pile group based on the charging behavior data and the preset normal charging behavior habit model.

[0122] After determining that there is a charging anomaly in the target charging pile group, for each charging pile in the target charging pile group that is connected to an electric vehicle, in response to the random number perturbation request, multiple random numbers are generated through the random number perturbation request, and the charging output parameters of the charging pile are adjusted according to each random number.

[0123] Obtain the charging status data of the electric vehicle during the charging phase corresponding to the adjusted charging output parameters each time, and determine the fault status of each charging pile based on the adjusted charging output parameters and charging status data each time.

[0124] In some embodiments, the normal charging behavior habit model includes a first charging behavior habit model and a second charging behavior habit model; the first charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging time and battery remaining power SOC, and the second charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging power and the charging time period.

[0125] In some embodiments, charging behavior data includes the charging time required for a single full charge of the electric vehicle, the charging power, the time period during which charging takes place, and the remaining battery charge (SOC) at the start of charging.

[0126] When the computer program is executed by the processor 30, the processor 30 also executes:

[0127] The charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging are input into the first charging behavior habit model to obtain the first probability density value; the charging power and the charging time period are input into the second charging behavior habit model to obtain the second probability density value.

[0128] Based on the first probability density value and the second probability density value, determine whether there is any charging anomaly in the target charging pile group:

[0129] If the first probability density value is lower than the preset first threshold and / or the second probability density value is lower than the preset second threshold, then it is determined that there is a charging abnormality in the target charging pile group.

[0130] In some embodiments, the charging output parameters include the output supply voltage and the output supply current;

[0131] When the computer program is executed by the processor 30, the processor 30 also executes:

[0132] The charging pile uses a built-in random number generation module to generate multiple random numbers at preset time intervals.

[0133] For each random number, the system finds the corresponding preset voltage and current levels in a preset random number mapping table, and adjusts the output voltage and current of the charging pile according to the preset voltage and current levels. The preset random number mapping table includes multiple random numbers and the mapping relationship between the preset voltage and current levels corresponding to the random numbers. The voltage difference between any two preset voltage levels corresponding to any two random numbers is not less than a preset voltage threshold, and the current difference between any two preset current levels corresponding to any two random numbers is not less than a preset current threshold.

[0134] In some embodiments, the state of charging data includes the remaining time expected for a full charge and the current temperature of the battery; when the computer program is executed by the processor 30, the processor 30 also performs:

[0135] Based on the charging output parameters after each adjustment, determine the trends in charging voltage and charging current of the charging pile.

[0136] Based on the remaining time required for full charge and the current temperature of the battery corresponding to the adjusted charging output parameters, the charging efficiency trend of the charging pile and the current temperature trend of the battery are determined respectively.

[0137] By comparing the trends of charging efficiency and charging voltage, if the trends of charging efficiency and charging voltage are not consistent, it is determined that there is a fault in the charging pile.

[0138] By comparing the current temperature change trend of the battery with the charging current change trend, if it is determined that the current temperature change trend of the battery is inconsistent with the charging current change trend, it is determined that there is a fault in the charging pile.

[0139] In some embodiments, when the computer program is executed by the processor 30, the processor 30 also performs:

[0140] Obtain the charging power and the remaining battery charge (SOC) of each electric vehicle connected to the target charging pile group during the current detection period;

[0141] Based on the charging power of each electric vehicle and the remaining battery charge (SOC) at the start of charging, multiple target electric vehicles are determined; wherein, the difference between the charging power of any two target electric vehicles is less than a preset power difference threshold, and the difference between the remaining battery charge (SOC) at the start of charging is less than a preset SOC difference threshold.

[0142] Acquire charging status data for each target electric vehicle; the charging status data includes the time required for a single full charge and the current temperature of the battery;

[0143] The time required for a single full charge and the current temperature of the battery are normalized, and the normalized time required for a single full charge and the normalized current temperature of the battery are weighted and fused to generate a comprehensive status score.

[0144] For each pair of target electric vehicles among all target electric vehicles, a comparison group is formed. The difference between the comprehensive status scores of the two target electric vehicles in each comparison group is calculated as the comprehensive status score difference value of the comparison group.

[0145] The comparison groups are sorted in descending order according to the size of the difference in the comprehensive status score. The charging piles corresponding to the comparison groups with a preset number of groups before sorting are taken as suspected fault charging piles.

[0146] Obtain the comprehensive status score difference value between each suspected faulty charging pile and other charging piles. If the comprehensive status score difference value between the suspected faulty charging pile and at least two other charging piles exceeds the preset score difference threshold, the suspected faulty charging pile is determined to be a faulty charging pile.

[0147] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed, performs the following steps:

[0148] Acquire charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period, and determine whether there is any charging abnormality in the target charging pile group based on the charging behavior data and the preset normal charging behavior habit model.

[0149] After determining that there is a charging anomaly in the target charging pile group, for each charging pile in the target charging pile group that is connected to an electric vehicle, in response to the random number perturbation request, multiple random numbers are generated through the random number perturbation request, and the charging output parameters of the charging pile are adjusted according to each random number.

[0150] Obtain the charging status data of the electric vehicle during the charging phase corresponding to the adjusted charging output parameters each time, and determine the fault status of each charging pile based on the adjusted charging output parameters and charging status data each time.

[0151] In some embodiments, the normal charging behavior habit model includes a first charging behavior habit model and a second charging behavior habit model; the first charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging time and battery remaining power SOC, and the second charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging power and the charging time period.

[0152] In some embodiments, charging behavior data includes the charging time required for a single full charge of the electric vehicle, the charging power, the time period during which charging takes place, and the remaining battery charge (SOC) at the start of charging.

[0153] When a computer program is executed, it also performs the following:

[0154] The charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging are input into the first charging behavior habit model to obtain the first probability density value; the charging power and the charging time period are input into the second charging behavior habit model to obtain the second probability density value.

[0155] Based on the first probability density value and the second probability density value, determine whether there is any charging anomaly in the target charging pile group:

[0156] If the first probability density value is lower than the preset first threshold and / or the second probability density value is lower than the preset second threshold, then it is determined that there is a charging abnormality in the target charging pile group.

[0157] In some embodiments, the charging output parameters include the output supply voltage and the output supply current;

[0158] When a computer program is executed, it also performs the following:

[0159] The charging pile uses a built-in random number generation module to generate multiple random numbers at preset time intervals.

[0160] For each random number, the system finds the corresponding preset voltage and current levels in a preset random number mapping table, and adjusts the output voltage and current of the charging pile according to the preset voltage and current levels. The preset random number mapping table includes multiple random numbers and the mapping relationship between the preset voltage and current levels corresponding to the random numbers. The voltage difference between any two preset voltage levels corresponding to any two random numbers is not less than a preset voltage threshold, and the current difference between any two preset current levels corresponding to any two random numbers is not less than a preset current threshold.

[0161] In some embodiments, the state of charging data includes the remaining time expected to fully charge and the current temperature of the battery; the computer program, when executed, also implements:

[0162] Based on the charging output parameters after each adjustment, determine the trends in charging voltage and charging current of the charging pile.

[0163] Based on the remaining time required for full charge and the current temperature of the battery corresponding to the adjusted charging output parameters, the charging efficiency trend of the charging pile and the current temperature trend of the battery are determined respectively.

[0164] By comparing the trends of charging efficiency and charging voltage, if the trends of charging efficiency and charging voltage are not consistent, it is determined that there is a fault in the charging pile.

[0165] By comparing the current temperature change trend of the battery with the charging current change trend, if it is determined that the current temperature change trend of the battery is inconsistent with the charging current change trend, it is determined that there is a fault in the charging pile.

[0166] In some embodiments, the computer program, when executed, also implements:

[0167] Obtain the charging power and the remaining battery charge (SOC) of each electric vehicle connected to the target charging pile group during the current detection period;

[0168] Based on the charging power of each electric vehicle and the remaining battery charge (SOC) at the start of charging, multiple target electric vehicles are determined; wherein, the difference between the charging power of any two target electric vehicles is less than a preset power difference threshold, and the difference between the remaining battery charge (SOC) at the start of charging is less than a preset SOC difference threshold.

[0169] Acquire charging status data for each target electric vehicle; the charging status data includes the time required for a single full charge and the current temperature of the battery;

[0170] The time required for a single full charge and the current temperature of the battery are normalized, and the normalized time required for a single full charge and the normalized current temperature of the battery are weighted and fused to generate a comprehensive status score.

[0171] For each pair of target electric vehicles among all target electric vehicles, a comparison group is formed. The difference between the comprehensive status scores of the two target electric vehicles in each comparison group is calculated as the comprehensive status score difference value of the comparison group.

[0172] The comparison groups are sorted in descending order according to the size of the difference in the comprehensive status score. The charging piles corresponding to the comparison groups with a preset number of groups before sorting are taken as suspected fault charging piles.

[0173] Obtain the comprehensive status score difference value between each suspected faulty charging pile and other charging piles. If the comprehensive status score difference value between the suspected faulty charging pile and at least two other charging piles exceeds the preset score difference threshold, the suspected faulty charging pile is determined to be a faulty charging pile.

[0174] This application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer performs the following steps:

[0175] Acquire charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period, and determine whether there is any charging abnormality in the target charging pile group based on the charging behavior data and the preset normal charging behavior habit model.

[0176] After determining that there is a charging anomaly in the target charging pile group, for each charging pile in the target charging pile group that is connected to an electric vehicle, in response to the random number perturbation request, multiple random numbers are generated through the random number perturbation request, and the charging output parameters of the charging pile are adjusted according to each random number.

[0177] Obtain the charging status data of the electric vehicle during the charging phase corresponding to the adjusted charging output parameters each time, and determine the fault status of each charging pile based on the adjusted charging output parameters and charging status data each time.

[0178] In some embodiments, the normal charging behavior habit model includes a first charging behavior habit model and a second charging behavior habit model; the first charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging time and battery remaining power SOC, and the second charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging power and the charging time period.

[0179] In some embodiments, charging behavior data includes the charging time required for a single full charge of the electric vehicle, the charging power, the time period during which charging takes place, and the remaining battery charge (SOC) at the start of charging.

[0180] When program instructions are executed by the computer, the computer also performs the following:

[0181] The charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging are input into the first charging behavior habit model to obtain the first probability density value; the charging power and the charging time period are input into the second charging behavior habit model to obtain the second probability density value.

[0182] Based on the first probability density value and the second probability density value, determine whether there is any charging anomaly in the target charging pile group:

[0183] If the first probability density value is lower than the preset first threshold and / or the second probability density value is lower than the preset second threshold, then it is determined that there is a charging abnormality in the target charging pile group.

[0184] In some embodiments, the charging output parameters include the output supply voltage and the output supply current;

[0185] When program instructions are executed by the computer, the computer also performs the following:

[0186] The charging pile uses a built-in random number generation module to generate multiple random numbers at preset time intervals.

[0187] For each random number, the system finds the corresponding preset voltage and current levels in a preset random number mapping table, and adjusts the output voltage and current of the charging pile according to the preset voltage and current levels. The preset random number mapping table includes multiple random numbers and the mapping relationship between the preset voltage and current levels corresponding to the random numbers. The voltage difference between any two preset voltage levels corresponding to any two random numbers is not less than a preset voltage threshold, and the current difference between any two preset current levels corresponding to any two random numbers is not less than a preset current threshold.

[0188] In some embodiments, the state of charging data includes the remaining time expected for a full charge and the current temperature of the battery; when program instructions are executed by the computer, the computer also performs:

[0189] Based on the charging output parameters after each adjustment, determine the trends in charging voltage and charging current of the charging pile.

[0190] Based on the remaining time required for full charge and the current temperature of the battery corresponding to the adjusted charging output parameters, the charging efficiency trend of the charging pile and the current temperature trend of the battery are determined respectively.

[0191] By comparing the trends of charging efficiency and charging voltage, if the trends of charging efficiency and charging voltage are not consistent, it is determined that there is a fault in the charging pile.

[0192] By comparing the current temperature change trend of the battery with the charging current change trend, if it is determined that the current temperature change trend of the battery is inconsistent with the charging current change trend, it is determined that there is a fault in the charging pile.

[0193] In some embodiments, when program instructions are executed by the computer, the computer also performs:

[0194] Obtain the charging power and the remaining battery charge (SOC) of each electric vehicle connected to the target charging pile group during the current detection period;

[0195] Based on the charging power of each electric vehicle and the remaining battery charge (SOC) at the start of charging, multiple target electric vehicles are determined; wherein, the difference between the charging power of any two target electric vehicles is less than a preset power difference threshold, and the difference between the remaining battery charge (SOC) at the start of charging is less than a preset SOC difference threshold.

[0196] Acquire charging status data for each target electric vehicle; the charging status data includes the time required for a single full charge and the current temperature of the battery;

[0197] The time required for a single full charge and the current temperature of the battery are normalized, and the normalized time required for a single full charge and the normalized current temperature of the battery are weighted and fused to generate a comprehensive status score.

[0198] For each pair of target electric vehicles among all target electric vehicles, a comparison group is formed. The difference between the comprehensive status scores of the two target electric vehicles in each comparison group is calculated as the comprehensive status score difference value of the comparison group.

[0199] The comparison groups are sorted in descending order according to the size of the difference in the comprehensive status score. The charging piles corresponding to the comparison groups with a preset number of groups before sorting are taken as suspected fault charging piles.

[0200] Obtain the comprehensive status score difference value between each suspected faulty charging pile and other charging piles. If the comprehensive status score difference value between the suspected faulty charging pile and at least two other charging piles exceeds the preset score difference threshold, the suspected faulty charging pile is determined to be a faulty charging pile.

[0201] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, electronic devices, computer storage media, and computer program products described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0202] It should be noted that the user information and data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0203] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0204] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0205] In the several embodiments provided by this invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0206] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0207] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0208] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the various embodiments of the present invention through a computer device (which may be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0209] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting faults in a group of charging piles, characterized in that, include: The system acquires charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period. Based on the charging behavior data and a preset normal charging behavior habit model, it determines whether there is any charging abnormality in the target charging pile group. After determining that there is a charging abnormality in the target charging pile group, for each charging pile in the target charging pile group that is connected to an electric vehicle, in response to the random number perturbation request, multiple random numbers are generated through the random number perturbation request, and the charging output parameters of the charging pile are adjusted according to each random number. Obtain the charging status data of the electric vehicle during the charging phase corresponding to the adjusted charging output parameters each time, and determine the fault status of each charging pile based on the adjusted charging output parameters and the charging status data.

2. The charging pile group fault detection method according to claim 1, characterized in that, The normal charging behavior habit model includes a first charging behavior habit model and a second charging behavior habit model; the first charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging time and battery remaining power SOC, and the second charging behavior habit model is a two-dimensional normal distribution model constructed based on the probability density function of charging power and the charging time period.

3. The charging pile group fault detection method according to claim 2, characterized in that, The charging behavior data includes the charging time required for a single full charge of the electric vehicle, the charging power, the time period during which charging occurs, and the remaining battery charge (SOC) at the start of charging. The step of determining whether there is a charging anomaly in the target charging pile group based on the charging behavior data and a preset normal charging behavior habit model includes: The charging time required for a single full charge and the remaining battery charge (SOC) at the start of charging are input into the first charging behavior habit model to obtain a first probability density value; the charging power and the charging time period are input into the second charging behavior habit model to obtain a second probability density value. Based on the first probability density value and the second probability density value, determine whether the target charging pile group has any charging anomalies: If the first probability density value is lower than a preset first threshold and / or the second probability density value is lower than a preset second threshold, then it is determined that the target charging pile group has a charging abnormality.

4. The charging pile group fault detection method according to claim 1, characterized in that, The charging output parameters include the output power supply voltage and the output power supply current; The step of generating multiple random numbers through the random number perturbation request and adjusting the charging output parameters of the charging pile according to each random number includes: The charging pile uses a built-in random number generation module to generate multiple random numbers at preset time intervals. For each random number, the preset voltage level and preset current level corresponding to the random number are found in a preset random number mapping table, and the output supply voltage and output supply current of the charging pile are adjusted according to the preset voltage level and preset current level. The preset random number mapping table includes multiple random numbers and the mapping relationship between the preset voltage level and preset current level corresponding to the random number, and the voltage difference between any two preset voltage levels corresponding to the random numbers is not less than a preset voltage threshold, and the current difference between any two preset current levels corresponding to the random numbers is not less than a preset current threshold.

5. The charging pile group fault detection method according to claim 4, characterized in that, The charging status data includes the remaining time required for a full charge and the current battery temperature; determining the fault status of each charging station based on the adjusted charging output parameters and the charging status data includes: Based on the charging output parameters after each adjustment, determine the charging voltage and charging current variation trends of the charging pile. Based on the remaining time required for full charging corresponding to the adjusted charging output parameters and the current temperature of the battery, the charging efficiency change trend of the charging pile and the current temperature change trend of the battery are determined respectively. By comparing the trend of charging efficiency change with the trend of charging voltage change, if it is determined that the trend of charging efficiency change is inconsistent with the trend of charging voltage change, then it is determined that the charging pile has a fault. By comparing the current temperature change trend of the battery with the charging current change trend, if it is determined that the current temperature change trend of the battery is inconsistent with the charging current change trend, then the charging pile is determined to be faulty.

6. The charging pile group fault detection method according to claim 1, characterized in that, Also includes: The charging power and the remaining battery charge (SOC) at the start of charging are obtained for each electric vehicle connected to the target charging pile group during the current detection period. Multiple target electric vehicles are determined based on the charging power of each electric vehicle and the remaining battery charge (SOC) at the start of charging; wherein the difference between the charging power of any two target electric vehicles is less than a preset power difference threshold, and the difference between the remaining battery charge (SOC) at the start of charging is less than a preset SOC difference threshold. Acquire charging status data for each of the target electric vehicles; wherein the charging status data includes the time required for a single full charge and the current temperature of the battery; The time required for a single full charge and the current temperature of the battery are normalized, and the normalized time required for a single full charge and the normalized current temperature of the battery are weighted and fused to generate a comprehensive status score. Take every two target electric vehicles among all the target electric vehicles as a comparison group, and calculate the difference between the comprehensive status scores of the two target electric vehicles in each comparison group as the comprehensive status score difference value of the comparison group; The comparison groups are sorted in descending order according to the size of the difference in the comprehensive status score, and the charging piles corresponding to the comparison groups with a preset number of groups before sorting are taken as suspected fault charging piles. Obtain the comprehensive status score difference value between each suspected faulty charging pile and other charging piles. If the comprehensive status score difference value between the suspected faulty charging pile and at least two other charging piles exceeds the preset score difference threshold, then the suspected faulty charging pile is determined to be a faulty charging pile.

7. A fault detection system for charging pile groups, characterized in that, include: The charging anomaly detection module is used to acquire charging behavior data of multiple electric vehicles connected to the target charging pile group during the current detection period, and to determine whether there is a charging anomaly in the target charging pile group based on the charging behavior data and a preset normal charging behavior habit model. The charging parameter adjustment module is used to, after determining that there is a charging abnormality in the target charging pile group, generate multiple random numbers for each charging pile in the target charging pile group that is connected to an electric vehicle in response to a random number perturbation request, and adjust the charging output parameters of the charging pile according to each random number. The fault detection module is used to acquire the charging status data of the electric vehicle during the charging phase corresponding to the adjusted charging output parameters each time, and to determine the fault status of each charging pile based on the adjusted charging output parameters and the charging status data.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor performs the steps of the charging pile group fault detection method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the steps of the charging pile group fault detection method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the charging pile group fault detection method as described in any one of claims 1-6.

Citation Information

Patent Citations

  • Health detection method, device and equipment for charging pile cluster and storage medium

    CN121142201A