DC charging pile anomaly detection method and system

Abstract

The invention provides a DC charging pile anomaly detection method and system. The method comprises the following steps: selecting a general meter electric energy indicating value in a charging station and a charging pile electric energy indicating value to form meter-pile pairing metering data; constructing a table-pile metering error coefficient solving equation, and extracting characteristic parameters representing metering performance in the solving equation; quantifying unknown parameters in the characteristic parameters based on a rectification loss mathematical model, and solving specific numerical values of the characteristic parameters; averaging the characteristic parameters to serve as a total meter metering performance parameter, and judging whether the total meter metering performance is qualified or not based on the position of the total meter metering performance parameter in the normal distribution of the historical test data of the charging pile; and qualified meter-pile pairing metering data are extracted, abnormal values in the meter-pile pairing metering data are identified through a symmetrically optimized box graph anomaly detection algorithm, and charging piles with abnormal metering performance are positioned. According to the scheme, online and real-time abnormal detection of the charging pile can be realized, the detection efficiency is high, the implementation cost is low, and deviation of electric energy settlement can be avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of charging piles, and in particular relates to a method and system for detecting anomalies in a DC charging pile. Background Art

[0002] As a large current power transmission and metering equipment, DC charging piles for electric vehicles are closely related to the personal safety and property safety of users. During long-term operation, DC charging piles are affected by factors such as temperature, humidity, and magnetic field strength, which leads to degradation of metering performance and even metering performance errors, which in turn affects the fairness of power trade. Therefore, it is necessary to test the metering performance of DC charging piles.

[0003] At present, the traditional charging pile measurement verification method uses a load to simulate electric vehicles for charging, connects standard measuring instruments in series into the circuit, and compares the display value of the standard measuring instrument with the display value of the charging pile after charging the set electric energy, so as to determine the display error of the charging pile. However, as residential electrical equipment, DC charging piles have the characteristics of scattered distribution, large quantity, and uneven quality. For measurement performance, the verification regulations stipulate that the charger should be verified in a three-year cycle, which has poor timeliness, low detection efficiency and high implementation cost. Obviously, if the metering performance of the charging pile is abnormal during the two verification periods, the existing method cannot detect the abnormal charging pile in time, which will lead to deviations in the charging energy settlement of electric vehicles, undermine the fairness of electricity trade, and fail to timely discover potential risks such as aging and failure of charging pile components that cause abnormal metering performance, endangering personal and property safety. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a DC charging pile abnormality detection method and system, which are used to solve the problems of poor timeliness, low detection efficiency and high implementation cost of current charger abnormality detection.

[0005] In a first aspect of an embodiment of the present invention, a method for detecting an abnormality of a DC charging pile is provided, comprising: Obtain the electric energy metering data of each DC charging pile in the charging station during operation, and select the total meter electric energy indication of the station and the electric energy indication of the running charging pile in the same period to form meter-pile paired metering data; Based on the meter-pile paired metering data, a meter-pile metering error coefficient solution equation for the whole charging process loss of the charging pile is constructed, and characteristic parameters characterizing the meter-pile metering performance in the solution equation are extracted; Constructing a rectification loss mathematical model, quantifying unknown parameters in characteristic parameters of meter-pile metering performance based on the rectification loss mathematical model, solving specific values ​​of the characteristic parameters, and storing the specific values ​​in a characteristic data set; Extract characteristic parameter data covering meter-pile metering performance of all charging piles from the characteristic data set, take the mean of the characteristic parameter data as the total meter metering performance parameter, and judge whether the total meter metering performance is qualified based on the position of the total meter metering performance parameter in the normal distribution of the charging pile historical test data; The meter-pile paired metering data whose total metering performance is judged to be qualified in the feature data set are extracted, and the outliers in the meter-pile paired metering data are identified through the symmetrically optimized box plot anomaly detection algorithm, and the charging piles with abnormal metering performance are located.

[0006] In a second aspect of an embodiment of the present invention, a DC charging pile abnormality detection system is provided, comprising: The data screening module is used to obtain the electric energy metering data of each DC charging pile in the charging station during operation, and select the electric energy indication of the total meter in the station and the electric energy indication of the charging pile in operation during the same period to form the meter-pile paired metering data; A parameter extraction module is used to construct a meter-pile measurement error coefficient solution equation for the whole charging process loss of the charging pile based on the meter-pile pairing measurement data, and extract characteristic parameters characterizing the meter-pile measurement performance in the solution equation; The parameter quantification module is used to construct a rectification loss mathematical model, quantify the unknown parameters in the characteristic parameters of the metering performance of the table-pile based on the rectification loss mathematical model, and solve the specific values ​​of the characteristic parameters, and store the specific values ​​in the characteristic data set; The total meter detection module is used to extract characteristic parameter data covering the meter-pile metering performance of all charging piles from the characteristic data set, take the mean of the characteristic parameter data as the total meter metering performance parameter, and judge whether the total meter metering performance is qualified based on the position of the total meter metering performance parameter in the normal distribution of the charging pile historical test data; The charging pile detection module is used to extract the meter-pile paired metering data whose total metering performance is judged to be qualified in the feature data set, identify the outliers in the meter-pile paired metering data through the symmetrically optimized box plot anomaly detection algorithm, and locate the charging piles with abnormal metering performance.

[0007] In a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect of the embodiment of the present invention when executing the computer program.

[0008] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiment of the present invention are implemented.

[0009] In the embodiment of the present invention, by selecting metering data of meter-pile pairing, solving characteristic parameters characterizing meter-pile metering performance and quantifying its characteristic parameters, and proposing the mean value of characteristic parameters based on meter-pile metering performance and the distribution of historical test data, it is judged whether the total metering performance is qualified, and the abnormal value in qualified meter-pile pairing metering data is identified based on the symmetrically optimized box plot anomaly detection algorithm, so as to realize abnormal charging pile positioning. Thereby, it can not only meet the demand for real-time and accurate abnormal positioning of DC charging piles, but also effectively improve the efficiency of abnormal detection of charging piles and reduce the detection cost. In addition, it can avoid the deviation of charging power settlement, undermine the fairness of power trade, and timely discover the problems such as aging and failure of charging pile components that cause abnormal metering performance, so as to ensure personal and property safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a flow chart of a DC charging pile abnormality detection method provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a DC charging pile abnormality detection system provided by an embodiment of the present invention; Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] It should be understood that the term "including" and other similar expressions in the specification or claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, such as a process, method, system, or device including a series of steps or units is not limited to the listed steps or units. In addition, "first" and "second" are used to distinguish different objects, not to describe a specific order.

[0014] See also Figure 1, a flow chart of a DC charging pile abnormality detection method provided by an embodiment of the present invention includes: S101, obtaining the electric energy metering data of each DC charging pile in the charging station during operation, selecting the electric energy indication of the total meter in the station and the electric energy indication of the running charging pile in the same period to form meter-pile paired metering data; A DC charging pile is a device that is fixedly installed outside an electric vehicle, connected to the AC power grid, and outputs adjustable DC power to charge the onboard battery. In a charging station, the total meter measures the energy consumed by all charging piles in the charging station. A single charging pile is responsible for the energy consumed by charging the pile body. Charging stations of different sizes will be equipped with different numbers of charging piles.

[0015] The electric energy metering data includes the total meter electric energy indication and the charging pile electric energy indication. In the time series, the meter-pile paired metering data can be obtained by pairing the electric energy indication of the total meter in the station with the electric energy indication of the running charging pile in the same period.

[0016] For example, for a DC charging station with 6 charging piles, the time period is The total number of representations is , The number of charging piles is Assuming time period There are 3 charging piles involved in charging, numbered 1, 3, and 5. Therefore, the energy indications of the total meter and the 3 charging piles can be calculated as follows: ) Save as table - pile pairing measurement data The combination of table-stub paired data in different time periods can form a paired time series data set .

[0017] Preferably, the total meter power indication in the station during the time period when only one charging pile is in operation is paired with the power indication of the operating charging pile to form a meter-pile paired metering data set.

[0018] The time period when only one charging station is involved in charging Meter-pile pairing measurement data Extract and form a new table-pile paired measurement data set , as the data source for subsequent methods. In each set of paired data, there are only total table data and 1 charging pile data.

[0019] S102, based on the meter-pile paired metering data, constructing a meter-pile metering error coefficient solution equation for the whole charging process loss of the charging pile, and extracting characteristic parameters characterizing the meter-pile metering performance in the solution equation; Among them, the equation for solving the meter-pile measurement error coefficient of the entire charging process loss is expressed as: ; (1) Based on the known quantities in the solution equation, the characteristic parameters characterizing the metering performance of the meter-pile are expressed as: (2) In the formula, , They are respectively the general table, The measurement error coefficient of the charging pile is For time period The total meter electric energy indication value, for The rectification loss of the charging pile is For time period of No. Charging pile power indication value, is the other loss during this charging, Characteristic parameters used to characterize the meter-pile measurement performance.

[0020] It can be understood that when the total meter measurement performance is stable, Much smaller than and Approximately 1, It can be regarded as an inherent bias A; when the total meter performance exceeds the tolerance, the characteristic parameter of the charging pile meter performance will be increased. fluctuations.

[0021] Since the measurement accuracy level of the total meter is higher than that of the charging pile, and the operating environment of the total meter is better than that of the charging pile, Much smaller than , and is relatively stable. and are all known quantities, It is the rectification loss, and its size is related to the charging power of the electric vehicle. During the charging process, the fixed power consumption of the charging pile display can be ignored compared with the power consumption during charging. Therefore, formula (1) can be simplified to formula (2).

[0022] S103, constructing a rectification loss mathematical model, quantifying unknown parameters in characteristic parameters of the metering performance of the table-pile based on the rectification loss mathematical model, solving specific values ​​of the characteristic parameters, and storing the specific values ​​in a characteristic data set; Among them, the time period Inside The output power of the charging pile is expressed as: , the mathematical model of rectification loss is expressed as: ; The quantified charging pile electric energy value and the rectification loss of the charging pile Input formula (2) to solve the specific value of the characteristic parameter; Rectification loss is a mathematical model of charging power, which can be obtained by the supplier after factory testing and can be abbreviated as , so the rectification loss can also be expressed as ; Time period Inside The characteristic parameters of the metering performance of the charging pile can be the total indication value, the charging pile indication value and the time period. Calculated, time period The specific values ​​of the characteristic parameters within can be stored in the characteristic data set.

[0023] in, Indicates time period Inside The output power of the charging pile is For time period of No. Charging pile power indication value, represents the i-th time period, for The rectification loss of the charging pile.

[0024] S104, extracting characteristic parameter data covering meter-pile metering performance of all charging piles from the characteristic data set, taking the mean of the characteristic parameter data as the total metering performance parameter, and judging whether the total metering performance is qualified based on the position of the total metering performance parameter in the normal distribution of the charging pile historical test data; The characteristic parameter data of the meter-pile metering performance covering all charging piles within a period of time t are extracted from the characteristic data set and the average is taken as the total metering performance parameter.

[0025] For example, taking a DC charging station with 6 charging piles as an example, the first group of characteristic parameter data covering the meter-pile metering performance of all charging piles is extracted in the time span t, and the total metering performance parameter is calculated according to the following formula: : ; Extract the remaining The group covers the characteristic parameter data of all charging piles and obtains the total meter measurement performance parameters , and calculate the final total meter performance parameters .

[0026] It should be understood that all charging piles in the same charging station have the same model and the same operating environment, and the metering performance should follow the same distribution and the distribution mean should be 0. At the same time, the vast majority of charging piles should maintain normal metering performance within the time span t, and only a few charging piles have abnormal metering performance. Therefore, after the average calculation of the characteristic parameter data of the meter-pile metering performance of m groups, , i.e. parameter It can effectively characterize the total meter measurement performance.

[0027] The charging pile historical test data is the historical data of testing the DC charging pile and the master meter, including the test data before the DC charging station is put into use, fault test data, etc.

[0028] Specifically, the characteristic parameter data of the meter-pile metering performance are averaged to obtain the total meter metering performance parameter; The numerical distribution of characteristic parameters is formed based on the historical test data of charging piles , numerical distribution The mean value of , the variance is ; according to Principle, when the total meter performance parameter is in range, the total meter measurement performance is judged to be qualified. When the total meter measurement performance parameters are within range, and determine that the total meter measurement performance is unqualified.

[0029] S105, extracting meter-pile paired metering data whose total metering performance is judged to be qualified from the feature data set, identifying abnormal values ​​in the meter-pile paired metering data through a symmetrically optimized box plot anomaly detection algorithm, and locating charging piles with abnormal metering performance.

[0030] Optionally, extract meter-pile paired metering data with qualified total meter metering performance from the feature data set to form a data set , dataset The number of data in the data set is X, and the data is symmetrically replicated with 0 as the center to form an extended data set , expand the dataset , the number of data in the extended data set is 2X; Based on the box plot principle, calculate the limit of normal data; ;

[0031] In the formula, for , is the lower quartile, is the upper quartile, is the interquartile range, is the normal data cap, It is the lower limit of normal data; Identify extended data sets based on the upper and lower limits of normal data The abnormal values ​​in the data are detected, and the charging piles with abnormal metering performance are located according to the sources of the abnormal values.

[0032] In this embodiment, by selecting meter-pile paired metering data, constructing equations to extract characteristic parameters that characterize meter-pile metering performance, and quantifying characteristic parameters, the metering performance of the total meter is judged based on the distribution of the mean of the characteristic parameters of meter-pile metering performance in historical test data, and the abnormal values ​​are identified through the symmetrically optimized box plot anomaly detection algorithm to locate charging piles with abnormal metering performance. Not only can the online detection and positioning of abnormal DC charging piles and abnormal total meters be achieved, but the detection efficiency is high, the cost is low, and the real-time detection requirements can be met. In this way, deviations in charging power settlement are avoided, the fairness of power trade is guaranteed, and problems such as aging and failure of charging pile components can be discovered in a timely manner to ensure personal and property safety.

[0033] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0034] Figure 2 A schematic diagram of a DC charging pile abnormality detection system 20 provided in an embodiment of the present invention, the system 20 includes: The data screening module 210 is used to obtain the electric energy metering data of each DC charging pile in the charging station during operation, and select the electric energy indication of the total meter in the station and the electric energy indication of the charging pile in operation during the same period to form meter-pile paired metering data; Preferably, the total meter power indication in the station during the time period when only one charging pile is in operation is paired with the power indication of the operating charging pile to form a meter-pile paired metering data set.

[0035] The parameter extraction module 220 is used to construct a meter-pile metering error coefficient solution equation for the whole charging process loss of the charging pile based on the meter-pile paired metering data, and extract characteristic parameters representing the meter-pile metering performance in the solution equation; Among them, the equation for solving the meter-pile measurement error coefficient is expressed as: ; (1) Based on the known quantities in the solution equation, the characteristic parameters characterizing the metering performance of the meter-pile are expressed as: (2) In the formula, , They are respectively the general table, The measurement error coefficient of the charging pile is For time period The total meter electric energy indication value, for The rectification loss of the charging pile is For time period of No. Charging pile power indication value, The other losses during this charging are negligible compared to the energy consumed during charging. Characteristic parameters used to characterize the meter-pile measurement performance.

[0036] The parameter quantization module 230 is used to construct a rectification loss mathematical model, quantify unknown parameters in the characteristic parameters of the metering performance of the table-pile based on the rectification loss mathematical model, and solve the specific values ​​of the characteristic parameters, and store the specific values ​​in the characteristic data set; Among them, the time period Inside The output power of the charging pile is expressed as: , the mathematical model of rectification loss is expressed as: ; The quantified charging pile electric energy value and the rectification loss of the charging pile Input formula (2) to solve the specific value of the characteristic parameter; in, Indicates time period Inside The output power of the charging pile is For time period of No. Charging pile power indication value, represents the i-th time period, for The rectification loss of the charging pile.

[0037] The total meter detection module 240 is used to extract characteristic parameter data covering meter-pile metering performance of all charging piles from the characteristic data set, take the mean of the characteristic parameter data as the total meter metering performance parameter, and judge whether the total meter metering performance is qualified based on the position of the total meter metering performance parameter in the normal distribution of the charging pile historical test data; Specifically, judging whether the total metering performance is qualified based on the position of the total metering performance parameter in the normal distribution of the charging pile historical test data includes: The characteristic parameter data of meter-pile metering performance are averaged to obtain the total meter metering performance parameter; The numerical distribution of characteristic parameters is formed based on the historical test data of charging piles , numerical distribution The mean value of , the variance is ; according to Principle, when the total meter performance parameter is in range, the total meter measurement performance is judged to be qualified. When the total meter measurement performance parameters are within range, and determine that the total meter measurement performance is unqualified.

[0038] The charging pile detection module 250 is used to extract the meter-pile paired metering data whose total meter metering performance is judged to be qualified in the feature data set, identify the abnormal values ​​in the meter-pile paired metering data through the symmetrically optimized box plot anomaly detection algorithm, and locate the charging piles with abnormal metering performance.

[0039] Optionally, the charging pile detection module 250 includes: Symmetric expansion unit, used to extract meter-pile paired metering data with qualified total meter metering performance from the feature data set to form a data set , dataset The number of data in the data set is X, and the data is symmetrically replicated with 0 as the center to form an extended data set , expand the dataset , the number of data in the extended data set is 2X; A limit value calculation unit is used to calculate the limit value of normal data based on the box plot principle; ;

[0040] In the formula, for , is the lower quartile, is the upper quartile, is the interquartile range, is the normal data cap, It is the lower limit of normal data; Anomaly identification unit, used to identify extended data sets based on the upper and lower limits of normal data The abnormal values ​​in the data are detected, and the charging piles with abnormal metering performance are located according to the sources of the abnormal values.

[0041] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0042] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is used for detecting abnormal performance of charging pile metering. Figure 3 As shown, the electronic device 3 of this embodiment includes: a memory 310, a processor 320 and a system bus 330, wherein the memory 310 includes an executable program 3101 stored thereon, and those skilled in the art can understand that Figure 3The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0043] Combine the following Figure 3 A detailed introduction to the various components of electronic equipment: The memory 310 can be used to store software programs and modules. The processor 320 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 310. The memory 310 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device (such as cache data), etc. In addition, the memory 310 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0044] The executable program 3101 of the network request method is included in the memory 310, and the executable program 3101 can be divided into one or more modules / units, which are stored in the memory 310 and executed by the processor 320 to realize abnormal detection and positioning of charging piles, etc. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the executable program 3101 in the electronic device 3. For example, the executable program 3101 can be divided into functional modules such as a data screening module, a parameter extraction module, a parameter quantization module, a total table detection module, and a charging pile detection module.

[0045] The processor 320 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 310, and calling data stored in the memory 310, it performs various functions of the electronic device and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 320 may include one or more processing units; preferably, the processor 320 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 320.

[0046] The system bus 330 is used to connect the various functional components inside the computer, and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, CAN bus, etc. The instructions of the processor 320 are transmitted to the memory 310 through the bus, and the memory 310 feeds back data to the processor 320. The system bus 330 is responsible for the data and instruction exchange between the processor 320 and the memory 310. Of course, the system bus 330 can also be connected to other devices, such as network interfaces, display devices, etc.

[0047] In the embodiment of the present invention, the executable program executed by the processor 320 included in the electronic device includes: Obtain the electric energy metering data of each DC charging pile in the charging station during operation, and select the total meter electric energy indication of the station and the electric energy indication of the running charging pile in the same period to form meter-pile paired metering data; Based on the meter-pile paired metering data, a meter-pile metering error coefficient solution equation for the whole charging process loss of the charging pile is constructed, and characteristic parameters characterizing the meter-pile metering performance in the solution equation are extracted; Constructing a rectification loss mathematical model, quantifying unknown parameters in characteristic parameters of meter-pile metering performance based on the rectification loss mathematical model, solving specific values ​​of the characteristic parameters, and storing the specific values ​​in a characteristic data set; Extract characteristic parameter data covering meter-pile metering performance of all charging piles from the characteristic data set, take the mean of the characteristic parameter data as the total meter metering performance parameter, and judge whether the total meter metering performance is qualified based on the position of the total meter metering performance parameter in the normal distribution of the charging pile historical test data; The meter-pile paired metering data whose total metering performance is judged to be qualified in the feature data set are extracted, and the outliers in the meter-pile paired metering data are identified through the symmetrically optimized box plot anomaly detection algorithm, and the charging piles with abnormal metering performance are located.

[0048] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0049] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0050] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A DC charging pile abnormality detection method, characterized in that: include: Obtain the electric energy metering data of each DC charging pile in the charging station during operation, and select the total meter electric energy indication of the station and the electric energy indication of the running charging pile in the same period to form meter-pile paired metering data; Based on the meter-pile paired metering data, a meter-pile metering error coefficient solution equation for the whole charging process loss of the charging pile is constructed, and characteristic parameters characterizing the meter-pile metering performance in the solution equation are extracted; Constructing a rectification loss mathematical model, quantifying unknown parameters in characteristic parameters of meter-pile metering performance based on the rectification loss mathematical model, solving specific values ​​of the characteristic parameters, and storing the specific values ​​in a characteristic data set; Extract characteristic parameter data covering meter-pile metering performance of all charging piles from the characteristic data set, take the mean of the characteristic parameter data as the total meter metering performance parameter, and judge whether the total meter metering performance is qualified based on the position of the total meter metering performance parameter in the normal distribution of the charging pile historical test data; The meter-pile paired metering data whose total metering performance is judged to be qualified in the feature data set are extracted, and the outliers in the meter-pile paired metering data are identified through the symmetrically optimized box plot anomaly detection algorithm, and the charging piles with abnormal metering performance are located.

2. The method according to claim 1, characterized in that The selection of the total meter power indication in the station and the running charging pile power indication in the same period to form the meter-pile pairing metering data includes: The total meter power indication in the station during the time period when only one charging pile is in operation is paired with the power indication of the operating charging pile to form a meter-pile paired metering data set.

3. The method according to claim 1, characterized in that Based on the meter-pile paired metering data, the meter-pile metering error coefficient solution equation of the charging pile charging loss during the whole process is constructed, and the characteristic parameters characterizing the meter-pile metering performance in the solution equation are extracted, including: The equation for solving the meter-pile measurement error coefficient is expressed as: ；（1） Based on the known quantities in the solution equation, the characteristic parameters characterizing the metering performance of the meter-pile are expressed as: （2） In the formula, , They are respectively the general table, The measurement error coefficient of the charging pile is For time period The total meter electric energy indication value, for The rectification loss of the charging pile is For time period of Charging pile power indication value, is the other loss during this charging, Characteristic parameters used to characterize the meter-pile measurement performance.

4. The method according to claim 3, characterized in that The method of constructing a rectification loss mathematical model, quantifying unknown parameters in characteristic parameters of meter-pile metering performance based on the rectification loss mathematical model, and solving specific values ​​of the characteristic parameters includes: Set time period Inside The output power of the charging pile is expressed as: , the mathematical model of rectification loss is expressed as: ; The quantified charging pile electric energy value and the rectification loss of the charging pile Input formula (2) to solve the table-specific values ​​of characteristic parameters of pile measurement performance; In the formula, Indicates time period Inside The output power of the charging pile is For time period of Charging pile power indication value, represents the i-th time period, for The rectification loss of the charging pile.

5. The method according to claim 1, characterized in that The determining whether the total metering performance is qualified based on the position of the total metering performance parameter in the normal distribution of the charging pile historical test data includes: The characteristic parameter data of meter-pile metering performance are averaged to obtain the total meter metering performance parameter; The numerical distribution of characteristic parameters is formed based on the historical test data of charging piles , numerical distribution The mean value of , the variance is ; according to Principle, when the total meter performance parameter is in range, the total meter measurement performance is judged to be qualified. When the total meter measurement performance parameters are within range, and determine that the total meter measurement performance is unqualified.

6. The method according to claim 1, characterized in that The method of identifying abnormal values ​​in meter-pile paired metering data by using a symmetrically optimized box plot anomaly detection algorithm and locating charging piles with abnormal metering performance includes: Extract meter-pile paired metering data with qualified total meter metering performance from the feature data set to form a data set , dataset The number of data in the data set is X, and the data is symmetrically replicated with 0 as the center to form an extended data set , expand the dataset , the number of data in the extended data set is 2X; Based on the box plot principle, calculate the limit of normal data; ； In the formula, for , is the lower quartile, is the upper quartile, is the interquartile range, is the normal data cap, It is the lower limit of normal data; Identify extended data sets based on the upper and lower limits of normal data The abnormal values ​​in the data are detected, and the charging piles with abnormal metering performance are located according to the sources of the abnormal values.

7. A DC charging pile abnormality detection system, characterized in that: include: The data screening module is used to obtain the electric energy metering data of each DC charging pile in the charging station during operation, and select the electric energy indication of the total meter in the station and the electric energy indication of the charging pile in operation during the same period to form the meter-pile paired metering data; A parameter extraction module is used to construct a meter-pile measurement error coefficient solution equation for the whole charging process loss of the charging pile based on the meter-pile pairing measurement data, and extract characteristic parameters characterizing the meter-pile measurement performance in the solution equation; The parameter quantification module is used to construct a rectification loss mathematical model, quantify the unknown parameters in the characteristic parameters of the metering performance of the table-pile based on the rectification loss mathematical model, and solve the specific values ​​of the characteristic parameters, and store the specific values ​​in the characteristic data set; The total meter detection module is used to extract characteristic parameter data covering the meter-pile metering performance of all charging piles from the characteristic data set, take the mean of the characteristic parameter data as the total meter metering performance parameter, and judge whether the total meter metering performance is qualified based on the position of the total meter metering performance parameter in the normal distribution of the charging pile historical test data; The charging pile detection module is used to extract the meter-pile paired metering data whose total metering performance is judged to be qualified in the feature data set, identify the outliers in the meter-pile paired metering data through the symmetrically optimized box plot anomaly detection algorithm, and locate the charging piles with abnormal metering performance.

8. The system according to claim 7, characterized in that The method of identifying abnormal values ​​in meter-pile paired metering data by using a symmetrically optimized box plot anomaly detection algorithm and locating charging piles with abnormal metering performance includes: Extract meter-pile paired metering data with qualified total meter metering performance from the feature data set to form a data set , dataset The number of data in the data set is X, and the data is symmetrically replicated with 0 as the center to form an extended data set , expand the dataset , the number of data in the extended data set is 2X; Based on the box plot principle, calculate the limit of normal data; ； In the formula, for , is the lower quartile, is the upper quartile, is the interquartile range, is the normal data cap, It is the lower limit of normal data; Identify extended data sets based on the upper and lower limits of normal data The abnormal values ​​in the data are detected, and the charging piles with abnormal metering performance are located according to the sources of the abnormal values.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the DC charging pile abnormality detection method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the steps of a DC charging pile abnormality detection method as described in any one of claims 1 to 6 are implemented.

Images