A DC charging pile measurement and verification method, system, device and storage medium

Abstract

The present invention relates to a DC charging pile measurement and verification method, system, equipment and storage medium. The measurement and verification method comprises the following steps: collecting charging data of electric vehicles of different models on the same charging pile, and preprocessing the collected charging data; collecting charging data of metering meters of all electric vehicles, and calculating the basic charging error of the charging pile based on the charging data of the metering meters of each electric vehicle and the charging data of the charging pile; classifying the charging data of the charging pile under different charging modes by using an improved Gaussian mixture model; calculating the error contribution of each charging mode by using the charging data of the charging pile under each charging mode, and then calculating the final charging error of the charging pile under each charging mode based on the error contribution of each charging mode and the basic charging error of the charging pile.

Description

Technical Field

[0001] The present invention relates to a DC charging pile measurement and verification method, system, equipment and storage medium, belonging to the technical field of electric energy measurement. Background Art

[0002] Since the accuracy of charging pile metering directly affects the settlement of charging fees, any small metering deviation may accumulate into huge economic losses in the context of large-scale transactions, which may not only damage the legitimate rights and interests of consumers, but also bring operational burdens to power grid operating companies. To this end, the measures generally taken by the industry and outside are to regularly calibrate the on-site metering performance of DC charging piles one by one to ensure that the metering accuracy of each charging pile meets the standard. This verification work is tedious and meticulous. Not only does it require professionals to carry standard verification equipment to the locations of various charging piles, but it also needs to take into account the actual situation of the wide distribution of charging piles and different environments. It is undoubtedly a time-consuming, labor-intensive and costly task.

[0003] The invention patent with the announcement number "CN112505386B" discloses a method and system for calibrating the current value of a DC charging pile. The invention method includes the following steps: determine the interpolated and expanded current / voltage data, and the influencing characteristics affected by different environmental conditions; determine the voltage / current influencing factor matrix and the measurement error matrix according to the influencing characteristics; establish a correction model for the influence of the measured voltage / current on the influencing factor matrix and the measurement error matrix; correct the current / voltage according to the correction model, and determine the ripple influencing factor matrix and error matrix of the corrected current / voltage according to the corrected current / voltage; establish an error model according to the ripple influencing factor matrix and error matrix of the corrected current / voltage; determine the DC charging pile current value according to the error model. This invention realizes the anti-interference calibration of the voltage and current of the calibration device under the on-site environmental conditions.

[0004] However, the above scheme is not comprehensive enough in considering the error influencing conditions, resulting in insufficient accuracy of the error calculation results. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention proposes a DC charging pile measurement and calibration method, system, equipment and storage medium.

[0006] The technical solution of the present invention is as follows:

[0007] In one aspect, the present invention provides a DC charging pile measurement and verification method, comprising the following steps:

[0008] Collect charging data of electric vehicles of different models on the same charging pile, and pre-process the collected charging data;

[0009] Collect charging data from all electric vehicle meters, and calculate the basic charging error of the charging pile based on the charging data from each electric vehicle meter and the charging pile data;

[0010] The charging data of charging piles under different charging modes are classified by using an improved Gaussian mixture model;

[0011] The error contribution of each charging mode is calculated through the charging data of the charging pile under each charging mode, and then the final charging error of the charging pile under each charging mode is calculated based on the error contribution of each charging mode and the basic charging error of the charging pile.

[0012] As a preferred embodiment of the present invention, the preprocessing steps of the collected charging data are:

[0013] The collected charging data is constructed into a sample set and normalized, as shown in the following formula:

[0014]

[0015] in: represents any sample in the sample set; represents a sample set; represents the sample mean;

[0016] Build an autoencoder model, define the input layer, hidden layer and output layer of the autoencoder model, select the sigmoid activation function, use the root mean square error of the prediction residual as the loss function, and use the Adam optimizer to update the network weights;

[0017] The normalized sample set is input into the autoencoder model for outlier cleaning, as shown in the following formula:

[0018]

[0019] in: Indicates the first The actual value of samples; represents the first Sample prediction value; Represents the standard deviation of the sample set; replace the sample mean with the outlier to complete the outlier cleaning.

[0020] As a preferred embodiment of the present invention, the specific calculation steps of the charging pile basic charging error are:

[0021] Calculate the error between the charging data of the same charging pile and the charging data of each electric vehicle meter, and construct a normal distribution model , as shown in the following formula:

[0022]

[0023] in: represents the expectation of the error distribution; represents the variance of the error distribution;

[0024] The error data with a distribution probability greater than 50% are selected to construct an error sample set and the error sample set is averaged. According to the central limit theorem, the mean is used as the basic charging error of the charging pile. , as shown in the following formula:

[0025]

[0026] in: Represents the number of samples in the error sample set; represents the first samples.

[0027] As a preferred embodiment of the present invention, the charging pile charging data includes voltage data, current data and battery capacity data, and the charging mode classification steps are:

[0028] A variable sliding window is set to perform sliding average processing on the voltage data, current data and battery capacity data in the charging data of the charging pile, as shown in the following formula:

[0029]

[0030] in: Represents the charging data of any type of charging pile after sliding average processing; Indicates the charging data length of the charging pile; Indicates the sliding window length; Indicates the charging data of this type of charging pile. samples; Indicates the number of sliding windows;

[0031] Based on the voltage data, current data and battery capacity data after sliding average processing, the weight coefficients of the voltage data, current data and battery capacity data in different charging modes are calculated, as shown in the following formula:

[0032]

[0033]

[0034]

[0035] in: , , Respectively represent the weight coefficients of voltage data, current data and battery capacity data in the current charging mode; Indicates the number of samples of each type of data after sliding average processing; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples;

[0036] Based on the voltage data, current data and battery capacity data after the above sliding average processing and their corresponding weight coefficients, the Gaussian mixture model is constructed as shown in the following formula:

[0037]

[0038] in: represents the output of the Gaussian mixture model;

[0039] Then input the output of the Gaussian mixture model into the multilayer perceptron, as shown in the following formula:

[0040]

[0041] in: represents a multi-layer perceptron; Represents the output of a multilayer perceptron; Represents the parameters of the multilayer perceptron;

[0042] Then pass the output of the multi-layer perceptron through The function calculates the probability output that the charging pile belongs to the current charging mode, as shown in the following formula:

[0043]

[0044] in: Indicates the probability output that the charging pile belongs to the current charging mode;

[0045] Based on the probability output of all charging modes of the charging pile, the probability value of the charging pile belonging to each charging mode is obtained, as shown in the following formula:

[0046]

[0047] in: Respectively represent the probability of the charging pile in fast, medium and slow charging modes; Indicates the charging mode of the charging pile.

[0048] As a preferred embodiment of the present invention, the error contribution calculation formula of each charging mode is:

[0049]

[0050]

[0051]

[0052] in: , , Respectively represent the error contribution of fast, medium and slow charging modes; Represents the mean value of charging pile charging data after sliding average processing; , , Respectively represent the mean values ​​of voltage data after sliding average processing belonging to fast, medium and slow charging modes; , , Respectively represent the mean current data after sliding average processing belonging to fast, medium and slow charging modes; , , Respectively represent the mean values ​​of battery capacity data after sliding average processing belonging to fast, medium and slow charging modes.

[0053] As a preferred embodiment of the present invention, the final charging error calculation formula of the charging pile is:

[0054]

[0055]

[0056]

[0057] in: , , Respectively represent the final charging errors of the charging pile in fast, medium and slow charging modes.

[0058] On the other hand, the present invention also provides a DC charging pile measurement and verification system, characterized in that it includes a data acquisition module, a basic error calculation module, a charging mode classification module and a final error calculation module;

[0059] The data acquisition module is used to collect charging data of electric vehicles of different models on the same charging pile, and pre-process the collected charging data;

[0060] The basic error calculation module is used to collect charging data from all electric vehicle metering meters, and calculate the basic charging error of the charging pile based on the charging data from the metering meter of each electric vehicle and the charging data from the charging pile;

[0061] The charging mode classification module is used to classify charging data of charging piles under different charging modes through an improved Gaussian mixture model;

[0062] The final error calculation module is used to calculate the error contribution of each charging mode through the charging data of the charging pile under each charging mode, and then calculate the final charging error of the charging pile under each charging mode based on the error contribution of each charging mode and the basic charging error of the charging pile.

[0063] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0064] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0065] The present invention has the following beneficial effects:

[0066] 1. The present invention improves the accuracy level of the electric energy meter of the electric vehicle according to the central limit theorem analysis, and obtains the basic error of the charging pile; processes each variable data by means of sliding average, and then uses the processed variable data to adaptively set the weight coefficient based on the sensitivity of the charging mode, constructs a feature matrix and inputs it into the Gaussian mixture model to identify the charging mode; calculates the mode coefficient under the corresponding charging mode, reduces the influence of different charging modes on the error, and improves the error measurement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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.

[0069] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0070] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0071] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0072] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0073] Embodiment 1:

[0074] See also Figure 1 , a DC charging pile measurement and verification method, comprising the following steps:

[0075] Collect charging data of electric vehicles of different models on the same charging pile, and pre-process the collected charging data;

[0076] Collect charging data from all electric vehicle meters, and calculate the basic charging error of the charging pile based on the charging data from each electric vehicle meter and the charging pile data;

[0077] The charging data of charging piles under different charging modes are classified by using an improved Gaussian mixture model;

[0078] The error contribution of each charging mode is calculated through the charging data of the charging pile under each charging mode, and then the final charging error of the charging pile under each charging mode is calculated based on the error contribution of each charging mode and the basic charging error of the charging pile.

[0079] As a preferred implementation of this embodiment, the preprocessing steps of the collected charging data are:

[0080] Perform preliminary data cleaning on the collected data to ensure data accuracy, avoid outliers from affecting the prediction accuracy of subsequent models, and improve the robustness of the model and enhance its adaptability. Since the charging power is closely related to the capacity and remaining power of the electric vehicle battery, the power will gradually decrease as the charging time increases. Therefore, through deep learning algorithms, trend prediction of charging pile and electric vehicle data is carried out to identify outliers.

[0081] The collected charging data is constructed into a sample set and normalized, as shown in the following formula:

[0082]

[0083] in: represents any sample in the sample set; represents a sample set; represents the sample mean;

[0084] Build an autoencoder model, define the input layer, hidden layer and output layer of the autoencoder model, select the sigmoid activation function, use the root mean square error of the prediction residual as the loss function, and use the Adam optimizer to update the network weights;

[0085] The normalized sample set is input into the autoencoder model for outlier cleaning, as shown in the following formula:

[0086]

[0087] in: Indicates the first The actual value of samples; represents the first Sample prediction value; Represents the standard deviation of the sample set; replace the sample mean with the outlier to complete the outlier cleaning.

[0088] As a preferred implementation of this embodiment, the specific calculation steps of the charging pile basic charging error are:

[0089] Since the accuracy level of a single ordinary electric vehicle meter is low, usually lower than the accuracy level of the calibration device, its calibration error data can only reflect its own error. In the physical method, a physical standard meter with a higher accuracy level than the calibration device is used for calibration to verify the calibration device. According to the central limit theorem, The average of the calibration data of ordinary smart energy meters produced in the same batch can be regarded as the calibration data of the virtual standard energy meter, and the accuracy level of the virtual standard energy meter is higher than that of a single ordinary energy meter. Times. If it is large enough, the accuracy level of the virtual standard electric energy meter can reach the accuracy level of the standard electric energy meter in the physical method, and can be used for the verification of electric energy meters;

[0090] Calculate the error between the charging data of the same charging pile and the charging data of each electric vehicle meter, assuming that its distribution conforms to the normal distribution, and construct a normal distribution model , as shown in the following formula:

[0091]

[0092] in: represents the expectation of the error distribution; represents the variance of the error distribution;

[0093] The error data with a distribution probability greater than 50% are selected to construct an error sample set and the error sample set is averaged. According to the central limit theorem, the mean is used as the basic charging error of the charging pile. , as shown in the following formula:

[0094]

[0095] in: Represents the number of samples in the error sample set; represents the first samples;

[0096] The basic charging error of the charging pile That is the virtual standard electricity meter.

[0097] As a preferred implementation of this embodiment, the charging pile charging data includes voltage data, current data and battery capacity data, and the charging mode classification steps are:

[0098] The current-voltage trajectory during the charging process is an intuitive feature that can clearly show the changing trend of the charging mode. However, the power difference between adjacent charging piles may also interfere with the charging mode identification of a single charging pile. Extract the voltage, current, battery capacity, and temperature data during the charging process of the charging pile, set a variable sliding window, perform sliding average processing on each type of data, and then calculate the correlation between each type of data and the charging mode after processing with windows of different lengths. Select the length of the window with the strongest correlation to enhance the variable distinction under each type of charging mode;

[0099] A variable sliding window is set to perform sliding average processing on the voltage data, current data and battery capacity data in the charging data of the charging pile, as shown in the following formula:

[0100]

[0101] in: Represents the charging data of any type of charging pile after sliding average processing; Indicates the charging data length of the charging pile; Indicates the sliding window length; Indicates the charging data of this type of charging pile. samples; Indicates the number of sliding windows;

[0102] Based on the voltage data, current data and battery capacity data after sliding average processing, the weight coefficients of the voltage data, current data and battery capacity data in different charging modes are calculated, as shown in the following formula:

[0103]

[0104]

[0105]

[0106] in: , , Respectively represent the weight coefficients of voltage data, current data and battery capacity data in the current charging mode; Indicates the number of samples of each type of data after sliding average processing; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples;

[0107] Based on the voltage data, current data and battery capacity data after the above sliding average processing and their corresponding weight coefficients, the Gaussian mixture model is constructed as shown in the following formula:

[0108]

[0109] in: represents the output of the Gaussian mixture model;

[0110] Then input the output of the Gaussian mixture model into the multilayer perceptron, as shown in the following formula:

[0111]

[0112] in: represents a multi-layer perceptron; Represents the output of a multilayer perceptron; Represents the parameters of the multilayer perceptron;

[0113] Then pass the output of the multi-layer perceptron through The function calculates the probability output that the charging pile belongs to the current charging mode, as shown in the following formula:

[0114]

[0115] in: Indicates the probability output that the charging pile belongs to the current charging mode;

[0116] Based on the probability output of all charging modes of the charging pile, the probability value of the charging pile belonging to each charging mode is obtained, as shown in the following formula:

[0117]

[0118] in: Respectively represent the probability of the charging pile in fast, medium and slow charging modes; Indicates the charging mode of the charging pile.

[0119] As a preferred implementation of this embodiment, the error contribution calculation formula of each charging mode is:

[0120]

[0121]

[0122]

[0123] in: , , Respectively represent the error contribution of fast, medium and slow charging modes; Represents the mean value of charging pile charging data after sliding average processing; , , Respectively represent the mean values ​​of voltage data after sliding average processing belonging to fast, medium and slow charging modes; , , Respectively represent the mean current data after sliding average processing belonging to fast, medium and slow charging modes; , , Respectively represent the mean values ​​of battery capacity data after sliding average processing belonging to fast, medium and slow charging modes.

[0124] As a preferred implementation of this embodiment, the final charging error calculation formula of the charging pile is:

[0125]

[0126]

[0127]

[0128] in: , , Respectively represent the final charging errors of the charging pile in fast, medium and slow charging modes.

[0129] Embodiment 2:

[0130] A DC charging pile measurement and verification system includes a data acquisition module, a basic error calculation module, a charging mode classification module and a final error calculation module;

[0131] The data acquisition module is used to collect charging data of electric vehicles of different models on the same charging pile, and pre-process the collected charging data;

[0132] The basic error calculation module is used to collect charging data from all electric vehicle metering meters, and calculate the basic charging error of the charging pile based on the charging data from the metering meter of each electric vehicle and the charging data from the charging pile;

[0133] The charging mode classification module is used to classify charging data of charging piles under different charging modes through an improved Gaussian mixture model;

[0134] The final error calculation module is used to calculate the error contribution of each charging mode through the charging data of the charging pile under each charging mode, and then calculate the final charging error of the charging pile under each charging mode based on the error contribution of each charging mode and the basic charging error of the charging pile.

[0135] This system is used to implement the functions in the first embodiment, which will not be described in detail here.

[0136] Embodiment three:

[0137] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the DC charging pile measurement and verification method as described in any embodiment of the present invention is implemented.

[0138] Embodiment 4:

[0139] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the DC charging pile measurement and verification method as described in any embodiment of the present invention is implemented.

[0140] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0141] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] 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 units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0143] In several embodiments provided in the present application, if any function is implemented in the form of 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 application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0144] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A DC charging pile measurement and verification method, characterized in that: The following steps are involved: Collect charging data of electric vehicles of different models on the same charging pile, and pre-process the collected charging data; Collect charging data from all electric vehicle meters, and calculate the basic charging error of the charging pile based on the charging data from each electric vehicle meter and the charging pile data; The charging data of charging piles under different charging modes are classified by using an improved Gaussian mixture model; The error contribution of each charging mode is calculated through the charging data of the charging pile under each charging mode, and then the final charging error of the charging pile under each charging mode is calculated based on the error contribution of each charging mode and the basic charging error of the charging pile; The charging pile charging data includes voltage data, current data and battery capacity data, and the charging mode classification steps are as follows: A variable sliding window is set to perform sliding average processing on the voltage data, current data and battery capacity data in the charging data of the charging pile, as shown in the following formula: in: Represents the charging data of any type of charging pile after sliding average processing; Indicates the charging data length of the charging pile; Indicates the sliding window length; Indicates the charging data of this type of charging pile. samples; Indicates the number of sliding windows; Based on the voltage data, current data and battery capacity data after sliding average processing, the weight coefficients of the voltage data, current data and battery capacity data in different charging modes are calculated, as shown in the following formula: in: , , Respectively represent the weight coefficients of voltage data, current data and battery capacity data in the current charging mode; Indicates the number of samples of each type of data after sliding average processing; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples; Based on the voltage data, current data and battery capacity data after the above sliding average processing and their corresponding weight coefficients, the Gaussian mixture model is constructed as shown in the following formula: in: represents the output of the Gaussian mixture model; Then input the output of the Gaussian mixture model into the multilayer perceptron, as shown in the following formula: in: represents a multi-layer perceptron; Represents the output of a multilayer perceptron; Represents the parameters of the multilayer perceptron; Then pass the output of the multi-layer perceptron through The function calculates the probability output that the charging pile belongs to the current charging mode, as shown in the following formula: in: Indicates the probability output that the charging pile belongs to the current charging mode; Based on the probability output of all charging modes of the charging pile, the probability value of the charging pile belonging to each charging mode is obtained, as shown in the following formula: in: Respectively represent the probability of the charging pile in fast, medium and slow charging modes; Indicates the charging mode of the charging pile.

2. A DC charging pile measurement and verification method according to claim 1, characterized in that: The preprocessing steps of the collected charging data are: The collected charging data is constructed into a sample set and normalized, as shown in the following formula: in: represents any sample in the sample set; represents a sample set; represents the sample mean; Build an autoencoder model, define the input layer, hidden layer and output layer of the autoencoder model, select the sigmoid activation function, use the root mean square error of the prediction residual as the loss function, and use the Adam optimizer to update the network weights; The normalized sample set is input into the autoencoder model for outlier cleaning, as shown in the following formula: in: Indicates the first The actual value of samples; represents the first Sample prediction value; Represents the standard deviation of the sample set; replace the sample mean with the outlier to complete the outlier cleaning.

3. A DC charging pile measurement and verification method according to claim 1, characterized in that: The specific calculation steps of the charging pile basic charging error are: Calculate the error between the charging data of the same charging pile and the charging data of each electric vehicle meter, and construct a normal distribution model , as shown in the following formula: in: represents the expectation of the error distribution; represents the variance of the error distribution; The error data with a distribution probability greater than 50% are selected to construct an error sample set and the error sample set is averaged. According to the central limit theorem, the mean is used as the basic charging error of the charging pile. , as shown in the following formula: in: Represents the number of samples in the error sample set; represents the first samples.

4. A DC charging pile measurement and verification method according to claim 1, characterized in that: The error contribution calculation formula of each charging mode is: in: , , Respectively represent the error contribution of fast, medium and slow charging modes; Represents the mean value of charging pile charging data after sliding average processing; , , Respectively represent the mean values ​​of voltage data after sliding average processing belonging to fast, medium and slow charging modes; , , Respectively represent the mean current data after sliding average processing belonging to fast, medium and slow charging modes; , , Respectively represent the mean values ​​of battery capacity data after sliding average processing belonging to fast, medium and slow charging modes.

5. A DC charging pile measurement and verification method according to claim 4, characterized in that: The final charging error calculation formula of the charging pile is: in: , , Respectively represent the final charging errors of the charging pile in fast, medium and slow charging modes.

6. A DC charging pile measurement and verification system, characterized in that: It includes a data acquisition module, a basic error calculation module, a charging mode classification module and a final error calculation module; The data acquisition module is used to collect charging data of electric vehicles of different models on the same charging pile, and pre-process the collected charging data; The basic error calculation module is used to collect charging data of all electric vehicle metering meters, and calculate the basic charging error of the charging pile based on the charging data of the metering meter of each electric vehicle and the charging data of the charging pile, wherein the charging data of the charging pile includes voltage data, current data and battery capacity data; The charging mode classification module is used to classify the charging data of charging piles under different charging modes through an improved Gaussian mixture model. The charging mode classification steps are as follows: A variable sliding window is set to perform sliding average processing on the voltage data, current data and battery capacity data in the charging data of the charging pile, as shown in the following formula: in: Represents the charging data of any type of charging pile after sliding average processing; Indicates the charging data length of the charging pile; Indicates the sliding window length; Indicates the charging data of this type of charging pile. samples; Indicates the number of sliding windows; Based on the voltage data, current data and battery capacity data after sliding average processing, the weight coefficients of the voltage data, current data and battery capacity data in different charging modes are calculated, as shown in the following formula: in: , , Respectively represent the weight coefficients of voltage data, current data and battery capacity data in the current charging mode; Indicates the number of samples of each type of data after sliding average processing; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples; , , Respectively represent the voltage data, current data and battery capacity data after sliding average processing. samples; Based on the voltage data, current data and battery capacity data after the above sliding average processing and their corresponding weight coefficients, the Gaussian mixture model is constructed as shown in the following formula: in: represents the output of the Gaussian mixture model; Then input the output of the Gaussian mixture model into the multilayer perceptron, as shown in the following formula: in: represents a multi-layer perceptron; Represents the output of a multilayer perceptron; Represents the parameters of the multilayer perceptron; Then pass the output of the multi-layer perceptron through The function calculates the probability output that the charging pile belongs to the current charging mode, as shown in the following formula: in: Indicates the probability output that the charging pile belongs to the current charging mode; Based on the probability output of all charging modes of the charging pile, the probability value of the charging pile belonging to each charging mode is obtained, as shown in the following formula: in: Respectively represent the probability of the charging pile in fast, medium and slow charging modes; Indicates the charging mode of the charging pile; The final error calculation module is used to calculate the error contribution of each charging mode through the charging data of the charging pile under each charging mode, and then calculate the final charging error of the charging pile under each charging mode based on the error contribution of each charging mode and the basic charging error of the charging pile.

7. 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 program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images