Electric energy meter fault discrimination method based on Deep-SVDD

Abstract

The invention discloses an electric energy meter fault discrimination method based on Deep-SVDD, and relates to the technical field of electric energy metering device fault identification, and the method comprises the steps: obtaining the data of each type of electric energy meter, and constructing a data set based on the data of the electric energy meter; constructing a first hypersphere Q1 based on the data set; adjusting the boundary of the first hyper-sphere Q1, and constructing a second hyper-sphere Q2; performing iterative correction on the second hyper-sphere Q2 to construct a third hyper-sphere Q3; measuring data of the to-be-detected electric energy meter are obtained, the measuring data are judged based on the third hypersphere Q3, a judgment result is obtained, and the problems that an existing electric energy meter fault judgment mode is low in interpretability, low in accuracy and high in computing power dependency degree can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault identification of electric energy metering devices, and in particular to an electric energy meter fault identification method based on Deep-SVDD. Background Art

[0002] As a basic and important part of the electric energy metering device, the state identification and fault identification of the electric energy meter are directly related to the reliability and fairness of electric energy metering. The existing fault identification technology of electric energy meters usually relies on a single data type of voltage and current for analysis and judgment. Although this type of method has good stability, occupies less computing resources, and is suitable for manual troubleshooting and edge computing equipment, the defect is that it does not fully utilize the inherent coupling between various data, and the basis for analysis and judgment is relatively linear, which is prone to misjudgment or missed judgment.

[0003] Although the intelligent algorithm of machine learning is currently used to analyze and judge electricity meter faults, the nonlinear coupling relationship between various data can be utilized to a large extent, but there is excessive coupling and the process is unexplainable. At the same time, the requirements for computing power are too high, which makes it difficult to meet the requirements of explainability, high accuracy and low dependence on computing power in the existing electricity meter fault judgment. Summary of the invention

[0004] In order to solve the problems of low interpretability, low accuracy and high dependence on computing power in the existing electric energy meter fault identification method, the present invention provides an electric energy meter fault identification method based on Deep-SVDD, the method comprising:

[0005] S1. Obtaining electric energy meter data of each model, and constructing a data set based on the electric energy meter data;

[0006] S2, constructing a first hypersphere Q1 based on the data set;

[0007] S3, adjusting the boundary of the first hypersphere Q1 to construct a second hypersphere Q2;

[0008] S4, iteratively modifying the second hypersphere Q2 to construct a third hypersphere Q3;

[0009] S5. Acquire measurement data of the electric energy meter to be detected, and discriminate the measurement data based on the third hypersphere Q3 to obtain a discrimination result.

[0010] Deep-SVDD (Deep One-Class Classification) is an anomaly detection method based on deep learning, which aims to cluster normal samples into a hypersphere through a neural network, while abnormal samples are far away from this hypersphere.

[0011] In the field of machine learning and data mining, a hypersphere is a geometric structure used to represent the minimum norm of all data points in a data set. It refers to the set of all points with a fixed distance from a certain point as the center in n-dimensional space. It is the volume enclosed by the n-dimensional spherical surface, which is called the volume of the n-dimensional sphere.

[0012] The principle of the present invention is to construct a fault hypersphere in a multidimensional space, and to judge whether the electric energy meter to be judged is faulty by analyzing the relationship between the characterization point of the measured data of the electric energy meter to be judged in the multidimensional space and the fault hypersphere. The direct construction of the SVDD hypersphere is decomposed by using three hyperspheres, and the initial hypersphere center and radius are customized to reduce the computational complexity. The coarse construction is performed first and then the fine construction is performed to improve the accuracy of the hypersphere construction. To a certain extent, the situation of computational contradictions caused by too much data and simultaneous input in an iterative situation is reduced. The SVDD hypersphere makes full use of the inherent nonlinear coupling relationship between the various measurement data of the electric energy meter, and effectively improves the accuracy of the fault state judgment of the electric energy meter.

[0013] The first hypersphere is used to locate the multidimensional coordinate system for calculation, which provides an initial input for the entire SVDD and locates the center of the hypersphere at zero, reducing the complexity of the calculation. The second hypersphere is iterated using normal data, roughly constructed based on the first hypersphere, and iteratively calculated on the radius and center of the hypersphere to obtain a hypersphere for judging normal data. The third hypersphere is iterated using a data set with abnormal data, finely constructed based on the second hypersphere, fine-tuned on the radius and center of the hypersphere, and further refined on the edge of the hypersphere to obtain a hypersphere that can judge both normal and abnormal data.

[0014] Using a neural network algorithm to reduce the dimension of the data and map it to a low-dimensional space can increase the accuracy of subsequent hypersphere construction, reduce the computing power requirements for iterative solution of the hypersphere, and reduce the dependence on computing power hardware. It can be better applied to existing edge computing devices and greatly improve the speed of solving fault hyperspheres. At the same time, the algorithm is a black box model algorithm with good interpretability. It is also a data model. The amount of data contained in the power grid is very large. Using neural networks to deal with large amounts of data can perform parallel computing and gradient optimization to achieve faster solutions.

[0015] Moreover, the hypersphere constructed by this method can be used offline and only requires computing power resources during training, which further reduces the dependence on computing power hardware and can be better applied to existing edge computing devices. If new data is added in the subsequent iteration process, the hypersphere is stable and the new data will not affect the historical data. The hypersphere constructed by the historical data can be used as the initial hypersphere for constructing the hypersphere with the new data. Therefore, it is only necessary to input the new data to adjust the hypersphere that has been constructed, so that the hypersphere that judges the abnormal data will be continuously improved, and there is no need to re-calculate with the historical data, which greatly reduces the large amount of calculation time and computing power.

[0016] Furthermore, the electric energy meter data includes normal sample data and misjudgment sample data, and the specific steps of constructing the data set include: dividing the electric energy meter data into a training set and a verification set, and both the training set and the verification set include the normal sample data and the misjudgment sample data.

[0017] Mining the intrinsic value of data, including abnormal and normal user data, will make the subsequent construction of the hypersphere more accurate.

[0018] Furthermore, the specific steps of constructing the first hypersphere Q1 include: constructing the first hypersphere Q1 based on the normal sample data in the training set; and constructing the first hypersphere Q1 by a first calculation formula:

[0019]

[0020] Where R1 represents the radius of the first hypersphere Q1, c1 represents the center of the first hypersphere Q1, subject to represents the restriction condition, and x i represents the i-th normal sample, i represents the sequence number, ‖x i -c1‖ represents x i The distance to c1.

[0021] The multi-dimensional coordinate system used for positioning calculation gives an initial input to the entire SVDD and locates the center of the hypersphere at the zero point, reducing the complexity of the calculation.

[0022] Furthermore, the specific steps of constructing the second hypersphere Q2 include: adjusting the boundary of the first hypersphere Q1 based on a preset slack variable to construct the second hypersphere Q2; and the second calculation formula for constructing the second hypersphere Q2 is:

[0023]

[0024] Among them, R2 represents the radius of the second hypersphere Q2, C represents the weight parameter, subject to represents the restriction condition, and x i′ represents the i′th normal sample, i′ represents the sequence number, ξi′ It represents the allowable deviation of the i′th normal sample, and n represents the number of samples.

[0025] Taking into account the possibility of missing some data and in order to better handle the noise and outliers that may exist in the data set, the boundary of the hypersphere is adjusted so that it can correctly identify the normal state outside the normal data set.

[0026] Furthermore, the specific steps of constructing the third hypersphere Q3 include:

[0027] S401, constructing a first neural network, and obtaining a first midpoint of the third hypersphere Q3 based on the second hypersphere Q2;

[0028] S402, initializing target parameters;

[0029] S403, reducing the dimension of the training set based on the first neural network to obtain reduced-dimensional data;

[0030] S404: based on the target parameter and the dimension reduction data, updating a first parameter of the first neural network to obtain a second parameter, and updating the first neural network based on the second parameter to obtain a second neural network;

[0031] S405, based on the second neural network, updating the first center to obtain a second center;

[0032] S406, obtaining a loss value based on the second center;

[0033] S407, determining whether the loss value is less than a first threshold value, if so, obtaining a first radius based on the second center, and constructing the third hypersphere Q3 based on the second center and the first radius; if not, returning to S403, and updating the first neural network to the second neural network;

[0034] The third calculation formula for constructing the third hypersphere Q3 is:

[0035]

[0036] Where R3 represents the radius of the third hypersphere Q3, c3 represents the center of the third hypersphere Q3, θ represents the parameters of the neural network, and f (θ) () represents a neural network, x i″ represents the sample in the i″th training set after dimensionality reduction, i″ represents the sequence number, λ represents the regularization parameter, and n1 represents the number of samples.

[0037] Based on the second hypersphere, the hypersphere is precisely constructed, the radius and center of the hypersphere are fine-tuned, and the edge of the hypersphere is further refined to obtain a hypersphere that can judge both normal and abnormal data.

[0038] Furthermore, the specific steps of constructing the third hypersphere Q3 also include:

[0039] S408, obtaining a first number of the verification set, verifying the verification set based on the third hypersphere Q3, and obtaining a number of unqualified ones;

[0040] S409, obtaining a non-conforming value based on the first quantity and the non-conforming quantity;

[0041] S410, determining whether the unqualified value is greater than or equal to a second threshold value, if so, adjusting the first parameter to obtain a third parameter, updating the first neural network based on the third parameter to obtain a third neural network, returning to S403, and updating the first neural network to the third neural network.

[0042] The hypersphere is verified through the validation set to ensure its accuracy.

[0043] Furthermore, the first neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer, the first hidden layer is connected to both the input layer and the second hidden layer, and the second hidden layer is connected to the output layer.

[0044] Furthermore, the specific steps of obtaining the judgment result include: obtaining the distance between the measurement data and the second center, and judging whether the distance is greater than the first radius, if so, the electric energy meter is faulty; otherwise, the electric energy meter is normal.

[0045] Based on the collaboration of neural network and support vector data descriptor, the fault area and non-fault area are divided in multi-dimensional space. By judging the position of each measurement value of the electric energy meter in the multi-dimensional space, it is determined whether the electric energy meter has a fault.

[0046] Furthermore, before executing S3, the method also includes: obtaining the number of in-operation electric energy meters to be tested and obtaining a second number of normal sample data in the training set; obtaining a first ratio based on the second number and the in-operation number, and judging whether the first ratio is greater than a third threshold value, and if so, skipping S3 and executing S4 to update the second hypersphere Q2 to the first hypersphere Q1.

[0047] Furthermore, the fourth calculation formula from the input layer to the first hidden layer is:

[0048] h1=ReLU(W1x in +b1);

[0049] The fifth calculation formula from the first hidden layer to the second hidden layer is:

[0050] h2=ReLU(W2h1+b2);

[0051] The sixth calculation formula from the second hidden layer to the output layer is:

[0052] y = Softmax(W3h2+b3);

[0053] Among them, h1, h2 and y all represent output values, ReLU() represents the ReLU function, W1, W2 and W3 all represent weights, b1, b2 and b3 all represent offsets, and x in Represents input data, and Softmax() represents the Softmax function.

[0054] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0055] 1. The direct construction of the SVDD hypersphere was decomposed using three hyperspheres, and the initial hypersphere center and radius were customized to reduce the computational complexity. A rough construction was performed first and then a fine construction was performed to improve the accuracy of the hypersphere construction. To a certain extent, the situation in which calculation contradictions occurred due to too much data and simultaneous input in the iterative case was reduced. A fault hypersphere was constructed in the multidimensional space. By analyzing the relationship between the representation points of the measurement data of the electric energy meter to be judged in the multidimensional space and the fault hypersphere, whether the electric energy meter to be judged was faulty was judged, and the judgment result was more accurate.

[0056] 2. The SVDD hypersphere makes full use of the inherent nonlinear coupling relationship between the various measurement data of the electricity meter, effectively improving the accuracy of the fault status analysis of the electricity meter.

[0057] 3. The neural network algorithm is used to reduce the dimension of the data and map it to a low-dimensional space, which reduces the computing power requirements for iterative solution of the hypersphere and the dependence on computing power hardware. It can be better applied to existing edge computing devices and greatly improves the speed of solving fault hyperspheres. At the same time, the algorithm is a black box model algorithm with good interpretability. The hypersphere optimized by the deep neural network can be observed in three-dimensional space, and its judgment process and logic are clear and observable.

[0058] 4. Neural networks are used to assist in the construction of hyperspheres, which increases the accuracy of hypersphere construction and is used for the calculation of hypersphere parameters. Compared with the traditional SVDD which uses optimization algorithms such as the simplex method, genetic algorithm, and particle swarm algorithm to solve the hypersphere parameters, neural networks can better cope with large-scale data situations. For scenarios where the power grid has a large amount of data, the use of neural networks can calculate the hypersphere parameters faster. At the same time, it also solves the problem that the traditional optimization algorithm solves large-scale data, causing the calculation to enter an infinite loop. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation on the embodiments of the present invention;

[0060] Figure 1 It is a schematic diagram of the process of constructing the third hypersphere Q3 in the present invention;

[0061] Figure 2 is a schematic diagram of the structure of the first neural network in the present invention;

[0062] Figure 3 It is a schematic diagram of the process of reducing the dimension of a data set by the first neural network in the present invention;

[0063] Figure 4 is a schematic diagram of the relationship between the first hypersphere Q1 and the second hypersphere Q2 in the present invention;

[0064] Figure 5 is a schematic diagram of the relationship between the second hypersphere Q2 and the third hypersphere Q3 in the present invention;

[0065] Wherein, p and k both represent integers greater than or equal to 2, Q1, Q2 and Q3 represent the first hypersphere Q1, the second hypersphere Q2 and the third hypersphere Q3, respectively. A ,I B and I C Represent the x, y and z axes respectively. DETAILED DESCRIPTION

[0066] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those within the scope of this description. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0068] Embodiment 1

[0069] refer to Figure 1-Figure 5 This embodiment provides a method for identifying faults in an electric energy meter based on Deep-SVDD, the method comprising:

[0070] S1. Obtaining electric energy meter data of each model, and constructing a data set based on the electric energy meter data;

[0071] The electric energy meter data includes normal sample data and misjudgment sample data, and the specific steps of constructing the data set include:

[0072] The electric energy meter data is divided into a training set and a validation set, and both the training set and the validation set include the normal sample data and the misjudged sample data. For example, the electric energy meter data is divided into a training set and a validation set according to a certain ratio, and the training set and the validation set respectively include the normal sample data and the misjudged sample data in the same ratio.

[0073] S2, constructing a first hypersphere Q1 based on the data set; the specific steps include: constructing the first hypersphere Q1 based on the normal sample data in the training set; the first calculation formula for constructing the first hypersphere Q1 is:

[0074]

[0075] Where R1 represents the radius of the first hypersphere Q1, c1 represents the center of the first hypersphere Q1, subject to represents the restriction condition, and x i represents the i-th normal sample, i represents the sequence number, ‖x i -c1‖ represents x i The distance to c1.

[0076] Before executing S3, the method further includes: obtaining the number of in-operation electric energy meters to be detected, obtaining the second number of normal sample data in the training set; obtaining a first ratio based on the second number and the in-operation number, judging whether the first ratio is greater than a third threshold, if so, skipping S3, exceeding the threshold indicates that the current data is not suitable for adjusting the hypersphere in S3, and there is no need to correct the hypersphere, executing S4, and updating the second hypersphere Q2 to the first hypersphere Q1. If the amount of data of the normal data set used to construct the first hypersphere Q1 is greater than 10% of the number of in-operation electric energy meters of a certain model, S3 can be skipped.

[0077] The number in operation refers to the number of different types of electricity meters put into use.

[0078] S3, adjusting the boundary of the first hypersphere Q1 to construct the second hypersphere Q2; the specific steps include: adjusting the boundary of the first hypersphere Q1 based on the preset slack variables to construct the second hypersphere Q2; the second calculation formula for constructing the second hypersphere Q2 is:

[0079]

[0080] Among them, R2 represents the radius of the second hypersphere Q2, C represents the weight parameter, which can be 0.02, subject to represents the restriction condition, and x i′ represents the i′th normal sample, i′ represents the sequence number, ξ i′It represents the allowable deviation of the i′th normal sample, and n represents the number of samples.

[0081] For example, define the slack variable: i′ ≧0, the second hypersphere Q2 is iterated on the basis of the first hypersphere Q1, and the initial value of R2 in the iterative process is the radius R1 of the first hypersphere Q1; C represents the weight parameter, which is used to balance the influence of the radius and the slack variable. The value range is [0.01, 0.03]. The actual parameter range needs to be adjusted according to the characteristics of the data set; ξ i′ The allowable deviation rate is 2%, so ξ i′ =2%*|x i′ |, * indicates multiplication.

[0082] S4, iteratively correcting the second hypersphere Q2 to construct a third hypersphere Q3; the specific steps include:

[0083] S401, constructing a first neural network, and obtaining a first midpoint of the third hypersphere Q3 based on the second hypersphere Q2; the third hypersphere Q3 is iterated on the basis of the second hypersphere Q2, and during the iteration, the initial value of R3 is the radius R2 of the second hypersphere Q2;

[0084] S402, initializing target parameters; if minimizing the volume of the hypersphere is used as the target function, the target function can be expressed as:

[0085]

[0086] Where R3 represents the radius of the third hypersphere Q3, c3 represents the center of the third hypersphere Q3, θ represents the parameters of the neural network, which may include the regularization parameter λ, the learning rate η and the number of learning rounds E, f (θ) () represents a neural network, x i″ represents the sample in the i″th training set after dimensionality reduction, i″ represents the sequence number, λ represents the regularization parameter, and n1 represents the number of samples.

[0087] Initialize the objective parameters of the objective function.

[0088] S403, reducing the dimension of the training set based on the first neural network to obtain reduced-dimensional data, and the calculation method may be:

[0089] x i″ =f (θ) (x i′ ); (4)

[0090] Among them, x i″ represents the data after dimensionality reduction, f (θ) () represents a neural network, x i′ Represents the i′th data in the training set, and i′ represents the sequence number.

[0091] S404: Based on the target parameter and the dimension reduction data, the first parameter of the first neural network is updated by using the Adam optimization algorithm to obtain the second parameter, and the calculation method may be:

[0092]

[0093] Where c3 represents the center of the third hypersphere Q3, θ represents the parameters of the neural network, and f ( θ ) () represents a neural network, x i″ represents the sample in the training set after the ith dimension reduction, i″ represents the sequence number, η represents the learning rate, which is usually set to 0.01, represents the partial differential symbol, n1 represents the number of samples, and ← represents the assignment operation.

[0094] Update the first neural network based on the second parameter to obtain a second neural network;

[0095] S405: Based on the second neural network, the first center is updated to obtain a second center, and the calculation method may be:

[0096]

[0097] Where c3 represents the center of the third hypersphere Q3, f (θ) () represents a neural network, x i″ It represents the sample in the i″th training set after dimensionality reduction, i″ represents the sequence number, and n1 represents the number of samples.

[0098] S406. Based on the second center, input the second center into a loss function to obtain a loss value;

[0099] S407: Determine whether the loss value is less than a first threshold value. If so, obtain a first radius based on the second center. The calculation method may be:

[0100]

[0101] Wherein, R3 represents the radius of the third hypersphere Q3, c3 represents the center of the third hypersphere Q3, and f (θ) () represents a neural network, x i″ It represents the sample in the i″th training set after dimensionality reduction, i″ represents the sequence number, and n1 represents the number of samples.

[0102] Based on the second center and the first radius, the third hypersphere Q3 is constructed; a third calculation formula for constructing the third hypersphere Q3 is:

[0103]

[0104] Where R3 represents the radius of the third hypersphere Q3, c3 represents the center of the third hypersphere Q3, θ represents the parameters of the neural network, and f (θ) () represents a neural network, x i″ represents the sample in the i″th training set after dimensionality reduction, i″ represents the sequence number, λ represents the regularization parameter, and n1 represents the number of samples.

[0105] If not, return to S403 to update the first neural network to the second neural network;

[0106] S5. Acquire measurement data of the electric energy meter to be detected, and discriminate the measurement data based on the third hypersphere Q3 to obtain a discrimination result.

[0107] The specific steps of obtaining the judgment result include: obtaining the distance between the measurement data and the second center, and judging whether the distance is greater than the first radius. If so, the electric energy meter is faulty; otherwise, the electric energy meter is normal. f , use the following formula to judge the state of the energy meter:

[0108]

[0109] Right now:

[0110] Fault state: The outer area of ​​the hypersphere Q3, i.e. ‖x f ‖>R3;

[0111] Normal state: the inner region of the hypersphere Q3, namely ‖x f ‖≤R3.

[0112] Embodiment 2

[0113] refer to Figure 1 Based on the first embodiment, in this embodiment, the specific steps of constructing the third hypersphere Q3 also include:

[0114] S408, obtaining a first number m1 of the verification set V, verifying the verification set V based on the third hypersphere Q3, and obtaining a number k of unqualified persons in the verification set V located outside the hypersphere Q3 f ;

[0115] S409: Obtain a non-conforming value based on the first quantity and the non-conforming quantity, and the calculation method may be:

[0116]

[0117] Among them, a represents the unqualified value, k frepresents the number of unqualified samples, and m1 represents the number of samples in the validation set.

[0118] S410, determining whether the unqualified value is greater than or equal to a second threshold value, if so, adjusting the first parameter to obtain a third parameter, updating the first neural network based on the third parameter to obtain a third neural network, returning to S403, and updating the first neural network to the third neural network.

[0119] It can be expressed as:

[0120] If a≥μ, μ can take a value of 0.01-0.05, then adjust the parameter θ of the neural network and return to S403 to execute again;

[0121] If a<μ, the resulting hypersphere Q3 is the final output result.

[0122] Embodiment 3

[0123] refer to Figure 2-Figure 3 Based on the above embodiment, in this embodiment, the first neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer, the first hidden layer is connected to the input layer and the second hidden layer, and the second hidden layer is connected to the output layer.

[0124] The fourth calculation formula from the input layer to the first hidden layer is:

[0125] h1=ReLU(W1x in +b1); (10)

[0126] The fifth calculation formula from the first hidden layer to the second hidden layer is:

[0127] h2=ReLU(W2h1+b2); (11)

[0128] The sixth calculation formula from the second hidden layer to the output layer is:

[0129] y=Softmax(W3h2+b3); (12)

[0130] Among them, h1, h2 and y all represent output values, ReLU() represents the ReLU function, W1, W2 and W3 all represent weights, b1, b2 and b3 all represent offsets, and x in Represents input data, and Softmax() represents the Softmax function.

[0131] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0132] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for fault identification of electric energy meter based on Deep-SVDD, characterized in that: The method comprises: S1. Obtaining electric energy meter data of each model, and constructing a data set based on the electric energy meter data; S2, constructing a first hypersphere Q1 based on the data set; S3, adjusting the boundary of the first hypersphere Q1 to construct a second hypersphere Q2; S4, iteratively modifying the second hypersphere Q2 to construct a third hypersphere Q3; S5. Acquire measurement data of the electric energy meter to be detected, and discriminate the measurement data based on the third hypersphere Q3 to obtain a discrimination result.

2. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 1, characterized in that: The electric energy meter data includes normal sample data and misjudgment sample data. The specific steps of constructing the data set include: The electric energy meter data is divided into a training set and a verification set, and both the training set and the verification set include the normal sample data and the misjudged sample data.

3. The method for fault identification of electric energy meter based on Deep-SVDD according to claim 2, characterized in that: The specific steps of constructing the first hypersphere Q1 include: Constructing the first hypersphere Q1 based on the normal sample data in the training set; The first calculation formula for constructing the first hypersphere Q1 is: Where R1 represents the radius of the first hypersphere Q1, c1 represents the center of the first hypersphere Q1, subject to represents the restriction condition, and x i represents the i-th normal sample, i represents the sequence number, ‖x i -c1‖ represents x i The distance to c1.

4. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 3 is characterized in that: The specific steps of constructing the second hypersphere Q2 include: Based on the preset relaxation variables, the boundary of the first hypersphere Q1 is adjusted to construct the second hypersphere Q2; The second calculation formula for constructing the second hypersphere Q2 is: Among them, R2 represents the radius of the second hypersphere Q2, C represents the weight parameter, subject to represents the restriction condition, and x i′ represents the i′th normal sample, i′ represents the sequence number, ξ i′ It represents the allowable deviation of the i′th normal sample, and n represents the number of samples.

5. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 4 is characterized in that: The specific steps of constructing the third hypersphere Q3 include: S401, constructing a first neural network, and obtaining a first midpoint of the third hypersphere Q3 based on the second hypersphere Q2; S402, initializing target parameters; S403, reducing the dimension of the training set based on the first neural network to obtain reduced-dimensional data; S404: based on the target parameter and the dimension reduction data, updating a first parameter of the first neural network to obtain a second parameter, and updating the first neural network based on the second parameter to obtain a second neural network; S405, based on the second neural network, updating the first center to obtain a second center; S406, obtaining a loss value based on the second center; S407, determining whether the loss value is less than a first threshold value, if so, obtaining a first radius based on the second center, and constructing the third hypersphere Q3 based on the second center and the first radius; if not, returning to S403, and updating the first neural network to the second neural network; The third calculation formula for constructing the third hypersphere Q3 is: Where R3 represents the radius of the third hypersphere Q3, c3 represents the center of the third hypersphere Q3, θ represents the parameters of the neural network, and f (θ) () represents a neural network, x i″ represents the sample in the i″th training set after dimensionality reduction, i″ represents the sequence number, λ represents the regularization parameter, and n1 represents the number of samples.

6. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 5, characterized in that: The specific steps of constructing the third hypersphere Q3 also include: S408, obtaining a first number of the verification set, verifying the verification set based on the third hypersphere Q3, and obtaining a number of unqualified ones; S409, obtaining a non-conforming value based on the first quantity and the non-conforming quantity; S410, determining whether the unqualified value is greater than or equal to a second threshold value, if so, adjusting the first parameter to obtain a third parameter, updating the first neural network based on the third parameter to obtain a third neural network, returning to S403, and updating the first neural network to the third neural network.

7. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 6, characterized in that: The first neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer, wherein the first hidden layer is connected to both the input layer and the second hidden layer, and the second hidden layer is connected to the output layer.

8. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 7, characterized in that: The specific steps to obtain the discrimination results include: Obtain the distance between the measurement data and the second center, and determine whether the distance is greater than the first radius. If so, the electric energy meter is faulty; otherwise, the electric energy meter is normal.

9. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 2, characterized in that: Before executing S3, the method further includes: Obtaining the number of the electric energy meters to be detected that are in operation, and obtaining a second number of normal sample data in the training set; A first ratio is obtained based on the second number and the in-operation number, and it is determined whether the first ratio is greater than a third threshold. If so, S3 is skipped and S4 is executed to update the second hypersphere Q2 to the first hypersphere Q1.

10. The method for identifying faults of electric energy meters based on Deep-SVDD according to claim 7, characterized in that: The fourth calculation formula from the input layer to the first hidden layer is: h1=ReLU(W1x in +b1); The fifth calculation formula from the first hidden layer to the second hidden layer is: h2=ReLU(W2h1+b2); The sixth calculation formula from the second hidden layer to the output layer is: y = Softmax(W3h2+b3); Among them, h1, h2 and y all represent output values, ReLU() represents the ReLU function, W1, W2 and W3 all represent weights, b1, b2 and b3 all represent offsets, and x in Represents input data, and Softmax() represents the Softmax function.

Images