A method and system for analyzing and judging wrong wiring of three-phase four-wire electric energy meter

Abstract

The present invention provides a method and system for judging the wrong wiring of a three-phase four-wire electric energy meter, which relates to the field of electric power metering. Based on a laboratory environment, typical characteristic values ​​of a three-phase four-wire N-type wiring type library are obtained; actual field collection values ​​are obtained, and the typical characteristic values ​​obtained in the laboratory environment are corrected and optimized using a clustering algorithm, so that the construction of the three-phase four-wire N-type wiring type library is close to the actual field data; data is obtained from an electricity consumption information collection system; the collected data is combined and preprocessed at preset time intervals; and the wiring type of the three-phase four-wire electric energy meter is judged. The present invention solves the problem that the existing wrong wiring judgment technology cannot be used on a large scale, is costly, and cannot accurately perceive which type of wrong wiring is.

Description

Background Art

[0002] With the accelerated integration of the energy revolution and the digital revolution, the market-oriented reform of the power industry has been deepened. Power supply and demand, power purchasing agents, spot transactions, etc. have put forward high requirements on the accuracy of electricity metering and the timeliness of abnormality handling. It is urgently necessary to have online efficient intelligent perception and inspection and analysis capabilities for various abnormalities such as wrong wiring of electricity meters, metering failures, electricity theft, etc., to meet the needs of online inspection and analysis of doubtful metering issues, correct them in time, and safeguard the rights and interests of both power suppliers and users.

[0003] The existing analysis and judgment technology for various abnormalities such as wrong wiring of electric energy meters, metering failures, and electricity theft is mainly divided into two directions, one is through hardware detection, and the other is through analysis of the data collected by the electric energy meter. There are many technical methods for hardware detection, such as using wave blocking devices and sensing devices to realize the detection of wrong wiring of non-household uninterrupted power electric energy meters, or using a wrong wiring detector with a microprocessor to obtain the measurement signal of the circuit to determine whether the wiring of the device to be tested on site is correct. However, the hardware detection method cannot solve the problem of judging the wiring of a large number of electric energy meters at the same time, and the cost of use is also high. It cannot be promoted and used on a large scale, and it cannot be perceived in time when the electric energy meter is wrongly wired. The analysis of the electric energy meter data collected in real time is to determine whether a wrong wiring has occurred based on the change amount Δ of the active power, reactive power, power factor, etc. of the collected data, but it is impossible to accurately perceive the specific type of wrong wiring, so that the subsequent power recovery cannot be calculated in time. Therefore, how to timely judge the type of wrong wiring based on the existing data of the electric energy meter is a technical problem that urgently needs to be solved in the current technology.

[0004] In order to judge the wiring type of the electric energy meter, if a supervised algorithm is used, a large amount of data is required for each wiring type to train the model. However, there are only theoretical values ​​for each wiring type at present. Therefore, in order to make full use of the existing data, a semi-supervised algorithm is a more suitable algorithm for judging the wiring type of the electric energy meter. That is, only a small amount of labeled data and a large amount of unlabeled data are needed for learning, and finally a better performance can be achieved, which improves the accuracy of online judgment of wrong wiring of the electric energy meter and calculation of error electricity, and meets business needs. The label propagation algorithm (LPA) is a graph-based semi-supervised learning method. It is believed that closely connected nodes will have the same label value. Its basic idea is to use the label information of the labeled nodes to predict the label information of the unlabeled nodes, and finally the nodes with the same label value are divided into one category. LPA has the characteristics of simple ideas, strong scalability, lowest complexity, and fastest speed. The time complexity is close to linear 0(m) (m is the number of edges). In addition, the label propagation algorithm does not need to optimize the predefined objective function, and there is no limit on the number of wiring types. However, although the label propagation algorithm is simple and efficient, the randomness of label propagation in the algorithm leads to poor accuracy of the algorithm, unstable partitioning results, strong randomness, and the robustness needs to be improved. Summary of the invention

[0005] The present invention provides a method for analyzing and judging the wrong wiring of a three-phase four-wire electric energy meter. The method can realize real-time analysis and judgment of 96 types of wiring of the three-phase four-wire electric energy meter, has the characteristics of high analysis and judgment accuracy, low cost and high efficiency, and improves the maintenance efficiency of metering personnel.

[0006] Methods include:

[0007] S1: Based on the laboratory environment, obtain the typical characteristic values ​​of the three-phase four-wire N wiring type library;

[0008] S2: Obtain the actual collected values ​​on site, and use the clustering algorithm to modify and optimize the typical characteristic values ​​obtained in the laboratory environment, so that the constructed three-phase four-wire N types of wiring type library is close to the actual field data;

[0009] S3: Obtain data from the electricity consumption information collection system;

[0010] S4: combining and preprocessing the collected data at preset time intervals;

[0011] S5: Analyze the wiring type of the three-phase four-wire electric energy meter.

[0012] It should be further explained that the three-phase four-wire N wiring type library in step S1 includes: typical characteristic values ​​of phase A voltage, phase B voltage, phase C voltage, phase A voltage phase angle, phase B voltage phase angle, phase C voltage phase angle, phase A voltage and current phase angle, phase B voltage and current phase angle, and phase C voltage and current phase angle.

[0013] It should be further explained that the clustering algorithm in step S2 adopts the density peak clustering algorithm, and determines the center of the cluster based on the five steps of calculating the local density, calculating the minimum distance to the high-density point, visualization, and determining the cluster center based on the density peak clustering algorithm, so as to correct and optimize the typical eigenvalues ​​obtained in the laboratory environment.

[0014] It should be further explained that the density peak clustering algorithm used includes the following processing methods:

[0015] The local density is calculated as follows:

[0016]

[0017] Among them, d c The size setting is satisfied;

[0018] The minimum distance to high-density points is calculated using the following formula:

[0019]

[0020] Plot the local density ρ i The distance δ from the high local density point i Scatter plot of the relationship between

[0021] Select the information whose local density and high local density distance are both greater than the threshold as the cluster center;

[0022] The typical characteristic values ​​of N wiring types obtained in the experimental environment are corrected and optimized into the A-phase voltage, B-phase voltage, C-phase voltage, A-phase voltage phase angle, B-phase voltage phase angle, C-phase voltage phase angle, A-phase voltage and current phase angle, B-phase voltage and current phase angle, and C-phase voltage and current phase angle data of the cluster center sample point.

[0023] It should be further explained that the data obtained from the power consumption information collection system in step S3 includes three-phase active power, current, voltage, reactive power and voltage phase angle, voltage-current phase angle, and power factor data.

[0024] It should be further explained that in step S4, the collected data is preprocessed in the following manner:

[0025] Clean the distorted data in the original data;

[0026] The Lagrange interpolation method is used to interpolate and correct missing data values;

[0027] The data value is limited to the interval [0,1], and the calculation formula is as follows:

[0028]

[0029] Where X max is the maximum value of the corresponding influencing factor data, X min is the minimum value of the corresponding influencing factor data in the data.

[0030] It should be further explained that in step five, a label propagation algorithm model is used to determine the wiring type of the three-phase four-wire electric energy meter.

[0031] In the method, a label propagation algorithm model is used to judge the wiring type of a three-phase four-wire electric energy meter. The judgment steps include the following:

[0032] (1) The constructed three-phase four-wire N wiring type library (UA1, UB1, UC1, UB1, .....y1),

[0033] (UA2,UB2,UC2,UB2,...y2),...,(UA 96 ,UB 96 ,UC 96 ,UB 96 ,.....y 96 ) data as labeled data, (UA 97 ,UB 97 ,UC 97 ,UB 97 ,.....y 97 ),......,(UA 96+u ,UB 96+u ,UC 96+u ,UB 96+u ,.....y 96+u ) as unlabeled data;

[0034] (2) All data are used as nodes to create a fully connected graph, and the edge weights are calculated as follows:

[0035]

[0036] Among them, d ij Represents the Euclidean distance between any two nodes, with weight w ij Controlled by parameter σ;

[0037] (3) Calculate the probability T that a node's annotation is propagated to other nodes through edges. The probability T is calculated using the following formula:

[0038]

[0039] (4) Define a (96+u) x 96 dimension labeling matrix Y;

[0040] (5) Each node adds the weighted annotation values ​​propagated by its surrounding nodes according to the propagation probability and updates its own probability distribution:

[0041]

[0042] Limit the labeled data and reassign the probability distribution of the labeled data to the initial value;

[0043] Repeat step (5) until convergence.

[0044] The present invention also provides a three-phase four-wire electric energy meter wrong wiring analysis and judgment system, the system comprises: an experimental data acquisition module, a field data processing module, an electricity information collection module, a data processing module and a wiring analysis and judgment module;

[0045] The experimental data acquisition module obtains typical characteristic values ​​of N wiring type libraries of three-phase four-wire based on the laboratory environment;

[0046] The field data processing module is used to obtain the actual field data, and use the clustering algorithm to modify and optimize the typical characteristic values ​​obtained in the laboratory environment, so that the construction of the three-phase four-wire N-type wiring type library is close to the actual field data;

[0047] The power consumption information collection module is used to obtain data from the power consumption information collection system;

[0048] The data processing module is used to combine and pre-process the collected data at preset time intervals;

[0049] The wiring analysis module is used to analyze the wiring type of the three-phase four-wire electric energy meter.

[0050] It can be seen from the above technical solutions that the present invention has the following advantages:

[0051] The method for judging the wrong wiring of a three-phase four-wire electric energy meter provided by the present invention corrects and optimizes the typical characteristic values ​​obtained in the laboratory environment, so that the construction of a three-phase four-wire N-type wiring type library is close to the actual field data; then the data is obtained from the power consumption information collection system; the collected data is combined and preprocessed at preset time intervals; and the wiring type of the three-phase four-wire electric energy meter is judged. In this way, the real-time judgment of 96 types of wiring of the three-phase four-wire electric energy meter is realized, which has the characteristics of high judgment accuracy, low cost and high efficiency, and improves the maintenance efficiency of the metering personnel. It is also possible to efficiently collect, store and process the data of 96 types of wiring types of the three-phase four-wire electric energy meter, and use multi-dimensional space to describe the entire power state. Improve the management level and efficiency of the judgment of the wrong wiring of the three-phase four-wire electric energy meter, control the operation risk of the power process, and thus realize the timeliness and scientificity of the supervision, management and control of the whole process of the judgment of the wiring of the three-phase four-wire electric energy meter. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0053] Figure 1 This is a flow chart of the method for analyzing the wrong wiring of a three-phase four-wire electric energy meter;

[0054] Figure 2 This is a schematic diagram of the system for analyzing the miswiring of three-phase four-wire electric energy meters. DETAILED DESCRIPTION

[0055] The three-phase four-wire electric energy meter wrong wiring judgment method provided by the present invention is mainly to solve the problem that the randomness of label propagation in the label propagation algorithm during the three-phase four-wire electric energy meter wrong wiring judgment process leads to poor algorithm accuracy, unstable division results and low robustness.

[0056] Of course, the three-phase four-wire electric energy meter wrong wiring judgment method of the present invention can acquire and process the associated data based on artificial intelligence technology. Among them, the three-phase four-wire electric energy meter wrong wiring judgment method uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. The theory, method, technology and application device.

[0057] The method of the present invention includes both hardware-level technology and software-level technology. The basic technology of the three-phase four-wire electric energy meter wrong wiring analysis method generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. The software technology of the three-phase four-wire electric energy meter wrong wiring analysis method mainly includes computer perspective technology, voice processing technology, machine learning / deep learning and programming language. Programming languages ​​include but are not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages.

[0058] According to the needs, the method for judging the wrong wiring of three-phase four-wire electric energy meters also has a machine learning function, wherein the machine learning and deep learning in the method of the present invention generally include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning. Through the density peak clustering algorithm and label propagation algorithm model, etc., using sensor monitoring, data transmission and other technologies, the real-time judgment of 96 types of wiring of three-phase four-wire electric energy meters is realized, which has the characteristics of high judgment accuracy, low cost and high efficiency, and improves the maintenance efficiency of metering personnel.

[0059] 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.

[0060] See also Figure 1 The figure is a flow chart of a method for analyzing and judging the wrong wiring of a three-phase four-wire electric energy meter in a specific embodiment, and the method includes:

[0061] S1: Based on the laboratory environment, obtain the typical characteristic values ​​of the three-phase four-wire N wiring type library;

[0062] Among them, taking the typical characteristic values ​​of the three-phase four-wire 96 wiring type library as an example, the typical characteristic values ​​of the meter's A-phase voltage, B-phase voltage, C-phase voltage, A-phase voltage phase angle, B-phase voltage phase angle, C-phase voltage phase angle, A-phase voltage and current phase angle, B-phase voltage and current phase angle, and C-phase voltage and current phase angle were read on the three-phase meter platform in the laboratory according to 96 wiring methods.

[0063] A comparison table 1 of 96 wiring situations is shown below.

[0064] Table 1

[0065]

[0066]

[0067] S2: Obtain the actual collected values ​​on site, and use the clustering algorithm to modify and optimize the typical characteristic values ​​obtained in the laboratory environment, so that the constructed three-phase four-wire 96 wiring type library is close to the actual field data.

[0068] It should be noted that the clustering method used is Density Peak Clustering (DPC), which is a density-based clustering method. The main idea is to find a high-density and significant area in the data set as the cluster center. The advantage of this clustering algorithm is that it can obtain non-spherical clustering results, which can well describe the data distribution. At the same time, the algorithm complexity is lower than that of the general K-means algorithm. Its use process usually includes five steps: calculating local density, calculating the minimum distance to high-density points, visualization, and determining the cluster center.

[0069] The calculation formula of local density is as follows:

[0070]

[0071] where d c The size setting is satisfied, and the point falls on d c The average number of points in the circle area accounts for 1%-2% of the total number of points.

[0072] Optionally, the minimum distance to high-density points is calculated using the following formula:

[0073]

[0074] It should be noted that in this embodiment, the local density ρ i The distance δ from the high local density point i relationship scatter plot; select the information where the local density and the high local density distance are greater than the threshold as the cluster center; correct and optimize the typical eigenvalues ​​of 96 wiring types obtained in the experimental environment to the A phase voltage, B phase voltage, C phase voltage, A phase voltage phase angle, B phase voltage phase angle, C phase voltage phase angle, A phase voltage and current phase angle, B phase voltage and current phase angle, and C phase voltage and current phase angle data of the cluster center sample point.

[0075] S3: Obtain data from the electricity consumption information collection system.

[0076] In this embodiment, 96 points of data including active power, current, voltage, reactive power and voltage phase angle, voltage-current phase angle, and power factor of three phases A, B, and C are obtained from the power consumption information collection system.

[0077] S4: Combine and pre-process the collected data at preset time intervals.

[0078] According to the embodiments of the present application, there are some incomplete, inconsistent, and abnormal data in the original data, which will affect the execution efficiency and accuracy of data mining, and may even cause a large deviation between the mining results and the expected ones. Therefore, it is extremely important to perform data preprocessing to obtain a high-quality data set.

[0079] The first thing that needs to be processed in this embodiment is the distorted data in the original data, such as cleaning the distorted data of voltage phase loss, illegal voltage amplitude, and current less than the error range; secondly, power users have 96 points of load data every day, some of which will have zero values, empty values ​​or wrong values, which will affect the results of the analysis.

[0080] The present invention uses Lagrange interpolation to interpolate and correct these missing values. The specific method is as follows: determine the dependent variable and the independent variable from the original load data set, extract 5 data before and after the missing value position, form a group of 10 extracted data, and use the interpolation method to interpolate all the missing data in turn.

[0081] In an embodiment of the present invention, the data is also normalized. The input data of the present invention is the electricity customer profile and load data information, specifically including voltage, current, power, current phase angle, voltage phase angle, and power factor.

[0082] The voltage, current, and power factor in the data source have data magnitude mismatches. This disordered data will cause large errors in the wiring type judgment results. The present invention will normalize the sample data and use a normalization method to eliminate this unfavorable factor. The present invention limits the value of the sample data to the interval [0,1], and the calculation formula is as follows:

[0083]

[0084] Among them, X max is the maximum value of the corresponding influencing factor data, X min is the minimum value of the corresponding influencing factor data in the sample data. After data normalization, the input data at the same level can not only speed up the training efficiency of the prediction model, but also reduce the output error.

[0085] S5: Analyze the wiring type of the three-phase four-wire electric energy meter.

[0086] The algorithm model for judging the wiring type of three-phase four-wire electric energy meters uses the label propagation algorithm model. The steps are as follows:

[0087] (1) The constructed three-phase four-wire 96 wiring type library (UA1, UB1, UC1, UB1, .....y1),

[0088] (UA2,UB2,UC2,UB2,...y2),...,(UA 96 ,UB 96 ,UC 96 ,UB 96 ,.....y 96 ) data as labeled data, (UA 97 ,UB 97 ,UC 97 ,UB 97 ,.....y 97 ),......,(UA 96+u ,UB 96+u ,UC 96+u ,UB 96+u ,.....y 96+u ) as unlabeled data.

[0089] (2) All data are taken as nodes (including labeled and unlabeled data) to create a fully connected graph, and the edge weight calculation formula is as follows:

[0090]

[0091] where d ij Represents the Euclidean distance between any two nodes, with weight w ij is controlled by the parameter σ.

[0092] (3) The probability T of a node’s annotation being propagated to other nodes through edges is calculated as follows:

[0093]

[0094] (4) Define a (96+u) x 96 dimension labeling matrix Y.

[0095] (5) Each node adds the weighted annotation values ​​propagated by the surrounding nodes according to the propagation probability and updates its own probability distribution:

[0096]

[0097] Here, we limit the labeled data and reassign the probability distribution of the labeled data to the initial value. Repeat step 5 until convergence.

[0098] Based on the above method, the real-time analysis and judgment of 96 types of connection of three-phase four-wire electric energy meters is realized, which has the characteristics of high accuracy, low cost and high efficiency, and improves the maintenance efficiency of metering personnel. It can also efficiently collect, store and process the data of 96 types of connection of three-phase four-wire electric energy meters, and use multi-dimensional space to describe the entire power state. Improve the management level and efficiency of the analysis and judgment of wrong wiring of three-phase four-wire electric energy meters, control the operation risk of the power process, and thus realize the timeliness and scientificity of the supervision, management and control of the whole process of the three-phase four-wire electric energy meter connection analysis.

[0099] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0100] The following is an embodiment of a three-phase four-wire electricity meter miswiring analysis system provided by an embodiment of the present disclosure. This system and the three-phase four-wire electricity meter miswiring analysis method of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the three-phase four-wire electricity meter miswiring analysis system, reference can be made to the above-mentioned embodiment of the three-phase four-wire electricity meter miswiring analysis method.

[0101] like Figure 2 As shown, the system includes: an experimental data acquisition module, a field data processing module, an electricity consumption information collection module, a data processing module and a wiring analysis module.

[0102] The experimental data acquisition module obtains typical characteristic values ​​of N wiring type libraries of three-phase four-wire based on the laboratory environment.

[0103] The field data processing module is used to obtain the actual collected values ​​on site, and uses the clustering algorithm to correct and optimize the typical characteristic values ​​obtained in the laboratory environment, so that the constructed three-phase four-wire N types of wiring type library is close to the actual field data.

[0104] The electricity consumption information collection module is used to obtain data from the electricity consumption information collection system.

[0105] The data processing module is used to combine and pre-process the collected data at preset time intervals.

[0106] The wiring analysis module is used to analyze the wiring type of the three-phase four-wire electric energy meter.

[0107] The system of the present invention solves the problems that the existing miswiring analysis technology cannot be used on a large scale, is relatively costly, and cannot accurately sense which type of miswiring occurs.

[0108] The three-phase four-wire electric energy meter miswiring analysis system provided by the present invention is a combination of the units and algorithm steps of each example described in the embodiments disclosed herein, and can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. 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 exceed the scope of the present invention.

[0109] Those skilled in the art will appreciate that the various aspects of the three-phase four-wire electric energy meter miswiring analysis method provided by the present invention can be implemented as a system, method or program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, which can be collectively referred to as a "circuit", "module" or "system" here.

[0110] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for judging the wrong wiring of a three-phase four-wire electric energy meter, characterized in that the method include: S1: Based on the laboratory environment, obtain the typical characteristic values ​​of the three-phase four-wire N wiring type library; S2: Obtain the actual collected values ​​on site, and use the clustering algorithm to modify and optimize the typical characteristic values ​​obtained in the laboratory environment, so that the constructed three-phase four-wire N types of wiring type library is close to the actual field data; S3: Obtain data from the electricity consumption information collection system; S4: combining and preprocessing the data obtained in S3 at preset time intervals; S5: Using the label propagation algorithm model, the connection type of the three-phase four-wire electric energy meter after processing the data in S4 is judged through the three-phase four-wire N connection type library in S2.

2. The method for determining the wrong wiring of a three-phase four-wire electric energy meter according to claim 1 is characterized in that: The three-phase four-wire N wiring type library in step S1 contains typical characteristic values ​​corresponding to all the following parameters: phase A voltage, phase B voltage, phase C voltage, phase A voltage phase angle, phase B voltage phase angle, phase C voltage phase angle, phase A voltage and current phase angle, phase B voltage and current phase angle, and phase C voltage and current phase angle.

3. The method for determining the wrong wiring of a three-phase four-wire electric energy meter according to claim 1 is characterized in that: The clustering algorithm in step S2 adopts the density peak clustering algorithm, and determines the center of the cluster through four steps: calculating the local density based on the density peak clustering algorithm, calculating the minimum distance to the high-density point, visualizing, and determining the cluster center, so as to correct and optimize the typical characteristic values ​​obtained in the laboratory environment.

4. The method for determining the wrong wiring of a three-phase four-wire electric energy meter according to claim 3 is characterized in that: The density peak clustering algorithm used includes the following processing methods: The local density is calculated as follows: in, represents the local density of point i; Represents the Euclidean distance between point i and point j; The minimum distance to the high-density point is calculated by the following formula : in, represents the local density of point j; Plotting the local density Minimum distance to points of high local density Scatter plot of the relationship between Select the information whose local density and high local density distance are both greater than the threshold as the cluster center; The typical characteristic values ​​of N wiring types obtained in the experimental environment are corrected and optimized into the A-phase voltage, B-phase voltage, C-phase voltage, A-phase voltage phase angle, B-phase voltage phase angle, C-phase voltage phase angle, A-phase voltage and current phase angle, B-phase voltage and current phase angle, and C-phase voltage and current phase angle data of the cluster center sample point.

5. The method for determining the wrong wiring of a three-phase four-wire electric energy meter according to claim 1 is characterized in that: The data acquired from the power consumption information collection system in step S3 includes three-phase active power, current, voltage, reactive power and voltage phase angle, voltage-current phase angle, and power factor data.

6. The method for determining the wrong wiring of a three-phase four-wire electric energy meter according to claim 1 is characterized in that: In step S4, the collected data is preprocessed in the following manner: Clean the distorted data in the original data; The Lagrange interpolation method is used to interpolate and correct missing data values; Limit the data value to the interval [0,1], and the calculation formula is as follows: in is the maximum value of the corresponding influencing factor data, is the minimum value of the corresponding influencing factor data in the data.

7. A three-phase four-wire electric energy meter wrong wiring analysis system, characterized in that: The system adopts the method for analyzing and judging the wrong wiring of a three-phase four-wire electric energy meter as described in any one of claims 1 to 6; The system includes: experimental data acquisition module, field data processing module, power consumption information collection module, data processing module and wiring analysis module; The experimental data acquisition module obtains typical characteristic values ​​of N wiring type libraries of three-phase four-wire based on the laboratory environment; The field data processing module is used to obtain the actual field data, and use the clustering algorithm to modify and optimize the typical characteristic values ​​obtained in the laboratory environment, so that the construction of the three-phase four-wire N-type wiring type library is close to the actual field data; The power consumption information collection module is used to obtain data from the power consumption information collection system; The data processing module is used to combine and pre-process the data acquired by the power consumption information collection module at preset time intervals; The wiring judgment module is used to adopt a label propagation algorithm model to judge the wiring type of the three-phase four-wire energy meter of the processed data in the data processing module through the three-phase four-wire N wiring type library in the field data processing module.

Images