A Phase Identification Method for Substation Areas Considering Incomplete Data

By acquiring and processing the user voltage data of the station area and the three-phase voltage data of the transformer, and extracting and comparing the feature matrix, the problems of low efficiency and high cost of the existing station area phase recognition technology are solved, and efficient and accurate phase recognition and data processing are achieved. , meet the needs of power supply companies.

CN114912519BActive Publication Date: 2024-12-03JIANGSU FRONTIER ELECTRIC TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210460733.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-28
Publication Date
2024-12-03
Estimated Expiration
2042-04-28

AI Technical Summary

Technical Problem

The existing station phase recognition technology cannot meet the needs of power supply companies. Its identification speed is slow, expensive, and is not easy to carry, and cannot effectively process incomplete data, resulting in the inability to meet business needs.

Method used

By obtaining the user voltage data of the station area and the transformer three-phase voltage data, data completion and normalization are performed, the voltage feature matrix is ​​extracted, and the characteristic data is compared to identify the station area and phase to which the user belongs, and phase information is output.

Benefits of technology

It significantly improves the efficiency and accuracy of phase recognition in the station area, reduces costs, can effectively process incomplete data, and meets the business needs of power supply companies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114912519B_ABST
    Figure CN114912519B_ABST
Patent Text Reader

Abstract

The present invention discloses a phase identification method for a substation taking into account incomplete data, including: obtaining three-phase voltage data of all substation users and transformers in each substation, completing the missing data, and then performing normalization processing; extracting voltage features based on the normalized data to obtain a voltage feature matrix of the substation users and a voltage feature matrix of each phase of the transformer in each substation; comparing the voltage feature data in the voltage feature matrix of the substation users and the voltage feature matrix of each phase of the transformer in each substation to obtain the substation and phase to which each user belongs; and outputting the phase information of each user in each substation. The present invention utilizes the similarity between the voltage feature of a single-phase user in a low-voltage substation and the phase of the substation substation to which the user belongs to realize the identification of the phase of the substation to which the user belongs, which can effectively improve the identification accuracy, efficiency and stability of substation phase identification and reduce costs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of phase identification of a transformer station, and in particular to a phase identification method of a transformer station taking into account incomplete data. Background Art

[0002] With the continuous maturity and development of electricity consumption information collection technology, the success rate and accuracy of electricity consumption reading have also been significantly improved. In particular, the promotion and application of HPLC communication technology in recent years has realized the high-frequency collection of 15-minute curve data of residential users' electricity meters in low-voltage substations. The business needs of power supply companies are also constantly increasing, such as substation ownership and meter phase relationship, analysis of the causes of unbalanced public transformer loads, more refined line loss analysis requirements, early warning of line safety hazards, and timely fault repair requirements.

[0003] In recent years, low-voltage substations have been fully covered by smart meters, which has improved the quality of power consumption measurement data in the substations and made it possible to identify user topology driven by data. However, the current substation phase identification uses a phase identifier, which can only identify one user at a time. It has a slow identification speed, is expensive, and is not easy to carry, which cannot meet the needs of power supply companies. Therefore, in order to meet the gradually increasing business needs of power supply companies, the line topology relationship of the low-voltage substation and the phase relationship of the electric energy meter of each residential user are particularly important. Summary of the invention

[0004] The purpose of the present invention is to provide a phase identification method for a substation taking into account incomplete data, so as to improve the efficiency of phase identification for the substation and reduce the cost. The technical solution adopted by the present invention is as follows.

[0005] In one aspect, the present invention provides a method for phase identification of a station area taking into account incomplete data, comprising:

[0006] Obtain the voltage data of users in the substation area and the three-phase voltage data of transformers in each substation area, and complete the missing data;

[0007] Normalize the completed user voltage data of the substation area and the three-phase voltage data of the transformers in each substation area respectively;

[0008] Based on the normalized data, voltage feature extraction is performed to obtain the voltage feature matrix of the users in the substation area and the voltage feature matrix of each phase of the transformer in each substation area;

[0009] Compare the voltage characteristic data in the voltage characteristic matrix of the users in the substation area and the voltage characteristic matrix of each phase of the transformer in each substation area to obtain the substation area and phase to which each user belongs;

[0010] Output the phase information of each user in each area.

[0011] In the present invention, the acquired user voltage data of the substation area may be user voltage data collected by a smart meter.

[0012] Optionally, corresponding to the voltage data of the users in the substation area, the completing of the missing data includes:

[0013] S11, determine the initial voltage matrix :

[0014]

[0015] Among them, m is the number of users in the area, n is the number of time points for voltage measurement, and the column vector of U is Indicates the same time point The voltage measurements of different users, the row vector of U Represents a single user The voltage measurements at different time points, For lost data;

[0016] S12, the initial voltage matrix is ​​calculated according to the following formula Complete the missing data in:

[0017]

[0018] The completed matrix can be expressed as :

[0019] .

[0020] Optionally, the normalization process adopts a Z-score normalization method, wherein the user voltage data of the area after the completion process is normalized to obtain a normalized voltage matrix :

[0021]

[0022] Among them, after the completion process, the matrix The normalization formula is:

[0023]

[0024] To complete the matrix Single user The average voltage data, For a single user The standard deviation of voltage data;

[0025] Normalized voltage matrix It is expressed as:

[0026] .

[0027] Optionally, the voltage feature extraction based on the normalized data is to extract the fluctuation characteristic parameters of the voltage data, and the voltage fluctuation characteristic parameters include the voltage standard deviation The slope of the voltage curve ; Among them, corresponding to the voltage data of user i in the substation, the voltage fluctuation characteristic parameters are calculated and extracted according to the following formula:

[0028]

[0029]

[0030] In the formula, is the average value of the data collected by a single user in the normalized voltage matrix;

[0031] At this time, the voltage characteristic matrix of the users in the substation area can be obtained, which is expressed as:

[0032] .

[0033] Referring to the above method of processing the voltage data of users in the substation area to obtain the characteristic matrix, the three-phase voltage characteristic matrix of each substation area can be obtained by the same method:

[0034]

[0035] in, , , are the voltage characteristic matrices of the three phases A, B, and C of the K transformers in the substation area. At this time, the substation user characteristic parameter matrix Respectively with the three-phase voltage characteristic matrix of the transformer , , By comparing, the type and phase of the area described by the user in the area can be obtained.

[0036] Optionally, the voltage characteristic data in the transformer area user voltage characteristic matrix and the voltage characteristic matrix of each phase of each transformer area transformer are compared as follows:

[0037] For each user, the corresponding voltage characteristic parameters are compared with the voltage characteristic parameters in the A, B, and C three-phase voltage characteristic matrices of all substation transformers, and the substation transformer phase corresponding to the voltage characteristic parameters with the highest similarity is determined to be the substation and phase of the corresponding user.

[0038] The above technical solution uses the most similar correlation features between the single-phase user voltage features and the corresponding substation transformer phase voltage features, which can ensure the reliability of the identification results.

[0039] In a second aspect, the present invention provides a phase identification device for a station area, comprising:

[0040] The data preprocessing module is configured to obtain the voltage data of users in the substation area and the three-phase voltage data of transformers in each substation area, and to complete the lost data;

[0041] The data normalization module is configured to normalize the completed user voltage data of the substation area and the three-phase voltage data of the transformers in each substation area respectively;

[0042] The feature extraction module is configured to extract voltage features based on the normalized data to obtain a voltage feature matrix of users in the substation area and a voltage feature matrix of each phase of the transformer in each substation area;

[0043] The feature matching module is configured to compare the voltage feature data in the voltage feature matrix of the users in the substation area with the voltage feature matrix of each phase of the transformer in each substation area to obtain the substation area and phase to which each user belongs;

[0044] And, the identification result output module is configured to output the phase information of each user in each station area.

[0045] Optionally, the data preprocessing module completes the missing data according to the following formula:

[0046]

[0047] in, Represents the voltage data matrix Line Column data, , Indicates the number of time points of data collection, in the voltage data matrix, Indicates different users or different transformers.

[0048] Optionally, the data normalization module performs normalization processing using a Z-score normalization method, and the normalization formula is:

[0049]

[0050] In the formula, The first The average voltage data of the row, For the The standard deviation of the voltage data for each row.

[0051] Optionally, the feature extraction module extracts voltage features by extracting fluctuation feature parameters of voltage data, where the voltage fluctuation feature parameters include voltage standard deviation The slope of the voltage curve , the following formula is used to calculate the extraction:

[0052]

[0053]

[0054] In the formula, is the first element in the normalized voltage matrix The average value of the row data.

[0055] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the phase identification method for the station area as introduced in the first aspect is implemented.

[0056] Beneficial Effects

[0057] The present invention utilizes the similarity between the voltage characteristics of single-phase electric energy meters in low-voltage areas and the phase voltage characteristics of the transformers to which they belong, and performs feature extraction and similarity matching based on batch-acquired voltage data, which can significantly improve the efficiency of phase identification in the area. At the same time, the present invention can effectively improve the accuracy of phase identification results by supplementing the missing voltage data and normalizing the voltage matrix. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Shown is a schematic flow chart of the phase identification method of the station area of ​​the present invention;

[0059] Figure 2 Shown is a schematic diagram of a user voltage phase identification result in an application example of the method of the present invention. DETAILED DESCRIPTION

[0060] The invention is further described below with reference to the accompanying drawings and specific embodiments.

[0061] Example 1

[0062] This embodiment introduces a phase identification method for a station area taking into account incomplete data, including:

[0063] Obtain the voltage data of users in the substation area and the three-phase voltage data of transformers in each substation area, and complete the missing data;

[0064] Normalize the completed user voltage data of the substation area and the three-phase voltage data of the transformers in each substation area respectively;

[0065] Based on the normalized data, voltage feature extraction is performed to obtain the voltage feature matrix of the users in the substation area and the voltage feature matrix of each phase of the transformer in each substation area;

[0066] Compare the voltage characteristic data in the voltage characteristic matrix of the users in the substation area and the voltage characteristic matrix of each phase of the transformer in each substation area to obtain the substation area and phase to which each user belongs;

[0067] Output the phase information of each user in each area.

[0068] refer to Figure 1 As shown, the specific implementation steps of this embodiment are introduced as follows.

[0069] 1. Voltage data acquisition

[0070] The data that need to be obtained include the voltage data of users in the substation area and the three-phase voltage data of each transformer in each substation area. The relevant data can be obtained from existing channels. The voltage data of users in the substation area can be the voltage data collected by the smart meter. Since there may be loss in the data collection or transmission process, the final data matrix is ​​an incomplete data matrix. For example, for users in the substation area, the corresponding initial voltage matrix is:

[0071]

[0072] Among them, m is the number of users in the area, n is the number of time points for voltage measurement, and the column vector of U is Indicates the same time point The voltage measurements of different users, the row vector of U Represents a single user The voltage measurements at different time points, For lost data;

[0073] For the three-phase voltage data of the transformer in the substation, three initial voltage data matrices corresponding to different phases can be obtained:

[0074] ,

[0075]

[0076] in, is the number of all transformers in the substation, the horizontal quantity in the matrix represents the phase voltage data collected at different time points of a phase of the same transformer in the substation, and the column vector represents the same-phase phase voltage data of all transformers in the substation collected at the same time point. There may also be missing data in the initial voltage data matrix, which is not marked above.

[0077] 2. Completion of lost data

[0078] This embodiment completes the lost data according to the following formula:

[0079]

[0080] in, Represents the voltage data matrix Line Column data, , Indicates the number of time points for data collection. In the user voltage data matrix, Represents different users, in the transformer three-phase voltage data matrix, Indicates different transformers.

[0081] For example, for the user voltage data matrix , the completed matrix can be expressed as :

[0082] .

[0083] 3. Data Normalization

[0084] In this embodiment, the Z-score normalization method is used to normalize the voltage data, and the completed user voltage data of the substation area and the phase voltage data of the substation area transformer are processed separately to obtain the normalized user voltage matrix , Normalized transformer A phase voltage matrix , Normalized transformer B phase voltage matrix And the normalized transformer C phase voltage matrix .like It is expressed as:

[0085]

[0086] The normalization formula is:

[0087] In the formula, The first The average voltage data of the row, For the The standard deviation of the voltage data for each row.

[0088] 4. Voltage characteristic parameter extraction

[0089] According to the characteristics of voltage characteristic similarity, if the voltage phase of a user belongs to a phase of a certain substation transformer, then compared with the voltage characteristics of each phase of other substation transformers, the voltage characteristic parameters of the user should be most similar to the voltage characteristic parameters on the corresponding phase of the substation transformer. Therefore, this embodiment determines the substation transformer and phase described by each user through feature comparison.

[0090] Specifically, this embodiment selects the voltage data fluctuation characteristic parameters as the basis for comparison, wherein the voltage fluctuation characteristic parameters include the voltage standard deviation The slope of the voltage curve , can be calculated according to the following formula:

[0091]

[0092]

[0093] In the formula, is the first element in the normalized voltage matrix The average value of the row data.

[0094] According to the above formula, for the normalized user voltage matrix, the voltage standard deviation and voltage curve slope corresponding to each user can be calculated. For the normalized phase voltage matrix of the substation transformer, the voltage standard deviation and voltage curve slope of each phase of each substation transformer can be calculated.

[0095] The voltage characteristic matrix of the users in the substation area is expressed as:

[0096]

[0097] The three-phase voltage characteristic matrices of A, B, and C of K transformers are:

[0098]

[0099] 5. Compare the similarity of voltage characteristic parameters to determine the area and phase to which the user belongs

[0100] When comparing features, traverse the , , The voltage characteristic parameters of the transformers in each substation are compared with the two voltage characteristic parameters of the user to obtain a group of voltage characteristic parameters that are most similar to the user's voltage characteristic parameters. The transformer and phase corresponding to this group of voltage characteristic parameters are the substation and transformer phase to which the user belongs.

[0101] By the above traversal comparison method, we can get the substation area and transformer phase of each user, such as Figure 2 The user phase identification results are shown.

[0102] 6. Recognition result output

[0103] After identifying the substation and transformer phase to which each user belongs, the user and user phase information under each substation can be further obtained, and the user and phase information in each substation can be output.

[0104] Example 2

[0105] Based on the same inventive concept as that of Embodiment 1, this embodiment introduces a phase identification device for a station area, including:

[0106] The data preprocessing module is configured to obtain the voltage data of users in the substation area and the three-phase voltage data of transformers in each substation area, and to complete the lost data;

[0107] The data normalization module is configured to normalize the completed user voltage data of the substation area and the three-phase voltage data of the transformers in each substation area respectively;

[0108] The feature extraction module is configured to extract voltage features based on the normalized data to obtain a voltage feature matrix of users in the substation area and a voltage feature matrix of each phase of the transformer in each substation area;

[0109] The feature matching module is configured to compare the voltage feature data in the voltage feature matrix of the users in the substation area with the voltage feature matrix of each phase of the transformer in each substation area to obtain the substation area and phase to which each user belongs;

[0110] And, the identification result output module is configured to output the phase information of each user in each station area.

[0111] The specific functional implementation of the above functional modules refers to the relevant content in the method of Example 1 and will not be repeated here.

[0112] Example 3

[0113] This embodiment introduces a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the station phase identification method introduced in the first embodiment are implemented.

[0114] For the above embodiments, it should be understood by those skilled in the art that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A phase identification method for a station area taking into account incomplete data, characterized in that: include: Obtain the voltage data of users in the substation area and the three-phase voltage data of transformers in each substation area, and complete the missing data; Normalize the completed user voltage data of the substation area and the three-phase voltage data of the transformers in each substation area respectively; Based on the normalized data, voltage feature extraction is performed to obtain the voltage feature matrix of the users in the substation area and the voltage feature matrix of each phase of the transformer in each substation area; Compare the voltage characteristic data in the voltage characteristic matrix of the users in the substation area and the voltage characteristic matrix of each phase of the transformer in each substation area to obtain the substation area and phase to which each user belongs; Output the phase information of each user in each area; Wherein, corresponding to the voltage data of the users in the substation area, the completion of the lost data includes: S11, determine the initial voltage matrix U: Among them, m is the number of users in the area, n is the number of time points of voltage measurement, and the column vector U of U j =[u 1,j ,u 2,j ,…,u m,j ] T The row vector U represents the voltage measurement values ​​of different users measured at the same time point j. i =[u i,1 ,u i,2 ,…,u i,n ] represents the voltage measurement value of a single user i at different time points, and × represents the missing data; S12, complete the missing data in the initial voltage matrix U according to the following formula: The completed matrix is ​​represented as U * :

2. The method according to claim 1, characterized in that: The normalization process adopts the Z-score normalization method, wherein the voltage data of the users in the substation area after the completion process is normalized to obtain the normalized voltage matrix Among them, for the matrix u after completion processing i,j The normalization formula is: for u i,j The normalized result, μ i The matrix U after completion processing * The average voltage data of a single user i, σ i is the standard deviation of voltage data of a single user i; Normalized voltage matrix It is expressed as:

3. The method according to claim 1, characterized in that: The voltage characteristic data in the transformer area user voltage characteristic matrix and the voltage characteristic matrix of each phase of each transformer area transformer are compared as follows: For each user, the corresponding voltage characteristic parameters are compared with the voltage characteristic parameters in the A, B, and C three-phase voltage characteristic matrices of all substation transformers, and the substation transformer phase corresponding to the voltage characteristic parameters with the highest similarity is determined to be the substation and phase of the corresponding user.

4. A phase identification device for a station area using the phase identification method for a station area taking into account incomplete data as described in any one of claims 1 to 3, characterized in that: include: The data preprocessing module is configured to obtain the voltage data of users in the substation area and the three-phase voltage data of transformers in each substation area, and to complete the lost data; The data normalization module is configured to normalize the completed user voltage data of the substation area and the three-phase voltage data of the transformers in each substation area respectively; The feature extraction module is configured to extract voltage features based on the normalized data to obtain a voltage feature matrix of users in the substation area and a voltage feature matrix of each phase of the transformer in each substation area; The feature matching module is configured to compare the voltage feature data in the voltage feature matrix of the users in the substation area with the voltage feature matrix of each phase of the transformer in each substation area to obtain the substation area and phase to which each user belongs; And, the identification result output module is configured to output the phase information of each user in each station area.

5. The phase identification device according to claim 4, characterized in that: The data normalization module adopts the Z-score normalization method for normalization processing, and the normalization formula is: In the formula, For u i,j The normalized data, u i,j To complete the voltage data of the i-th row and j-th column in the matrix after processing, μ i is the average voltage data of the i-th row in the matrix after completion processing, σ i is the standard deviation of the voltage data in the i-th row.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for phase identification of a station area taking into account incomplete data as described in any one of claims 1 to 3 is implemented.