A phase sequence identification method and device, a storage medium, and an electronic device

Abstract

The application discloses a phase sequence identification method and device, a storage medium and electronic equipment. The method comprises the following steps: collecting voltage time sequence data samples of a total table and each single-phase table to construct initial sample data sets corresponding to each phase sequence and containing a plurality of voltage time sequence data samples; performing calculation and processing based on each initial sample data set to obtain initial clustering center data sets corresponding to each initial sample data set, so as to obtain an initial phase sequence identification model; cyclically updating the initial phase sequence identification model based on each to-be-identified sample, and obtaining a phase sequence identification model when a preset iteration condition is met; identifying a target to-be-identified sample based on the phase sequence identification model, determining a target clustering center corresponding to the target to-be-identified sample, and determining a phase sequence corresponding to the target clustering center as a target phase sequence corresponding to the target to-be-identified sample. The phase sequence identification method in the application does not require manual identification of the phase sequence on site, saves manual cost, and improves work efficiency.

Description

Technical Field

[0001] This invention relates to power line communication technology, and in particular to a phase sequence identification method, apparatus, storage medium, and electronic device. Background Technology

[0002] Power line communication (PLC) technology refers to a communication technology that uses power lines as the communication medium for data transmission. HPLC technology is a high-speed PLC technology that significantly improves communication reliability and stability compared to previous narrowband PLCs, and offers multiple functions such as high-frequency acquisition, transformer area identification, and phase sequence identification. The principle of the HPLC transformer area's phase sequence identification function is as follows: the CCO module in the concentrator and the STA module in the meter acquire their respective voltage zero-crossing time information. The CCO executes the acquisition command, obtains the zero-crossing time information of each STA, compares and analyzes it with the zero-crossing time information locally in the CCO, identifies the meter phase sequence information, and reports it to the master station. However, this method can only identify the phase sequence of single-phase meters and cannot identify the phase sequence of three-phase meters. Currently, three-phase meter phase sequence identification requires on-site verification, which is labor-intensive and inefficient. Summary of the Invention

[0003] In view of this, the present invention provides a phase sequence identification method, device, storage medium and electronic device, the main purpose of which is to solve the problem that the current three-phase meter phase sequence identification requires on-site verification, which is labor-intensive and inefficient.

[0004] To address the above problems, this application provides a phase sequence identification method, comprising:

[0005] Collect voltage timing data samples from each phase sequence of the transformer area's main meter and each individual phase meter to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence.

[0006] Each initial sample dataset is processed to obtain an initial cluster center dataset corresponding to each initial sample dataset, thereby obtaining an initial phase sequence recognition model.

[0007] The initial phase sequence recognition model is updated iteratively based on each sample to be identified, and the phase sequence recognition model is obtained when the preset iteration conditions are met.

[0008] Based on the phase sequence recognition model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample to be identified is determined, so that the phase sequence corresponding to the target cluster center is the target phase sequence corresponding to the target sample to be identified.

[0009] Optionally, the step of calculating an initial cluster center dataset corresponding to each of the initial sample datasets to obtain an initial phase sequence recognition model specifically includes:

[0010] The mean of the voltage time series data corresponding to each sample at the same time in each of the initial sample datasets is calculated to obtain the initial cluster center sample set corresponding to each phase sequence.

[0011] Based on the initial sample datasets and the initial cluster center sample sets, a model is constructed using the first preset function to obtain an initial phase sequence recognition model for recognizing the phase sequence of the three-phase table.

[0012] Optionally, the step of iteratively updating the initial phase sequence recognition model based on each sample to be identified, and obtaining the phase sequence recognition model when a preset iteration condition is met, specifically includes:

[0013] Based on the initial sample datasets and the initial cluster center sample sets, a second preset function is used to perform calculations to obtain the first calculated distance value.

[0014] Based on each of the sample sets to be identified and each of the initial cluster center sample sets, a first preset function is used for calculation to obtain the first distance values ​​corresponding to each of the sample sets to be identified and each of the initial cluster center sample sets respectively.

[0015] Based on each of the first distance values ​​and each of the sample sets to be identified, a second preset function is used to perform calculation processing to obtain a second calculated distance value;

[0016] Based on the first calculated distance value and the second calculated distance value, a judgment is made. When the judgment result meets the preset conditions, the phase sequence recognition model is obtained. When the judgment result does not meet the preset conditions, the initial sample dataset of the previous generation is updated iteratively based on each of the sample sets to be identified to obtain the initial sample dataset of the current generation. The first calculated distance value and the second distance value of the previous generation are updated based on each of the sample sets to be identified and the initial sample dataset of the current generation until the first calculated distance value and the second distance value of the current generation meet the preset conditions to obtain the phase sequence recognition model.

[0017] Optionally, the step of calculating the second calculated distance value based on each of the first distance values ​​and each of the sample sets to be identified using a second preset function specifically includes:

[0018] Based on each of the first distance values, each of the sample sets to be identified is divided into samples, and the data in each of the initial sample datasets is updated to obtain each of the first sample sets.

[0019] The voltage time series data in each of the first sample sets at the same time are averaged to obtain the first cluster center time series dataset corresponding to each of the first sample sets.

[0020] Based on each of the first sample sets and each of the first cluster center time series datasets, a second preset function is used for calculation to obtain the second calculated distance value.

[0021] Optionally, the step of dividing each of the first sample sets to be identified based on each of the first distance values, updating the data in each of the initial sample datasets, and obtaining each first sample set specifically includes:

[0022] Based on each of the first distance values, the minimum distance value among the first distance values ​​is determined to be the first target distance value;

[0023] Based on the first target distance value, the sample set to be identified with the first target distance value is divided into the initial sample set with the first target distance value, so as to obtain the first sample set corresponding to the first phase sequence;

[0024] Each of the first distance values ​​is filtered to obtain each of the second distance values;

[0025] Based on each of the second distance values, the minimum distance value among the second distance values ​​is determined as the second target distance value;

[0026] Based on the second target distance value, the sample set to be identified with the calculated second target distance value is divided into the corresponding initial sample set, so as to obtain the first sample set corresponding to the second phase sequence and the first sample set corresponding to the third phase sequence, so as to obtain the first sample set corresponding to each phase sequence.

[0027] Optionally, the step of filtering each of the first distance values ​​to obtain each of the second distance values ​​specifically includes:

[0028] Based on the first target distance value, determine the target sample set to be identified by calculating the first target distance value and the target initial cluster center sample set corresponding to the target phase sequence;

[0029] Based on the target sample set to be identified and the target initial sample dataset, each of the first distance values ​​is filtered to remove the first distance values ​​calculated by the target sample set to be identified and / or the target cluster center sample set to obtain each of the second distance values.

[0030] Optionally, when the judgment result does not meet the preset conditions, the method iteratively updates the initial sample dataset of the previous generation based on each of the sample sets to be identified to obtain the initial sample dataset of the current generation. The method further includes:

[0031] Determine whether the current iteration count meets the preset conditions;

[0032] When the determination result is that the current iteration number is greater than or equal to a preset threshold, the phase sequence recognition model is obtained;

[0033] When the determination result is that the current iteration number is less than a preset threshold, the initial sample dataset of the previous generation is updated cyclically based on each of the sample sets to be identified, so as to obtain the initial sample dataset of the current generation.

[0034] To solve the above problems, this application provides a phase sequence identification device, comprising:

[0035] Construction module: Used to collect voltage timing data samples of each phase sequence of the transformer area's main meter and voltage timing data samples of each single phase meter, in order to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence.

[0036] Calculation module: used to perform calculations based on each of the initial sample datasets to obtain the initial cluster center datasets corresponding to each of the initial sample datasets, so as to obtain the initial phase sequence recognition model;

[0037] Update module: used to iteratively update the initial phase sequence recognition model based on each sample to be identified, and obtain the phase sequence recognition model when the preset iteration conditions are met;

[0038] Identification module: used to identify the target sample to be identified based on the phase sequence identification model, determine the target cluster center corresponding to the target sample to be identified, and determine the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample to be identified.

[0039] To address the aforementioned problems, this application provides a storage medium storing a computer program that, when executed by a processor, implements the steps of the phase sequence identification method described above.

[0040] To address the aforementioned problems, this application provides an electronic device, comprising at least a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the phase sequence identification method described above.

[0041] This application collects voltage timing data samples from the overall phase sequence meter of a transformer substation and from individual phase meters to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence. Based on each initial sample dataset, an initial cluster center dataset corresponding to each initial sample dataset is calculated to obtain an initial phase sequence identification model. The initial phase sequence identification model is iteratively updated based on each sample to be identified, and a phase sequence identification model is obtained when a preset iteration condition is met. Based on the phase sequence identification model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample is determined, thus determining the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample. The phase sequence identification method in this application efficiently identifies the unknown phase sequence of a three-phase meter by training the phase sequence identification model, eliminating the need for manual on-site identification, saving labor costs, and improving work efficiency.

[0042] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0043] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0044] Figure 1 A schematic flowchart of a phase sequence identification method provided in an embodiment of this application is shown;

[0045] Figure 2 A flowchart illustrating another phase sequence identification method provided in an embodiment of this application is shown;

[0046] Figure 3 A structural block diagram of a phase sequence identification method device provided in an embodiment of this application is shown. Detailed Implementation

[0047] Various embodiments and features of this application are described herein with reference to the accompanying drawings.

[0048] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this application will be apparent to those skilled in the art.

[0049] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0050] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0051] It should also be understood that although this application has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this application.

[0052] The above and other aspects, features and advantages of this application will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0053] Specific embodiments of this application are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the application. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to teach those skilled in the art to use this application in a variety of substantially any suitable detailed structures.

[0054] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments,” all of which may refer to one or more of the same or different embodiments according to this application.

[0055] This application provides a phase sequence identification method, such as... Figure 1 As shown, it includes:

[0056] Step S101: Collect voltage timing data samples of each phase sequence of the transformer area's main meter and voltage timing data samples of each single phase meter to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence.

[0057] In the specific implementation process of this step, the voltage curve data of 96 points of each meter under the same date and time period in the power consumption information collection system are queried by phase to obtain the first voltage time series dataset corresponding to each phase sequence of the total meter of the distribution area and the second voltage time series dataset corresponding to each single phase meter. Based on each first voltage time series data and each second voltage time series data, the data is reorganized to obtain an initial sample dataset containing several voltage time series data samples corresponding to each phase sequence.

[0058] Step S102: Perform calculations based on each of the initial sample datasets to obtain the initial cluster center datasets corresponding to each of the initial sample datasets, so as to obtain the initial phase sequence recognition model;

[0059] In the specific implementation process of this step, the mean value of the voltage time series data corresponding to each sample at the same time in each of the initial sample datasets is calculated to obtain the initial cluster center sample set corresponding to each phase sequence; based on each of the initial sample datasets and each of the initial cluster center sample sets, a model is constructed using the first preset function to obtain the initial phase sequence identification model for identifying the phase sequence of the three-phase meter. Based on the first voltage time-series data and the second voltage time-series data, data recombination is performed to obtain an initial sample dataset containing several voltage time-series data samples corresponding to each phase sequence. Specifically, the phase sequence of the transformer area master meter and the single-phase meter is queried through the electricity information acquisition system to obtain the first voltage time-series data corresponding to the three phase sequences of the transformer area master meter, the phase sequence corresponding to each single-phase voltmeter, and the second voltage time-series dataset corresponding to each single-phase voltmeter. The phase sequence includes: phase A, phase B, and phase C. Each first voltage time-series data includes: the first voltage time-series dataset corresponding to phase A of the transformer area master meter, the first voltage time-series dataset corresponding to phase B of the transformer area master meter, and the first voltage time-series dataset corresponding to phase C of the transformer area master meter. Each second voltage time-series dataset includes: the second voltage time-series dataset corresponding to each single-phase meter of phase A, the second voltage time-series dataset corresponding to each single-phase meter of phase B, and the second voltage time-series dataset corresponding to each single-phase meter of phase C. The voltage timing data of the same phase sequence from the transformer substation master meter and each individual phase meter are recombined to obtain three initial sample datasets: Specifically, the first voltage timing dataset corresponding to phase sequence A of the transformer substation master meter is recombined with the second voltage timing dataset corresponding to each A-phase sequence individual phase meter to obtain the initial sample dataset corresponding to phase sequence A; the first voltage timing dataset corresponding to phase sequence B of the transformer substation master meter is recombined with the second voltage timing dataset corresponding to each B-phase sequence individual phase meter to obtain the initial sample dataset corresponding to phase sequence B; the first voltage timing dataset corresponding to phase sequence C of the transformer substation master meter is recombined with the second voltage timing dataset corresponding to each C-phase sequence individual phase meter to obtain the initial sample dataset corresponding to phase sequence C. This yields the initial sample datasets corresponding to each phase sequence. The mean of the voltage time series data corresponding to each sample at the same time in each of the initial sample datasets is calculated to obtain the initial cluster center sample set corresponding to each phase sequence; based on each of the initial sample datasets and each of the initial cluster center sample sets, a model is constructed using a first preset function to obtain an initial phase sequence identification model for identifying the phase sequence of the three-phase meter.

[0060] Step S103: Update the initial phase sequence recognition model iteratively based on each sample to be identified, and obtain the phase sequence recognition model when the preset iteration conditions are met;

[0061] In this step, based on each initial sample dataset and each initial cluster center sample set, a first preset function is used to calculate and process the data to obtain a first calculated distance value. Based on each sample set to be identified and each initial cluster center sample set, a second preset function is used to calculate and process the data to obtain a first distance value corresponding to each sample set to be identified and each initial cluster center sample set. Based on each first distance value and each sample set to be identified, a second calculated distance value is obtained by calculating and processing the data using the first preset function. Based on the first calculated distance value and the second calculated distance value, a judgment is made. When the judgment result meets a preset condition, the phase sequence recognition model is obtained. When the judgment result does not meet the preset condition, the initial sample dataset of the previous generation is updated iteratively based on each sample set to be identified to obtain the initial sample dataset of the current generation. The first calculated distance value and the second distance value of the previous generation are updated based on each sample set to be identified and the initial sample dataset of the current generation until the first calculated distance value and the second distance value of the current generation meet the preset condition, at which point the phase sequence recognition model is obtained.

[0062] Step S104: Identify the target sample to be identified based on the phase sequence recognition model, determine the target cluster center corresponding to the target sample to be identified, and determine the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample to be identified.

[0063] In this step, the target sample to be identified is input into the phase sequence recognition model. Based on the phase sequence recognition model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample to be identified is determined. The phase sequence corresponding to the target cluster center is then determined as the target phase sequence corresponding to the target sample to be identified.

[0064] This application collects voltage timing data samples from the overall phase sequence meter of a transformer substation and from individual phase meters to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence. Based on each initial sample dataset, an initial cluster center dataset corresponding to each initial sample dataset is calculated to obtain an initial phase sequence identification model. The initial phase sequence identification model is iteratively updated based on each sample to be identified, and a phase sequence identification model is obtained when a preset iteration condition is met. Based on the phase sequence identification model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample is determined, thus determining the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample. The phase sequence identification method in this application efficiently identifies the unknown phase sequence of a three-phase meter by training the phase sequence identification model, eliminating the need for manual on-site identification, saving labor costs, and improving work efficiency.

[0065] Another embodiment of this application provides a phase sequence identification method, such as... Figure 2 As shown, it includes:

[0066] Step S201: Collect voltage timing data samples of each phase sequence of the transformer area's main meter and voltage timing data samples of each single phase meter to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence.

[0067] In this step, the electricity information collection system queries 96 voltage curve data points from various meters within the same period on the same date in the transformer substation area. This yields the first voltage time-series dataset corresponding to each phase sequence of the main meter in the substation area, the second voltage time-series dataset corresponding to each single-phase meter, and the sample sets to be identified for each phase sequence of the three-phase meter. The voltage time-series dataset is a collection of voltage values ​​corresponding to each moment within a predetermined time period. For example, the predetermined time period can be 24 hours a day. At a preset sampling frequency of one voltage time-series data point every 15 minutes, within 24 hours, 96 voltage time-series data points are collected for each of the three phase sequences of the main meter in the substation area, each of the single-phase meters, and each of the three-phase meters. Therefore, each of the first voltage time-series datasets, each of the second voltage time-series datasets, and each sample set to be identified contains 96 voltage time-series data points. In practical applications, the predetermined time period can be set according to actual needs: for example, 1 day, 2 days, etc.; the preset sampling frequency can also be set according to actual needs: for example, 5 minutes, 20 minutes, etc. Based on each of the first voltage time-series datasets and each of the second voltage time-series datasets, data recombination is performed to obtain an initial sample dataset containing several voltage time-series data samples corresponding to each phase sequence. Specifically, by querying the phase sequence of the transformer area master meter and the single-phase meter through the electricity information acquisition system, the first voltage time-series data corresponding to the three phase sequences of the transformer area master meter, the phase sequence corresponding to each single-phase voltmeter, and the second voltage time-series dataset corresponding to each single-phase voltmeter are obtained. The phase sequence includes: phase A, phase B, and phase C. Each of the first voltage time-series datasets includes: the first voltage time-series dataset corresponding to phase A of the transformer area master meter, the first voltage time-series dataset corresponding to phase B of the transformer area master meter, and the first voltage time-series dataset corresponding to phase C of the transformer area master meter. Each of the second voltage time-series datasets includes: the second voltage time-series dataset corresponding to each single-phase meter of phase A, the second voltage time-series dataset corresponding to each single-phase meter of phase B, and the second voltage time-series dataset corresponding to each single-phase meter of phase C. The voltage timing data of the same phase sequence from the transformer area master meter and each individual phase meter are recombined to obtain three initial sample datasets: Specifically, the first voltage timing dataset corresponding to phase sequence A of the transformer area master meter is recombined with the second voltage timing dataset corresponding to each A phase sequence individual phase meter to obtain the initial sample dataset corresponding to phase sequence A; the first voltage timing dataset corresponding to phase sequence B of the transformer area master meter is recombined with the second voltage timing dataset corresponding to each B phase sequence individual phase meter to obtain the initial sample dataset corresponding to phase sequence B; the first voltage timing dataset corresponding to phase sequence C of the transformer area master meter is recombined with the second voltage timing dataset corresponding to each C phase sequence individual phase meter to obtain the initial sample dataset corresponding to phase sequence C, thus obtaining the initial sample dataset corresponding to each phase sequence.

[0068] Step S202: Calculate the mean of the voltage time series data corresponding to each sample at the same time in each of the initial sample datasets to obtain the initial cluster center sample set corresponding to each phase sequence;

[0069] In the specific implementation process of this step, the voltage time series data in the initial sample dataset corresponding to phase A, phase B, and phase C are respectively averaged, and the voltage time series data corresponding to each sample at the same time are calculated to obtain the initial cluster center sample set corresponding to phase A, phase B, and phase C.

[0070] Step S203: Based on each of the initial sample datasets and each of the initial cluster center sample sets, a model is constructed using the first preset function to obtain an initial phase sequence identification model for identifying the phase sequence of the three-phase table;

[0071] In the specific implementation of this step, the first preset function is as shown in Formula 1 below:

[0072]

[0073] Where i represents the number of sample sets to be identified; j represents the number of initial cluster center sample sets; L ij Let be the first distance value between each voltage time series data in the i-th sample set to be identified and each initial voltage mean time series data in the j-th initial cluster center time series dataset. Based on each of the initial sample datasets and each of the initial cluster center sample sets, a model is constructed using the first preset function to obtain an initial phase sequence identification model for identifying the phase sequence of the three-phase meter. Subsequently, phase sequence identification is performed on the phase sequence sample set data to be identified based on the initial phase sequence identification model to obtain the cluster centers corresponding to each phase sequence sample set to be identified, thereby obtaining the phase sequence corresponding to each cluster center.

[0074] Step S204: Based on each of the initial sample datasets and each of the initial cluster center sample sets, a second preset function is used to perform calculation processing to obtain a first calculated distance value;

[0075] In the specific implementation process of this step, the second preset function is as shown in Formula 2 below:

[0076]

[0077] Where s is the initial number of sample datasets, m s For the initial voltage mean time series data, C s For each initial sample dataset, U q C s Voltage time series data in the sample set.

[0078] The voltage time series data and the initial cluster center sample sets in each of the initial sample datasets are substituted into Formula 2 to calculate the first calculated distance value E1.

[0079] Step S205: Based on each of the sample sets to be identified and each of the initial cluster center sample sets, a preset first function is used to perform calculation processing to obtain the first distance values ​​corresponding to each of the sample sets to be identified and each of the initial cluster center sample sets respectively;

[0080] In the specific implementation of this step, the preset second function is as shown in Formula 2 below:

[0081]

[0082] Where i represents the number of samples to be identified; j represents the number of samples in the initial cluster center set; : L ij This is the first distance value between the voltage time series data in the i-th sample set to be identified and the initial voltage mean time series data in the j-th initial cluster center sample set. Specifically, a mapping relationship is constructed between each of the sample sets to be identified and each of the initial cluster center sample sets; for example, the three sample sets to be identified with unknown phase sequences are a, b, and c; the three initial cluster center sample sets are d, e, and f; where phase sequence A corresponds to d, phase sequence B corresponds to e, and phase sequence C corresponds to f. Then, the mapping relationships are constructed as follows: mapping relationship between a and d, mapping relationship between a and e, mapping relationship between a and f, mapping relationship between b and d, mapping relationship between b and e, mapping relationship between b and f, mapping relationship between c and d, mapping relationship between c and e, and mapping relationship between c and f, resulting in 9 mapping relationships; the time series data in the sample sets to be identified and the voltage mean time series data in the initial cluster center sample sets corresponding to each mapping relationship are substituted into the above formula 2 to calculate the first distance value corresponding to each mapping relationship.

[0083] Step S206: Based on each of the first distance values ​​and each of the sample sets to be identified, a first preset function is used to perform calculation processing to obtain a second calculated distance value;

[0084] In this step, the following steps are implemented: First, the sample sets to be identified are divided based on each first distance value; data in each initial sample dataset is updated to obtain each first sample set; based on each first distance value, the minimum distance value among the first distance values ​​is determined as the first target distance value; based on the first target distance value, the sample sets to be identified with the calculated first target distance value are divided into the initial sample datasets with the calculated first target distance value to obtain the first sample set corresponding to the first phase sequence; each first distance value is filtered to obtain each second distance value; specifically, based on the first target distance value, the target sample set to be identified with the calculated first target distance value and the target initial mean time series sample set corresponding to the target phase sequence are determined; based on the target sample set to be identified and the target initial sample dataset, each first distance value is filtered to remove the first distance values ​​calculated from the target sample set to be identified and / or the target initial cluster center sample set to obtain each second distance value. For example: if the first distance value calculated through the mapping relationship between b and d is the smallest among the above 9 mapping relationships, then the mapping relationship containing b and d, or containing both b and d, is removed. The remaining 4 mapping relationships, namely the mapping relationship between a and e, the mapping relationship between a and f, the mapping relationship between c and e, and the mapping relationship between c and f, correspond to the second distance value. b is assigned to the initial sample dataset of the phase sequence corresponding to d. That is, when d is phase sequence A, the sample set to be identified corresponding to b is assigned to the initial sample dataset corresponding to phase sequence A. Based on each second distance value, the minimum distance value among the second distance values ​​is determined to be the second target distance value. Based on the second target distance value, the sample set to be identified with the calculated second target distance value is assigned to the corresponding initial sample dataset, thus obtaining the first sample set corresponding to the second phase sequence and the first sample set corresponding to the third phase sequence, and so on, to obtain the first sample set corresponding to each phase sequence. For example, among the four remaining mapping relationships—the mapping relationship between a and e, the mapping relationship between a and f, the mapping relationship between c and e, and the mapping relationship between c and f—the second distance value corresponding to the mapping relationship between a and f is the smallest. Therefore, a is assigned to the initial sample dataset corresponding to the phase sequence f. That is, when f is phase sequence C, the sample set to be identified corresponding to a is assigned to the initial sample dataset corresponding to phase sequence C. After removing mapping relationships containing a and f, or both a and f, the remaining mapping relationship is c and e. When e is phase sequence B, the sample set to be identified corresponding to c is assigned to the initial sample dataset corresponding to phase sequence B. The voltage time-series data in each of the first sample sets at the same time are averaged to obtain the first cluster center time-series dataset corresponding to each of the first sample sets. Based on each of the first sample sets and each of the first cluster center time-series datasets, a first preset function is used for calculation to obtain the second calculated distance value E2.

[0085] Step S207: Based on the first calculated distance value and the second calculated distance value, a judgment is made. When the judgment result meets the preset conditions, the phase sequence recognition model is obtained.

[0086] In this step, the difference between the first calculated distance value E1 and the second calculated distance value E2 is calculated, and then the absolute value of the difference between the first calculated distance value E1 and the second calculated distance value E2 is calculated. When the calculated absolute value is less than or equal to a preset threshold, the phase sequence recognition model is obtained.

[0087] Step S208: When the judgment result does not meet the preset conditions, the initial phase sequence recognition model of the previous generation is updated iteratively based on each of the sample sets to be identified until the first calculated distance value and the second distance value of the current generation meet the preset conditions to obtain the phase sequence recognition model.

[0088] In this step, when the judgment result does not meet the preset conditions, the initial sample dataset of the previous generation is updated iteratively based on each of the sample sets to be identified, and the first calculated distance value and the second distance value of the previous generation are updated based on each of the sample sets to be identified and the initial sample dataset of the current generation, until the first calculated distance value and the second distance value of the current generation meet the preset conditions to obtain the phase sequence recognition model. In the specific implementation process, the phase sequence recognition model can also be obtained by judging whether the current iteration number meets the preset conditions. Specifically, it is determined whether the current iteration number meets a preset condition; when the determination result is that the current iteration number is greater than or equal to a preset threshold, the phase sequence recognition model is obtained; when the determination result is that the current iteration number is less than the preset threshold, the initial sample dataset of the previous generation is updated iteratively based on each of the sample sets to be identified to obtain the initial sample dataset of the current generation, and calculation processing is performed based on the initial sample set of the current generation to obtain the cluster center sample set of the current generation corresponding to the initial sample set of the current generation, so as to update the initial phase sequence recognition model based on the initial sample set of the current generation and the cluster center sample set of the current generation to obtain the initial phase sequence recognition model of the current generation, until the current iteration number is greater than or equal to the preset threshold to obtain the phase sequence recognition model.

[0089] Step S209: Identify the target sample to be identified based on the phase sequence recognition model, determine the target cluster center corresponding to the target sample to be identified, and determine the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample to be identified.

[0090] In this step, the target sample to be identified is input into the phase sequence recognition model. Based on the phase sequence recognition model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample to be identified is determined. The phase sequence corresponding to the target cluster center is then determined as the target phase sequence corresponding to the target sample to be identified.

[0091] This application constructs an initial sample dataset containing several voltage time-series data samples corresponding to each phase sequence by collecting voltage time-series data samples of each phase sequence from the overall meter of the transformer substation and voltage time-series data samples of each individual phase meter. The mean of the voltage time-series data corresponding to each sample at the same time in each of the initial sample datasets is calculated to obtain an initial cluster center sample set corresponding to each phase sequence. Based on the initial sample datasets and the initial cluster center sample sets, a model is constructed using a first preset function to obtain an initial phase sequence identification model for identifying the phase sequence of the three-phase meters. Based on the initial sample datasets and the initial cluster center sample sets, a second preset function is used for calculation to obtain a first calculated distance value. Based on the sample sets to be identified and the initial cluster center sample sets, a preset first function is used for calculation to obtain... The method involves defining a first distance value between each set of samples to be identified and each set of initial cluster centers. Based on these first distance values ​​and each set of samples to be identified, a second calculated distance value is obtained using a first preset function. A judgment is made based on the first and second calculated distance values. When the judgment result meets a preset condition, the phase sequence identification model is obtained. When the judgment result does not meet the preset condition, the initial phase sequence identification model of the previous generation is iteratively updated based on each set of samples to be identified until the first and second calculated distance values ​​of the current generation meet the preset condition, thus obtaining the phase sequence identification model. The target sample to be identified is identified based on the phase sequence identification model, and the target cluster center corresponding to the target sample is determined, thereby determining the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample. The phase sequence identification method in this application efficiently identifies the unknown phase sequence of a three-phase meter by training a phase sequence identification model, eliminating the need for manual on-site phase sequence identification, saving labor costs, and improving work efficiency.

[0092] Another embodiment of this application provides a phase sequence identification device, such as... Figure 3 As shown, it includes:

[0093] Module 1: Used to collect voltage timing data samples of each phase sequence of the transformer substation master meter and voltage timing data samples of each single phase meter, so as to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence.

[0094] Calculation module 2: is used to perform calculations based on each of the initial sample datasets to obtain the initial cluster center datasets corresponding to each of the initial sample datasets, so as to obtain the initial phase sequence recognition model;

[0095] Update module 3: used to iteratively update the initial phase sequence recognition model based on each sample to be identified, and obtain the phase sequence recognition model when the preset iteration conditions are met;

[0096] Identification module 4: is used to identify the target sample to be identified based on the phase sequence identification model, determine the target cluster center corresponding to the target sample to be identified, and determine the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample to be identified.

[0097] In the specific implementation process, the calculation module 2 is specifically used to: calculate the mean of the voltage time series data corresponding to each sample at the same time in each of the initial sample datasets to obtain the initial cluster center sample set corresponding to each phase sequence; and construct a model based on each of the initial sample datasets, each of the initial cluster center sample sets, and using a first preset function to obtain an initial phase sequence identification model for identifying the phase sequence of the three-phase meter.

[0098] In specific implementation, the update module 3 is specifically used for: calculating and processing a first calculated distance value using a second preset function based on each initial sample dataset and each initial cluster center sample set; calculating and processing a first distance value corresponding to each sample set to be identified and each initial cluster center sample set using a first preset function based on each sample set to be identified and each initial cluster center sample set respectively; calculating and processing a second calculated distance value using a second preset function based on each first distance value and each sample set to be identified; judging based on the first calculated distance value and the second calculated distance value, and obtaining the phase sequence recognition model when the judgment result meets the preset condition; when the judgment result does not meet the preset condition, iteratively updating the initial sample dataset of the previous generation based on each sample set to be identified to obtain the initial sample dataset of the current generation, and updating the first calculated distance value and the second distance value of the previous generation based on each sample set to be identified and the initial sample dataset of the current generation, until the first calculated distance value and the second distance value of the current generation meet the preset condition to obtain the phase sequence recognition model.

[0099] In the specific implementation process, the update module 3 is further used to: divide each of the sample sets to be identified based on each of the first distance values, update the data in each of the initial sample datasets, and obtain each of the first sample sets; perform mean calculation processing on the voltage time series data in each of the first sample sets at the same time to obtain the first cluster center time series dataset corresponding to each of the first sample sets; and perform calculation processing using a second preset function based on each of the first sample sets and each of the first cluster center time series datasets to obtain the second calculated distance value.

[0100] In the specific implementation process, the update module 3 is further configured to: determine the minimum distance value among the first distance values ​​as the first target distance value based on each first distance value; divide the sample set to be identified with the calculated first target distance value into the initial sample dataset with the calculated first target distance value based on the first target distance value, to obtain the first sample set corresponding to the first phase sequence; perform filtering processing on each first distance value to obtain each second distance value; determine the minimum distance value among the second distance values ​​as the second target distance value based on each second distance value; divide the sample set to be identified with the calculated second target distance value into the corresponding initial sample dataset based on the second target distance value, to obtain the first sample set corresponding to the second phase sequence and the first sample set corresponding to the third phase sequence, so as to obtain the first sample set corresponding to each phase sequence.

[0101] In the specific implementation process, the update module 3 is further configured to: determine the target sample set to be identified and the target initial cluster center sample set corresponding to the target phase sequence based on the first target distance value; filter each first distance value based on the target sample set to be identified and the target initial sample set, and remove the first distance values ​​calculated through the target sample set to be identified and / or the target cluster center sample set to obtain each second distance value.

[0102] In the specific implementation process, the update module 3 is also used to: determine whether the current iteration number meets the preset condition; when the determination result is that the current iteration number is greater than or equal to the preset threshold, obtain the phase sequence recognition model; when the determination result is that the current iteration number is less than the preset threshold, iteratively update the initial sample dataset of the previous generation based on each of the samples to be identified, and obtain the initial sample dataset of the current generation.

[0103] This application collects voltage timing data samples from the overall phase sequence meter of a transformer substation and from individual phase meters to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence. Based on each initial sample dataset, an initial cluster center dataset corresponding to each initial sample dataset is calculated to obtain an initial phase sequence identification model. The initial phase sequence identification model is iteratively updated based on each sample to be identified, and a phase sequence identification model is obtained when a preset iteration condition is met. Based on the phase sequence identification model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample is determined, thus determining the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample. The phase sequence identification method in this application efficiently identifies the unknown phase sequence of a three-phase meter by training the phase sequence identification model, eliminating the need for manual on-site identification, saving labor costs, and improving work efficiency.

[0104] Another embodiment of this application provides a storage medium storing a computer program, which, when executed by a processor, implements the following method steps:

[0105] Step 1: Collect voltage timing data samples of each phase sequence of the transformer area's main meter and voltage timing data samples of each single phase meter to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence.

[0106] Step 2: Perform calculations based on each of the initial sample datasets to obtain the initial cluster center datasets corresponding to each of the initial sample datasets, so as to obtain the initial phase sequence recognition model;

[0107] Step 3: Iteratively update the initial phase sequence recognition model based on each sample to be identified, and obtain the phase sequence recognition model when the preset iteration conditions are met;

[0108] Step 4: Identify the target sample based on the phase sequence recognition model, determine the target cluster center corresponding to the target sample, and determine the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample.

[0109] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0110] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0111] The specific implementation process of the above method steps can be found in the embodiments of the above arbitrary phase sequence identification method, which will not be repeated here.

[0112] This application collects voltage timing data samples from the overall phase sequence meter of a transformer substation and from individual phase meters to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence. Based on each initial sample dataset, an initial cluster center dataset corresponding to each initial sample dataset is calculated to obtain an initial phase sequence identification model. The initial phase sequence identification model is iteratively updated based on each sample to be identified, and a phase sequence identification model is obtained when a preset iteration condition is met. Based on the phase sequence identification model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample is determined, thus determining the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample. The phase sequence identification method in this application efficiently identifies the unknown phase sequence of a three-phase meter by training the phase sequence identification model, eliminating the need for manual on-site identification, saving labor costs, and improving work efficiency.

[0113] Another embodiment of this application provides an electronic device, which can be a server. The electronic device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the program is executed by the processor, it implements the functions or steps of a sequence identification method on the server side.

[0114] In one embodiment, an electronic device is provided, which can be a client. The electronic device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with an external server via a network connection. When the program of the electronic device is executed by the processor, it implements the functions or steps of a sequence identification method on the client side.

[0115] Another embodiment of this application provides an electronic device, including at least a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program in the memory, performs the following method steps:

[0116] Step 1: Collect voltage timing data samples of each phase sequence of the transformer area's main meter and voltage timing data samples of each single phase meter to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence.

[0117] Step 2: Perform calculations based on each of the initial sample datasets to obtain the initial cluster center datasets corresponding to each of the initial sample datasets, so as to obtain the initial phase sequence recognition model;

[0118] Step 3: Iteratively update the initial phase sequence recognition model based on each sample to be identified, and obtain the phase sequence recognition model when the preset iteration conditions are met;

[0119] Step 4: Identify the target sample based on the phase sequence recognition model, determine the target cluster center corresponding to the target sample, and determine the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample.

[0120] The specific implementation process of the above method steps can be found in the embodiments of the above phase sequence identification method, which will not be repeated here.

[0121] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.

Claims

1. A phase sequence identification method, characterized in that, include: Collect voltage timing data samples from each phase sequence of the transformer area's main meter and each individual phase meter to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence. Each initial sample dataset is processed to obtain an initial cluster center dataset corresponding to each initial sample dataset, thereby obtaining an initial phase sequence recognition model. The initial phase sequence recognition model is updated iteratively based on each sample to be identified, and the phase sequence recognition model is obtained when the preset iteration conditions are met. Based on the phase sequence recognition model, the target sample to be identified is identified, and the target cluster center corresponding to the target sample to be identified is determined, so that the phase sequence corresponding to the target cluster center is the target phase sequence corresponding to the target sample to be identified. The step of calculating an initial cluster center dataset corresponding to each of the initial sample datasets to obtain an initial phase sequence recognition model specifically includes: The mean of the voltage time series data corresponding to each sample at the same time in each of the initial sample datasets is calculated to obtain the initial cluster center sample set corresponding to each phase sequence. Based on the initial sample datasets and the initial cluster center sample sets, a model is constructed using the first preset function to obtain an initial phase sequence recognition model for recognizing the phase sequence of the three-phase table. The process of iteratively updating the initial phase sequence recognition model based on each sample to be identified, and obtaining the phase sequence recognition model when a preset iteration condition is met, specifically includes: Based on the initial sample datasets and the initial cluster center sample sets, a second preset function is used to perform calculations to obtain the first calculated distance value. Based on each of the sample sets to be identified and each of the initial cluster center sample sets, a first preset function is used for calculation to obtain the first distance values ​​corresponding to each of the sample sets to be identified and each of the initial cluster center sample sets respectively. Based on each of the first distance values ​​and each of the sample sets to be identified, a second preset function is used to perform calculation processing to obtain a second calculated distance value; Based on the first calculated distance value and the second calculated distance value, a judgment is made. When the judgment result meets the preset conditions, the phase sequence recognition model is obtained. When the judgment result does not meet the preset conditions, the initial sample dataset of the previous generation is updated iteratively based on each of the sample sets to be identified to obtain the initial sample dataset of the current generation. The first calculated distance value and the second distance value of the previous generation are updated based on each of the sample sets to be identified and the initial sample dataset of the current generation until the first calculated distance value and the second distance value of the current generation meet the preset conditions to obtain the phase sequence recognition model.

2. The method as described in claim 1, characterized in that, The step of calculating and processing the second calculated distance value based on each of the first distance values ​​and each of the sample sets to be identified using a second preset function specifically includes: Based on each of the first distance values, each of the sample sets to be identified is divided into samples, and the data in each of the initial sample datasets is updated to obtain each of the first sample sets. The voltage time series data in each of the first sample sets at the same time are averaged to obtain the first cluster center time series dataset corresponding to each of the first sample sets. Based on each of the first sample sets and each of the first cluster center time series datasets, a second preset function is used for calculation to obtain the second calculated distance value.

3. The method as described in claim 2, characterized in that, The step of dividing each of the target sample sets based on each of the first distance values, updating the data in each of the initial sample datasets, and obtaining each first sample set specifically includes: Based on each of the first distance values, the minimum distance value among the first distance values ​​is determined to be the first target distance value; Based on the first target distance value, the sample set to be identified with the first target distance value is divided into the initial sample set with the first target distance value, so as to obtain the first sample set corresponding to the first phase sequence; Each of the first distance values ​​is filtered to obtain each of the second distance values; Based on each of the second distance values, the minimum distance value among the second distance values ​​is determined as the second target distance value; Based on the second target distance value, the sample set to be identified with the calculated second target distance value is divided into the corresponding initial sample set, so as to obtain the first sample set corresponding to the second phase sequence and the first sample set corresponding to the third phase sequence, so as to obtain the first sample set corresponding to each phase sequence.

4. The method as described in claim 3, characterized in that, The step of filtering each of the first distance values ​​to obtain each of the second distance values ​​specifically includes: Based on the first target distance value, determine the target sample set to be identified by calculating the first target distance value and the target initial cluster center sample set corresponding to the target phase sequence; Based on the target sample set to be identified and the target initial sample dataset, each of the first distance values ​​is filtered to remove the first distance values ​​calculated by the target sample set to be identified and / or the target cluster center sample set to obtain each of the second distance values.

5. The method as described in claim 1, characterized in that, When the judgment result does not meet the preset conditions, the initial sample dataset of the previous generation is updated iteratively based on each of the sample sets to be identified to obtain the initial sample dataset of the current generation. The method further includes: Determine whether the current iteration count meets the preset conditions; When the determination result is that the current iteration number is greater than or equal to a preset threshold, the phase sequence recognition model is obtained; When the determination result is that the current iteration number is less than a preset threshold, the initial sample dataset of the previous generation is updated cyclically based on each of the sample sets to be identified, so as to obtain the initial sample dataset of the current generation.

6. A phase sequence identification device, characterized in that, For implementing the phase sequence identification method as described in any one of claims 1 to 5, comprising: Construction module: Used to collect voltage timing data samples of each phase sequence of the transformer area's main meter and voltage timing data samples of each single phase meter, in order to construct an initial sample dataset containing several voltage timing data samples corresponding to each phase sequence. Calculation module: used to perform calculations based on each of the initial sample datasets to obtain the initial cluster center datasets corresponding to each of the initial sample datasets, so as to obtain the initial phase sequence recognition model; Update module: used to iteratively update the initial phase sequence recognition model based on each sample to be identified, and obtain the phase sequence recognition model when the preset iteration conditions are met; Identification module: used to identify the target sample to be identified based on the phase sequence identification model, determine the target cluster center corresponding to the target sample to be identified, and determine the phase sequence corresponding to the target cluster center as the target phase sequence corresponding to the target sample to be identified.

7. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the phase sequence identification method according to any one of claims 1-5.

8. An electronic device, characterized in that, It includes at least a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program in the memory to implement the steps of the phase sequence identification method according to any one of claims 1-5.

Images