A voltage flicker monitoring method and device for power distribution terminals and a storage medium

Abstract

The application discloses a voltage flicker monitoring method and device of a distribution terminal and a storage medium, and relates to the technical field of voltage flicker monitoring. The method comprises the following steps: acquiring voltage signals of a distribution terminal according to time intervals to obtain time-series voltage data; intercepting the voltage data and converting the voltage data into frequency domain information; analyzing the frequency domain information to obtain voltage fluctuation characteristic data; acquiring a voltage flicker data set, training and testing iterations of the voltage flicker data set, and obtaining a voltage flicker evaluation model; and importing the voltage fluctuation characteristic data into the voltage flicker evaluation model for analysis and calculation to obtain a voltage flicker value. According to the application, voltage fluctuation characteristic data can be obtained according to voltage signals, and then voltage flicker values can be directly calculated based on voltage fluctuation characteristics and a voltage flicker evaluation model, so that the time for monitoring can be saved, the calculation efficiency of voltage flicker values is improved, and the result of the voltage flicker values is more reliable.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of voltage flicker monitoring, and in particular to a voltage flicker monitoring method and device for a distribution transformer terminal and a storage medium. BACKGROUND

[0002] IEC61000-4-15 is one of the standards on electromagnetic compatibility published by the International Electrotechnical Commission. The electromagnetic compatibility (EMC) part 4-15: test and measurement technology flicker meter function and design specification standard, which specifies the equipment and method for measuring short-time flicker (Pst) and long-time flicker (Plt) in voltage quality, short-time flicker is calculated using the formula Pst = [(∑(ΔVi)² / T) / (10 × Vmp)³]^(1 / 2), ΔVi is the voltage change, T is the measurement time window (usually 10 minutes), Vmp is the average voltage value during the measurement period, and the Pst value should be usually lower than a certain threshold 1.0.

[0003] At present, in the distribution transformer terminal, a voltage monitoring module can be selected to realize the voltage monitoring function, so as to realize real-time monitoring on the operation parameters of the distribution transformer. The existing method for real-time monitoring on the operation parameters of the distribution transformer is to obtain the monitoring result through a calculation formula based on the collected voltage data, so as to obtain the real-time voltage flicker value. This method needs a long calculation sampling time to ensure the accuracy of the calculation result, and this method can only obtain the result after a period of time after the voltage flicker occurs, which is low in efficiency and affects the reliability of the monitoring result.

[0004] In the process of implementing the present application, the inventors have found that at least the following problems exist in the prior art:

[0005] The accuracy and reliability of the monitoring result calculated by the voltage monitoring module used in the existing distribution transformer terminal are low. SUMMARY

[0006] The present application aims to provide a voltage flicker monitoring method and device for a distribution transformer terminal and a storage medium, so as to solve the technical problem of low accuracy and reliability of the monitoring result calculated by the voltage monitoring module used in the prior art.

[0007] The preferred technical solutions in the technical solutions provided by the present application can produce the technical effects as follows.

[0008] In order to achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0009] In a first aspect, the present application discloses a voltage flicker monitoring method for a distribution transformer terminal, comprising:

[0010] The voltage signal of the distribution transformer is acquired according to a time interval, and time-series voltage data is obtained;

[0011] The voltage data is intercepted, the voltage data is converted into frequency domain information, the frequency domain information is analyzed, and voltage fluctuation characteristic data is obtained;

[0012] A voltage flicker data set is acquired, and the voltage flicker data set is trained and tested iteratively to obtain a voltage flicker evaluation model; wherein the voltage flicker data in the voltage flicker data set is extracted from the distribution transformer;

[0013] The voltage fluctuation characteristic data is imported into the voltage flicker evaluation model for analysis and calculation, and a voltage flicker value is obtained.

[0014] Optionally, the acquisition of the voltage flicker data set, the training and testing iteration of the voltage flicker data set, and the obtaining of the voltage flicker evaluation model comprise:

[0015] The voltage flicker data is acquired from a voltage waveform database to obtain a voltage flicker data set; wherein the voltage waveform database stores voltage waveform data of a plurality of distribution transformers;

[0016] The voltage flicker data set is trained using a convolutional neural network algorithm to obtain a voltage flicker training model library;

[0017] The voltage flicker training model library is tested and iterated using the voltage flicker data set to generate a voltage flicker evaluation model.

[0018] Optionally, the intercepting of the voltage data, the converting of the voltage data into frequency domain information, the analyzing of the frequency domain information, and the obtaining of the voltage fluctuation characteristic data comprise:

[0019] The voltage data is intercepted using a sliding window method;

[0020] The voltage data is converted into frequency domain information through Fourier transform;

[0021] The frequency domain information is processed and analyzed to obtain voltage fluctuation characteristic data.

[0022] Optionally, the processing and analyzing of the frequency domain information to obtain the voltage fluctuation characteristic data comprises:

[0023] The frequency domain information is feature extracted to identify high-frequency components in the frequency spectrum components;

[0024] The frequency and amplitude of voltage fluctuation are detected according to the high-frequency components to obtain the voltage fluctuation characteristic data.

[0025] Optionally, the voltage fluctuation feature data is introduced into the voltage flicker evaluation model for analysis and calculation to obtain a voltage flicker value, including:

[0026] The voltage fluctuation feature data is introduced into the voltage flicker evaluation model.

[0027] In the voltage flicker evaluation model, the voltage fluctuation feature data is matched and voltage short-time flicker calculation is performed to obtain a voltage flicker value.

[0028] Optionally, after the voltage fluctuation feature data is introduced into the voltage flicker evaluation model for analysis and calculation, it further includes:

[0029] In the voltage flicker evaluation model, a predicted voltage evaluation value is generated based on the voltage fluctuation feature data.

[0030] Optionally, the predicted voltage evaluation value is generated, including:

[0031] The voltage fluctuation feature data is introduced into the voltage flicker evaluation model.

[0032] In the voltage flicker evaluation model, the voltage fluctuation feature data is matched and the matching similarity of the voltage fluctuation feature data in the voltage flicker evaluation model is calculated.

[0033] A predicted voltage evaluation value is generated according to the matching similarity.

[0034] Optionally, the voltage signal of the distribution terminal is obtained at a time interval, including: using a high-speed voltage sampling metering chip to obtain the voltage signal at a time interval.

[0035] In a second aspect, the application further discloses a terminal device, including:

[0036] One or more processors and memories;

[0037] The memory is used to store one or more computer programs, and the one or more processors are used to execute the one or more computer programs stored in the memory, so that the processor executes the voltage flicker monitoring method steps of the distribution terminal as described above.

[0038] In a third aspect, the application further discloses a computer-readable storage medium, and the readable storage medium stores a computer program, which is executed by a processor to realize the voltage flicker monitoring method steps of the distribution terminal as described above.

[0039] The implementation of one of the technical solutions of the application has the following advantages or beneficial effects:

[0040] The voltage flicker monitoring method of the distribution transformer terminal disclosed in the application comprises: obtaining voltage signals of the distribution transformer terminal according to time intervals to obtain time-series voltage data; intercepting the voltage data and converting the voltage data into frequency domain information, analyzing the frequency domain information to obtain voltage fluctuation characteristic data; obtaining a voltage flicker data set, training and testing iteration of the voltage flicker data set to obtain a voltage flicker evaluation model; wherein the voltage flicker data in the voltage flicker data set is extracted from the distribution transformer terminal; and the voltage fluctuation characteristic data is imported into the voltage flicker evaluation model for analysis and calculation to obtain a voltage flicker value.

[0041] The application can obtain voltage fluctuation characteristic data according to voltage signals, and directly calculate a voltage flicker value based on the voltage fluctuation characteristic and the voltage flicker evaluation model, thereby saving monitoring time, improving the calculation efficiency of the voltage flicker value, and making the result of the voltage flicker value more reliable. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can also be obtained according to these drawings without creative labor for those skilled in the art. In the drawings:

[0043] Figure 1 Fig. 1 is a flowchart of a voltage flicker monitoring method of a distribution transformer terminal according to an embodiment of the application;

[0044] Figure 2 Fig. 2 is a structural schematic diagram of a terminal device according to an embodiment of the application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the application more clear, the various exemplary embodiments to be described below will be described with reference to the corresponding drawings, which constitute a part of the exemplary embodiments, and various exemplary embodiments that can be used to implement the application are described. Unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation described in the following exemplary embodiments does not represent all the implementations consistent with the present disclosure. It should be understood that they are only examples of processes, methods and devices, etc. consistent with some aspects of the present disclosure as described in detail in the appended claims, and other embodiments can also be used, or structural and functional modifications can be made to the embodiments listed herein without departing from the scope and spirit of the application.

[0046] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse" and the like indicate the orientation or positional relationship shown in the drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the elements referred to must have a specific orientation, be constructed and operated in a specific orientation. The terms "first", "second" and the like are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. The term "a plurality of" means two or more. The terms "connected", "connected" should be broadly understood, for example, it can be fixed connection, detachable connection, integral connection, mechanical connection, electrical connection, communication connection, direct connection, indirect connection through intermediate medium, internal communication of two elements or interaction relationship between two elements. The term "and / or" includes any and all combinations of one or more related listed items. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0047] In order to illustrate the technical solutions described in the present application, the following will be described by specific examples, only showing the part related to the embodiment of the present application.

[0048] Example one:

[0049] As Figure 1 shown, the present application provides a voltage flicker monitoring method of distribution transformer terminal, comprising:

[0050] S10, obtaining the voltage signal of the distribution transformer terminal according to the time interval, obtaining the voltage data with time sequence;

[0051] S20, intercepting the voltage data, converting the voltage data into frequency domain information, analyzing the frequency domain information, and obtaining the voltage fluctuation characteristic data;

[0052] S30, obtaining the voltage flicker data set, training and testing iteration of the voltage flicker data set, and obtaining the voltage flicker evaluation model; wherein the voltage flicker data in the voltage flicker data set is extracted from the distribution transformer terminal;

[0053] S40, importing the voltage fluctuation characteristic data into the voltage flicker evaluation model for analysis and calculation, and obtaining the voltage flicker value.

[0054] Specifically, the voltage flicker method of the distribution transformer terminal described in the embodiment realizes real-time monitoring of the voltage signal of the distribution transformer terminal by obtaining the voltage signal of the distribution transformer terminal according to the time interval and obtaining the voltage data with time sequence. Then intercept the voltage data, and convert the voltage data into frequency domain information, analyze the frequency domain information, and obtain the voltage fluctuation data. The voltage fluctuation data obtained above can provide an important basis for subsequent calculation of voltage flicker value.

[0055] Before, during or after the above two steps, a voltage flicker dataset is obtained, the voltage flicker dataset is trained and tested iteratively, and a voltage flicker evaluation model is obtained; wherein the voltage flicker data in the voltage flicker dataset is extracted from the distribution transformer terminal. Finally, the voltage fluctuation feature data is imported into the voltage flicker evaluation model for analysis and calculation to obtain the voltage flicker value.

[0056] In this way, the voltage fluctuation feature data is obtained from the voltage signal, and the voltage flicker value is directly calculated based on the voltage fluctuation feature and the voltage flicker evaluation model, which can save monitoring time, improve the calculation efficiency of the voltage flicker value, and the result of the voltage flicker value has higher reliability.

[0057] In the following, the specific implementation steps of the voltage flicker monitoring method of the distribution transformer terminal provided in the embodiment will be described in detail. Figure 1

[0058] First, step S10 is performed, and the voltage signal of the distribution transformer terminal is obtained at a time interval to obtain time-sequenced voltage data. Specifically, when obtaining the voltage signal of the distribution transformer terminal, a high-speed voltage sampling metering chip is used to obtain the voltage signal at a time interval. The use of a high-speed voltage sampling metering chip can accurately sample a higher voltage signal, and then convert the high voltage signal into a low voltage signal that can be processed by the metering chip, which can ensure the accuracy and stability of the sampling.

[0059] The distribution transformer terminal is a device for monitoring and controlling the operation state of the distribution transformer, and the voltage signal in the distribution transformer terminal reflects the real-time situation of the voltage in the distribution system. In the embodiment, the voltage signal is obtained at a time interval, and the obtained voltage signal is converted into time-sequenced voltage data, which can clearly reflect the change of the voltage with time, and is helpful for analyzing the stability of the voltage and the fluctuation of the voltage, and realizing real-time detection of the distribution transformer terminal.

[0060] Next, step S20 is performed, the voltage data is intercepted, and the voltage data is converted into frequency domain information, and the frequency domain information is analyzed to obtain voltage fluctuation feature data. Specifically, the time-sequenced voltage data is converted into frequency domain information, and then the frequency domain information is further analyzed to obtain the voltage fluctuation feature data, and subsequent analysis and calculation of the voltage fluctuation feature data can obtain the voltage flicker value.

[0061] More specifically, step S20 includes the following steps: the voltage data is intercepted using a sliding window method; the voltage data is converted into frequency domain information by Fourier transform; and the frequency domain information is processed and analyzed to obtain the voltage fluctuation feature data.​

[0062] First, the voltage data is intercepted using a sliding window method, which can flexibly handle voltage data sequences of different lengths, ensuring the integrity and continuity of the voltage data. The size of the sliding window can be adjusted according to actual needs to adapt to the characteristics of voltage data in different monitoring scenarios. In this way, key information can be effectively extracted from the original voltage signal, providing a reliable data basis for subsequent analysis and calculation. At the same time, the sliding window interception method can reduce the complexity of data processing, improve the real-time performance and accuracy of voltage data monitoring.

[0063] Then, the voltage data is converted into frequency domain information using Fourier transform. This process is actually a data transformation process. The voltage waveform changes over time during processing, which is a time-domain signal. Fourier transform can decompose this time-domain signal into a combination of sine and cosine waves of different frequencies, amplitudes, and phases, so that the distribution of voltage data at different frequencies, i.e., frequency domain information, is obtained. This facilitates subsequent analysis of voltage fluctuations based on frequency domain information.

[0064] Finally, the frequency domain information is processed and analyzed to obtain voltage fluctuation characteristic data. Specifically, after obtaining the frequency domain information of the voltage data, further processing and analysis of the frequency domain information can be performed. The specific steps are as follows: feature extraction of the frequency domain information to identify high-frequency components in the frequency spectrum; detecting the frequency and amplitude of voltage fluctuations based on the high-frequency components to obtain voltage fluctuation characteristic data.

[0065] Feature extraction of the frequency domain information to identify high-frequency components in the frequency spectrum. The frequency domain information contains frequency spectrum components of different frequencies and their corresponding amplitude values, and the high-frequency components contain key information of voltage fluctuations. Therefore, feature extraction of the frequency domain information is required to identify high-frequency components in the frequency spectrum. Specifically, to identify high-frequency components in the frequency spectrum, a frequency threshold can be set to filter frequency components above the threshold to obtain high-frequency components in the frequency spectrum. More specifically, the frequency threshold can be set according to actual conditions, which is not limited in this embodiment.

[0066] Detecting the frequency and amplitude of voltage fluctuations based on the high-frequency components to obtain voltage fluctuation characteristic data. Specifically, after obtaining the high-frequency components in the frequency domain information, the frequency and amplitude of voltage fluctuations in the high-frequency components are further detected, and the detected frequency and amplitude of voltage fluctuations are sorted, analyzed, and quantized to ultimately obtain voltage fluctuation characteristic data.

[0067] In the embodiment, the voltage data is intercepted, the voltage data is converted into frequency domain information through Fourier transform, and feature extraction is performed on the frequency domain information, and finally voltage fluctuation feature data is obtained. The obtained voltage fluctuation feature data has high reliability and accuracy, and provides an important basis for subsequent calculation of voltage flicker value.

[0068] Then, step S30 is performed to obtain a voltage flicker data set, and the voltage flicker data set is trained and tested iteratively to obtain a voltage flicker evaluation model; wherein the voltage flicker data in the voltage flicker data set is extracted from the distribution transformer terminal. It should be noted that step S30 can be performed before steps S10 and S20 are performed, or can be performed after step S20 is performed, or can be performed simultaneously with steps S10 and S20. Regardless of which stage it is performed, it will not affect its specific implementation, and therefore, in the embodiment, it is not specifically limited.

[0069] In the embodiment, the voltage flicker data set is obtained, the voltage flicker data set is trained and tested iteratively to obtain the voltage flicker evaluation model, including: obtaining voltage flicker data from the voltage waveform database to obtain the voltage flicker data set; wherein the voltage waveform database stores voltage waveform data of a plurality of distribution transformer terminals; training the voltage flicker data set using a convolutional neural network algorithm to obtain a voltage flicker training model library; and testing and iterating the voltage flicker training model library using the voltage flicker data set to generate the voltage flicker evaluation model.

[0070] Specifically, the voltage waveform database is a database specially storing voltage waveform related data. The voltage waveform data generated by the existing plurality of distribution transformer terminals during the working process is stored in the voltage waveform database, facilitating subsequent data extraction. Then, a plurality of voltage flicker data is obtained from the voltage waveform database to obtain the voltage flicker data set. The voltage flicker data includes the change amount, change frequency and change time of the voltage amplitude.

[0071] After obtaining the voltage flicker data set, the voltage flicker data set is trained using a convolutional neural network algorithm to obtain a voltage flicker training model. The convolutional neural network algorithm is used for deep learning of the voltage flicker data set. The voltage flicker data set is input into the convolutional neural network, the convolutional neural network automatically learns the features and rules in the data, and in the training process, the convolutional neural network continuously adjusts its own parameters, so that the prediction result of the input data is more real, and finally the voltage flicker training model library is obtained.

[0072] The voltage flicker training model library is tested multiple times based on the voltage flicker data set to fully mine the features in the data, and the model is continuously optimized through training iterations to improve the accuracy and stability of the subsequent numerical values. After multiple test iterations, the voltage flicker training model library converges to a relatively stable state, at which point the voltage flicker evaluation model is obtained. The voltage flicker evaluation model directly presets the characteristic values corresponding to the voltage. Finally, the voltage flicker evaluation model can analyze and predict the voltage fluctuation characteristic data, assess the voltage flicker degree, and predict the possibility of flicker occurrence, which can be used for monitoring, analysis, and management of the power system, and can improve the accuracy and reliability of voltage monitoring.

[0073] Finally, step S40 is performed to import the voltage fluctuation characteristic data into the voltage flicker evaluation model for analysis and calculation to obtain the voltage flicker value. This step includes: importing the voltage fluctuation characteristic data into the voltage flicker evaluation model; in the voltage flicker evaluation model, performing feature matching on the voltage fluctuation characteristic data and performing voltage short-time flicker calculation to obtain the voltage flicker value.

[0074] Specifically, when the voltage flicker value is obtained, the voltage fluctuation characteristic data obtained in step S20 is imported into the voltage flicker evaluation model, so that the voltage fluctuation characteristic data serves as the input parameter of the voltage flicker evaluation model, and the voltage fluctuation characteristic data is subjected to subsequent analysis and calculation in the voltage flicker evaluation model.

[0075] Since the voltage flicker evaluation model has undergone multiple test iterations and has preset characteristic values corresponding to the voltage, the voltage fluctuation characteristic data imported into the voltage flicker evaluation model will be matched with the above-mentioned characteristic values to determine the similarity between the current voltage fluctuation characteristic data and the characteristic values, and obtain the feature matching result. Then, a specific algorithm in the voltage flicker evaluation model is used to process and calculate the voltage fluctuation characteristic data to determine the flicker degree of the voltage at the distribution transformer terminal in a short time, and finally obtain the voltage flicker value.

[0076] It should be noted that the voltage flicker value represents the severity of voltage flicker, and the higher the value, the more obvious the voltage flicker, which may affect the electrical equipment connected to the distribution transformer terminal. If the voltage flicker value exceeds the set threshold, a related warning will be generated subsequently.

[0077] The above method can quickly obtain the voltage flicker value corresponding to the voltage signal based on the voltage signal, has high accuracy and reliability, can realize real-time monitoring of the voltage signal of the distribution transformer terminal, and can ensure the stability of the electrical equipment connected to the distribution transformer terminal.

[0078] In the embodiment, in addition to obtaining the voltage flicker value according to the above steps, the corresponding predicted voltage evaluation value can also be generated according to the above steps.

[0079] After step S30, further comprising: importing the voltage fluctuation feature data into the voltage flicker evaluation model for analysis and calculation, and generating the predicted voltage evaluation value based on the voltage fluctuation feature data in the voltage flicker evaluation model. The steps specifically include: importing the voltage fluctuation feature data into the voltage flicker evaluation model; in the voltage flicker evaluation model, performing feature matching on the voltage fluctuation feature data to calculate the matching similarity of the voltage fluctuation feature data in the voltage flicker evaluation model; wherein the matching similarity is the similarity between the voltage fluctuation feature data and the feature value in the voltage flicker evaluation model; and generating the predicted voltage evaluation value according to the matching similarity.

[0080] Specifically, after importing the voltage fluctuation feature data into the voltage flicker evaluation model, the voltage fluctuation feature data also needs to be subjected to feature matching, and a specific algorithm in the voltage flicker evaluation model is used to calculate the matching similarity of the voltage fluctuation feature data in the voltage flicker evaluation model. Finally, the voltage evaluation value is inferred according to the matching similarity. For example, when the current circuit state has a high similarity with a previous state, the voltage value under the previous state can be referred to, and a predicted voltage evaluation value under the current condition is generated by combining some correction factors.

[0081] Therefore, in addition to being able to obtain the voltage flicker value to improve the accuracy and reliability of the voltage flicker value in the detection process, the voltage of the distribution and transformation terminal can also be predicted, the voltage can be quickly and efficiently predicted and evaluated through the matching similarity, the potential line voltage flicker that may be caused can be predicted in advance, and early warning can be performed.

[0082] The embodiment is only one specific example, and does not mean that the present application is only in this implementation.

[0083] Embodiment two:

[0084] Based on the same inventive concept, the second embodiment of the present application also provides a terminal device, as shown in Figure 2 The terminal device includes one or more processors 301 and a memory 302; wherein the memory is used to store one or more computer programs, and the one or more processors are used to execute the one or more computer programs stored in the memory, so that the processor executes the features / steps of the voltage flicker monitoring method of the distribution and transformation terminal according to the first embodiment.

[0085] Those skilled in the art can understand that all or part of the features / steps of the above-mentioned method embodiments can be implemented by a method, a data processing system or a computer program, and the features can be implemented in a manner of not using hardware, in a manner of using software entirely or in a manner of using a combination of hardware and software. The aforementioned computer program can be stored in one or more computer readable storage media, and the computer program stored on the storage media is executed by a processor to perform the steps of the voltage flicker monitoring method of the distribution terminal.

[0086] Embodiment three:

[0087] Based on the same inventive concept, the third embodiment of the present application also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the program is executed by a processor to implement the steps of any one of the methods of the voltage flicker monitoring method of the distribution terminal according to the first embodiment.

[0088] The above only describes the preferred embodiments of the present application, and those skilled in the art can make various changes or equivalent replacements to the features and embodiments without departing from the spirit and scope of the present application. In addition, the features and embodiments can be modified to adapt to specific conditions and materials under the guidance of the present application without departing from the spirit and scope of the present application. Therefore, the present application is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of the present application are within the protection scope of the present application.

Claims

1. A method for monitoring voltage flicker at a distribution transformer terminal, characterized in that: include: Obtain voltage signals from distribution transformer terminals at time intervals to obtain time-series voltage data; intercepting the voltage data, converting the voltage data into frequency domain information, and analyzing the frequency domain information to obtain voltage fluctuation characteristic data; Acquire a voltage flicker dataset, perform training and testing iterations on the voltage flicker dataset, and obtain a voltage flicker evaluation model; wherein the voltage flicker data in the voltage flicker dataset is extracted from the distribution transformer terminal; Importing the voltage fluctuation characteristic data into the voltage flicker evaluation model for analysis and calculation to obtain a voltage flicker value; The step of obtaining a voltage flicker dataset, iteratively training and testing the voltage flicker dataset, and obtaining a voltage flicker evaluation model includes: Acquire voltage flicker data from a voltage waveform database to obtain a voltage flicker data set; wherein the voltage waveform database stores voltage waveform data of a plurality of distribution transformer terminals; Using a convolutional neural network algorithm to train the voltage flicker dataset to obtain a voltage flicker training model library; Using a voltage flicker dataset to iterate the voltage flicker training model library, generating a voltage flicker evaluation model, wherein the voltage flicker evaluation model is directly preset with characteristic values ​​corresponding to the voltage; The step of importing the voltage fluctuation characteristic data into the voltage flicker evaluation model for analysis and calculation to obtain a voltage flicker value includes: Importing the voltage fluctuation characteristic data into the voltage flicker assessment model; In the voltage flicker evaluation model, the voltage fluctuation characteristic data is subjected to characteristic matching, and a voltage short-time flicker calculation is performed to obtain a voltage flicker value.

2. The voltage flicker monitoring method of a distribution transformer terminal according to claim 1, characterized in that: The intercepting the voltage data, converting the voltage data into frequency domain information, and analyzing the frequency domain information to obtain voltage fluctuation characteristic data includes: intercepting the voltage data using a sliding window method; Converting the voltage data into frequency domain information through Fourier transform; The frequency domain information is processed and analyzed to obtain voltage fluctuation characteristic data.

3. The voltage flicker monitoring method of a distribution transformer terminal according to claim 2, characterized in that: The frequency domain information is processed and analyzed to obtain voltage fluctuation characteristic data, including: Extracting features from the frequency domain information to identify high-frequency components in the spectrum; The frequency and amplitude of the voltage fluctuation are detected according to the high-frequency component to obtain the voltage fluctuation characteristic data.

4. The voltage flicker monitoring method of a distribution transformer terminal according to claim 1, characterized in that: After the voltage fluctuation characteristic data is imported into the voltage flicker evaluation model for analysis and calculation, the method further includes: In the voltage flicker evaluation model, a predicted voltage evaluation value is generated based on the voltage fluctuation characteristic data.

5. The voltage flicker monitoring method of a distribution transformer terminal according to claim 4, characterized in that: Generating a predicted voltage evaluation value includes: Importing the voltage fluctuation characteristic data into the voltage flicker assessment model; In the voltage flicker assessment model, feature matching is performed on the voltage fluctuation characteristic data to calculate the matching similarity of the voltage fluctuation characteristic data in the voltage flicker assessment model; A predicted voltage evaluation value is generated according to the matching similarity.

6. The voltage flicker monitoring method of a distribution transformer terminal according to claim 1, characterized in that: The obtaining of the voltage signal of the distribution transformer terminal according to the time interval includes: obtaining the voltage signal according to the time interval using a metering chip for high-speed voltage sampling.

7. A terminal device, characterized in that: include: one or more processors and memory; The memory is used to store one or more computer programs, and the one or more processors are used to execute the one or more computer programs stored in the memory, so that the processor performs the steps of the voltage flicker monitoring method for the distribution transformer terminal according to any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for monitoring voltage flicker of a distribution transformer terminal as claimed in any one of claims 1 to 6 are implemented.

Images