Method, device and equipment for correcting dielectric loss measurement error of voltage transformer and storage medium

Abstract

The invention discloses a voltage transformer dielectric loss measurement error correction method, device and equipment and a storage medium, and the method comprises the steps: carrying out the dielectric loss measurement of a voltage transformer based on an energy gravity center method and a dynamic windowing harmonic analysis method, and obtaining original dielectric loss data; obtaining a target dielectric loss error correction model, wherein the dielectric loss error correction model is obtained through parameter optimization of a saddle point search algorithm, a differential evolution algorithm and a rapid local search algorithm; obtaining structure parameters, working environment parameters and historical dielectric loss data of the voltage transformer, and training the target dielectric loss error correction model to obtain a trained dielectric loss error correction model; the original dielectric loss data is corrected through the trained dielectric loss error correction model to obtain the corrected dielectric loss data, and the original dielectric loss data is corrected through the target dielectric loss error correction model obtained through parameter optimization by introducing multiple optimization algorithms, so that the dielectric loss measurement error of the voltage transformer can be effectively reduced, and the measurement accuracy of the voltage transformer is improved. And the accuracy of dielectric loss measurement is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of dielectric loss measurement, and particularly relates to a voltage transformer dielectric loss measurement error correction method and device, equipment and a storage medium. BACKGROUND

[0002] The voltage transformer is an important device widely used in the power system, and is mainly used for converting high-voltage current into low-voltage current for power equipment measurement and protection. In the working process of the voltage transformer, the dielectric loss, as one of the key performance indicators, directly affects the measurement accuracy and long-term stability of the voltage transformer. Therefore, accurately measuring the dielectric loss of the voltage transformer is an important means to ensure the reliability and accuracy of the power system.

[0003] Dielectric loss measurement is an important technology in voltage transformer performance evaluation. Traditional dielectric loss measurement methods mainly rely on static testing and frequency response analysis, however, these methods are often affected by environmental changes, equipment aging and manufacturing processes, resulting in large errors in the measurement results. Especially in complex working environments, the accuracy of the dielectric loss data will be affected by various external disturbances, thereby affecting the performance evaluation of the voltage transformer. SUMMARY

[0004] The main purpose of the application is to provide a voltage transformer dielectric loss measurement error correction method, device, equipment and storage medium, which aims to solve the technical problem of large measurement result error of the traditional dielectric loss measurement method.

[0005] To achieve the above purpose, the application provides a voltage transformer dielectric loss measurement error correction method, which comprises the following steps:

[0006] The dielectric loss of the voltage transformer is measured based on the energy barycenter method and the dynamic windowed harmonic analysis method to obtain original dielectric loss data;

[0007] An objective dielectric loss error correction model is obtained, wherein the dielectric loss error correction model is obtained by parameter optimization of an initial dielectric loss error correction model through a saddle point search algorithm, a differential evolution algorithm and a fast local search algorithm;

[0008] The structure parameters, working environment parameters and historical dielectric loss data of the voltage transformer are obtained, and the objective dielectric loss error correction model is trained based on the structure parameters, working environment parameters and historical dielectric loss data of the voltage transformer to obtain a trained dielectric loss error correction model;

[0009] The original dielectric loss data is corrected through the trained dielectric loss error correction model to obtain corrected dielectric loss data.

[0010] In an embodiment, the dielectric loss of the voltage transformer is measured based on the energy center method and the dynamic windowing harmonic analysis method to obtain original dielectric loss data, including:

[0011] An AC voltage signal is applied to the voltage transformer, and an output signal of the voltage transformer is collected;

[0012] The fundamental component in the output signal of the voltage transformer is determined by using the energy center method;

[0013] The output signal of the voltage transformer is analyzed by using the dynamic windowing harmonic analysis method to extract the harmonic component;

[0014] The dielectric loss value of the voltage transformer is calculated according to the fundamental component and the harmonic component;

[0015] The dielectric loss value of the voltage transformer is taken as the original dielectric loss data.

[0016] In an embodiment, the fundamental component in the output signal of the voltage transformer is determined by using the energy center method, including:

[0017] The output signal of the voltage transformer is preprocessed to obtain a preprocessed output signal of the voltage transformer;

[0018] The preprocessed output signal of the voltage transformer is subjected to Fourier transform to obtain a frequency spectrum of the output signal of the voltage transformer;

[0019] The energy of each frequency component in the frequency spectrum is calculated, and the energy of each frequency component is taken as a weight;

[0020] The energy center of the fundamental component in the output signal of the voltage transformer is calculated according to the weight, and the frequency of the fundamental component in the output signal of the voltage transformer is determined according to the frequency corresponding to the energy center;

[0021] The amplitude and phase of the fundamental component in the output signal of the voltage transformer are determined according to the frequency of the fundamental component in the output signal of the voltage transformer;

[0022] The fundamental component in the output signal of the voltage transformer is obtained by calculation according to the amplitude and phase of the fundamental component in the output signal of the voltage transformer.

[0023] In an embodiment, the output signal of the voltage transformer is analyzed by using the dynamic windowing harmonic analysis method to extract the harmonic component, including:

[0024] The output signal of the voltage transformer is subjected to segmentation processing to obtain a plurality of signal segments, wherein the length of the signal segment is dynamically adjusted according to a preset condition or signal characteristics;

[0025] A window function is set in each signal segment according to an expected frequency range of the harmonic component, wherein a type and parameters of the window function are selected according to characteristics of the harmonic component and a signal noise condition;

[0026] Each signal segment is weighted according to the window function to obtain a plurality of weighted signal segments;

[0027] Fourier transform is performed on each weighted signal segment to obtain a frequency spectrum of each signal segment;

[0028] In the frequency spectrum of each signal segment, a corresponding sub-harmonic component information of each signal segment is identified according to a preset sub-harmonic component identification rule, wherein the sub-harmonic component information at least includes frequency, amplitude and phase information of the sub-harmonic component, and the frequency of the sub-harmonic component is an integer multiple of the frequency of the fundamental wave component;

[0029] The corresponding sub-harmonic component information of each signal segment is integrated to obtain a sub-harmonic component in the voltage transformer output signal.

[0030] In an embodiment, the target dielectric loss error correction model is obtained, comprising:

[0031] Obtaining a dielectric loss error source and an influencing factor of the voltage transformer;

[0032] An initial dielectric loss error correction model is constructed according to the dielectric loss error source and the influencing factor of the voltage transformer;

[0033] Parameter optimization is performed on the initial dielectric loss error correction model based on a saddle point search algorithm, a differential evolution algorithm and a fast local search algorithm to obtain a plurality of candidate dielectric loss error correction models;

[0034] The performance of each candidate dielectric loss error correction model is evaluated, and the candidate dielectric loss error correction model with the best performance is selected as the target dielectric loss error correction model.

[0035] In an embodiment, the parameter optimization is performed on the initial dielectric loss error correction model based on the saddle point search algorithm, the differential evolution algorithm and the fast local search algorithm to obtain a plurality of candidate dielectric loss error correction models, comprising:

[0036] Global search is performed in a parameter space by using the saddle point search algorithm to determine a potential optimal solution region;

[0037] In the potential optimal solution region, the initial parameter combination of the initial dielectric loss error correction model is iteratively optimized by using the differential evolution algorithm to generate a new candidate solution through mutation, crossover and selection operations;

[0038] A fast local search algorithm is used to perform fine search near the new candidate solution to obtain a local optimal solution;

[0039] use the local optimal solution as an optimal parameter combination of a candidate dielectric loss error correction model;

[0040] re-perform the step of performing a global search in the parameter space by using the saddle point search algorithm to determine a potential optimal solution region until a preset stop condition is met, to obtain multiple optimal parameter combinations;

[0041] update the initial parameter combination of the initial dielectric loss error correction model based on the multiple optimal parameter combinations respectively, to obtain multiple candidate dielectric loss error correction models.

[0042] In an embodiment, the performance of each candidate dielectric loss error correction model is evaluated, and the candidate dielectric loss error correction model with the optimal performance is selected as the target dielectric loss error correction model, which includes:

[0043] obtaining a verification set and dividing the verification set into multiple subsets, wherein each subset contains a certain amount of voltage transformer dielectric loss measurement data;

[0044] for each candidate dielectric loss error correction model, each subset is sequentially used as a test set, and the remaining subsets other than the test set are used as training sets;

[0045] training and testing the candidate dielectric loss error correction model, and during the testing process, the dielectric loss data in the test set is corrected by using the trained candidate dielectric loss error correction model to obtain corrected dielectric loss data;

[0046] calculating the error between the corrected dielectric loss data and the true dielectric loss data to obtain the error index of each candidate dielectric loss error correction model on the test set;

[0047] the average value of the error index of each candidate dielectric loss error correction model on all test sets is used as the performance index of the corresponding candidate dielectric loss error correction model on the verification set;

[0048] According to the performance index, each candidate dielectric loss error correction model is evaluated, and the candidate dielectric loss error correction model with the optimal performance index is selected as the target dielectric loss error correction model.

[0049] In addition, to achieve the above-mentioned purpose, the present application also provides a voltage transformer dielectric loss measurement error correction device, which comprises:

[0050] a measurement module for measuring the dielectric loss of the voltage transformer based on the energy center method and the dynamic windowed harmonic analysis method to obtain raw dielectric loss data;

[0051] The acquisition module is configured to acquire a target dielectric loss error correction model, wherein the dielectric loss error correction model is obtained by performing parameter optimization on an initial dielectric loss error correction model through a saddle point search algorithm, a differential evolution algorithm and a fast local search algorithm.

[0052] The training module is configured to acquire structure parameters and working environment parameters of the voltage transformer and historical dielectric loss data, and train the target dielectric loss error correction model based on the structure parameters and working environment parameters of the voltage transformer and the historical dielectric loss data to obtain a trained dielectric loss error correction model.

[0053] The correction module is configured to correct original dielectric loss data through the trained dielectric loss error correction model to obtain corrected dielectric loss data.

[0054] In addition, to achieve the above object, the present application further provides a voltage transformer dielectric loss measurement error correction device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the voltage transformer dielectric loss measurement error correction method as described above.

[0055] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the voltage transformer dielectric loss measurement error correction method as described above.

[0056] In addition, to achieve the above object, the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the voltage transformer dielectric loss measurement error correction method as described above.

[0057] One or more technical solutions provided in the application perform dielectric loss measurement on a voltage transformer based on an energy barycenter method and a dynamic windowed harmonic analysis method to obtain original dielectric loss data; an error correction model of target dielectric loss is obtained, wherein the error correction model of target dielectric loss is obtained by performing parameter optimization on an initial error correction model of dielectric loss through a saddle point search algorithm, a differential evolution algorithm, and a fast local search algorithm; structure parameters, working environment parameters, and historical dielectric loss data of the voltage transformer are obtained, and the error correction model of target dielectric loss is trained based on the structure parameters, the working environment parameters, and the historical dielectric loss data of the voltage transformer to obtain a trained error correction model of dielectric loss; the original dielectric loss data is corrected through the trained error correction model of dielectric loss to obtain corrected dielectric loss data. In the foregoing manner, the error correction model of target dielectric loss obtained by introducing various optimization algorithms for parameter optimization is used to correct the original dielectric loss data, which can effectively reduce the dielectric loss measurement error of the voltage transformer, improve the accuracy of dielectric loss measurement, and further improve the performance evaluation accuracy of the voltage transformer. BRIEF DESCRIPTION OF DRAWINGS

[0058] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and serve to explain the principles of the application together with the specification.

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced in the following. Obviously, for those of ordinary skill in the art, the other drawings can also be obtained based on these drawings without any creative work.

[0060] Figure 1 A flowchart is provided for the first embodiment of the voltage transformer dielectric loss measurement error correction method of the application.

[0061] Figure 2 A flowchart is provided for the second embodiment of the voltage transformer dielectric loss measurement error correction method of the application.

[0062] Figure 3 A module structure diagram is provided for the voltage transformer dielectric loss measurement error correction device of the embodiment of the application.

[0063] Figure 4 A device structure diagram of a hardware operating environment involved in the voltage transformer dielectric loss measurement error correction device in the embodiment of the application is provided.

[0064] The object implementation, functional features, and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0066] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and specific embodiments.

[0067] The main solution of the embodiment of the present application is: based on the energy barycenter method and the dynamic windowing harmonic analysis method, the dielectric loss of the voltage transformer is measured to obtain the original dielectric loss data; an error correction model of the target dielectric loss is obtained, wherein the error correction model of the target dielectric loss is obtained by parameter optimization of an initial error correction model of the dielectric loss through a saddle point search algorithm, a differential evolution algorithm and a fast local search algorithm; the structure parameters, the working environment parameters and the historical dielectric loss data of the voltage transformer are obtained, and the error correction model of the target dielectric loss is trained based on the structure parameters, the working environment parameters and the historical dielectric loss data of the voltage transformer to obtain a trained error correction model of the dielectric loss; the original dielectric loss data is corrected through the trained error correction model of the dielectric loss to obtain corrected dielectric loss data.

[0068] The traditional dielectric loss measurement method mainly depends on static test and frequency response analysis, however, these methods are often affected by factors such as environmental changes, equipment aging and manufacturing process, resulting in large errors in the measurement results. Especially in a complex working environment, the accuracy of the dielectric loss data will be affected by various external disturbances, thereby affecting the performance evaluation of the voltage transformer.

[0069] The present application provides a solution, which corrects the original dielectric loss data through the target dielectric loss error correction model obtained by introducing various optimization algorithms for parameter optimization, can effectively reduce the dielectric loss measurement error of the voltage transformer, improve the accuracy of the dielectric loss measurement, and further improve the performance evaluation accuracy of the voltage transformer.

[0070] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a voltage transformer dielectric loss measurement error correction device, etc. The following takes the voltage transformer dielectric loss measurement error correction device as an example to describe the embodiment and the following embodiments.

[0071] Based on this, the present application provides a voltage transformer dielectric loss measurement error correction method, which refers to Figure 1 , Figure 1 The flowchart of the first embodiment of the voltage transformer dielectric loss measurement error correction method of the present application is shown in the figure.

[0072] In this embodiment, the voltage transformer dielectric loss measurement error correction method comprises steps S10-S40:

[0073] Step S10: Based on the energy barycenter method and dynamic windowing harmonic analysis method, the dielectric loss of the voltage transformer is measured to obtain the original dielectric loss data.

[0074] It should be noted that the energy barycenter method is a method for obtaining dielectric loss value by calculating the barycenter position of the energy distribution of the voltage transformer dielectric loss signal. The dynamic windowing harmonic analysis method is a method for analyzing the harmonic components in the voltage transformer dielectric loss signal by dynamically adjusting the window size, so as to more accurately obtain the dielectric loss information. The combination of these two methods can complement each other and improve the accuracy and stability of dielectric loss measurement.

[0075] In specific implementation, the energy barycenter method is used to measure the dielectric loss of the voltage transformer. By collecting and processing the voltage and current signals of the voltage transformer, the energy distribution of the voltage transformer dielectric loss signal can be obtained. Then, the barycenter position of the energy distribution, i.e. the dielectric loss value, is calculated. Then, the dynamic windowing harmonic analysis method is used to analyze the harmonic components in the voltage transformer dielectric loss signal. The size and position of the window are dynamically adjusted to adapt to different frequency harmonic components. Through the analysis of the harmonic components, the dielectric loss value obtained by the energy barycenter method can be further verified and corrected, thereby improving the accuracy of the measurement. The dielectric loss value obtained at this time is the original dielectric loss data.

[0076] It should be noted that the specific implementation and parameter setting of the energy barycenter method and the dynamic windowing harmonic analysis method may vary depending on the model, working environment, and other factors of the voltage transformer. Therefore, in actual application, it needs to be adjusted and optimized according to the specific situation.

[0077] In one possible implementation, step S20 can comprise steps A11-A15:

[0078] Step A11: Apply an alternating voltage signal to the voltage transformer and collect the output signal of the voltage transformer.

[0079] It should be noted that in order to obtain accurate dielectric loss data, a stable alternating voltage signal needs to be applied to the voltage transformer. This signal can be a sine wave or other suitable waveform, depending on the characteristics of the voltage transformer and the measurement requirements. This embodiment does not make specific limitations.

[0080] It can be understood that after an alternating voltage signal is applied to the voltage transformer, the voltage transformer will output a response voltage signal, which contains dielectric loss information of the voltage transformer. Therefore, the output signal of the voltage transformer can be collected in real time by a suitable sensor and collection device, and converted into a digital signal for subsequent digital signal processing and analysis.

[0081] Step A12: determining the fundamental component in the voltage transformer output signal by using the energy center method.

[0082] It should be noted that the energy center method mainly relies on the analysis of the energy distribution of the voltage transformer output signal when determining the fundamental component. By performing Fourier transform or other frequency domain analysis methods on the signal, the energy distribution of the signal at different frequencies can be obtained. Then, according to the characteristics of the energy distribution, the frequency component with the most concentrated energy, i.e. the fundamental component, is determined. The fundamental component is the main component in the voltage transformer output signal, which reflects the basic characteristics and working state of the voltage transformer.

[0083] Step A13: analyzing the voltage transformer output signal by using the dynamic windowing harmonic analysis method to extract the sub-harmonic component.

[0084] It should be noted that the dynamic windowing harmonic analysis method can more accurately capture the sub-harmonic component in the signal by dynamically adjusting the size and position of the analysis window when analyzing the voltage transformer output signal. The sub-harmonic component is an important part of the voltage transformer output signal, which reflects some subtle changes and characteristics of the voltage transformer during operation. By extracting and analyzing the sub-harmonic component, the dielectric loss of the voltage transformer can be further understood, providing more accurate data support for subsequent error correction.

[0085] In specific implementation, appropriate dynamic windowing harmonic analysis method and parameter setting can be selected according to the characteristics of the voltage transformer output signal and measurement requirements to ensure the accuracy and reliability of the analysis. Through comprehensive analysis and processing of the fundamental component and the sub-harmonic component, more comprehensive and accurate dielectric loss information of the voltage transformer can be obtained.

[0086] Step A14: calculating the dielectric loss value of the voltage transformer according to the fundamental component and the sub-harmonic component.

[0087] Step A15: taking the dielectric loss value of the voltage transformer as the original dielectric loss data.

[0088] It should be noted that the dielectric loss value is one of the key parameters for measuring the performance of the voltage transformer, which reflects the loss of the voltage transformer in the energy transmission process. Through accurate analysis and processing of the fundamental component and the harmonic component, a more accurate dielectric loss value can be obtained, which is of great significance for evaluating the performance of the voltage transformer and correcting errors.

[0089] In a specific implementation, according to the amplitude, phase and frequency information of the fundamental component and the harmonic component, the dielectric loss calculation formula is used for calculation. The dielectric loss calculation formula is usually derived based on the physical characteristics and electromagnetic theory of the voltage transformer, which takes into account various loss factors of the voltage transformer in the working process, such as resistance loss, inductance loss and capacitance loss, etc. By substituting the relevant information of the fundamental component and the harmonic component into the dielectric loss calculation formula, the dielectric loss value of the voltage transformer under the current working state can be obtained, which reflects the loss of the voltage transformer in the energy transmission process and is an important basis for evaluating the performance of the voltage transformer and correcting errors. The obtained dielectric loss value is used as the original dielectric loss data for further error correction processing.

[0090] In a feasible implementation, step A12 can include: pre-processing the voltage transformer output signal to obtain a pre-processed voltage transformer output signal; performing Fourier transform on the pre-processed voltage transformer output signal to obtain a frequency spectrum of the voltage transformer output signal; calculating the energy of each frequency component in the frequency spectrum and taking the energy of each frequency component as a weight; calculating the energy center of the fundamental component in the voltage transformer output signal according to the weight, and determining the frequency of the fundamental component in the voltage transformer output signal according to the frequency corresponding to the energy center; determining the amplitude and phase of the fundamental component in the voltage transformer output signal according to the frequency of the fundamental component in the voltage transformer output signal; and calculating the fundamental component in the voltage transformer output signal according to the amplitude and phase of the fundamental component in the voltage transformer output signal.

[0091] It should be noted that pre-processing is a series of operations on the voltage transformer output signal, aiming to improve the quality and reliability of the signal. The specific steps of pre-processing can include filtering, denoising, smoothing, etc. These operations can effectively remove the interference components in the signal, improve the signal-to-noise ratio, and make the extraction of the fundamental component more accurate. Through pre-processing of the voltage transformer output signal, a clearer and more accurate signal can be obtained.

[0092] It can be understood that the pre-processed voltage transformer output signal is a time domain signal, and discrete Fourier transform (DFT) can be used to convert the time domain signal to a frequency domain signal, thereby obtaining the frequency spectrum of the voltage transformer output signal.

[0093] It is worth noting that the energy of each frequency component in the spectrum is calculated to provide a weight for the fundamental component calculation. The energy can be obtained by calculating the square of the amplitude of each frequency component. The energy center of the fundamental component is calculated according to the energy of each frequency component as the weight, that is, the energy of each frequency component in the spectrum is taken as the weight, and the weighted average of all frequency components is calculated to obtain the corresponding frequency, which is the frequency corresponding to the energy center of the fundamental component. The frequency corresponding to the energy center can more accurately reflect the actual frequency of the fundamental component in the voltage transformer output signal, thereby improving the accuracy of the fundamental component extraction. Further, according to the frequency corresponding to the energy center, the amplitude and phase of the fundamental component in the voltage transformer output signal can be determined, and then the fundamental component in the voltage transformer output signal is obtained. This method can reduce the influence of environmental noise and interference on the extraction of the fundamental component, and improve the accuracy and stability of the dielectric loss measurement.

[0094] In a feasible implementation, step A13 can include: segmenting the voltage transformer output signal to obtain a plurality of signal segments, wherein the length of the signal segment is dynamically adjusted according to a preset condition or signal characteristics; setting a window function in each signal segment according to an expected frequency range of the harmonic component, wherein the type and parameters of the window function are selected according to the characteristics of the harmonic component and the signal noise condition; performing weighted processing on each signal segment according to the window function to obtain a plurality of weighted signal segments; performing Fourier transform on each weighted signal segment to obtain the spectrum of each signal segment; identifying the corresponding sub-harmonic component information of each signal segment in the spectrum of each signal segment according to a preset harmonic component identification rule, wherein the sub-harmonic component information at least includes the frequency, amplitude and phase information of the sub-harmonic component, and the frequency of the sub-harmonic component is an integer multiple of the frequency of the fundamental component; and integrating the sub-harmonic component information corresponding to each signal segment to obtain the sub-harmonic component in the voltage transformer output signal.

[0095] It is worth noting that according to the change characteristics of the signal, appropriate segment length is selected, which can be adjusted according to the time window, frequency range or signal change condition. The signal segmentation can be performed by sliding window or fixed length segmentation.

[0096] It can be understood that the window function is set in each signal segment, and the signal segment is weighted and processed to optimize the spectrum analysis and reduce the edge effect and noise. According to the signal characteristics (such as harmonic frequency range, noise condition, etc.), appropriate window function type and parameters are selected. Common window functions include rectangular window, Hamming window, Hanning window, Blackman window, etc.

[0097] It is worth noting that discrete Fourier transform (DFT) or fast Fourier transform (FFT) is used to transform each weighted signal segment to obtain a frequency domain representation, and the Fourier transform calculation formula is:

[0098]

[0099] where X i (k) is the frequency domain representation of the ith signal segment, is the weighted nth signal segment, and N is the total number of signal segments.

[0100] It is worth noting that in the spectrum of each signal segment, the sub-harmonic components correspond to integer multiples of the fundamental frequency. By searching for these integer multiple frequencies in the spectrum, the frequency, amplitude, and phase of the sub-harmonic are identified. The sub-harmonic components identified in all signal segments (including frequency, amplitude, and phase information) are integrated to obtain the sub-harmonic information in the entire signal, and the integrated sub-harmonic component x harmonic (t) is:

[0101]

[0102] where A n is the amplitude of the sub-harmonic component, f n is the sub-harmonic frequency, and φ n is the sub-harmonic phase, and N is the maximum identified sub-harmonic order.

[0103] Step S20: Obtain the target dielectric loss error correction model, wherein the dielectric loss error correction model is obtained by parameter optimization of the initial dielectric loss error correction model using the saddle point search algorithm, the differential evolution algorithm, and the fast local search algorithm.

[0104] It should be noted that the dielectric loss error correction model is obtained by parameter optimization of the initial dielectric loss error correction model using the saddle point search algorithm, the differential evolution algorithm, and the fast local search algorithm. The combination of these optimization algorithms can efficiently search in the parameter space and find the optimal parameter combination, thereby improving the accuracy, stability, and generalization ability of the dielectric loss error correction model.

[0105] In specific implementation, the saddle point search algorithm is used to locate possible saddle points in the parameter space, which are usually key positions for parameter optimization. The differential evolution algorithm iteratively optimizes parameters by simulating mutation, crossover, and selection operations in the biological evolution process to find the global optimal solution. The fast local search algorithm is used to perform fine search near the saddle point to further improve the accuracy of the parameters. By processing the initial dielectric loss error correction model with these optimization algorithms, a more accurate and stable dielectric loss error correction model can be obtained, which can better adapt to the characteristics and working environment of different voltage transformers and improve the accuracy and reliability of dielectric loss measurement. After obtaining the target dielectric loss error correction model, it is used to correct the original dielectric loss data to obtain more accurate dielectric loss values.

[0106] Step S30: Obtain the structural parameters, working environment parameters, and historical dielectric loss data of the voltage transformer, and train the target dielectric loss error correction model based on the structural parameters, working environment parameters, and historical dielectric loss data of the voltage transformer to obtain the trained dielectric loss error correction model.

[0107] It should be noted that the structural parameters of the voltage transformer include but are not limited to the number of turns, capacitance distribution, inductance, etc. of its winding, which will directly affect the dielectric loss characteristics of the voltage transformer. The working environment parameters include temperature, humidity, electromagnetic interference, etc. external factors, which may also affect the dielectric loss measurement. The historical dielectric loss data records the dielectric loss of the voltage transformer in the past period of time, which can be used to evaluate the accuracy and reliability of the dielectric loss error correction model.

[0108] It can be understood that in the training process, the structural parameters, working environment parameters, and historical dielectric loss data of the voltage transformer are first input into the target dielectric loss error correction model. Then, by comparing the difference between the corrected dielectric loss value output by the model and the actually measured dielectric loss value, the parameters of the model are adjusted to reduce the difference. This process is usually an iterative process, which requires multiple training and adjustment to obtain the optimal dielectric loss error correction model.

[0109] It is worth mentioning that the trained dielectric loss error correction model will more accurately reflect the actual dielectric loss characteristics of the voltage transformer, thereby improving the accuracy and reliability of the dielectric loss measurement. The model can be integrated into the dielectric loss measurement system of the voltage transformer to realize real-time correction and processing of the dielectric loss data.

[0110] Step S40: Correct the original dielectric loss data through the trained dielectric loss error correction model to obtain the corrected dielectric loss data.

[0111] It should be noted that the original dielectric loss data may be affected by various factors such as the accuracy of the measurement equipment, the aging degree of the voltage transformer, etc. These factors will cause the deviation of the dielectric loss data. By correcting these original data through the trained dielectric loss error correction model, the deviation can be effectively eliminated, thereby obtaining more accurate dielectric loss data.

[0112] It can be understood that the corrected dielectric loss data can not only be used to evaluate the insulation performance of the voltage transformer, but also provide important reference for the stable operation of the power system. In addition, the corrected dielectric loss data can also be used for fault prediction and diagnosis of the voltage transformer, helping the operation and maintenance personnel to discover and handle potential safety hazards in time, improving the reliability and safety of the power system.

[0113] In a specific implementation, the original dielectric loss data is input into the trained dielectric loss error correction model, and the model automatically calculates the corrected dielectric loss value according to the structural parameters of the voltage transformer, the working environment parameters, and the characteristics of the historical dielectric loss data. This process is real-time and can complete the correction of a large amount of data in a short time, greatly improving the efficiency of dielectric loss measurement.

[0114] The embodiment provides a voltage transformer dielectric loss measurement error correction method, which measures the dielectric loss of a voltage transformer based on an energy barycenter method and a dynamic windowed harmonic analysis method to obtain original dielectric loss data; obtains a target dielectric loss error correction model, wherein the dielectric loss error correction model is obtained by performing parameter optimization on an initial dielectric loss error correction model through a saddle point search algorithm, a differential evolution algorithm, and a fast local search algorithm; obtains structural parameters, working environment parameters, and historical dielectric loss data of the voltage transformer, and trains the target dielectric loss error correction model based on the structural parameters, the working environment parameters, and the historical dielectric loss data of the voltage transformer to obtain a trained dielectric loss error correction model; and corrects the original dielectric loss data through the trained dielectric loss error correction model to obtain corrected dielectric loss data. In this way, the original dielectric loss data is corrected through the target dielectric loss error correction model obtained by introducing various optimization algorithms for parameter optimization, which can effectively reduce the dielectric loss measurement error of the voltage transformer, improve the accuracy of dielectric loss measurement, and further improve the performance evaluation accuracy of the voltage transformer.

[0115] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above-mentioned first embodiment can be referred to the above introduction, and the following will not be repeated. On this basis, please refer to Figure 2 , step S20 includes steps S201-S204:

[0116] Step S201: obtaining the dielectric loss error sources and influencing factors of the voltage transformer.

[0117] It should be noted that the dielectric loss error sources and influencing factors of the voltage transformer can include but are not limited to the accuracy limitation of the measuring equipment, the change of the environmental temperature and humidity, the electromagnetic interference, the material aging of the voltage transformer, and the design defects, etc. These factors can all have different degrees of influence on the dielectric loss measurement results, thereby causing errors.

[0118] Step S202: constructing an initial dielectric loss error correction model according to the dielectric loss error sources and influencing factors of the voltage transformer.

[0119] It should be noted that the initial dielectric loss error correction model is based on the understanding of the source and influencing factors of the dielectric loss error of the voltage transformer, and is constructed by combining relevant mathematical and physical models. The model aims to realize the prediction and correction of dielectric loss measurement error through quantitative analysis of various error factors.

[0120] Step S203: Based on the saddle point search algorithm, differential evolution algorithm and fast local search algorithm, the parameters of the initial dielectric loss error correction model are optimized to obtain a plurality of candidate dielectric loss error correction models.

[0121] It should be noted that the saddle point search algorithm, differential evolution algorithm and fast local search algorithm are used to search and optimize the parameters of the initial dielectric loss error correction model to find the optimal parameter combination. This process aims to improve the accuracy and reliability of the model, so that it can more accurately reflect the dielectric loss error of the voltage transformer.

[0122] It can be understood that using multiple optimization algorithms for parameter optimization can increase the possibility of finding a global optimal solution and avoid falling into a local optimal solution. At the same time, these algorithms each have different characteristics and advantages, which can complement each other, thereby improving the efficiency and accuracy of parameter optimization.

[0123] In one possible implementation, step S203 can include steps B11-B16:

[0124] Step B11: Use the saddle point search algorithm to perform global search in the parameter space to determine the potential optimal solution region.

[0125] It should be noted that the saddle point search algorithm is a global search-based optimization algorithm that can perform extensive search in the parameter space to quickly locate the potential optimal solution region. This process helps to narrow the range of subsequent search and improve search efficiency.

[0126] It can be understood that finding the saddle point in the parameter space finds the potential optimal solution region by following the gradient direction or through optimization techniques. Assuming a target function f(θ), where θ represents the parameter vector, the saddle point is a point where the gradient of the target function is zero, but near this point, the target function is locally minimum in some directions, while it is locally maximum in other directions.

[0127] In a specific implementation, a set of initial parameters θ0is randomly generated within the parameter space as the starting point of the search. The value of the objective function f(θ0) is calculated and taken as the current optimal solution. A number of search directions are randomly selected within the parameter space, and search is conducted along these directions respectively. For each search direction, iterative search is conducted with a certain step size, the value of the objective function at each iteration point is calculated and compared with the current optimal solution. If a better solution is found, the current optimal solution is updated, and the region where the solution lies is recorded as a potential optimal solution region. The above process is repeated until a certain stopping condition is met, such as reaching a pre-set number of iterations or the improvement of the objective function being less than a pre-set threshold. Through this process, the saddle point search algorithm can conduct extensive search within the parameter space and quickly locate the potential optimal solution region.

[0128] Step B12: Within the potential optimal solution region, the initial parameter combination of the initial dielectric loss error correction model is iteratively optimized using a differential evolution algorithm to generate a new candidate solution through mutation, crossover and selection operations.

[0129] It should be noted that the differential evolution algorithm is a population-based evolutionary algorithm that searches for the optimal solution by simulating natural selection and genetic mechanisms. In the differential evolution algorithm, a set of initial parameter combinations is randomly generated as the population. Then, mutation operation is performed on each individual in the population, i.e. a differential vector is added to the current individual to generate a mutated individual. Next, crossover operation is performed to cross the current individual with the mutated individual to generate a new candidate solution. Finally, selection operation is performed to compare the current individual and the candidate solution according to the objective function value, and the better individual is selected as part of the next generation population. Through continuous iteration of this process, the differential evolution algorithm can conduct fine search within the potential optimal solution region and gradually approach the optimal solution.

[0130] In a specific implementation, the initial parameter combination of the initial dielectric loss error correction model is obtained as the initial population of the differential evolution algorithm. Then, a mutation operation is performed on each individual in the initial population to generate a mutated individual. The mutation operation is implemented by adding a difference vector composed of the difference between two other individuals to the current individual, which can increase the diversity of the population and help explore new solution space. Next, a crossover operation is performed to exchange part of the genes between the current individual and the mutated individual to generate a crossover individual, i.e., a new candidate solution. The crossover operation can retain the excellent genes of the current individual while introducing new genes of the mutated individual, which helps to generate a solution with better performance. Finally, a selection operation is performed to compare the current individual and the crossover individual according to the objective function value, and the better individual is selected as part of the next generation population. Through continuous iteration of the mutation, crossover, and selection operations, the differential evolution algorithm can perform fine search in the potential optimal solution region and gradually approach the optimal solution, thereby improving the accuracy and reliability of the initial dielectric loss error correction model.

[0131] Step B13: performing fine search around the new candidate solution using a fast local search algorithm to obtain a local optimal solution.

[0132] It should be noted that the fast local search algorithm is an optimization algorithm based on neighborhood search, which can find a better solution by searching in the neighborhood of the current solution. In the fast local search algorithm, the neighborhood range of the current solution is first determined, i.e., a set of new candidate solutions is generated by changing part of the parameter values of the current solution. Then, the objective function values of these candidate solutions are calculated and compared with the current solution. If a better solution is found, the current solution is updated and the search in its neighborhood continues. Through continuous iteration of this process, the fast local search algorithm can perform fine search around the current solution and find a local optimal solution.

[0133] In a specific implementation, the candidate solution generated by the differential evolution algorithm is taken as the current solution, and its neighborhood range is determined. Then, a set of new candidate solutions is generated in the neighborhood of the current solution, and their objective function values are calculated. According to the objective function values, the best candidate solution is selected as the new current solution, and the search in its neighborhood continues. Through this process, the fast local search algorithm can perform fine search around the candidate solution generated by the differential evolution algorithm and find a local optimal solution, thereby further improving the accuracy and reliability of the initial dielectric loss error correction model.

[0134] Step B14: taking the local optimal solution as the optimal parameter combination of the candidate dielectric loss error correction model.

[0135] Step B15: Re-execute the step of global search in parameter space using the saddle point search algorithm until the preset stopping condition is met, obtaining multiple optimal parameter combinations.

[0136] Step B16: Update the initial parameter combination of the initial dielectric loss error correction model based on multiple optimal parameter combinations, obtaining multiple candidate dielectric loss error correction models.

[0137] It should be noted that after taking the local optimal solution as the optimal parameter combination of the candidate dielectric loss error correction model, the entire parameter optimization process does not end. Because there may be multiple local optimal solutions, and our goal is to find the global optimal solution or the solution as close as possible to the global optimal solution. Therefore, it is necessary to re-execute the step of global search in parameter space using the saddle point search algorithm, i.e., step B11, to explore new potential optimal solution regions. This process is iterative, and each iteration will conduct a more in-depth search based on the current optimal solution region in order to find a better solution.

[0138] Before the preset stopping condition is met, such iterative search will continue. The preset stopping condition can be that the number of iterations reaches a preset upper limit, or that the improvement amplitude of the objective function is less than a preset threshold, depending on the requirements of actual application and the limitations of computing resources. Through continuous iterative search, multiple optimal parameter combinations can be obtained, and these combinations are based on different potential optimal solution regions, so they may have different characteristics and advantages.

[0139] Finally, based on these multiple optimal parameter combinations, the initial parameter combination of the initial dielectric loss error correction model is updated respectively to generate multiple candidate dielectric loss error correction models. These models each represent the correction effect under different parameter combinations, providing a rich sample for further selection and optimization. By evaluating and comparing these candidate models, the model with the best performance can be selected for actual voltage transformer dielectric loss error correction. This process not only improves the correction accuracy, but also enhances the generalization ability of the model,

[0140] In specific implementation, multiple optimal parameter combinations are obtained through saddle point search and differential evolution optimization each time. Each optimal solution can be used to update the initial model, and finally multiple candidate correction models are obtained. The formula for updating the model parameters is:

[0141]

[0142] where θ updated is the updated model parameter, N is the number of optimal solutions, is the optimal parameter obtained by the i-th optimization.

[0143] Step S204: Evaluate the performance of each candidate dielectric loss error correction model, and select the candidate dielectric loss error correction model with the best performance as the target dielectric loss error correction model.

[0144] It should be noted that when evaluating the performance of each candidate dielectric loss error correction model, one or more evaluation indicators can be used to measure the pros and cons of the model. These evaluation indicators can be selected according to the needs and background of actual application, such as correction accuracy, calculation efficiency, stability, etc. By comparing the performance of the candidate models on these evaluation indicators, the candidate model with the best performance can be determined as the target dielectric loss error correction model.

[0145] In a specific implementation, known voltage transformer dielectric loss data can be used as test samples, and each candidate model can be applied to these test samples to calculate and compare their correction effects. The performance of the model can be evaluated according to the size of the corrected error, the calculation time of the correction process, etc. At the same time, the stability of the model can also be considered, that is, whether the performance is consistent under different test samples.

[0146] Through this process, the candidate dielectric loss error correction model with the best performance can be selected as the target model for actual voltage transformer dielectric loss error correction. This model not only has high correction accuracy, but also can maintain good stability while ensuring calculation efficiency, thereby meeting the needs of actual application.

[0147] In a feasible implementation, step S203 can include steps C11-C16:

[0148] Step C11: Obtain a validation set and divide the validation set into multiple subsets, wherein each subset contains a certain amount of voltage transformer dielectric loss measurement data.

[0149] It should be noted that the validation set is an independent data set for evaluating the performance of the model, and it does not overlap with the training set and the test set. After obtaining the validation set, in order to more comprehensively evaluate the performance of the model on different data, the validation set can be divided into multiple subsets. Each subset contains a certain amount of voltage transformer dielectric loss measurement data, which should be representative and can reflect various situations in actual application.

[0150] The advantage of dividing the validation set into multiple subsets is that the performance of the model can be independently evaluated on each subset, thereby obtaining more robust evaluation results. This helps to reduce the evaluation bias caused by improper data division, and improves the accuracy and reliability of model evaluation.

[0151] Step C12: For each candidate dielectric loss error correction model, sequentially use each subset as a test set and the remaining subsets as a training set.

[0152] It should be noted that in the present embodiment, the performance of the candidate dielectric loss error correction model is evaluated by using the cross-validation method, that is, for each candidate model, each subset in the validation set is sequentially taken as the test set, and the remaining subsets except the test set are combined as the training set. The purpose of doing so is to more comprehensively examine the generalization ability of the model on different data by training and testing on different data subsets.

[0153] Step C13: training and testing the candidate dielectric loss error correction model, and during the testing process, using the trained candidate dielectric loss error correction model to correct the dielectric loss data in the test set to obtain the corrected dielectric loss data.

[0154] It should be noted that during the training and testing process, the training set needs to be used to train the candidate dielectric loss error correction model so that it learns the rules and features in the data. After training, the test set is used to test the model to evaluate its performance on unseen data. During the testing process, the voltage transformer dielectric loss data in the test set is input into the trained model, and the model will correct these data according to the rules and features it has learned, and output the corrected dielectric loss data. By comparing the data before and after correction, the correction effect of the model can be evaluated, and the performance of the model can be judged.

[0155] Step C14: calculating the error between the corrected dielectric loss data and the true dielectric loss data to obtain the error index of each candidate dielectric loss error correction model on the test set.

[0156] It should be noted that in order to quantify the correction effect of the candidate dielectric loss error correction model, the error between the corrected dielectric loss data and the true dielectric loss data needs to be calculated. This error index is a key basis for measuring the performance of the model, which reflects the accuracy and reliability of the model in correcting the voltage transformer dielectric loss error.

[0157] In specific implementation, a variety of error calculation methods can be used, such as mean square error, mean absolute error, etc. The selection of these methods depends on the actual application requirements and background. By calculating the error index of each candidate model on the test set, the correction effect of the model can be objectively evaluated and compared, thereby providing a basis for selecting the model with the best performance.

[0158] Step C15: taking the average value of the error index of each candidate dielectric loss error correction model on all test sets as the performance index of the corresponding candidate dielectric loss error correction model on the validation set.

[0159] It should be noted that in order to more comprehensively evaluate the performance of each candidate dielectric loss error correction model, the average value of the error indicators of each candidate model on all test sets is taken as the performance indicator on the validation set. This indicator comprehensively reflects the performance of the model on different data subsets, has higher robustness and reliability. By comparing the performance indicators of each candidate model on the validation set, we can more accurately judge the pros and cons of the model, thereby providing a strong basis for selecting the model with the best performance.

[0160] Step C16: Evaluate each candidate dielectric loss error correction model according to the performance indicator, and select the candidate dielectric loss error correction model with the best performance indicator as the target dielectric loss error correction model.

[0161] It should be noted that in the evaluation process, in addition to considering the average value of the error indicators, other evaluation dimensions such as the stability of the model, the calculation efficiency and the adaptability in actual application scenarios can also be considered. These dimensions together constitute a comprehensive and objective evaluation system for candidate dielectric loss error correction models.

[0162] According to the performance indicator and considering other evaluation dimensions, the candidate dielectric loss error correction model with the best performance can be selected as the target model. This target model will accurately correct the dielectric loss error of the voltage transformer, thereby improving the measurement accuracy and stability of the power system.

[0163] In this embodiment, the source and influencing factors of the dielectric loss error of the voltage transformer are obtained; an initial dielectric loss error correction model is constructed according to the source and influencing factors of the dielectric loss error of the voltage transformer; the parameters of the initial dielectric loss error correction model are optimized based on the saddle point search algorithm, the differential evolution algorithm and the fast local search algorithm to obtain multiple candidate dielectric loss error correction models; the performance of each candidate dielectric loss error correction model is evaluated, and the candidate dielectric loss error correction model with the best performance is selected as the target dielectric loss error correction model. Through the above manner, by introducing multiple optimization algorithms to optimize the parameters of the initial dielectric loss error correction model, the correction accuracy and generalization ability of the model can be significantly improved, and then the candidate dielectric loss error correction model with the best performance is selected as the target dielectric loss error correction model, thereby effectively improving the dielectric loss measurement accuracy.

[0164] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the voltage transformer dielectric loss measurement error correction method of the present application. Further simple transformations based on this technical concept are within the scope of protection of the present application.

[0165] The present application also provides a voltage transformer dielectric loss measurement error correction device, which is described in detail in Figure 3 The voltage transformer dielectric loss measurement error correction device comprises:

[0166] The measurement module 10 is configured to measure dielectric loss of the voltage transformer based on the energy barycenter method and the dynamic windowed harmonic analysis method, and obtain raw dielectric loss data.

[0167] The acquisition module 20 is configured to acquire a target dielectric loss error correction model, wherein the dielectric loss error correction model is obtained by parameter optimization of an initial dielectric loss error correction model through a saddle point search algorithm, a differential evolution algorithm and a fast local search algorithm.

[0168] The training module 30 is configured to acquire structural parameters, working environment parameters and historical dielectric loss data of the voltage transformer, and train the target dielectric loss error correction model based on the structural parameters, the working environment parameters and the historical dielectric loss data of the voltage transformer, to obtain a trained dielectric loss error correction model.

[0169] The correction module 40 is configured to correct the raw dielectric loss data through the trained dielectric loss error correction model, to obtain corrected dielectric loss data.

[0170] The voltage transformer dielectric loss measurement error correction device provided by the application adopts the voltage transformer dielectric loss measurement error correction method in the above embodiment, and can solve the technical problem of large measurement result error of the traditional dielectric loss measurement method. Compared with the prior art, the voltage transformer dielectric loss measurement error correction device provided by the application has the same beneficial effects as the voltage transformer dielectric loss measurement error correction method provided by the above embodiment, and other technical features in the voltage transformer dielectric loss measurement error correction device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0171] The application provides a voltage transformer dielectric loss measurement error correction device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the voltage transformer dielectric loss measurement error correction method in the above embodiment one.

[0172] Reference will be made to the following Figure 4This document illustrates a structural schematic diagram of a voltage transformer dielectric loss measurement error correction device suitable for implementing embodiments of this application. The voltage transformer dielectric loss measurement error correction device in this application embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The voltage transformer dielectric loss measurement error correction device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0173] like Figure 4 As shown, the voltage transformer dielectric loss measurement error correction device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the voltage transformer dielectric loss measurement error correction device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the voltage transformer dielectric loss measurement error correction device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows voltage transformer dielectric loss measurement error correction devices with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0174] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0175] The voltage transformer dielectric loss measurement error correction device provided by the present application adopts the voltage transformer dielectric loss measurement error correction method in the above-mentioned embodiments, and can solve the technical problem of large measurement result error of the traditional dielectric loss measurement method. Compared with the prior art, the voltage transformer dielectric loss measurement error correction device provided by the present application has the same beneficial effects as the voltage transformer dielectric loss measurement error correction method provided by the above-mentioned embodiments, and other technical features in the voltage transformer dielectric loss measurement error correction device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0176] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0177] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0178] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the voltage transformer dielectric loss measurement error correction method in the above-mentioned embodiments.

[0179] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electrical connection with one or more conductive wires, a portable computer disk, a hard disk, a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable Read Only Memory or flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electrical wire, an optical cable, an RF (Radio Frequency), and the like, or any suitable combination of the above.

[0180] The computer readable storage medium described above may be contained in the voltage transformer dielectric loss measurement error correction device, or may exist separately without being assembled into the voltage transformer dielectric loss measurement error correction device.

[0181] The computer readable storage medium described above carries one or more programs, which, when executed by the voltage transformer dielectric loss measurement error correction device, cause the voltage transformer dielectric loss measurement error correction device to: measure the dielectric loss of the voltage transformer based on the energy center method and the dynamic window harmonic analysis method to obtain original dielectric loss data; obtain a target dielectric loss error correction model, wherein the dielectric loss error correction model is obtained by parameter optimization of an initial dielectric loss error correction model through a saddle point search algorithm, a differential evolution algorithm, and a fast local search algorithm; obtain the structural parameters, working environment parameters, and historical dielectric loss data of the voltage transformer, and train the target dielectric loss error correction model based on the structural parameters, working environment parameters, and historical dielectric loss data of the voltage transformer to obtain a trained dielectric loss error correction model; and correct the original dielectric loss data through the trained dielectric loss error correction model to obtain corrected dielectric loss data.

[0182] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0183] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0184] The modules involved in the embodiments of the present application can be implemented in software or hardware. In some cases, the names of the modules do not limit the modules themselves.

[0185] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer program) for executing the above-mentioned voltage transformer dielectric loss measurement error correction method, and can solve the technical problem of large measurement result error of the traditional dielectric loss measurement method. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the dielectric loss measurement error correction method provided by the above-mentioned embodiments, which will not be described here.

[0186] The application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the voltage transformer dielectric loss measurement error correction method as described above.

[0187] The computer program product provided by the application can solve the technical problem of large measurement result error of the traditional dielectric loss measurement method. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the voltage transformer dielectric loss measurement error correction method provided by the above-mentioned embodiments, and are not described here.

[0188] The above-mentioned is only part of the embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or direct / indirect application in other related technical fields within the technical concept of the application, including in the patent protection scope of the application.

Claims

1. A voltage transformer dielectric loss measurement error correction method, characterized in that, The method includes: The dielectric loss of voltage transformers is measured using the energy centroid method and dynamic windowed harmonic analysis method to obtain raw dielectric loss data. A target dielectric loss error correction model is obtained, wherein the dielectric loss error correction model is obtained by optimizing the parameters of an initial dielectric loss error correction model using a saddle point search algorithm, a differential evolution algorithm, and a fast local search algorithm. The structural parameters, operating environment parameters, and historical dielectric loss data of the voltage transformer are obtained, and the target dielectric loss error correction model is trained based on the structural parameters, operating environment parameters, and historical dielectric loss data of the voltage transformer to obtain the trained dielectric loss error correction model. The original dielectric loss data is corrected by the trained dielectric loss error correction model to obtain the corrected dielectric loss data.

2. The method of claim 1, wherein, The method based on the energy centroid method and dynamic windowed harmonic analysis is used to measure the dielectric loss of the voltage transformer, obtaining raw dielectric loss data, including: An AC voltage signal is applied to the voltage transformer, and the output signal of the voltage transformer is acquired. The fundamental component in the output signal of the voltage transformer is determined using the energy centroid method. The output signal of the voltage transformer was analyzed using dynamic windowed harmonic analysis to extract the subharmonic components. The dielectric loss value of the voltage transformer is calculated based on the fundamental component and the subharmonic component. The dielectric loss value of the voltage transformer is used as the original dielectric loss data.

3. The method of claim 2, wherein, The method of determining the fundamental component in the output signal of the voltage transformer using the energy centroid method includes: The voltage transformer output signal is preprocessed to obtain the preprocessed voltage transformer output signal. Perform a Fourier transform on the preprocessed voltage transformer output signal to obtain the spectrum of the voltage transformer output signal; Calculate the energy of each frequency component in the spectrum and use the energy of each frequency component as a weight; The energy centroid of the fundamental component in the voltage transformer output signal is calculated based on the weights, and the frequency of the fundamental component in the voltage transformer output signal is determined based on the frequency corresponding to the energy centroid. The amplitude and phase of the fundamental component in the voltage transformer output signal are determined based on the frequency of the fundamental component in the voltage transformer output signal. The fundamental component of the voltage transformer output signal is obtained by calculating the amplitude and phase of the fundamental component.

4. The method of claim 2, wherein, The method of using dynamic windowed harmonic analysis to analyze the output signal of the voltage transformer and extract the subharmonic components includes: The output signal of the voltage transformer is segmented to obtain multiple signal segments, wherein the length of the signal segments is dynamically adjusted according to preset conditions or signal characteristics. Window functions are set within each signal segment according to the expected frequency range of the harmonic components, wherein the type and parameters of the window functions are selected according to the characteristics of the harmonic components and the signal noise situation; The signal segments are weighted according to the window function to obtain multiple weighted signal segments. Perform a Fourier transform on each of the weighted signal segments to obtain the spectrum of each signal segment; In the spectrum of each signal segment, corresponding sub-harmonic component information of each signal segment is identified according to a preset sub-harmonic component identification rule, wherein the sub-harmonic component information at least includes frequency, amplitude and phase information of the sub-harmonic component, and the frequency of the sub-harmonic component is an integer multiple of the fundamental component frequency; The sub-harmonic component information corresponding to each signal segment is integrated to obtain the sub-harmonic component in the voltage transformer output signal.

5. The method of claim 1, wherein, The target dielectric loss error correction model comprises: Obtain the dielectric loss error source and influencing factors of the voltage transformer; According to the dielectric loss error source and influencing factors of the voltage transformer, an initial dielectric loss error correction model is constructed; Based on the saddle point search algorithm, differential evolution algorithm and fast local search algorithm, the initial dielectric loss error correction model is parameter optimized to obtain a plurality of candidate dielectric loss error correction models; The performance of each candidate dielectric loss error correction model is evaluated, and the candidate dielectric loss error correction model with the best performance is selected as the target dielectric loss error correction model.

6. The method of claim 5, wherein, The parameter optimization of the initial dielectric loss error correction model based on the saddle point search algorithm, differential evolution algorithm and fast local search algorithm to obtain a plurality of candidate dielectric loss error correction models comprises: Global search is performed in the parameter space by using the saddle point search algorithm to determine the potential optimal solution region; In the potential optimal solution region, the initial parameter combination of the initial dielectric loss error correction model is iteratively optimized by using the differential evolution algorithm, and new candidate solutions are generated by mutation, crossover and selection operations; A fine search is performed near the new candidate solution by using the fast local search algorithm to obtain a local optimal solution; The local optimal solution is used as the optimal parameter combination of the candidate dielectric loss error correction model; The step of performing global search in the parameter space by using the saddle point search algorithm to determine the potential optimal solution region is re-executed until a preset stop condition is met, and a plurality of optimal parameter combinations are obtained; Based on a plurality of the optimal parameter combinations, the initial parameter combination of the initial dielectric loss error correction model is updated respectively to obtain a plurality of candidate dielectric loss error correction models.

7. The method of claim 5, wherein, The performance of each candidate dielectric loss error correction model is evaluated, and the candidate dielectric loss error correction model with the best performance is selected as the target dielectric loss error correction model, comprising: A verification set is obtained, and the verification set is divided into a plurality of subsets, wherein each subset contains a certain amount of voltage transformer dielectric loss measurement data; For each candidate dielectric loss error correction model, each subset is sequentially used as a test set, and the remaining subsets other than the test set are used as training sets; The candidate dielectric loss error correction model is trained and tested, and during the testing process, the dielectric loss data in the test set is corrected by using the trained candidate dielectric loss error correction model to obtain corrected dielectric loss data; The error between the corrected dielectric loss data and the true dielectric loss data is calculated to obtain the error index of each candidate dielectric loss error correction model on the test set; The average value of the error indexes of each candidate dielectric loss error correction model on all test sets is used as the performance index of the corresponding candidate dielectric loss error correction model on the verification set. According to the performance index, each candidate dielectric loss error correction model is evaluated, and a candidate dielectric loss error correction model with optimal performance index is selected as a target dielectric loss error correction model.

8. A voltage transformer dielectric loss measurement error correction device, characterized by, The voltage transformer dielectric loss measurement error correction device comprises: The measurement module is configured to measure the dielectric loss of the voltage transformer based on the energy center method and the dynamic window harmonic analysis method to obtain original dielectric loss data. The acquisition module is configured to acquire a target dielectric loss error correction model, wherein the dielectric loss error correction model is obtained by optimizing parameters of an initial dielectric loss error correction model through a saddle point search algorithm, a differential evolution algorithm, and a fast local search algorithm. The training module is configured to acquire structure parameters, working environment parameters, and historical dielectric loss data of the voltage transformer, and train the target dielectric loss error correction model based on the structure parameters, the working environment parameters, and the historical dielectric loss data of the voltage transformer to obtain a trained dielectric loss error correction model. The correction module is configured to correct the original dielectric loss data through the trained dielectric loss error correction model to obtain corrected dielectric loss data.

9. A voltage transformer dielectric loss measurement error correction device, characterized by, The voltage transformer dielectric loss measurement error correction device comprises a memory, a processor, and a voltage transformer dielectric loss measurement error correction program stored on the memory and executable on the processor, and the voltage transformer dielectric loss measurement error correction program is configured to implement the voltage transformer dielectric loss measurement error correction method according to any one of claims 1 to 7.

10. A storage medium, characterized by The voltage transformer dielectric loss measurement error correction program is stored on the storage medium and is executed by the processor to implement the voltage transformer dielectric loss measurement error correction method according to any one of claims 1 to 7.

Images