Power quality control method and device based on disturbance classification, equipment and medium

Abstract

The invention discloses an electric energy quality control method and device based on disturbance classification, equipment and a medium. The method comprises the steps of obtaining original three-phase voltage data of a transformer, and performing preprocessing operation on the original three-phase voltage data to obtain preprocessed three-phase voltage data; performing feature extraction on the preprocessed three-phase voltage data to obtain voltage disturbance features; performing anomaly detection based on the voltage disturbance characteristics, and determining a voltage disturbance classification result through an anomaly detection result and the voltage disturbance characteristics; and determining a target device control strategy based on the voltage disturbance classification result so as to control the electric energy quality through the target device control strategy. According to the technical scheme, the target device control strategy can be determined according to analysis of the voltage disturbance characteristics, accurate control over the electric energy quality problem is achieved, and the electric energy quality treatment precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method, device, equipment and medium for controlling power quality based on disturbance classification. Background Art

[0002] The distribution system is a new type of power system built mainly on new energy sources. The distribution transformer is the most critical electrical equipment in the distribution system. It also has the functions of interconnection and power exchange between power grids of different voltage levels. Therefore, the safe and stable operation of the distribution transformer has a direct impact on the safety and stability of the distribution system. However, with the increasing proportion of new energy sources such as large-scale distributed photovoltaics, electric vehicles and battery energy storage in the distribution network, the application demand of the distribution network in power quality control, power grid operation regulation, and source-load multi-integration is growing, which also brings new challenges to the safe operation of the distribution network.

[0003] Although traditional transformers have the advantages of low cost, high reliability and high efficiency, their functions are too single and cannot meet the requirements of smart distribution network construction. However, the power electronic transformers of full power electronic devices are complex in structure, have many switching devices and are expensive. The control of power quality is an urgent problem that technicians in this field need to solve. Summary of the invention

[0004] The present invention provides a power quality control method, device, equipment and medium based on disturbance classification, which can determine the target device control strategy according to the analysis of voltage disturbance characteristics, realize accurate control of power quality problems, and improve the accuracy of power quality management.

[0005] According to one aspect of the present invention, there is provided a power quality control method based on disturbance classification, comprising:

[0006] Acquire original three-phase voltage data of the transformer, and perform a preprocessing operation on the original three-phase voltage data to obtain preprocessed three-phase voltage data;

[0007] Perform feature extraction on the preprocessed three-phase voltage data to obtain voltage disturbance features;

[0008] Performing anomaly detection based on the voltage disturbance feature, and determining a voltage disturbance classification result according to the anomaly detection result and the voltage disturbance feature;

[0009] A target device control strategy is determined based on the voltage disturbance classification result, so as to control the power quality through the target device control strategy.

[0010] Optionally, the preprocessed three-phase voltage data includes instantaneous phasors and sequence components of the three-phase voltage;

[0011] Acquiring three-phase voltage raw data, and performing a preprocessing operation on the three-phase voltage raw data to obtain three-phase voltage data, including:

[0012] Acquire three-phase voltage raw data, and filter the three-phase voltage raw data using a set filter to obtain filtered three-phase voltage data;

[0013] Performing wavelet packet transformation on the filtered three-phase voltage data to obtain transformed three-phase voltage data;

[0014] The instantaneous phasor and sequence component of the three-phase voltage are determined according to the transformed three-phase voltage data.

[0015] Optionally, feature extraction is performed on the preprocessed three-phase voltage data to obtain voltage disturbance features, including:

[0016] Performing time-frequency analysis on the preprocessed three-phase voltage data to obtain a time-frequency analysis result;

[0017] Determine the time-frequency feature matrix and texture features according to the time-frequency analysis results;

[0018] Determining the instantaneous amplitude and phase of the three-phase voltage according to the instantaneous phasor of the three-phase voltage;

[0019] The voltage disturbance feature is obtained by performing feature fusion based on the time-frequency feature matrix, texture feature, instantaneous amplitude and phase.

[0020] Optionally, determining a time-frequency feature matrix and a texture feature according to the time-frequency analysis result includes:

[0021] Determine time domain energy, frequency domain energy and time-frequency energy distribution data according to the time-frequency analysis results;

[0022] Obtaining a time-frequency feature matrix according to the time domain energy, the frequency domain energy and the time-frequency energy distribution data combination;

[0023] The texture features are determined according to the time-frequency analysis results and the texture analysis algorithm.

[0024] Optionally, performing anomaly detection based on the voltage disturbance feature, and determining a voltage disturbance classification result according to the anomaly detection result and the voltage disturbance feature, includes:

[0025] Inputting the voltage disturbance characteristics into a set data description model to perform anomaly detection to obtain an anomaly detection result;

[0026] If the abnormality degree in the abnormality detection result is greater than a set threshold, wavelet singularity detection is performed on the preprocessed three-phase voltage data to determine the start time and end time of the voltage disturbance;

[0027] Constructing a multi-resolution phase space according to the starting time and the ending time of the voltage disturbance;

[0028] The multi-resolution phase space is used to determine a dynamic invariant of a voltage signal, and voltage disturbance classification is performed based on the dynamic invariant to obtain a voltage disturbance classification result.

[0029] Optionally, determining a target device control strategy based on the voltage disturbance detection result includes:

[0030] Determine the state space model and state observer;

[0031] determining an initial device control strategy based on the state-space model and the state observer;

[0032] The initial device control strategy is adjusted based on the voltage disturbance classification result to obtain a target device control strategy.

[0033] Optionally, after controlling the power quality by using the target device control strategy, the method further includes:

[0034] Determine system performance indicators based on the control results of the target device control strategy for controlling power quality;

[0035] A comprehensive performance evaluation is performed based on the system performance indicators to obtain a performance report.

[0036] According to another aspect of the present invention, there is provided a power quality control device based on disturbance classification, comprising:

[0037] A data acquisition module is used to acquire original three-phase voltage data of the transformer, and perform a preprocessing operation on the original three-phase voltage data to obtain preprocessed three-phase voltage data;

[0038] A feature extraction module is used to extract features from the preprocessed three-phase voltage data to obtain voltage disturbance features;

[0039] A voltage disturbance classification result determination module, used for performing anomaly detection based on the voltage disturbance feature, and determining a voltage disturbance classification result through anomaly detection results and the voltage disturbance feature;

[0040] A control strategy determination module is used to determine a target device control strategy based on the voltage disturbance classification result, so as to control the power quality through the target device control strategy.

[0041] Optionally, the preprocessed three-phase voltage data includes instantaneous phasors and sequence components of the three-phase voltage;

[0042] The data acquisition module is specifically used to acquire the original data of the three-phase voltage, filter the original data of the three-phase voltage using a set filter to obtain filtered three-phase voltage data; perform wavelet packet transformation on the filtered three-phase voltage data to obtain transformed three-phase voltage data; and determine the instantaneous phasor and sequence component of the three-phase voltage based on the transformed three-phase voltage data.

[0043] Optionally, the feature extraction module includes:

[0044] A data time-frequency analysis unit, used to perform time-frequency analysis on the preprocessed three-phase voltage data to obtain a time-frequency analysis result;

[0045] A feature determination unit, used to determine a time-frequency feature matrix and a texture feature according to the time-frequency analysis result;

[0046] A voltage instantaneous data determination unit, configured to determine the instantaneous amplitude and phase of the three-phase voltage according to the instantaneous phasor of the three-phase voltage;

[0047] The feature fusion unit is used to obtain voltage disturbance features by performing feature fusion based on the time-frequency feature matrix, texture features, instantaneous amplitude and phase.

[0048] Optionally, the feature determination unit is specifically used to determine the time domain energy, frequency domain energy and time-frequency energy distribution data according to the time-frequency analysis results; obtain a time-frequency feature matrix according to the combination of the time domain energy, the frequency domain energy and the time-frequency energy distribution data; and determine the texture feature according to the time-frequency analysis results and the texture analysis algorithm.

[0049] Optionally, the voltage disturbance classification result determination module is specifically used to input the voltage disturbance feature into a set data description model for anomaly detection to obtain anomaly detection results; if the degree of anomaly in the anomaly detection result is greater than a set threshold, wavelet singularity detection is performed on the preprocessed three-phase voltage data to determine the start time and end time of the voltage disturbance; a multi-resolution phase space is constructed according to the start time and end time of the voltage disturbance; the multi-resolution phase space is used to determine the dynamic invariant of the voltage signal, and voltage disturbance classification is performed based on the dynamic invariant to obtain a voltage disturbance classification result.

[0050] Optionally, a control strategy determination module is specifically used to determine a state space model and a state observer; determine an initial device control strategy based on the state space model and the state observer; and adjust the initial device control strategy based on the voltage disturbance classification result to obtain a target device control strategy.

[0051] Optionally, also include:

[0052] The performance evaluation module is used to determine the system performance index according to the control result of controlling the power quality by the target device control strategy after controlling the power quality by the target device control strategy; and to perform a comprehensive performance evaluation based on the system performance index to obtain a performance report.

[0053] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0054] at least one processor; and

[0055] a memory communicatively connected to the at least one processor; wherein,

[0056] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the power quality control method based on disturbance classification described in any embodiment of the present invention.

[0057] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the power quality control method based on disturbance classification described in any embodiment of the present invention when executed.

[0058] The technical solution of the embodiment of the present invention obtains the original three-phase voltage data of the transformer, performs preprocessing operations on the original three-phase voltage data to obtain preprocessed three-phase voltage data; performs feature extraction on the preprocessed three-phase voltage data to obtain voltage disturbance features; performs anomaly detection based on the voltage disturbance features, and determines the voltage disturbance classification result through the anomaly detection result and the voltage disturbance features; determines the target device control strategy based on the voltage disturbance classification result, so as to control the power quality through the target device control strategy. This technical solution can determine the target device control strategy based on the analysis of the voltage disturbance features, realizes the precise control of power quality problems, and improves the accuracy of power quality management.

[0059] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 is a flow chart of a power quality control method based on disturbance classification provided according to Embodiment 1 of the present invention;

[0062] Figure 2 is a flow chart of a power quality control method based on disturbance classification provided according to Embodiment 2 of the present invention;

[0063] Figure 3 is a structural schematic diagram of a comprehensive power quality management system provided according to Embodiment 3 of the present invention;

[0064] Figure 4 is a structural schematic diagram of a power quality control device based on disturbance classification provided according to a fourth embodiment of the present invention;

[0065] Figure 5 It is a schematic diagram of the structure of an electronic device provided according to Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0066] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0067] It should be noted that the terms "initial", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] Embodiment 1

[0069] Figure 1This is a flow chart of a power quality control method based on disturbance classification according to the first embodiment of the present invention. This embodiment is applicable to the case of controlling the power quality of the distribution network. The method can be executed by a power quality control device based on disturbance classification. The power quality control device based on disturbance classification can be implemented in the form of hardware and / or software. The power quality control device based on disturbance classification can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0070] S110, obtaining original three-phase voltage data of the transformer, and performing a preprocessing operation on the original three-phase voltage data to obtain preprocessed three-phase voltage data.

[0071] Among them, the transformer can be a three-phase three-winding transformer. The original three-phase voltage data can be sampled data of the three-phase voltage obtained by collecting the transformer. In this embodiment, the specific method of obtaining the original three-phase voltage data of the transformer can be to sample the three-phase voltage using a high-speed analog-to-digital converter, and the sampling frequency is set to 50,000 Hz. The sampled data is stored as an original voltage sampling data set, which contains three-phase voltage data, and each phase voltage data consists of a series of sampling point values ​​arranged in chronological order. The preprocessing operation may include processing operations such as adaptive filtering, wavelet packet transform processing, and threshold denoising. The preprocessed three-phase voltage data can be the data obtained after the original three-phase voltage data is processed by adaptive filtering and wavelet packet transform processing. In this embodiment, the preprocessed three-phase voltage data may include the time-frequency representation, instantaneous phasor, and sequence component of the three-phase voltage.

[0072] In this embodiment, the original three-phase voltage data of the transformer can be filtered through an adaptive filter to obtain filtered three-phase voltage data, and the filtered three-phase voltage data can be subjected to wavelet packet transformation for time-frequency analysis. Adaptive threshold operation and other processing methods can also be performed based on the wavelet packet transformation results to obtain pre-processed three-phase voltage data.

[0073] In this embodiment, optionally, the preprocessed three-phase voltage data includes instantaneous phasors and sequence components of the three-phase voltage; the three-phase voltage original data is obtained, and the three-phase voltage original data is preprocessed to obtain the three-phase voltage data, including: obtaining the three-phase voltage original data, filtering the three-phase voltage original data using a set filter to obtain filtered three-phase voltage data; performing wavelet packet transform on the filtered three-phase voltage data to obtain transformed three-phase voltage data; and determining the instantaneous phasors and sequence components of the three-phase voltage based on the transformed three-phase voltage data.

[0074] Among them, the set filter can be a pre-set filter. In this embodiment, the set filter can be an adaptive Savitzky-Golay filter, and can also be set according to actual needs. The filtered three-phase voltage data can be the data obtained after the high-frequency noise is removed by the adaptive Savitzky-Golay filter. In this embodiment, the three-phase voltage original data obtained by high-speed sampling is obtained, and the high-frequency noise is removed by an improved adaptive Savitzky-Golay filter. In this embodiment, the filter order can be calculated according to the pre-estimated signal-to-noise ratio, the signal-to-noise ratio is divided by ten, rounded down, and then added one. Then the window length is calculated based on the preset fundamental frequency and sampling frequency, the sampling frequency is divided by the fundamental frequency, rounded up, and then multiplied by two plus one. By using the calculated filter order and window length, the Savitzky-Golay filter is applied to each phase voltage data in the original voltage sampling data set to obtain the filtered three-phase voltage data. The application of the adaptive Savitzky-Golay filter can effectively remove high-frequency noise while retaining the important characteristics of the signal, especially when processing nonlinear and non-stationary power system signals.

[0075] Among them, the wavelet packet transform processing can be to perform wavelet basis decomposition processing on the filtered three-phase voltage data. In this embodiment, the three-phase voltage data set obtained after filtering is subjected to time-frequency analysis by applying wavelet packet transform. Specifically, Daubechies4 can be selected as the wavelet basis function, and the number of decomposition layers is obtained by calculating the logarithm of the ratio of the sampling frequency to the fundamental frequency with base two. In this embodiment, wavelet packet transform can be performed on each phase voltage data in the filtered three-phase voltage data to obtain the corresponding time-frequency representation. In this embodiment, the wavelet packet transform result obtained by performing wavelet packet transform processing can also be subjected to adaptive threshold denoising by applying the improved SURE (Stein's Unbiased Risk Estimate) threshold method. For each node of each decomposition layer, the threshold is calculated, and the calculation method can be to multiply the noise standard deviation estimate of the node by the square root of the natural logarithm of twice the number of sampling points. In this embodiment, the wavelet packet coefficients in the wavelet packet transform result are subjected to soft threshold processing using the calculated threshold to obtain the denoised wavelet packet coefficients; the denoised wavelet packet coefficients obtained are subjected to inverse wavelet packet transform to reconstruct the voltage signal. The denoised wavelet packet coefficients of each phase voltage are respectively subjected to inverse wavelet packet transform to obtain reconstructed high-quality three-phase voltage data, including the reconstructed voltage data of the three phases, that is, the transformed three-phase voltage data.

[0076] Exemplarily, the process of adaptive threshold denoising in this embodiment can be: obtaining the output wavelet packet transform results WPT_a, WPT_b and WPT_c. For each node k of each decomposition layer j, calculate the noise standard deviation estimate σj,k. Using the median absolute deviation method, take the median of the absolute value of the wavelet coefficient and divide it by 0.6745 to obtain σj,k. Using the calculated σj,k, calculate the SURE threshold for each node. Use the formula λj,k=σj,k*sqrt(2*log(N)) to calculate the threshold, where N is the number of sampling points. Store the calculated threshold in the threshold matrix Λ, and the matrix dimension is the same as the wavelet packet transform result. For each coefficient in the obtained WPT_a, WPT_b and WPT_c, apply the calculated SURE threshold to perform soft threshold processing. If the absolute value of the coefficient is less than the corresponding threshold, it is set to zero; otherwise, the sign of the difference between it and the threshold is retained unchanged. The denoised wavelet packet coefficients WPT_denoised_a, WPT_denoised_b and WPT_denoised_c are obtained. Calculate the signal-to-noise ratio improvement before and after denoising. Use the original wavelet packet coefficients and the denoised coefficients to calculate the signal energy and noise energy respectively. Calculate the signal-to-noise ratio before and after denoising to obtain the signal-to-noise ratio improvement value ΔSNR. Compare ΔSNR with the preset threshold. If it is lower than the threshold, return to the step of recalculating the SURE threshold for each node and adjust the threshold calculation parameters; otherwise, output the final denoising result.

[0077] Among them, the instantaneous phasor of the three-phase voltage may refer to the complex representation of the voltage of each phase in the three-phase AC power system at a specific moment. The sequence component of the three-phase voltage refers to the decomposition of the asymmetric three-phase voltage into symmetrical components, namely, positive sequence component, negative sequence component and zero sequence component. The specific method of determining the instantaneous phasor and sequence component of the three-phase voltage according to the transformed three-phase voltage data in this embodiment can be to calculate the instantaneous phasor and sequence component based on the transformed three-phase voltage data. The Hilbert transform is applied to the reconstructed voltage data of each phase respectively to obtain the corresponding analytical signal. The analytical signal is expressed in a complex form to obtain the instantaneous phasor of the three phases. Then, the instantaneous positive sequence component, the instantaneous negative sequence component and the instantaneous zero sequence component are calculated using the symmetrical component method. The calculation method of the instantaneous positive sequence component is to add the instantaneous phasor of the first phase to the instantaneous phasor of the second phase multiplied by the first power of the complex unit root, and then add the instantaneous phasor of the third phase multiplied by the second power of the complex unit root, and finally divide the result by three. The instantaneous negative sequence component is calculated by adding the instantaneous phasor of the first phase plus the instantaneous phasor of the second phase multiplied by the square of the complex unity root, plus the instantaneous phasor of the third phase multiplied by the first power of the complex unity root, and finally dividing the result by three. The instantaneous zero sequence component is calculated by adding the instantaneous phasors of the three phases and dividing by three. The complex unity root is the exponential of the product of two π divided by three and the imaginary unit.

[0078] Through such a setting in this embodiment, high-quality three-phase voltage data acquisition and preprocessing can be achieved through high-speed sampling, adaptive filtering, wavelet packet transform and other processing operations, thereby improving the accuracy and real-time performance of power quality monitoring and providing high-quality data support for comprehensive power quality management.

[0079] S120, extracting features from the preprocessed three-phase voltage data to obtain voltage disturbance features.

[0080] Among them, the voltage disturbance feature can be a feature vector obtained by extracting the time domain, frequency domain and time-frequency domain characteristics of the voltage signal. In this embodiment, the voltage disturbance feature extraction operation can be performed on the pre-processed three-phase voltage data, time-frequency representation, instantaneous phasor and sequence component. In this embodiment, the Stockwell transformation can be performed on each phase voltage data in the pre-processed three-phase voltage data to obtain the Stockwell transformation result; the time-frequency feature matrix and texture features are extracted according to the Stockwell transformation result, and the voltage disturbance feature is obtained by fusion processing.

[0081] S130 . Perform anomaly detection based on the voltage disturbance characteristics, and determine a voltage disturbance classification result according to the anomaly detection result and the voltage disturbance characteristics.

[0082] Among them, the abnormality detection result can be an abnormality degree index obtained by inputting the voltage disturbance feature into a trained model for abnormality detection. In this embodiment, the voltage disturbance feature can be input into a trained support vector data description model for abnormality detection to obtain a quantitative index of the abnormality degree. In this embodiment, the quantitative index of the abnormality degree obtained can be used to accurately identify and quantitatively describe the voltage disturbance feature through wavelet singularity detection, multi-resolution phase space reconstruction, dynamic invariant calculation, empirical mode decomposition, Hilbert-Huang transform and fuzzy reasoning, thereby obtaining the final voltage disturbance classification result.

[0083] S140. Determine a target device control strategy based on the voltage disturbance classification result, so as to control power quality through the target device control strategy.

[0084] Among them, the target device control strategy can be understood as a specific way to control the switching device of the transformer. In this embodiment, a state space model can be constructed based on the voltage disturbance classification result, a robust observer can be designed, model predictive control can be applied, control weights can be dynamically adjusted, and optimization problems can be solved to generate a PWM control signal, and the switch of the power electronic device can be controlled according to the PWM control signal, which is used as the target device control strategy to achieve accurate control of power quality.

[0085] The technical solution of the embodiment of the present invention obtains the original three-phase voltage data of the transformer, performs preprocessing operations on the original three-phase voltage data to obtain preprocessed three-phase voltage data; performs feature extraction on the preprocessed three-phase voltage data to obtain voltage disturbance features; performs anomaly detection based on the voltage disturbance features, and determines the voltage disturbance classification results based on the anomaly detection results and the voltage disturbance features; determines the target device control strategy based on the voltage disturbance classification results, so as to control the power quality through the target device control strategy. This technical solution can determine the target device control strategy based on the analysis of the voltage disturbance features, realizes the precise control of power quality problems, and improves the accuracy of power quality management.

[0086] Embodiment 2

[0087] Figure 2 It is a flow chart of a power quality control method based on disturbance classification provided according to the second embodiment of the present invention. This embodiment is optimized based on the above embodiment. The specific optimization is: extracting features from the preprocessed three-phase voltage data to obtain voltage disturbance features, including: performing time-frequency analysis on the preprocessed three-phase voltage data to obtain time-frequency analysis results; determining the time-frequency feature matrix and texture features according to the time-frequency analysis results; determining the instantaneous amplitude and phase of the three-phase voltage according to the instantaneous phasor of the three-phase voltage; and obtaining voltage disturbance features by performing feature fusion based on the time-frequency feature matrix, texture features, instantaneous amplitude and phase. Figure 2 As shown, the method includes:

[0088] S210, obtaining original three-phase voltage data of the transformer, and performing a preprocessing operation on the original three-phase voltage data to obtain preprocessed three-phase voltage data.

[0089] S220: Perform time-frequency analysis on the preprocessed three-phase voltage data to obtain a time-frequency analysis result.

[0090] Among them, the time-frequency analysis can be performed by the time-frequency analysis method to perform localized analysis on the pre-processed three-phase voltage data at different times and frequencies. The time-frequency domain analysis method in this embodiment can be a Stockwell transform method, which is a time-frequency analysis method that extends the short-time Fourier transform (STFT) and wavelet transform (WT). In this embodiment, the pre-processed three-phase voltage data can be subjected to a time-frequency analysis by performing a time-Stockwell transform to obtain a corresponding video analysis result. In this embodiment, the Stockwell transform can be performed on each phase voltage data separately, specifically, the product of the voltage data and the Gaussian window function can be Fourier transformed. Among them, the width of the Gaussian window function varies with the frequency, and adaptive adjustment of the time-frequency resolution is achieved. In this embodiment, by performing a Stockwell transform on each phase voltage data, the Stockwell transform result of each phase voltage data, that is, the time-frequency analysis result, can be obtained, which can be expressed as three-dimensional data of time, frequency and amplitude.

[0091] S230: Determine a time-frequency feature matrix and texture features according to the time-frequency analysis results.

[0092] Among them, the time-frequency feature matrix can be extracted from the time-frequency analysis results. In this embodiment, the time-frequency feature matrix can be extracted from the Stockwell transformation results of each phase voltage data. The time-frequency feature matrix may include a feature matrix obtained by combining time domain energy, frequency domain energy, and time-frequency energy distribution data. The texture feature can be a texture feature extracted from the time-frequency analysis results using a texture analysis algorithm. In this embodiment, the texture features of the three-phase voltage data can be extracted by applying an improved local binary pattern algorithm to the Stockwell transformation results of each phase voltage data.

[0093] In this embodiment, optionally, the time-frequency feature matrix and texture features are determined according to the time-frequency analysis results, including: determining the time domain energy, frequency domain energy and time-frequency energy distribution data according to the time-frequency analysis results; obtaining the time-frequency feature matrix according to the combination of time domain energy, frequency domain energy and time-frequency energy distribution data; determining the texture features according to the time-frequency analysis results and the texture analysis algorithm.

[0094] Among them, the time-frequency energy can be the energy distribution of the three-phase voltage data in the time dimension. The frequency domain energy can be the energy distribution of the three-phase voltage data in the frequency dimension. The time-frequency energy distribution data can refer to data such as the location of the energy distribution, the degree of dispersion of the distribution, and the skewness and kurtosis of the distribution. The time-frequency energy distribution data of this embodiment can include the time-frequency centroid, the time-frequency variance, and the skewness and kurtosis of the time-frequency distribution.

[0095] In this embodiment, the Stockwell transformation results in the time-frequency analysis results can be used to extract the time-frequency feature matrix, specifically, calculating the time domain energy and frequency domain energy, which correspond to the integral of the Stockwell transformation results in the time dimension and frequency dimension respectively; calculating the time-frequency centroid, indicating the center position of the energy distribution; calculating the time-frequency variance, indicating the degree of discreteness of the energy distribution; calculating the skewness and kurtosis of the time-frequency distribution, indicating the asymmetry and sharpness of the distribution respectively. In this embodiment, the specific method of obtaining the time-frequency feature matrix based on the combination of time domain energy, frequency domain energy and time-frequency energy distribution data can be to combine the time domain energy, frequency domain energy, time-frequency centroid, time-frequency variance and the skewness and kurtosis of the time-frequency distribution into a time-frequency feature matrix.

[0096] Exemplarily, the specific method for extracting the time-frequency feature matrix according to the time-frequency analysis results in this embodiment can be: obtain the Stockwell transformation results S_a(τ,f), S_b(τ,f) and S_c(τ,f) in the time-frequency analysis results. Calculate the time domain energy E_t, and for each frequency f, calculate the integral of |S(τ,f)|^2 over time τ. Obtain the time domain energies E_t_a, E_t_b and E_t_c of the three phases. Calculate the frequency domain energy E_f using the Stockwell transformation results of each phase voltage data. For each time τ, calculate the integral of |S(τ,f)|^2 over frequency f. Obtain the frequency domain energies E_f_a, E_f_b and E_f_c of the three phases. Calculate the time-frequency centroid based on the time domain energy of the three phases and the frequency domain energy of the three phases. The time centroid Centroid_t is the weighted average of |S(τ,f)|^2 and τ, and the frequency centroid Centroid_f is the weighted average of |S(τ,f)|^2 and f. The time-frequency centroids Centroid_t_abc and Centroid_f_abc of the three phases are obtained. The time-frequency variance is calculated using the Stockwell transformation results in the time-frequency analysis results. The time variance Var_t is the weighted average of |S(τ,f)|^2 and (τ-Centroid_t)^2, and the frequency variance Var_f is the weighted average of |S(τ,f)|^2 and (f-Centroid_f)^2. The time-frequency variance Var_t_abc and Var_f_abc of the three phases are obtained. The skewness and kurtosis of the time-frequency distribution are calculated using the Stockwell transformation results in the time-frequency analysis results. The skewness is the third-order central moment divided by the 1.5th power of the variance, and the kurtosis is the fourth-order central moment divided by the square of the variance. The skewness_abc and kurtosis_abc of the three phases are obtained. These calculated features are combined into a time-frequency feature matrix TF_features. Each row of the matrix corresponds to a time-frequency feature, and each column corresponds to one of the three phases. Output TF_features for subsequent analysis.

[0097] The texture analysis algorithm can be used for local feature comparison and texture analysis of an image, thereby extracting local texture features of the image. The texture analysis algorithm in this embodiment can be a local binary pattern algorithm or other texture analysis algorithms, which can be set according to actual needs.

[0098] The time-frequency analysis result in this embodiment may include a Stockwell transform amplitude map, and the Stockwell transform amplitude map may be analyzed and processed using a local binary pattern algorithm to extract texture features. Specifically, in this embodiment, a rotationally invariant uniform local binary pattern operator may be used to process the Stockwell transform amplitude map of each phase voltage, and a binary code is generated by comparing the relationship between the central pixel and its neighboring pixels, and the distribution of these codes is counted to form a local binary pattern feature vector, that is, the texture feature is obtained.

[0099] In this embodiment, through such a setting, the construction of the time-frequency feature matrix not only includes the traditional energy distribution information, but also introduces high-order statistical features such as time-frequency centroid, variance, skewness and kurtosis, which greatly enhances the description ability of complex nonlinear disturbances. The improved local binary pattern algorithm takes rotation invariance into account when extracting the texture features of the time-frequency graph, which makes the feature extraction more robust to the phase change of the signal, which is conducive to accurately identifying various types of voltage fluctuations.

[0100] S240. Determine the instantaneous amplitude and phase of the three-phase voltage according to the instantaneous phasor of the three-phase voltage.

[0101] Among them, the instantaneous amplitude of the three-phase voltage, also called the instantaneous value, may refer to the numerical value of the voltage at a certain moment. The phase of the three-phase voltage may be used to indicate the position of the voltage waveform at a certain moment. In this embodiment, the instantaneous phasor of the preprocessed three-phase voltage may be used to calculate the instantaneous amplitude and phase of the three-phase voltage. Specifically, the modulus of each phase instantaneous phasor may be calculated to obtain the corresponding instantaneous amplitude; the angle of each phase instantaneous phasor may be calculated to obtain the corresponding instantaneous phase. In this embodiment, the calculated instantaneous amplitude and phase data may be stored separately for subsequent analysis.

[0102] S250, performing feature fusion based on the time-frequency feature matrix, texture features, instantaneous amplitude and phase to obtain voltage disturbance features.

[0103] The feature fusion may be a processing operation of splicing features in order to fuse them into a complete feature vector.

[0104] In this embodiment, the statistical characteristics of instantaneous amplitude and phase (including mean, standard deviation, maximum value, minimum value, skewness, kurtosis), time-frequency feature matrix and texture feature vector can be sequentially spliced ​​to form a high-dimensional feature vector, namely, voltage disturbance feature. This feature vector fully characterizes the time domain, frequency domain and time-frequency domain characteristics of the voltage signal.

[0105] S260: Perform anomaly detection based on the voltage disturbance characteristics, and determine a voltage disturbance classification result according to the anomaly detection result and the voltage disturbance characteristics.

[0106] In this embodiment, optionally, anomaly detection is performed based on voltage disturbance characteristics, and a voltage disturbance classification result is determined through the anomaly detection result and the voltage disturbance characteristics, including: inputting the voltage disturbance characteristics into a set data description model for anomaly detection to obtain anomaly detection results; if the degree of abnormality in the anomaly detection result is greater than a set threshold, performing wavelet singularity detection on the preprocessed three-phase voltage data to determine the start and end times of the voltage disturbance; constructing a multi-resolution phase space based on the start and end times of the voltage disturbance; using the multi-resolution phase space to determine the dynamic invariant of the voltage signal, and classifying the voltage disturbance based on the dynamic invariant to obtain a voltage disturbance classification result.

[0107] Among them, the set data description model can be a support vector data description model. Support vector data description (SVDD) is an important data description method that can be used for heterogeneous point detection or classification. The anomaly detection result can be a quantitative indicator of the degree of anomaly. In this embodiment, a pre-trained support vector data description model can be used to perform anomaly detection on the voltage disturbance feature vector. Specifically, in this embodiment, the voltage disturbance feature vector can be input into the support vector data description model, the distance from the vector to the decision boundary is calculated, and this distance is used as a quantitative indicator of the degree of anomaly.

[0108] Exemplarily, in this embodiment, the specific method of supporting vector data description abnormality detection can be to obtain the voltage disturbance feature vector F. Standardize F so that the mean of each feature is 0 and the standard deviation is 1. Get the standardized feature vector F_norm. Read the pre-trained SVDD model parameters, including the support vector SV, the Lagrange multiplier α, and the kernel function parameter γ. These parameters are stored in the model parameter file. Calculate the kernel distance between F_norm and each support vector SV_i. Use the Gaussian kernel function K(F_norm,SV_i)=exp(-γ||F_norm-SV_i||^2). Get the kernel distance vector K_dist. Using K_dist and α, calculate the decision function value f(F_norm)=Σαi*K(F_norm,SV_i)-ρ, where ρ is the threshold parameter of the SVDD model. Get the decision function value f_value. Convert the obtained f_value into the degree of abnormality. Abnormality degree score=max(0,-f_value). If the score is greater than the preset threshold, it is marked as abnormal, triggering subsequent detailed analysis; otherwise, it is marked as normal; finally, the abnormal detection results are output, including the abnormality score and abnormal flag. These results will be used for subsequent disturbance analysis and control strategy adjustment.

[0109] The threshold value may be a pre-set value, and in this embodiment, it may be set according to actual needs. Wavelet singularity detection is a method of detecting singular points in signals or data using wavelet transform theory. The start and end times of the voltage disturbance correspond to the singular points obtained by wavelet singularity detection.

[0110] In this embodiment, if the degree of abnormality in the abnormality detection result is greater than a preset threshold, wavelet singularity detection is performed on the preprocessed three-phase voltage data, and the start and end times of the voltage disturbance are determined based on the identified singular points. In this embodiment, wavelet singularity detection can be performed on the wavelet packet transform results in the preprocessed three-phase voltage data, and the modulus maximum point can be found for the wavelet coefficients of each scale, that is, the position where the absolute value of the coefficient is greater than the adjacent point, and then the propagation characteristics of these modulus maximum points are compared across scales to identify the singular points in the signal. Since these singular points usually correspond to the start and end times of the voltage disturbance, the start and end times of the point cloud disturbance can be determined through these singular points.

[0111] Among them, the multi-resolution phase space can refer to the space for representing and analyzing the phase and amplitude of the signal at different resolutions. In this embodiment, for the three-phase voltage data, the amplitude and phase changes of the voltage can be observed and analyzed at different scales. In this embodiment, the multi-resolution phase space can be constructed by preprocessing the three-phase voltage data and the singular points identified by wavelet singularity detection. Specifically, three different time delays are selected to construct three phase spaces with the same embedding dimension. Each phase space consists of the original voltage data and its different delayed versions. This multi-resolution reconstruction can capture the dynamic characteristics of the signal at different time scales.

[0112] In this embodiment, the specific method of calculating the dynamic invariants of the voltage signal using the constructed multi-resolution phase space can be: first, calculate the correlation dimension, which is obtained by estimating the ratio limit of the logarithm of the correlation integral and the logarithm of the scale at different scales; then, calculate the maximum Lyapunov exponent, which is obtained by tracking the separation rate of similar trajectories in the phase space; finally, calculate the approximate entropy, which is obtained by comparing the difference in pattern matching probabilities under different embedding dimensions. These dynamic invariants characterize the complexity and prediction difficulty of the voltage signal.

[0113] Exemplarily, in this embodiment, the constructed multi-resolution phase space X(t), Y(t) and Z(t) can be used to calculate the reconstructed trajectory under different embedding dimensions m and time delay τ. For each reconstructed trajectory, the Euclidean distance between the point pairs is calculated to obtain the distance matrix D_m. Based on the distance matrix D_m, the correlation integral C(ε) is calculated. For different distance thresholds ε, the proportion of the distance logarithm less than ε to the total distance logarithm is counted. The relationship between the correlation integral curve C(ε) and ε is obtained. Using the correlation integral curve, the correlation dimension D is estimated. In double logarithmic coordinates, the linear relationship between log(C(ε)) and log(ε) is fitted. The slope of the linear part is the correlation dimension D. Output the estimated correlation dimension D_est. Based on the phase space reconstruction data of the multi-resolution phase space, calculate the maximum Lyapunov exponent λ. Select a reference trajectory in the phase space and track the separation process of adjacent trajectories. Fit the change of the separation distance over time, the slope is λ, and the maximum Lyapunov exponent λ_max is output. Using the reconstructed data of the multi-resolution phase space, calculate the approximate entropy ApEn. For different pattern lengths m, the pattern matching probability is calculated. The difference in pattern matching probability under lengths m and m+1 is calculated to obtain the approximate entropy ApEn value. The dynamic invariant vector DI = [D_est, λ_max, ApEn] is formed by comprehensively outputting the estimated correlation dimension D_est, the maximum Lyapunov exponent λ_max, and the approximate entropy ApEn value. The output DI is used for subsequent disturbance characteristic analysis and classification.

[0114] Furthermore, in this embodiment, an improved empirical mode decomposition algorithm is also applied to the preprocessed three-phase voltage data, specifically: through an iterative screening process, the original signal is decomposed into a series of intrinsic mode functions and a residual term. Each intrinsic mode function represents an inherent oscillation mode of the signal. The Hilbert transform of each intrinsic mode function is calculated to obtain an analytical signal. The instantaneous frequency and instantaneous amplitude are extracted from the analytical signal to form a Hilbert spectrum. Based on the obtained intrinsic mode function and its Hilbert spectrum, a Hilbert-Huang spectrum is constructed. The instantaneous amplitude and instantaneous frequency of each intrinsic mode function are represented on the time-frequency plane. The time-frequency representations of all intrinsic mode functions are superimposed to obtain a complete Hilbert-Huang spectrum. This spectrum clearly shows the time-varying frequency characteristics of the signal, which helps to identify complex nonlinear and non-stationary disturbances.

[0115] In this embodiment, based on the determination of dynamic invariants, singular point detection, and the Hilbert-Huang spectrum of voltage signals, a Takagi-Sugeno fuzzy inference system is constructed to classify voltage disturbances to obtain voltage disturbance classification results. Specifically, first, a fuzzy set and membership function are defined for each input feature; then, a series of if-then rules are designed, in which the antecedent part of each rule is a fuzzy description of the input feature, and the consequent part is a linear function; these rules are activated using the input features, and the trigger strength of each rule is calculated. Finally, the final disturbance classification result and confidence are obtained by weighted averaging.

[0116] In this embodiment, through such a setting, the depth and breadth of power quality analysis are greatly improved, and a strong theoretical support and data basis are provided for the formulation of accurate compensation strategies and preventive maintenance plans. In this embodiment, through wavelet singularity detection, multi-resolution phase space reconstruction, dynamic invariant calculation, empirical mode decomposition and Takagi-Sugeno fuzzy reasoning system and other technologies, accurate identification and quantitative analysis of voltage disturbances are achieved. In the specific scenario of comprehensive power quality management, they can accurately identify and quantitatively describe various complex voltage disturbances, including harmonics, interharmonics, voltage flicker, transient overvoltage, etc., and improve the system's ability to diagnose various power quality problems. Secondly, by calculating dynamic invariants, the system can evaluate the overall stability of the power grid and predict potential voltage collapse risks, which is of great significance for the safe operation of large power systems. Furthermore, the combination of EEMD and Hilbert-Huang transform enables the system to accurately separate and quantitatively analyze complex power quality problems, such as the superposition of harmonics and flicker, the coexistence of transient and continuous disturbances, etc. Finally, the application of fuzzy inference system improves the interpretability and reliability of classification results, especially when dealing with disturbance types with fuzzy boundaries, it can give more reasonable classification results and confidence.

[0117] S270 . Determine a target device control strategy based on the voltage disturbance classification result, so as to control power quality through the target device control strategy.

[0118] In this embodiment, optionally, a target device control strategy is determined based on the voltage disturbance detection result, including: determining a state space model and a state observer; determining an initial device control strategy based on the state space model and the state observer; and adjusting the initial device control strategy based on the voltage disturbance classification result to obtain a target device control strategy.

[0119] Among them, the state space model is a kind of dynamic time domain model, which uses the implicit time as the independent variable and describes the dynamic behavior of the system through the state equation and the output equation. In this embodiment, the state space model of the control system can be constructed by the voltage disturbance detection results, as well as the results and data obtained after various analyses of the pre-processed three-phase voltage. In this embodiment, the specific way to determine the state space model is to define the state vector, including key variables such as voltage and current; define the input vector, including control variables and measurable disturbances; define the output vector, including variables to be controlled; and establish the state equation and output equation according to the physical characteristics and dynamic behavior of the voltage data. The state equation describes the evolution of the system state, and the output equation describes the relationship between the system output and the state and input.

[0120] Among them, the state observer can be a type of dynamic system that obtains the estimated value of the state variable based on the measured value of the external variables (input variables and output variables) of the system. In this embodiment, a robust H∞ state observer can be designed based on the constructed state space model. First, a set of constraints for system disturbances and measurement noise is defined; then, a Riccati equation is constructed, which contains a system matrix and a noise covariance matrix; the Riccati equation is solved to obtain a positive definite matrix solution. Using this matrix solution, the observer gain matrix is ​​calculated. Finally, a state observer equation is constructed, including a state prediction part and an error correction part.

[0121] Exemplarily, the specific process of robust H∞ state observer design can be to obtain the constructed state space model parameters, including system matrix A, input matrix B, output matrix C and direct transfer matrix D. Define the system disturbance matrix E and measurement noise matrix F. Set the H∞ performance index γ. Construct a generalized control system, take the state estimation error as the controlled output, and take the system disturbance and measurement noise as external input. Form an augmented system matrix [A, E; C, F]. Construct the algebraic Riccati equation AX+XA^T+X(γ^-2*EE^TC^TC)X+BB^T=0. Use numerical methods (such as Schur decomposition method) to solve the equation and obtain the positive definite matrix solution X. Using the obtained positive definite matrix solution X, calculate the observer gain matrix L=XC^T*R^(-1), where R is the measurement noise covariance matrix. Store L for subsequent state estimation. Construct the state observer equation dx^ / dt=Ax^+Bu+L(y-Cx^-Du). Where x^ is the state estimate, u is the control input, and y is the system measured output. Perform observer stability analysis. Calculate the eigenvalues ​​of A-LC and ensure that the real part of all eigenvalues ​​is negative to ensure the asymptotic stability of the observer. Output the stability analysis results.

[0122] Among them, the initial device control strategy can be the initial device control mode predicted by the model. In this embodiment, the state space model and the state observer can be used to generate the initial device control strategy by model predictive control. Define the prediction time domain and the control time domain; construct the objective function, including the state tracking error term and the control input penalty term; set the constraints, including the state constraints and the control input constraints; transform the problem into a finite time domain optimization problem, the goal is to minimize the objective function under the condition of satisfying the constraints to obtain the preliminary device control strategy. Then, according to the voltage disturbance analysis results, the weight matrix of the model predictive control can be dynamically adjusted; the weight matrix of the state tracking error can be adjusted according to the importance of different state variables and the current disturbance characteristics; the penalty weight matrix of the control input can be adjusted according to the current system state and the control target. This adaptive weight adjustment enables the control strategy to better cope with disturbances of different types and degrees. The improved interior point method can also be used to solve the constructed model predictive control optimization problem. First, the constraint problem is converted into an unconstrained problem and the barrier function is introduced. Then, the modified KKT (Karush-Kuhn-Tucker) condition is solved using the Newton method. Through the iterative process, the barrier parameters are gradually reduced, and the original variables and dual variables are updated at the same time; finally, the optimal control sequence that meets the accuracy requirements is obtained; the obtained optimal control sequence is converted into a PWM (pulse width modulation) control signal. The space vector pulse width modulation algorithm is used to map the continuous control quantity to the discrete switching state. First, the reference voltage vector is calculated according to the control quantity. Then, the adjacent basic voltage vectors are selected. The action time of each basic vector is calculated. Finally, according to the calculated time sequence, a specific PWM waveform is generated to control the switch of the power electronic device, that is, the target device control strategy is obtained.

[0123] Exemplarily, the specific process of the model predictive control application in this embodiment can be to obtain the state estimate x^ of the step state space model and the state observer. Define the prediction time domain Np and the control time domain Nc. Initialize the state prediction sequence X and the control sequence U. Construct a prediction model: Use the state equation x(k+1)=Ax(k)+Bu(k) to gradually predict the state of the next Np steps. Form a state prediction matrix X=f(x^,U), where f represents the iterative prediction process. Define the objective function J=Σ(||x(k+i|k)-xref||^2_Q+||u(k+i|k)||^2_R). Where Q is the state weight matrix, R is the control weight matrix, and xref is the reference trajectory. Express the objective function as a quadratic form of the control sequence U. Set constraints. Including the control input constraint umin≤u(k+i|k)≤umax and the state constraint xmin≤x(k+i|k)≤xmax. Express the constraints as the linear inequality AU≤b about U. Combine the defined objective function and the set constraints to form a standard quadratic programming problem: min0.5U^THU+f^TU, stAU≤b. H is the Hessian matrix of the objective function and f is the coefficient of the first-order term. Use a quadratic programming solver (such as the interior point method) to solve the optimization problem constructed in S435. Obtain the optimal control sequence U*. Extract the first element u(k|k) of U as the current control input.

[0124] In this embodiment, through such a setting, the accuracy, speed and adaptability of power quality management are significantly improved, and strong technical support is provided for achieving high-quality and high-reliability power supply. In this embodiment, by constructing an accurate state space model, designing a robust H∞ state observer, applying model predictive control, dynamically adjusting control weights and other technologies, accurate control and compensation of power quality problems are achieved. In the specific scenario of comprehensive power quality management, rapid and accurate compensation of various voltage disturbances can be achieved. For example, in the case of a voltage sag, the system can respond quickly within a few cycles, restore the voltage to the allowable range, and effectively protect sensitive loads. For harmonic problems, the control strategy can accurately generate reverse compensation currents, significantly reduce the total harmonic distortion (THD), and improve power quality. Secondly, the application of MPC enables the system to seek the best balance between multiple objectives. For example, when dealing with voltage imbalance problems, the controller can simultaneously consider negative sequence current compensation and power loss minimization to achieve the best compensation effect. Furthermore, the use of robust observers greatly improves the stability and reliability of the system in a complex power grid environment. Even when the load changes sharply or the grid parameters are uncertain, the system can still maintain good control performance. This is particularly important for modern power grids that contain a large number of distributed energy resources and nonlinear loads. Finally, the dynamic weight adjustment strategy enables the system to flexibly respond to disturbances of different types and degrees. For example, when facing severe voltage sags, the system automatically increases the weight of voltage stability control; when dealing with minor harmonic problems, it will pay more attention to energy efficiency. This adaptive capability ensures that the system can maintain optimal performance under various conditions.

[0125] In this embodiment, optionally, after controlling the power quality through the target device control strategy, it also includes: determining system performance indicators according to the control results of controlling the power quality through the target device control strategy; and performing a comprehensive performance evaluation based on the system performance indicators to obtain a performance report.

[0126] Among them, the system performance index can be a performance index of the power quality control system, which can be used to evaluate the performance status of the entire power quality control system. In this embodiment, the system performance index may include index data such as voltage deviation, total harmonic distortion, voltage imbalance, and dynamic response time. In this embodiment, the system performance can be evaluated and self-optimized based on the results of the above analysis and processing steps. Continuous improvement of the system can be achieved by calculating performance indicators, applying fuzzy comprehensive evaluation, updating optimization targets, performing parameter optimization, and generating performance reports. The comprehensive performance evaluation can be a comprehensive evaluation result of the system performance obtained by establishing an evaluation grade and a membership function through a fuzzy comprehensive evaluation method. The performance report can be a report formed based on data in the process of determining the system performance indicators for comprehensive performance evaluation.

[0127] In this embodiment, the pre-processed voltage data and the control results of the target device control strategy to control the power quality can be used to calculate the system performance index, which can be specifically calculated as voltage deviation, that is, the relative error between the actual voltage and the reference voltage; total harmonic distortion, that is, the ratio of the square sum of the effective values ​​of each harmonic voltage to the effective value of the fundamental voltage; voltage imbalance, that is, the ratio of the negative sequence voltage component to the positive sequence voltage component; and dynamic response time, that is, the time interval from the occurrence of the disturbance to the voltage recovery to the steady state. Based on the calculated performance indicators, the fuzzy comprehensive evaluation method is applied. First, an evaluation level and a membership function are established for each performance indicator. Then, a fuzzy relationship matrix is ​​constructed, whose elements represent the membership of each indicator corresponding to each evaluation level. A weight vector is defined to reflect the relative importance of each indicator. Finally, a comprehensive evaluation result of the system performance is obtained through fuzzy synthesis operation. According to the comprehensive performance evaluation results, the objective function of parameter optimization is updated. Indicators such as voltage deviation, total harmonic distortion, voltage imbalance and dynamic response time are integrated into the objective function. According to the current system state and control requirements, the weights of each indicator in the objective function are dynamically adjusted. This updated objective function will guide the subsequent parameter optimization process. Then, the improved particle swarm optimization algorithm is used to optimize the control parameters based on the updated objective function. Initialize the particle swarm, and each particle represents a set of candidate control parameters. Define the particle position update formula and velocity update formula, which contain inertia weight, individual learning factor and social learning factor. Iterate the update of particle position and velocity, and evaluate the fitness of each particle. Record the global optimal solution and individual optimal solution until the termination condition is met. Apply the optimized parameters to the target device control strategy. Update the prediction model parameters used in model predictive control, including the state transfer matrix and input matrix. Update the gain matrix of the state observer to improve the accuracy of state estimation. Adjust the weight matrix of the objective function in model predictive control, including the weight of state tracking error and the penalty weight of control input. These updates will improve the performance and robustness of the control system. Generate a detailed system performance report based on the system evaluation process and results. Summarize the current system status, including key electrical parameters and operating indicators. Analyze each performance indicator in detail, including its value, change trend and deviation from the target value. List the optimized control parameters and compare them with the previous parameters. Provide optimization suggestions, including possible hardware upgrades and control strategy adjustments. Analyze historical data, plot trend charts of key indicators, and identify long-term performance changes and potential problems. Finally, generate a comprehensive evaluation report that summarizes the overall performance of the system and proposes directions for further improvement.

[0128] Exemplarily, in this embodiment, the specific process of fuzzy comprehensive evaluation based on system performance indicators can be: obtaining calculated performance indicators, including voltage deviation ΔV, total harmonic distortion THD, voltage imbalance VUF and dynamic response time Tr. Define the evaluation level set V = {very good, good, general, poor, very poor}. Construct a membership function for each performance indicator. Use a trapezoidal or Gaussian function to define the membership of each level. For example, define μΔV(x) = {μ1(x), μ2(x), μ3(x), μ4(x), μ5(x)} for ΔV, where μi(x) represents the membership of the i-th level. Using the defined membership function, calculate the membership of each performance indicator to each evaluation level. Form a fuzzy relationship matrix R, where Ri j represents the membership of the i-th indicator to the j-th evaluation level. Determine the weight vector W = {w1, w2, w3, w4}, which represents the relative importance of each performance indicator. The weight can be determined using the hierarchical analysis method or the expert scoring method. Ensure that the sum of the weights is 1. Perform fuzzy synthesis operation S = W○R, where ○ represents the fuzzy synthesis operator. Commonly used synthesis operators include M(∧,∨) and M(·,∨). Obtain the comprehensive evaluation result vector S. Defuzzify the obtained evaluation result S. The maximum membership method or the centroid method can be used. Obtain the quantitative score and qualitative grade of system performance, and output the evaluation result for subsequent optimization decision-making.

[0129] The improved particle swarm optimization algorithm in this embodiment is implemented as follows: obtain the comprehensive performance evaluation results and update the objective function J_opt of parameter optimization. Define the particle position vector x to represent the control parameter to be optimized, and the velocity vector v to represent the update direction and step size of the parameter. Initialize the particle swarm and randomly generate the position x and velocity v of N particles. Evaluate the fitness of each particle. Substitute the position x of each particle into the objective function J_opt and calculate the function value. Record the individual optimal position pi and the global optimal position pg of each particle. Update the speed of each particle. Use the formula v(t+1)=wv(t)+c1r1*(pi-x(t))+c2r2(pg-x(t)). Where w is the inertia weight, c1 and c2 are acceleration constants, and r1 and r2 are random numbers between [0,1]. Update the particle position based on the calculated speed of each particle. Use the formula x(t+1)=x(t)+v(t+1). Check whether the updated position meets the constraints and make corrections if it exceeds the boundary. Re-evaluate the fitness of the updated particle, compare the fitness of the new position with the individual optimal position pi, and update pi if it is better. Compare the pi of all particles and update the global optimal position pg. Check the termination condition. It can be that the maximum number of iterations is reached, or the improvement of the global optimal solution is less than the preset threshold. If the termination condition is met, the optimal solution pg is output; otherwise, return to the step of updating the speed of each particle to continue iterating. Perform local search optimization on the optimal solution pg. Use the pattern search method to explore a small range around pg. Try along the positive and negative directions of each dimension, and update pg if a better solution is found. Repeat this process until no better solution can be found. Verify the feasibility of the final optimization result. Substitute the optimized control parameters into the system model for simulation verification. Check whether all constraints are met and calculate various performance indicators. If the requirements are not met, adjust the optimization parameters and return to obtain the comprehensive performance evaluation results. Update the objective function of parameter optimization and re-execute the optimization process. Output the final optimization results, including the optimal control parameter values, objective function values, and various performance indicators. These results will be used to update the control strategy and system configuration.

[0130] In this embodiment, through such a setting, by introducing system performance evaluation and self-optimization mechanism, including calculating multi-dimensional performance indicators, applying fuzzy comprehensive evaluation, updating optimization targets, executing improved particle swarm optimization algorithm and other innovative technologies, the continuous optimization and performance improvement of the comprehensive power quality management system are achieved, and the intelligent level and adaptive ability of the comprehensive power quality management system are enhanced, which provides strong technical support for the long-term stable operation and continuous optimization of the power grid. First, the calculation of multi-dimensional performance indicators, such as voltage deviation, total harmonic distortion, voltage imbalance and dynamic response time, provides a comprehensive evaluation of system performance. This multi-angle evaluation method can capture all aspects of power quality problems and avoid the one-sidedness that may be caused by a single indicator. The application of fuzzy comprehensive evaluation method can handle the uncertainty and ambiguity in performance evaluation and give more reasonable and comprehensive evaluation results. In the specific scenario of comprehensive power quality management, first of all, they realize a comprehensive and objective evaluation of the performance of the power quality control system. Secondly, the application of fuzzy comprehensive evaluation method greatly improves the reliability and practicality of the evaluation results. Especially when dealing with some performance indicators that are difficult to quantify, such as the stability margin of the system or the ability to respond to emergencies, fuzzy evaluation can give more realistic evaluation results. In addition, the self-optimization mechanism of this step also significantly improves the long-term reliability and efficiency of the system. Through continuous performance monitoring and parameter optimization, the system can continuously adapt to long-term factors such as equipment aging and changes in load characteristics to maintain optimal operating conditions. This not only improves the power quality, but also reduces the operating costs and maintenance requirements of the system. Finally, this self-optimization mechanism provides the power quality management system with the ability to learn and evolve. Through the long-term accumulation of operating data and optimization experience, the system can continuously improve its control strategy and evaluation criteria, and gradually improve its ability to handle complex power quality issues.

[0131] In a further embodiment, it also includes: performing system adaptive optimization based on the performance evaluation results in the performance report. Through online parameter identification, adaptive control law update, multi-objective optimization and robustness analysis, continuous optimization and performance improvement of the system are achieved. Online parameter identification is performed using pre-processed high-quality voltage data and the control output of the target device control strategy. The system model parameters are updated in real time using the recursive least squares method. First, the error equation for parameter estimation is constructed. Then, the Kalman gain is calculated to update the parameter estimation value. The covariance matrix is ​​updated to reflect the uncertainty of the parameter estimation. Finally, the updated system model parameters are obtained, including elements of the state transfer matrix and the input matrix. Based on the identified system parameters, the adaptive control law is updated. The model reference adaptive control method is adopted to design the reference model and define the tracking error. The Lyapunov function is constructed to ensure the stability of the system. The parameter adaptive law is derived so that the actual system output gradually approaches the reference model output. The controller parameters are updated, including the feedback gain and the feedforward gain. This adaptive mechanism enables the control system to adapt to changes in system parameters and external disturbances. Multi-objective optimization is performed using the updated objective function in the above performance evaluation process. An improved non-dominated sorting genetic algorithm (NSGA-III) is used to consider multiple objectives such as voltage stability, harmonic suppression and energy efficiency. The population is initialized, and each individual represents a set of control parameters. Crossover and mutation operations are performed to generate new offspring. Elite individuals are selected based on non-dominated sorting and crowding calculations. The evolutionary process is iterated to obtain a set of Pareto optimal solutions. This set of solutions reflects the trade-offs between different objectives and provides multiple options for decision-making. The robustness analysis of the obtained Pareto optimal solutions is performed. The system parameters and external disturbances are randomly sampled using the Monte Carlo simulation method. For each set of Pareto optimal solutions, simulations are performed under different parameters and disturbance conditions. The statistical characteristics of the performance indicators, including mean, variance and probability distribution, are calculated. The stability and performance degradation of each set of solutions under parameter uncertainty and disturbance are evaluated. The solution with the best comprehensive performance and robustness is selected as the final control parameter.

[0132] Update the control strategy based on the robustness analysis results. Introduce parameter uncertainty description to the prediction model of model predictive control to improve the accuracy of prediction. Add robustness terms to the objective function to balance nominal performance and worst-case performance. Update constraints to consider the impact of parameter changes. Modify the solution algorithm and use robust optimization techniques such as the minimax method or probabilistic constraint methods. These updates will improve the performance of the control system under uncertainty and disturbances. Apply the updated control strategy to the actual system. First, conduct comprehensive tests in a simulation environment to verify the effectiveness and safety of the new strategy. Then, design a smooth transition mechanism to gradually introduce the new control parameters and algorithms to the actual system. Monitor key performance indicators, including voltage stability, harmonic content, and dynamic response characteristics. Record system responses and compare and analyze them with previous performance. If anomalies occur, immediately trigger a rollback mechanism to restore to the previous stable configuration. Perform long-term performance analysis and predictive maintenance based on actual operating data. Use time series analysis methods such as the autoregressive integrated moving average model (ARIMA) to perform trend analysis and forecasting of key performance indicators. Apply machine learning algorithms, such as support vector regression or random forest, to build equipment health status assessment models. Based on the analysis results, formulate predictive maintenance plans, including equipment inspections, parameter fine-tuning, and component replacement recommendations. This data-based maintenance strategy can improve the long-term reliability and efficiency of the system.

[0133] The technical solution of the embodiment of the present invention obtains the original three-phase voltage data of the transformer, performs preprocessing operations on the original three-phase voltage data to obtain preprocessed three-phase voltage data; performs feature extraction on the preprocessed three-phase voltage data to obtain voltage disturbance features; performs anomaly detection based on the voltage disturbance features, and determines the voltage disturbance classification results based on the anomaly detection results and the voltage disturbance features; determines the target device control strategy based on the voltage disturbance classification results, so as to control the power quality through the target device control strategy. This technical solution can determine the target device control strategy based on the analysis of the voltage disturbance features, realizes the precise control of power quality problems, and improves the accuracy of power quality management.

[0134] Embodiment 3

[0135] Figure 3 1 is a schematic diagram of the structure of a power quality comprehensive management system provided according to the third embodiment of the present invention. The power quality comprehensive management system can be used to execute a power quality control method based on disturbance classification in any of the above embodiments. Figure 3As shown in the figure, the comprehensive power quality management system mainly includes a three-phase three-winding transformer, a back-to-back converter and a bypass switch. The three windings in the three-winding transformer are the primary winding D1, the auxiliary circuit winding D2 and the main circuit winding Y1. Among them, the output of D2 is used as the AC input of the rectifier stage of the back-to-back converter, and each phase in Y1 is connected to the load after being connected in series with the inverter stage output in the back-to-back converter. The bypass switch is used to switch the output of the inverter stage.

[0136] In this embodiment, by controlling the back-to-back converter in the auxiliary circuit, the power quality compensation and support functions that traditional transformers do not have can be achieved. According to the two-stage structure and functional characteristics of the back-to-back converter, the working principles of the rectifier stage and the inverter stage can be analyzed separately. The rectifier stage is connected to D2 through a filter inductor and connected in parallel to the load circuit through transformer coupling, which can provide reactive power compensation for the power grid when necessary. At the same time, as the front stage of the back-to-back converter, the rectifier stage needs to provide stable DC voltage support for the inverter stage. In the present invention, the inverter stage converter is a three-phase four-bridge arm topology, with the fourth bridge arm as the midpoint, and the three phases are independent. The output of the inverter stage is directly connected in series to the sensitive load power supply circuit, which can adjust the voltage in the main circuit, provide voltage support for sensitive loads, and maintain the stability of the load voltage. The input of the inverter stage compensation can be controlled by controlling the opening and closing of the bypass switch.

[0137] The main control objectives of the rectifier converter are twofold: one is to control the DC side capacitor voltage to maintain at a reference value, and the other is to absorb or emit reactive power to complete reactive compensation for the grid by controlling the output reactive current. In order to achieve these two control objectives, this paper adopts a dual closed-loop decoupled PI control structure with a voltage outer loop and a current inner loop.

[0138] The design steps of the rectifier stage voltage outer loop control strategy are:

[0139] According to the low-frequency model of the three-phase two-level rectifier, when the switching frequency is much larger than the grid fundamental frequency, the harmonic components in the PWM can be ignored. At this time, the switching function s k (k=a,b,c) can be expressed as

[0140]

[0141] Where m is the modulation ratio of PWM, θ is the initial phase angle of the fundamental wave of the switching function, and ω is the fundamental angular frequency of the grid voltage.

[0142] For unity power factor sine wave current control, the grid-side current of the three-phase two-level rectifier is

[0143]

[0144] In the formula, I m Indicates the peak current of the grid side.

[0145] In addition, the DC side current i of the three-phase two-level rectifier dc The switch function has the following relationship:

[0146] i dc =s a i a +s b i b +s c i c ;

[0147] Based on the above formula, the DC side current can be approximately expressed as:

[0148] i dc ≈0.75mcosθI m ;

[0149] The 0.75mcosθ in the formula is a time-varying coefficient. In order to facilitate the design of control parameters, the maximum value of the coefficient, 0.75 (m≤1), can be selected to replace the coefficient.

[0150] When the PI controller is used to control the DC side voltage, the current loop transfer function can be approximated as a small inertia link, that is:

[0151]

[0152] In the formula, G V (s) represents the DC side voltage controller, G I (s) is the current loop closed-loop equivalent transfer function, K v and T v is the parameter of the voltage controller, T s Indicates the sampling period.

[0153] At this time, the voltage outer loop open-loop transfer function is:

[0154]

[0155] The voltage outer loop controller parameters can be designed according to the above formula.

[0156] The specific design steps of the rectifier stage current inner loop control strategy are as follows:

[0157] The dq model of the three-phase two-level rectifier is as follows:

[0158]

[0159] In the formula, e d and e q is the dq axis component of the three-phase grid voltage; v d and v qis the dq axis component of the AC side voltage of the three-phase two-level rectifier; i d and i q is the dq-axis component of the AC side current of the three-phase two-level rectifier, and ρ is the differential operator.

[0160] It can be seen from the equation that there is coupling between the d and q axes, which makes the controller design difficult. Therefore, this paper adopts the current control strategy of feedforward decoupling, oriented to the d axis, and the control equation is as follows:

[0161]

[0162] Where, KiP and KiI are the regulation gain and integral regulation gain of the current inner loop PI respectively; d * and i q * are the reference values ​​of the grid-side current dq axis respectively.

[0163] Considering the sampling delay and the inertial characteristics of PWM, after zero-pole correction according to the I-type system, the open-loop transfer function of the current inner loop is:

[0164]

[0165] Where KPWM is the three-phase two-level rectifier bridge PWM equivalent gain.

[0166] In this embodiment, the parameters of the current inner loop controller can be designed according to the above formula.

[0167] In this embodiment, the inverter stage of the back-to-back converter is responsible for providing voltage support when the load voltage drops to ensure the stability of the sensitive load voltage. Therefore, the control strategy for the inverter stage is mainly divided into two parts, one is the grid connection point voltage detection algorithm, and the other is the inverter stage output control strategy. This paper selects voltage and current dual closed-loop control as the control method for the inverter stage output. In this embodiment, the grid connection point voltage detection process is: the three-phase voltage at the grid connection point collected is Park transformed to obtain the grid connection point three-phase voltage in the dq coordinate system, which is used to determine whether the voltage drop occurs at the grid connection point after low-pass filtering: if no voltage drop occurs, no compensation is made; if a voltage drop occurs, the inverter stage compensation is started, and the compensation voltage reference value in the dq coordinate system is calculated. The voltage drop on the load is controlled by the voltage and current dual closed-loop control. In this embodiment, the inverter stage output control strategy voltage outer loop adopts PI controller, and the current inner loop adopts proportional control. After obtaining the output control compensation voltage of the inverter-stage converter in the dq coordinate system, a Park inverse transform is performed to obtain the control compensation voltage of the inverter-stage converter in the three-phase stationary coordinate system, and SVPWM modulation is performed to obtain the switch control signal of the inverter-stage converter.

[0168] When the power quality control method based on disturbance classification in this embodiment is implemented using the topology structure shown in the power quality comprehensive management system, the data processing flow is as follows:

[0169] Step S310: Obtain the original three-phase voltage data, and obtain the pre-processed three-phase voltage data, time-frequency representation, instantaneous phasor and sequence component through a series of data processing steps. Specifically, firstly, the voltage data is collected from the primary winding D1, the auxiliary circuit winding D2 and the main circuit winding Y1 of the three-phase three-winding transformer. Then, the original data is adaptively filtered and denoised, time-frequency analysis and adaptive threshold denoising are performed, and then a high-quality voltage signal is reconstructed, and finally the instantaneous phasor and sequence component are calculated.

[0170] Step S320: Use the pre-processed high-quality three-phase voltage data, time-frequency representation, instantaneous phasor and sequence component to extract and classify voltage disturbance features. At the same time, the capacitor voltage data is collected from the DC side of the back-to-back converter as an additional feature input. By calculating the instantaneous amplitude and phase, applying the Stockwell transform, extracting the time-frequency features, applying the local binary pattern, constructing the feature vector, and finally using the support vector data description for anomaly detection.

[0171] Step S330: Based on the abnormality detection result of step S2, the detected voltage disturbance is accurately identified and quantitatively analyzed. In addition, current data is collected from the rectifier and inverter stages of the back-to-back converter for auxiliary analysis. Accurate identification and quantitative description of disturbances are achieved through wavelet singularity detection, multi-resolution phase space reconstruction, dynamic invariant calculation, empirical mode decomposition, Hilbert-Huang transform and fuzzy reasoning.

[0172] Step S340: Generate an adaptive control strategy based on the disturbance analysis results of step S3. Collect the state information of the bypass switch to decide whether to start the inverter compensation. Accurately control the power quality by constructing a state space model, designing a robust observer, applying model predictive control, dynamically adjusting the control weight, solving the optimization problem and generating a PWM control signal. Finally, the generated control signal is output to the rectifier and inverter stages of the back-to-back converter.

[0173] Step S350: Based on the results of steps S310 to S340, the system performance is evaluated and self-optimized. The voltage and current data on the load side are collected to calculate the actual power quality indicators. The system is continuously improved by calculating performance indicators, applying fuzzy comprehensive evaluation, updating optimization targets, performing parameter optimization, and generating performance reports. Finally, the optimized parameter settings are output to the back-to-back converter and control system.

[0174] In this embodiment, the three-phase winding transformer (including the primary winding D1, the auxiliary circuit winding D2 and the main circuit winding Y1) provides the basis for the entire system. The system is able to convert electric energy between different voltage levels and provide a flexible interface for power quality control. In the data processing flow of Example 2, the high-speed sampling and signal processing of step S1 are based on the voltage data collected by this transformer structure. The back-to-back converter, including the rectifier stage and the inverter stage, is the core hardware for realizing power quality control. The model predictive control (MPC) and PWM control signal generation in step S4 are designed for this back-to-back converter. The rectifier stage is used for reactive power compensation and DC voltage support, while the inverter stage is used for voltage support, which is directly related to the design of the control strategy. The structure of the auxiliary circuit (D2 winding connected to the rectifier stage of the back-to-back converter) and the main circuit (Y1 winding connected to the load through the inverter stage output) provides a way to implement the control strategy. The control strategy designed in step S340 is based on this structure, which realizes reactive power compensation by controlling the rectifier stage and realizes voltage support by controlling the inverter stage. The bypass switch is used to switch the inverter output and plays a key role in the control strategy. In the control strategy of step S340, the system needs to decide whether to start the inverter compensation according to the voltage disturbance, which is achieved by controlling the bypass switch.

[0175] The control objectives and strategies of the inverter level include DC side capacitor voltage control and reactive power compensation. This corresponds directly to the model predictive control strategy designed in step S340, especially in dealing with reactive power compensation and DC voltage stability. The inverter level control strategy, including grid connection point voltage detection and dynamic voltage support, is related to the disturbance identification and control strategy designed in steps S330 and S340. This function is enhanced by more advanced algorithms such as wavelet singularity detection and fuzzy reasoning. The voltage and current dual closed-loop control structure is consistent with the control strategy framework designed in step S340.

[0176] In general, based on the hardware topology of the power quality comprehensive management system in this embodiment, the power quality control method based on disturbance classification realizes a more efficient and intelligent power quality comprehensive management system through advanced signal processing, intelligent identification algorithm and optimization control strategy. This solution fully utilizes the advantages of the existing hardware structure, and at the same time, through the innovation of software algorithms, it greatly improves the performance and adaptability of the system.

[0177] Embodiment 4

[0178] Figure 4 is a schematic diagram of the structure of a power quality control device based on disturbance classification according to Embodiment 4 of the present invention. Figure 4 As shown, the device comprises:

[0179] The data acquisition module 410 is used to acquire the original three-phase voltage data of the transformer, and perform a preprocessing operation on the original three-phase voltage data to obtain the preprocessed three-phase voltage data;

[0180] A feature extraction module 420 is used to extract features from the preprocessed three-phase voltage data to obtain voltage disturbance features;

[0181] A voltage disturbance classification result determination module 430 is used to perform anomaly detection based on voltage disturbance characteristics, and determine a voltage disturbance classification result through anomaly detection results and voltage disturbance characteristics;

[0182] The control strategy determination module 440 is used to determine the target device control strategy based on the voltage disturbance classification result, so as to control the power quality through the target device control strategy.

[0183] Optionally, the preprocessed three-phase voltage data includes instantaneous phasors and sequence components of the three-phase voltage;

[0184] The data acquisition module 410 is specifically used to obtain the original data of the three-phase voltage, filter the original data of the three-phase voltage using a set filter to obtain filtered three-phase voltage data; perform wavelet packet transformation on the filtered three-phase voltage data to obtain transformed three-phase voltage data; and determine the instantaneous phasor and sequence component of the three-phase voltage based on the transformed three-phase voltage data.

[0185] Optionally, the feature extraction module 420 includes:

[0186] A data time-frequency analysis unit is used to perform time-frequency analysis on the preprocessed three-phase voltage data to obtain a time-frequency analysis result;

[0187] A feature determination unit, used to determine a time-frequency feature matrix and texture features according to the time-frequency analysis result;

[0188] A voltage instantaneous data determination unit, used to determine the instantaneous amplitude and phase of the three-phase voltage according to the instantaneous phasor of the three-phase voltage;

[0189] The feature fusion unit is used to obtain voltage disturbance features by performing feature fusion based on the time-frequency feature matrix, texture features, instantaneous amplitude and phase.

[0190] Optionally, a feature determination unit is specifically used to determine time domain energy, frequency domain energy and time-frequency energy distribution data based on the time-frequency analysis results; obtain a time-frequency feature matrix based on the combination of time domain energy, frequency domain energy and time-frequency energy distribution data; and determine texture features based on the time-frequency analysis results and a texture analysis algorithm.

[0191] Optionally, the voltage disturbance classification result determination module 430 is specifically configured to:

[0192] Input the voltage disturbance characteristics into the set data description model to perform anomaly detection and obtain anomaly detection results;

[0193] If the abnormality degree in the abnormality detection result is greater than the set threshold, the preprocessed three-phase voltage data is subjected to wavelet singularity detection to determine the start and end time of the voltage disturbance;

[0194] Construct a multi-resolution phase space according to the start and end times of the voltage disturbance;

[0195] The dynamic invariant of the voltage signal is determined using the multi-resolution phase space, and the voltage disturbance classification is performed based on the dynamic invariant to obtain the voltage disturbance classification result.

[0196] Optionally, the control strategy determination module 440 is specifically used to:

[0197] Determine the state space model and state observer;

[0198] Determining an initial device control strategy based on a state-space model and a state observer;

[0199] The initial device control strategy is adjusted based on the voltage disturbance classification result to obtain the target device control strategy.

[0200] Optionally, the device also includes a performance evaluation module, which is used to determine system performance indicators based on the control results of controlling the power quality by the target device control strategy after controlling the power quality through the target device control strategy; and perform a comprehensive performance evaluation based on the system performance indicators to obtain a performance report.

[0201] A power quality control device based on disturbance classification provided in an embodiment of the present invention can execute a power quality control method based on disturbance classification provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0202] Embodiment 5

[0203] Figure 5 1 is a schematic diagram of the structure of an electronic device provided according to Embodiment 5 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0204] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0205] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0206] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a power quality control method based on disturbance classification.

[0207] In some embodiments, the power quality control method based on disturbance classification may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the power quality control method based on disturbance classification described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the power quality control method based on disturbance classification in any other appropriate manner (e.g., by means of firmware).

[0208] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0209] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0210] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0211] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0212] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0213] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0214] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0215] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A power quality control method based on disturbance classification, characterized in that: include: Acquire original three-phase voltage data of the transformer, and perform a preprocessing operation on the original three-phase voltage data to obtain preprocessed three-phase voltage data; Perform feature extraction on the preprocessed three-phase voltage data to obtain voltage disturbance features; Performing anomaly detection based on the voltage disturbance feature, and determining a voltage disturbance classification result according to the anomaly detection result and the voltage disturbance feature; A target device control strategy is determined based on the voltage disturbance classification result, so as to control the power quality through the target device control strategy.

2. The method according to claim 1, characterized in that The preprocessed three-phase voltage data includes instantaneous phasors and sequence components of the three-phase voltage; Acquiring three-phase voltage raw data, and performing a preprocessing operation on the three-phase voltage raw data to obtain three-phase voltage data, including: Acquire three-phase voltage raw data, and filter the three-phase voltage raw data using a set filter to obtain filtered three-phase voltage data; Performing wavelet packet transformation on the filtered three-phase voltage data to obtain transformed three-phase voltage data; The instantaneous phasor and sequence component of the three-phase voltage are determined according to the transformed three-phase voltage data.

3. The method according to claim 2, characterized in that The voltage disturbance features are obtained by extracting the preprocessed three-phase voltage data, including: Performing time-frequency analysis on the preprocessed three-phase voltage data to obtain a time-frequency analysis result; Determine the time-frequency feature matrix and texture features according to the time-frequency analysis results; Determining the instantaneous amplitude and phase of the three-phase voltage according to the instantaneous phasor of the three-phase voltage; The voltage disturbance feature is obtained by performing feature fusion based on the time-frequency feature matrix, texture feature, instantaneous amplitude and phase.

4. The method according to claim 3, characterized in that Determining a time-frequency feature matrix and a texture feature according to the time-frequency analysis result includes: Determine time domain energy, frequency domain energy and time-frequency energy distribution data according to the time-frequency analysis results; Obtaining a time-frequency feature matrix according to the time domain energy, the frequency domain energy and the time-frequency energy distribution data combination; The texture features are determined according to the time-frequency analysis results and the texture analysis algorithm.

5. The method according to claim 1, characterized in that Performing anomaly detection based on the voltage disturbance feature, and determining a voltage disturbance classification result according to the anomaly detection result and the voltage disturbance feature, including: Inputting the voltage disturbance characteristics into a set data description model to perform anomaly detection to obtain an anomaly detection result; If the abnormality degree in the abnormality detection result is greater than a set threshold, wavelet singularity detection is performed on the preprocessed three-phase voltage data to determine the start time and end time of the voltage disturbance; Constructing a multi-resolution phase space according to the starting time and the ending time of the voltage disturbance; The multi-resolution phase space is used to determine a dynamic invariant of a voltage signal, and voltage disturbance classification is performed based on the dynamic invariant to obtain a voltage disturbance classification result.

6. The method according to claim 1, characterized in that Determining a target device control strategy based on the voltage disturbance detection result includes: Determine the state space model and state observer; determining an initial device control strategy based on the state-space model and the state observer; The initial device control strategy is adjusted based on the voltage disturbance classification result to obtain a target device control strategy.

7. The method according to claim 1, characterized in that After controlling the power quality by the target device control strategy, the method further includes: Determine system performance indicators based on the control results of the target device control strategy for controlling power quality; A comprehensive performance evaluation is performed based on the system performance indicators to obtain a performance report.

8. A power quality control device based on disturbance classification, characterized in that: include: A data acquisition module is used to acquire original three-phase voltage data of the transformer, and perform a preprocessing operation on the original three-phase voltage data to obtain preprocessed three-phase voltage data; A feature extraction module is used to extract features from the preprocessed three-phase voltage data to obtain voltage disturbance features; A voltage disturbance classification result determination module, used for performing anomaly detection based on the voltage disturbance feature, and determining a voltage disturbance classification result through anomaly detection results and the voltage disturbance feature; A control strategy determination module is used to determine a target device control strategy based on the voltage disturbance classification result, so as to control the power quality through the target device control strategy.

9. The device according to claim 8, characterized in that The preprocessed three-phase voltage data includes instantaneous phasors and sequence components of the three-phase voltage; The data acquisition module is specifically used to acquire the original data of the three-phase voltage, filter the original data of the three-phase voltage using a set filter to obtain filtered three-phase voltage data; perform wavelet packet transformation on the filtered three-phase voltage data to obtain transformed three-phase voltage data; and determine the instantaneous phasor and sequence component of the three-phase voltage based on the transformed three-phase voltage data.

10. The device according to claim 8, characterized in that The feature extraction module comprises: A data time-frequency analysis unit, used to perform time-frequency analysis on the preprocessed three-phase voltage data to obtain a time-frequency analysis result; A feature determination unit, used to determine a time-frequency feature matrix and a texture feature according to the time-frequency analysis result; A voltage instantaneous data determination unit, configured to determine the instantaneous amplitude and phase of the three-phase voltage according to the instantaneous phasor of the three-phase voltage; The feature fusion unit is used to obtain voltage disturbance features by performing feature fusion based on the time-frequency feature matrix, texture features, instantaneous amplitude and phase.

11. The device according to claim 10, characterized in that The feature determination unit is specifically used to determine the time domain energy, frequency domain energy and time-frequency energy distribution data according to the time-frequency analysis results; obtain a time-frequency feature matrix according to the combination of the time domain energy, the frequency domain energy and the time-frequency energy distribution data; and determine the texture feature according to the time-frequency analysis results and the texture analysis algorithm.

12. The device according to claim 8, characterized in that The voltage disturbance classification result determination module is specifically used to input the voltage disturbance feature into the set data description model for abnormality detection to obtain an abnormality detection result; if the abnormality degree in the abnormality detection result is greater than a set threshold, the pre-processed three-phase voltage data is subjected to wavelet singularity detection to determine the start time and end time of the voltage disturbance; and a multi-resolution phase space is constructed according to the start time and end time of the voltage disturbance; The multi-resolution phase space is used to determine a dynamic invariant of a voltage signal, and voltage disturbance classification is performed based on the dynamic invariant to obtain a voltage disturbance classification result.

13. The device according to claim 8, characterized in that The control strategy determination module is specifically used to determine a state space model and a state observer; determine an initial device control strategy based on the state space model and the state observer; and adjust the initial device control strategy based on the voltage disturbance classification result to obtain a target device control strategy.

14. The device according to claim 8, characterized in that Also includes: The performance evaluation module is used to determine the system performance index according to the control result of controlling the power quality by the target device control strategy after controlling the power quality by the target device control strategy; and to perform a comprehensive performance evaluation based on the system performance index to obtain a performance report.

15. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the power quality control method based on disturbance classification according to any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the power quality control method based on disturbance classification according to any one of claims 1 to 7 when executed.

Images