Data quality assessment method and system

Abstract

The present application provides a data quality assessment method and system. Among them, first, three types of data sets are collected: three-phase imbalance, free charge density distribution, and line impedance decomposition. Then, by performing spatial topological mapping of the charge density gradient extreme points in the cable joint area and the voltage phase angle, and considering the charge migration effect compensation, the corrected three-phase voltage imbalance parameters are calculated. Then, based on the separated line inherent impedance component and load fluctuation impedance component, a coupling factor matrix is ​​established, and a time-domain convolution operation is performed with the voltage imbalance parameter to generate a distortion feature vector. Finally, the data credibility weight distribution of the global monitoring node is calculated based on the nonlinear correlation between the three-phase imbalance data and the distortion feature vector, which is used to evaluate the quality of the low-voltage management data. The technical solution provided by the present application can improve the accuracy and reliability of data quality assessment.

Description

Technical Field

[0001] The present application relates to the technical field of quality assessment, and in particular to a data quality assessment method and system. Background Art

[0002] As power systems continue to expand in size and complexity, ensuring data quality has become a key factor in improving grid efficiency and reliability. In modern smart grids, a large number of sensors and monitoring devices are deployed to collect various electrical parameters, such as voltage, current, and power, in real time. However, due to factors such as equipment aging, environmental interference, or communication failures, the collected data often contains noise, missing data, or errors. To accurately assess the data quality of monitoring nodes across the entire distribution network and formulate effective maintenance strategies accordingly, an efficient and accurate data quality assessment method is required. This method should not only identify abnormal data but also quantify the data credibility of each monitoring node, providing a reliable basis for subsequent data processing and analysis.

[0003] Existing solutions typically employ statistical methods to assess data quality, such as calculating means and standard deviations to detect outliers or employing time series analysis techniques to identify unusual patterns in changing trends. Furthermore, some research attempts to incorporate machine learning algorithms, such as support vector machines and neural networks, to train historical data to predict potential future issues. These methods can, to a certain extent, detect anomalies in the data and provide preliminary assessments of data quality. Furthermore, some solutions incorporate multi-source data fusion techniques, comprehensively considering datasets from different sources to improve the accuracy of assessment results.

[0004] Although the above schemes have achieved good results in specific scenarios, they still have some obvious flaws. First, statistical-based methods often rely on the assumption that data follows a certain distribution, which may not always hold true in practical applications, resulting in a high misjudgment rate. Second, machine learning models require a large amount of high-quality labeled data for training, but obtaining such data in power systems is costly and time-consuming. Finally, although multi-source data fusion can improve evaluation accuracy, it also increases the complexity and computational burden of the system, especially in large-scale power grid environments, which may lead to insufficient real-time performance. Therefore, there is an urgent need to develop a more flexible, efficient and adaptable data quality assessment method to overcome the limitations of existing solutions and meet the growing needs of power systems. Summary of the Invention

[0005] The present application provides a data quality assessment method and system to solve the problems of poor accuracy and insufficient reliability of data quality assessment in the prior art.

[0006] In a first aspect, the present application provides a data quality assessment method, comprising:

[0007] When the distribution network lines are in operation, a three-phase imbalance dataset, a free charge density distribution dataset generated by millimeter-wave radar space charge detection technology, and a line impedance decomposition dataset generated by impedance spectrum dynamic reconstruction technology are obtained;

[0008] Performing spatial topological mapping on the charge density gradient extreme value point in the cable joint area in the free charge density distribution data set and the voltage phase angle in the three-phase imbalance degree data set, and generating a three-phase voltage imbalance parameter after phase deviation correction by charge migration effect compensation calculation;

[0009] Establishing an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuation impedance component separated from the line impedance decomposition data set, and performing a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion eigenvector of the line impedance and voltage;

[0010] According to the nonlinear correlation between the three-phase imbalance data set and the distortion eigenvector, the data credibility weight distribution of the global monitoring nodes of the distribution network line is calculated, and the data credibility weight distribution is used to characterize the quality assessment results of the low voltage management data.

[0011] Optionally, establishing an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuating impedance component separated from the line impedance decomposition data set includes:

[0012] Decomposing the inherent impedance component of the line in the frequency domain and extracting the maximum points of the steady-state amplitude-frequency response curve within a preset frequency band, and generating a set of dominant resonant frequencies based on the distribution range of the maximum points;

[0013] Dividing the load fluctuating impedance component into time domain intervals according to the load switching timestamp, and calculating the composite parameters of the dynamic change rate and phase offset of the load fluctuating impedance component in each time domain interval;

[0014] An initial coupling factor matrix is ​​constructed using the set of dominant resonant frequencies as row indices and the composite parameters as column indices, and dynamic constraints are imposed on the initial coupling factor matrix, including generating spatial correction coefficients based on impedance transfer functions of adjacent monitoring nodes and generating statistical correction coefficients based on the kurtosis and skewness of the historical probability density of the load fluctuation impedance component;

[0015] The correlation between the spatial correction coefficient and the statistical correction coefficient is superimposed on the matrix diagonal elements to establish an impedance parameter coupling factor matrix.

[0016] Optionally, constructing an initial coupling factor matrix using the dominant resonant frequency set as a row index and the composite parameter as a column index includes:

[0017] In the dominant resonant frequency set, the frequency interval and amplitude attenuation slope between adjacent maximum points on the steady-state amplitude-frequency response curve of each resonant frequency point are extracted to generate a resonance intensity factor;

[0018] Discretize the composite parameter into segments according to the time domain interval corresponding to the load switching timestamp, and construct an anti-aliasing weight coefficient of the composite parameter based on the cosine similarity of the dynamic change rate and the phase offset in adjacent time domain intervals;

[0019] The resonance intensity factor is used as a row vector element, the composite parameter weighted by the anti-aliasing weight coefficient is used as a column vector element, and an initial matrix framework is generated by performing an outer product operation between the row vector element and the column vector element;

[0020] Based on the initial matrix framework, the row vector elements corresponding to each resonant frequency point are superimposed with the amplitude-frequency integral value of the maximum point in the preset frequency band to which the corresponding resonant frequency point belongs, and are associated element by element with the cumulative energy distribution of the composite parameters of the corresponding column vector elements in the time domain interval to construct an initial coupling factor matrix.

[0021] Optionally, dividing the load fluctuating impedance component into time domain intervals according to the load switching timestamps, and calculating a composite parameter of a dynamic change rate and a phase offset of the load fluctuating impedance component in each time domain interval includes:

[0022] Based on the trigger interval of the load switching timestamp, the time window between adjacent timestamps is used as an independent time domain interval, and the extreme value point of the load fluctuation impedance component is extracted in the independent time domain interval as a sampling reference point of the dynamic change rate;

[0023] Constructing a local time window with the sampling reference point as the center, and calculating the time domain curvature change rate mean of the load fluctuating impedance component to generate an original parameter pair of the dynamic change rate and the phase offset;

[0024] Cross-validating the original parameter pair, applying a time window scaling constraint to the dynamic change rate by using the load switching timestamp interval lengths of adjacent time domain intervals, and performing phase polarity correction on the phase offset according to the continuity characteristics of adjacent time domain intervals;

[0025] The scaled dynamic change rate and the corrected phase offset are nonlinearly superimposed, and weighted by the energy proportion coefficient of the load fluctuation impedance component in the corresponding time domain interval to obtain a composite parameter.

[0026] Optionally, performing a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion eigenvector of a combination of line impedance and voltage includes:

[0027] Based on the orthogonal decomposition relationship between the inherent impedance component and the load fluctuation impedance component in the impedance parameter coupling factor matrix, a three-dimensional convolution kernel function with time-varying characteristics is constructed;

[0028] Expanding the three-phase voltage imbalance parameter into a multi-channel pulse sequence according to a preset time granularity, and mapping each channel to a voltage amplitude differential increment of a corresponding phase;

[0029] In a sliding time window, the three-dimensional convolution kernel function is tensor-sliced ​​along the time axis, and asymmetric boundary-constrained circular convolution is performed on the multi-channel pulse sequence. When the impedance parameter suddenly changes, the three-dimensional convolution kernel function is automatically expanded into a hyperbolic secant attenuation function.

[0030] The interaction strength coefficient between the voltage trajectory and impedance trajectory of each phase in the convolution output is extracted, and a multidimensional tensor containing the joint spectrum characteristics of impedance and voltage is constructed. The multidimensional tensor is then screened for an energy threshold along the principal axis of impedance coupling, and the projected components exceeding the energy threshold are used as distortion eigenvectors.

[0031] Optionally, when the impedance parameter changes suddenly, the three-dimensional convolution kernel function is automatically expanded into a hyperbolic secant attenuation function, including:

[0032] Setting a mutation detection window on the time axis of the three-dimensional convolution kernel function to calculate in real time the instantaneous rate of change of the load fluctuation impedance component in the impedance parameter coupling factor matrix and the trigger expansion mechanism of the hyperbolic secant attenuation function;

[0033] Applying energy conservation constraints to the frequency domain components of the trigger expansion mechanism, and maintaining the total energy of the trigger expansion mechanism consistent before and after the mutation by integrating the energy of the load fluctuation impedance component;

[0034] According to the phase difference change trajectory between the impedance parameter and the three-phase voltage imbalance parameter within the mutation detection window, the constrained trigger expansion mechanism is dynamically corrected. When the instantaneous change rate exceeds the corrected trigger expansion mechanism, the three-dimensional convolution kernel function is automatically expanded to a hyperbolic secant attenuation function.

[0035] Optionally, the calculating, based on the nonlinear correlation between the three-phase imbalance dataset and the distortion eigenvector, the data credibility weight distribution of the global monitoring nodes of the distribution network line includes:

[0036] Multi-dimensionally coupling the voltage imbalance parameters of each phase in the three-phase imbalance dataset with the distortion feature vector in the time domain dimension, and establishing a nonlinear correlation index of each monitoring node through a phase sensitivity kernel function;

[0037] Based on the spatial distribution of the nonlinear correlation index in the three-dimensional charge density gradient field, a probability density diffusion surface reflecting the line impedance coupling strength is constructed;

[0038] Perform multi-scale convolution fusion on the probability density diffusion surface and the inherent impedance spectrum features in the line impedance decomposition data set to generate a dynamic weight base value for each monitoring node;

[0039] A weight correction equation based on the dual constraints of impedance and charge is established, and the path integral optimization is performed on the dynamic weight base value. The steady-state solution set of the weight correction equation under the action of charge migration effect is solved by an iterative convergence algorithm. The data credibility weight distribution is obtained according to the projection amplitude of the steady-state solution set in the spatial coordinate system of the monitoring node.

[0040] In a second aspect, the present application provides a data quality assessment system, comprising:

[0041] The acquisition module acquires a three-phase imbalance dataset, a free charge density distribution dataset generated by millimeter-wave radar space charge detection technology, and a line impedance decomposition dataset generated by impedance spectrum dynamic reconstruction technology when the distribution network line is in operation;

[0042] A mapping module performs spatial topological mapping between the charge density gradient extreme value points in the cable joint area in the free charge density distribution dataset and the voltage phase angles in the three-phase imbalance dataset, and generates three-phase voltage imbalance parameters after phase deviation correction by charge migration effect compensation calculation;

[0043] An establishment module is provided for establishing an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuation impedance component separated from the line impedance decomposition data set, and performing a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion feature vector of the line impedance and voltage;

[0044] The characterization module calculates the data credibility weight distribution of the global monitoring nodes of the distribution network line based on the nonlinear correlation between the three-phase imbalance data set and the distortion characteristic vector. The data credibility weight distribution is used to characterize the quality assessment results of the low voltage management data.

[0045] In a third aspect, an embodiment of the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a data quality assessment method as described in the first aspect above.

[0046] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a data quality assessment method as described in the first aspect.

[0047] In an embodiment of the present application, when the distribution network line is in operation, a three-phase imbalance data set, a free charge density distribution data set generated based on millimeter-wave radar space charge detection technology, and a line impedance decomposition data set generated by impedance spectrum dynamic reconstruction technology are obtained; the charge density gradient extreme points in the cable joint area in the free charge density distribution data set are spatially topologically mapped with the voltage phase angle in the three-phase imbalance data set, and the three-phase voltage imbalance parameters after phase deviation correction are generated by charge migration effect compensation calculation; based on the line inherent impedance component and the load fluctuation impedance component separated from the line impedance decomposition data set, an impedance parameter coupling factor matrix is ​​established, and a time-domain convolution operation is performed on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion eigenvector of the line impedance and voltage; based on the nonlinear correlation between the three-phase imbalance data set and the distortion eigenvector, the data credibility weight distribution of the global monitoring nodes of the distribution network line is calculated, and the data credibility weight distribution is used to characterize the quality assessment results of the low voltage management data.

[0048] The technical solution of this application has the following beneficial effects:

[0049] This application achieves comprehensive monitoring and evaluation of the operating status of the distribution network by obtaining data sets of three-phase imbalance, free charge density distribution and line impedance decomposition. This provides rich basic data support for subsequent analysis. The charge density gradient extreme points in the cable joint area are spatially topologically mapped to the voltage phase angle, and the three-phase voltage imbalance parameters are corrected by charge migration effect compensation, thereby improving the accuracy of voltage imbalance problem detection. Based on the separated line inherent impedance component and load fluctuation impedance component, a coupling factor matrix is ​​established, and a distortion eigenvector is generated through time domain convolution operation, which helps to deeply understand the complex relationship between line impedance and voltage and improve the accuracy of fault diagnosis. The data credibility weight distribution is calculated based on the nonlinear correlation between the three-phase imbalance data set and the distortion eigenvector, thereby providing an effective low voltage management data quality assessment method and enhancing the reliability of power grid management decisions.

[0050] Furthermore, the dominant resonant frequency set is first extracted by performing frequency domain decomposition on the inherent impedance component of the line, and the composite parameters of the dynamic change rate and phase offset of the load fluctuation impedance component are calculated by time interval division. Then, based on this information, an initial coupling factor matrix is ​​constructed and dynamic constraints are imposed, including the introduction of spatial correction coefficients and statistical correction coefficients to enhance the accuracy and stability of the matrix. The impedance parameter coupling factor matrix finally established can more accurately reflect the interaction between line impedance and load fluctuations, improving the level of detail and predictive ability of distribution network operation status monitoring. By comprehensively considering spatial and statistical characteristics, the understanding and analysis of the grid impedance characteristics are more in-depth, effectively improving the accuracy and reliability of grid fault diagnosis and status assessment.

[0051] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 A flow chart of a data quality assessment method provided by the present application is shown;

[0054] Figure 2 A schematic diagram of the structure of a data quality assessment system provided by the present application is shown;

[0055] Figure 3 A schematic structural diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0057] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0058] This project aims to comprehensively analyze a variety of key data under the operating conditions of the distribution network, including three-phase imbalance, free charge density distribution, and line impedance decomposition data. First, the three-phase voltage imbalance parameters are adjusted through spatial topology mapping combined with charge migration effect compensation. Then, a coupling factor matrix is ​​established based on the separated line inherent and load fluctuation impedance components. Finally, the data credibility weight distribution is calculated based on the nonlinear correlation between three-phase imbalance and distortion eigenvectors to evaluate the quality of low-voltage control data. This process effectively improves the accuracy and reliability of data processing at distribution network monitoring nodes, providing solid data support for grid management.

[0059] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0060] Figure 1 A flowchart of a data quality assessment method is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0061] 101. Under the operating state of the distribution network line, obtain a three-phase imbalance dataset, a free charge density distribution dataset generated by millimeter-wave radar space charge detection technology, and a line impedance decomposition dataset generated by impedance spectrum dynamic reconstruction technology;

[0062] In this step, the three-phase imbalance dataset contains the voltage and current parameters of each monitoring point in the power grid, which is used to evaluate the balance state between the three phases of the power system.

[0063] Millimeter-wave radar space charge detection technology is a technology that detects the charge density in the cable joint area by transmitting and receiving millimeter waves. The generated free charge density distribution data set can reveal local charge anomalies.

[0064] The line impedance decomposition dataset is a data set obtained by dynamically reconstructing the impedance spectrum of the distribution network. It can separate the inherent impedance (determined by the line material and structure) and the load fluctuation impedance component (which changes with load) to reflect the line operating conditions.

[0065] In the embodiment of the present application, first, when the distribution network is operating normally, sensors deployed in the grid begin to collect three-phase imbalance data, including voltage and current parameters. Next, millimeter-wave radar equipment is used to scan selected key cable joint areas and record the spatial distribution of charge density. Then, the impedance spectrum dynamic reconstruction technology is applied to process the data collected from the distribution line to extract the inherent impedance component representing the line properties and the impedance fluctuation component caused by load changes. Finally, all of this data is integrated to form a complete line impedance decomposition data set, providing basic support for subsequent analysis.

[0066] In a smart power distribution network project in a certain city, technicians installed multiple sensor nodes within the substation to monitor changes in voltage and current for each phase in real time. They also used millimeter-wave radar to scan a cable joint known to have frequent problems, obtaining a detailed charge density map. Furthermore, advanced software tools were used to deeply analyze the collected data, successfully separating the inherent impedance and load fluctuation impedance components, providing a crucial basis for subsequent optimization of grid performance.

[0067] 102. Perform spatial topological mapping between the charge density gradient extreme value point in the cable joint area in the free charge density distribution dataset and the voltage phase angle in the three-phase imbalance dataset, and generate a three-phase voltage imbalance parameter after phase deviation correction by charge migration effect compensation calculation;

[0068] In this step, the charge density gradient extreme point refers to the location of the maximum rate of change of the charge density in its spatial distribution, which usually indicates the potential fault point.

[0069] The voltage phase angle is an important parameter that describes the relative time offset between the three-phase voltages and is crucial for evaluating voltage unbalance.

[0070] Spatial topology mapping refers to the process of correlating the two points mentioned above, while charge migration effect compensation adjusts the voltage phase angle on this basis to more accurately correct the voltage imbalance problem.

[0071] Three-phase voltage unbalance parameters are a set of indicators used to quantify the differences between the three-phase voltages in a power system. These differences may be caused by the asymmetry of the power supply system, load imbalance or other factors.

[0072] In the present embodiment, the charge density gradient extreme points in the cable joint region are first identified from the free charge density distribution dataset. Next, the location information of these extreme points is associated with the voltage phase angles in the three-phase imbalance data, establishing a spatial mapping relationship between the two. Then, based on charge migration theory, the phase deviation value that requires correction is calculated, and the original three-phase voltage imbalance parameters are adjusted accordingly. Finally, after a series of precise calculations, the three-phase voltage imbalance parameters are obtained after phase deviation correction, improving the assessment accuracy.

[0073] Based on the data collected earlier, technicians first identified the gradient extremes in the free charge density distribution, which often indicate potential problem areas. They then mapped this location information to the voltage phase angles in the three-phase imbalance data, establishing a spatial mapping between the two. Using a complex algorithm model and based on charge migration theory, they calculated the phase deviation that needed correction and adjusted the original three-phase voltage imbalance parameters accordingly. This step significantly improved the accuracy of the original data and laid the foundation for more precise subsequent analysis.

[0074] 103. Establish an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuating impedance component separated from the line impedance decomposition data set, and perform a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion eigenvector of the line impedance and voltage.

[0075] In this step, the inherent impedance component of the line is the resistance, inductance and other characteristics determined by the material and structure of the line itself.

[0076] The load fluctuation impedance component is the impedance change caused by load changes.

[0077] The impedance parameter coupling factor matrix is ​​designed to describe the interaction between the inherent impedance component of the line and the fluctuating impedance component of the load.

[0078] The time-domain convolution operation refers to combining the three-phase voltage imbalance parameters with the matrix to generate a comprehensive eigenvector to fully characterize the relationship between line impedance and voltage.

[0079] Distortion eigenvector is a mathematical representation used to characterize the complex interaction between voltage and impedance in power systems, especially distribution network lines.

[0080] In this embodiment, the inherent impedance and load fluctuation impedance components are first separated from the line impedance decomposition dataset. Next, a coupling factor matrix is ​​constructed using frequency and time domain analysis methods, taking into account the influence of the dominant resonant frequency set and composite parameters. A three-dimensional convolution kernel function is then designed to convert the three-phase voltage imbalance parameters into a pulse train. Finally, a circular convolution operation is performed, combined with the impedance parameter coupling factor matrix, to generate a distortion feature vector containing the joint impedance and voltage characteristics, enabling in-depth analysis of the line health status.

[0081] Using the previously obtained data, technicians further analyzed and constructed a detailed impedance parameter coupling factor matrix. First, the inherent impedance and load fluctuation impedance components were separated from the line impedance decomposition dataset. Then, frequency-domain and time-domain analysis methods were used to construct the coupling factor matrix, taking into account the influence of the dominant resonant frequency set and composite parameters. Next, a three-dimensional convolution kernel function was designed to convert the three-phase voltage imbalance parameters into a pulse train. Finally, a circular convolution operation was performed, combined with the impedance parameter coupling factor matrix, to generate a distortion eigenvector containing the joint impedance and voltage characteristics. This process provided a deeper understanding of the line health status and provided a basis for further optimization.

[0082] 104. Based on the nonlinear correlation between the three-phase imbalance data set and the distortion characteristic vector, calculate the data credibility weight distribution of the global monitoring nodes of the distribution network line, and the data credibility weight distribution is used to characterize the quality assessment results of the low voltage management data.

[0083] In this step, the three-phase unbalance dataset is a set of key data used to evaluate the balance state between three-phase voltages or currents in the power system.

[0084] Nonlinear correlation is a quantitative indicator used to measure the complex relationship between the three-phase imbalance dataset and the distortion eigenvector.

[0085] The data credibility weight distribution is based on this correlation and is used to evaluate the data quality of each monitoring node to ensure the effectiveness and scientific nature of low voltage control measures.

[0086] Low voltage management data refers to a series of relevant data collected and processed in the power system, especially the distribution network, in order to identify, analyze and solve low voltage problems.

[0087] In this embodiment, the nonlinear correlation between the three-phase imbalance dataset and the distortion eigenvector is first calculated. Based on this correlation, a probability density diffusion surface is constructed to reflect the line impedance coupling strength. Then, through multi-scale convolution fusion, a dynamic weight base value for each monitoring node is generated. Finally, through path integral optimization, a data credibility weight distribution result is derived to guide the formulation of low-voltage management strategies.

[0088] After obtaining detailed distortion eigenvectors, technicians calculated the nonlinear correlation between the three-phase imbalance dataset and these eigenvectors. Based on this correlation, a probability density diffusion surface was constructed, reflecting the strength of line impedance coupling. Subsequently, multi-scale convolution fusion was used to generate dynamic weight base values ​​for each monitoring node. Path integral optimization was performed to determine the data credibility weight distribution. These analyses not only improved data quality assessment but also provided a scientific basis for more effective low-voltage control measures, ensuring the safe and stable operation of the entire smart distribution network.

[0089] In summary, steps 101 to 104 cover the entire process, from basic data collection and in-depth analysis to final data quality assessment. This approach not only accurately captures subtle changes in distribution network operation but also effectively guides low-voltage management efforts, significantly improving grid management efficiency and power supply reliability. Each step is closely linked, forming a complete technical chain that provides strong support for the development of smart grids.

[0090] In order to solve the problem of accurately describing the complex dynamic behavior in the distribution network, the inherent impedance component of the line is first decomposed in the frequency domain and the dominant resonant frequency set is extracted. At the same time, the load fluctuation impedance component is divided into time domain intervals according to the load switching timestamp. Then, dynamic constraints are imposed, including spatial correction coefficients based on the impedance transfer function of adjacent monitoring nodes and statistical correction coefficients based on historical probability density characteristics. Finally, these correction coefficients are superimposed on the diagonal elements of the matrix to form an optimized impedance parameter coupling factor matrix to more accurately reflect the actual operating conditions. In some embodiments, the impedance parameter coupling factor matrix is ​​established based on the line inherent impedance component and the load fluctuation impedance component separated from the line impedance decomposition data set in step 103, including:

[0091] 201. Decompose the inherent impedance component of the line in the frequency domain and extract the maximum points of the steady-state amplitude-frequency response curve within a preset frequency band, and generate a set of dominant resonant frequencies based on the distribution range of the maximum points;

[0092] In step 201, the inherent impedance component of the line refers to characteristics such as resistance and inductance determined by the line's material and construction. Frequency domain decomposition is a technique that converts time-domain signals into a frequency-domain representation. It identifies the dominant resonant frequency set by extracting the maximum points of the steady-state amplitude-frequency response curve within a preset frequency band. The dominant resonant frequency set is defined as those frequencies that exhibit significant vibration characteristics within a specific frequency range and are used to reflect the primary vibration mode of the line.

[0093] In this embodiment, the inherent impedance components of the line are first decomposed in the frequency domain and converted into a frequency-domain representation using fast Fourier transform technology. Next, the maximum points on the steady-state amplitude-frequency response curve are searched within a preset frequency range. Based on the distribution range of these maximum points, a set of dominant resonant frequencies is generated. Ultimately, a set of frequencies that accurately reflects the main vibration modes of the line is obtained.

[0094] 202. Divide the load fluctuating impedance component into time domain intervals according to the load switching timestamps, and calculate composite parameters of the dynamic change rate and phase offset of the load fluctuating impedance component in each time domain interval;

[0095] In step 202, the load fluctuation impedance component refers to the impedance variation caused by load changes. Dividing the time domain interval by load switching timestamp means segmenting the data into multiple independent time periods based on the actual load switching time points. Composite parameters include the dynamic change rate and phase offset, which are used to quantify the load fluctuation characteristics within each time period.

[0096] In this embodiment, independent time domain intervals are first determined based on the load switching timestamps. Then, the dynamic rate of change and phase offset of the load fluctuation impedance component are calculated within each interval to form composite parameters. Specifically, the dynamic rate of change is calculated using a differential algorithm, and the phase offset is obtained using a phase detection method. Finally, these composite parameters are aggregated to form a dataset that comprehensively reflects the load fluctuation characteristics.

[0097] 203. Construct an initial coupling factor matrix using the set of dominant resonant frequencies as row indices and the composite parameters as column indices, and impose dynamic constraints on the initial coupling factor matrix, including generating spatial correction coefficients based on impedance transfer functions of adjacent monitoring nodes and generating statistical correction coefficients based on the kurtosis and skewness of the historical probability density of the load fluctuation impedance component;

[0098] In step 203, the initial coupling factor matrix is ​​a matrix structure with the dominant resonant frequency set as the row index and the composite parameter as the column index. Spatial correction coefficients are generated based on the impedance transfer function between adjacent monitoring nodes, while statistical correction coefficients are generated based on the kurtosis and skewness of the historical probability density of the load's fluctuating impedance component. These two types of correction coefficients are used to adjust the matrix elements to more accurately reflect the actual situation.

[0099] In this embodiment, an initial coupling factor matrix is ​​first constructed, with the set of dominant resonant frequencies as row vectors and the composite parameters as column vectors. Next, spatial correction coefficients are generated using the impedance transfer function between adjacent monitoring nodes, and statistical correction coefficients are generated by analyzing the probability density characteristics of historical data. These correction coefficients are then superimposed on the matrix diagonal elements to complete the adjustment of the initial matrix, ultimately forming a more accurate impedance parameter coupling factor matrix.

[0100] 204. Superimpose the correlation between the spatial correction coefficient and the statistical correction coefficient on the matrix diagonal elements to establish an impedance parameter coupling factor matrix.

[0101] In step 204, spatial correction coefficients and statistical correction coefficients are generated based on the impedance transfer function between adjacent monitoring nodes and the historical probability density characteristics of the load fluctuation impedance component. These correction coefficients are used to adjust the elements in the initial coupling factor matrix to more accurately reflect the actual situation. The impedance parameter coupling factor matrix is ​​a mathematical model used to describe the complex interaction between different physical quantities and line impedance characteristics in the power system. The correlation refers to the relationship between the spatial correction coefficient and the statistical correction coefficient. Superimposing them on the matrix diagonal elements can further optimize the matrix structure to ensure that it can more accurately describe the dynamic behavior of the system.

[0102] In the embodiment of the present application, the correlation between the spatial correction coefficient and the statistical correction coefficient is first calculated, and the strength of the relationship between the two is quantified by a correlation analysis method. Then, the obtained correlation value is superimposed on the diagonal elements of the initial coupling factor matrix, thereby achieving the final adjustment of the matrix. Finally, the impedance parameter coupling factor matrix formed after this series of adjustments not only includes the inherent characteristics of the line and the load fluctuation characteristics, but also takes into account the influence between different nodes and the statistical characteristics of historical data, so that the matrix can more accurately describe the actual operating status of the distribution network.

[0103] Here's a specific example:

[0104] In a smart distribution network project in a certain city, technicians first identified the dominant resonant frequency set, calculated composite parameters, and constructed an initial coupling factor matrix. They then generated spatial correction coefficients and, through historical data analysis, generated statistical correction coefficients. Next, they calculated the correlation between the spatial and statistical correction coefficients and superimposed these correlation values ​​on the diagonal elements of the initial coupling factor matrix. The result was an optimized impedance parameter coupling factor matrix, which significantly improved the understanding of cable segment health and provided solid data support for subsequent grid maintenance and low-voltage management.

[0105] In summary, steps 201 to 204 successfully construct an impedance parameter coupling factor matrix that accurately describes the complex dynamic behavior within the power system through in-depth analysis of the line's inherent impedance components and the load's fluctuating impedance components, combined with frequency domain decomposition, time domain interval division, the application of multidimensional correction coefficients, and final correlation superposition adjustment. This approach not only improves the understanding of the grid's health but also provides scientific support for the formulation of effective low-voltage management strategies, greatly improving grid management efficiency and power supply reliability. Furthermore, by introducing spatial and statistical correction coefficients and the superposition of their correlations, the model's adaptability and accuracy are further enhanced, making the assessment of the grid's operating status more comprehensive and reliable.

[0106] In order to solve the problem of accurately describing the complex dynamic behavior in the power system, the scheme extracts the frequency interval and amplitude attenuation slope of each frequency point in the dominant resonant frequency set to generate a resonance intensity factor, and constructs the anti-aliasing weight coefficient of the composite parameter based on the dynamic change rate and phase offset of the adjacent time domain interval. Subsequently, the initial matrix framework is generated by the outer product operation of the row vector elements and the column vector elements to construct a more accurate initial coupling factor matrix, thereby improving the ability to capture subtle changes. In some embodiments, the construction of the initial coupling factor matrix using the dominant resonant frequency set as the row index and the composite parameter as the column index in step 203 includes:

[0107] 301. Extract the frequency interval and amplitude attenuation slope between adjacent maximum points on the steady-state amplitude-frequency response curve of each resonant frequency point in the dominant resonant frequency set to generate a resonance intensity factor;

[0108] In step 301, the resonance intensity factor (RIF) refers to the frequency interval and amplitude decay slope between adjacent maximum points on the steady-state amplitude-frequency response curve. The frequency interval represents the frequency difference between two adjacent maximum points, while the amplitude decay slope reflects the rate of amplitude change between these maximum points. The RIF is used to quantify the importance of each resonant frequency point and its impact on the overall system vibration characteristics.

[0109] In this embodiment, adjacent maxima on the steady-state amplitude-frequency response curve for each resonant frequency point are first extracted from the set of dominant resonant frequencies. Next, the frequency intervals and amplitude decay slopes between these maxima are calculated to generate resonance intensity factors. Specifically, frequency domain analysis techniques (such as fast Fourier transform) are used to identify the maxima, and the slopes are calculated using numerical differentiation. Ultimately, a set of resonance intensity factors is obtained that accurately reflects the importance of each resonant frequency point.

[0110] 302. Discretize the composite parameter into segments according to the time domain intervals corresponding to the load switching timestamps, and construct an anti-aliasing weight coefficient of the composite parameter based on the cosine similarity of the dynamic change rate and the phase offset in adjacent time domain intervals;

[0111] In step 302, the composite parameter is discretized in segments according to the time domain interval corresponding to the load switching timestamp, which means that the data is divided into multiple independent time periods according to the actual load switching time point. The anti-aliasing weight coefficient is constructed based on the cosine similarity of the dynamic change rate and the phase offset in adjacent time domain intervals, and is used to reduce the aliasing error that may occur during the data sampling process and ensure the accuracy of the composite parameter. The cosine similarity of the phase offset refers to the measurement of the degree of correlation between the two by calculating the similarity of the phase angle difference of the voltage or current signal between different time points (or time periods) in the power system analysis. Specifically, the mathematical method of cosine similarity is used to compare the phase offsets to determine the degree of similarity between the two. The dynamic change rate in adjacent time domain intervals refers to the speed or amplitude of the change of the composite parameter over time in continuous time intervals.

[0112] In the embodiment of the present application, independent time domain intervals are first determined based on the load switching timestamps, and the composite parameters are discretized into segments according to these intervals. Then, the dynamic rate of change and phase offset are calculated within each interval, and the cosine similarity algorithm is used to construct anti-aliasing weight coefficients. Specifically, a differential algorithm is used to calculate the dynamic rate of change, and a phase offset is obtained through a phase detection method. Finally, these anti-aliasing weight coefficients are weighted onto the composite parameters to form a more accurate data set.

[0113] 303. Using the resonance intensity factor as a row vector element and the composite parameter weighted by the anti-aliasing weight coefficient as a column vector element, an initial matrix framework is generated by performing an outer product operation between the row vector element and the column vector element;

[0114] In step 303, the row vector elements refer to a vector consisting of resonance intensity factors, while the column vector elements refer to a vector consisting of composite parameters weighted by anti-aliasing weight coefficients. The outer product operation is a mathematical operation used to generate a matrix form between two vectors, which is used here to construct an initial matrix framework. The resonance intensity factors, as elements of the row vectors, reflect the response strength or sensitivity of the system at different frequencies. The initial matrix framework is a preliminary data analysis model constructed based on the resonance intensity factors and weighted composite parameters, which is used to reveal the complex correlations within the data.

[0115] In the embodiment of the present application, the resonance intensity factor is first used as a row vector element, and the composite parameter weighted by the anti-aliasing weight coefficient is used as a column vector element. Then, an outer product operation is performed to generate an initial matrix framework. Specifically, the outer product formula in linear algebra is used to multiply the row vector and the column vector to obtain a preliminary matrix structure. This process not only integrates data from different sources but also provides a foundation for subsequent optimization.

[0116] 304. Based on the initial matrix framework, the row vector elements corresponding to each resonant frequency point are superimposed with the amplitude-frequency integral value of the maximum point in the preset frequency band to which the corresponding resonant frequency point belongs, and are associated element by element with the cumulative energy distribution of the composite parameters of the corresponding column vector elements in the time domain interval to construct an initial coupling factor matrix.

[0117] In step 304, the initial matrix framework is based on the matrix structure generated in the previous step. The amplitude-frequency integral value is the result of integrating the amplitude of the maximum point in the preset frequency band, and the cumulative energy distribution is the sum of the energy of the composite parameter in the time domain interval. Element-by-element association means that these values ​​are matched one by one and combined to improve the initial coupling factor matrix. The resonant frequency point refers to the specific frequency position where the resonance phenomenon occurs in the power system. Resonance refers to the phenomenon that the system response is amplified to a significant level when the input frequency of the system matches the natural frequency of the system. In power system analysis, identifying these resonant frequency points is crucial for evaluating system stability, optimizing performance, and fault detection. The initial coupling factor matrix is ​​a matrix calculated based on the initial matrix framework, which aims to capture the interaction or correlation between different parameters.

[0118] In the embodiment of the present application, the row vector elements corresponding to each resonant frequency point in the initial matrix framework are first superimposed with the amplitude-frequency integral value of the maximum point within the preset frequency band to which it belongs. Next, the cumulative energy distribution of the composite parameters of the corresponding column vector elements in the time domain interval is calculated and element-by-element correlation is performed. Specifically, the amplitude-frequency response of each frequency point is integrated and combined with the energy distribution in the time domain interval to adjust the matrix elements. Ultimately, a more accurate initial coupling factor matrix is ​​constructed.

[0119] Here's a specific example:

[0120] In a smart distribution network project in a certain city, technicians first extracted the adjacent maximum points of each resonant frequency point from the dominant resonant frequency set of the selected cable segment, calculated the frequency interval and amplitude attenuation slope, and generated the resonance intensity factor. Next, the time domain interval was divided according to the load switching timestamp, and the anti-aliasing weight coefficient was constructed using the cosine similarity algorithm. Then, the resonance intensity factor was used as the row vector element, and the weighted composite parameter of the anti-aliasing weight coefficient was used as the column vector element to generate the initial matrix framework. Finally, the amplitude-frequency integral value was superimposed on each resonant frequency point, and combined with the cumulative energy distribution of the time domain interval, an initial coupling factor matrix that accurately describes the operating status of the cable segment was constructed, providing solid data support for subsequent power grid maintenance and low voltage management.

[0121] In summary, steps 301 to 304 successfully construct an initial coupling factor matrix that accurately describes the complex dynamic behavior within the power system through in-depth analysis of the dominant resonant frequency set and composite parameters, combined with methods such as frequency domain decomposition, time domain interval division, outer product operation, and element-by-element association. This method not only improves the accuracy of understanding the health of the power grid, but also provides scientific support for the formulation of effective low-voltage management strategies, greatly improving the efficiency of power grid management and power supply reliability. In addition, by introducing anti-aliasing weight coefficients and amplitude-frequency integral values, the adaptability and accuracy of the model are further enhanced, making the assessment of the power grid operation status more comprehensive.

[0122] In order to solve the problem of accurate quantification of the load fluctuation impedance component in the power system, the data is first divided into independent time domain intervals based on the load switching timestamp, and the extreme points of the load fluctuation impedance component are extracted in each interval as sampling reference points. Then, a local time window is constructed around these reference points, the mean of the time domain curvature change rate is calculated, and the original parameter pair is generated. Finally, the scaled dynamic change rate and the corrected phase offset are nonlinearly superimposed to obtain a composite parameter. This method significantly improves the quantification accuracy of the load fluctuation characteristics. In some embodiments, the load fluctuation impedance component is divided into time domain intervals according to the load switching timestamp in step 202, and the composite parameters of the dynamic change rate and phase offset of the load fluctuation impedance component in each time domain interval are calculated, including:

[0123] 401. Based on the trigger interval of the load switching timestamp, a time window between adjacent timestamps is used as an independent time domain interval, and an extreme point of the load fluctuation impedance component is extracted within the independent time domain interval as a sampling reference point of the dynamic change rate;

[0124] In step 401, the independent time domain interval refers to a time period determined by the trigger interval based on the load switching timestamp. Each independent time domain interval is used to analyze changes in the load fluctuation impedance component. A load switching timestamp is a data mark in the power system that records the exact time when a specific load (for example, industrial equipment, commercial buildings, or household appliances) is connected to or disconnected from the power grid. The sampling reference point is the extreme value of the load fluctuation impedance component extracted within this interval and serves as the basic data point for calculating the dynamic change rate. These reference points accurately reflect the maximum or minimum change points of the load fluctuation.

[0125] In this embodiment, the time window between adjacent timestamps is first determined based on the load switching timestamps as an independent time domain interval. Next, the extreme points of the load fluctuation impedance component are extracted within each independent time domain interval and used as sampling reference points for the dynamic rate of change. Specifically, a peak detection algorithm is used to identify the extreme points, and their corresponding times and values ​​are recorded. Ultimately, a set of sampling reference points is obtained that accurately describes the load fluctuation characteristics.

[0126] 402. Construct a local time window with the sampling reference point as the center, and calculate the time domain curvature change rate mean of the load fluctuating impedance component to generate an original parameter pair of the dynamic change rate and the phase offset;

[0127] In step 402, a local time window is constructed, centered around the sampling reference point, to more closely analyze the changing trends of the load's fluctuating impedance component. The mean of the time-domain curvature rate of change reflects the average rate of change of the load's fluctuating impedance component within that time period. The original parameter pair, consisting of the dynamic rate of change and the phase offset, provides a preliminary description of the load's fluctuating characteristics.

[0128] In this embodiment, a local time window is first constructed centered around the sampling reference point. Then, the mean time-domain curvature change rate of the load fluctuation impedance component is calculated within each local time window. Finally, a primitive parameter pair of the dynamic change rate and phase offset is generated. Specifically, a differential algorithm is used to calculate the curvature change rate, and a phase detection method is used to obtain the phase offset. These parameters are combined into a primitive parameter pair to form a preliminary description of the load fluctuation.

[0129] 403. Cross-validate the original parameter pair, apply a time window scaling constraint to the dynamic change rate by using the load switching timestamp interval lengths of adjacent time domain intervals, and perform phase polarity correction on the phase offset according to the continuity characteristics of adjacent time domain intervals.

[0130] In step 403, cross-validation is the process of performing multiple checks on the original parameter pairs to ensure the accuracy and consistency of the data. The time window scaling constraint is to adjust the time window size of the dynamic change rate according to the length of the load switching timestamp interval of the adjacent time domain interval. Phase polarity correction is to correct the phase offset according to the continuity characteristics of the adjacent time domain interval to ensure the accuracy of the phase information. The load switching timestamp interval length refers to the time difference between the time points when different loads in the power system are connected (connected) or disconnected (cut). These time points are called load switching timestamps, and the length of the interval between adjacent time domain intervals reflects the frequency and pattern of load changes. Phase offset refers to the phase angle difference of the voltage or current signal in the AC power system.

[0131] In this embodiment, the original parameter pairs are first cross-validated, and a time window scaling constraint is imposed on the dynamic rate of change using the length of the load switching timestamp interval between adjacent time domain intervals. Next, a phase polarity correction is performed on the phase offset based on the continuity characteristics of the adjacent time domain intervals. Specifically, a time series analysis method is used to adjust the time window of the dynamic rate of change, and the phase offset is corrected using a phase continuity check. Ultimately, a set of corrected dynamic rate of change and phase offset is obtained.

[0132] 404. Nonlinearly superimpose the scaled dynamic change rate and the corrected phase offset, and weight them by the energy proportion coefficient of the load fluctuation impedance component in the corresponding time domain interval to obtain a composite parameter.

[0133] In step 404, nonlinear superposition is the process of combining the scaled dynamic rate of change with the corrected phase offset, aiming to integrate the information of the two. The energy proportion coefficient is the energy ratio of the load fluctuation impedance component in the corresponding time domain interval, which is used to weight the composite parameter to ensure that it can accurately reflect the impact of actual load fluctuations. The scaled dynamic rate of change refers to the speed at which electrical parameters such as voltage or current change over time after adjustment. The corrected phase offset refers to the phase difference between voltage or current signals after phase polarity correction. In an AC power system, the phase offset describes the relative position relationship between different signals or the same signal at different times.

[0134] In this embodiment, the scaled dynamic rate of change and the corrected phase offset are first nonlinearly superimposed. Next, a composite parameter is obtained by weighting the load fluctuation impedance component using the energy contribution coefficient within the corresponding time domain interval. Specifically, a nonlinear function is used to combine the dynamic rate of change and the phase offset, and the weighting is adjusted using the energy contribution coefficient. Ultimately, a set of composite parameters is obtained that comprehensively describes the load fluctuation characteristics.

[0135] Here's a specific example:

[0136] In a smart distribution network project in a certain city, technicians first determined the time window between adjacent timestamps as an independent time domain interval based on the load switching timestamps, and extracted the extreme points of the load fluctuation impedance component in each interval as the sampling reference points for the dynamic change rate. Next, local time windows were constructed with these reference points as the center to generate original parameter pairs of the dynamic change rate and the phase offset. The original parameter pairs were then cross-validated, and the phase offset was corrected based on the continuity characteristics. Finally, the scaled dynamic change rate and the corrected phase offset were nonlinearly superimposed and weighted by the energy proportion coefficient to obtain a set of composite parameters that can fully describe the load fluctuation characteristics, providing solid data support for subsequent power grid maintenance and low voltage management.

[0137] In summary, steps 401 to 404, through in-depth analysis of the load fluctuation impedance components, combined with time-domain interval partitioning, local time window construction, cross-validation, and nonlinear superposition methods, successfully generated a set of composite parameters that accurately describe the load fluctuation characteristics. This approach not only improves the understanding of load fluctuations but also provides a scientific basis for formulating effective low-voltage management strategies, significantly improving grid management efficiency and power supply reliability. Furthermore, the introduction of time window scaling constraints and phase polarity correction further enhances the model's adaptability and accuracy.

[0138] In order to solve the problem of accurately describing the complex dynamic behavior in the power system, first, the three-phase voltage imbalance parameters are expanded into a multi-channel pulse sequence. Then, a circular convolution is performed on the multi-channel pulse sequence within a sliding time window. When a sudden change in the impedance parameter is detected, the convolution kernel function is automatically expanded. Finally, by screening the energy threshold of the convolution output result, a distorted feature vector containing the joint spectrum characteristics of impedance and voltage is obtained, which effectively characterizes the health status of the line. In some embodiments, the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter are subjected to a time domain convolution operation in step 103 to generate a distorted feature vector of the joint line impedance and voltage, including:

[0139] 501. Constructing a three-dimensional convolution kernel function with time-varying characteristics based on the orthogonal decomposition relationship between the inherent impedance component and the load fluctuation impedance component in the impedance parameter coupling factor matrix;

[0140] In step 501, the intrinsic impedance component and the load fluctuation impedance component are the two main components separated from the line impedance decomposition dataset. The orthogonal decomposition relationship refers to the fact that these two impedance components are independent of each other and do not affect each other. The three-dimensional convolution kernel function is a mathematical tool used to process multidimensional data (such as time, frequency, and space dimensions). It has time-varying characteristics and can adapt to data changes over different time periods.

[0141] In the embodiments of the present application, the orthogonal decomposition relationship between the intrinsic impedance component and the load fluctuation impedance component in the impedance parameter coupling factor matrix is ​​first analyzed. Next, a three-dimensional convolution kernel function with time-varying characteristics is constructed based on these relationships. Specifically, a tensor decomposition method is used to extract the time series characteristics of the intrinsic impedance and load fluctuation impedance, and a corresponding convolution kernel is constructed. Ultimately, a three-dimensional convolution kernel function is obtained that can dynamically adapt to changes in the power grid.

[0142] 502. Expand the three-phase voltage imbalance parameter into a multi-channel pulse sequence according to a preset time granularity, and map each channel to a voltage amplitude differential increment of a corresponding phase;

[0143] In step 502, presetting the time granularity means dividing time into fixed-length time segments to facilitate data analysis. A multi-channel pulse sequence is the result of expanding the three-phase voltage imbalance parameters at this time granularity, with each channel corresponding to the differential increment of the voltage amplitude for a single phase. This representation helps capture the trends and subtle differences in voltage over time. The differential increment of the voltage amplitude refers to the rate of change of the voltage amplitude of a particular phase relative to time within a specific time interval, reflecting the increase or decrease of voltage over a very short period of time.

[0144] In this embodiment, the three-phase voltage imbalance parameter is first expanded into a multi-channel pulse sequence according to a preset time granularity. Each channel is then mapped to the differential increment of the voltage amplitude for the corresponding phase. Specifically, a differential algorithm is used to calculate the differential increments of each phase voltage and organize them into a multi-channel pulse sequence. Finally, a multi-channel pulse sequence is obtained that accurately describes the three-phase voltage imbalance characteristics.

[0145] 503. Within a sliding time window, tensor-slice the three-dimensional convolution kernel function along the time axis, and perform asymmetric boundary-constrained circular convolution on the multi-channel pulse sequence. When the impedance parameter suddenly changes, the three-dimensional convolution kernel function automatically expands to a hyperbolic secant attenuation function.

[0146] In step 503, the sliding time window is a fixed-length time period that moves in the time domain and is used to analyze data segment by segment. Tensor slicing extracts data segments within a specific time period from the three-dimensional convolution kernel function. Asymmetric boundary-constrained circular convolution is a method for addressing boundary effects, ensuring that the convolution operation is performed correctly even at boundaries. The hyperbolic secant decay function is a special mathematical function used to describe the behavior of impedance parameters when they undergo sudden changes.

[0147] In the embodiments of the present application, a three-dimensional convolution kernel function is first tensor-sliced ​​along the time axis within a sliding time window. Then, asymmetric boundary-constrained circular convolution is applied to the multi-channel pulse sequence. When a sudden change in the impedance parameter is detected, the three-dimensional convolution kernel function is automatically expanded to a hyperbolic secant attenuation function. Specifically, a sudden change detection window is set to monitor the impedance parameter changes in real time, and the convolution kernel morphology is adjusted when a sudden change occurs. Ultimately, a set of convolution-processed output results is obtained.

[0148] 504. Extract the interaction intensity coefficient between the voltage trajectory and the impedance trajectory of each phase in the convolution output result, and construct a multidimensional tensor containing the joint spectrum characteristics of impedance and voltage. Perform energy threshold screening on the multidimensional tensor along the impedance coupling axis, and use the projected component exceeding the energy threshold as the distortion feature vector.

[0149] In step 504, the interaction strength coefficient is an indicator that measures the degree of mutual influence between the voltage and impedance traces of each phase. A multidimensional tensor is a high-dimensional array structure used to store data across multiple dimensions. Energy threshold screening is a method for selectively retaining data components with high energy to highlight important characteristic information. A distortion eigenvector is a multidimensional data structure used to characterize the complex interaction between line impedance and voltage in a power system.

[0150] In this embodiment, the interaction strength coefficients between the voltage and impedance traces of each phase are first extracted from the convolution output. Next, a multidimensional tensor is constructed containing the joint spectral characteristics of the impedance and voltage. Next, the multidimensional tensor is subjected to energy threshold screening along the principal axis of impedance coupling, retaining projected components exceeding the energy threshold. Specifically, spectral analysis techniques are used to extract the joint spectral characteristics, and an energy threshold screening algorithm is applied to highlight important features. Ultimately, a set of distorted eigenvectors is obtained that comprehensively describe the joint characteristics of the line impedance and voltage.

[0151] Here's a specific example:

[0152] In a smart distribution network project in a certain city, technicians first constructed a three-dimensional convolution kernel function with time-varying characteristics based on the orthogonal decomposition relationship between the inherent impedance component and the load fluctuation impedance component in the impedance parameter coupling factor matrix. Next, the three-phase voltage imbalance parameters were expanded into a multi-channel pulse sequence according to a preset time granularity. Then, asymmetric boundary-constrained circular convolution was performed on the multi-channel pulse sequence within a sliding time window. When a sudden change in the impedance parameter was detected, the three-dimensional convolution kernel function was automatically expanded into a hyperbolic secant attenuation function. Finally, the interaction strength coefficients between the voltage and impedance trajectories of each phase were extracted from the convolution output, a multidimensional tensor was constructed, and energy threshold screening was performed. This yielded a set of distorted eigenvectors that comprehensively describe the joint characteristics of line impedance and voltage, providing solid data support for subsequent grid maintenance and low-voltage management.

[0153] In summary, steps 501 to 504, through in-depth analysis of the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameters, combined with methods such as three-dimensional convolution kernel functions and time-domain convolution operations, successfully generate a set of distortion feature vectors that accurately describe the joint characteristics of line impedance and voltage. This approach not only improves the understanding of grid health but also provides a scientific basis for formulating effective low-voltage management strategies, significantly improving grid management efficiency and power supply reliability. Furthermore, the introduction of a hyperbolic secant decay function and energy threshold screening further enhances the model's adaptability and accuracy.

[0154] In order to solve the problem of accurately describing the dynamic behavior of the power system when the impedance parameters suddenly change, a mutation detection window is set on the time axis of the three-dimensional convolution kernel function, the instantaneous rate of change is calculated in real time, and the convolution kernel function shape is adjusted according to the trigger expansion mechanism. In addition, energy conservation constraints are imposed on the frequency domain components of the trigger expansion mechanism to ensure the consistency of total energy. According to the phase difference change trajectory between the impedance parameter and the three-phase voltage imbalance parameter, the trigger expansion mechanism is dynamically corrected so that the system can adapt to rapidly changing grid conditions and provide stable and reliable evaluation results. In some embodiments, when the impedance parameter suddenly changes in step 503, the three-dimensional convolution kernel function is automatically expanded to a hyperbolic secant attenuation function, including:

[0155] 601. Setting a mutation detection window on the time axis of the three-dimensional convolution kernel function to calculate in real time the instantaneous rate of change of the load fluctuation impedance component in the impedance parameter coupling factor matrix and the trigger expansion mechanism of the hyperbolic secant attenuation function;

[0156] In step 601, the mutation detection window refers to a specific time period set on the time axis for real-time monitoring of impedance parameter changes. The instantaneous rate of change is the rate at which the load's fluctuating impedance component changes over time and is used to identify the occurrence of mutations. The trigger expansion mechanism is a predefined rule or algorithm that determines when and how to adjust the shape of the 3D convolution kernel function to adapt to mutations.

[0157] In an embodiment of the present application, a mutation detection window is first set on the time axis of the three-dimensional convolution kernel function, and the instantaneous rate of change of the load fluctuation impedance component is calculated in real time. Next, based on a preset trigger expansion mechanism, it is determined whether the three-dimensional convolution kernel function needs to be expanded. Specifically, a sliding window technique is used to monitor data in real time, and a numerical differentiation method is used to calculate the instantaneous rate of change. Once a significant change is detected, the trigger expansion mechanism is activated and the convolution kernel function is prepared to be adjusted. Ultimately, a set of data sets that can accurately reflect the sudden change of the impedance parameters is obtained.

[0158] 602. Apply energy conservation constraints to the frequency domain component of the trigger expansion mechanism, and maintain the total energy of the trigger expansion mechanism consistent before and after the mutation by integrating the energy of the load fluctuation impedance component;

[0159] In step 602, the energy conservation constraint refers to the principle of ensuring that the total energy of the system remains unchanged before and after the sudden change. Frequency domain components are the individual frequency components after converting the time domain signal to the frequency domain. Energy integration is used to maintain the total energy of the trigger expansion mechanism consistent before and after the sudden change, ensuring system stability. The energy conservation constraint means that when certain frequency domain components (such as frequency changes caused by load fluctuations) are analyzed or processed, the total energy of these components remains unchanged before and after the entire process. A trigger expansion mechanism is a program or algorithm that can be activated when a specific condition or event is detected, such as a voltage sag, swell, or other power quality issues.

[0160] In the embodiment of the present application, energy conservation constraints are first applied to the frequency domain components of the trigger expansion mechanism. Next, the consistency of the total energy before and after the mutation is maintained by integrating the energy of the load fluctuating impedance component. Specifically, a fast Fourier transform is used to convert the time domain signal into a frequency domain representation, and the energy integration formula is applied to calculate the energy of each frequency band. Then, according to the principle of energy conservation, the parameters of the trigger expansion mechanism are adjusted to ensure that the total energy of the system remains unchanged before and after the mutation. Ultimately, a trigger expansion mechanism that has been corrected for energy conservation is obtained.

[0161] 603. Dynamically correct the constrained trigger expansion mechanism based on the phase difference change trajectory between the impedance parameter and the three-phase voltage imbalance parameter within the mutation detection window. When the instantaneous change rate exceeds the corrected trigger expansion mechanism, the three-dimensional convolution kernel function is automatically expanded into a hyperbolic secant attenuation function.

[0162] In step 603, the phase difference change trajectory refers to the temporal evolution of the phase difference between the impedance parameter and the three-phase voltage imbalance parameter within the mutation detection window. Dynamically correcting the constrained trigger expansion mechanism means further optimizing the trigger expansion mechanism based on the observed change trajectory to improve its accuracy. A three-dimensional convolution kernel function can be used to detect and analyze the interactions between different parameters (such as the impedance parameter and the three-phase voltage imbalance parameter) and their temporal evolution. A hyperbolic secant decay function is used to adjust the analytical model to more accurately simulate the impact of these drastic changes, potentially contributing to a better understanding and prediction of abnormal behavior in power systems.

[0163] In an embodiment of the present application, first, based on the phase difference change trajectory between the impedance parameter and the three-phase voltage imbalance parameter within the mutation detection window, the constrained trigger expansion mechanism is dynamically corrected. Next, the instantaneous rate of change is monitored in real time and compared with the corrected trigger expansion mechanism. Once the instantaneous rate of change exceeds the threshold, the three-dimensional convolution kernel function is immediately adjusted to expand it into a hyperbolic secant attenuation function. Specifically, a phase detection algorithm is used to track the phase difference change, and the trigger expansion mechanism is adjusted according to the actual change situation. Ultimately, a three-dimensional convolution kernel function that can adapt to the mutation situation is obtained, thereby more accurately describing the dynamic behavior of the power grid.

[0164] Here's a specific example:

[0165] In a smart power distribution network project in a certain city, technicians first set a mutation detection window on the time axis of the three-dimensional convolution kernel function and calculated the instantaneous rate of change of the load fluctuation impedance component in real time. The technicians used sliding window technology and numerical differentiation methods to calculate the instantaneous rate of change and activated the trigger expansion mechanism. Next, they imposed energy conservation constraints on the frequency domain components of the trigger expansion mechanism, and maintained the consistency of the total energy before and after the mutation by integrating the energy of the load fluctuation impedance component. Once the instantaneous rate of change exceeded the corrected trigger expansion mechanism, the three-dimensional convolution kernel function automatically expanded to a hyperbolic secant attenuation function. This method not only improves the accuracy of understanding the health of the power grid, but also provides a scientific basis for formulating effective low-voltage management strategies, greatly improving the efficiency of power grid management and power supply reliability.

[0166] In summary, steps 601 to 603 successfully implement the adaptive expansion of the three-dimensional convolution kernel function by real-time monitoring and analysis of impedance parameter mutations, combined with energy conservation constraints and a dynamic correction mechanism. This approach not only accurately captures sudden changes in the power grid but also effectively maintains system stability and avoids abnormal fluctuations caused by sudden changes. Furthermore, the introduction of a hyperbolic secant decay function further enhances the model's adaptability and accuracy, making the assessment of power grid operating status more efficient.

[0167] In order to solve the accuracy and reliability problems of data quality assessment in the system, first, the nonlinear correlation index of each monitoring node is established through the phase sensitivity kernel function, and a probability density diffusion surface is constructed. Then, the surface is multi-scale convolution fused with the inherent impedance spectrum characteristics to generate a dynamic weight base value. Finally, a weight correction equation based on the dual constraints of impedance and charge is established to obtain the final data credibility weight distribution, providing a scientific basis for low voltage governance measures. In some embodiments, the data credibility weight distribution of the global monitoring nodes of the distribution network line is calculated according to the nonlinear correlation between the three-phase imbalance data set and the distortion eigenvector in step 104, including:

[0168] 701. Perform multi-dimensional coupling on the voltage imbalance parameters of each phase in the three-phase imbalance dataset and the distortion feature vector in the time domain, and establish a nonlinear correlation index of each monitoring node through a phase sensitivity kernel function;

[0169] In step 701, the phase voltage imbalance parameter refers to information such as the effective value and phase angle deviation of each phase voltage recorded in the three-phase imbalance dataset. The distortion eigenvector is a multidimensional data structure that describes the joint characteristics of line impedance and voltage. The phase sensitivity kernel function is a mathematical model used to quantify the nonlinear correlation between different monitoring nodes. The nonlinear correlation index reflects the complex relationship between voltage imbalance and distortion characteristics between monitoring nodes.

[0170] In the embodiments of the present application, the voltage imbalance parameters of each phase in the three-phase imbalance dataset are first multi-dimensionally coupled with the distortion eigenvectors in the time domain. Next, a nonlinear correlation index is established for each monitoring node using a phase sensitivity kernel function. Specifically, time series analysis techniques are used to synchronously process the voltage imbalance parameters and distortion eigenvectors of each phase, and the phase sensitivity kernel function is applied to calculate their nonlinear correlation. Ultimately, a set of nonlinear correlation indices is obtained that accurately reflects the dynamic relationship between each monitoring node.

[0171] 702. Constructing a probability density diffusion surface reflecting line impedance coupling strength based on the spatial distribution of the nonlinear correlation index in the three-dimensional charge density gradient field;

[0172] In step 702, a three-dimensional charge density gradient field is generated based on spatial charge detection technology to describe the spatial distribution of charge density variations in the cable joint area. The distribution of nonlinear correlation indicators in this field can reveal the spatial characteristics of line impedance coupling strength. A probability density diffusion surface is a probability distribution model used to represent how these characteristics vary with spatial location.

[0173] In this embodiment, a probability density diffusion surface reflecting the line impedance coupling strength is constructed based on the spatial distribution of the nonlinear correlation index in a three-dimensional charge density gradient field. Specifically, a spatial interpolation method (such as Kriging interpolation) is used to construct the charge density gradient field, and the probability density diffusion surface is generated in combination with the nonlinear correlation index. Ultimately, a surface model is obtained that comprehensively describes the spatial distribution of the line impedance coupling strength.

[0174] 703. Perform multi-scale convolution fusion on the probability density diffusion surface and the inherent impedance spectrum features in the line impedance decomposition data set to generate a dynamic weight base value for each monitoring node;

[0175] In step 703, the intrinsic impedance spectrum features are frequency response characteristics extracted from the line impedance decomposition dataset. Multi-scale convolution fusion of the probability density diffusion surface and the intrinsic impedance spectrum features involves performing convolution operations on the two at different scales to generate a dynamic weight base value for each monitoring node. The dynamic weight base value is a basic weight value that reflects the importance of the data at each monitoring node.

[0176] In this embodiment, a multi-scale convolutional fusion of the probability density diffusion surface and the intrinsic impedance spectrum features from the line impedance decomposition dataset is first performed. Specifically, a multi-scale convolutional neural network is used to process both and generate dynamic weight base values ​​for each monitoring node. The convolution operation is performed at different scales to capture a variety of features from local to global. Ultimately, a set of dynamic weight base values ​​is obtained that accurately reflects the importance of the data at each monitoring node.

[0177] 704. Establish a weight correction equation based on the dual constraints of impedance and charge, perform path integral optimization on the dynamic weight base value, solve the steady-state solution set of the weight correction equation under the action of charge migration effect through an iterative convergence algorithm, and obtain the data credibility weight distribution based on the projection amplitude of the steady-state solution set in the monitoring node space coordinate system.

[0178] In step 704, the dual impedance and charge constraints simultaneously consider the influencing factors of line impedance and spatial charge density variations. The weight correction equation is a mathematical model used to optimize the dynamic weight base value. Path integral optimization is a method for solving the weight correction equation, using an iterative convergence algorithm to find a steady-state solution. The steady-state solution is the optimal weight allocation scheme under the influence of charge migration effects. Projection amplitude refers to the numerical magnitude of multidimensional data mapped onto a specific dimension (usually one or more axes of a spatial coordinate system).

[0179] In the embodiment of the present application, a weight correction equation based on the dual constraints of impedance and charge is first established. Then, the dynamic weight base value is optimized by path integral, and the weight correction equation is solved by an iterative convergence algorithm. Specifically, the path integral optimization algorithm is used to adjust the parameters in the weight correction equation, and the steady-state solution set is found through multiple iterations. Finally, the data credibility weight distribution is obtained based on the projection amplitude of the steady-state solution set in the spatial coordinate system of the monitoring node. Finally, a set of weight distributions that can accurately reflect the credibility of the data of each monitoring node is obtained.

[0180] Here's a specific example:

[0181] In a smart power distribution network project in a certain city, technicians first multi-dimensionally coupled the phase voltage imbalance parameters and distortion eigenvectors in the three-phase imbalance dataset in the time domain and established a nonlinear correlation index. Next, they constructed a probability density diffusion surface reflecting the strength of line impedance coupling. Then, they generated dynamic weight base values ​​for each monitoring node. Finally, an iterative convergence algorithm was used to solve the steady-state solution set of the weight correction equation under the influence of charge migration effects, resulting in a data credibility weight distribution. For example, in a certain cable segment, every time a large piece of equipment started or stopped, it would cause significant voltage imbalance and impedance changes. Using this method to generate a data credibility weight distribution, technicians found that the data from certain monitoring nodes was more reliable, providing a scientific basis for subsequent maintenance work.

[0182] In summary, steps 701 to 704, through in-depth analysis of the three-phase imbalance dataset and distortion eigenvectors, combined with methods such as phase sensitivity kernel functions, probability density diffusion surfaces, multi-scale convolution fusion, and path integral optimization, successfully generated a set of data credibility weight distributions that accurately describe the global monitoring nodes of the distribution network. This approach not only improves the understanding of grid health but also provides a scientific basis for developing effective low-voltage management strategies.

[0183] Figure 2 A structural diagram of a data quality assessment system is provided for an embodiment of the present application. Figure 2 As shown, the system includes:

[0184] Acquisition module 21, when the distribution network line is in operation, acquires a three-phase imbalance dataset, a free charge density distribution dataset generated based on millimeter-wave radar space charge detection technology, and a line impedance decomposition dataset generated by impedance spectrum dynamic reconstruction technology;

[0185] A mapping module 22 performs spatial topological mapping between the charge density gradient extreme value point in the cable joint area in the free charge density distribution dataset and the voltage phase angle in the three-phase imbalance dataset, and generates a three-phase voltage imbalance parameter after phase deviation correction by charge migration effect compensation calculation;

[0186] Establishing module 23, establishing an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuating impedance component separated from the line impedance decomposition data set, and performing a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion eigenvector of the line impedance and voltage;

[0187] The characterization module 24 calculates the data credibility weight distribution of the global monitoring nodes of the distribution network line based on the nonlinear correlation between the three-phase imbalance data set and the distortion characteristic vector. The data credibility weight distribution is used to characterize the quality assessment results of the low voltage management data.

[0188] Figure 2 The data quality assessment system can be executed Figure 1 The implementation principle and technical effects of the data quality assessment method described in the embodiment are not described in detail here. The specific manner in which each module and unit performs operations in the data quality assessment system in the above embodiment has been described in detail in the embodiment of the method and will not be elaborated on here.

[0189] In one possible design, Figure 2 A data quality assessment system of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0190] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0191] The processing component 32 is used for the above Figure 1 The embodiment provides a data quality assessment method.

[0192] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0193] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0194] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0195] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0196] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0197] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0198] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 A data quality assessment method according to the illustrated embodiment.

[0199] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0200] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0201] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0202] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data quality assessment method, characterized in that: include: When the distribution network lines are in operation, a three-phase imbalance dataset, a free charge density distribution dataset generated by millimeter-wave radar space charge detection technology, and a line impedance decomposition dataset generated by impedance spectrum dynamic reconstruction technology are obtained; Performing spatial topological mapping on the charge density gradient extreme value point in the cable joint area in the free charge density distribution data set and the voltage phase angle in the three-phase imbalance degree data set, and generating a three-phase voltage imbalance parameter after phase deviation correction by charge migration effect compensation calculation; Establishing an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuation impedance component separated from the line impedance decomposition data set, and performing a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion eigenvector of the line impedance and voltage; According to the nonlinear correlation between the three-phase imbalance data set and the distortion eigenvector, the data credibility weight distribution of the global monitoring nodes of the distribution network line is calculated, and the data credibility weight distribution is used to characterize the quality assessment result of the low voltage control data; The calculating of the data credibility weight distribution of the global monitoring nodes of the distribution network line according to the nonlinear correlation between the three-phase imbalance data set and the distortion characteristic vector includes: Multi-dimensionally coupling the voltage imbalance parameters of each phase in the three-phase imbalance dataset with the distortion feature vector in the time domain dimension, and establishing a nonlinear correlation index of each monitoring node through a phase sensitivity kernel function; Based on the spatial distribution of the nonlinear correlation index in the three-dimensional charge density gradient field, a probability density diffusion surface reflecting the line impedance coupling strength is constructed; Perform multi-scale convolution fusion on the probability density diffusion surface and the inherent impedance spectrum features in the line impedance decomposition data set to generate a dynamic weight base value for each monitoring node; A weight correction equation based on the dual constraints of impedance and charge is established, and the path integral optimization is performed on the dynamic weight base value. The steady-state solution set of the weight correction equation under the action of charge migration effect is solved by an iterative convergence algorithm. The data credibility weight distribution is obtained according to the projection amplitude of the steady-state solution set in the spatial coordinate system of the monitoring node.

2. The method according to claim 1, characterized in that The step of establishing an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuation impedance component separated from the line impedance decomposition data set includes: Decomposing the inherent impedance component of the line in the frequency domain and extracting the maximum points of the steady-state amplitude-frequency response curve within a preset frequency band, and generating a set of dominant resonant frequencies based on the distribution range of the maximum points; Dividing the load fluctuating impedance component into time domain intervals according to the load switching timestamp, and calculating the composite parameters of the dynamic change rate and phase offset of the load fluctuating impedance component in each time domain interval; An initial coupling factor matrix is ​​constructed using the set of dominant resonant frequencies as row indices and the composite parameters as column indices, and dynamic constraints are imposed on the initial coupling factor matrix, including generating spatial correction coefficients based on impedance transfer functions of adjacent monitoring nodes and generating statistical correction coefficients based on the kurtosis and skewness of the historical probability density of the load fluctuation impedance component; The correlation between the spatial correction coefficient and the statistical correction coefficient is superimposed on the matrix diagonal elements to establish an impedance parameter coupling factor matrix.

3. The method according to claim 2, characterized in that The constructing of an initial coupling factor matrix using the dominant resonant frequency set as a row index and the composite parameter as a column index includes: In the dominant resonant frequency set, the frequency interval and amplitude attenuation slope between adjacent maximum points on the steady-state amplitude-frequency response curve of each resonant frequency point are extracted to generate a resonance intensity factor; Discretize the composite parameter into segments according to the time domain interval corresponding to the load switching timestamp, and construct an anti-aliasing weight coefficient of the composite parameter based on the cosine similarity of the dynamic change rate and the phase offset in adjacent time domain intervals; The resonance intensity factor is used as a row vector element, the composite parameter weighted by the anti-aliasing weight coefficient is used as a column vector element, and an initial matrix framework is generated by performing an outer product operation between the row vector element and the column vector element; Based on the initial matrix framework, the row vector elements corresponding to each resonant frequency point are superimposed with the amplitude-frequency integral value of the maximum point in the preset frequency band to which the corresponding resonant frequency point belongs, and are associated element by element with the cumulative energy distribution of the composite parameters of the corresponding column vector elements in the time domain interval to construct an initial coupling factor matrix.

4. The method according to claim 2, characterized in that The step of dividing the load fluctuation impedance component into time domain intervals according to the load switching timestamps and calculating the composite parameters of the dynamic change rate and phase offset of the load fluctuation impedance component in each time domain interval includes: Based on the trigger interval of the load switching timestamp, the time window between adjacent timestamps is used as an independent time domain interval, and the extreme value point of the load fluctuation impedance component is extracted in the independent time domain interval as a sampling reference point of the dynamic change rate; Constructing a local time window with the sampling reference point as the center, and calculating the time domain curvature change rate mean of the load fluctuating impedance component to generate an original parameter pair of the dynamic change rate and the phase offset; Cross-validating the original parameter pair, applying a time window scaling constraint to the dynamic change rate by using the load switching timestamp interval lengths of adjacent time domain intervals, and performing phase polarity correction on the phase offset according to the continuity characteristics of adjacent time domain intervals; The scaled dynamic change rate and the corrected phase offset are nonlinearly superimposed, and weighted by the energy proportion coefficient of the load fluctuation impedance component in the corresponding time domain interval to obtain a composite parameter.

5. The method according to claim 1, wherein The step of performing a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion feature vector of a combination of line impedance and voltage includes: Based on the orthogonal decomposition relationship between the inherent impedance component and the load fluctuation impedance component in the impedance parameter coupling factor matrix, a three-dimensional convolution kernel function with time-varying characteristics is constructed; Expanding the three-phase voltage imbalance parameter into a multi-channel pulse sequence according to a preset time granularity, and mapping each channel to a voltage amplitude differential increment of a corresponding phase; In a sliding time window, the three-dimensional convolution kernel function is tensor-sliced ​​along the time axis, and asymmetric boundary-constrained circular convolution is performed on the multi-channel pulse sequence. When the impedance parameter suddenly changes, the three-dimensional convolution kernel function is automatically expanded into a hyperbolic secant attenuation function. The interaction strength coefficient between the voltage trajectory and impedance trajectory of each phase in the convolution output is extracted, and a multidimensional tensor containing the joint spectrum characteristics of impedance and voltage is constructed. The multidimensional tensor is then screened for an energy threshold along the principal axis of impedance coupling, and the projected components exceeding the energy threshold are used as distortion eigenvectors.

6. The method according to claim 5, characterized in that When the impedance parameter changes suddenly, the three-dimensional convolution kernel function automatically expands to a hyperbolic secant attenuation function, including: Setting a mutation detection window on the time axis of the three-dimensional convolution kernel function to calculate in real time the instantaneous rate of change of the load fluctuation impedance component in the impedance parameter coupling factor matrix and the trigger expansion mechanism of the hyperbolic secant attenuation function; Applying energy conservation constraints to the frequency domain components of the trigger expansion mechanism, and maintaining the total energy of the trigger expansion mechanism consistent before and after the mutation by integrating the energy of the load fluctuation impedance component; According to the phase difference change trajectory between the impedance parameter and the three-phase voltage imbalance parameter within the mutation detection window, the constrained trigger expansion mechanism is dynamically corrected. When the instantaneous change rate exceeds the corrected trigger expansion mechanism, the three-dimensional convolution kernel function is automatically expanded to a hyperbolic secant attenuation function.

7. A data quality assessment system, characterized in that: include: The acquisition module acquires a three-phase imbalance dataset, a free charge density distribution dataset generated by millimeter-wave radar space charge detection technology, and a line impedance decomposition dataset generated by impedance spectrum dynamic reconstruction technology when the distribution network line is in operation; A mapping module performs spatial topological mapping between the charge density gradient extreme value points in the cable joint area in the free charge density distribution dataset and the voltage phase angles in the three-phase imbalance dataset, and generates three-phase voltage imbalance parameters after phase deviation correction by charge migration effect compensation calculation; An establishment module is provided for establishing an impedance parameter coupling factor matrix based on the line inherent impedance component and the load fluctuation impedance component separated from the line impedance decomposition data set, and performing a time-domain convolution operation on the impedance parameter coupling factor matrix and the three-phase voltage imbalance parameter to generate a distortion feature vector of the line impedance and voltage; A characterization module calculates the data credibility weight distribution of the global monitoring nodes of the distribution network line according to the nonlinear correlation between the three-phase imbalance data set and the distortion eigenvector, and the data credibility weight distribution is used to characterize the quality assessment result of the low voltage control data; The calculating of the data credibility weight distribution of the global monitoring nodes of the distribution network line according to the nonlinear correlation between the three-phase imbalance data set and the distortion characteristic vector includes: Multi-dimensionally coupling the voltage imbalance parameters of each phase in the three-phase imbalance dataset with the distortion feature vector in the time domain dimension, and establishing a nonlinear correlation index of each monitoring node through a phase sensitivity kernel function; Based on the spatial distribution of the nonlinear correlation index in the three-dimensional charge density gradient field, a probability density diffusion surface reflecting the line impedance coupling strength is constructed; Perform multi-scale convolution fusion on the probability density diffusion surface and the inherent impedance spectrum features in the line impedance decomposition data set to generate a dynamic weight base value for each monitoring node; A weight correction equation based on the dual constraints of impedance and charge is established, and the path integral optimization is performed on the dynamic weight base value. The steady-state solution set of the weight correction equation under the action of charge migration effect is solved by an iterative convergence algorithm. The data credibility weight distribution is obtained according to the projection amplitude of the steady-state solution set in the spatial coordinate system of the monitoring node.

8. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a data quality assessment method as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, a data quality assessment method according to any one of claims 1 to 6 is implemented.

Images