Distribution area anomaly positioning method and system based on multi-modal dynamic characteristic analysis

Abstract

The invention discloses a power distribution area anomaly positioning method and system based on multi-modal dynamic feature analysis, and belongs to the technical field of data processing, and the method comprises the following steps: S1, obtaining area multi-source fusion data according to a sliding time window, and determining a hidden danger path corresponding to an instantaneous drop event in combination with a line topology; s2, performing state fluctuation analysis according to the real-time state data and the historical state data of the monitoring point to determine a state fluctuation factor, and constructing an impedance prediction model according to the path disturbance data to determine an environment disturbance factor; s3, performing activation processing on the hidden danger path according to the state fluctuation factor and the environment disturbance factor to obtain a transformer area degradation graph; and S4, dynamically cutting the transformer area degradation graph through the hidden danger risk values corresponding to the monitoring points to determine degradation blocks, and determining corresponding early warning measures according to the degradation degrees corresponding to the degradation blocks. According to the scheme, the limitation of single data dimension analysis and static evaluation is overcome, and the monitoring point hidden danger recognition accuracy and intelligent processing efficiency in a complex scene are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent distribution network, and in particular to a method and system for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis. Background Art

[0002] During the operation of the power system, the low-voltage distribution substation is the terminal link of the power system, and its real-time monitoring of the operating status and abnormal location are crucial to the reliability of power supply. The traditional distribution substation abnormal location method mainly relies on a single type of data and relatively simple analysis methods. The diagnosis of substation line abnormalities mainly relies on a single monitoring data (such as voltage and current steady-state parameters) and a static topology model, and fault judgment is performed through threshold comparison or impedance matching algorithm. However, in actual operation, the state of the substation will be dynamically affected by various factors, such as environmental factors (temperature, humidity, wind speed, etc.) and random changes in user electricity consumption behavior. These dynamic factors will cause the operating parameters of the substation to present complex fluctuation characteristics, and traditional methods cannot effectively capture these dynamic characteristics, making it difficult to accurately identify abnormal conditions in the early stages, delaying the best time for fault handling.

[0003] The above information disclosed in the Background section is only for enhancement of understanding of the background of the present application and therefore it may contain information that does not constitute the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0004] In response to the problem that the prior art relies on manual inspections or simple analysis of a single data source, which leads to inaccurate and inefficient identification of hidden dangers in distribution station areas, this application proposes a distribution station area abnormality positioning method and system based on multi-modal dynamic feature analysis. By collecting multi-source data in the station area for correlation analysis, it overcomes the limitations of single data dimension analysis and static evaluation, and achieves accurate positioning of hidden danger paths from multi-source data fusion and topological association. The degree of station area degradation is dynamically evaluated through quantitative analysis of state fluctuations and environmental disturbances combined with the hidden danger risk values ​​corresponding to the monitoring points, and differentiated early warning measures are automatically generated, which significantly improves the accuracy of hidden danger identification at monitoring points in complex scenarios and the efficiency of intelligent processing.

[0005] In a first aspect, a technical solution provided in an embodiment of the present invention is: a method for locating abnormalities in a distribution station area based on multimodal dynamic feature analysis, comprising the following steps: S1. Obtain multi-source fusion data of the substation area according to the sliding time window and determine the hidden danger path corresponding to the instantaneous drop event in combination with the line topology; S2. Perform state fluctuation analysis on the real-time state data and historical state data of the monitoring point to determine the state fluctuation factor, and build an impedance prediction model based on the path disturbance data to determine the environmental disturbance factor; S3, according to the state fluctuation factor and the environmental disturbance factor, the potential danger path is intensified to obtain the degradation map of the substation area; S4. Dynamically cut the degradation map of the substation area according to the hidden danger risk value corresponding to the monitoring point to determine the degraded block, and determine the corresponding early warning measures according to the degradation degree corresponding to the degraded block.

[0006] Preferably, the method of acquiring multi-source fusion data of the substation area according to the sliding time window and determining the hidden danger path corresponding to the instantaneous drop event in combination with the line topology comprises the following steps: S11, dynamically generate a sliding time window based on the response characteristics of the equipment in the substation area and the environmental noise coefficient; S12, the distributed acquisition terminal acquires the multi-source fusion data of the substation according to the sliding time window, wherein the multi-source fusion data of the substation includes at least voltage sag waveform data, harmonic distortion rate data, zero-sequence current phase difference data and temperature gradient data; S13, using spline interpolation and kernel density estimation to perform spatiotemporal alignment operations on the multi-source fusion data of the station area to obtain a preliminary data set; S14, screening the preliminary data set by impedance constraint and instantaneous drop event criterion and determining the candidate path set in combination with line topology coordinate mapping; S15. Determine the credibility of each candidate path according to the impedance change rate, node coupling degree, fault density and their corresponding weight coefficients; and take the candidate path with a credibility greater than a set threshold as a potential risk path.

[0007] Preferably, in S2, performing state fluctuation analysis on the real-time state data and historical state data of the monitoring point to determine the state fluctuation factor includes the following steps: S211, acquiring voltage data and current data of the monitoring point according to the time series, performing Z-score standardization to obtain a real-time voltage series and a real-time current series; S212, comparing the real-time voltage sequence and the real-time current sequence with the historical state data in the same domain in sequence to obtain a voltage fluctuation variance sequence and a current fluctuation variance sequence; S213, based on the real-time voltage sequence and the real-time current sequence, calculate the voltage and current anti-correlation in sequence by using the Pearson correlation coefficient method to obtain a voltage and current anti-correlation sequence; S214. Calculate the state fluctuation factor corresponding to the monitoring point in the time series according to the voltage fluctuation variance sequence, the current fluctuation variance sequence, the voltage-current anti-correlation sequence and their corresponding weight coefficients.

[0008] Preferably, in S2, an impedance prediction model is constructed according to the path disturbance data to determine the environmental disturbance factor; the steps include: S221, mapping the hidden danger path into a directed graph according to the line topology characteristics, constructing a node set and a directed edge set corresponding to the hidden danger path; dividing the hidden danger path into unit grids according to the edge characteristics in the directed edge set, and obtaining path disturbance data of each unit grid; the path disturbance data includes temperature field data, load fluctuation data and zero-sequence current data; S222, constructing a state equation of time-varying impedance based on the path disturbance data, and constructing an observation equation based on Ohm's law; iteratively calculating the state equation and the observation equation through a Kalman filter algorithm to obtain an optimal time-varying impedance state equation and using it as an impedance prediction model; S223, obtaining the predicted impedance at each moment through the impedance prediction model, and taking the difference between the predicted impedance and the measured impedance as the impedance prediction residual; using the principal component analysis method to perform characteristic decomposition on the impedance prediction residual to obtain a temperature disturbance component, a load disturbance component, and a zero-sequence current disturbance component; S224. Calculate the environmental disturbance factor of each unit grid according to the temperature characteristic component, the load characteristic component, the zero-sequence current characteristic component and their corresponding standard deviations.

[0009] Preferably, the state equation is: ; The observation equation is: ; represents the impedance value of the line at the kth moment, is the impedance value of the line at the (k-1)th moment; is the temperature influence coefficient; is the temperature change at the kth moment relative to the reference moment, is the load influence factor; is the load change at the kth moment; is the zero-sequence interference coefficient; is the zero-sequence current phase difference at the kth moment; is the process noise; is the line voltage value measured at the kth moment; is the line current value measured at the kth moment; is the measurement noise.

[0010] Preferably, the impedance prediction residual: ; Environmental disturbance factors: ; in, is the impedance prediction residual; For the unit grid Environmental disturbance factors; is the temperature change at the kth moment relative to the reference moment; is the load change at the kth moment; is the zero-sequence current phase difference at the kth moment; , , They are temperature disturbance load factor, load disturbance load factor, and zero-sequence current disturbance load factor respectively; They are the standard deviation of the temperature disturbance component, the standard deviation of the load disturbance component and the standard deviation of the zero-sequence current disturbance component respectively.

[0011] Preferably, the method of performing an intensification process on the hidden danger path according to the state fluctuation factor and the environmental disturbance factor to obtain the substation degradation map comprises the following steps: S31. Perform Z-score standardization on the state fluctuation factor and the environmental disturbance factor to obtain a state fluctuation factor sequence and an environmental disturbance factor sequence belonging to the same hidden danger path; S32, configuring a corresponding fluctuation trend factor for each state fluctuation factor in the state fluctuation factor sequence and configuring a corresponding disturbance trend factor for each environmental disturbance factor in the environmental disturbance factor sequence; S33, inputting the standardized state fluctuation factor, fluctuation trend factor, standardized environmental disturbance factor, disturbance trend factor, and fluctuation disturbance correlation coefficient into the degradation prediction model to obtain a degradation degree sequence corresponding to each hidden danger path; S34. Combine the degradation degree sequence with the topological structure of the potential hazard path to obtain a degradation map of the substation area.

[0012] Preferably, the degradation prediction model is constructed by a bidirectional LSTM model, with 5 input layers, and the state fluctuation factor, fluctuation trend factor, environmental disturbance factor, disturbance trend factor and fluctuation disturbance correlation coefficient are used as input parameters of the input layer; the hidden layer includes a forward LSTM layer and a backward LSTM layer; there is 1 output layer; the mean square error and trend penalty mechanism are used as loss functions; the AdamW optimizer is used to optimize the degradation prediction model and the root mean square error is used as the model evaluation reliability indicator.

[0013] Preferably, the degradation degree sequence is combined with the topological structure of the potential danger path to obtain a substation degradation map, which includes the following steps: S341, expanding the degradation degree sequence according to the timestamp and mapping it onto a directed graph according to the edge characteristics and node characteristics to form a degradation trajectory; S342, superimposing the degradation values ​​at different times on the degradation trajectory and obtaining a spatiotemporal heat map through graded color rendering; determining the degradation direction and degree in the spatiotemporal heat map through the direction and length of the arrow.

[0014] As a preferred embodiment, S4, dynamically cutting the degradation map of the substation area according to the hidden danger risk value corresponding to the monitoring point to determine the degradation block, and determining the corresponding early warning measures according to the degradation degree corresponding to the degradation block; comprising the following steps: S41, obtaining oxidation characteristics corresponding to the instantaneous drop event within the time window, and determining the oxidation risk value of each degradation trajectory according to the oxidation characteristics and the corresponding weight factors; S42, obtaining melting characteristics corresponding to the instantaneous drop event within the time window, and obtaining a melting risk value according to a melting characteristic criterion; S43, determining the hidden danger risk value corresponding to the monitoring point according to the oxidation risk value and the melting risk value; forming a multidimensional feature vector according to the hidden danger risk value corresponding to the monitoring point in the substation degradation map and the degradation degree sequence: dynamically cutting the substation degradation map to determine the degradation block through the fuzzy C-means clustering method combined with the multidimensional feature vector; S44. Determine the degradation degree of the degraded block according to the degraded block division rule table; and determine corresponding early warning measures according to the degradation degree corresponding to the degraded block.

[0015] In a second aspect, a technical solution provided in an embodiment of the present invention is: a distribution station area abnormality positioning system, applicable to the distribution station area abnormality positioning method based on multimodal dynamic feature analysis, comprising: Hidden danger preliminary judgment module: obtain multi-source fusion data of the substation area according to the sliding time window and determine the hidden danger path corresponding to the instantaneous drop event in combination with the line topology; The first determination module: performs state fluctuation analysis on the real-time state data and historical state data of the monitoring point to determine the state fluctuation factor; The second determination module: constructs an impedance prediction model based on the path disturbance data to determine the environmental disturbance factor; Construction module: According to the state fluctuation factor and environmental disturbance factor, the potential danger path is intensified to obtain the degradation map of the substation area; Execution module: Dynamically cut the degradation map of the substation to determine the degraded blocks through the hidden danger risk values ​​corresponding to the monitoring points, and determine the corresponding early warning measures according to the degree of degradation corresponding to the degraded blocks.

[0016] In the third aspect, a technical solution provided in an embodiment of the present invention is: an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the distribution station area anomaly positioning method based on multimodal dynamic feature analysis are implemented.

[0017] In a fourth aspect, a technical solution provided in an embodiment of the present invention is: a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the distribution station area anomaly positioning method based on multimodal dynamic feature analysis are implemented.

[0018] Beneficial effects of the present invention: (1) In view of the problem that multi-source data fusion is insufficient and hidden danger path location relies on single-dimensional analysis in the existing technology, this application dynamically generates a sliding time window based on the response characteristics of the substation equipment, distributes and collects multi-source fusion data such as voltage sag waveform and harmonic distortion rate, and uses time-space alignment, impedance constraint screening and credibility weighted calculation to overcome the shortcomings of traditional methods that rely only on a single data source or simple analysis, and significantly improves the ability to accurately locate the hidden danger path of instantaneous sag events in complex substation environments; (2) In view of the problem that traditional methods lack the coupling analysis of monitoring point state fluctuation and environmental disturbance, and the static degradation trend assessment, this application performs Z-score standardization on the real-time and historical voltage and current data of the monitoring points, calculates the voltage and current fluctuation variance and anti-correlation to obtain the state fluctuation factor, and constructs an impedance prediction model based on Kalman filtering, decomposes environmental disturbance components such as temperature, load, and zero-sequence current, and calculates the environmental disturbance factor. Finally, the dual factors and trend characteristics are input into the bidirectional LSTM degradation prediction model to generate a spatiotemporal thermal degradation map. This overcomes the defect of the existing technology in the lack of comprehensive analysis of the dynamic changes of equipment status and the multi-physical quantity disturbance of the external environment, and significantly improves the dynamic quantitative assessment accuracy of the degradation degree of the substation equipment; (3) In response to the problems of extensive judgment of existing hidden danger risk levels and lack of real-time and differentiation of early warning measures, this application constructs hidden danger risk values ​​corresponding to monitoring points containing multiple physical quantity parameters by extracting oxidation characteristics such as voltage difference and low voltage drop, and melting characteristics such as instantaneous power drop and current continuity characteristics. The fuzzy C-means clustering algorithm is used to dynamically cut and divide the degradation blocks of the substation degradation map, and finally the corresponding early warning strategy is matched according to the degree of block degradation. This overcomes the shortcomings of traditional methods that rely on manual experience and have a single risk assessment dimension, and significantly improves the intelligence level of hidden danger identification at the front end of the monitoring point and the precise adaptation capability of early warning measures.

[0019] The above invention content is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0021] Figure 1 The present invention is a flow chart of the method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis.

[0022] Figure 2 A flow chart is generated for the hidden danger path of the present invention.

[0023] Figure 3 A flow chart is generated for the state fluctuation factor of the present invention.

[0024] Figure 4 A flow chart is generated for the environmental disturbance factors of the present invention.

[0025] Figure 5 A flow chart for generating a station area degradation map of the present invention.

[0026] Figure 6 It is a structural diagram of the distribution station area abnormality positioning system of the present invention. DETAILED DESCRIPTION

[0027] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the drawings; the process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0029] Embodiment 1: At present, the traditional abnormal location method of distribution substation mainly relies on a single type of data and relatively simple analysis methods. With the access of distributed energy, the intensification of load fluctuations and the complexity of environmental factors, the traditional methods have exposed significant defects in the accuracy of hidden danger path identification, dynamic disturbance response speed and positioning granularity. For example, some methods only judge whether there is an abnormality in the substation based on electrical quantity data. This method cannot fully reflect the actual operation status of the substation due to the single data source, which easily leads to inaccurate abnormal location and misses some potential hidden dangers. Moreover, traditional methods often focus on the analysis of static data and ignore the dynamic change characteristics during the operation of the substation. In actual operation, the state of the substation will be dynamically affected by various factors, such as environmental factors (temperature, humidity, wind speed, etc.) and random changes in user electricity consumption behavior. These dynamic factors will cause the operating parameters of the substation to present complex fluctuation characteristics, and the traditional methods cannot effectively capture these dynamic characteristics, making it difficult to accurately identify abnormal conditions in the early stage, delaying the best time for fault handling. In addition, the existing positioning methods have great limitations when facing complex low-voltage line topology structures. The topology of low-voltage lines is complex. When abnormal situations such as instantaneous drops occur, traditional methods make it difficult to quickly and accurately determine the corresponding potential danger paths, resulting in time-consuming and labor-intensive troubleshooting, which seriously affects the efficiency of power supply restoration.

[0030] In view of the above shortcomings of the prior art, this application proposes a method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis. Figure 1 As shown, the following steps are included: S1. Obtain multi-source fusion data of the substation area according to the sliding time window and determine the potential hazard path corresponding to the instantaneous drop event in combination with the line topology.

[0031] As an optional embodiment, Figure 2 As shown, S1 includes the following steps: S11. Dynamically generate a sliding time window based on the response characteristics of the substation equipment and the environmental noise coefficient.

[0032] It is understandable that the action delay of the intelligent switch in the substation area is 10 minutes according to historical data statistics, and the minimum step length of the time window is determined =15 minutes (matching the 15-minute sampling period of the monitoring point); the standard deviation of the zero-sequence current phase difference As a noise indicator, the time window length is dynamically adjusted; ; It represents the mean value of the historical zero-sequence current phase difference, which is generally calculated based on 30 days of historical data. In this embodiment, the time window length is dynamically adaptive to the environmental noise to avoid missed or redundant collection of high-frequency / low-frequency disturbances with a fixed window length; it achieves precise matching of temporary sag events with the equipment response cycle, and improves the pertinence of data collection.

[0033] S12. The distributed acquisition terminal obtains the multi-source fusion data of the substation according to the sliding time window, wherein the multi-source fusion data of the substation includes at least voltage sag waveform data, harmonic distortion rate data, zero-sequence current phase difference data and temperature gradient data.

[0034] It can be understood that the voltage sag waveform data includes the voltage sag amplitude and duration (calculated by counting continuous monitoring points), the harmonic distortion rate data generally indicates the third harmonic content; the zero-sequence current phase difference can be expressed as ,in, represents the phase angle of the i-th phase current, It is the mean of the three-phase phase angles. In normal operation, θ<10°, and in abnormal conditions (such as single-phase grounding), θ>15°; Cable joint temperature: obtained through distributed fiber optic temperature measurement (DTS), such as the temperature of the A-phase joint TA=75°C, the adjacent healthy joint TB=50°C, and the gradient difference of 25°C (exceeding the warning threshold of 15°C). By integrating multi-dimensional data such as voltage, current, harmonics, temperature, and phase difference to detect hidden faults (such as joint failures caused by heating of the wire clamp), avoiding missed judgments caused by single voltage and current analysis, the recognition rate of hidden faults can be improved. In this embodiment, multi-dimensional data collection covers electrical quantities (voltage / current data), harmonic characteristics, three-phase balance, and temperature field data, and a three-dimensional hidden danger feature library can be constructed; the one-sidedness of single data dimension analysis is eliminated, and full-factor input is provided for subsequent hidden danger nature judgment.

[0035] S13. Use spline interpolation and kernel density estimation to perform spatiotemporal alignment operations on the multi-source fusion data in the station area to obtain the preliminary data set.

[0036] It is understandable that spline interpolation is used to handle missing values ​​in the time series. Assume that in the voltage sag waveform data, the data at a certain moment (set as t=30 minutes) is missing. Using the cubic spline interpolation formula: y(t)=a0+a1(t-tg)+a2(t-tg) 2 +a3(t-tg) 3 (Where y(t) is the value at time t after interpolation, tg is the time of the known data point, and a0, a1, a2, and a3 are coefficients obtained by solving the known data points). The coefficients are determined by using the known adjacent data points (such as the data points at t=20 minutes and t=40 minutes) to calculate the voltage value at the missing time to ensure the continuity of the time series.

[0037] It can be understood that kernel density estimation is used to smooth spatially distributed data (such as the measured values ​​of zero-sequence current phase difference at different locations) to eliminate the influence of outliers. Assume that at a certain moment, the zero-sequence current phase difference at different locations in the substation is measured to obtain a series of data points x1, x2,..., xn. The kernel density estimation formula can be: , where f(x) is the estimated density at position x, n is the number of data points, h is the bandwidth (determined according to the discreteness of the data, here set to h=5°), and K is the kernel function (such as the Gaussian kernel function). This formula is used to process the zero-sequence current phase difference data, making the data smoother and better reflecting the actual distribution of the data.

[0038] In this embodiment, spline interpolation ensures the integrity of multi-source fusion data in the time dimension, avoiding analysis deviations caused by missing data; kernel density estimation smoothes the spatial data, effectively removing the interference of outliers, so that the data can more accurately reflect the actual status of substation operation, improve data quality, and provide a reliable data basis for subsequent precise analysis and screening of potential hidden danger paths.

[0039] S14. Screen the preliminary data set through impedance constraints and instantaneous drop event criteria and determine the candidate path set in combination with line topology coordinate mapping.

[0040] It is understandable that the impedance constraint filters data by setting a reasonable impedance range. The theoretical range of known line impedance can be calculated based on line material, length and other parameters. If the impedance value calculated at a certain measurement point exceeds this range, the data point is considered abnormal data and excluded; the instantaneous drop event judgment criteria include multiple conditions. For example, condition 1: the meter voltage difference ΔV>7V and the measured user voltage V user <225V; Condition 2: Current change rate (I high -I low ) / I high >50%; Condition 3: The voltage of three-phase users does not drop at the same time. Assume that at a certain moment, the measured data of a user shows that the voltage drops from 225V to 210V (ΔV=15V, V user =210V), the current increases from 2A to 3.5A (current change rate 23.5-2=75%>50%), and only this phase of the three phases has a voltage drop, which meets the criterion for the instantaneous drop event. Combined with the line topology coordinate mapping, the data points that meet the impedance constraint and the instantaneous drop event criterion are associated with the line topology map of the substation to determine the line path that may have hidden dangers and form a set of candidate paths.

[0041] In this embodiment, the preliminary data set is screened by impedance constraints and instantaneous drop event criteria, so that data related to potential hidden dangers can be accurately screened out from a large amount of data, the interference of invalid data can be removed, and the scope of analysis can be narrowed; combined with line topology coordinate mapping, accurate positioning from data to actual line paths can be achieved, providing accurate candidate objects for the subsequent determination of the real hidden danger path, thereby improving the accuracy and pertinence of the hidden danger path positioning.

[0042] S15. Determine the credibility of each candidate path according to the impedance change rate, node coupling degree, fault density and their corresponding weight coefficients; and take the candidate path with a credibility greater than a set threshold as a potential risk path.

[0043] It can be understood that the impedance change rate is used to measure the change of line impedance over time, and the node coupling degree reflects the degree of connection between the line node and other nodes or devices. Specifically, the node coupling degree is calculated by the ratio of the sum of the active power and reactive power of two adjacent nodes to the sum of the active power and reactive power of the current node and all nodes in the substation area. The fault density refers to the frequency of faults in a certain line or area within a certain period of time. Weight coefficients are assigned to the impedance change rate, node coupling degree, and fault density of each candidate path, which are set to w1=0.4, w2=0.3, and w3=0.3 respectively. The credibility calculation formula for each candidate path is: C = w 1× R rate + w 2× D node + w 3× F density (where C is the credibility, R rate Impedance change rate, D node is the node coupling degree, F density is the fault density); Assuming that the impedance change rate of a candidate path is 30%, the node coupling degree is 5, and the fault density is 3 times / year, its credibility C=0.4×0.3+0.3×5+0.3×3=2.52. Set a credibility threshold (for example, the credibility threshold is set to 2), and determine the candidate path with a credibility greater than the threshold as a potential hazard path.

[0044] In this embodiment, the credibility of the candidate path is determined by comprehensively considering the impedance change rate, node coupling degree, fault density and its weight coefficient, and the potential hidden danger degree of each candidate path can be quantitatively evaluated. This quantitative evaluation method makes the judgment of the hidden danger path more scientific and accurate, avoiding the error of subjective judgment; taking the path with a credibility greater than the set threshold as the hidden danger path, further focusing on the line with real hidden dangers, improving the accuracy of hidden danger identification, providing a reliable basis for the subsequent targeted maintenance measures, reasonably allocating maintenance resources, and improving maintenance efficiency.

[0045] S2. Perform state fluctuation analysis on the real-time state data and historical state data of the monitoring point to determine the state fluctuation factor, and build an impedance prediction model based on the path disturbance data to determine the environmental disturbance factor.

[0046] As an optional embodiment, in S2, the state fluctuation analysis is performed on the real-time state data and the historical state data of the monitoring point to determine the state fluctuation factor, such as Figure 3 As shown, the following steps are included: S211 , obtaining voltage data and current data of the monitoring point according to the time series, performing Z-score standardization, and obtaining a real-time voltage series and a real-time current series.

[0047] In this embodiment, for example, in a specific distribution station area, a voltage data sequence {V1, V2, ..., Vn} and a current data sequence {I1, I2, ..., In} are obtained from a monitoring point for a period of time (e.g., once every 15 minutes in a day), and the voltage data and current data are standardized using the Z-score standardization method to obtain a real-time voltage sequence and real-time current sequence ; Z-score standardization eliminates the dimensionality of voltage and current data, making data of different magnitudes comparable. This lays the foundation for the subsequent accurate analysis of voltage and current fluctuation characteristics, ensuring that the weights of each data point are consistent when calculating fluctuation variance and correlation, and improving the reliability and accuracy of the analysis results.

[0048] S212, comparing the real-time voltage sequence and the real-time current sequence with the historical state data in the same domain in sequence to obtain the voltage fluctuation variance sequence and the current fluctuation variance sequence.

[0049] In this embodiment, the voltage fluctuation variance sequence and the current fluctuation variance sequence are calculated to quantify the fluctuation degree of the voltage and current at different times relative to the historical data. The variance sequence can reflect the stability change of the voltage and current. The larger the fluctuation variance, the more drastic the change of the voltage or current at that moment compared with the historical data, which provides an important quantitative indicator for judging whether the state (deterioration trend) of the monitoring point is abnormal.

[0050] S213. Based on the real-time voltage sequence and the real-time current sequence, the voltage and current anti-correlations are calculated in sequence by using the Pearson correlation coefficient method to obtain a voltage and current anti-correlation sequence.

[0051] In this embodiment, based on the standardized real-time voltage sequence and real-time current sequence, the Pearson correlation coefficient method is used to calculate the voltage and current anti-correlation. The voltage and current anti-correlation sequence reflects the degree of correlation between the voltage and current change trends. Under normal circumstances, the changes in voltage and current have certain rules, and when abnormalities occur (such as poor line contact, load mutation, etc.), this correlation will change. By analyzing the anti-correlation sequence, potential abnormal situations can be discovered, which supplements the deficiencies of variance analysis based only on voltage or current fluctuations, and improves the ability to detect abnormalities in the state of the monitoring point. It should be noted that the Pearson correlation coefficient method is a data analysis technique that can be mastered by technicians in this field, and will not be described here.

[0052] S214. Calculate the state fluctuation factor corresponding to the monitoring point in the time series according to the voltage fluctuation variance sequence, the current fluctuation variance sequence, the voltage-current anti-correlation sequence and their corresponding weight coefficients.

[0053] In this embodiment, according to the voltage fluctuation variance sequence , current fluctuation variance series , voltage and current anti-correlation sequence {r1, r2, ..., rn} and its corresponding weight coefficient , , (Assumption =0.4, , =0.3), calculate the state fluctuation factor fluctuation corresponding to the monitoring point in the time series: ; For example, at a certain time i, the voltage fluctuation variance =0.5, current fluctuation variance =0.3, voltage-current correlation coefficient ri=-0.8, then the state fluctuation factor at this moment fluctuates .

[0054] In this embodiment, the state fluctuation factor comprehensively considers the voltage fluctuation, current fluctuation and the correlation between them, and comprehensively quantifies the state fluctuation of the monitoring point. By adjusting the weight coefficient, the influence of different factors on the state fluctuation can be highlighted according to the actual situation. This factor can more accurately reflect the operating status of the monitoring point, provide a comprehensive quantitative indicator for judging whether there are potential hidden dangers at the monitoring point, and improve the accuracy and comprehensiveness of the status evaluation of the monitoring point.

[0055] As an optional embodiment, in S2, an impedance prediction model is constructed according to the path disturbance data to determine the environmental disturbance factor; Figure 4 As shown, the following steps are included: S221. Perform directed graph mapping on the potential danger path according to the line topology characteristics, and construct a node set and a directed edge set corresponding to the potential danger path; divide the potential danger path into unit grids according to the edge characteristics in the directed edge set, and obtain path disturbance data of each unit grid; the path disturbance data includes temperature field data, load fluctuation data, and zero-sequence current data.

[0056] In this embodiment, a certain hidden danger path is taken as an example, and a directed graph mapping is performed on it according to the line topology characteristics. Each connection point on the path is defined as a node, and a node set N={n1,n2,...,ns} is constructed; the line segments connecting the nodes are defined as directed edges, and a directed edge set E={e1,e2,...,et} is constructed. According to the length, material and other characteristics of the directed edges, the hidden danger path is divided into multiple unit grids, and the multi-dimensional path disturbance data of each unit grid is obtained, so as to realize the refined analysis of the hidden danger path. These disturbance data reflect the real-time operating conditions on the path from different physical quantity perspectives, provide rich input information for the subsequent construction of the impedance prediction model, and help to more accurately analyze the impact of environmental factors on line impedance, thereby improving the ability to identify potential hidden dangers.

[0057] S222. Construct a state equation of time-varying impedance based on the path disturbance data, and construct an observation equation based on Ohm's law; iterate the state equation and the observation equation through the Kalman filter algorithm to obtain the optimal time-varying impedance state equation and use it as the impedance prediction model.

[0058] Furthermore, the state equation is: ; The observation equation is: ; represents the impedance value of the line at the kth moment, is the impedance value of the line at the (k-1)th moment; is the temperature influence coefficient; is the temperature change at the kth moment relative to the reference moment, is the load influence factor; is the load change at the kth moment; is the zero-sequence interference coefficient; is the zero-sequence current phase difference at the kth moment; is the process noise; is the line voltage value measured at the kth moment; is the line current value measured at the kth moment; is the measurement noise.

[0059] In this embodiment, the impedance prediction model constructed comprehensively considers the influence of multiple factors such as temperature, load, zero-sequence current, etc. on line impedance, and optimizes the model through the Kalman filter algorithm so that it can more accurately predict the change of line impedance. The model can dynamically track the real-time changes of line impedance, provide a reliable basis for the subsequent analysis of the impact of environmental disturbances on the line, improve the ability to predict the operation status of the line, and help to discover potential impedance abnormalities in advance.

[0060] S223. Obtain the predicted impedance at each moment through the impedance prediction model, and use the difference between the predicted impedance and the measured impedance as the impedance prediction residual; use the principal component analysis method to perform characteristic decomposition on the impedance prediction residual to obtain the temperature disturbance component, the load disturbance component and the zero-sequence current disturbance component.

[0061] Furthermore, the constructed impedance prediction model is used to obtain the predicted impedance at each moment, and the difference between the predicted impedance and the measured impedance is taken as the impedance prediction residual; the impedance prediction residual is: ;in, is the impedance prediction residual; For the unit grid Environmental disturbance factors; is the temperature change at the kth moment relative to the reference moment; is the load change at the kth moment; is the zero-sequence current phase difference at the kth moment; , , They are temperature disturbance load factor, load disturbance load factor, and zero-sequence current disturbance load factor respectively; In this embodiment, by calculating the impedance prediction residual and using the principal component analysis method to perform characteristic decomposition on the impedance prediction residual, the influence of different factors on the impedance change can be separated. This helps to clarify whether factors such as temperature, load or zero-sequence current cause abnormal changes in impedance, provides detailed information for in-depth analysis of the impact of environmental disturbances on line impedance, improves the ability to analyze the causes of line impedance changes, and thus more accurately determines the source of potential hidden dangers.

[0062] S224. Calculate the environmental disturbance factor of each unit grid according to the temperature characteristic component, the load characteristic component, the zero-sequence current characteristic component and their corresponding standard deviations.

[0063] In this embodiment, the environmental disturbance factor of each grid unit is calculated based on the temperature characteristic component, the load characteristic component, and the zero-sequence current characteristic component and their corresponding standard deviations: ; For the unit grid Environmental disturbance factors; are the standard deviation of the temperature disturbance component, the standard deviation of the load disturbance component, and the standard deviation of the zero-sequence current disturbance component. For example, in a unit grid, the temperature disturbance load coefficient , the standard deviation of the temperature disturbance component ; Load disturbance load factor , standard deviation of load disturbance component ; Zero-sequence current disturbance load factor , standard deviation of zero-sequence current disturbance component , then the environmental disturbance factor of the unit grid is .

[0064] In this embodiment, the environmental disturbance factor comprehensively considers the disturbance degree of factors such as temperature, load, and zero-sequence current. By calculating the environmental disturbance factor, the comprehensive impact of environmental disturbance on each unit grid can be quantified. This provides a unified quantitative index for evaluating the degree of interference of environmental factors on the line at different locations, helps to determine the areas that are most affected by the environment, provides a clear direction for key monitoring and hidden danger investigation, and improves the ability to locate and evaluate potential hidden dangers.

[0065] S3. According to the state fluctuation factor and the environmental disturbance factor, the potential danger path is intensified to obtain the substation degradation map.

[0066] As an optional embodiment, Figure 5 As shown, S3 includes the following steps: S31. Perform Z-score standardization on the state fluctuation factor and the environmental disturbance factor to obtain the state fluctuation factor sequence and the environmental disturbance factor sequence belonging to the same hidden danger path.

[0067] In this embodiment, the state fluctuation factor sequence is assumed to be , environmental disturbance factor sequence The state fluctuation factor is standardized by Z-score to obtain , the environmental disturbance factor is standardized by Z-score to obtain Through Z-score standardization, the dimensional differences of state fluctuation factors and environmental disturbance factors are eliminated, making data of different magnitudes comparable. This ensures that in subsequent analysis, each factor can be comprehensively considered on a unified scale, avoiding the excessive or neglected impact of certain factors due to dimensional issues, and provides a basis for accurately analyzing the degradation of hidden danger paths.

[0068] S32, configuring a corresponding fluctuation trend factor for each state fluctuation factor in the state fluctuation factor sequence and configuring a corresponding disturbance trend factor for each environmental disturbance factor in the environmental disturbance factor sequence.

[0069] In this embodiment, the changing trend of the state fluctuation factor is determined by calculating the rate of change of the state fluctuation factor within adjacent unit time lengths. Similarly, the changing trend of the environmental disturbance factor is determined by calculating the rate of change of the environmental disturbance factor within adjacent unit time lengths. By configuring the fluctuation trend factor and the disturbance trend factor, a quantitative basis is provided for analyzing the dynamic changes of state fluctuations and environmental disturbances. These trend factors can capture the rate of change of factors over time and help discover potential trends of change, such as judging whether state fluctuations or environmental disturbances are gradually intensifying or tending to stabilize. This is of great significance for predicting future degradation trends of hidden danger paths, making the assessment of the status of substation equipment more forward-looking.

[0070] S33. Input the standardized state fluctuation factor, fluctuation trend factor, standardized environmental disturbance factor, disturbance trend factor, and fluctuation disturbance correlation coefficient into the degradation prediction model to obtain a degradation degree sequence corresponding to each hidden danger path.

[0071] As an optional embodiment, the degradation prediction model is constructed by a bidirectional LSTM model, with 5 input layers, and the state fluctuation factor, fluctuation trend factor, environmental disturbance factor, disturbance trend factor and fluctuation disturbance correlation coefficient are used as input parameters of the input layer; the hidden layer includes a forward LSTM layer and a backward LSTM layer; there is 1 output layer, which outputs the degradation degree sequence {D1, D2, ..., Dm} corresponding to each hidden danger path; the mean square error and trend penalty mechanism are used as loss functions; the AdamW optimizer is used to optimize the degradation prediction model and the root mean square error is used as the model evaluation reliability indicator.

[0072] In this embodiment, the fluctuation disturbance correlation coefficient Corr is obtained by calculating the correlation between the standardized state fluctuation factor sequence and the environmental disturbance factor sequence. The correlation calculation method belongs to the conventional technology mastered by the technicians in this field and will not be repeated; when training the model, the mean square error MSE (the mean square error between the actual degradation degree and the predicted degradation degree) and the trend penalty mechanism are used as the loss function, and the AdamW optimizer is used to optimize the model, and the model reliability is evaluated according to the root mean square error RMSE. This embodiment uses a bidirectional LSTM model with multi-feature input to predict the degradation degree sequence, and fully considers multiple factors such as state fluctuations, environmental disturbances, their changing trends and correlations. Through the learning and prediction of the model, it is possible to more accurately evaluate the changes in the degradation degree of each hidden danger path over time, which provides strong support for the subsequent formulation of targeted maintenance strategies and improves the accuracy and reliability of the prediction of the degradation state of the substation equipment.

[0073] S34. Combine the degradation degree sequence with the topological structure of the potential hazard path to obtain a degradation map of the substation area.

[0074] As an optional embodiment, combining the degradation degree sequence with the topological structure of the potential danger path to obtain a substation degradation map includes the following steps: S341, expanding the degradation degree sequence according to the timestamp and mapping it onto a directed graph according to the edge characteristics and node characteristics to form a degradation trajectory; S342, superimposing the degradation values ​​at different times on the degradation trajectory and obtaining a spatiotemporal heat map through graded color rendering; determining the degradation direction and degree in the spatiotemporal heat map through the direction and length of the arrow.

[0075] It can be understood that the degradation degree sequence {D1, D2, ..., Dm} is expanded by timestamp, assuming that the timestamp is t1, t2, ..., tm. The degradation degree is mapped to a directed graph according to edge characteristics (such as line length, material, etc.) and node characteristics (such as the number of devices connected to the node, importance, etc.). For example, if an edge connects two important nodes, and the degradation degree corresponding to the edge is higher at a certain moment, the corresponding degradation information is marked at the position of the edge on the directed graph to form a degradation trajectory. In S342, the degradation values ​​at different times on the degradation trajectory are superimposed. For example, the degradation value of a node at time t1 is D1, and at time t2 is D2. After superposition, the comprehensive degradation value D=D1+D2 of the node at these two moments is obtained. Through graded color rendering, such as dividing the degradation value into three levels of low, medium, and high, it can be represented by green, yellow, and red respectively. At the same time, the direction and length of the arrow are determined according to the direction and amplitude of the change in the degradation value. The direction of the arrow indicates the degradation trend (such as the direction from low degradation to high degradation), and the length indicates the amplitude of the change in the degree of degradation.

[0076] In this embodiment, the degradation degree sequence is combined with the topological structure of the hidden danger path to construct the substation degradation map, which displays the degradation of the substation equipment in an intuitive and visual way. Through the degradation trajectory, spatiotemporal heat map and arrow indication, the operation and maintenance personnel can quickly understand the distribution, change trend and development direction of the degradation degree at different locations in the substation, which is convenient for intuitively identifying high-risk areas, providing a clear basis for the reasonable arrangement of maintenance plans and the optimization of resource allocation, and improving the efficiency and pertinence of operation and maintenance management.

[0077] S4. Dynamically cut the degradation map of the substation area according to the hidden danger risk value corresponding to the monitoring point to determine the degraded block, and determine the corresponding early warning measures according to the degradation degree corresponding to the degraded block.

[0078] As an optional embodiment, S4 includes the following steps: S41. Obtain oxidation characteristics corresponding to the instantaneous drop event within the time window, and determine the oxidation risk value of each degradation trajectory according to the oxidation characteristics and their corresponding weight factors; wherein the oxidation characteristics include voltage difference, low voltage drop amplitude, theoretical electric group, and electric group change rate.

[0079] In this embodiment, oxidation characteristics are extracted for transient voltage drop events that occur in the substation within a specific time window (such as the past 24 hours). The voltage difference ΔV is the difference between the voltage before and after the transient voltage drop. The low voltage drop refers to the drop below the normal voltage (such as 220V). Theoretical resistance It is the ratio of the voltage difference to the current difference before and after the instantaneous drop event. is the ratio of the difference between the current power group and the power group in the same time window in history to the historical power group. Assume that the weight factors corresponding to the voltage difference, low voltage drop, theoretical resistance, and resistance change rate are g1, g2, g3, and g4 respectively (for example, g1=0.3, g2=0.2, g3=0.3, and g4=0.2). Assuming that in a certain instantaneous drop event, the voltage drops from 220V to 200V, the voltage difference ΔV = 20V, and the low voltage drop is 20V. If the current changes from 5A to 6A, the theoretical resistance .

[0080] This embodiment calculates the oxidation risk value by comprehensively considering the oxidation characteristics and their weight factors, and can quantify the degree of potential hidden dangers of the line due to oxidation. This quantification method integrates multiple electrical parameters related to oxidation, comprehensively reflects the impact of oxidation on the line state, and provides a comprehensive indicator for evaluating the potential oxidation risk of the substation line, making the evaluation of oxidation hazards more scientific and accurate.

[0081] S42, obtaining melting characteristics corresponding to the instantaneous drop event within the time window, and obtaining a melting risk value according to the melting characteristic criterion; the melting characteristics include instantaneous drop power, voltage-current anti-correlation, current continuity characteristics, and recovery period electrical parameter characteristics.

[0082] In this embodiment, the melting characteristics are also obtained for the instantaneous drop event within the time window. ,in It is the lowest current value during the voltage drop process. The voltage-current anti-correlation is measured by calculating the Pearson correlation coefficient CorrVI of voltage and current. When CorrVI is less than a certain threshold (such as -0.5), it is considered that there is a voltage-current anti-correlation. The current continuity characteristic refers to whether the current continues to maintain a certain level (such as I The recovery period electrical parameter characteristics include whether the voltage V and current I of multiple measuring points meet specific conditions (such as I ). Assuming a certain instantaneous drop event, ΔV=20V, , then the instantaneous power drop , the calculated CorrVI=-0.6, which satisfies the voltage-current anti-correlation condition. During the voltage recovery process, the current remained at 3.5A for 10 minutes ( ), meeting the current continuity characteristics. Within 24 hours after the instantaneous drop ends, the average current of multiple measuring points is I=5A (5A>1.2×4A), and the average voltage is V=210V ( , assuming ), meeting the electrical parameter characteristics of the recovery period. The melting characteristic criterion is set as when all the above melting characteristics are met, the melting risk value melts ;otherwise .

[0083] In this embodiment, the melting risk value is obtained based on the melting feature criterion, which can specifically identify the potential melting hazards caused by overheating in the line. Through the combined judgment of multiple key features, the detection accuracy of melting hazards is improved, and the misjudgment or missed judgment caused by single feature judgment is avoided, which provides an effective means for timely discovery and handling of melting hazards that may cause serious damage to the line.

[0084] S43. Determine the hidden danger risk value corresponding to the monitoring point according to the oxidation risk value and the melting risk value; form a multidimensional feature vector according to the hidden danger risk value corresponding to the monitoring point in the substation degradation map and the degradation degree sequence: dynamically cut the substation degradation map through the fuzzy C-means clustering method combined with the multidimensional feature vector to determine the degraded block.

[0085] In this embodiment, the hidden danger risk value corresponding to the monitoring point . Combine the hidden danger risk values ​​corresponding to the monitoring points in the substation degradation map with the previously obtained degradation degree sequence {D1, D2, ..., Dm} to form a multidimensional feature vector {Dtotal, D1, D2, ..., Dm}. The fuzzy C-means clustering method is a partition-based clustering algorithm. By continuously iteratively optimizing the objective function, the membership degree and cluster center are continuously updated, and the substation degradation map is finally dynamically cut into different degradation blocks. The fuzzy C-means clustering method belongs to the conventional technology mastered by technicians in this field and will not be described in detail.

[0086] In this embodiment, the oxidation risk value and the melting risk value are combined to obtain the hidden danger risk value corresponding to the monitoring point, and a multidimensional feature vector is constructed with the degradation degree sequence. The fuzzy C-means clustering method is used for dynamic cutting, which can automatically divide the substation into degraded blocks with similar characteristics according to the comprehensive risk and degradation degree of different areas. This division method takes into account multiple factors and can more reasonably reflect the actual risk status of different areas in the substation, providing a clear basis for regional division for subsequent targeted management and maintenance.

[0087] S44. Determine the degradation degree of the degraded block according to the degraded block division rule table; and determine corresponding early warning measures according to the degradation degree corresponding to the degraded block.

[0088] In this embodiment, the degradation degree of each degraded block is determined according to a pre-defined degraded block division rule table. For example, when the hidden danger risk value corresponding to the monitoring point of the degraded block is Greater than a high risk threshold (e.g. ) and the average degradation value in the degradation degree sequence exceeds a certain standard, it is judged as a high degradation degree; when In a certain medium risk range (such as ) and the degree of degradation is moderate, it is judged as medium degradation; when Less than a low risk threshold (e.g. And when the degree of degradation is low, it is determined to be a low degree of degradation.

[0089] Furthermore, corresponding early warning measures are formulated for different degrees of degradation. For example, for blocks with high degradation, immediate power outage and maintenance measures are taken; for blocks with medium degradation, recent key monitoring and pre-maintenance are arranged; for blocks with low degradation, regular inspections and status tracking are carried out.

[0090] In this embodiment, corresponding early warning measures are formulated according to the degree of degradation of the degraded blocks, realizing hierarchical management of hidden dangers in the substation area. This differentiated early warning strategy can reasonably allocate resources according to the severity of the risk, give priority to high-risk areas, and effectively avoid the occurrence or expansion of faults. At the same time, different management methods are adopted for areas with different risk levels, which improves the pertinence and efficiency of operation and maintenance management and ensures the stable operation of the substation area.

[0091] Embodiment 2: A technical solution also provided in the embodiment of the present invention is: a distribution station area abnormality positioning system, which is applicable to the distribution station area abnormality positioning method based on multi-modal dynamic feature analysis, such as Figure 6 As shown, including: Hidden danger preliminary judgment module 101: obtain multi-source fusion data of the substation area according to the sliding time window and determine the hidden danger path corresponding to the instantaneous drop event in combination with the line topology; The first determination module 102: performs a state fluctuation analysis on the real-time state data and historical state data of the monitoring point to determine a state fluctuation factor; The second determination module 103: constructs an impedance prediction model according to the path disturbance data to determine the environmental disturbance factor; Construction module 104: performing intensification processing on the hidden danger path according to the state fluctuation factor and the environmental disturbance factor to obtain a substation degradation map; Execution module 105: dynamically cut the degradation map of the substation area according to the hidden danger risk value corresponding to the monitoring point to determine the degraded block, and determine the corresponding early warning measures according to the degradation degree corresponding to the degraded block.

[0092] Embodiment 3: A technical solution also provided by the embodiment of the present invention is: an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the method for locating abnormalities in distribution station areas based on multimodal dynamic feature analysis are implemented.

[0093] Embodiment 4: A technical solution provided in the embodiment of the present invention is: a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the distribution station area abnormality positioning method based on multimodal dynamic feature analysis are implemented.

[0094] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the specific device can be divided into different functional modules to complete all or part of the functions described above.

[0095] In the embodiments provided in the present application, it should be understood that the disclosed structures and methods can be implemented in other ways. For example, the embodiments of the structure described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another structure, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, structures or units, which can be electrical, mechanical or other forms.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0097] In addition, each functional unit in the embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0099] The specific implementation described above is a preferred implementation of the distribution station area abnormality positioning method and system based on multimodal dynamic feature analysis of the present invention, and is not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to this specific implementation. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis, characterized in that: The following steps are involved: S1. Obtain multi-source fusion data of the substation area according to the sliding time window and determine the hidden danger path corresponding to the instantaneous drop event in combination with the line topology; S2. Perform state fluctuation analysis on the real-time state data and historical state data of the monitoring point to determine the state fluctuation factor, and build an impedance prediction model based on the path disturbance data to determine the environmental disturbance factor; S3, according to the state fluctuation factor and the environmental disturbance factor, the potential danger path is intensified to obtain the degradation map of the substation area; S4. Dynamically cut the degradation map of the substation area according to the hidden danger risk value corresponding to the monitoring point to determine the degraded block, and determine the corresponding early warning measures according to the degradation degree corresponding to the degraded block.

2. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 1 is characterized in that: The method of obtaining multi-source fusion data of the substation area according to the sliding time window and determining the hidden danger path corresponding to the instantaneous drop event in combination with the line topology comprises the following steps: S11, dynamically generate a sliding time window based on the response characteristics of the equipment in the substation area and the environmental noise coefficient; S12, the distributed acquisition terminal acquires the multi-source fusion data of the substation according to the sliding time window, wherein the multi-source fusion data of the substation includes at least voltage sag waveform data, harmonic distortion rate data, zero-sequence current phase difference data and temperature gradient data; S13, using spline interpolation and kernel density estimation to perform spatiotemporal alignment operations on the multi-source fusion data of the station area to obtain a preliminary data set; S14, screening the preliminary data set by impedance constraint and instantaneous drop event criterion and determining the candidate path set in combination with line topology coordinate mapping; S15. Determine the credibility of each candidate path according to the impedance change rate, node coupling degree, fault density and their corresponding weight coefficients; and take the candidate path with a credibility greater than a set threshold as a potential risk path.

3. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 1 is characterized in that: In S2, a state fluctuation analysis is performed based on the real-time state data and historical state data of the monitoring point to determine the state fluctuation factor, including the following steps: S211, acquiring voltage data and current data of the monitoring point according to the time series, performing Z-score standardization to obtain a real-time voltage series and a real-time current series; S212, comparing the real-time voltage sequence and the real-time current sequence with the historical state data in the same domain in sequence to obtain a voltage fluctuation variance sequence and a current fluctuation variance sequence; S213, based on the real-time voltage sequence and the real-time current sequence, calculate the voltage and current anti-correlation in sequence by using the Pearson correlation coefficient method to obtain a voltage and current anti-correlation sequence; S214. Calculate the state fluctuation factor corresponding to the monitoring point in the time series according to the voltage fluctuation variance sequence, the current fluctuation variance sequence, the voltage-current anti-correlation sequence and their corresponding weight coefficients.

4. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 1 is characterized in that: In S2, an impedance prediction model is constructed according to the path disturbance data to determine the environmental disturbance factor; the steps include: S221, mapping the hidden danger path into a directed graph according to the line topology characteristics, constructing a node set and a directed edge set corresponding to the hidden danger path; dividing the hidden danger path into unit grids according to the edge characteristics in the directed edge set, and obtaining path disturbance data of each unit grid; the path disturbance data includes temperature field data, load fluctuation data and zero-sequence current data; S222, constructing a state equation of time-varying impedance based on the path disturbance data, and constructing an observation equation based on Ohm's law; iteratively calculating the state equation and the observation equation through a Kalman filter algorithm to obtain an optimal time-varying impedance state equation and using it as an impedance prediction model; S223, obtaining the predicted impedance at each moment through the impedance prediction model, and taking the difference between the predicted impedance and the measured impedance as the impedance prediction residual; using the principal component analysis method to perform characteristic decomposition on the impedance prediction residual to obtain a temperature disturbance component, a load disturbance component, and a zero-sequence current disturbance component; S224. Calculate the environmental disturbance factor of each unit grid according to the temperature characteristic component, the load characteristic component, the zero-sequence current characteristic component and their corresponding standard deviations.

5. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 4 is characterized in that: The state equation is: ; The observation equation is: ; represents the impedance value of the line at the kth moment, is the impedance value of the line at the (k-1)th moment; is the temperature influence coefficient; is the temperature change at the kth moment relative to the reference moment, is the load influence factor; is the load change at the kth moment; is the zero-sequence interference coefficient; is the zero-sequence current phase difference at the kth moment; is the process noise; is the line voltage value measured at the kth moment; is the line current value measured at the kth moment; is the measurement noise.

6. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 4 is characterized in that: Impedance prediction residuals: ; Environmental disturbance factors: ; in, is the impedance prediction residual; For the unit grid Environmental disturbance factors; is the temperature change at the kth moment relative to the reference moment; is the load change at the kth moment; is the zero-sequence current phase difference at the kth moment; , , They are temperature disturbance load factor, load disturbance load factor, and zero-sequence current disturbance load factor respectively; They are the standard deviation of the temperature disturbance component, the standard deviation of the load disturbance component and the standard deviation of the zero-sequence current disturbance component respectively.

7. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 1 is characterized in that: The method of performing an intensification process on the hidden danger path according to the state fluctuation factor and the environmental disturbance factor to obtain a station area degradation map comprises the following steps: S31. Perform Z-score standardization on the state fluctuation factor and the environmental disturbance factor to obtain a state fluctuation factor sequence and an environmental disturbance factor sequence belonging to the same hidden danger path; S32, configuring a corresponding fluctuation trend factor for each state fluctuation factor in the state fluctuation factor sequence and configuring a corresponding disturbance trend factor for each environmental disturbance factor in the environmental disturbance factor sequence; S33, inputting the standardized state fluctuation factor, fluctuation trend factor, standardized environmental disturbance factor, disturbance trend factor, and fluctuation disturbance correlation coefficient into the degradation prediction model to obtain a degradation degree sequence corresponding to each hidden danger path; S34. Combine the degradation degree sequence with the topological structure of the potential hazard path to obtain a degradation map of the substation area.

8. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 7 is characterized in that: The degradation prediction model is constructed by a bidirectional LSTM model, and has 5 input layers, with state fluctuation factor, fluctuation trend factor, environmental disturbance factor, disturbance trend factor and fluctuation disturbance correlation coefficient as input parameters of the input layer; The hidden layer includes a forward LSTM layer and a backward LSTM layer; there is one output layer; The mean square error and trend penalty mechanism are used as loss functions; the AdamW optimizer is used to optimize the degradation prediction model and the root mean square error is used as the reliability indicator for model evaluation.

9. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 1, characterized in that: Combining the degradation degree sequence with the topological structure of the potential hazard path to obtain the degradation map of the substation area includes the following steps: S341, expanding the degradation degree sequence according to the timestamp and mapping it onto a directed graph according to the edge characteristics and node characteristics to form a degradation trajectory; S342, superimposing the degradation values ​​at different times on the degradation trajectory and obtaining a spatiotemporal heat map through graded color rendering; determining the degradation direction and degree in the spatiotemporal heat map through the direction and length of the arrow.

10. The method for locating abnormalities in distribution station areas based on multi-modal dynamic feature analysis according to claim 1, characterized in that: S4. Dynamically cut the degradation map of the substation area according to the risk value of hidden dangers corresponding to the monitoring point to determine the degradation block, and determine the corresponding early warning measures according to the degree of degradation corresponding to the degradation block; including the following steps: S41, obtaining oxidation characteristics corresponding to the instantaneous drop event within the time window, and determining the oxidation risk value of each degradation trajectory according to the oxidation characteristics and the corresponding weight factors; S42, obtaining melting characteristics corresponding to the instantaneous drop event within the time window, and obtaining a melting risk value according to a melting characteristic criterion; S43, determining the hidden danger risk value corresponding to the monitoring point according to the oxidation risk value and the melting risk value; A multidimensional feature vector is formed based on the hidden danger risk value and degradation degree sequence corresponding to the monitoring points in the degradation map of the substation area: the degradation block is determined by dynamically cutting the degradation map of the substation area through the fuzzy C-means clustering method combined with the multidimensional feature vector; S44, determining the degradation degree of the degraded block according to the degraded block division rule table; Determine the corresponding early warning measures according to the degree of degradation of the degraded block.

11. A distribution station area abnormality locating system, applicable to the distribution station area abnormality locating method based on multi-modal dynamic feature analysis as claimed in any one of claims 1 to 10, characterized in that: include: Hidden danger preliminary judgment module: obtain multi-source fusion data of the substation area according to the sliding time window and determine the hidden danger path corresponding to the instantaneous drop event in combination with the line topology; The first determination module: performs state fluctuation analysis based on the real-time state data and historical state data of the monitoring point to determine the state fluctuation factor; The second determination module: constructs an impedance prediction model based on the path disturbance data to determine the environmental disturbance factor; Construction module: According to the state fluctuation factor and environmental disturbance factor, the potential danger path is intensified to obtain the degradation map of the substation area; Execution module: Dynamically cut the degradation map of the substation to determine the degraded blocks through the hidden danger risk values ​​corresponding to the monitoring points, and determine the corresponding early warning measures according to the degree of degradation corresponding to the degraded blocks.

12. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, it implements the steps of the method for locating abnormalities in distribution station areas based on multimodal dynamic feature analysis as described in any one of claims 1 to 10.

13. A storage medium, characterized in that: The storage medium stores computer executable instructions, which, when loaded and executed by the processor, implement the steps of the method for locating abnormalities in distribution station areas based on multimodal dynamic feature analysis as described in any one of claims 1 to 10.

Images