Inspection management method for power distribution network

Abstract

The invention relates to the technical field of data processing, and discloses an inspection management method for a power distribution network, which is used for improving the inspection management efficiency of the power distribution network. The method comprises the following steps: collecting and preprocessing multi-source data of a plurality of distribution network inspection nodes of a distribution network to obtain de-noised multi-dimensional image data; performing feature extraction processing on the multi-dimensional image data to obtain equipment abnormal feature data of a plurality of distribution network inspection nodes; performing data fusion processing on the equipment anomaly feature data of the plurality of distribution network inspection nodes to obtain time-space associated equipment anomaly comprehensive data; performing continuous analysis processing on the equipment abnormal comprehensive data through a space-time tracking algorithm to obtain equipment abnormal space-time change data; performing intelligent positioning processing on the equipment abnormal spatial-temporal change data to obtain equipment fault spatial coordinate data; and performing anomaly level evaluation processing on the equipment fault space coordinate data based on a priority ranking algorithm to obtain equipment anomaly priority information.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a patrol inspection management method for a distribution network. Background Art

[0002] In the operation and management of modern distribution networks, inspection is increasingly valued as an important part of ensuring the normal operation of power equipment. Existing technologies usually use regular manual inspections and basic automatic monitoring methods to evaluate the status and detect faults of equipment in distribution networks. These methods collect the operating data and image information of the equipment, rely on traditional image processing technology and simple feature extraction algorithms to detect abnormalities in the equipment. However, with the increase in the types and number of distribution network equipment, traditional manual inspection methods are inefficient and prone to missing problems, and cannot reflect the status of equipment in a timely and comprehensive manner.

[0003] Although the existing technology has improved the inspection efficiency of the distribution network to a certain extent, there are still many shortcomings. On the one hand, the traditional image processing algorithm is sensitive to image noise in complex environments, resulting in poor image data processing effects and difficulty in accurately extracting equipment features. On the other hand, the existing anomaly detection methods lack intelligence and automation, cannot respond to the dynamic changes of equipment failures in real time, and cannot provide effective decision support. This makes the location and evaluation of equipment failures have a certain lag, affecting the safe and stable operation of the distribution network. Therefore, there is an urgent need for a more intelligent and efficient inspection management method to solve the many problems existing in the existing technology. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a distribution network inspection management method for improving the efficiency of the distribution network inspection management.

[0005] The present invention provides a distribution network inspection management method, comprising: In the technical solution provided by the present invention, multi-source data collection and denoising processing are adopted, which can effectively filter out environmental interference and equipment noise, and ensure the quality of the original data obtained. Secondly, feature extraction through image recognition algorithm can deeply explore the potential abnormal features of the equipment, not only can the minor faults of the equipment be identified in time, but also the feature library can be gradually improved through learning of historical data to realize the recognition ability of new faults. Furthermore, through data fusion processing, the equipment feature data of multiple inspection nodes are integrated to generate time-space related equipment abnormal comprehensive data. This process can effectively capture the change trend of the equipment in time and space, and thus improve the overall understanding of the overall state of the equipment. In addition, the continuous analysis and processing of the equipment abnormal comprehensive data combined with the time-space tracking algorithm makes it possible to monitor the state changes of the equipment within a long time range, provide strong data support for fault prediction, and is particularly suitable for high-risk and complex power distribution environments. It can effectively reduce the risk of power outages caused by equipment failures. This efficient fault location capability greatly reduces the workload of manual inspections and improves inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0007] Figure 1 The present invention is a flowchart of a method for managing inspection of a distribution network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0008] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0009] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0010] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0011] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , Figure 1 is a flow chart of a distribution network inspection management method according to an embodiment of the present invention, such as Figure 1 As shown, the following steps are included: S101, collecting and preprocessing multi-source data of multiple distribution network inspection nodes to obtain multi-dimensional image data after denoising; S102, performing feature extraction processing on the multi-dimensional image data by using an image recognition algorithm to obtain device abnormality feature data of multiple distribution network inspection nodes; S103, performing data fusion processing on the equipment abnormality feature data of multiple distribution network inspection nodes to obtain time-space related equipment abnormality comprehensive data; S104, continuously analyzing and processing the equipment abnormality comprehensive data through a spatiotemporal tracking algorithm to obtain equipment abnormality spatiotemporal variation data; S105, performing intelligent positioning processing on the abnormal spatiotemporal change data of the equipment to obtain the spatial coordinate data of the equipment failure; S106. Perform abnormality level evaluation processing on the spatial coordinate data of the equipment fault based on a priority sorting algorithm to obtain equipment abnormality priority information.

[0012] It should be noted that the multi-source data of multiple distribution network inspection nodes are first collected and preprocessed to obtain multi-dimensional image data after denoising. Multi-source data includes monitoring data from different sensors, such as video surveillance, infrared imaging, and temperature sensors. These data will be uniformly formatted to ensure their consistency. For example, the original image collected by the image acquisition device may contain high-frequency noise. To this end, the original image is first denoised, and the wavelet transform method is used to separate the signal and noise through multi-scale decomposition. Specifically, the image is decomposed into different frequency bands, and the low-frequency part is maintained, while the high-frequency noise is suppressed to obtain multi-dimensional image data after denoising. Then, the multi-dimensional image data is feature extracted using an image recognition algorithm to extract the abnormal feature data of the equipment of multiple distribution network inspection nodes. Image recognition algorithms such as convolutional neural networks (CNNs) can automatically extract important features in images. The trained model can identify different states of the equipment and extract key features of the equipment from the denoised image, such as abnormal features such as cracks and deformation. The process involves region segmentation, which divides the image into sections to be analyzed separately, and then classifying and identifying the features of each region. For example, for an image of an electrical box, the algorithm might detect whether the door is properly closed or whether there are obvious signs of corrosion or aging.

[0013] After data fusion processing of the equipment abnormality feature data of multiple distribution network inspection nodes, the spatiotemporally correlated equipment abnormality comprehensive data can be obtained. This process involves integrating data obtained at different times and spaces. A weighted fusion algorithm is usually used to weight the importance and abnormality of each node to ensure that key data dominates the comprehensive results. Specifically, assuming that the abnormality of a node is evaluated as 0.8 and another node is 0.5, the comprehensive data will be synthesized according to these weights to obtain more representative abnormal comprehensive data. For example, if the temperatures of two nodes are 80°C and 75°C respectively, the fused data may be displayed as 78°C, and the abnormal conditions of the two nodes are indicated. Through the spatiotemporal tracking algorithm, the equipment abnormality comprehensive data can be continuously analyzed and processed to obtain the equipment abnormality spatiotemporal change data. This algorithm uses time series analysis to identify abnormal change trends, such as continuously rising temperatures or frequent equipment failures. For data analysis, sliding window technology can be applied to regularly update the equipment status to more accurately reflect the real-time situation of the equipment. For example, if the operating temperature of a device has been rising every day over the past week and the change exceeds the set threshold, this indicates that there may be a potential failure.

[0014] After completing the intelligent positioning processing of the equipment abnormal spatiotemporal change data, the spatial coordinate data of the equipment fault can be obtained. This process involves using a spatial positioning algorithm to infer the actual fault location of the equipment based on the processed abnormal data. By comparing historical fault records and combining current abnormal data, the specific location where the fault occurred can be located, such as a module in the distribution box. For example, by analyzing the temperature changes and load conditions before and after the fault, the system may derive the fault location of a module. Finally, based on the priority sorting algorithm, the equipment fault spatial coordinate data is evaluated for abnormal level, thereby obtaining the equipment abnormality priority information. In this step, the algorithm considers the importance of the equipment, the severity of the fault, and the possible impact on the overall distribution network, and comprehensively evaluates the priority of each fault. Assuming that there are three devices with faults, their importance scores are 0.9, 0.7 and 0.5, and the fault impact scores are 0.8, 0.4 and 0.6 respectively. After weighted sorting, the highest priority fault will be determined so that the operation and maintenance team can handle it quickly.

[0015] By executing the above steps, multi-source data acquisition and denoising processing can effectively filter out environmental interference and equipment noise, ensuring the quality of the original data obtained. Secondly, feature extraction through image recognition algorithm can deeply explore the potential abnormal characteristics of the equipment, not only can timely identify the minor faults of the equipment, but also gradually improve the feature library through learning historical data, and realize the recognition ability of new faults. Furthermore, through data fusion processing, the equipment feature data of multiple inspection nodes are integrated to generate time-space related equipment abnormal comprehensive data. This process can effectively capture the change trend of the equipment in time and space, and thus improve the overall understanding of the overall status of the equipment. In addition, the continuous analysis and processing of the equipment abnormal comprehensive data combined with the time-space tracking algorithm makes it possible to monitor the state changes of the equipment over a long period of time, providing strong data support for fault prediction, especially suitable for high-risk and complex power distribution environments, and can effectively reduce the risk of power outages caused by equipment failures. This efficient fault location capability greatly reduces the workload of manual inspections and improves inspection efficiency.

[0016] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Perform data acquisition and processing on multi-source data of multiple distribution network inspection nodes to obtain original image data, and perform format conversion processing on the original image data to obtain image data in a unified format; (2) graying the image data in a unified format to obtain grayscale image data, and normalizing the grayscale image data to obtain standardized image data; (3) De-noising the standardized image data by using a wavelet transform algorithm to obtain denoised image data, and performing edge smoothing on the denoised image data to obtain smoothed image data; (4) Performing feature enhancement processing on the smoothed image data to obtain enhanced feature image data, and performing image reconstruction processing on the enhanced feature image data to obtain multi-dimensional image data after denoising processing.

[0017] Specifically, firstly, data acquisition and processing are performed on multi-source data of multiple distribution network inspection nodes to obtain raw image data. These data can come from different types of sensors, such as surveillance cameras, infrared imaging devices, and temperature sensors, covering the visual information and thermal imaging data of the equipment. In the process of data acquisition, by setting a reasonable sampling frequency and resolution, it is ensured that the key status information of the equipment can be captured. For example, the surveillance camera shoots at a rate of 30 frames per second, and the image data obtained constitutes a rich raw image data set. Then, the raw image data is format converted to obtain image data in a unified format. The key to this step is to convert images from different sensors into a consistent file format, such as JPEG or PNG, for subsequent processing. In this process, all images are adjusted to a uniform size and color depth using image processing tools to ensure that each image works within the same processing framework. This format unification is helpful for subsequent data processing and feature extraction.

[0018] The image data in a unified format will then be grayscaled to obtain grayscale image data. Grayscale is the process of converting a color image into a black and white image. Usually, the weighted average method is used to convert each pixel value in the RGB color space into a grayscale value through a formula. Specifically, the grayscale value can be calculated by the following formula: ; in, Represents the gray value, , and are the color values ​​of red, green, and blue, respectively. Through grayscale processing, image information becomes simpler and is convenient for subsequent analysis. Subsequently, the grayscale image data is normalized to obtain standardized image data. The purpose of normalization is to map the grayscale value range to [0, 1] to avoid image analysis errors caused by changes in illumination. Through normalization, standardized image data can eliminate the impact of illumination changes on subsequent processing, making feature extraction more accurate. Then, the standardized image data is denoised by the wavelet transform algorithm to obtain denoised image data. Wavelet transform is a signal processing technology that can effectively separate signals from noise. Specifically, the image data is first decomposed by wavelet to obtain different frequency components. Then, through thresholding processing, high-frequency components below the set threshold are removed, and the main low-frequency information is retained. In this way, the denoised image data can retain key information while removing useless noise and improving the clarity of the image.

[0019] After denoising, the denoised image data is further smoothed to obtain smoothed image data. Edge smoothing usually uses filtering techniques such as Gaussian blur to reduce the edge noise of the image by performing weighted averaging on each pixel and its neighborhood. For example, using a 3×3 Gaussian filter, the following weighting coefficients can be used for calculation: ; Through this method, the image smoothing effect is significant, which can eliminate noise in a small range and improve the accuracy of subsequent feature extraction. Then, the smoothed image data is subjected to feature enhancement processing to obtain enhanced feature image data. The purpose of feature enhancement is to make the important features of the device more prominent by adjusting the contrast or applying an image enhancement algorithm. This step can use the histogram equalization method to improve the visibility of weak features in the image by adjusting the contrast distribution of the image. For example, after enhancement processing, the fault features (such as cracks) of some equipment may be significantly highlighted, making it easier to identify. Finally, the enhanced feature image data is subjected to image reconstruction processing to obtain multidimensional image data after denoising. The image reconstruction process reconstructs the processed data into a higher quality image through inverse wavelet transform. This process not only retains the information after denoising and feature enhancement, but also ensures the integrity and accuracy of the image. By synthesizing each frequency component, the multidimensional image data finally output can clearly show the status of the distribution network inspection node, thus laying the foundation for subsequent anomaly detection and analysis.

[0020] For example, in actual applications, after the above processing steps, the standard deviation of the image data of a distribution node before denoising is 20, and after wavelet transform denoising, the standard deviation is reduced to 5, which shows that the noise is significantly reduced and the image quality is significantly improved. Through these data processing methods, the inspection efficiency of the distribution network has been effectively improved, and equipment faults can be identified and handled more timely and accurately.

[0021] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) performing feature preprocessing on the multidimensional image data to obtain processed image data, and performing feature enhancement processing on the processed image data to obtain enhanced image feature data; (2) performing region segmentation processing on the enhanced image feature data to obtain segmented feature region data, and performing shape description processing on the segmented feature region data to obtain shape feature data; (3) Perform feature extraction on the shape feature data through a convolutional neural network to obtain a preliminary feature set, and perform feature selection on the preliminary feature set to obtain an optimized feature set; (4) Performing abnormal pattern recognition processing on the optimized feature set to obtain equipment abnormal pattern data, and classifying the equipment abnormal pattern data to obtain classified feature data; (5) Perform abnormal feature identification processing on the classified feature data to obtain equipment abnormal feature data of multiple distribution network inspection nodes.

[0022] Specifically, the multidimensional image data is subjected to noise filtering and information extraction to obtain processed image data. This process includes applying a smoothing algorithm, such as a Gaussian filter, which reduces random noise in the image by weighted averaging surrounding pixel values. In a specific implementation, if the signal-to-noise ratio of the original image data is 5 dB, after Gaussian filtering, the signal-to-noise ratio is increased to 15 dB, indicating that the noise interference has been effectively reduced and the image quality has been improved. After feature preprocessing, feature enhancement processing is performed to highlight important features and make them more obvious in subsequent analysis. This process can be achieved through contrast enhancement and edge enhancement techniques. For example, through histogram equalization technology, the grayscale distribution of the image is made more uniform, thereby enhancing the contrast of the image. The contrast enhancement factor is set to 2, which means that the contrast between the brightest and darkest parts of the image is doubled. The enhanced image feature data can more clearly display the fault characteristics of the distribution equipment, such as cracks or deformation.

[0023] Subsequently, the image data after feature enhancement processing will be processed for regional segmentation to obtain the segmented feature region data. The regional segmentation technology uses the threshold segmentation method to divide the image into foreground and background according to the signal strength (such as grayscale value). The threshold is set to 120, and all pixels above this value are marked as foreground to extract key information. After segmentation, if the foreground area obtained is 30, it indicates that the key features in the device are effectively separated, providing a clear data basis for subsequent analysis. After obtaining the segmented feature region data, shape description processing is performed to obtain shape feature data. Shape description usually includes methods such as boundary extraction, shape moment and Fourier descriptor, through which the shape information of the device features can be accurately captured. The shape index indicates that the shape of the area is close to a circle, which is convenient for feature matching in subsequent abnormal pattern recognition.

[0024] The shape feature data is processed by feature extraction using a convolutional neural network (CNN) to obtain a preliminary feature set. CNN is suitable for processing image data due to its good feature extraction capabilities. In this process, the low-level features of the image (such as edges and textures) are gradually converted into high-level features (such as the shape and structure of the object) through the combination of multiple convolutional layers and pooling layers. The preliminary feature set will contain multi-dimensional information, such as edge features and texture features of the shape. The preliminary feature set is processed by feature selection to obtain an optimized feature set. The purpose of feature selection is to filter out the features that have the greatest impact on the classification results from the preliminary feature set. Commonly used methods include principal component analysis (PCA) and LASSO regression. Through feature selection, the optimized feature set may be reduced from the initial 100 features to 30. This process not only reduces the complexity of data processing, but also improves the accuracy of subsequent analysis. Then, the optimized feature set is processed by abnormal pattern recognition to obtain device abnormal pattern data. Abnormal pattern recognition uses classification algorithms, such as support vector machines (SVM) or random forests, which can effectively distinguish between normal and abnormal patterns. After training, if 8 different abnormal modes can be identified, including overheating, short circuit, etc., it can provide a reliable basis for subsequent fault diagnosis.

[0025] The equipment abnormal pattern data is classified and processed to obtain classification feature data. The classification process usually adopts a multi-class classification algorithm. By learning the training data, the model maps each input feature to a specific category. For example, if the classification result shows that a certain distribution node has a 60% probability of short circuit risk, this node needs to be paid special attention during the inspection. Finally, the classification feature data is processed for abnormal feature identification to obtain the equipment abnormal feature data of multiple distribution network inspection nodes. In the identification process, based on the classification results, the status of each node is marked to form an abnormal feature data set. This data set contains the status information and potential fault types of each node, which provides an important basis for subsequent operation and maintenance decisions. For example, if a node is identified as a short circuit risk, the operation and maintenance personnel can immediately arrange maintenance to reduce the risk of accidents.

[0026] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Normalize the abnormal feature data of the equipment at multiple distribution network inspection nodes to obtain normalized feature data, and perform outlier detection on the normalized feature data to identify and eliminate outliers to obtain valid feature data; (2) Perform time series labeling on the effective feature data to obtain feature data with timestamps, and perform spatial coordinate mapping on the feature data with timestamps to obtain spatiotemporal mapping feature data; (3) Perform multi-dimensional data fusion processing on the spatiotemporal mapping feature data through a weighted fusion algorithm to obtain a fused feature set, and perform clustering processing on the fused feature set based on similarity analysis to obtain cluster feature data; (4) Performing principal component analysis on the clustering feature data to extract key principal components to obtain principal component feature data, and performing time series correlation analysis on the principal component feature data to obtain time series correlation feature data; (5) Perform multi-dimensional data visualization processing on the time series correlation feature data to obtain visualization results, and perform interactive analysis on the visualization results to obtain comprehensive equipment anomaly data with temporal and spatial correlation.

[0027] Specifically, normalizing the abnormal feature data of equipment at multiple inspection nodes is a key step to ensure data consistency and comparability. The goal of normalization is to convert feature data of different dimensions and ranges into the same scale. This process ensures that the feature data is within the range of [0, 1], which is convenient for subsequent analysis and comparison. After completing the normalization process, the next step is to perform outlier detection on the normalized feature data. Common outlier detection methods include the Z-score method and the IQR method (interquartile range method). Using the Z-score method, the Z-score of each data point is calculated, and the formula is: Through this method, if the Z-score of a temperature data point of 65 degrees Celsius at a certain node is detected to be 4, then this data will be identified as an outlier and eliminated. After outlier detection, the effective feature data obtained will be more accurate and reliable, which is conducive to subsequent analysis.

[0028] After the effective feature data is processed, the time series annotation process is performed. This step is achieved by adding a timestamp to each data point, which provides contextual information about the data changes over time. For example, if the temperature data point of 65 degrees Celsius is at 12:00 on September 30, 2024, the feature data obtained after annotation is (65, 2024-09-30 12:00). This form of time series data will facilitate subsequent time series analysis and visualization. After the time series data is annotated, the next step is to perform spatial coordinate mapping on the feature data with timestamps. This process visualizes the spatial distribution of data by associating each data point with the corresponding spatial coordinates (such as longitude and latitude). For example, combining the data point (65, 2024-09-30 12:00) with the coordinates (37.7749°N, 122.4194°W) yields the mapped feature data ((65,2024-09-30 12:00), (37.7749, -122.4194)). This processing combines the temporal and spatial features of the data, which helps in the subsequent analysis of the performance of the device at different times and locations.

[0029] The weighted fusion algorithm is used to perform multi-dimensional data fusion processing on the spatiotemporal mapping feature data to generate a fusion feature set. The weighted fusion algorithm gives different weights to each feature data to make full use of the advantages of each type of data. The weight of the temperature feature is set to 0.6, and the weight of the humidity feature is set to 0.4. The fusion feature can be calculated using the following formula: ; in, is the temperature characteristic, is the humidity characteristic, and is the corresponding weight. If the temperature at a certain moment is 65 degrees Celsius and the humidity is 70%, the fusion feature is: ; The fused feature set will provide a more comprehensive perspective for subsequent cluster analysis. Then, the fused feature set is clustered based on similarity analysis. Use a clustering algorithm (such as the K-means algorithm) to group similar features together. The K value is set to 3. If the clustering results show that the feature set is divided into three categories, representing different equipment states, it can provide more targeted analysis for equipment fault diagnosis.

[0030] Perform principal component analysis (PCA) on the cluster feature data to extract key principal components to obtain principal component feature data. PCA transforms the original feature data into a new feature space through linear transformation, reducing the dimension while retaining the main features of the data. The number of principal components is set to 2. If the original data is 4-dimensional, the principal component data will be 2-dimensional after PCA conversion. This principal component feature data provides key information to help understand the overall operating status of the equipment.

[0031] Finally, the time series correlation analysis is performed on the principal component feature data to obtain the time series correlation feature data. This step identifies potential trends and periodic patterns by analyzing the relationship between the principal component features at different time points. If the analysis results show that a certain feature appears frequently in a specific time period, this will help the operation and maintenance personnel identify the potential risk of equipment abnormalities. After all processing is completed, multidimensional data visualization is performed, and the analysis results are presented in a graphical manner to obtain visualization results. This visualization effect helps the operation and maintenance personnel to intuitively understand the operating status and abnormal conditions of the equipment, which facilitates subsequent decision-making. At the same time, interactive analysis is carried out so that users can freely explore and analyze data as needed, thereby obtaining comprehensive data on equipment abnormalities that are temporally and spatially correlated. Through the above methods, the distribution network inspection management method can effectively improve the detection and analysis capabilities of equipment abnormalities and ensure the stable and safe operation of the distribution network.

[0032] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Performing time series reorganization processing on the equipment abnormality comprehensive data to obtain reorganized time series data, and performing data smoothing processing on the reorganized time series data to obtain smoothed time series data; (2) Perform trend analysis on the smoothed time series data to identify long-term trends and seasonal fluctuations, obtain trend feature data, and conduct timeliness assessment on the trend feature data to determine the timeliness assessment results; (3) Dynamically track the timeliness evaluation results through the spatiotemporal tracking algorithm to obtain dynamic change feature data, and perform abnormal pattern recognition on the dynamic change feature data to identify potential abnormal patterns; (4) Perform spatial clustering analysis on potential abnormal patterns to obtain clustering results, and perform adjacent node association analysis on the clustering results to identify the association between nodes and obtain association feature data; (5) Perform multi-dimensional visualization of the associated feature data, combine the time axis and spatial distribution, and obtain the abnormal spatiotemporal change data of the equipment.

[0033] Specifically, by reorganizing the equipment abnormality comprehensive data in time series, the abnormal status of the equipment at each time point can be rearranged in chronological order to form a set of continuous time series data. This process helps capture the performance of the equipment in different time periods and provides a more systematic perspective. After obtaining the original data, the data smoothing technology is used to remove short-term random fluctuations to obtain smoothed time series data, which lays the foundation for trend analysis. After the smoothed time series data is processed, long-term trends and seasonal fluctuations can be identified. By analyzing these data, it is possible to determine the operating status of the equipment over a long period of time. For example, it is found that the temperature of a certain equipment generally shows an upward trend within a year, and in certain seasons, such as summer, the temperature fluctuation is aggravated. This analysis not only provides a historical background for the equipment status, but also provides a reference for future maintenance.

[0034] After obtaining the trend characteristic data, the timeliness assessment process is to determine whether the data is reliable. This step usually includes an assessment of the integrity and consistency of the data to confirm that the data used in the analysis does reflect the true status of the equipment. If the data is continuous and there is no obvious missing, it can be judged as valid data, which is crucial for subsequent dynamic tracking processing. The timeliness assessment results are dynamically tracked through the spatiotemporal tracking algorithm to obtain dynamic characteristic data of equipment status changes. This algorithm can combine time series and spatial information to monitor changes in the operating status of the equipment in real time. If the temperature of a certain device is found to continue to rise over a period of time, and it shows anomalies when compared with historical data, potential equipment problems can be quickly identified and timely measures can be taken.

[0035] Then, the identified potential abnormal patterns will enter the spatial cluster analysis stage. Cluster analysis can help find the similarities between different devices, thereby revealing potential correlations. In this process, the distance and similarity between adjacent nodes are used to determine the degree of influence between devices. For example, if a device abnormally heats up, the temperature of the adjacent device also rises accordingly, and there may be a certain correlation between the two. By analyzing these associated feature data, it is possible to determine which devices may affect each other during operation and adjust the inspection strategy in time. Finally, the associated feature data is visualized in multiple dimensions, combined with the time axis and spatial distribution information, to form an intuitive representation of the abnormal spatiotemporal change data of the equipment. This display method enables inspection personnel to quickly identify the abnormal situation of the equipment and improves the efficiency of decision-making. Through visualization methods such as heat maps and time series diagrams, the abnormal status of different devices in a specific time period is clearly displayed, which assists decision makers in determining the equipment that needs to be processed first and ensures the safe operation of the distribution network.

[0036] For example, suppose that during a month-long monitoring of a group of equipment, the smoothed temperature series shows a clear upward trend. After analysis, it is found that the temperature of a certain device exceeds the preset safety threshold during a specific period of time. Through the spatiotemporal tracking algorithm, it is found that before the abnormality of the device occurs, the temperature of its adjacent devices also rises accordingly. This indicates that there may be a certain correlation between the devices. Based on the results of cluster analysis, the inspection team decides to give priority to the inspection and maintenance of this group of equipment, thereby effectively preventing possible failures.

[0037] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Perform coordinate system conversion processing on the abnormal spatiotemporal change data of the equipment to obtain converted spatiotemporal data, and perform feature calibration processing on the converted spatiotemporal data to obtain calibrated feature data; (2) Performing position inference processing on the calibration feature data through a machine learning-based spatial positioning algorithm to obtain inferred spatial coordinate data, and performing reliability assessment on the inferred spatial coordinate data to screen out valid coordinates; (3) Perform spatial clustering on the valid coordinates to identify the fault hotspot area, obtain the hotspot coordinate data, and perform density analysis on the hotspot coordinate data to determine the dense area where the fault occurs; (4) Based on historical fault data, fuzzy logic processing is performed on dense areas to obtain fuzzy decision feature data, and the fuzzy decision feature data is precisely positioned to obtain the spatial coordinate data of equipment faults.

[0038] Specifically, it is crucial to perform coordinate system conversion processing on the abnormal spatiotemporal change data of the equipment. This process aims to standardize the data under different coordinate systems and obtain the converted spatiotemporal data. This conversion usually requires reference to the geographical location and spatial layout of the equipment so that data from different sources can be analyzed in the same coordinate system. After completing the coordinate system conversion, feature calibration processing is performed, which is the process of accurately identifying the characteristic attributes of the equipment to obtain calibrated feature data. The calibrated feature data integrates information such as the operating parameters and historical fault records of the equipment to make it comparable and analyzable, laying the foundation for subsequent data processing. Based on the calibrated feature data, a spatial positioning algorithm based on machine learning is applied for position inference processing. This algorithm uses known calibration feature data to infer the actual spatial coordinate data of the equipment by analyzing the relationship between the data. In the inference process, multi-dimensional information such as the working status of the equipment, the surrounding environment, and historical fault data is usually combined to improve the accuracy of the inference. After completing the position inference, reliability assessment is necessary. By setting thresholds and standards, valid coordinates are screened out to ensure the accuracy and reliability of subsequent analysis. Valid coordinates refer to those data points that have been verified multiple times and have high accuracy, which will provide the basis for subsequent clustering analysis.

[0039] Spatial clustering of valid coordinates is performed to identify fault hotspots. Cluster analysis is a process of finding data points with high similarity in a data set by calculating the distance between data points. In this process, an algorithm is used to divide valid coordinates into different groups, each representing a potential fault hotspot. Through cluster analysis, hotspot coordinate data can be obtained, which reflects the areas where faults frequently occur in a certain period of time. On this basis, density analysis further helps to determine the dense areas where faults occur. By calculating the ratio of the number of faults to the number of equipment in each hotspot area, it can be determined which areas have a higher risk of failure. When fuzzy logic processing is performed on dense areas, fuzzy decision feature data can be obtained in combination with historical fault data. Fuzzy logic processing allows reasoning and decision-making in the presence of uncertainty and ambiguity, and can take into account multiple possibilities and influencing factors of equipment failure. On this basis, precise positioning processing is performed to obtain spatial coordinate data of equipment failure. These spatial coordinate data will be provided to the inspection team so that high-risk areas can be given priority in subsequent inspections and maintenance work.

[0040] For example, in a certain period of time, by analyzing the abnormal data of distribution network equipment, the spatiotemporal variation data of 1,000 abnormal events were obtained. After these data were converted and calibrated through the coordinate system, the spatial coordinates corresponding to these abnormal events were inferred using machine learning algorithms, and 800 valid coordinates were obtained. Through cluster analysis, several hot spots were identified. For example, in a certain area, fault events occurred frequently with a density of 20%. Combined with historical fault data, after fuzzy logic processing of dense areas, it was determined that there was a 70% probability that the area would fail again in the future. At this time, the inspection team can prioritize the inspection of this area to reduce the economic losses caused by potential equipment failures.

[0041] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) Perform feature extraction processing on the spatial coordinate data of equipment faults to obtain fault feature data; (2) Perform risk scoring on the fault feature data through the risk assessment model, calculate the risk score of each equipment failure, obtain risk scoring data, and sort the risk scoring data to obtain sorted risk data; (3) Perform weight allocation processing on the sorted risk data, combine the equipment importance and the impact of the fault to obtain weighted risk data, and perform abnormal level classification processing on the weighted risk data to obtain preliminary abnormal level information; (4) Perform decision tree analysis on the preliminary abnormality level information to obtain a decision tree model, and re-evaluate the abnormality level through the decision tree model to obtain equipment abnormality priority information.

[0042] Specifically, the fault feature data is extracted and processed. Feature extraction is the process of identifying key attributes that affect fault judgment from raw data. At this stage, the spatial coordinate data of the equipment fault is analyzed to identify multiple features, such as the time, frequency, equipment type, environmental factors, and correlation with other equipment. These features together constitute the fault feature data, laying the foundation for subsequent risk assessment. Then, the risk assessment model is used to perform risk scoring on the fault feature data. The risk assessment model calculates the risk score of each equipment fault by analyzing the extracted feature data and combining the known fault history and influencing factors. This process involves the calculation of multiple parameters, including the importance of the equipment, the probability of the fault, and the impact of the fault on the system. Through the weighted calculation of these parameters, the risk score data of each fault is finally obtained. The score range is usually between 0 and 100, with 0 indicating no risk and 100 indicating extremely high risk. After completing the risk scoring, the scores are sorted from high to low to obtain the sorted risk data. This sorting process helps to quickly identify the equipment that needs the most attention and ensure the reasonable allocation of resources. The next key step is to perform weight distribution processing on the sorted risk data. In this process, the risk score of each device is weighted based on the importance of the device and the impact of the failure. The importance of the device is usually based on its role in the distribution network, such as a critical transformer or distribution line, whose failure may cause a wider power outage or equipment damage. At the same time, the impact of the failure takes into account the impact of the failure on surrounding equipment and systems. After the weights are assigned, weighted risk data is obtained, which not only reflects the risk score, but also shows the importance of the device in the system and the possible consequences of the failure.

[0043] After obtaining the weighted risk data, the abnormality level classification process is carried out. By setting thresholds, the weighted risk data is divided into multiple abnormality levels, such as "normal", "attention", "warning" and "danger". This division helps to quickly identify the abnormal status of the equipment, so as to carry out timely maintenance and inspection. Then, based on the preliminary abnormality level information, a decision tree analysis process is carried out. Decision tree is a popular machine learning method used to extract decision rules from data. In this process, the preliminary abnormality level is used as input to build a decision tree model, and by analyzing historical data, it is determined which features are most important for judging different abnormality levels. Finally, the decision tree model re-evaluates the abnormality level and obtains the equipment abnormality priority information. This priority information will provide strong guidance for the inspection team to ensure that high-risk equipment can be repaired first.

[0044] For example, suppose that after feature extraction of the spatial coordinate data of a certain equipment failure, it is found that the equipment failure frequency is 5 times / year, the failure type is insulation failure, and the failure occurs in a high temperature environment. Based on these features, the risk assessment model calculates a risk score of 80 for the equipment, which ranks third among all equipment after sorting. According to the importance of the equipment, assuming that the importance score of the equipment is 0.9 and the failure impact score is 0.8, the weighted risk data is: ; Next, the weighted risk data was classified into abnormal levels, with a threshold of 120, and the abnormal level of the device was finally classified as "dangerous". Subsequently, through decision tree analysis, it was found that the insulation failure of the device was strongly correlated with temperature, humidity and age. Finally, the device abnormality priority information will show that the device has the highest priority among all devices, and the inspection team will give priority to its inspection and maintenance.

[0045] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the embodiments, a person skilled in the art should understand that the specific implementation modes of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A distribution network inspection management method, characterized in that: include: Collect and preprocess multi-source data of multiple distribution network inspection nodes to obtain multi-dimensional image data after denoising; Performing feature extraction processing on the multi-dimensional image data through an image recognition algorithm to obtain device abnormality feature data of multiple distribution network inspection nodes; Perform data fusion processing on the equipment abnormality feature data of multiple distribution network inspection nodes to obtain the comprehensive equipment abnormality data with temporal and spatial correlation; Continuously analyzing and processing the equipment abnormality comprehensive data through a spatiotemporal tracking algorithm to obtain equipment abnormality spatiotemporal variation data; Intelligently positioning the abnormal spatiotemporal change data of the equipment to obtain spatial coordinate data of equipment failure; Based on the priority sorting algorithm, the equipment fault spatial coordinate data is evaluated for abnormality level to obtain equipment abnormality priority information.

2. The inspection management method for distribution network according to claim 1, characterized in that: The step of collecting and preprocessing multi-source data of multiple distribution network inspection nodes to obtain multi-dimensional image data after denoising includes: Performing data acquisition processing on multi-source data of multiple distribution network inspection nodes to obtain original image data, and performing format conversion processing on the original image data to obtain image data in a unified format; Performing grayscale processing on the image data in the unified format to obtain grayscale image data, and performing normalization processing on the grayscale image data to obtain standardized image data; Performing denoising processing on the standardized image data by using a wavelet transform algorithm to obtain denoised image data, and performing edge smoothing processing on the denoised image data to obtain smoothed image data; The smoothed image data is subjected to feature enhancement processing to obtain enhanced feature image data, and the enhanced feature image data is subjected to image reconstruction processing to obtain multi-dimensional image data after denoising processing.

3. The inspection management method for distribution network according to claim 1, characterized in that: The step of performing feature extraction processing on the multi-dimensional image data by using an image recognition algorithm to obtain device abnormality feature data of multiple distribution network inspection nodes includes: Performing feature preprocessing on the multidimensional image data to obtain processed image data, and performing feature enhancement processing on the processed image data to obtain enhanced image feature data; Performing region segmentation processing on the enhanced image feature data to obtain segmented feature region data, and performing shape description processing on the segmented feature region data to obtain shape feature data; Performing feature extraction processing on the shape feature data through a convolutional neural network to obtain a preliminary feature set, and performing feature selection processing on the preliminary feature set to obtain an optimized feature set; Performing abnormal pattern recognition processing on the optimized feature set to obtain device abnormal pattern data, and performing classification processing on the device abnormal pattern data to obtain classification feature data; The classified feature data is processed for abnormal feature identification to obtain equipment abnormal feature data of multiple distribution network inspection nodes.

4. The inspection management method for distribution network according to claim 1, characterized in that: The step of performing data fusion processing on the equipment abnormality feature data of multiple distribution network inspection nodes to obtain the time-space associated equipment abnormality comprehensive data includes: Normalizing the abnormal feature data of the equipment of multiple distribution network inspection nodes to obtain normalized feature data, and performing outlier detection on the normalized feature data to identify and remove outliers to obtain valid feature data; Performing time series labeling processing on the effective feature data to obtain feature data with timestamps, and performing space coordinate mapping processing on the feature data with timestamps to obtain spatiotemporal mapping feature data; Performing multi-dimensional data fusion processing on the spatiotemporal mapping feature data by a weighted fusion algorithm to obtain a fused feature set, and performing clustering processing on the fused feature set based on similarity analysis to obtain cluster feature data; Performing principal component analysis on the clustering feature data to extract key principal components to obtain principal component feature data, and performing time series correlation analysis on the principal component feature data to obtain time series correlation feature data; Multi-dimensional data visualization processing is performed on the time series correlation feature data to obtain visualization results, and interactive analysis is performed on the visualization results to obtain comprehensive equipment anomaly data with time and space correlation.

5. The inspection management method for distribution network according to claim 1, characterized in that: The step of continuously analyzing and processing the equipment abnormality comprehensive data by using a spatiotemporal tracking algorithm to obtain equipment abnormality spatiotemporal variation data includes: Performing time series reorganization processing on the equipment abnormality comprehensive data to obtain reorganized time series data, and performing data smoothing processing on the reorganized time series data to obtain smoothed time series data; Performing trend analysis on the smoothed time series data to identify long-term trends and seasonal fluctuations to obtain trend characteristic data, and performing timeliness evaluation on the trend characteristic data to determine a timeliness evaluation result; Dynamically tracking the timeliness evaluation results through a spatiotemporal tracking algorithm to obtain dynamically changing feature data, and performing abnormal pattern recognition on the dynamically changing feature data to identify potential abnormal patterns; Performing spatial clustering analysis on the potential abnormal patterns to obtain clustering results, and performing adjacent node association analysis on the clustering results to identify the association between nodes and obtain association feature data; The associated feature data is displayed in a multi-dimensional visual manner, and the abnormal spatiotemporal variation data of the equipment is obtained by combining the time axis and spatial distribution.

6. The inspection management method for distribution network according to claim 1, characterized in that: The step of performing intelligent positioning processing on the abnormal spatiotemporal change data of the equipment to obtain spatial coordinate data of equipment failure includes: Performing coordinate system conversion processing on the abnormal spatiotemporal change data of the equipment to obtain converted spatiotemporal data, and performing feature calibration processing on the converted spatiotemporal data to obtain calibrated feature data; Performing position inference processing on the calibration feature data through a spatial positioning algorithm based on machine learning to obtain inferred spatial coordinate data, and performing reliability assessment on the inferred spatial coordinate data to screen and obtain valid coordinates; Performing spatial clustering processing on the effective coordinates to identify fault hotspot areas, obtaining hotspot coordinate data, and performing density analysis on the hotspot coordinate data to determine dense areas where faults occur; Based on the historical fault data, fuzzy logic processing is performed on the dense area to obtain fuzzy decision feature data, and precise positioning processing is performed on the fuzzy decision feature data to obtain equipment fault spatial coordinate data.

7. The inspection management method for distribution network according to claim 6, characterized in that: The step of performing abnormality level evaluation processing on the spatial coordinate data of the equipment fault based on the priority sorting algorithm to obtain equipment abnormality priority information includes: Performing feature extraction processing on the spatial coordinate data of the equipment fault to obtain fault feature data; Performing risk scoring processing on the fault feature data through a risk assessment model, calculating the risk score of each equipment fault to obtain risk scoring data, and sorting the risk scoring data to obtain sorted risk data; Performing weight distribution processing on the ranked risk data, combining the importance of equipment and the impact of failure to obtain weighted risk data, and performing abnormality level classification processing on the weighted risk data to obtain preliminary abnormality level information; The preliminary abnormality level information is subjected to decision tree analysis to obtain a decision tree model, and the abnormality level is re-evaluated through the decision tree model to obtain equipment abnormality priority information.

Images