Distribution network risk early warning method and device based on multi-data linkage

Abstract

The present invention discloses a distribution network risk warning method and device based on multi-data linkage, which relates to the technical field of power system. The method includes: collecting the position parameters of the distribution lines in the target distribution network, the distance information between the lines and the dangerous sources in the stable state, and the meteorological forecast data; identifying the movement coefficient, the load parameter and the position parameter; analyzing the sag and movement of the distribution lines according to the meteorological forecast data, and obtaining the line position space; analyzing the dangerous source load and movement parameters in combination with the meteorological data and the dangerous source parameters; calculating the minimum distance and the distance change amplitude, classifying the distribution network risks, obtaining the risk level and issuing warnings. The technical problems of insufficient consideration of the comprehensive impact of the distribution lines and dangerous sources under wind and rain weather, lack of dynamic risk warning and poor data linkage in the prior art are solved, and the technical effects of dynamic warning, reduced fault risk, and improved safety, stability and reliability of the distribution network are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a distribution network risk early warning method and device based on multi-data linkage. Background Art

[0002] In the distribution network operation scenario, the safety issues under wind and rain weather conditions are particularly prominent, and the contradiction between the demand for distribution network risk warning and response is more obvious. Accurately assessing risks and timely warnings, and taking effective measures to ensure the safe operation of the distribution network have become crucial links. Traditional distribution network risk assessment methods are often relatively single and localized, and only consider single factors such as line load and equipment aging. They do not consider the comprehensive impact of external factors such as wind and rain weather on distribution lines and surrounding hazardous sources. There is a lack of effective monitoring and analysis methods for hazardous sources, and it is difficult to accurately predict their potential threats to distribution lines under wind and rain weather. At the same time, there are deficiencies in data linkage, and it is difficult to integrate data from multiple monitoring devices to achieve a comprehensive and accurate assessment of distribution network risks. There are unreasonable situations in resource allocation (risk response measures formulation), which cannot well cope with the complex and changeable actual operation of the distribution network.

[0003] At the current stage, relevant technologies have technical problems such as insufficient consideration of the comprehensive impact of distribution lines and hazardous sources under wind and rain weather, incomplete analysis of hazardous source characteristics, lack of dynamic risk warning and poor data linkage. Summary of the invention

[0004] The present application provides a distribution network risk warning method and device based on multi-data linkage, which adopts the distribution network monitoring equipment to collect the distribution line location parameters in the target distribution network, the nearby hazard source image and the distance measurement information of the line and the hazard source in the stable state obtained by the distance measurement equipment, and the meteorological monitoring equipment to collect the meteorological forecast data; the hazard source image is identified to obtain the movement coefficient, the load parameter and the position parameter; the sag and movement parameters of the distribution line are analyzed according to the meteorological forecast data, and the line location parameters are expanded to obtain the line location space; the hazard source load and movement parameters are analyzed in combination with the meteorological data and the hazard source parameters, and the location parameters are expanded to obtain the hazard source location space; the minimum distance and the distance change amplitude are calculated according to the line and hazard source location space and the distance measurement information, and the distribution network risk is classified to obtain the risk level and warn. The distribution network risk warning method based on multi-data linkage can accurately assess the risk of the distribution network under windy and rainy weather, and achieves the technical effect of dynamic warning, reducing the risk of failure, and improving the safety, stability and reliability of the distribution network.

[0005] This application provides a distribution network risk warning method based on multi-data linkage, including:

[0006] Through the distribution network monitoring equipment, the line location parameters of the distribution lines in the target distribution network are collected, the images of the hazardous sources near the target distribution network are collected, and the stable distance measurement information of the distribution lines and hazardous sources in a stable state is obtained by measuring at the stable monitoring point with the distance measuring equipment. Through the meteorological monitoring equipment, the meteorological forecast data is collected; the hazardous source features are identified on the hazardous source images to obtain the hazardous source movement coefficient, load parameters and hazardous source location parameters of the hazardous source; according to the meteorological forecast data, the sag analysis and movement analysis of the distribution lines are performed to obtain the line sag change parameters and line movement parameters, and the line location parameters are expanded to obtain the line location space; according to the meteorological forecast data, the hazardous source movement coefficient, load parameters and hazardous source location parameters are combined to obtain the line location space. Parameters, analyze the load position change and movement of the hazardous source, obtain the load change parameters and movement parameters of the hazardous source, expand the hazardous source location parameters, and obtain the hazardous source location space; according to the line location space and the hazardous source location space, calculate and obtain the minimum distance information, combine the stable ranging information to calculate the distance change amplitude, combine the minimum distance information, classify the distribution network risk, obtain the distribution network risk level, make a judgment and early warning, adjust the monitoring points of the mobile ranging equipment according to the meteorological forecast data, obtain the mobile monitoring points, perform mobile ranging on the distribution lines and hazardous sources, obtain mobile ranging information, verify the minimum distance information, and update and judge the distribution network risk level.

[0007] This application also provides a distribution network risk warning device based on multi-data linkage, including:

[0008] A meteorological forecast data acquisition module, the meteorological forecast data acquisition module is used to collect line location parameters of distribution lines in the target distribution network through distribution network monitoring equipment, collect hazardous source images near the target distribution network, and obtain stable ranging information of the distribution lines and hazardous sources in a stable state at a stable monitoring point through mobile ranging equipment, and collect meteorological forecast data through meteorological monitoring equipment; a hazardous source feature identification module, the hazardous source feature identification module is used to identify hazardous source features of the hazardous source images, and obtain the hazardous source movement coefficient, load parameters and hazardous source location parameters of the hazardous source; a line location space acquisition module, the line location space acquisition module is used to perform sag analysis and movement analysis of the distribution line according to the meteorological forecast data, obtain line sag change parameters and line movement parameters, expand the line location parameters, and obtain line location space; a hazardous source location space acquisition module, the hazardous source location space acquisition module The module is used to perform the load position change and movement analysis of the hazardous source according to the meteorological forecast data combined with the hazardous source movement coefficient and load parameters, obtain the load change parameters and hazardous source movement parameters of the hazardous source, expand the hazardous source location parameters, and obtain the hazardous source location space; the distribution network risk classification module, the distribution network risk classification module is used to calculate the minimum distance information according to the line location space and the hazardous source location space, calculate the distance change amplitude combined with the stable ranging information, and classify the distribution network risk in combination with the minimum distance information, obtain the distribution network risk level, and make a judgment and warning; the mobile ranging information acquisition module, the mobile ranging information acquisition module is used to adjust the monitoring points of the mobile ranging equipment according to the meteorological forecast data, obtain the mobile monitoring points, perform mobile ranging on the distribution lines and hazardous sources, obtain mobile ranging information, verify the minimum distance information, and update the distribution network risk level and make a judgment and warning.

[0009] The distribution network risk warning method and device based on multi-data linkage proposed in this application are firstly to collect the distribution line location parameters in the target distribution network, the image of the nearby hazardous source and the distance measurement information of the line and the hazardous source in the stable state obtained by the distance measurement equipment and the meteorological monitoring equipment to collect the meteorological forecast data; the hazardous source image is identified to obtain the movement coefficient, load parameter and location parameter; the sag and movement parameters of the distribution line are analyzed according to the meteorological forecast data, and the line location parameters are expanded to obtain the line location space; the load and movement parameters of the hazardous source are analyzed in combination with the meteorological data and the hazardous source parameters, and the location parameters are expanded to obtain the hazardous source location space; the minimum distance and the distance change amplitude are calculated according to the line and hazardous source location space and the distance measurement information, and the distribution network risk is classified to obtain the risk level and issue a warning, so as to achieve the technical effect that the distribution network risk under windy and rainy weather conditions can be accurately assessed through the distribution network risk warning method based on multi-data linkage, dynamic warning is achieved, the failure risk is reduced, and the safety, stability and reliability of the distribution network are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0011] Figure 1 A flow chart of a distribution network risk warning method based on multi-data linkage provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of the structure of a distribution network risk warning device based on multi-data linkage provided in an embodiment of the present application.

[0013] Explanation of the reference numerals: meteorological forecast data acquisition module 10 , hazard source feature identification module 20 , line location space acquisition module 30 , hazard source location space acquisition module 40 , distribution network risk classification module 50 , mobile ranging information acquisition module 60 . DETAILED DESCRIPTION

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0017] The present application embodiment provides a distribution network risk warning method based on multi-data linkage, such as Figure 1 As shown, the method includes:

[0018] Step S100, through the distribution network monitoring equipment, the line location parameters of the distribution lines in the target distribution network are collected, the images of the hazardous sources near the target distribution network are collected, and the stable ranging information of the distribution lines and hazardous sources under the stable state is obtained by measuring at the stable monitoring point by the mobile ranging equipment, and the meteorological forecast data is collected by the meteorological monitoring equipment.Specifically, the data types and source devices that need to be collected are clearly defined. The distribution network monitoring equipment is used to collect the line location parameters of the distribution lines in the target distribution network. The parameters include line coordinates, height and other information. The dangerous sources near the target distribution network, such as tree branches, are collected through image acquisition equipment. Image acquisition can use high-definition cameras and other equipment to ensure that the appearance characteristics of the dangerous sources can be clearly captured. The mobile ranging equipment is responsible for measuring the distance between the distribution line and the dangerous source in a stable state at a stable monitoring point to obtain the ranging information. The ranging information can be obtained through technical means such as laser rangefinders and radar ranging, which can accurately reflect the initial distance between the line and the dangerous source. Meteorological monitoring equipment is used to collect meteorological forecast data, mainly including rainfall and wind data. Meteorological monitoring equipment can be a professional meteorological station or a meteorological sensor integrated in the distribution network monitoring system, which can monitor and predict meteorological changes in the future in real time. Among them, the distribution network monitoring equipment conducts a comprehensive scan and monitoring of the distribution lines in the target distribution network, and determines the specific position of each distribution line in space through sensors and positioning technology. Image acquisition points are set for dangerous sources near the target distribution network, such as branches of trees. The acquisition points can be distributed at different angles and positions to ensure that the appearance characteristics of the dangerous sources can be fully captured. The image acquisition equipment can take pictures of the dangerous sources regularly or in real time. The image is captured and transmitted to the data processing center for analysis. During the shooting process, attention should be paid to the clarity and resolution of the image so that the characteristics of the dangerous source can be accurately identified. The distance between the distribution line and the dangerous source is measured using the distance measuring equipment. In a stable state, that is, when there is no influence of meteorological factors such as wind and rain, multiple measurements are made and the average value is taken to improve the accuracy of the distance measurement. The distance measuring equipment can use laser distance measurement technology to calculate the distance by emitting a laser beam and measuring the time it takes for the laser to go back and forth, or use radar distance measurement technology to determine the distance using the reflection principle of electromagnetic waves. The distance measurement information will serve as an important basis for the subsequent analysis of the distance change between the line and the dangerous source. The meteorological monitoring equipment continuously monitors the weather in the target area. For rainfall data, the amount and intensity of rainfall can be measured by rain sensors, and the size and direction of wind speed can be measured by wind speed sensors. Meteorological monitoring equipment transmits the meteorological data collected in real time to the data processing center for subsequent analysis and prediction. The meteorological prediction model is used, combined with historical meteorological data and current meteorological trends, to predict rainfall and wind conditions in the future, providing a basis for early warning of distribution network risks, completing the collection of line location parameters of distribution lines in the target distribution network, hazardous source images, distance measurement information of distribution lines and hazardous sources, and meteorological forecast data, providing comprehensive and accurate data support for subsequent risk analysis and warning.

[0019] In a possible implementation, the line location parameters of the distribution lines in the target distribution network are collected by the distribution network monitoring equipment, the dangerous source images near the target distribution network are collected, and the stable distance measurement information of the distribution lines and dangerous sources in a stable state is obtained by measuring at a stable monitoring point by a mobile distance measuring device. The meteorological monitoring equipment is used to collect meteorological forecast data. Step S100 further includes step S110, in which the line sag parameters and line coordinate parameters of the distribution lines in the target distribution network are collected in space by the distribution network monitoring equipment as line location parameters. Specifically, the distribution lines in the target distribution network are comprehensively monitored by the distribution network monitoring equipment. The equipment measures the line sag parameters and line coordinate parameters of the lines in space. The parameters together constitute the line location parameters. The line sag parameters reflect the degree of bending of the line in the vertical direction, which is crucial for evaluating the changes of the line under different meteorological conditions. The line coordinate parameters determine the specific position of the line in space, which provides a basis for the subsequent analysis of the relative position relationship between the line and the dangerous source. For example, by using high-precision sensors and measurement technology, the length, height and other parameters of the line sag, as well as the longitude and latitude coordinates of the line, can be accurately obtained.

[0020] Step S120, collect images of dangerous sources near the target distribution network. Specifically, for potential dangerous sources near the target distribution network, such as tree branches, etc., use image acquisition equipment to shoot. Dangerous sources may pose a threat to distribution lines under meteorological conditions such as wind and rain, so detailed image acquisition is required. The image acquisition device can be a high-definition camera or a drone, etc., which can capture the appearance characteristics of the dangerous source from different angles and distances. By analyzing the dangerous source image, the shape, size, position and other information of the dangerous source can be obtained, providing a basis for subsequent risk assessment. For example, if the dangerous source is a tree branch, its thickness, length, inclination angle, etc., as well as its relative position relationship with the distribution line can be determined through the image.

[0021] Step S130, using a mobile ranging device, collects ranging information of the distribution line and the dangerous source in a stable state at a stable monitoring point. Specifically, the distance between the distribution line and the dangerous source in a stable state collected at the stable monitoring point is measured by a mobile ranging device. In a stable state without the influence of external factors such as wind and rain, the mobile ranging device can accurately obtain the initial distance between the line and the dangerous source. The mobile ranging device can use laser rangefinders, radar ranging and other technologies to accurately measure the distance between the line and the dangerous source. For example, by measuring multiple times and taking the average value, the accuracy of ranging can be improved. At the same time, different ranging devices can be selected according to actual conditions to meet different measurement needs.

[0022] Step S140, collect the maximum rainfall data and the maximum wind data within the preset time range in the future as meteorological forecast data through meteorological monitoring equipment. Specifically, the meteorological conditions within the preset time range in the future are predicted with the help of meteorological monitoring equipment, focusing on the maximum rainfall data and the maximum wind data, because these data have the most significant impact on distribution lines and dangerous sources. The meteorological monitoring equipment can collect meteorological satellite data, ground meteorological station data and other channels, and combine meteorological models to make predictions. For example, by analyzing historical meteorological data and current meteorological trends, the maximum rainfall and maximum wind intensity that may occur in a period of time in the future can be predicted. The meteorological forecast data will provide an important basis for the subsequent analysis of the changes of lines and dangerous sources under different meteorological conditions.

[0023] Step S200, identify the characteristics of the hazardous source image, and obtain the hazardous source movement coefficient, bearing parameters and hazardous source location parameters of the hazardous source. Specifically, the hazardous source image is first collected and preprocessed to improve the quality and clarity, and the image is analyzed to determine the thickness of the tree and the number of leaves. Based on this, a relationship model between wind force and offset distance is established and the movement coefficient is calculated in combination with the image analysis results. At the same time, the tree structure and material characteristics are analyzed to establish a bearing model, and the mass of the bearing rainfall and the degree of bending coefficient, i.e., the bearing parameters, are calculated in combination with the image parameters. Through image coordinate conversion and position analysis, the hazardous source location parameters are determined according to the relative position of the hazardous source to the distribution network, providing important data support for distribution network risk assessment and early warning.

[0024] In a possible implementation, the hazard source features are identified on the hazard source image to obtain the hazard source movement coefficient, bearing parameters and hazard source position parameters of the hazard source. Step S200 further includes step S210, collecting a set of sample hazard source images, marking the movement amplitude variation coefficient of the hazard source under different wind forces and the bending amplitude under the bearing rainfall in the sample hazard source image, and marking the relative position parameters of the hazard source and the distribution network to obtain a set of sample hazard source movement coefficients, a set of sample bearing parameters and a set of sample relative position parameters. Specifically, a large number of sample hazard source image sets are collected. The sample images should cover hazard sources under various conditions, such as the status of different types of trees under different wind and rainfall conditions. For each sample hazard source image, professionals mark the coefficient of change of the movement amplitude of the hazard source under different wind forces. Based on actual experience or measurement data, the amplitude change of the hazard source (such as trees) after being blown by the wind under a specific wind force is determined, and this coefficient is recorded. The bending amplitude of the hazard source under the rainfall load is also marked. When it rains, the hazard source will increase its weight due to absorbing rainwater, which may cause bending. The labeling personnel determine the value of the bending amplitude according to the degree of bending of the hazard source under different rainfall, and mark the relative position parameters of the hazard source and the distribution network, including distance, direction and other information. Through these labeling work, the sample hazard source movement coefficient set, sample load parameter set and sample relative position parameter set are obtained, providing accurate labeling data for the subsequent training of the hazard source feature identifier.

[0025] Step S220, using the sample hazard source image set, sample hazard source movement coefficient set, sample bearing parameter set and sample relative position parameter set to train the hazard source feature identifier. Specifically, the collected sample hazard source image set and the corresponding sample hazard source movement coefficient set, sample bearing parameter set and sample relative position parameter set are used to train the hazard source feature identifier, using a machine learning algorithm, taking the sample image as input and the corresponding annotated data as output target, allowing the algorithm to continuously learn the relationship between the features in the image and the movement coefficient, bearing parameter and relative position parameter, and repeatedly training through a large amount of sample data, so that the hazard source feature identifier can gradually and accurately extract feature information related to these parameters from the image.

[0026] Step S230, using the hazard feature identifier, perform hazard feature identification on the hazard image to obtain the hazard movement coefficient, load-bearing parameter and relative position parameter of the hazard. Specifically, after the training is completed, the hazard feature identifier is used to perform feature identification on a new hazard image. The identifier will analyze various features in the image, determine the movement coefficient, load-bearing parameter and relative position parameter of the hazard based on the previously learned pattern, and quickly provide these key parameters for each hazard image to provide data support for subsequent risk assessment.

[0027] Step S240, calculate and obtain the hazard source location parameter according to the relative position parameter and the line location parameter of the distribution line. Specifically, the hazard source location parameter is calculated according to the relative position parameter obtained by the hazard source feature identifier and the line location parameter of the distribution line previously obtained by the distribution network monitoring device, and the relative position parameter and the position of the distribution line are used for reference and calculation to determine the specific position coordinates and other parameters of the hazard source in the entire distribution network system, accurately know the positional relationship between the hazard source and the distribution line, and provide key information for evaluating the distribution network risk.

[0028] Step S300, according to the meteorological forecast data, the sag analysis and movement analysis of the distribution line are performed, the line sag change parameters and line movement parameters are obtained, the line position parameters are expanded, and the line position space is obtained. Specifically, the distribution line sag analysis is performed according to the rainfall data in the meteorological forecast data. Since rainfall will increase the mass of rainwater attached to the line, resulting in a larger sag and a lower sag height, the line sag change parameters can be calculated based on the current rainfall data by establishing a mathematical model, and the movement analysis is performed in combination with the wind data and the rainfall data. Considering that the increase in line quality due to rainfall will reduce the deviation distance under the same wind force, the line movement parameters are calculated according to the current wind and rainfall data after the comprehensive model is established. The line position parameters are expanded using the obtained sag change parameters and movement parameters, and the sag change and movement are taken into account. The position range to which the line may move under different meteorological conditions is calculated to obtain the line position space, that is, the position space where the line moves under the influence of meteorology, which provides basic data for distribution network risk assessment and early warning.

[0029] In a possible implementation, according to the meteorological forecast data, the sag analysis and movement analysis of the distribution line are performed to obtain the line sag change parameters and line movement parameters, the line position parameters are expanded, and the line position space is obtained. Step S300 further includes step S310, according to the historical monitoring data of the line, the sample line sag parameter set and the sample rainfall data set of the line in a stable state are collected, and the sag change parameters of the line under different sample line sag parameters and sample rainfall data are marked to obtain the sample line sag change parameter set. Specifically, data collection work is performed according to the historical monitoring data of the line, and the sample line sag parameter set of the line in a stable state is collected, and the parameters reflect the sag state of the line under normal conditions. The sample rainfall data set is collected, the rainfall conditions at different time points are recorded, and the sag change parameters of the line under different sample line sag parameters and sample rainfall data are marked. Professionals determine the degree of change of the line sag under a specific combination of line sag and rainfall based on actual conditions and experience, and record the change parameters, so as to obtain the sample line sag change parameter set.

[0030] Step S320, using the sample line sag parameter set, sample rainfall data set and sample line sag change parameter set to train a line sag change predictor. Specifically, the collected sample line sag parameter set, sample rainfall data set and sample line sag change parameter set are used to train the line sag change predictor, using a machine learning algorithm, taking the sample line sag parameters and sample rainfall data as inputs, and the corresponding sag change parameters as output targets, and repeatedly training through a large amount of sample data, so that the predictor learns the relationship pattern between line sag parameters, rainfall data and sag changes.

[0031] Step S330, using the line sag change predictor, the line sag parameters in the line location parameters of the distribution line are combined with the rainfall data in the meteorological forecast data to perform sag change prediction to obtain the line sag change parameters. Specifically, after the training is completed, the line sag change predictor is used to predict the line sag parameters in the line location parameters of the distribution line in combination with the rainfall data in the meteorological forecast data. The predictor analyzes the current line sag parameters and rainfall data based on the previously learned relationship model, and calculates the line sag change parameters, thereby providing accurate data for evaluating the sag change of the line under the current meteorological conditions.

[0032] Step S340, performing a movement analysis of the distribution line according to the meteorological forecast data to obtain line movement parameters. Specifically, performing a movement analysis of the distribution line according to the meteorological forecast data, taking into account the influence of wind and possible other factors on the line, and determining the fluttering of the line under the action of wind by establishing a suitable model and analysis method, thereby obtaining line movement parameters.

[0033] Step S350, according to the line sag change parameter, set the sag expansion distance, according to the line movement parameter, set the line movement expansion distance, expand the line position parameter, and obtain the line position space. Specifically, after obtaining the line sag change parameter and the line movement parameter, the line position parameter is expanded, and according to the line sag change parameter, the sag expansion distance is set, and the distance reflects the range of possible movement of the line under the influence of sag change, and according to the line movement parameter, the line movement expansion distance is set, which represents the movement range of the line under the influence of movement. Combining the expansion distance with the original line position parameter, the line position space can be obtained, which fully considers the possible movement range of the line under the combined action of sag change and movement.

[0034] In a possible implementation, according to the meteorological forecast data, the movement analysis of the distribution line is performed to obtain the line movement parameters, and step S340 further includes step S341, collecting a sample line sag parameter set, a sample rainfall data set, and a sample wind data set, and marking the movement distance of the line under different sample line sag parameters, sample rainfall data, and sample wind data, to obtain a sample line movement parameter set. Specifically, data collection work is performed to collect sample line sag parameter sets respectively, and the parameters reflect the sag state of different lines under various conditions; collect sample rainfall data sets to record rainfall conditions in different time periods; collect sample wind data sets to obtain information such as wind force at different times, and mark the movement distance of the line for different combinations of sample line sag parameters, sample rainfall data, and sample wind data. Professionals determine the distance that the line is blown away from its original position by the wind under specific line sag, rainfall, and wind conditions based on actual observations and experience, and record the movement distance, thereby obtaining a sample line movement parameter set.

[0035] Step S342, using the sample line sag parameter set, sample rainfall data set, sample wind data set and sample line movement parameter set to train the line movement predictor. Specifically, the collected sample line sag parameter set, sample rainfall data set, sample wind data set and sample line movement parameter set are used to train the line movement predictor, using a machine learning algorithm, taking the sample line sag parameters, sample rainfall data and sample wind data as inputs, and the corresponding movement parameters as output targets, and repeatedly training through a large amount of sample data, so that the predictor learns the complex relationship pattern between line sag parameters, rainfall data, wind data and movement.

[0036] Step S343, using the line movement predictor, the line sag parameters in the line location parameters of the distribution line are combined with the rainfall data and wind data in the meteorological forecast data to perform movement analysis to obtain the line movement parameters. Specifically, after the training is completed, the line movement predictor is used to perform movement analysis on the line sag parameters in the line location parameters of the distribution line in combination with the rainfall data and wind data in the meteorological forecast data. The predictor analyzes the current line sag parameters and the actual rainfall data and wind data based on the previously learned relationship model, calculates the line movement parameters, and accurately predicts the possible movement of the distribution line under the current specific meteorological conditions, providing key data for subsequent risk assessment and early warning.

[0037] Step S400, according to the meteorological forecast data combined with the dangerous source movement coefficient and bearing parameters, the dangerous source bearing position change and movement analysis is performed to obtain the dangerous source bearing change parameters and dangerous source movement parameters, and the dangerous source position parameters are expanded to obtain the dangerous source position space. Specifically, according to the meteorological forecast data (including rainfall data and wind data), combined with the dangerous source movement coefficient and bearing parameters, the analysis is performed, and for the rainfall data, the distance of the dangerous source bearing change decrease affected by it is analyzed to obtain the bearing change parameters; using the wind data and rainfall data in the meteorological data and the dangerous source movement coefficient, the distance of the dangerous source being offset by wind and rainfall is analyzed to obtain the dangerous source movement parameters. After obtaining the parameters, the dangerous source position parameters are expanded, and the bearing position change and movement are considered. The possible position range of the dangerous source under different meteorological conditions is calculated to obtain the dangerous source position space, which provides important basic data for distribution network risk assessment and early warning.

[0038] In a possible implementation, according to the meteorological forecast data combined with the movement coefficient and bearing parameters of the hazard source, the bearing position change and movement analysis of the hazard source is performed to obtain the bearing change parameters and movement parameters of the hazard source, and the hazard source position parameters are expanded to obtain the hazard source position space. Step S400 further includes step S410, collecting a sample rainfall data set and a sample bearing parameter set, and marking the bearing position change of the hazard source under different sample rainfall data and sample bearing parameters to obtain a sample bearing change parameter set. Specifically, the sample rainfall data set and the sample bearing parameter set are collected respectively, the sample rainfall data reflects the rainfall conditions under different conditions, and the sample bearing parameters are related to the inherent characteristics of the hazard source (such as tree branches, etc.), such as the structural strength of the hazard source, the material and other factors determine the bearing capacity, the bearing position change of the hazard source under different combinations of sample rainfall data and sample bearing parameters is marked, and the professional determines the position change of the hazard source due to factors such as rainfall under specific rainfall conditions and bearing parameters based on actual experience or experimental data, and records the changes, thereby obtaining a sample bearing change parameter set.

[0039] Step S420, using the sample rainfall data set, the sample bearing parameter set and the sample bearing change parameter set, training the hazard source bearing change predictor, analyzing the bearing position change of the rainfall data in the meteorological forecast data in combination with the bearing parameters, and obtaining the bearing change parameters. Specifically, the collected sample rainfall data set, the sample bearing parameter set and the sample bearing change parameter set are used to train the hazard source bearing change predictor. In this process, a machine learning algorithm is used, with the sample rainfall data and the sample bearing parameters as input, and the corresponding bearing change parameters as output targets. Through repeated training with a large amount of sample data, the predictor learns the relationship pattern between rainfall data, bearing parameters and the hazard source bearing position change. After the training is completed, when there is new rainfall data in the meteorological forecast data and known bearing parameters, the predictor can analyze the bearing position change of the hazard source and obtain the bearing change parameters.

[0040] Step S430, collect a set of sample wind data, a set of sample hazard source movement coefficients, and a set of sample load-bearing change parameters, and annotate the movement distances of the hazard sources under different sample wind data, sample hazard source movement coefficients, and sample load-bearing change parameters to obtain a set of sample hazard source movement parameters. Specifically, collect a set of sample wind data, a set of sample hazard source movement coefficients, and a set of sample load-bearing change parameters. The sample wind data reflects the conditions of different wind forces. The sample hazard source movement coefficient is a parameter obtained by analyzing the hazard source image. The sample load-bearing change parameter is a parameter obtained in the previous step. Annotate the movement distances of the hazard sources under different combinations of sample wind data, sample hazard source movement coefficients, and sample load-bearing change parameters. According to actual observation and analysis, determine the offset distance of the hazard source caused by the wind under specific wind forces, movement coefficients, and load-bearing change parameters, and record it to obtain a set of sample hazard source movement parameters.

[0041] Step S440, using the sample wind data set, the sample hazard source movement coefficient set, the sample load change parameter set and the sample hazard source movement parameter set, to train the hazard source movement predictor, and analyzing the rainfall data and wind data in the meteorological forecast data, combined with the load change parameters of the hazard source and the hazard source movement coefficient, to obtain the hazard source movement parameters. Specifically, using the sample wind data set, the sample hazard source movement coefficient set, the sample load change parameter set and the sample hazard source movement parameter set, to train the hazard source movement predictor, using the sample wind data, the sample hazard source movement coefficient and the sample load change parameter as input, and the corresponding hazard source movement parameters as output targets, through training, the predictor learns the complex relationship between these factors and the hazard source movement, and when there are rainfall data and wind data in the meteorological forecast data, as well as known hazard source load change parameters and hazard source movement coefficients, the predictor can analyze and obtain the hazard source movement parameters.

[0042] Step S450, using the load change parameters and the hazard source movement parameters, setting the load expansion distance and the hazard source movement expansion distance, expanding the hazard source location parameters, and obtaining the hazard source location space. Specifically, after obtaining the load change parameters and the hazard source movement parameters, these two parameters are used to set the load expansion distance and the hazard source line movement expansion distance. The load expansion distance reflects the possible movement range of the hazard source under the influence of the load change, and the hazard source line movement expansion distance indicates the movement range under the influence of the movement. The hazard source location parameters are expanded, and the expansion distance is combined with the original hazard source location parameters. Taking into account the load position changes and movement of the hazard source under different meteorological conditions, the hazard source location space is obtained, which provides important data support for distribution network risk assessment and early warning.

[0043] Step S500, according to the line location space and the hazard source location space, the minimum distance information is calculated and obtained, and the distance change amplitude is calculated in combination with the stable distance measurement information. In combination with the minimum distance information, the distribution network risk classification is performed, the distribution network risk level is obtained, and a judgment warning is performed. Specifically, in the distribution network risk warning scheme based on multi-data linkage, the minimum distance information is first calculated according to the line location space and the hazard source location space, that is, the minimum distance is found by calculating the distance between each point in the two spaces, reflecting the proximity between the distribution line and the hazard source under the most unfavorable conditions, and the distance change amplitude is calculated in combination with the distance measurement information, and the initial distance is compared with the minimum distance to obtain the change amount, and then divided by the initial distance to obtain the change amplitude, reflecting the degree of change of the distance under different meteorological conditions, and combined with the minimum distance information, according to the pre-set risk classification standard, different minimum distance ranges are corresponded to different risk levels, and the distribution network risk level is obtained. According to the risk level, a judgment warning is performed, and when the risk level reaches a certain level, a warning signal is issued to notify relevant personnel to take measures to improve the safety and reliability of the distribution network.

[0044] In a possible implementation, according to the line location space and the hazard source location space, the minimum distance information is calculated, and the distance change amplitude is calculated in combination with the stable distance measurement information. In combination with the minimum distance information, the distribution network risk classification is performed, the distribution network risk level is obtained, and the judgment and warning are performed. Step S500 further includes step S510, according to the line location space and the hazard source location space, the minimum distance between the line location space and the hazard source location space is calculated to obtain the minimum distance information. Specifically, the operation is performed according to the determined line location space and hazard source location space. The line location space represents the possible position range of the distribution line under different meteorological conditions, and the hazard source location space is the possible position range of the hazard source under the influence of meteorology. For each line location space and the corresponding hazard source location space, the distance between each point in the two spaces is calculated one by one, and the minimum distance value is determined therefrom to ensure that the minimum distance is accurately found, and a minimum distance information is obtained for each combination of line and hazard source, and finally the minimum distance information is obtained.

[0045] Step S520, calculate the distance danger coefficient of the minimum distance information according to the safe distance between the distribution line and the danger source. Specifically, the calculation is performed according to the safe distance between the distribution line and the danger source. The safe distance is a pre-set standard value, which represents the minimum distance that should be maintained between the distribution line and the danger source under normal circumstances to ensure safe operation. For each minimum distance information, it is compared with the safe distance, and the distance danger coefficient is calculated through a specific calculation formula. The distance danger coefficient reflects the relative relationship between the actual minimum distance and the safe distance. The larger the value, the higher the degree of danger.

[0046] Step S530, calculate the distance change amplitude according to the distance measurement information and the minimum distance information. Specifically, the distance measurement information and the minimum distance information are combined for calculation, the distance measurement information is the distance between the distribution line and the danger source measured in a stable state, each distance measurement information is compared with the corresponding minimum distance information, the distance change amount is calculated, the change amount is divided by the distance measurement information, and the distance change amplitude is obtained, which reflects the degree of change of the distance between the distribution line and the danger source under different conditions.

[0047] Step S540, collect the sample distance hazard coefficient set and the sample distance variation range set, and annotate to obtain the sample distribution network risk level set according to the line accident probability under different sample distance hazard coefficients and sample distance variation ranges. Specifically, a large number of sample distance hazard coefficient sets and sample distance variation range sets are collected, and the sample data are collected from the actual situation in the past, representing different distance hazard coefficient and distance variation range combinations. For each sample combination, annotate according to its corresponding line accident probability, and determine the probability of distribution line accidents under different distance hazard coefficients and distance variation ranges through the analysis of historical data. The annotation results are integrated to obtain the sample distribution network risk level set.

[0048] Step S550, based on the decision tree, the sample distance hazard coefficient set, the sample distance variation range set and the sample distribution network risk level set are used to construct a distribution risk classifier, the distance hazard coefficient and the distance variation range are classified, and the line distribution network risk level is obtained. Specifically, based on the decision tree algorithm, the sample distance hazard coefficient set, the sample distance variation range set and the sample distribution network risk level set are used to construct a distribution risk classifier. The decision tree algorithm is a commonly used machine learning algorithm that can make classification decisions based on input feature data. The sample data is used as training data and input into the decision tree algorithm for training. By continuously adjusting the structure and parameters of the decision tree, it can accurately classify the risks of the distribution line according to the distance hazard coefficient and the distance variation range. After the training is completed, a distribution risk classifier that can classify new distance hazard coefficients and distance variation ranges is obtained.

[0049] Step S560, according to the risk level of the line distribution network, calculate the risk level of the distribution network, and make a judgment and early warning. Specifically, use the constructed distribution risk classifier to classify the distance hazard coefficient and the distance change amplitude, and input the actually calculated distance hazard coefficient and the distance change amplitude into the classifier. The classifier assigns a line distribution network risk level to each input combination according to its learned pattern. After obtaining the line distribution network risk level, a comprehensive calculation is performed according to the level to obtain the risk level of the entire distribution network. According to the distribution network risk level, a judgment and early warning are made. If the risk level exceeds a certain threshold, a warning signal is issued to notify relevant personnel to take corresponding measures to reduce the risk and ensure the safe operation of the distribution network.

[0050] Step S600, according to the meteorological forecast data, the monitoring point of the mobile ranging device is adjusted to obtain the mobile monitoring point, the mobile ranging of the distribution line and the dangerous source is performed, the mobile ranging information is obtained, the minimum distance information is verified, and the risk level of the distribution network is updated and the early warning is judged. Specifically, first, the monitoring point of the mobile ranging device is adjusted according to the meteorological forecast data, because different meteorological conditions such as heavy rain and strong wind will affect the measurement results, and it is necessary to select a suitable location as the mobile monitoring point in combination with the historical data rules and the current meteorological forecast data. Next, the mobile ranging device is used at the mobile monitoring point to perform mobile ranging of the distribution line and the dangerous source, and the mobile ranging information reflecting the relative position relationship between the two is obtained. Then, the mobile ranging information is compared with the previously calculated minimum distance information for verification. If the mobile distance measurement information is less than the minimum distance information, it means that the actual distance is smaller than expected and the risk may increase. At this time, the mobile distance measurement information and the distance change range are used to re-evaluate the distribution network risk level, and make judgments and warnings based on the updated risk level, and send warning information to relevant personnel to take corresponding measures; if the mobile distance measurement information is not less than the minimum distance information, it means that the risk situation has not changed significantly, and there is no need to update the distribution network risk level or issue a warning.

[0051] In a possible implementation, the monitoring point of the mobile ranging device is adjusted according to the meteorological forecast data to obtain the mobile monitoring point, the distribution line and the dangerous source are mobile ranging to obtain the mobile ranging information, the minimum distance information is verified, the risk level of the distribution network is updated and the warning is judged, and step S600 further includes step S610 to obtain the monitoring point space of the mobile ranging device in the target distribution network. Specifically, to obtain the monitoring point space of the mobile ranging device in the target distribution network, first clarify the area range that the mobile ranging device can monitor around the target distribution network. The monitoring point space may be determined based on factors such as the performance of the device, the layout of the target distribution network, and the surrounding environment. For example, the effective measurement distance of the device determines the approximate range of the monitoring point space, and factors such as the geographical location of the distribution network and the surrounding topography may further limit or affect the specific form of this space.

[0052] Step 620, randomly select monitoring points in the monitoring point space, combine the meteorological forecast data, perform mobile ranging impact analysis, and obtain the mobile ranging impact range. Specifically, randomly select monitoring points in the monitoring point space, combine the meteorological forecast data, perform mobile ranging impact analysis, and obtain the mobile ranging impact range. In the determined monitoring point space, randomly select multiple different monitoring point locations, combine the meteorological forecast data, and consider the impact of possible future rainfall, wind and other factors on mobile ranging. For example, rainfall may cause light refraction and affect the measurement accuracy of the equipment, and wind may cause the equipment to shake and affect the stability of the measurement. By analyzing each randomly selected monitoring point, the possible impact of these monitoring points on the distribution lines and dangerous sources during mobile ranging under different meteorological conditions is evaluated, and a numerical value is used to represent the impact range.

[0053] Step 630, after the random selection of monitoring points for impact analysis is completed, the monitoring point with the smallest impact amplitude of mobile ranging is output as the mobile monitoring point. Specifically, after the random selection of monitoring points for impact analysis is completed, the monitoring point with the smallest impact amplitude of mobile ranging is output as the mobile monitoring point. After the impact analysis is performed on all randomly selected monitoring points, the impact amplitudes of the various monitoring points are compared, and the monitoring point with the smallest impact amplitude of mobile ranging is selected. This monitoring point is most likely to provide accurate and stable mobile ranging results under current meteorological conditions. It is determined as the mobile monitoring point for subsequent mobile ranging operations.

[0054] Step 640, at the mobile monitoring point, the mobile ranging device is used to perform mobile ranging on the distribution line and the dangerous source to obtain mobile ranging information. Specifically, at the mobile monitoring point, the mobile ranging device is used to perform mobile ranging on the distribution line and the dangerous source to obtain mobile ranging information, the mobile ranging device is placed at a determined mobile monitoring point, the distribution line in the target distribution network and the nearby dangerous source are measured, and the actual distance between the distribution line and the dangerous source and other information are obtained through the measurement function of the device, that is, the mobile ranging information, which reflects the relative position relationship between the distribution line and the dangerous source at the current mobile monitoring point.

[0055] Step 650, verify whether the mobile ranging information is less than the minimum distance information. If so, the mobile ranging information and the distance change amplitude are used to update and distinguish the risk level of the distribution network and give an early warning. If not, the risk level of the distribution network is not updated. Specifically, verify whether the mobile ranging information is less than the minimum distance information. If so, the mobile ranging information and the distance change amplitude are used to update and distinguish the risk level of the distribution network and give an early warning. If not, the risk level of the distribution network is not updated. The obtained mobile ranging information is compared with the previously calculated minimum distance information. If the mobile ranging information is less than the minimum distance information, it means that the actual distance between the distribution line and the dangerous source is smaller than expected, and the risk may increase. At this time, the mobile ranging information and the previously calculated distance change amplitude are used to re-evaluate the risk level of the distribution network, and distinguish and warn according to the new risk level, and remind relevant personnel to take corresponding measures. If the mobile ranging information is not less than the minimum distance information, it means that the current risk situation has not changed significantly, and the risk level of the distribution network does not need to be updated.

[0056] The embodiment of the present application adopts the following steps: collecting the position parameters of the distribution lines in the target distribution network, the images of nearby hazardous sources, and the distance measurement information of the lines and hazardous sources in a stable state obtained by the distribution network monitoring equipment, and collecting meteorological forecast data by the meteorological monitoring equipment; identifying the hazardous source images to obtain the movement coefficient, load parameters and position parameters; analyzing the sag and movement parameters of the distribution lines based on the meteorological forecast data and expanding the line position parameters to obtain the line position space; analyzing the load and movement parameters of the hazardous sources in combination with the meteorological data and the hazardous source parameters and expanding the position parameters to obtain the hazardous source position space; calculating the minimum distance and the distance change amplitude according to the line and hazardous source position space and the distance measurement information, classifying the distribution network risks to obtain the risk level and issuing warnings, so as to achieve the technical effect that the distribution network risks under windy and rainy weather conditions can be accurately assessed through the distribution network risk warning method based on multi-data linkage, dynamic warning is achieved, the failure risk is reduced, and the safety, stability and reliability of the distribution network are improved.

[0057] In the above, refer to Figure 1 The distribution network risk warning method based on multi-data linkage according to an embodiment of the present invention is described in detail. Figure 2 A distribution network risk warning device based on multi-data linkage according to an embodiment of the present invention is described.

[0058] The distribution network risk warning device based on multi-data linkage according to the embodiment of the present invention is used to solve the technical problems in the prior art of insufficient consideration of the comprehensive impact of distribution lines and dangerous sources under wind and rain weather, incomplete analysis of dangerous source characteristics, lack of dynamic risk warning and poor data linkage. The distribution network risk warning method based on multi-data linkage can accurately assess the risk of distribution network under wind and rain weather, achieve dynamic warning, reduce fault risks, and improve the technical effects of safety, stability and reliability of distribution network. The distribution network risk warning device based on multi-data linkage includes: a meteorological forecast data acquisition module 10, a dangerous source feature identification module 20, a line location space acquisition module 30, a dangerous source location space acquisition module 40, a distribution network risk classification module 50, and a mobile ranging information acquisition module 60.

[0059] The meteorological forecast data acquisition module 10 is used to collect the line location parameters of the distribution lines in the target distribution network through the distribution network monitoring equipment, collect the images of the hazardous sources near the target distribution network, and obtain the stable ranging information of the distribution lines and hazardous sources in a stable state at a stable monitoring point through a mobile ranging device, and collect meteorological forecast data through the meteorological monitoring equipment.

[0060] The hazard source feature recognition module 20 is used to perform hazard source feature recognition on the hazard source image to obtain the hazard source movement coefficient, load-bearing parameters and hazard source position parameters of the hazard source.

[0061] The line location space acquisition module 30 is used to perform sag analysis and movement analysis of the distribution line according to the meteorological forecast data, obtain line sag change parameters and line movement parameters, expand line location parameters, and obtain line location space.

[0062] The hazard source location space acquisition module 40 is used to perform the bearing position change and movement analysis of the hazard source based on the meteorological forecast data combined with the hazard source movement coefficient and bearing parameters, obtain the bearing change parameters and hazard source movement parameters of the hazard source, expand the hazard source location parameters, and obtain the hazard source location space.

[0063] The distribution network risk classification module 50 is used to calculate the minimum distance information according to the line location space and the hazard source location space, calculate the distance change amplitude in combination with the stable distance measurement information, and classify the distribution network risks in combination with the minimum distance information to obtain the distribution network risk level and perform judgment and warning.

[0064] The mobile ranging information acquisition module 60 is used to adjust the monitoring points of the mobile ranging equipment according to the meteorological forecast data, obtain mobile monitoring points, perform mobile ranging on the distribution lines and hazardous sources, obtain mobile ranging information, verify the minimum distance information, and update and identify the distribution network risk level.

[0065] The specific configuration of the meteorological forecast data acquisition module 10 will be described in detail below. As described above, the line location parameters of the distribution lines in the target distribution network are collected through the distribution network monitoring equipment, the dangerous source images near the target distribution network are collected, and the stable distance information of the distribution lines and dangerous sources in a stable state is obtained by measuring at a stable monitoring point through a mobile ranging device, and the meteorological forecast data is collected through the meteorological monitoring equipment. The meteorological forecast data acquisition module 10 further includes: a line parameter acquisition unit, the line parameter acquisition unit is used to collect the line sag parameters and line coordinate parameters of the distribution lines in the target distribution network in space through the distribution network monitoring equipment as line location parameters; a dangerous source image acquisition unit, the dangerous source image acquisition unit is used to collect dangerous source images near the target distribution network; a ranging information acquisition unit, the ranging information acquisition unit is used to collect the ranging information of the distribution lines and dangerous sources in a stable state at a stable monitoring point through a mobile ranging device; a meteorological forecast data acquisition unit, the meteorological forecast data acquisition unit is used to collect the maximum rainfall data and the maximum wind force data within a preset time range in the future through the meteorological monitoring equipment as meteorological forecast data.

[0066] Next, the specific configuration of the hazard source feature identification module 20 will be described in detail. As described above, the hazardous source image is subjected to hazardous source feature identification to obtain the hazardous source movement coefficient, bearing parameter and hazardous source position parameter of the hazardous source. The hazardous source feature identification module 20 further includes: a labeling unit, the labeling unit is used to collect a set of sample hazardous source images, label the movement amplitude variation coefficient of the hazardous source in the sample hazardous source image under different wind forces and the bending amplitude under the bearing rainfall, and label the relative position parameters of the hazardous source and the distribution network to obtain a set of sample hazardous source movement coefficients, a set of sample bearing parameters and a set of sample relative position parameters; an identifier training unit, the identifier training unit is used to train a hazardous source feature identifier using the sample hazardous source image set, the sample hazardous source movement coefficient set, the sample bearing parameter set and the sample relative position parameter set; a hazardous source feature identification unit, the hazardous source feature identification unit is used to use the hazardous source feature identifier to perform hazardous source feature identification on the hazardous source image to obtain the hazardous source movement coefficient, bearing parameter and relative position parameter of the hazardous source; a hazardous source position parameter calculation unit, the hazardous source position parameter calculation unit is used to calculate the hazardous source position parameters according to the relative position parameters and the line position parameters of the distribution line.

[0067] The specific configuration of the line position space acquisition module 30 will be described in detail below. As described above, according to the meteorological forecast data, the sag analysis and movement analysis of the distribution line are performed to obtain the line sag change parameters and line movement parameters, and the line position parameters are expanded to obtain the line position space. The line position space acquisition module 30 further includes: a sample line sag change parameter set acquisition unit, the sample line sag change parameter set acquisition unit is used to collect the sample line sag parameter set and the sample rainfall data set of the line in the stable state according to the line historical monitoring data, and mark the sag change parameters of the line under different sample line sag parameters and sample rainfall data to obtain the sample line sag change parameter set; a line sag change predictor training unit, the line sag change predictor training unit is used to adopt the sample line sag parameter set and the sample rainfall data to obtain the sample line sag change parameter set. A line sag change predictor is trained based on a data set and a sample line sag change parameter set; a sag change prediction unit is used to use the line sag change predictor to predict the line sag parameters within the line location parameters of the distribution line in combination with the rainfall data in the meteorological forecast data, so as to obtain the line sag change parameters; a line movement parameter acquisition unit is used to perform movement analysis on the distribution line according to the meteorological forecast data to obtain the line movement parameters; a line location parameter expansion unit is used to set the sag expansion distance according to the line sag change parameters, set the line movement expansion distance according to the line movement parameters, expand the line location parameters, and obtain the line location space.

[0068] Wherein, according to the meteorological forecast data, the movement analysis of the distribution line is performed to obtain the line movement parameters, and the line movement parameter acquisition unit further includes: a sample line movement parameter set acquisition subunit, the sample line movement parameter set acquisition subunit is used to collect the sample line sag parameter set, the sample rainfall data set, and the sample wind data set, and mark the movement distance of the line under different sample line sag parameters, sample rainfall data, and sample wind data to obtain the sample line movement parameter set; a line movement predictor training subunit, the line movement predictor training subunit is used to train the line movement predictor by using the sample line sag parameter set, the sample rainfall data set, the sample wind data set, and the sample line movement parameter set; a line movement parameter acquisition subunit, the line movement parameter acquisition subunit is used to use the line movement predictor to perform movement analysis on the line sag parameters within the line location parameters of the distribution line in combination with the rainfall data and wind data in the meteorological forecast data to obtain the line movement parameters.

[0069] The specific configuration of the hazard source location space acquisition module 40 will be described in detail below. As described above, according to the meteorological forecast data combined with the hazard source movement coefficient and the bearing parameter, the bearing position change and movement analysis of the hazard source is performed to obtain the bearing change parameter and the hazard source movement parameter of the hazard source, and the hazard source location parameter is expanded to obtain the hazard source location space. The hazard source location space acquisition module 40 further includes: a sample bearing change parameter set acquisition unit, the sample bearing change parameter set acquisition unit is used to collect a sample rainfall data set and a sample bearing parameter set, and annotate the bearing position change of the hazard source under different sample rainfall data and sample bearing parameters to obtain a sample bearing change parameter set; a bearing change parameter acquisition unit, the bearing change parameter acquisition unit is used to use the sample rainfall data set, the sample bearing parameter set and the sample bearing change parameter set to train a hazard source bearing change predictor, analyze the bearing position change of the rainfall data in the meteorological forecast data combined with the bearing parameters to obtain the bearing change parameters; the sample hazard source movement parameter set acquisition unit The acquisition unit is used to collect the sample wind data set, the sample hazard source movement coefficient set and the sample bearing change parameter set, and mark the movement distance of the hazard source under different sample wind data, sample hazard source movement coefficient and sample bearing change parameter to obtain the sample hazard source movement parameter set; the hazard source movement parameter acquisition unit is used to adopt the sample wind data set, the sample hazard source movement coefficient set, the sample bearing change parameter set and the sample hazard source movement parameter set to train the hazard source movement predictor, analyze the rainfall data and wind data in the meteorological forecast data, combine the bearing change parameter and the hazard source movement coefficient of the hazard source, and obtain the hazard source movement parameter; the hazard source position space acquisition unit is used to adopt the bearing change parameter and the hazard source movement parameter to set the bearing expansion distance and the hazard source movement expansion distance, expand the hazard source position parameters, and obtain the hazard source position space.

[0070] The specific configuration of the distribution network risk classification module 50 will be described in detail below. As described above, according to the line location space and the hazard source location space, the minimum distance information is calculated, and the distance change amplitude is calculated in combination with the stable distance measurement information. In combination with the minimum distance information, the distribution network risk classification is performed to obtain the distribution network risk level, and a judgment and warning are performed. The distribution network risk classification module 50 further includes: a minimum distance calculation unit, the minimum distance calculation unit is used to calculate the minimum distance between the line location space and the hazard source location space according to the line location space and the hazard source location space, and obtain the minimum distance information; a distance hazard coefficient calculation unit, the distance hazard coefficient calculation unit is used to calculate the distance hazard coefficient of the minimum distance information according to the safe distance between the distribution line and the hazard source; step S530, a distance change amplitude calculation unit, the distance change amplitude calculation unit is used to calculate the distance hazard coefficient of the minimum distance information according to the distance measurement information and minimum distance information, calculate the distance change range; a sample distribution network risk level set labeling unit, the sample distribution network risk level set labeling unit is used to collect the sample distance hazard coefficient set and the sample distance change range set, and label the sample distribution network risk level set according to the line accident probability under different sample distance hazard coefficients and sample distance change ranges; a distribution risk classifier construction unit, the distribution risk classifier construction unit is used to construct a distribution risk classifier based on a decision tree, using the sample distance hazard coefficient set, the sample distance change range set and the sample distribution network risk level set, classify the distance hazard coefficient and the distance change range, and obtain the line distribution network risk level; a discrimination and early warning unit, the discrimination and early warning unit is used to calculate the distribution network risk level according to the line distribution network risk level, and perform discrimination and early warning.

[0071] The specific configuration of the mobile ranging information acquisition module 60 will be described in detail below. As described above, according to the meteorological forecast data, the monitoring point of the mobile ranging device is adjusted to obtain a mobile monitoring point, the distribution line and the dangerous source are mobile ranging to obtain mobile ranging information, the minimum distance information is verified, and the distribution network risk level is updated and judged for early warning. The mobile ranging information acquisition module 60 further includes: a monitoring point space acquisition unit, the monitoring point space acquisition unit is used to obtain the monitoring point space of the mobile ranging device in the target distribution network; a mobile ranging influence amplitude acquisition unit, the mobile ranging influence amplitude acquisition unit is used to randomly select monitoring points in the monitoring point space, and perform mobile ranging influence analysis in combination with the meteorological forecast data to obtain. A mobile ranging impact amplitude; a mobile monitoring point selection unit, the mobile monitoring point selection unit is used to randomly select monitoring points for impact analysis, and then output the monitoring point with the smallest mobile ranging impact amplitude as the mobile monitoring point; a mobile ranging information acquisition unit, the mobile ranging information acquisition unit is used to perform mobile ranging on the distribution line and the hazardous source through the mobile ranging device at the mobile monitoring point to obtain mobile ranging information; a risk level updating unit, the risk level updating unit is used to verify whether the mobile ranging information is less than the minimum distance information. If so, the distribution network risk level is updated and judged and warned using the mobile ranging information and the distance change amplitude. If not, the distribution network risk level is not updated.

[0072] The distribution network risk warning device based on multi-data linkage provided in the embodiment of the present invention can execute the distribution network risk warning method based on multi-data linkage provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0073] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0074] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A distribution network risk early warning method based on multi-data linkage, characterized in that: The method comprises: By means of distribution network monitoring equipment, the line location parameters of the distribution lines in the target distribution network are collected, the images of the hazardous sources near the target distribution network are collected, and the stable ranging information of the distribution lines and hazardous sources under the stable state is obtained by measuring at the stable monitoring point by means of mobile ranging equipment, and the meteorological forecast data is collected by means of meteorological monitoring equipment; Performing hazard source feature recognition on the hazard source image to obtain a hazard source movement coefficient, a load-bearing parameter, and a hazard source position parameter of the hazard source; According to the meteorological forecast data, sag analysis and movement analysis of the distribution line are performed to obtain line sag change parameters and line movement parameters, and the line position parameters are expanded to obtain line position space; According to the meteorological forecast data combined with the hazard source movement coefficient and bearing parameters, the bearing position change and movement analysis of the hazard source is performed to obtain the bearing change parameters and hazard source movement parameters of the hazard source, and the hazard source position parameters are expanded to obtain the hazard source position space. Specifically, a sample wind data set, a sample hazard source movement coefficient set, a sample bearing change parameter set and a sample hazard source movement parameter set are used to train a hazard source movement predictor, and the rainfall data and wind data in the meteorological forecast data are analyzed in combination with the bearing change parameters and hazard source movement coefficient of the hazard source to obtain the hazard source movement parameters; the bearing change parameters and hazard source movement parameters are used to set the bearing expansion distance and the hazard source movement expansion distance, and the hazard source position parameters are expanded to obtain the hazard source position space; According to the line location space and the hazard source location space, the minimum distance information is calculated, and the distance change amplitude is calculated in combination with the stable distance measurement information. In combination with the minimum distance information, the distribution network risk classification is performed to obtain the distribution network risk level, and a judgment warning is performed; According to the meteorological forecast data, the monitoring points of the mobile ranging equipment are adjusted to obtain mobile monitoring points, mobile ranging is performed on the distribution lines and hazardous sources to obtain mobile ranging information, the minimum distance information is verified, and the distribution network risk level is updated and judged and warned.

2. The distribution network risk early warning method based on multi-data linkage according to claim 1 is characterized in that: By means of distribution network monitoring equipment, line location parameters of distribution lines in a target distribution network are collected, images of hazardous sources near the target distribution network are collected, and ranging information of the distribution lines and hazardous sources in a stable state is obtained by measuring at a stable monitoring point using a mobile ranging device, including: By using the distribution network monitoring equipment, the line sag parameters and line coordinate parameters of the distribution lines in the target distribution network in space are collected as line position parameters; Collecting images of hazardous sources near the target distribution network; By means of mobile distance measuring equipment, distance measuring information of the power distribution lines and dangerous sources in a stable state is collected at a stable monitoring point; Through meteorological monitoring equipment, the maximum rainfall data and maximum wind speed data within a preset time range in the future are collected as meteorological forecast data.

3. The distribution network risk early warning method based on multi-data linkage according to claim 1 is characterized in that: Performing hazard source feature recognition on the hazard source image to obtain a hazard source movement coefficient, a load parameter, and a hazard source position parameter of the hazard source includes: Collect a set of sample hazard source images, mark the movement amplitude variation coefficient of the hazard source under different wind forces and the bending amplitude under the bearing rainfall in the sample hazard source image, and mark the relative position parameters of the hazard source and the distribution network, and obtain a set of sample hazard source movement coefficients, a set of sample bearing parameters, and a set of sample relative position parameters; Using the sample hazard source image set, the sample hazard source movement coefficient set, the sample load-bearing parameter set and the sample relative position parameter set to train a hazard source feature identifier; Using the hazard source feature identifier, perform hazard source feature identification on the hazard source image to obtain the hazard source movement coefficient, load-bearing parameter and relative position parameter of the hazard source; The hazard source location parameter is calculated based on the relative location parameter and the line location parameter of the distribution line.

4. The distribution network risk early warning method based on multi-data linkage according to claim 1 is characterized in that: According to the meteorological forecast data, sag analysis and movement analysis of the distribution line are performed to obtain line sag change parameters and line movement parameters, including: According to the historical monitoring data of the line, a set of sample line sag parameters and a set of sample rainfall data of the line in a stable state are collected, and the sag change parameters of the line under different sample line sag parameters and sample rainfall data are marked to obtain a set of sample line sag change parameters; Using the sample line sag parameter set, the sample rainfall data set and the sample line sag change parameter set to train a line sag change predictor; Using the line sag change predictor, the line sag parameters in the line location parameters of the distribution line are combined with the rainfall data in the meteorological forecast data to perform sag change prediction to obtain the line sag change parameters; According to the meteorological forecast data, performing movement analysis of the distribution line to obtain line movement parameters; According to the line sag change parameter, the sag expansion distance is set, according to the line movement parameter, the line movement expansion distance is set, and the line position parameter is expanded to obtain the line position space.

5. The distribution network risk early warning method based on multi-data linkage according to claim 4 is characterized in that: According to the meteorological forecast data, the movement analysis of the distribution line is performed to obtain line movement parameters, including: Collecting a set of sample line sag parameters, a set of sample rainfall data, and a set of sample wind data, and marking the moving distances of the lines under different sample line sag parameters, sample rainfall data, and sample wind data, to obtain a set of sample line movement parameters; Using the sample line sag parameter set, the sample rainfall data set, the sample wind data set and the sample line movement parameter set to train a line movement predictor; The line movement predictor is used to perform movement analysis on the line sag parameters within the line location parameters of the distribution line in combination with the rainfall data and wind data within the meteorological forecast data to obtain the line movement parameters.

6. The distribution network risk early warning method based on multi-data linkage according to claim 1 is characterized in that: According to the meteorological forecast data combined with the hazard source movement coefficient and bearing parameters, the hazard source bearing position change and movement analysis is performed, including: Collecting a sample rainfall data set and a sample bearing parameter set, and marking the changes in the bearing position of the hazard source under different sample rainfall data and sample bearing parameters, to obtain a sample bearing change parameter set; The sample rainfall data set, the sample bearing parameter set and the sample bearing change parameter set are used to train a hazard source bearing change predictor, and the rainfall data in the meteorological forecast data is combined with the bearing parameters to analyze the bearing position change, so as to obtain the bearing change parameters; A sample wind data set, a sample hazard source movement coefficient set and a sample load change parameter set are collected, and the movement distance of the hazard source under different sample wind data, sample hazard source movement coefficients and sample load change parameters are marked to obtain a sample hazard source movement parameter set.

7. The distribution network risk early warning method based on multi-data linkage according to claim 1 is characterized in that: According to the line location space and the hazard source location space, the minimum distance information is calculated, and the distance change amplitude is calculated in combination with the stable distance measurement information. The distribution network risk classification is performed in combination with the minimum distance information, including: According to the line location space and the hazard source location space, the minimum distance between the line location space and the hazard source location space is calculated to obtain minimum distance information; Calculate the distance risk coefficient of the minimum distance information according to the safety distance between the distribution line and the danger source; Calculate the distance change amplitude according to the distance measurement information and the minimum distance information; Collect the set of sample distance hazard coefficients and the set of sample distance variation ranges, and mark and obtain the sample distribution network risk level set according to the line accident probability under different sample distance hazard coefficients and sample distance variation ranges; Based on the decision tree, a distribution risk classifier is constructed by using the sample distance risk coefficient set, the sample distance change range set and the sample distribution network risk level set, and the distance risk coefficient and the distance change range are classified to obtain the line distribution network risk level; According to the risk level of the line distribution network, the risk level of the distribution network is calculated and a judgment and early warning are carried out.

8. The distribution network risk early warning method based on multi-data linkage according to claim 1 is characterized in that: According to the meteorological forecast data, the monitoring point of the mobile distance measuring device is adjusted to obtain the mobile monitoring point, the mobile distance measuring of the distribution line and the dangerous source is performed to obtain the mobile distance measuring information, and the minimum distance information is verified, including: Acquire the monitoring point space of the mobile ranging device in the target distribution network; Randomly selecting monitoring points in the monitoring point space, and performing mobile ranging impact analysis in combination with the meteorological forecast data to obtain the mobile ranging impact amplitude; After the random selection of monitoring points for impact analysis, the monitoring point with the smallest impact of mobile ranging is output as the mobile monitoring point; At the mobile monitoring point, the mobile distance measuring device is used to perform mobile distance measuring on the power distribution line and the dangerous source to obtain mobile distance measuring information; Verify whether the mobile distance measurement information is less than the minimum distance information. If so, use the mobile distance measurement information and the distance change amplitude to update and judge the distribution network risk level and warn. If not, do not update the distribution network risk level.

9. A distribution network risk early warning device based on multi-data linkage, characterized in that: The device is used to implement the distribution network risk early warning method based on multi-data linkage according to any one of claims 1 to 8, and the device includes: A meteorological forecast data acquisition module, which is used to collect line location parameters of distribution lines in a target distribution network through distribution network monitoring equipment, collect images of hazardous sources near the target distribution network, and obtain stable ranging information of the distribution lines and hazardous sources in a stable state by measuring at a stable monitoring point through a mobile ranging device, and collect meteorological forecast data through meteorological monitoring equipment; A hazard source feature recognition module, the hazard source feature recognition module is used to perform hazard source feature recognition on the hazard source image to obtain a hazard source movement coefficient, a load-bearing parameter and a hazard source position parameter of the hazard source; A line location space acquisition module, the line location space acquisition module is used to perform sag analysis and movement analysis of the distribution line according to the meteorological forecast data, obtain line sag change parameters and line movement parameters, expand the line location parameters, and obtain line location space; A hazard source location space acquisition module, the hazard source location space acquisition module is used to perform a hazard source bearing position change and movement analysis based on the meteorological forecast data combined with the hazard source movement coefficient and bearing parameters, obtain the hazard source bearing change parameters and hazard source movement parameters, expand the hazard source location parameters, and obtain the hazard source location space; A distribution network risk classification module, which is used to calculate the minimum distance information according to the line location space and the hazard source location space, calculate the distance change amplitude in combination with the stable distance measurement information, classify the distribution network risk in combination with the minimum distance information, obtain the distribution network risk level, and perform judgment and warning; A mobile ranging information acquisition module is used to adjust the monitoring points of the mobile ranging equipment according to the meteorological forecast data, obtain mobile monitoring points, perform mobile ranging on the distribution lines and hazardous sources, obtain mobile ranging information, verify the minimum distance information, and update and identify early warnings for the distribution network risk level.

Images