A method and system for dynamic prediction and analysis of wildfire faults in power transmission lines

Abstract

A method and system for dynamic prediction and analysis of wildfire faults in power transmission lines relates to the field of wildfire prediction in power transmission lines. The method divides the power transmission lines into regions to obtain multiple sub-observation regions, identifies tower information for each sub-observation region, and obtains multiple key inspection regions. The multiple key inspection regions are divided into grades to obtain a risk level factor group for each key inspection region, and a risk coefficient is determined based on the risk level factor group. A preliminary prediction model is used to predict wildfires on the lines in each key inspection region to obtain a corresponding wildfire prediction grade. The risk coefficient of each key inspection region is assigned to the wildfire prediction grade to obtain a revised wildfire risk grade. The method divides the power transmission line regions into grades to determine risk coefficients of different grades, assigns the coefficients to the model prediction results, and further optimizes the model prediction results, thereby improving the accuracy of the final prediction results.

Description

Technical Field

[0001] The present invention relates to the field of transmission line wildfire prediction, and in particular to a method and system for dynamic prediction and analysis of transmission line wildfire faults. Background Art

[0002] In the past, predicting transmission line wildfire failures relied primarily on relatively simple methods and limited data sources. Early meteorological data acquisition relied primarily on sparsely distributed weather stations, resulting in low spatial resolution and difficulty accurately reflecting the complex and changing meteorological conditions along transmission lines. For example, in mountainous areas, weather stations are often far apart, making it difficult to effectively capture local microclimate differences, which are crucial for wildfire occurrence. In complex terrain such as valleys and hillsides, even small changes in temperature and humidity can determine whether vegetation is susceptible to fire.

[0003] Traditionally, monitoring vegetation around transmission lines relies primarily on manual field surveys, which are inefficient and difficult to implement for large-scale, high-frequency monitoring. Manual assessments of vegetation dryness are subjective and lack precision. Furthermore, it's difficult to fully capture information such as vegetation type, coverage, and spatial relationship to transmission lines—critical information for assessing wildfire risk.

[0004] With the development of science and technology, the current prediction of transmission line wildfire failures is to use big data systems to track and record meteorological data and plant data in real time, use machine learning algorithms to collect a large amount of sample data related to transmission line wildfires, build a prediction model, and import the real-time tracking data into the prediction model to judge the risk level. On the one hand, this method relies on a large amount of data to train the prediction model, and on the other hand, it also relies on the input learning method of the prediction model. If the learning method is incorrect, it will also affect the accuracy of the subsequent output results. In addition, current predictions all use models alone to make predictions, without using historical data to make actual predictions, and then combining the actual predictions with model predictions for data optimization, which leads to the risk prediction accuracy obtained by the prediction model is not high.

[0005] In view of this, this application is hereby filed. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for dynamic prediction and analysis of transmission line wildfire faults, which divides the transmission line area into levels, determines risk factors of different levels, assigns the coefficients to the model prediction results, and further optimizes the model prediction results, thereby improving the accuracy of the final prediction results.

[0007] The embodiment of the present invention is achieved as follows:

[0008] A method for dynamic prediction and analysis of transmission line wildfire faults includes the following steps:

[0009] S100: Divide the area according to the transmission line to obtain multiple sub-observation areas, identify the tower information of each sub-observation area, and obtain multiple key inspection areas; the tower information includes: tower quantity information, tower distribution information, and line status information between towers;

[0010] S200: Classify multiple key inspection areas into levels, obtain a risk level factor group for each key inspection area, and determine a risk coefficient based on the risk level factor group;

[0011] S300: Using the preliminary prediction model, a wildfire prediction is performed on the lines within each key inspection area to obtain a corresponding wildfire prediction level;

[0012] S400: Assigning the risk coefficient of each key inspection area to the wildfire prediction level to obtain a revised wildfire risk level, and using the wildfire risk level to issue an early warning of wildfire fault information for the lines in the key inspection area;

[0013] Among them, when dividing the key inspection areas into levels, the main level and the secondary level are determined separately, and the main level and the secondary level are merged into the preliminary level. The main level is determined by the historical short-circuit data between towers, and the secondary level is determined by the number of towers and the tower distribution information.

[0014] Furthermore, the primary level is determined by historical short-circuit data between towers, and the secondary level is determined by the number of towers and tower distribution information, specifically including the following steps:

[0015] The main grade is determined based on the short-circuit points and the frequency of short-circuit. The first additional number of the secondary grade is determined based on the number of towers associated with the short-circuit. The second additional number of the secondary grade is determined based on the tower distribution information in the key inspection area where the short-circuit occurs. The first additional number and the second additional number are assigned to the main grade to obtain the preliminary grade.

[0016] Furthermore, obtaining the risk level factor group for each key inspection area includes the following steps:

[0017] Determine the risk level factors within the key inspection area, screen the risk level factors based on the preliminary level, and use the screened risk level factors to construct a risk level factor group for the key inspection area. When screening the risk level factors, follow the following steps:

[0018] According to the short-circuit points and short-circuit frequencies, the main risk factors are traced back, and based on the main risk factors, the risk level factors are preliminarily screened to obtain the preliminary screening factor group;

[0019] Determine a first secondary risk factor based on the number of towers associated with the short circuit, and screen the initial screening factor group based on the first secondary risk factor to obtain a first screening factor group;

[0020] Determine a second secondary risk factor based on the distribution information of the towers in the key inspection area where the short circuit occurs, and screen the first screening factor group based on the second secondary risk factor to obtain a second screening factor group;

[0021] A risk level factor group is constructed based on the risk level factors in the second screening factor group.

[0022] Furthermore, determining the first secondary risk factor based on the number of towers associated with the short circuit includes: marking the tower where the short circuit occurs as a risky tower, obtaining the number of all risky towers in the key inspection area, calculating the proportion of risky towers in the key inspection area, and obtaining the first secondary risk factor;

[0023] Determining the second secondary risk factor based on the pole tower distribution information in the key inspection area where the short circuit occurs includes: analyzing the distribution information of all risk pole towers, obtaining the distribution shape of the risk pole towers in the key inspection area, and obtaining the second secondary risk factor according to the distribution shape of the risk pole towers.

[0024] Furthermore, the types of main risk factors include meteorological factors, vegetation factors, route factors and external factors;

[0025] The types of the first secondary risk factors include A: 0-20%, B: 20%-30%, C: 30%-70%, D: 70%-90%, E: 90%-100%;

[0026] The types of the second secondary risk elements include: linear style, circular style, arc style, fan style or scattered point style.

[0027] Furthermore, the method further includes the step of determining whether the main risk factor, the first secondary risk factor, and the second secondary risk factor are a special combination:

[0028] When the meteorological element in the main risk factor of the key inspection area is strong wind, the first secondary risk factor is A: 0-20%, and the second secondary risk factor is linear, the following analysis steps are required:

[0029] Obtain the direction of the lines on both sides of the short-circuit tower and the wind direction, and calculate the angle between the wind direction and the line direction;

[0030] If the angle is less than 30°, obtain the vegetation height and line height, and determine the difference between the line height and the vegetation height;

[0031] If the difference is greater than 0 and the short circuit frequency increases, it is determined that the short circuit is caused by the bird flock factor.

[0032] Furthermore, the risk coefficient of each key inspection area is assigned to the wildfire prediction level to obtain the revised wildfire risk level. The specific steps are as follows:

[0033] Obtain the wildfire prediction level of each key inspection area, then obtain the risk coefficient of the key inspection area, determine the combined weight, which includes the wildfire prediction level weight and the risk coefficient weight. The result after assigning the wildfire prediction level weight to the wildfire prediction level is combined with the result after assigning the risk coefficient weight to the risk coefficient to calculate the wildfire risk level.

[0034] Furthermore, historical actual transmission line wildfire information is obtained, and the wildfire prediction level of the key inspection area when the wildfire occurred in the past is compared with the risk coefficient of the key inspection area. The accuracy of the wildfire prediction level and the risk coefficient are determined respectively, and the combined weight is determined based on the accuracy.

[0035] Furthermore, multiple historical actual transmission line wildfire information is obtained, and the wildfire prediction level of the key inspection area when the wildfire occurred in the past is compared to determine the accuracy of the wildfire prediction level; and the line status information between the towers in the key inspection area is obtained;

[0036] Obtain the line status information between towers in the current key inspection area, compare it with the line status information between towers in the key area during historical fires, obtain the similarity factor, assign the similarity factor to the wildfire prediction level weight, and obtain the revised wildfire prediction level weight.

[0037] A dynamic prediction and analysis system for wildfire faults on power transmission lines includes: a region division unit, a level division unit, a prediction unit, and a correction unit. The region division unit is used to divide the region according to the transmission line to obtain multiple sub-observation areas, and to identify tower information for each sub-observation area to obtain multiple key inspection areas. The tower information includes: tower quantity information, tower distribution information, and line status information between towers.

[0038] The grading unit is used to grade multiple key inspection areas, obtain a risk grade factor group for each key inspection area, and determine a risk coefficient based on the risk grade factor group; wherein, when grading the key inspection areas, a primary grade and a secondary grade are determined respectively, and the primary grade and the secondary grade are combined into a preliminary grade, the primary grade is determined by historical short-circuit data between towers, and the secondary grade is determined by the number of towers and tower distribution information;

[0039] The prediction unit uses the preliminary prediction model to predict wildfires on the lines within each key inspection area and obtain the corresponding wildfire prediction level;

[0040] The correction unit is used to assign a wildfire prediction level to the risk coefficient of each key inspection area to obtain a corrected wildfire risk level, and use the wildfire risk level to issue an early warning of wildfire fault information of the lines in the key inspection area.

[0041] The beneficial effects of the embodiments of the present invention are:

[0042] The dynamic prediction and analysis method and system for transmission line wildfire faults provided in the embodiments of the present invention utilize steps such as refined regional division, grading of key inspection areas, refining of risk factor groups, determination of risk coefficients, preliminary prediction of wildfire risk levels, and correction and optimization of wildfire risk levels to achieve high-precision prediction of transmission line wildfire fault information. In particular, key inspection areas are determined through tower information and graded, further improving the prediction screening conditions. Taking into account the impact of risk factors on transmission line wildfire faults, the risk level factor group for each key inspection area is obtained, and the risk coefficient is finally determined. The risk coefficient is assigned to the wildfire prediction level initially predicted by the preliminary prediction model to obtain a corrected wildfire risk level. The key lies in taking into account the risk factors that cause transmission line short circuits. Through grade division and determination of risk coefficients, the wildfire prediction level is further corrected and optimized, significantly improving the reliability and accuracy of transmission line wildfire fault prediction, especially in areas with different tower information, thereby providing more accurate prediction services for the safe operation of transmission lines.

[0043] In general, the dynamic prediction and analysis method and system for transmission line wildfire failures provided by the embodiments of the present invention divides the transmission line area into levels, determines risk factors of different levels, assigns the coefficients to the model prediction results, and further optimizes the model prediction results, thereby improving the accuracy of the final prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A flowchart of the main steps of the analysis method provided in an embodiment of the present invention;

[0046] Figure 2 for Figure 1 A flow chart of step S200 of the analysis method shown;

[0047] Figure 3 for Figure 2A flowchart of step S270 of step 200 is shown;

[0048] Figure 4 for Figure 2 A flowchart of step S280 of step 200 is shown;

[0049] Figure 5 for Figure 1 A flow chart of step S400 of the analysis method shown;

[0050] Figure 6 for Figure 5 A flowchart of step S420 of step 400 is shown;

[0051] Figure 7 for Figure 6 A flowchart of step S423 of step 420 is shown;

[0052] Figure 8 A modular schematic diagram of an analysis system provided in an embodiment of the present invention.

[0053] Icons: 500-analysis system, 510-region division unit, 520-level division unit, 530-prediction unit, 540-correction unit. DETAILED DESCRIPTION

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0055] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0056] It should be understood that the terms "system," "device," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0057] As used herein and in the claims, unless the context clearly indicates otherwise, the terms "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list; a method or apparatus may also include additional steps or elements.

[0058] Flowcharts are used in the present invention to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0059] Example: Currently, the main cause of wildfires caused by transmission lines is short circuits, including short circuits caused by extreme weather, short circuits caused by vegetation contacting the lines, short circuits caused by human factors, short circuits caused by overloads, etc. In short, short circuits are the main factors that lead to fires caused by transmission lines.

[0060] Currently, transmission line wildfire failure prediction relies on big data systems to track and record meteorological and plant data in real time. Machine learning algorithms are then used to collect large amounts of sample data related to transmission line wildfires, build prediction models, and then assess risk by importing the real-time tracking data into the prediction models. This approach relies on a large amount of data to train the prediction models, significantly impacting the accuracy of predictions without a large amount of existing data. It also relies on the input learning method of the prediction models, and incorrect learning methods can affect the accuracy of subsequent output results.

[0061] In addition, actual research found that the occurrence of wildfires is affected by the complex interactions of multiple factors such as meteorology, vegetation, and topography. Although the model can take multiple variables into account, it may not be able to fully and accurately capture and model some extremely complex nonlinear interactions, resulting in prediction deviations. Relying solely on meteorological data and plant data for prediction is too narrow, ignoring the situation where other factors cause wildfire failures in transmission lines, thereby further reducing the accuracy of the prediction.

[0062] Furthermore, forecasting models are often constructed based on certain assumptions and simplifications, while the actual wildfire process is highly complex, with numerous uncertainties and random factors. For example, a model may assume that meteorological conditions are uniformly distributed across a given area. However, in reality, localized meteorological variations in mountainous areas can be extremely drastic, contradicting these assumptions and thus affecting the accuracy of the forecasting model.

[0063] In addition to using predictive models for prediction, field surveys are also used in actual work. The collected data is statistically analyzed through field surveys to determine the risk of wildfires on transmission lines. This method is more accurate than model predictions, but it has greater limitations, especially for real-time predictions, which require a lot of manpower and material resources. After comparative analysis, we found that combining predictive models with actual surveys can not only improve the accuracy of predictions, but also does not consume a lot of manpower and material resources.

[0064] Based on the above reasons and ideas, please refer to Figure 1 This embodiment provides a method for dynamic prediction and analysis of power transmission line wildfire faults, comprising the following steps:

[0065] S100: Divide the area according to the transmission line to obtain multiple sub-observation areas, identify the tower information of each sub-observation area, and obtain multiple key inspection areas; the tower information includes: tower quantity information, tower distribution information, and line status information between towers;

[0066] For example, one kilometer to the left and one kilometer to the right of a predetermined transmission line are included in the wildfire detection range, thereby obtaining multiple sub-observation areas along the transmission line.

[0067] This step indicates that the transmission lines within the prediction range are recorded as lines to be monitored, and the area width is delineated according to one kilometer on each side of the transmission line to obtain multiple sub-observation areas, thereby determining the range of the transmission line that currently needs to be detected. In addition, the sub-observation area is further divided according to the tower information of the transmission line, that is, the key inspection area is divided in multiple sub-observation areas through the tower quantity information, tower distribution information and tower line status information, thereby narrowing the key detection range, so as to facilitate in-depth monitoring and analysis of wildfire faults caused by transmission lines, and provide a basic guarantee for improving prediction accuracy; among them, the tower quantity information mainly indicates the specific number of towers in the key inspection area, the tower distribution information mainly indicates the distribution pattern formed by the combination of all towers in the key inspection area, such as: linear distribution, concentrated distribution and dispersed distribution; the tower line status information mainly indicates the transmission current, line type, wiring method and line direction of the line. In other embodiments, the tower model, tower wiring method, etc. can also be considered.

[0068] S200: Divide multiple key inspection areas into levels, obtain a risk level factor group for each key inspection area, and determine the risk coefficient based on the risk level factor group; this step indicates that the risk level of the divided key inspection areas is first represented, that is, the levels are divided, and each corresponding level covers different risk situations, for example, it is reflected by the risk level factors it covers, so that for the key inspection areas divided into corresponding levels, it is possible to obtain the multiple risk level factors it covers to form a risk level factor group, which is used as the key inspection area to represent the possible risk points that may cause transmission line failures.

[0069] Considering that each key inspection area can be divided into different levels (different risk situations), it is necessary to clarify the different risk situations or degrees covered by different levels when dividing them. Therefore, it is necessary to provide data representations for different situations for different levels. On the one hand, this facilitates the understanding of different levels of risk situations, and on the other hand, it facilitates subsequent retrospective analysis. Specifically, when dividing key inspection areas into levels, a primary level and a secondary level are determined separately, and the primary and secondary levels are combined into a preliminary level. The primary level is determined by historical short-circuit data between towers, and the secondary level is determined by the number of towers and tower distribution information.

[0070] This step indicates that different (risk) levels are represented by a combination of main and sub-levels, which means that the main level determines the main risk level representation, and the sub-level determines the auxiliary representation of the key risk level. For example, for the main level, the towers in the key inspection area are marked with levels using existing information such as historical short-circuit data and towers, so as to obtain the frequency value of repeated short-circuit-induced transmission line wildfire failures in each key inspection area, and determine different main levels based on the frequency value of transmission line short circuits; for example, for the sub-level, the factors indirectly affecting transmission line wildfire failures can be obtained through the proportion of short-circuited towers and the distribution of short-circuited towers, thereby determining different sub-levels.

[0071] The risk factors that cause short circuits are obtained through different levels. By screening the risk factors, the risk factors corresponding to the levels of different key inspection areas are determined, and finally the risk coefficient of the key inspection area is obtained. The accuracy of the prediction is improved from another perspective through historical data.

[0072] S300: Using the preliminary prediction model, a wildfire prediction is performed on the lines within each key inspection area to obtain a corresponding wildfire prediction level;

[0073] The preliminary prediction model refers to an existing transmission line wildfire prediction model, which predicts transmission line wildfires through real-time analysis of weather and vegetation. This step represents a preliminary prediction of current transmission line wildfire faults using the existing model, thereby obtaining a wildfire prediction level for each key inspection area, and using this wildfire prediction level as the basis for the final prediction data. In some embodiments, the preliminary prediction model can be implemented through the following steps:

[0074] S1 Preliminary Data Collection:

[0075] S11: Establish data connection with professional meteorological departments to obtain real-time and historical meteorological information such as temperature, relative humidity, wind speed, precipitation, air pressure and lightning activities along the transmission lines at a stable frequency of hourly frequency.

[0076] S12: Use high-resolution satellite remote sensing technology to monitor vegetation conditions around transmission lines on a quarterly basis, and combine field surveys to calibrate data accuracy and identify vegetation types in detail.

[0077] S13: Every 15 minutes, operating parameters such as load current, voltage, and conductor temperature are collected through sensors installed on the line.

[0078] S2 data preprocessing:

[0079] S21: Comprehensively check all types of collected data for missing values ​​and outliers. For missing values, use the mean filling method, that is, fill the gaps with the average value of the historical data of the feature to ensure data integrity; for outliers, use the 3 times standard deviation method to identify and correct them, and eliminate erroneous or extreme data;

[0080] S22: Normalize meteorological data, converting temperature, humidity, and other data to a range of 0 to 1 to facilitate model calculations and comparisons. One-hot encode vegetation types into binary vectors to highlight the varying impacts of different vegetation types on wildfire risk. Furthermore, calculate the vegetation dryness index based on temperature and humidity data to provide a visual reflection of vegetation flammability.

[0081] S3 Data Calculation: After model training and optimization is complete, real-time meteorological, vegetation, and line operation data are continuously input. The model rapidly estimates the probability of wildfires along the transmission lines within the next 24 and 48 hours. If the probability exceeds the 30% threshold, an alert is immediately triggered and sent to operations and maintenance personnel, along with a detailed risk analysis and identifying the contributing factors.

[0082] In this embodiment, the wildfire prediction level is displayed in the form of a percentage, i.e., 0%-100%. The higher the percentage, the higher the probability of a fire on the transmission line. The wildfire prediction level is obtained by classifying the fire probability calculated by the preliminary prediction model and the wildfire prediction level.

[0083] S400: Assigning a wildfire prediction level to the risk coefficient of each key inspection area to obtain a revised wildfire risk level, and using the wildfire risk level to issue an early warning of wildfire fault information for the lines within the key inspection area.

[0084] This step indicates that the determined risk coefficient is assigned to the wildfire prediction level predicted by the preliminary model of the key inspection area through risk factor analysis, and then the wildfire prediction level is further revised and optimized to determine the final wildfire risk level.

[0085] This embodiment combines model prediction with actual risk detection results. It not only utilizes the advantages of the prediction model's rapid response, wide range, real-time response and resource saving, but also combines the advantages of the high accuracy of the actual prediction. By effectively combining the two, it not only ensures the rapid response of the overall prediction but also improves the accuracy of the prediction.

[0086] Through the above technical solution, by using the steps of refined area division, grading of key inspection areas, refining of risk factor groups, determination of risk coefficients, preliminary prediction of wildfire risk levels, and correction and optimization of wildfire risk levels, high-precision prediction of transmission line wildfire fault information is achieved. In particular, key inspection areas are determined through tower information, and key inspection areas are graded, which further improves the prediction screening conditions. Taking into account the impact of risk factors on transmission line wildfire faults, the risk factor group of each key inspection area is obtained, and the risk coefficient is finally determined. The risk coefficient is assigned to the wildfire prediction level initially predicted by the preliminary prediction model to obtain the corrected wildfire risk level. The key is to take into account the risk factors that cause transmission line short circuits. Through grade division and determination of risk coefficients, the wildfire prediction level is further corrected and optimized, which significantly improves the reliability and accuracy of transmission line wildfire fault prediction, especially in areas with different tower information, thereby providing more accurate prediction services for the safe operation of transmission lines.

[0087] Considering that the main inducing factor of transmission line wildfire failure is transmission line short circuit, when determining the main level, the main level is determined by the historical short circuit data between towers; in addition, considering that when determining the secondary level, the auxiliary representation of the key risk level is taken into account, some other factors also affect the cause of transmission line wildfire failure. For example, when the number of short-circuited towers per unit area is large, the probability of transmission line wildfire in the area will increase accordingly; for example, when the distance between the short-circuited towers is too close and too dense, the probability of transmission line wildfire in the area will also increase accordingly.

[0088] Please refer to the Figure 2 In this embodiment, the secondary grade is determined by the number of towers and the tower distribution information, which specifically includes the following steps: S210: determining the primary grade based on the short-circuit point and the short-circuit frequency; S220: determining the first additional number of the secondary grade based on the number of towers associated with the short circuit; S230: determining the second additional number of the secondary grade based on the tower distribution information in the key inspection area where the short circuit occurs; S240: assigning the first additional number and the second additional number to the primary grade to obtain a preliminary grade.

[0089] Through the above steps, the primary grade is determined based on the short-circuit point and frequency, the first additional number for the secondary grade is determined based on the number of towers associated with the short-circuit, and the second additional number for the secondary grade is determined based on the tower distribution information within the key inspection area where the short-circuit occurred. This effectively combines the primary and secondary factors, with the primary factor taking the primary position and the secondary factors taking the secondary position, ensuring the accuracy of the regional division. Furthermore, the division of the secondary grades takes into account the influence of multiple secondary factors, and by setting additional numbers, each of these secondary factors is statistically analyzed separately, thus ensuring the breadth and accuracy of the division data.

[0090] Specifically, in some embodiments, the calculation of the preliminary grade can be achieved in the following manner: preliminary grade = main grade * 60% + sub-grade first additional number * 30% + sub-grade second additional number * 10%; when determining the main grade, it is determined based on the number of short-circuit points and the maximum value of the short-circuit frequency, A: maximum value ≤ 3; B: 4 < maximum value ≤ 9; C: 10 < maximum value ≤ 15; D: maximum value ≥ 16; when calculating the preliminary grade, each grade in the main grade accounts for 25%; for example, if the number of short-circuit points in a key inspection area is 8 and the short-circuit frequency is 12, the main grade is C. When calculating the preliminary grade: preliminary grade = 75% * 60% + sub-grade first additional number * 30% + sub-grade second additional number * 10%, that is, preliminary grade = 45% + sub-grade first additional number * 30% + sub-grade second additional number * 10%.

[0091] At this time, when determining the first additional number of the sub-grade, a: the number of associated towers ≤ 3; b: 4<the number of associated towers ≤ 10; c: 11<the number of associated towers ≤ 20; d: the number of associated towers ≥ 21; each grade accounts for 25% of the proportion of the first additional number; for example, if the number of short-circuit associated towers in a key inspection area is 9, then its first additional number grade is b, and its proportion is 50%, that is, preliminary grade = 45% + 50%*30% + sub-grade second additional number * 10%.

[0092] Then, when determining the second additional number of the sub-grade, it is determined based on the pole tower distribution information in the key inspection area where the short circuit occurs. The distribution information can be directly determined based on the relative positions of the pole towers in the key inspection area, for example, it can be divided into linear style, circular style, arc style, fan style or scattered point style; when dividing the weight of each style, it can be adjusted according to actual conditions, for example: linear style: 20%; circular style: 40%; arc style: 60%; fan style: 80%; scattered point style: 90%; when the distribution style of the pole towers in a key inspection area is an arc style, the preliminary grade = 45% + 15% + 60% * 10%; the final preliminary grade = 66%.

[0093] It should be noted that in actual operations, other calculation methods can be adopted according to different scenarios in order to distinguish different ways of obtaining risk levels; of course, the weights of the main level, sub-level, sub-level first additional number and sub-level second additional number can also be adaptively adjusted according to actual conditions to adapt to changes in different regions and further improve data accuracy.

[0094] Another thing that needs to be explained is that in some embodiments, the transmission line wildfire failure prediction can be directly performed based on the preliminary level, and this preliminary level represents the final prediction level; similarly, in other embodiments, the wildfire prediction level predicted by the preliminary prediction model can also be directly used to represent the final prediction level.

[0095] In other embodiments, in order to further improve the accuracy and precision of the predicted data, the model prediction can be combined with the preliminary grade. By assigning different weights to the model prediction and the preliminary grade, and then combining the data of the two, the accuracy of the data can be improved. In combination with the above example data, assuming that a weight of 60% is assigned to the model prediction and a weight of 40% is assigned to the preliminary grade, when the wildfire prediction grade predicted by the model is 70%, then the final wildfire grade = 70% * 60% + 66% * 40%; that is, the final wildfire grade = 42% + 26.4% = 68.4%. In some embodiments, the final wildfire grade can also be used as the final prediction grade. It should be noted that when this method is used, the weights assigned to the prediction model and the preliminary grade can be adaptively adjusted according to the actual situation; in addition, in the actual operation process, other calculation methods can be used according to different scenarios in order to distinguish different ways of obtaining risk levels.

[0096] In this embodiment, in order to further improve the accuracy of the prediction data, please refer to Figure 2 By obtaining the risk level factor group of each key inspection area, determining the risk coefficient based on the risk level factor group, assigning the risk coefficient of each key inspection area to the wildfire prediction level, and obtaining the corrected wildfire risk level, the wildfire failure of the transmission line is predicted based on this wildfire risk level; in this process, it is first necessary to obtain the risk level factor group of each key inspection area, which specifically includes the following steps:

[0097] S250: Determine the risk level factors in the key inspection area, screen the risk level factors based on the preliminary level, and use the screened risk level factors to construct a risk level factor group for the key inspection area. When screening the risk level factors, follow the following steps:

[0098] S260: Tracing the main risk factors based on the short-circuit points and short-circuit frequencies, and preliminarily screening the risk level factors based on the main risk factors to obtain a preliminary screening factor group;

[0099] S270: Determine a first secondary risk factor based on the number of towers associated with the short circuit, and screen the initial screening factor group based on the first secondary risk factor to obtain a first screening factor group;

[0100] S280: determining a second secondary risk factor based on the distribution information of the towers in the key inspection area where the short circuit occurs, and screening the first screening factor group based on the second secondary risk factor to obtain a second screening factor group;

[0101] S290: Constructing a risk level factor group based on the risk level factors in the second screening factor group.

[0102] This step indicates that different conditions are used to conduct segmented screening of risk level factors in key inspection areas. By screening the main risk factors, the first secondary risk factors and the second secondary risk factors, the risk level factor group is finally determined, thereby achieving preliminary screening of the data. The purpose of this design is to be able to quickly screen the data, and through layered screening, the data can be screened more deeply, thereby further ensuring the accuracy of the final data, and providing refined support for improving the accuracy of the prediction level.

[0103] When tracing the primary risk factor based on a short circuit point, the focus is on the specific coordinates of the short circuit point and its geographic location, for example, near a city or densely populated area. If the short circuit point is located on the edge of a city or near a densely populated area, a wildfire could quickly spread to the urban area, threatening the lives and property of residents, and the risk level should be determined as high. For example, if the short circuit point is located at the urban-rural fringe, surrounded by numerous residential and commercial areas, once a wildfire is caused by a short circuit, the fire can easily spread rapidly through surrounding buildings and vegetation.

[0104] For example, if a short circuit point is located in a remote mountainous area with poor transportation, firefighting and rescue teams may struggle to reach it quickly. This can lead to wildfires spreading unchecked, burning large tracts of forest, and posing a high risk. If a short circuit point is located deep in a mountainous forest, far from the nearest town, with rugged roads, firefighting vehicles may have difficulty navigating quickly, making initial firefighting challenging.

[0105] In addition, if the short-circuit point is located in an open plain area with relatively little surrounding vegetation, which is conducive to firefighting operations, the possibility and speed of wildfire spread will be relatively low, and the risk level can be judged as medium or low.

[0106] By determining the location of short-circuit points, we can further analyze the impact range of wildfires, their development trends, and the difficulty of firefighting. Furthermore, based on the short-circuit points, we can further analyze the causes and triggers of different short-circuit points, thereby analyzing the main risk factors. This data can then be compiled into statistical data to provide a data foundation for subsequent analysis of the main risk factors of short-circuit fires.

[0107] In the primary risk analysis based on short circuit frequency, the primary focus is on the number of short circuits within a specific inspection area. This number of short circuits can be used to identify the primary risk factors that may cause short circuits, such as those caused by the condition of the transmission line (line aging, defects), the surrounding environment (vegetation, weather), and electrical equipment failures (insulator failure, transformer failure). By combining the short circuit locations and frequency, the primary risk factors can be effectively analyzed. A detailed database is created by collecting historical short circuit data on transmission lines within a specific area, including information such as the time, location, type (e.g., phase-to-phase, ground), environmental conditions (e.g., weather, vegetation), and line equipment status. Analysis of this data can reveal patterns in short circuit occurrence. For example, by counting short circuit frequencies in different seasons and weather conditions, the peak time periods and conditions can be identified, providing data support for tracing primary risk factors.

[0108] Specifically, the main risk factors are divided into: meteorological factors, vegetation factors, line factors and external factors.

[0109] By collecting data on short-circuit points and short-circuit frequencies, a main risk database is established. By analyzing the main risk database, the relationship between the corresponding short-circuit points, short-circuit frequencies and short-circuit risk levels is obtained, thereby forming a main risk data correspondence table. In the main risk data correspondence table, the short-circuit points, short-circuit frequencies and main risk factors are corresponded. Different short-circuit points and / or short-circuit frequencies correspond to different main risk factors, thereby also corresponding to different main risk coefficients; and thus different main risk factors can correspond to different main risk coefficients.

[0110] It should be noted that the main risk coefficient represents the probability value of a short circuit. When the main risk coefficient is higher, the probability of a short circuit is higher. Conversely, when the main risk coefficient is lower, the probability of a short circuit is lower.

[0111] Another thing that needs to be explained is that in addition to the above-mentioned method of using the database and the main risk data correspondence table to correspond the relationship between short-circuit points, short-circuit frequency, main risk factors and main risk coefficients, other conventional technical means such as big data models can also be used, which will not be elaborated here; its purpose is only to find the relationship between short-circuit points, short-circuit frequency, main risk factors and main risk coefficients through massive data, so as to correspond the data, so that in the subsequent work process, the main risk coefficient can be reversely deduced only through the main risk factors.

[0112] Please refer to Figure 3 and Figure 4In this embodiment, when determining the first secondary risk factor based on the number of towers associated with the short circuit, it includes: S271: marking the tower where the short circuit occurs as a risk tower, S272: obtaining the number of all risk towers in the key inspection area, S273: calculating the proportion of risk towers in the key inspection area to obtain the first secondary risk factor; determining the second secondary risk factor based on the tower distribution information in the key inspection area where the short circuit occurs includes: S281: analyzing the distribution information of all risk towers, S282: obtaining the distribution shape of the risk towers in the key inspection area, S283: obtaining the second secondary risk factor according to the distribution shape of the risk towers.

[0113] For example, if a short circuit affects only a few towers, it could be caused by a problem with the tower itself. For example, damaged insulators on the towers are a common cause. Long-term exposure to the outdoors and environmental factors can lead to cracking, contamination, and other problems, degrading insulation performance and causing a short circuit. Loose electrical connections on the towers can also cause a short circuit. When current flows through loose connections, arcing occurs, causing a short circuit.

[0114] When a short circuit involves multiple towers, it could be due to an overall line problem or external factors. Line aging is a significant factor. With age, conductor insulation ages and wears, potentially leading to insulation degradation in sections between towers and causing short circuits. Furthermore, severe weather conditions such as lightning strikes and high winds can affect multiple towers. Lightning strikes can directly strike a line, causing insulation breakdown; strong winds can cause conductors to swing excessively, leading to short circuits between conductors or between conductors and towers.

[0115] Furthermore, the proximity of short-circuit-related towers may be affected by environmental factors (vegetation and topography). For example, dense vegetation around the towers, especially tall trees close to the power lines, can cause short circuits due to fallen trees or branches contacting conductors. For short-circuit-related towers, investigate the surrounding vegetation to determine if any trees are located at a safe distance from the power lines. Furthermore, seasonal vegetation growth can affect the occurrence of short circuits. For example, during peak tree growth season, the distance between vegetation and power lines may decrease, increasing the risk of short circuits.

[0116] Furthermore, the topography of the towers can also affect short circuits. For example, towers located in low-lying, humid areas are susceptible to corrosion on their foundations, which can affect their stability and potentially cause them to tilt, shifting the distance between the conductors and the towers or other objects, leading to short circuits. If towers are located in mountainous areas, the impact of geological hazards such as rockfalls and landslides on the lines must also be considered, as these hazards can damage the lines and cause short circuits.

[0117] The first secondary risk database is established by collecting short-circuit-related data, including information such as the time of occurrence, the number of associated towers, tower location, surrounding environment, and short-circuit type. Through long-term accumulation and analysis of this data, this information is combined with the number of associated towers to map the risk of different short circuits. For example, by analyzing the changes in the number of towers associated with short circuits in different seasons and environments, the system can identify conditions and areas with high short-circuit incidence and calculate the different short-circuit risk levels associated with different numbers of associated towers.

[0118] Specifically, the first secondary risk factors include A: 0-20%, B: 20%-30%, C: 30%-70%, D: 70%-90%, E: 90%-100%;

[0119] During the specific implementation process, a first secondary risk data correspondence table can be established based on the data in the first secondary risk database, and the proportion of short-circuit associated towers can be matched with the first secondary risk coefficient, so that different first secondary risk coefficients can be obtained through different numbers of short-circuit associated towers.

[0120] It should be noted that the first secondary risk coefficient represents the probability value of a short circuit. When the first secondary risk coefficient is higher, the probability of a short circuit is higher. Conversely, when the first secondary risk coefficient is lower, the probability of a short circuit is lower.

[0121] Another thing that needs to be explained is that in addition to the above-mentioned method of using the first secondary database and the first secondary risk data correspondence table to correspond the relationship between the number of short-circuit associated towers and the first secondary risk factors and the first secondary risk coefficients, other conventional technical means such as big data models can also be used, which will not be elaborated here; its purpose is only to find the relationship between the number of short-circuit associated towers and the first secondary risk factors and the first secondary risk coefficients through massive data, so as to correspond the data, so that in the subsequent work process, the first secondary risk coefficient can be reversely deduced only through the first secondary risk factors.

[0122] Furthermore, when deriving the second secondary risk factor from the distribution pattern of risky towers, the distribution patterns can be categorized as linear, concentrated, and dispersed. For example, when the distribution pattern of risky towers is linear, the cause of the short circuit may be a line fault or a lightning strike. For example, conductors along the line may be damaged by external forces, such as being struck by flying rocks or scraped by construction equipment, causing insulation damage and a short circuit. Furthermore, long-term operation of conductors under high loads may lead to overheating and aging, resulting in a degradation of insulation performance. In this case, short circuits may occur continuously within a certain length of line, resulting in a linear distribution of associated towers. Furthermore, lightning may propagate along the line, striking linearly distributed towers and their connected conductors. Especially in areas with frequent lightning strikes, if line lightning protection measures are inadequate, such as improperly installed lightning conductors or ineffective arresters, lightning strikes can generate overvoltages on the lines between multiple towers, breaking down the insulation and causing a short circuit.

[0123] For example, when the risky poles are concentrated, and the short-circuit-related poles are concentrated in a certain area, this could be due to the specific environmental conditions of that area. For example, if the area is overgrown with vegetation, trees could come into contact with conductors, causing short circuits. Furthermore, if there are pollution sources such as factories or mines in the area, the accumulated dirt on the insulator surfaces could degrade insulation performance, leading to short circuits. Furthermore, concentrated poles may share common design, construction, or maintenance issues. For example, improper foundation treatment during tower construction could cause some towers to tilt, shifting the distance between conductors and the towers or other objects and causing short circuits. Furthermore, if the electrical equipment on the towers (such as insulators and hardware) is purchased from the same batch and contains quality defects, short circuits could occur simultaneously on multiple towers.

[0124] For example, when the concentration pattern of risky towers is dispersed, short circuits in these dispersed towers could be caused by random factors. For example, individual towers could be affected by bird nesting, which may contain conductive materials such as wire. During weather changes (such as strong winds), these conductive materials could attach to conductors, causing short circuits. Furthermore, unforeseen external forces, such as kite entanglement or balloon impacts, could also cause short circuits in individual towers. Furthermore, the seemingly dispersed distribution of short-circuit-related towers may be due to errors in data collection or transmission, resulting in inaccurate tower location information. For example, sensor failures or interference in communication lines can lead to erroneous short-circuit location information and misidentification of tower distribution. Furthermore, malfunctioning relay protection devices in the power system could cause some normal towers to be mistakenly identified as short-circuit-related towers.

[0125] During the specific implementation process, a second secondary risk database can be established based on the above data, and a second secondary risk data correspondence table can be established based on the data in the second secondary risk database to correspond the distribution pattern of the risk tower with the second secondary risk coefficient, so as to obtain different second secondary risk coefficients through the distribution patterns of different risk towers.

[0126] Specifically, the second secondary risk element is divided into: linear style, circular style, arc style, fan style or scattered point style.

[0127] In the specific implementation process, it should be noted that the second secondary risk coefficient represents the probability value of a short circuit. When the second secondary risk coefficient is higher, the probability of a short circuit is higher. Conversely, when the second secondary risk coefficient is lower, the probability of a short circuit is lower.

[0128] Another thing that needs to be explained is that in addition to the above-mentioned method of using the second database and the second risk data correspondence table to correspond the relationship between the risk tower distribution pattern and the second risk factor and the second risk coefficient, other conventional technical means such as big data models can also be used, which will not be elaborated here; its purpose is only to find the relationship between the risk tower distribution pattern and the second risk factor and the second risk coefficient through massive data, so as to correspond the data, so that in the subsequent work process, the second risk coefficient can be reversely deduced only through the second risk factor.

[0129] In addition to considering the above-described situations, there are also some situations that are not easy to analyze and judge. For example, when the meteorological factor in the key inspection area is strong wind, the first secondary risk factor is A: 0-20%, and the second secondary risk factor is linear. In this case, since the first secondary risk factor is of low level, the strong wind is first used as the main judgment basis in routine judgment. In addition, since the second secondary risk factor is linear, the probability of strong wind weather causing mutual influence of lines is low. Therefore, in routine judgment, the final forecast level will be determined only according to the level of strong wind, and the stronger the wind, the higher the forecast level. However, this process ignores the relationship between wind direction and line direction, as well as the influence of special situations such as bird flocks. Common sense knows that the angle between wind direction and line direction is 0-90°. Under the premise of the same wind force, the larger the angle, the greater the impact of the wind on the line, that is, the greater the swing amplitude of the line caused by strong wind. When the angle is smaller, the impact of the wind on the line will also decrease, that is, the swing amplitude of the line caused by strong wind will be smaller. Therefore, in this special case, the following steps are required:

[0130] Obtain the direction of the lines on both sides of the short-circuit tower and the wind direction, and calculate the angle between the wind direction and the line direction;

[0131] If the angle is less than 30°, obtain the vegetation height and line height, and determine the difference between the line height and the vegetation height;

[0132] If the difference is greater than 0 and the short circuit frequency increases, it is determined that the short circuit is caused by the bird flock factor.

[0133] The purpose of this design is not to simply determine that the short circuit must be caused by strong winds based on the main risk factor being strong winds, but to make further judgments on the overall situation (i.e. wind direction and line direction) to further determine the root cause of the short circuit. By making such judgments on special situations, the accuracy of the prediction and the depth of the judgment in special situations can be further improved.

[0134] Specifically, when revising the wildfire prediction level predicted by the preliminary prediction model, it is necessary to first determine the risk factor and assign the risk factor to the wildfire prediction level. When determining the risk factor, the risk factor mainly includes the primary risk factor, the first secondary risk factor, and the second secondary risk factor. The primary risk factor accounts for 60%, the first secondary risk factor accounts for 30%, and the second secondary risk factor accounts for 10%.

[0135] When calculating the risk factor, the risk factor = main risk factor * 60% + first secondary risk factor * 30% + second secondary risk factor * 10%.

[0136] It should be noted that the proportion of the main risk coefficient, the first secondary risk coefficient and the second secondary risk coefficient in the risk coefficient is not a fixed value, but can be adaptively adjusted according to actual conditions. The specific proportion can be adjusted according to actual conditions.

[0137] Please refer to Figure 5 In this embodiment, the risk coefficient of each key inspection area is assigned to a wildfire prediction level. The specific steps for obtaining the revised wildfire risk level are as follows:

[0138] S410: Obtain the wildfire prediction level of each key patrol area, and then obtain the risk coefficient of the key patrol area, S420: Determine the combined weight, S430: The combined weight includes the wildfire prediction level weight and the risk coefficient weight, and the result after assigning the wildfire prediction level weight to the two values ​​of the wildfire prediction level is combined with the result after assigning the risk coefficient weight to the risk coefficient and the weight is brought in to calculate the wildfire prediction level.

[0139] For example, if the meteorological data for a key inspection area indicates strong winds and thunderstorms, the proportion of at-risk towers is 75%, and the tower distribution pattern is fan-shaped, assuming that the primary risk factor is entered into the primary risk correspondence table to obtain a primary risk coefficient of 70%, the first secondary risk factor is entered into the first secondary risk correspondence table to obtain a first secondary risk coefficient of 80%, and the second secondary risk factor is entered into the second secondary risk correspondence table to obtain a second secondary risk coefficient of 70%. In this case, the risk coefficient = 70% * 60% + 80% * 30% + 70 * 10% = 73%. If the preliminary prediction model predicts a wildfire level of 80%, the risk coefficient is assigned to the wildfire level. If the combined weights are 50% each, the wildfire risk level = 73% * 50% + 80% * 50% = 76.5%, thus further revising the wildfire level.

[0140] It should be noted that the above example is only one method of calculating the wildfire prediction level. In practice, there are many different ways to calculate the risk factor. For example, if the combined weighted wildfire prediction level accounts for 60% and the risk factor accounts for 40%, then using the data from the previous example, the wildfire risk level = 73% * 60% + 80% * 40% = 75.8%.

[0141] Another thing that needs to be explained is that the merging weight is not a fixed weight, but can be adaptively adjusted according to actual conditions. Different weight distributions can be set artificially under different usage conditions or different weights can be distributed based on past data experience.

[0142] In addition, in actual work, it was found that when predicting wildfire risks through preliminary prediction models, there were certain errors in its accuracy. For example, sometimes the wildfire risk prediction level predicted a wildfire risk of 80%, but a wildfire actually occurred. This error also led to errors in the prediction of the final wildfire risk level, resulting in low data accuracy.

[0143] Based on the above situation, please refer to Figure 6 In this embodiment, to further improve the accuracy of wildfire prediction, the following steps are performed when determining the combined weight of the risk factor and the wildfire prediction level: S421: First, obtain historical information on actual transmission line wildfires. S422: Compare the wildfire prediction level of the key patrol area at the time of the historical wildfire with the risk factor of the key patrol area. S423: Determine the accuracy of the wildfire prediction level and the risk factor, respectively, and determine the combined weight based on the accuracy. For example, if the prediction accuracy of the wildfire prediction level in the historical data is lower than that of the risk factor, then when determining the combined weight, the risk factor will inevitably have a higher weight than the wildfire prediction level.

[0144] It should be noted that the above accuracy represents the average value of multiple data. For example, multiple wildfire prediction levels are compared with actual wildfire situations to determine the accuracy of the wildfire prediction level, and then the multiple accuracies are averaged.

[0145] In addition, please refer to Figure 7 In order to further determine the weight ratio of the wildfire prediction level and improve the accuracy of the final wildfire risk level prediction data, the following steps are performed when determining the weight ratio of the wildfire prediction level: S4231: First, obtain multiple historical actual transmission line wildfire information; S4232: Compare the wildfire prediction level of the key inspection area when the wildfire occurred in the past to determine the accuracy of the wildfire prediction level; S4233: and obtain the line status information between the towers in the key inspection area;

[0146] S4234: Obtain the line status information between the poles and towers in the current key inspection area, S4235: Compare the line status information between the poles and towers in the key area during historical fires to obtain a similarity factor, S4236: Assign the similarity factor to the wildfire prediction level weight to obtain a revised wildfire prediction level weight.

[0147] Specifically, a database of wildfire prediction accuracy and inter-tower line status information can be established, and the historical wildfire prediction accuracy can be matched with the inter-tower line status information one by one. Before the next prediction and allocation of merging weights, the inter-tower line status information of the area to be predicted is first entered into the database to obtain the similarity factor, and matched to the corresponding wildfire prediction accuracy, so as to determine the merging weight based on the wildfire prediction accuracy and the risk coefficient accuracy.

[0148] For example, if the current inter-tower line status information is 85% similar to the closest historical inter-tower line status information, then the similarity factor is 85%, and the current wildfire prediction accuracy is 85% of the wildfire prediction accuracy corresponding to the closest historical inter-tower line status information. This similarity factor can be used to further optimize the combined weight of the wildfire prediction level, thereby further improving data accuracy.

[0149] Through the above design, optimizing the combined weights of wildfire prediction level and risk factor allows, on the one hand, the combination of the prediction model and actual prediction to more accurately reflect the possibility and development trend of wildfires based on the changes in various factors at different times, making the prediction results more in line with actual conditions. On the other hand, through weight optimization, the errors and uncertainties of the prediction model and actual prediction can be balanced, making the final prediction results less error-prone and more reliable. After weight optimization, the model is more adaptable to different regions and environmental conditions, and can better cope with various complex situations. In addition, through weight optimization, it is clear in which cases the model prediction is more reliable and in which cases it is necessary to rely more on actual predictions. This helps to rationally allocate monitoring resources and avoid unnecessary waste of manpower, material and financial resources.

[0150] This embodiment also provides a transmission line wildfire fault dynamic prediction and analysis system 500, please refer to Figure 8 The modular schematic diagram of the transmission line wildfire fault dynamic prediction and analysis system is mainly used to divide the functional modules of the transmission line wildfire fault dynamic prediction and analysis system according to the embodiment of the above method. For example, each functional module can be divided, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, when each functional module is divided according to each function, Figure 8 What is shown is only a schematic diagram of a system / device.

[0151] Specifically, the transmission line wildfire fault dynamic prediction and analysis system includes: a region division unit 510, a level division unit 520, a prediction unit 530 and a correction unit 540, wherein the region division unit 510 is used to divide the region according to the transmission line to obtain multiple sub-observation areas, and identify the tower information of each sub-observation area to obtain multiple key inspection areas; wherein the tower information includes: tower quantity information, tower distribution information, and line status information between towers;

[0152] The grading unit 520 is used to grade multiple key inspection areas, obtain a risk grade factor group for each key inspection area, and determine a risk coefficient based on the risk grade factor group; wherein, when grading the key inspection areas, a main grade and a secondary grade are determined respectively, and the main grade and the secondary grade are combined into a preliminary grade, the main grade is determined by the historical short circuit data between towers, and the secondary grade is determined by the number of towers and the tower distribution information; in some embodiments, the main grade is determined according to the short circuit point and the short circuit frequency, and the first additional number of the secondary grade is determined according to the number of towers associated with the short circuit, and then The second additional number of the secondary grade is determined based on the tower distribution information within the key inspection area where the short circuit occurs, and the first additional number and the second additional number are assigned to the primary grade to obtain a preliminary grade. In addition, it is also used to determine the risk level factor within the key inspection area, screen the risk level factors based on the preliminary grade, and use the screened risk level factors to construct a risk level factor group for the key inspection area. When screening the risk level factors, the main risk factor is traced back based on the short circuit point and the short circuit frequency, and the risk level factors are preliminarily screened based on the main risk factor to obtain a preliminary screening factor group.

[0153] A first secondary risk factor is determined based on the number of towers associated with the short circuit, and the initial screening factor group is screened based on the first secondary risk factor to obtain a first screening factor group; a second secondary risk factor is determined based on the distribution information of towers in the key inspection area where the short circuit occurs, and the first screening factor group is screened based on the second secondary risk factor to obtain a second screening factor group; a risk level factor group is constructed based on the risk level factors in the second screening factor group. In some embodiments, the tower where the short circuit occurs is marked as a risk tower, the number of all risk towers in the key inspection area is obtained, and the proportion of risk towers in the key inspection area is calculated to obtain the first secondary risk factor; the distribution information of all risk towers is analyzed to obtain the distribution shape of the risk towers in the key inspection area, and the second secondary risk factor is obtained according to the distribution shape of the risk towers.

[0154] The prediction unit 530 uses the preliminary prediction model to perform wildfire prediction on the lines within each key inspection area and obtains the corresponding wildfire prediction level;

[0155] The correction unit 540 is used to assign the risk coefficient of each key inspection area to the wildfire prediction level to obtain a corrected wildfire risk level, and use the wildfire risk level to issue an early warning of wildfire fault information of the line in the key inspection area.

[0156] In the above embodiments, the more specific working process of each functional unit can refer to the corresponding content disclosed in the aforementioned method embodiment. In addition, each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive (SSD)).

[0157] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0158] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0160] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for dynamic prediction and analysis of transmission line wildfire faults, characterized in that: The steps include: S100: Divide the area according to the transmission line to obtain multiple sub-observation areas, identify the tower information of each sub-observation area, and obtain multiple key inspection areas; the tower information includes: tower quantity information, tower distribution information, and line status information between towers; S200: Classifying the plurality of key inspection areas into different levels, obtaining a risk level factor group for each key inspection area, and determining a risk coefficient based on the risk level factor group; S300: Performing wildfire prediction on each line within the key inspection area using a preliminary prediction model to obtain a corresponding wildfire prediction level; S400: Assigning the wildfire prediction level to the risk coefficient of each key inspection area to obtain a revised wildfire risk level, and issuing an early warning of wildfire fault information for the lines in the key inspection area based on the wildfire risk level; When the key inspection areas are graded, a primary grade and a secondary grade are determined respectively, and the primary grade and the secondary grade are combined into a preliminary grade. The primary grade is determined by historical short-circuit data between towers, and the secondary grade is determined by the number of towers and the distribution of towers. The primary level is determined by historical short-circuit data between towers, and the secondary level is determined by the number of towers and tower distribution information, specifically including the following steps: Determining the primary grade based on the short circuit point and the short circuit frequency, determining a first additional number for the secondary grade based on the number of towers associated with the short circuit, and determining a second additional number for the secondary grade based on the tower distribution information within the key inspection area where the short circuit occurs, assigning the first additional number and the second additional number to the primary grade to obtain the preliminary grade; The step of obtaining the risk level factor group for each key inspection area comprises the following steps: Determine the risk level factors within the key inspection area, screen the risk level factors based on the preliminary level, and use the screened risk level factors to construct a risk level factor group for the key inspection area, wherein the risk level factors are screened according to the following steps: According to the short-circuit points and short-circuit frequencies, the main risk factors are traced back, and the risk level factors are preliminarily screened based on the main risk factors to obtain a preliminary screening factor group; Determining a first secondary risk factor according to the number of towers associated with the short circuit, and screening the initial screening factor group based on the first secondary risk factor to obtain a first screening factor group; Determining a second secondary risk factor based on the distribution information of towers in the key inspection area where the short circuit occurs, and screening the first screening factor group based on the second secondary risk factor to obtain a second screening factor group; The risk level factor group is constructed based on the risk level factors in the second screening factor group.

2. The method for dynamic prediction and analysis of power transmission line wildfire faults according to claim 1, characterized in that: Determining the first secondary risk factor based on the number of towers associated with the short circuit includes: marking the tower where the short circuit occurs as a risk tower, obtaining the number of all risk towers in the key inspection area, calculating the proportion of risk towers in the key inspection area, and obtaining the first secondary risk factor; Determining the second secondary risk factor based on the pole tower distribution information in the key inspection area where the short circuit occurs includes: analyzing the distribution information of all risk pole towers, obtaining the distribution shape of the risk pole towers in the key inspection area, and obtaining the second secondary risk factor according to the distribution shape of the risk pole towers.

3. The method for dynamic prediction and analysis of power transmission line wildfire faults according to claim 2, characterized in that: The types of major risk factors include meteorological factors, vegetation factors, route factors and external factors; The types of the first secondary risk factors include A: 0-20%, B: 20%-30%, C: 30%-70%, D: 70%-90%, and E: 90%-100%; The types of the second secondary risk elements include: linear style, circular style, arc style, fan style or scattered point style.

4. The method for dynamic prediction and analysis of power transmission line wildfire faults according to claim 3, characterized in that: It also includes the step of determining whether the main risk factor, the first secondary risk factor and the second secondary risk factor are a special combination: When the meteorological element in the main risk factor of the key inspection area is strong wind, the first secondary risk factor is A: 0-20%, and the second secondary risk factor is linear, the following analysis steps are required: Obtain the direction of the lines on both sides of the short-circuit tower and the wind direction, and calculate the angle between the wind direction and the line direction; If the angle is less than 30°, obtain the vegetation height and line height, and determine the difference between the line height and the vegetation height; If the difference is greater than 0 and the short circuit frequency increases, it is determined that the short circuit is caused by the bird flock factor.

5. The method for dynamic prediction and analysis of power transmission line wildfire faults according to claim 1, characterized in that: The specific steps of assigning the risk coefficient of each key inspection area to the wildfire prediction level and obtaining the revised wildfire risk level are as follows: Obtain the wildfire prediction level of each key inspection area, then obtain the risk coefficient of the key inspection area, determine the combined weight, which includes the wildfire prediction level weight and the risk coefficient weight. The result after assigning the wildfire prediction level weight to the wildfire prediction level is combined with the result after assigning the risk coefficient weight to the risk coefficient to calculate the said wildfire risk level.

6. The method for dynamic prediction and analysis of power transmission line wildfire faults according to claim 5, characterized in that: Obtain historical actual transmission line wildfire information, compare the wildfire prediction level of the key inspection area when the wildfire occurred in the past with the risk factor of the key inspection area, determine the accuracy of the wildfire prediction level and risk factor respectively, and determine the merging weight based on the accuracy.

7. The method for dynamic prediction and analysis of power transmission line wildfire faults according to claim 6, characterized in that: Obtain multiple historical actual transmission line wildfire information, compare the wildfire prediction level of the key inspection area when the wildfire occurred in the past, and determine the accuracy of the wildfire prediction level; and obtain the line status information between the towers in the key inspection area; Obtain the line status information between towers in the current key inspection area, compare it with the line status information between towers in the key area during historical fires, obtain the similarity factor, assign the similarity factor to the wildfire prediction level weight, and obtain the revised wildfire prediction level weight.

8. A dynamic prediction and analysis system for power transmission line wildfire faults, characterized in that: A region division unit is configured to divide the region according to the transmission line to obtain a plurality of sub-observation regions, identify the tower information of each sub-observation region, and obtain a plurality of key inspection regions; wherein the tower information includes: tower quantity information, tower distribution information, and line status information between towers; A grading unit, the grading unit being configured to grade the plurality of key inspection areas, obtain a risk grade factor group for each key inspection area, and determine a risk coefficient based on the risk grade factor group; wherein, when grading the key inspection areas, a primary grade and a secondary grade are determined respectively, and the primary grade and the secondary grade are combined into a preliminary grade, the primary grade being determined by historical short-circuit data between towers, and the secondary grade being determined by information on the number of towers and information on the distribution of towers; A prediction unit, wherein the prediction unit uses a preliminary prediction model to perform wildfire prediction on each line within the key inspection area to obtain a corresponding wildfire prediction level; a correction unit configured to assign the wildfire prediction level to the risk coefficient of each key inspection area to obtain a corrected wildfire risk level, and to issue an early warning of wildfire fault information for the lines in the key inspection area based on the wildfire risk level; The primary level is determined by historical short-circuit data between towers, and the secondary level is determined by the number of towers and tower distribution information, specifically including the following steps: Determining the primary grade based on the short circuit point and the short circuit frequency, determining a first additional number for the secondary grade based on the number of towers associated with the short circuit, and determining a second additional number for the secondary grade based on the tower distribution information within the key inspection area where the short circuit occurs, assigning the first additional number and the second additional number to the primary grade to obtain the preliminary grade; The step of obtaining the risk level factor group for each key inspection area comprises the following steps: Determine the risk level factors within the key inspection area, screen the risk level factors based on the preliminary level, and use the screened risk level factors to construct a risk level factor group for the key inspection area, wherein the risk level factors are screened according to the following steps: According to the short-circuit points and short-circuit frequencies, the main risk factors are traced back, and the risk level factors are preliminarily screened based on the main risk factors to obtain a preliminary screening factor group; Determining a first secondary risk factor according to the number of towers associated with the short circuit, and screening the initial screening factor group based on the first secondary risk factor to obtain a first screening factor group; Determining a second secondary risk factor based on the distribution information of towers in the key inspection area where the short circuit occurs, and screening the first screening factor group based on the second secondary risk factor to obtain a second screening factor group; The risk level factor group is constructed based on the risk level factors in the second screening factor group.

Images