Power transmission line bird damage prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a power transmission line bird damage prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: analyzing multi-source heterogeneous data based on a risk prediction model to obtain a target risk probability value of bird damage in a power transmission line area; the risk prediction model comprises a first model, a second model, a third model and a fourth model; the first model is used for predicting bird damage risks based on the meteorological data and the biological characteristic data; the second model is used for predicting bird damage risks based on the power transmission line data and the geographical environment data; the third model is used for predicting bird damage risks based on meteorological data; the fourth model is used for predicting bird damage risks based on bird damage defect data; and based on the target risk probability value and a preset risk grade range, predicting a bird damage risk grade of the power transmission line area, and carrying out risk early warning based on the bird damage risk grade. According to the invention, the problems of low risk assessment accuracy and insufficient early warning timeliness are solved, and early prediction and active early warning of bird damage risks are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system transmission line disaster early warning, and in particular to a transmission line bird damage prediction method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the rapid development of China's power industry and the continuous improvement of the ecological environment, bird activities are becoming more and more frequent, and bird damage accidents on transmission lines have become one of the important factors affecting the safe and stable operation of the power grid. The traditional anti-bird damage work mainly relies on manual inspection and passive protection equipment installation, which has the problems of large workload, poor timeliness, insufficient protection targeting, etc. In recent years, with the rapid development of new generation information technologies such as Internet of Things, artificial intelligence and big data, new technical means have been provided for intelligent monitoring and active early warning of transmission lines. At present, a large amount of research work has been carried out on bird identification detection and online monitoring of transmission lines, but most of them focus on single-dimensional post-detection or simple early warning, and lack of deep mining of bird damage occurrence regularity and active prediction capability. SUMMARY

[0003] The present application provides a transmission line bird damage prediction method, device, electronic device and storage medium to solve the problems of low risk assessment accuracy and insufficient early warning timeliness, and realizes the early prediction and active early warning of bird damage risk.

[0004] According to one aspect of the present application, a transmission line bird damage prediction method is provided, the method comprising:

[0005] Obtaining multi-source heterogeneous data of a transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, transmission line data, biological characteristic data and bird damage defect data;

[0006] Analyzing the multi-source heterogeneous data based on a risk estimation model to obtain a target risk probability value of bird damage in the transmission line area; the risk estimation model includes a first model, a second model, a third model and a fourth model; the first model is used to predict bird damage risk based on meteorological data and biological characteristic data; the second model is used to predict bird damage risk based on transmission line data and geographical environment data; the third model is used to predict bird damage risk based on meteorological data; the fourth model is used to predict bird damage risk based on bird damage defect data;

[0007] Based on the target risk probability value and a preset risk level range, the bird damage risk level of the transmission line area is predicted, and risk early warning is carried out based on the bird damage risk level.

[0008] According to another aspect of the present application, a transmission line bird damage prediction device is provided, the device comprising:

[0009] a data acquisition module configured to acquire multi-source heterogeneous data of a power transmission line area, wherein the multi-source heterogeneous data comprises meteorological data, geographical environment data, power transmission line data, biological characteristic data and bird damage defect data;

[0010] an analysis module configured to analyze the multi-source heterogeneous data based on a risk estimation model to obtain a target risk probability value of bird damage in the power transmission line area, wherein the risk estimation model comprises a first model, a second model, a third model and a fourth model, the first model is configured to predict bird damage risk based on the meteorological data and the biological characteristic data, the second model is configured to predict bird damage risk based on the power transmission line data and the geographical environment data, the third model is configured to predict bird damage risk based on the meteorological data, and the fourth model is configured to predict bird damage risk based on the bird damage defect data;

[0011] a prediction module configured to predict a bird damage risk level of the power transmission line area based on the target risk probability value and a preset risk level range, and to perform risk warning based on the bird damage risk level.

[0012] According to another aspect of the present application, an electronic device is provided, which comprises:

[0013] at least one processor; and

[0014] a memory connected to the at least one processor in communication; wherein

[0015] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the power transmission line bird damage prediction method according to any one of the embodiments of the present application.

[0016] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to perform the power transmission line bird damage prediction method according to any one of the embodiments of the present application when executed by the processor.

[0017] The technical scheme of the embodiment of the present application acquires multi-source heterogeneous data of a power transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, power transmission line data, biological characteristic data and bird damage defect data; the value of the existing data resources is fully mined and utilized. Then, the multi-source heterogeneous data is analyzed based on a risk estimation model to obtain a target risk probability value of bird damage of the power transmission line area; the risk estimation model includes a first model, a second model, a third model and a fourth model; the first model is used for predicting bird damage risk based on meteorological data and biological characteristic data; the second model is used for predicting bird damage risk based on power transmission line data and geographical environment data; the third model is used for predicting bird damage risk based on meteorological data; the fourth model is used for predicting bird damage risk based on bird damage defect data; a multi-model fusion decision mechanism effectively integrates the advantages of different models, and reduces the prediction bias and uncertainty. Further, based on the target risk probability value and a preset risk level range, a bird damage risk level of the power transmission line area is predicted, risk warning is performed based on the bird damage risk level, the problems of low risk assessment accuracy and insufficient timeliness of early warning are solved, and the bird damage risk is predicted in advance and actively warned.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0020] Figure 1 is a flowchart of a power transmission line bird damage prediction method according to an embodiment of the present application;

[0021] Figure 2 is a flowchart of another power transmission line bird damage prediction method according to an embodiment of the present application;

[0022] Figure 3 is a structural schematic diagram of a power transmission line bird damage prediction device according to an embodiment of the present application;

[0023] Figure 4 is a structural schematic diagram of an electronic device for implementing the power transmission line bird damage prediction method according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application, so that those skilled in the art can better understand the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] Embodiment one

[0027] Figure 1 A flowchart of a power transmission line bird damage prediction method provided by the embodiment of the present application, the embodiment can be applicable to the case of predicting bird damage to the power transmission line, and the method can be executed by a power transmission line bird damage prediction device. The power transmission line bird damage prediction device can be realized in the form of hardware and / or software, and can be configured in any electronic device with network communication function. As shown in the figure, the power transmission line bird damage prediction method of the present application can include: Figure 1

[0028] S110, acquiring multi-source heterogeneous data of the power transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, power transmission line data, biological characteristic data and bird damage defect data.

[0029] The meteorological data can be real-time weather data and future preset hour refined weather forecast data of the power transmission line area, and the data content of the meteorological data covers temperature, humidity, wind speed, wind direction, precipitation, air pressure and other key meteorological elements, and the spatial resolution reaches the preset kilometer grid scale. For example, the preset kilometer can be 5 kilometers, and the preset hour can be 72 hours.

[0030] ​The geographic environment data can be geographic information system (GIS) platform data, which can include the precise longitude and latitude coordinates of each tower, elevation data, and environmental characteristic data such as the terrain slope, slope direction information, land use type, river and lake distribution, and forest vegetation coverage within a one-kilometer range.

[0031] The power transmission line data can be basic account data of the power transmission line region, which can include detailed technical parameter information such as the line name, voltage level, start and end coordinates, tower number, tower type, tower height, cross arm form, and insulator model.

[0032] The biological characteristic data can be the biological characteristics of common birds in the power transmission line region, which can be stored in a biological characteristic database and can cover a variety of bird species that pose a greater threat to the power transmission line, including detailed ecological information such as the size of each bird, the length of the wingspan, the preferred flight height, the migration time rule, the breeding season cycle, the nest-building habit characteristics, and the activity period preference.

[0033] The bird damage defect data can be the bird damage fault records in the power transmission line region in the past pre-set years, and the bird damage defect data of each power transmission line region can be stored in a historical bird damage defect database to facilitate quick access to the bird damage defect data of the power transmission line region. The bird damage defect data can include detailed information such as the fault occurrence time, the fault tower number, the bird damage type such as bird nest, bird droppings, and bird body short circuit, the bird species, the weather conditions, and the treatment measures.

[0034] Further, after obtaining the multi-source heterogeneous data of the power transmission line region, the method further includes: performing data cleaning on the multi-source heterogeneous data to obtain cleaned multi-source heterogeneous data; correlating and integrating the cleaned multi-source heterogeneous data according to the spatial position and the time sequence to obtain updated multi-source heterogeneous data; analyzing the updated multi-source heterogeneous data based on a risk estimation model to obtain a target risk probability value of bird damage in the power transmission line region.

[0035] The data cleaning of the multi-source heterogeneous data to obtain the cleaned multi-source heterogeneous data can include quality inspection, abnormal value processing, data completion operation, and data enhancement operation on the collected multi-source heterogeneous data to obtain the cleaned multi-source heterogeneous data.

[0036] For example, for abnormal values caused by sensor failure in meteorological data, a statistical method based on a sliding window is used for identification, and data deviating from the normal range by more than three standard deviations is marked as an abnormal value, and a linear interpolation method before and after the time is used for correction; For the field missing or format irregularity problem existing in the transmission line data, the completeness and standardization of the key fields such as tower coordinates, tower types, etc. can be checked according to the pre-established data verification rule library, and the data that do not meet the standard are marked and the data management personnel are prompted for manual checking and correction.

[0037] The data completion operation can be for the missing problem of part of the period record in the historical data, and the deep learning time series prediction model can be used for data interpolation to ensure the continuity and integrity of the time series data.

[0038] The data enhancement operation can be to derive and construct more valuable feature variables from multi-source heterogeneous data through feature engineering techniques, for example, calculating the temperature and humidity index according to the continuous multi-day temperature and precipitation data, calculating the water accessibility index according to the tower coordinates and the distance from the surrounding water source, and calculating the historical bird hazard prone index of the tower according to the historical bird hazard frequency statistics. These derived features can better represent the potential influencing factors of bird hazards and improve the prediction ability of the model.

[0039] S120, based on the risk estimation model, analyzing the multi-source heterogeneous data to obtain a target risk probability value of the bird hazard of the transmission line region; the risk estimation model includes a first model, a second model, a third model and a fourth model; the first model is used to predict the bird hazard risk based on meteorological data and biological characteristic data; the second model is used to predict the bird hazard risk based on transmission line data and geographic environment data; the third model is used to predict the bird hazard risk based on meteorological data; the fourth model is used to predict the bird hazard risk based on bird hazard defect data.

[0040] The target risk probability value can be used to reflect the risk level of the bird hazard risk, and the higher the target risk probability value, the higher the risk level.

[0041] The first model can predict the bird activity intensity of a specific region in a future time period by analyzing the correlation between the ecological habit characteristics of different bird species and the meteorological conditions, and then reflecting the bird hazard risk through the bird activity intensity. The first model can output the first bird hazard risk of the transmission line region in multiple time scales in the future. For example, the first model can output the first bird hazard risk of the transmission line region in twenty-four hours, forty-eight hours and seventy-two hours.

[0042] The second model can evaluate the attraction degree of the tower to birds and the inherent risk level of the tower suffering from bird damage according to the geographical location and environmental conditions of the tower. That is, the second model can output a second bird damage risk of the power transmission line area.

[0043] The third model can be a prediction model specially modeling the influence of short-term weather changes on bird behavior. The third model can output a third bird damage risk of bird activity changes caused by weather factors by analyzing the flight activities, foraging behavior, migration time, etc. of birds that are significantly affected by weather conditions, which can reflect the promotion or inhibition strength of meteorological conditions on bird activities. For example, the frequency of bird activities significantly increases before and after rainfall, strong wind weather changes the flight trajectory and height of birds, and sudden temperature changes trigger the concentrated migration behavior of migratory birds.

[0044] The fourth model can be a knowledge discovery model that extracts the spatiotemporal distribution rules and correlation characteristics of bird damage occurrence by deeply mining historical bird damage defect data. The fourth model uses data mining and association rule learning techniques to automatically discover the implicit bird damage occurrence patterns from massive bird damage fault records. That is, the fourth model outputs a fourth bird damage risk of the power transmission line area.

[0045] Further, the first bird damage risk, the second bird damage risk, the third bird damage risk, and the fourth bird damage risk can be combined using a weighted voting and Bayesian fusion strategy to obtain a target risk probability value of bird damage in the power transmission line area.

[0046] In S130, based on the target risk probability value and a preset risk level range, a bird damage risk level of the power transmission line area is predicted, and a risk warning is performed based on the bird damage risk level.

[0047] Different preset risk level ranges reflect different bird damage risk levels.

[0048] Specifically, there is a preset correspondence between the risk probability value and the preset risk level range. After obtaining the target risk probability value, the bird damage risk level of the power transmission line area can be matched from the preset correspondence according to the target risk probability value.

[0049] In the embodiment of the application, the first preset risk level range is from zero to a first preset risk value; the second preset risk level range is from the first preset risk value to a second preset risk value; the third preset risk level range is from the second preset risk value to a third preset risk value; the fourth preset risk level range is greater than the third preset risk value; the first preset risk value is less than the second preset risk value; the second preset risk value is less than the third preset risk value; the first risk level is higher than the second risk level; the second risk level is higher than the third risk level; and the third risk level is higher than the fourth risk level.

[0050] Correspondingly, based on the target risk probability value and the preset risk level range, the bird damage risk level of the power transmission line area can include the following steps: when the target risk probability value is in the first preset risk level range, the bird damage risk level of the power transmission line area is the first risk level; when the target risk probability value is in the second preset risk level range, the bird damage risk level of the power transmission line area is the second risk level; when the target risk probability value is in the third preset risk level range, the bird damage risk level of the power transmission line area is the third risk level; when the target risk probability value is in the fourth preset risk level range, the bird damage risk level of the power transmission line area is the fourth risk level.

[0051] For example, the first preset risk value is 0.25, the second preset risk value is 0.5, the third preset risk value is 0.75, and correspondingly, the first preset risk level range is 0 to 0.25, the second preset risk level range is 0.25 to 0.5, the third preset risk level range is 0.5 to 0.75, and the fourth preset risk level range is greater than 0.75. The first risk level can be understood as low risk; the second risk level can be understood as medium risk, which needs attention; the third risk level can be understood as high risk, which needs to be strengthened; and the fourth risk level can be understood as extremely high risk, which needs to take protective measures immediately.

[0052] Further, the risk warning based on the bird damage risk level can include: obtaining a warning rule library; the warning rule library stores warning contents and warning pushing manners corresponding to different risk levels; based on the bird damage risk level, matching target warning contents and target warning pushing manners from the warning rule library.

[0053] The warning contents can include warning levels, detailed location information of risk towers (such as line names and tower numbers), time windows of expected risks, risk types (such as nests, droppings and bird bodies), main causes (such as migration of migratory birds and weather changes), protective measures (such as installation of bird repellers, removal of nests and increase of patrol frequency), and the like.

[0054] The warning pushing manners for different risk levels can include: for the first risk level, a system internal prompt manner can be used to notify daily operation and maintenance personnel as reference information; for the second risk level, short message and system message manners can be used to notify relevant line operation and maintenance persons to strengthen patrol; for the third risk level, telephone, short message, system pop-up window and other multi-channel manners can be used to notify line management units to start emergency response plans; and for the fourth risk level, it can be directly reported to the dispatching center and the person in charge to coordinate resources for key protection.

[0055] In addition, the application can also provide a subscription and customization function of early warning information, and users of different levels and functions can set the line range and early warning level value of their attention according to their responsibility range, realize accurate push, and avoid information overload.

[0056] Optionally, after predicting the bird damage risk level of the power transmission line area based on the risk probability value and the preset risk level range, the method further comprises steps A1-A3:

[0057] Step A1, based on the bird damage risk level and the risk area corresponding to the bird damage risk level, a bird damage risk situation map of the power transmission line area is formed.

[0058] In addition, based on the bird damage risk situation map, a plurality of dimension data statistical charts can be determined; for example, a bird damage risk ranking column chart according to the line, a risk trend line chart according to the time, a risk distribution heat map according to the area, a proportion pie chart according to the bird damage type, etc., which are used to help the managers master the overall situation and change rule of the bird damage risk from a macroscopic level.

[0059] Step A2, the bird damage risk situation map is displayed on the display interface; the object icon displayed on the display interface is a trigger control; the object icon is the object of the corresponding risk area on the bird damage risk situation map.

[0060] Among them, the bird damage risk level in the bird damage risk situation map can be distinguished by different colors; for example, red represents the fourth risk level, that is, the extremely high risk; orange represents the third risk level, that is, the high risk; yellow represents the second risk level, that is, the medium risk; green represents the first risk level, that is, the low risk.

[0061] Step A3, in response to the triggering operation on the object icon, the object associated content is displayed, and the object associated content at least includes the position information, the risk level and the risk factor associated with the object.

[0062] For example, the object icon is a tower icon, and by clicking the tower icon on the map, the object associated content of the tower image can be popped up, that is, the tower number, the belonging line, the geographic coordinates, the risk level, the risk probability value, the main risk factor analysis, the historical bird damage record and other detailed contents are displayed.

[0063] In addition, the display interface can contain a time axis playback control, and by triggering the time axis playback control, the risk prediction information of the power transmission line area in different time periods can be obtained.

[0064] The embodiment of the present application forms a bird damage risk situation map of the power transmission line area based on the bird damage risk level and the risk area corresponding to the bird damage risk level, and displays the bird damage risk situation map on a display interface; a user can view the risk distribution of the whole network or a local area through zooming and panning the map. Further, the object icon displayed on the display interface is a trigger control; the object icon is an object of the risk area corresponding to the bird damage risk situation map, and by responding to the trigger operation on the object icon, the object associated content is displayed, and the object associated content at least includes the object associated position information, the risk level and the risk factor, so as to realize the display of more refined content.

[0065] The technical scheme of the embodiment of the present application obtains multi-source heterogeneous data of the power transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, power transmission line data, biological characteristic data and bird damage defect data; the value of the existing data resources is fully mined and utilized. Then, the multi-source heterogeneous data is analyzed based on a risk estimation model to obtain a target risk probability value of the bird damage of the power transmission line area; the risk estimation model includes a first model, a second model, a third model and a fourth model; the first model is used to predict the bird damage risk based on the meteorological data and the biological characteristic data; the second model is used to predict the bird damage risk based on the power transmission line data and the geographical environment data; the third model is used to predict the bird damage risk based on the meteorological data; the fourth model is used to predict the bird damage risk based on the bird damage defect data; the multi-model fusion decision mechanism effectively integrates the advantages of different models, reduces the prediction bias and uncertainty. Further, based on the risk probability value and a preset risk level range, the bird damage risk level of the power transmission line area is predicted, and the risk warning is performed based on the bird damage risk level, so as to solve the problems of low risk assessment accuracy and insufficient timeliness of the warning, and realize the advance prediction and active warning of the bird damage risk.

[0066] Embodiment two

[0067] Figure 2 The flowchart of another power transmission line bird damage prediction method provided by the embodiment of the present application, the technical scheme of the present embodiment is further optimized on the basis of the above-mentioned embodiment, and the present embodiment can be combined with each optional scheme in one or more of the above-mentioned embodiments. As shown in Figure 2 The power transmission line bird damage prediction method of the present application can include:

[0068] S210, multi-source heterogeneous data of the power transmission line area is obtained; the multi-source heterogeneous data includes meteorological data, geographical environment data, power transmission line data, biological characteristic data and bird damage defect data.

[0069] S220, based on the first model, the meteorological data and the biological characteristic data are analyzed to obtain a bird activity frequency prediction value, and a first risk probability value of bird damage in the power transmission line area is determined based on the bird activity frequency prediction value.

[0070] Specifically, the network structure of the first model can include an input layer, three layers of LSTM hidden layers, and a fully connected output layer. The input layer receives a time series feature vector with a length of a preset day, and each time has a feature dimension of thirty-two dimensions, including date encoding, weather parameters, bird ecological characteristics, and the like.

[0071] Among them, the first LSTM hidden layer contains one hundred and twenty-eight memory units, uses a tanh activation function, and sets a Dropout ratio of zero point two to prevent overfitting. The second LSTM hidden layer also contains one hundred and twenty-eight memory units, and inherits the hidden state and cell state of the first layer. The third LSTM hidden layer contains sixty-four memory units for feature dimension reduction.

[0072] The fully connected output layer contains a preset number of neurons, respectively corresponding to the bird activity frequency prediction values of a preset number of future time periods. The fully connected output layer uses a ReLU activation function to ensure that the output is non-negative. For example, the fully connected output layer contains three neurons, respectively corresponding to the bird activity frequency prediction values of twenty-four hours, forty-eight hours, and seventy-two hours in the future.

[0073] The loss function of the first model can be defined as:

[0074] Loss = MSE + a x R;

[0075] Wherein, MSE is the mean square error loss, R is the regularization term, and a is the regularization coefficient with a value of 0.001.

[0076] The optimizer uses the Adam optimization algorithm, and the initial learning rate is set to 0.001. The learning rate decay strategy is used to multiply the learning rate by 0.9 every ten rounds. The early stopping mechanism is used in the training process of the first model, and the training is stopped when the validation set loss does not decrease for a preset number of consecutive rounds, preventing overfitting and saving training time.

[0077] S230, based on the second model, the power transmission line data and the geographic environment data are analyzed to obtain a bird damage prone level, and a second risk probability value of bird damage in the power transmission line area is determined based on the bird damage prone level.

[0078] Specifically, the second model is a random forest model, which can use the random forest Random Forest algorithm as the core classifier. Random forest is an ensemble learning method that constructs multiple decision trees and makes voting decisions, which can effectively handle high-dimensional feature space and nonlinear relationships, and has strong generalization ability and robustness.

[0079] The top five reference features that have the greatest impact on bird hazard susceptibility are, in order: the distance between the tower and water source, which accounts for 23% of the importance, the vegetation coverage rate around the tower, which accounts for 19%, the tower type and cross arm structure, which accounts for 16%, the tower altitude, which accounts for 14%, and the historical bird hazard frequency, which accounts for 12%. In the construction of the decision tree of the second model, the square root of the number of reference features is randomly selected for each tree to split, that is, six feature candidates are randomly selected from the total of forty features to find the optimal split point. This randomness enhances the generalization ability of the model. The Gini Impurity is used as the splitting criterion for the tree splitting, and the calculation formula is:

[0080] ;

[0081] where p i represents the proportion of samples of class i in the node.

[0082] In the prediction stage of the second model, for a new tower to be evaluated, its feature vector is input into the two hundred decision trees for prediction, and each tree outputs a risk level prediction result. The final comprehensive risk level of the tower is determined through the majority voting mechanism, and the vote proportion of each level is used as a measure of the prediction confidence to determine the second risk probability value of the bird hazard in the power line area according to the measure of the prediction confidence.

[0083] S240, analyzing the meteorological data based on the third model to obtain a bird activity change coefficient, and determining a third risk probability value of the bird hazard in the power line area based on the bird activity change coefficient.

[0084] Specifically, the third model can be a GBDT model. The GBDT model can use the gradient boosting ensemble learning strategy to construct a series of weak decision trees through iteration, and each new tree is committed to fitting the residual error of all previous trees to gradually optimize the model performance. The loss function of the third model can be the mean square error. For the mth tree, the optimization objective is to minimize:

[0085] ;

[0086] where y i is the true label, f j is the prediction function of the first j trees, and Ω is the regularization term used to control the complexity of the tree.

[0087] In the learning process of each tree, firstly, the residual error between the predicted value of the current model and the true value is calculated, and then the residual error is taken as the fitting target of the new tree, and the optimal split feature and split point are found by a greedy algorithm to minimize the sum of the loss function values of the child nodes after splitting. The selection of the split point uses a histogram algorithm, which discretizes the continuous feature value into two hundred and fifty-five intervals, greatly improving the search efficiency of the split point. The weight value calculation formula of the leaf node can be:

[0088] ;

[0089] where G is the gradient statistic, H is the second derivative statistic, and λ is the regularization parameter.

[0090] When the third model is predicted, the feature vector formed by the meteorological data is sequentially passed through the judgment path of all trees, and finally reaches the corresponding leaf node. The final prediction result, i.e., the bird activity change coefficient, is obtained by adding the leaf node weight values of all trees, and then the third risk probability value of the bird damage in the transmission line area is determined based on the bird activity change coefficient.

[0091] S250, analyzing the bird damage defect data based on the fourth model to obtain the fourth risk probability value of the bird damage in the transmission line area.

[0092] Specifically, the fourth model includes a time dimension data analysis module, a spatial dimension data analysis module, a first factor analysis module, and a second factor analysis module. The fourth model can use binary cross-entropy as a loss function for end-to-end training.

[0093] The time dimension data analysis module is used to statistically analyze the bird damage defect data according to the time dimension, and identify the distribution characteristics of the bird damage high-occurrence seasons, months, and time periods; for example, the spring from March to May and the autumn from September to November are the corresponding bird damage high-occurrence periods of the migratory birds, and the morning from 5 to 7 o'clock and the evening from 17 to 19 o'clock are the peak periods of bird activity.

[0094] The spatial dimension data analysis module is used to cluster analyze the bird damage defect data in the spatial dimension, and can use the DBSCAN clustering algorithm based on density to identify the hot spot areas of bird damage, and divide the tower groups that are geographically adjacent and have frequent bird damage into key areas of attention.

[0095] The first factor analysis module can be used to analyze the association between the bird damage types and various influencing factors using the Apriori association rule mining algorithm; for example, bird nest defects occur more frequently on tangent towers with large crossarm platforms and close to water sources, bird droppings defects occur more frequently on high-voltage lines with long insulator strings, and bird body short-circuit defects occur more frequently on low-voltage distribution lines with small conductor spacing.

[0096] The first factor analysis module is a line-tower correlation network model based on a graph neural network (GNN), which is used to abstract the power transmission line into a graph structure, with the towers as nodes and the conductor connections between the towers as edges. The spatial dependency between nodes is learned through a graph convolutional neural network, and the propagation and diffusion law of bird damage on the line is mined.

[0097] The graph structure G can be represented as:

[0098] ;

[0099] wherein V represents a set of tower nodes, and E represents a set of conductor connection edges between the towers. The initial feature vector of each tower node contains attribute information of the tower, such as coordinates, height, environmental characteristics, etc.

[0100] The update formula of the graph convolution layer of the graph convolutional neural network can be:

[0101] ;

[0102] wherein represents the hidden representation of node i at the k+1 layer; N(i) represents a set of neighbor nodes of node i; AGG is an aggregation function, which is weighted summation using an attention mechanism; W k is a learnable weight matrix; and sigma is a nonlinear activation function, which can be ReLU.

[0103] The fourth model outputs the probability of bird damage predicted for each node, and the fourth risk probability value of the bird damage in the power transmission line area is obtained by weighted calculation of the probabilities.

[0104] S260, based on the first risk probability value, the second risk probability value, the third risk probability value and the fourth risk probability value, determining the target risk probability value of the bird damage in the power transmission line area.

[0105] Specifically, based on the first risk probability value, the second risk probability value, the third risk probability value and the fourth risk probability value, determining the target risk probability value of the bird damage in the power transmission line area can include: obtaining a first confidence degree of the first risk probability value, a second confidence degree of the second risk probability value, a third confidence degree of the third risk probability value, and a fourth confidence degree of the fourth risk probability value; based on the first confidence degree, the second confidence degree, the third confidence degree and the fourth confidence degree, determining a first weight of the first risk probability value, a second weight of the second risk probability value, a third weight of the third risk probability value and a fourth weight of the fourth risk probability value; based on the first risk probability value, the second risk probability value, the third risk probability value, the fourth risk probability value, the first weight, the second weight, the third weight and the fourth weight, determining the target risk probability value of the bird damage in the power transmission line area.

[0106] S270, predicting the bird damage risk level of the power transmission line area based on the target risk probability value and the preset risk level range, to perform risk warning based on the bird damage risk level.

[0107] The technical scheme of the embodiment of the present application acquires multi-source heterogeneous data of the power transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, power transmission line data, biological characteristic data and bird damage defect data. The first model is used to analyze the meteorological data and the biological characteristic data, to obtain a bird activity frequency prediction value, and the first risk probability value of bird damage in the power transmission line area is determined based on the bird activity frequency prediction value, to realize accurate analysis of the meteorological data and the biological characteristic data; the second model is used to analyze the power transmission line data and the geographical environment data, to obtain a bird damage prone level, and the second risk probability value of bird damage in the power transmission line area is determined based on the bird damage prone level, the second model can effectively process high-dimensional feature space and nonlinear relationship, and has strong generalization ability and robustness. The third model is used to analyze the meteorological data, to obtain a bird activity change coefficient, and the third risk probability value of bird damage in the power transmission line area is determined based on the bird activity change coefficient, to realize accurate analysis of the meteorological data and the bird activity change law; the fourth model is used to analyze the bird damage defect data, to obtain the fourth risk probability value of bird damage in the power transmission line area, to realize accurate analysis of the historical bird damage defect data; further, the first risk probability value, the second risk probability value, the third risk probability value and the fourth risk probability value are combined, to realize accurate determination of the target risk probability value of bird damage in the power transmission line area. Finally, based on the target risk probability value and the preset risk level range, the bird damage risk level of the power transmission line area is predicted, to perform risk warning based on the bird damage risk level, to solve the problems of low risk assessment accuracy and insufficient warning timeliness, to realize early prediction and active warning of bird damage risk.

[0108] Embodiment three

[0109] Figure 3 A structure diagram of a power transmission line bird damage prediction device provided by the embodiment of the present application, the embodiment can be applicable to the case of predicting bird damage of a power transmission line, the power transmission line bird damage prediction device can be realized in the form of hardware and / or software, and the power transmission line bird damage prediction device can be configured in any electronic device with network communication function. As shown in the figure, the power transmission line bird damage prediction device of the present application can include: Figure 3

[0110] The data acquisition module 310 is configured to acquire multi-source heterogeneous data of the power transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, power transmission line data, biological characteristic data and bird damage defect data;

[0111] ​The analysis module 320 is configured to analyze the multi-source heterogeneous data based on the risk estimation model to obtain a target risk probability value of bird damage in a power transmission line area; the risk estimation model comprises a first model, a second model, a third model and a fourth model; the first model is configured to predict bird damage risk based on meteorological data and biological characteristic data; the second model is configured to predict bird damage risk based on power transmission line data and geographical environment data; the third model is configured to predict bird damage risk based on meteorological data; and the fourth model is configured to predict bird damage risk based on bird damage defect data.

[0112] The prediction module 330 is configured to predict a bird damage risk level of the power transmission line area based on the target risk probability value and a preset risk level range, and to perform risk warning based on the bird damage risk level.

[0113] On the basis of the above-mentioned embodiments, the analysis module comprises a first analysis unit, a second analysis unit, a third analysis unit, a fourth analysis unit and a risk determination unit: the first analysis unit is configured to analyze the meteorological data and the biological characteristic data based on the first model to obtain a bird activity frequency prediction value, and to determine a first risk probability value of bird damage in the power transmission line area based on the bird activity frequency prediction value; the second analysis unit is configured to analyze the power transmission line data and the geographical environment data based on the second model to obtain a bird damage prone level, and to determine a second risk probability value of bird damage in the power transmission line area based on the bird damage prone level; the third analysis unit is configured to analyze the meteorological data based on the third model to obtain a bird activity change coefficient, and to determine a third risk probability value of bird damage in the power transmission line area based on the bird activity change coefficient; the fourth analysis unit is configured to analyze the bird damage defect data based on the fourth model to obtain a fourth risk probability value of bird damage in the power transmission line area; and the risk determination unit is configured to determine the target risk probability value of bird damage in the power transmission line area based on the first risk probability value, the second risk probability value, the third risk probability value and the fourth risk probability value.

[0114] On the basis of the above-mentioned embodiments, the risk determination unit is configured to: obtain a first confidence degree of the first risk probability value, a second confidence degree of the second risk probability value, a third confidence degree of the third risk probability value and a fourth confidence degree of the fourth risk probability value; determine a first weight of the first risk probability value, a second weight of the second risk probability value, a third weight of the third risk probability value and a fourth weight of the fourth risk probability value based on the first confidence degree, the second confidence degree, the third confidence degree and the fourth confidence degree; and determine the target risk probability value of bird damage in the power transmission line area based on the first risk probability value, the second risk probability value, the third risk probability value, the fourth risk probability value, the first weight, the second weight, the third weight and the fourth weight.

[0115] On the basis of the above-mentioned embodiments, optionally, the data acquisition module comprises a data cleaning unit, the data cleaning unit is configured to: perform data cleaning on the multi-source heterogeneous data to obtain cleaned multi-source heterogeneous data; and perform association and integration on the cleaned multi-source heterogeneous data according to spatial positions and time sequences to obtain updated multi-source heterogeneous data, so as to analyze the updated multi-source heterogeneous data based on a risk estimation model to obtain a target risk probability value of bird damage in a power line region.

[0116] On the basis of the above-mentioned embodiments, optionally, the prediction module comprises a risk level determination unit, the risk level determination unit is configured to: when the target risk probability value is in a first preset risk level range, a bird damage risk level of the power line region is a first risk level; the first preset risk level range is from zero to a first preset risk value; when the target risk probability value is in a second preset risk level range, the bird damage risk level of the power line region is a second risk level; the second preset risk level range is from the first preset risk value to a second preset risk value; when the target risk probability value is in a third preset risk level range, the bird damage risk level of the power line region is a third risk level; the third preset risk level range is from the second preset risk value to a third preset risk value; when the target risk probability value is in a fourth preset risk level range, the bird damage risk level of the power line region is a fourth risk level; the fourth preset risk level range is a range greater than the third preset risk value; the first preset risk value is less than the second preset risk value; the second preset risk value is less than the third preset risk value; the first risk level is higher than the second risk level; the second risk level is higher than the third risk level; and the third risk level is higher than the fourth risk level.

[0117] On the basis of the above-mentioned embodiments, optionally, the prediction module comprises a warning unit, the warning unit is configured to: acquire a warning rule library; the warning rule library stores warning contents and warning pushing manners corresponding to different risk levels; and based on the bird damage risk level, match target warning contents and a target warning pushing manner from the warning rule library.

[0118] On the basis of the above-mentioned embodiments, optionally, the power transmission line bird damage prediction device comprises a display module, which is configured to, after predicting the bird damage risk level of the power transmission line area based on the risk probability value and the preset risk level range, form a bird damage risk situation map of the power transmission line area based on the bird damage risk level and the risk area corresponding to the bird damage risk level, and display the bird damage risk situation map on a display interface; the object icon displayed on the display interface is a trigger control; the object icon is an object of the corresponding risk area on the bird damage risk situation map; in response to a trigger operation on the object icon, display object-associated content; the object-associated content at least includes object-associated position information, a risk level, and risk factors.

[0119] The power transmission line bird damage prediction device provided by the embodiments of the present application can execute the power transmission line bird damage prediction method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0120] Embodiment Four

[0121] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0122] Figure 4 A structural schematic diagram of an electronic device that can be used to implement the power transmission line bird damage prediction method of the embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0123] As Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the random access memory (RAM) 13. The processor 11, the read-only memory (ROM) 12, and the random access memory (RAM) 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0124] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0125] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the power transmission line bird hazard prediction method.

[0126] In some embodiments, the power transmission line bird hazard prediction method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the read-only memory (ROM) 12 and / or the communication unit 19. When the computer program is loaded into the random access memory (RAM) 13 and executed by the processor 11, one or more steps of the power transmission line bird hazard prediction method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the power transmission line bird hazard prediction method by any other appropriate means, such as by means of firmware.

[0127] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0128] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0129] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0130] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0131] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0132] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0133] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0134] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A method for predicting bird damage to power transmission lines, characterized in that, The method includes: Acquire multi-source heterogeneous data of the transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, transmission line data, biological characteristic data, and bird damage defect data; The multi-source heterogeneous data is analyzed based on a risk prediction model to obtain the target risk probability value of bird damage in the transmission line area. The risk prediction model includes a first model, a second model, a third model, and a fourth model. The first model is used to predict bird damage risk based on meteorological data and biological characteristic data. The second model is used to predict bird damage risk based on transmission line data and geographical environment data. The third model is used to predict bird damage risk based on meteorological data. The fourth model is used to predict bird damage risk based on bird damage defect data. Based on the target risk probability value and the preset risk level range, the bird damage risk level of the transmission line area is predicted, so as to carry out risk warning based on the bird damage risk level.

2. The method according to claim 1, characterized in that, Based on the risk prediction model, the multi-source heterogeneous data is analyzed to obtain the target risk probability value of bird damage in the transmission line area, including: Based on the first model, the meteorological data and the biological characteristic data are analyzed to obtain the predicted value of bird activity frequency, and the first risk probability value of bird damage in the transmission line area is determined based on the predicted value of bird activity frequency. Based on the second model, the transmission line data and the geographical environment data are analyzed to obtain the bird damage susceptibility level, and based on the bird damage susceptibility level, a second risk probability value of bird damage in the transmission line area is determined. The meteorological data is analyzed based on the third model to obtain the bird activity change coefficient, and the third risk probability value of bird damage in the transmission line area is determined based on the bird activity change coefficient. Based on the fourth model, the bird damage defect data is analyzed to obtain the fourth risk probability value of bird damage in the transmission line area; Based on the first risk probability value, the second risk probability value, the third risk probability value, and the fourth risk probability value, the target risk probability value of bird damage in the transmission line area is determined.

3. The method according to claim 2, characterized in that, Based on the first risk probability value, the second risk probability value, the third risk probability value, and the fourth risk probability value, the target risk probability value for bird damage in the transmission line area is determined, including: Obtain the first confidence level of the first risk probability value, the second confidence level of the second risk probability value, the third confidence level of the third risk probability value, and the fourth confidence level of the fourth risk probability value; Based on the first confidence level, the second confidence level, the third confidence level, and the fourth confidence level, a first weight, a second weight, a third weight, and a fourth weight are determined for the first risk probability value, the second risk probability value, the third risk probability value, and the fourth risk probability value. Based on the first risk probability value, the second risk probability value, the third risk probability value, the fourth risk probability value, the first weight, the second weight, the third weight, and the fourth weight, the target risk probability value of bird damage in the transmission line area is determined.

4. The method according to claim 1, characterized in that, After acquiring multi-source heterogeneous data of the transmission line area, the method further includes: The multi-source heterogeneous data is cleaned to obtain cleaned multi-source heterogeneous data; The cleaned multi-source heterogeneous data is correlated and integrated according to spatial location and time series to obtain updated multi-source heterogeneous data. The updated multi-source heterogeneous data is then analyzed based on a risk prediction model to obtain the target risk probability value of bird damage in the transmission line area.

5. The method according to claim 1, characterized in that, Based on the target risk probability value and the preset risk level range, the bird damage risk level of the transmission line area is predicted, including: When the target risk probability value is within the first preset risk level range, the bird damage risk level of the transmission line area is the first risk level; the first preset risk level range is from zero to the first preset risk value. When the target risk probability value is within the second preset risk level range, the bird damage risk level of the transmission line area is the second risk level; the second preset risk level range is from the first preset risk value to the second preset risk value. When the target risk probability value is within the range of the third preset risk level, the bird damage risk level of the transmission line area is the third risk level; the range of the third preset risk level is from the second preset risk value to the third preset risk value. When the target risk probability value is within the range of the fourth preset risk level, the bird damage risk level of the transmission line area is the fourth risk level; the range of the fourth preset risk level is greater than the range of the third preset risk value; the first preset risk value is less than the second preset risk value; the second preset risk value is less than the third preset risk value; the first risk level is higher than the second risk level; the second risk level is higher than the third risk level; the third risk level is higher than the fourth risk level.

6. The method according to claim 5, characterized in that, Risk warnings are issued based on the aforementioned bird damage risk levels, including: Obtain the early warning rule base; the early warning rule base stores the early warning content and early warning push methods corresponding to different risk levels; Based on the bird damage risk level, target warning content and target warning push method are matched from the warning rule base.

7. The method according to claim 1, characterized in that, After predicting the bird damage risk level in the transmission line area based on the risk probability value and the preset risk level range, the method further includes: Based on the bird damage risk level and the corresponding risk area, a bird damage risk situation map of the transmission line area is generated. The bird damage risk situation map is displayed on the display interface; the object icons displayed on the display interface are trigger controls; the object icons are objects in the corresponding risk areas on the bird damage risk situation map. In response to a triggering operation on the object icon, the associated content of the object is displayed; the associated content of the object includes at least the location information, risk level, and risk factors associated with the object.

8. A bird damage prediction device for power transmission lines, characterized in that, The device includes: The data acquisition module is used to acquire multi-source heterogeneous data of the transmission line area; the multi-source heterogeneous data includes meteorological data, geographical environment data, transmission line data, biological characteristic data, and bird damage defect data; The analysis module is used to analyze the multi-source heterogeneous data based on a risk prediction model to obtain the target risk probability value of bird damage in the transmission line area. The risk prediction model includes a first model, a second model, a third model, and a fourth model. The first model is used to predict bird damage risk based on meteorological data and biological characteristic data. The second model is used to predict bird damage risk based on transmission line data and geographical environment data. The third model is used to predict bird damage risk based on meteorological data. The fourth model is used to predict bird damage risk based on bird damage defect data. The prediction module is used to predict the bird damage risk level of the transmission line area based on the target risk probability value and the preset risk level range, so as to provide risk warning based on the bird damage risk level.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the transmission line bird damage prediction method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the transmission line bird damage prediction method according to any one of claims 1-7.

Images