A method, device, computer equipment, storage medium and computer program product for risk assessment of power line inspection roads

Abstract

The present application relates to a method, device, computer equipment, storage medium and computer program product for risk assessment of power line inspection roads. The method comprises: obtaining landslide disaster data and establishing a landslide database based on remote sensing images of the road area where the power line inspection road is located; the landslide database includes meteorological, geological and remote sensing information of the road area; obtaining multiple landslide influencing factors based on the landslide database, and establishing a landslide influencing factor data set; constructing a total landslide sample set based on landslide sample points and non-landslide sample points; selecting target landslide influencing factors and establishing a landslide sample set; training a gradient boosting tree model based on a training sample set and a test sample set to obtain a landslide hazard assessment model, and conducting a risk assessment on the power line inspection road. The use of this method can meet the comprehensiveness and real-time nature of risk assessment, continuously improve the accuracy and reliability of prediction, and significantly enhance the prediction ability of unbalanced sample data.

Description

Technical Field

[0001] The present application relates to the technical field of geological disaster risk assessment, and in particular to a method, device, computer equipment, storage medium and computer program product for risk assessment of power line inspection roads. Background Art

[0002] The progress of science and technology and the development of society are inseparable from energy, and electricity is one of the main energy sources at present. Therefore, it is of great significance to ensure the safety and stability of the power system. In the process of power line inspection, geological disasters are a risk factor that cannot be ignored. In order to deal with geological disasters, it is necessary to conduct risk assessment on power line inspection roads, identify and predict risks.

[0003] Traditional power line inspection road risk assessment mainly relies on manual inspections, which is difficult to meet the real-time and accuracy requirements of line inspection work. Summary of the invention

[0004] Based on this, it is necessary to provide a power line inspection road risk assessment method, device, computer equipment, computer readable storage medium and computer program product that can meet the real-time and accuracy requirements of line inspection work in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for risk assessment of power line inspection roads. The method comprises:

[0006] According to the remote sensing images of the road area where the power line inspection road is located, the landslide disaster data of the road area is obtained, and a landslide database is established based on the landslide disaster data; the landslide database includes meteorological, geological and remote sensing information of the road area;

[0007] According to the landslide database, a plurality of landslide influencing factors are obtained, and a landslide influencing factor data set is established according to the plurality of landslide influencing factors;

[0008] According to the landslide sample points and non-landslide sample points in the road area, a total landslide sample set is constructed;

[0009] According to the landslide influencing factor data set and the total landslide sample set, a target landslide influencing factor is selected from multiple landslide influencing factors, and a landslide sample set is established according to the target landslide influencing factor;

[0010] Based on the training sample set and the test sample set in the landslide sample set, the gradient boosting tree model is trained to obtain the landslide hazard assessment model;

[0011] According to the landslide hazard assessment model, risk assessment of power line inspection roads is carried out.

[0012] In one embodiment, constructing a total landslide sample set based on landslide sample points and non-landslide sample points in a road area includes:

[0013] Acquire landslide sample points in the road area that meet the first preset requirement;

[0014] According to the landslide triggering cause and landslide sample points, non-landslide sample points are obtained;

[0015] According to the landslide sample points and non-landslide sample points, the total landslide sample set is constructed.

[0016] In one embodiment, according to the landslide triggering cause and the landslide sample points, obtaining the non-landslide sample points includes:

[0017] In the case where the triggering cause of the landslide is landslide remains, the same number of non-landslide sample points as the landslide sample points are selected;

[0018] When the triggering cause of the landslide is rainfall, non-landslide sample points are selected according to the landslide area and the number of landslide sample points; the ratio of the number of landslide sample points to the number of non-landslide sample points is equal to the ratio of the landslide area to the non-landslide area.

[0019] In one embodiment, according to the landslide impact factor data set and the landslide total sample set, a target landslide impact factor is selected from multiple landslide impact factors, and establishing the landslide sample set according to the target landslide impact factor includes:

[0020] Based on the landslide influencing factor dataset, landslide sample points and non-landslide sample points, the multicollinearity and importance of each landslide influencing factor were determined;

[0021] Selecting a landslide impact factor that meets the first preset requirement as a target landslide impact factor;

[0022] According to the target landslide influencing factors, a landslide sample set is established.

[0023] In one embodiment, based on the training sample set and the test sample set in the landslide sample set, the gradient boosting tree model is trained to obtain the landslide hazard assessment model including:

[0024] According to a preset division method, the landslide sample set is divided into a training sample set and a test sample set; the preset division method includes a preset order and a preset ratio;

[0025] According to at least one gradient boosting tree algorithm or a combination algorithm of at least two gradient boosting tree algorithms, a training sample set and a test sample set, a gradient boosting tree model is trained to obtain a landslide hazard assessment model.

[0026] In one embodiment, performing risk assessment on a road area according to a landslide hazard assessment model includes:

[0027] According to the landslide hazard assessment model, the landslide hazard index of the road area is predicted to obtain the landslide hazard index of the road area, and the road area is divided into dangerous areas according to the landslide hazard index of the road area;

[0028] Obtain the exposure of the power line inspection road in the road area and the vulnerability index of the power line inspection road after the disaster;

[0029] Based on the exposure of the power line inspection road in the road area, the vulnerability index of the power line inspection road after the disaster and the landslide hazard index of the target area, the risk index of the target area is determined and the risk assessment of the target area is completed.

[0030] In a second aspect, the present application also provides a power line inspection road risk assessment device. The device comprises:

[0031] The data acquisition module is used to obtain the landslide disaster data of the road area according to the remote sensing image of the road area where the power line inspection road is located, and to establish a landslide database according to the landslide disaster data; the landslide database includes the meteorological, geological and remote sensing information of the road area;

[0032] A data processing module is used to obtain a plurality of landslide influencing factors according to a landslide database, and to establish a landslide influencing factor data set according to the plurality of landslide influencing factors;

[0033] The sample construction module is used to construct a total landslide sample set based on landslide sample points and non-landslide sample points in the road area; it is also used to select a target landslide influencing factor from multiple landslide influencing factors based on the landslide influencing factor data set and the total landslide sample set, and to establish a landslide sample set based on the target landslide influencing factor;

[0034] A model training module is used to train the gradient boosting tree model based on the training sample set and the test sample set in the landslide sample set to obtain a landslide hazard assessment model;

[0035] The risk assessment module is used to conduct risk assessment on power line inspection roads based on the landslide hazard assessment model.

[0036] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above methods when executing the computer program.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above methods are implemented.

[0038] In a fifth aspect, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the above methods are implemented.

[0039] The above-mentioned power line inspection road risk assessment method, device, computer equipment, storage medium and computer program product, through feature extraction and fusion of multi-source data such as geology, meteorology, remote sensing, etc., captures the dynamic changes of disaster factors, comprehensively identifies landslide influencing factors, and improves the comprehensiveness and real-time nature of the assessment; at the same time, this application adopts a gradient boosting tree model suitable for unbalanced disaster sample data to solve the problem that the number of minority class disaster samples is insufficient and it is difficult to train the model, and the prediction ability of unbalanced sample data is significantly improved, effectively avoiding the situation where minority class samples are ignored. In addition, training the landslide hazard assessment model based on the gradient boosting tree model also allows the landslide hazard assessment model to be continuously optimized through training, continuously improving the accuracy and reliability of the prediction, and providing high-quality risk warning information and safety guarantees for power line inspection personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 Schematic diagram of an application environment of a power line inspection road risk assessment method in one embodiment;

[0041] Figure 2 A schematic diagram of a flow chart of a method for risk assessment of power line inspection roads in one embodiment;

[0042] Figure 3 It is a schematic diagram of a process of constructing a total landslide sample set according to landslide sample points and non-landslide sample points in a road area in one embodiment;

[0043] Figure 4 A schematic diagram of a process for obtaining non-landslide sample points according to landslide triggering causes and landslide sample points in an embodiment;

[0044] Figure 5 A schematic diagram of a process of selecting a target landslide impact factor from a plurality of landslide impact factors according to a landslide impact factor data set and a landslide total sample set, and establishing a landslide sample set according to the target landslide impact factor in an embodiment;

[0045] Figure 6 A schematic diagram of a flow chart of a landslide hazard assessment model is shown in an embodiment, in which a gradient boosting tree model is trained based on a training sample set and a test sample set in a landslide sample set;

[0046] Figure 7 A schematic diagram of a process for performing risk assessment on a power line inspection road according to a landslide hazard assessment model in an embodiment;

[0047] Figure 8A schematic diagram of a flow chart of a method for risk assessment of power line inspection roads in another embodiment;

[0048] Fig. 9 A schematic diagram of the design concept of a power line inspection road risk assessment method in one embodiment;

[0049] Fig.10 It is a structural block diagram of a power line inspection road risk assessment device in one embodiment;

[0050] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The power system is one of the basic infrastructures of modern society. It is an indispensable infrastructure in many aspects such as energy supply, economic development, social life, national security, environmental protection and technological innovation. Therefore, ensuring the safe and stable operation of the power system is of great significance to the normal operation and sustainable development of society. Among them, power lines are an important part of the power system, and their safe and stable operation is directly related to the continuity and reliability of power supply. Therefore, it is necessary to timely discover and deal with potential safety hazards through power line inspection road risk assessment, prevent accidents, and ensure the safe and stable operation of the power system.

[0053] Traditional risk assessment technology for power line inspection roads mainly relies on manual inspections, analysis of historical disaster records, and preliminary assessments of terrain and meteorological conditions. Common methods include on-site surveys, terrain feature extraction, and disaster frequency statistics, which are used to assess the potential geological disaster risks along the inspection roads. In terms of data collection, remote sensing images, geological survey data, and meteorological information are usually used to assist in determining potential disaster threat factors. Some technologies also combine GIS (Geographic Information System or Geo-Information system) systems to use geographic information technology to perform spatial analysis of environmental parameters such as terrain slope and vegetation coverage along the road to identify risk areas. For specific high-risk areas, field surveys or sensor monitoring are also conducted regularly.

[0054] However, traditional methods still have obvious shortcomings in practical applications and are difficult to meet the real-time and accuracy requirements of line inspection work. First, the traditional manual inspection method has a long cycle and low efficiency, and cannot achieve a rapid response to sudden geological disasters, resulting in delayed warnings and insufficient coverage; secondly, the intelligence level of traditional methods is low, and it is difficult to make full use of meteorological, geological, topographic and other multi-source data to conduct a comprehensive analysis of risks, especially it is difficult to capture the dynamic changes of disaster factors, resulting in inaccurate prediction results; in addition, geological disasters are highly regional, with low incidence but high destructiveness. The insufficient number of samples of minority disasters makes model training and evaluation more difficult. Traditional methods have limited processing capabilities for unbalanced data, making it difficult to accurately identify and predict minority risks.

[0055] Therefore, this application proposes a method for rapid and accurate risk assessment of power line inspection roads based on a gradient boosting tree machine learning algorithm combined with multiple environmental factors to solve the problem of risk prediction of geological disasters on power line inspection roads under complex terrain.

[0056] The gradient boosting tree algorithm used in this application has the following advantages when dealing with unbalanced sample data:

[0057] Weighted loss function: Gradient boosting tree allows the use of weighted loss function, which can assign different weights to samples of different categories. In the case of unbalanced sample data, the weight of minority class samples can be increased so that the model pays more attention to these samples during training, thereby improving the prediction performance of the model.

[0058] Ensemble learning: Gradient boosting tree is an ensemble learning method that gradually improves the prediction performance of the model by building multiple decision trees. In the case of unbalanced sample data, each decision tree can focus on a different subset of samples, thereby improving the generalization ability of the model.

[0059] Regularization: Gradient boosting trees usually contain regularization terms to help prevent the model from overfitting. In the case of unbalanced sample data, regularization can reduce the model's over-reliance on majority class samples, thereby improving the model's predictive performance.

[0060] Sample resampling: During the training process of gradient boosting tree, sample resampling technology can be used to balance sample data. Copies of minority class samples can be generated during the training process of each decision tree, thereby improving the prediction performance of the model.

[0061] Multi-task learning: Gradient boosting trees can be used for multi-task learning, which means that multiple related tasks can be processed at the same time. In the case of imbalanced sample data, multi-task learning can be used to improve the prediction performance of the model, for example, the category and probability of the sample can be predicted at the same time.

[0062] Feature selection: Gradient boosting trees can automatically perform feature selection during training, which helps improve the model’s predictive performance. In the case of unbalanced sample data, feature selection can help the model identify features that have a greater impact on the predictive performance of minority class samples.

[0063] Model interpretability: Gradient boosting tree has good model interpretability, and the prediction process of the model can be understood by analyzing the structure of the decision tree. In the case of unbalanced sample data, model interpretability can help users understand the model's prediction performance for minority class samples.

[0064] In summary, the gradient boosting tree has the advantages of weighted loss function, integrated learning, regularization, sample resampling, multi-task learning, feature selection and model interpretability when dealing with unbalanced sample data, which help improve the predictive performance of the model.

[0065] The power line inspection road risk assessment method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the image acquisition device 102 communicates with the terminal 104 through the network. The image acquisition device 102 is used to collect remote sensing images of the road area where the power line inspection road is located, and send the remote sensing images of the road area where the power line inspection road is located to the terminal 104. The terminal 104 performs various steps in the power line inspection road risk assessment method of the present application based on the remote sensing images of the road area where the power line inspection road is located. Among them, the terminal 104 can be but is not limited to various personal computers, laptops, and workstations.

[0066] In an exemplary embodiment, Figure 2 As shown in the figure, a method for risk assessment of power line inspection roads is provided. Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0067] Step S202, acquiring landslide disaster data of the road area according to the remote sensing image of the road area where the power line inspection road is located, and establishing a landslide database according to the landslide disaster data; the landslide database includes meteorological, geological and remote sensing information of the road area.

[0068] The road area refers to the entire power line inspection road area. Furthermore, risk assessment may also be performed on a partial area in the road area, such as a selected target area.

[0069] Optionally, based on high-resolution, low-cloud coverage optical remote sensing images of power line inspection roads, historical landslide relics on the power line inspection roads and landslide disaster data triggered by events such as rainfall are obtained to construct a landslide database.

[0070] Exemplarily, the remote sensing image may include, but is not limited to, image data with a resolution greater than 6 meters, a cloud coverage rate less than 10%, and remote sensing images without cloud or fog obstructions.

[0071] Exemplarily, the landslide database contains historical landslide relic data and landslide data triggered by rainfall, and the landslide data contains spatial and attribute data, such as landslide location, range boundary, area, quantity information, etc.

[0072] Exemplarily, the landslide database may also include regional topographic and geomorphic conditions, regional engineering geological conditions, regional meteorological and hydrological conditions, regional surface cover conditions, and regional landslide catalog data.

[0073] Exemplarily, the landslide database formats include but are not limited to ".shp", ".kml" and ".kmz".

[0074] Step S204: acquiring a plurality of landslide influencing factors according to the landslide database, and establishing a landslide influencing factor data set according to the plurality of landslide influencing factors.

[0075] Optionally, based on multi-source data in the landslide database, multiple landslide influencing factors such as geology, topography and meteorology are selected, and a landslide influencing factor data set is established after normalizing each landslide influencing factor.

[0076] Exemplarily, multiple landslide influencing factors include, but are not limited to: historical earthquake parameters, elevation, slope, slope aspect, curvature, slope position, terrain undulation, terrain moisture index, land use type, vegetation coverage, stratum lithology, distance from active faults, distance from rivers and average annual rainfall in the past five years.

[0077] Exemplarily, the spatial resolution of all landslide impact factor data in the landslide impact factor dataset includes but is not limited to 12.5 m, 30 m and 100 m.

[0078] Step S206: construct a total landslide sample set based on the landslide sample points and non-landslide sample points in the road area.

[0079] Optionally, points in the landslide area within the road area are selected as landslide sample points, and points in the non-landslide area within the road area are selected as non-landslide sample points, and a total landslide sample set is constructed based on the landslide sample points and the non-landslide sample points.

[0080] Step S208, selecting a target landslide impact factor from a plurality of landslide impact factors according to the landslide impact factor data set and the landslide total sample set, and establishing a landslide sample set according to the target landslide impact factor.

[0081] Optionally, based on the landslide influencing factor data set and the selected landslide and non-landslide sample points, the multicollinearity and contribution degree of each landslide influencing factor are analyzed, and landslide influencing factors without multicollinearity and with large contribution degree are selected to establish a landslide training test sample set.

[0082] Step S210: training a gradient boosting tree model based on a training sample set and a test sample set in a landslide sample set to obtain a landslide hazard assessment model.

[0083] Optionally, the established landslide training sample set and test sample set are input into the gradient boosting tree model, and the gradient boosting tree model is trained until the training is completed, thereby constructing a landslide hazard assessment model.

[0084] Step S212: Perform risk assessment on the power line inspection road according to the landslide hazard assessment model.

[0085] Optionally, based on the landslide hazard assessment model, the exposure of the power line inspection road in the target area and the vulnerability index after the disaster are determined according to the geographical conditions and road design specifications near the power line inspection road, and the risk index of the power line inspection road area is calculated.

[0086] In the above-mentioned power line inspection road risk assessment method, by making full use of multi-source data such as meteorology, geology, and topography to conduct a comprehensive analysis of risks, the dynamic changes of disaster factors are captured, and the real-time problem of risk prediction of power line inspection roads is solved. At the same time, a landslide hazard assessment model is obtained through gradient boosting tree training, and the prediction ability of unbalanced sample data is significantly improved, which effectively avoids the situation where minority samples are ignored and improves the accuracy and reliability of risk prediction of power line inspection roads.

[0087] In order to construct a more comprehensive landslide sample set, this application provides the following scheme for the selection of sample points in landslide and non-landslide areas.

[0088] In an exemplary embodiment, Figure 3 As shown, step S206, constructing a total landslide sample set based on landslide sample points and non-landslide sample points in the road area includes:

[0089] Step S302: acquiring landslide sample points in the road area that meet the first preset requirement.

[0090] Among them, the first preset requirement represents the requirement for the landslide sample point selection method in the power line inspection road area, and can be adaptively adjusted according to different power line inspection situations.

[0091] Exemplarily, the landslide sample points in the power line inspection road area can be selected by: 1) converting the landslide surface elements into raster data, and extracting each pixel of the converted raster data as a landslide sample point; 2) converting the landslide surface elements into point elements, and one landslide corresponds to one point as a landslide sample.

[0092] Step S304, obtaining non-landslide sample points according to the landslide triggering cause and the landslide sample points.

[0093] Alternatively, the landslide triggering cause, the number of landslide sample points, and the area of ​​landslide sample points can all be used as factors affecting the selection of non-landslide sample points.

[0094] For example, the triggering cause of the landslide may be historical landslide relics or rainfall.

[0095] For example, for different types of landslides, the rules for selecting landslide and non-landslide sample points are different. When the triggering cause of the landslide is landslide remains, the same number of non-landslide sample points as the landslide sample points are selected; when the triggering cause of the landslide is rainfall, the non-landslide sample points are selected based on the landslide area and the number of landslide sample points; the ratio of the number of landslide sample points to the number of non-landslide sample points is equal to the ratio of the landslide area to the non-landslide area.

[0096] Step S306: construct a total landslide sample set based on the landslide sample points and the non-landslide sample points.

[0097] In this embodiment, a method for selecting landslide sample points and non-landslide sample points is provided, their internal connection is pointed out, and different non-landslide sample point selection methods are given according to the landslide triggering causes to ensure the comprehensiveness of the total landslide sample set.

[0098] The following describes in detail the method for selecting landslide sample points and non-landslide sample points in conjunction with the embodiments.

[0099] In an exemplary embodiment, Figure 4 As shown, step S304, according to the landslide triggering cause and the landslide sample points, obtaining non-landslide sample points includes:

[0100] Step S402: When the landslide triggering cause is landslide remains, select non-landslide sample points with the same number as the landslide sample points.

[0101] Step S404, when the landslide is triggered by rainfall, non-landslide sample points are selected according to the landslide area and the number of landslide sample points; the ratio of the number of landslide sample points to the number of non-landslide sample points is equal to the ratio of the landslide area to the non-landslide area.

[0102] Exemplarily, the landslide sample point selection method includes but is not limited to: 1) converting the landslide surface element into raster data, and extracting each pixel of the converted raster data as a landslide sample point; 2) converting the landslide surface element into point element, and one landslide corresponds to one point as a landslide sample.

[0103] Exemplarily, when the triggering cause of the landslide is a landslide relic, the method for selecting non-landslide sample points is not limited to: 1) extracting the non-landslide area within the road area and randomly selecting points within this range; 2) constructing a fishing net point matrix for the non-landslide area and randomly selecting points from it.

[0104] When the landslide is triggered by rainfall, the method of selecting the sample size according to the ratio of landslide to non-landslide area includes but is not limited to: 1) taking a large number of random points in the entire road area, and then counting whether the area where the points are located belongs to the landslide area, so as to mark the landslide and non-landslide sample labels for each point respectively; 2) first randomly selecting an appropriate amount of point data in the landslide area, and then selecting equivalent sample points in the non-landslide area corresponding to the ratio of landslide to non-landslide area.

[0105] This embodiment improves the selection scheme of landslide sample points and non-landslide sample points. The total landslide sample set constructed based on this is more comprehensive and accurate, providing a good foundation for the subsequent construction of a landslide hazard assessment model.

[0106] After the total landslide sample set is constructed, it is necessary to select landslide influencing factors to form landslide samples for landslide hazard assessment model training.

[0107] In an exemplary embodiment, Figure 5 As shown, step S208, selecting a target landslide impact factor from multiple landslide impact factors according to the landslide impact factor data set and the landslide total sample set, and establishing a landslide sample set according to the target landslide impact factor includes:

[0108] Step S502: determining the multicollinearity and importance of each landslide influencing factor based on the landslide influencing factor data set, landslide sample points and non-landslide sample points.

[0109] Optionally, based on the landslide influencing factor data set and the selected landslide sample points and non-landslide sample points, the multicollinearity and contribution degree of each landslide influencing factor are analyzed.

[0110] Exemplarily, multicollinearity analysis methods for landslide influencing factors include but are not limited to: 1) Variance Inflation Factor (VIF) analysis: By calculating the variance inflation factor (VIF) value of each influencing factor, the degree of collinearity between landslide influencing factors is determined. When the VIF value is higher than a specific threshold (such as 5 or 10), it indicates that there is collinearity between landslide influencing factors; 2) Correlation coefficient matrix analysis: Calculate the correlation coefficient between landslide influencing factors and generate a correlation coefficient matrix. A high correlation coefficient (close to 1 or -1) indicates that there may be collinearity between landslide influencing factors; 3) Condition number analysis: By calculating the condition number of the characteristic matrix of landslide influencing factors, the collinearity problem is determined. When the condition number is greater than 30, it indicates that there is serious collinearity.

[0111] Exemplarily, the contribution analysis method of landslide influencing factors includes but is not limited to: 1) Multiple regression analysis: Analyze the contribution of landslide influencing factors to the probability of landslide occurrence through a multiple linear regression model, and use the standardized regression coefficient to judge the importance of each factor. The larger the absolute value of the coefficient, the greater the contribution of the factor to the landslide; 2) Random forest feature importance: Calculate the feature importance of each influencing factor through a random forest algorithm. The higher the importance of the factor, the greater its contribution to the prediction of the landslide; 3) Information gain: Use the information gain method to evaluate the contribution of each influencing factor to the landslide classification information. The larger the information gain, the higher the importance of the factor to the occurrence of the landslide.

[0112] Step S504: Select a landslide impact factor that meets a first preset requirement as a target landslide impact factor.

[0113] Among them, the first preset requirement represents the performance requirements for selecting landslide influencing factors, such as no multicollinearity and a high ranking in contribution.

[0114] Optionally, target landslide impact factors without multicollinearity and with large contribution are selected to establish a landslide training test sample set. The number of target landslide impact factors can be adjusted according to training requirements, and this application does not impose any restrictions.

[0115] Step S506: establishing a landslide sample set according to the target landslide impact factor.

[0116] In the above-mentioned power line inspection road risk assessment method, multicollinearity and contribution analysis are performed on the landslide influencing factors extracted from the features of multi-source data such as geology, meteorology, and remote sensing to remove redundant information, obtain accurate and comprehensive target landslide influencing factors, and capture the dynamic changes of landslide influencing factors; in addition, through a variety of multicollinearity and contribution analysis methods, the limitations of a single selection method are avoided, the reliability and comprehensiveness of the landslide sample set are guaranteed, and the prediction accuracy of landslide risk disasters is enhanced.

[0117] After the sample set is constructed, it is necessary to perform training based on the landslide sample set. The model training method of the present application is described in detail below in conjunction with the embodiments.

[0118] In an exemplary embodiment, Figure 6 As shown, step S210, based on the training sample set and the test sample set in the landslide sample set, the gradient boosting tree model is trained to obtain the landslide hazard assessment model including:

[0119] Step S602: dividing the landslide sample set into a training sample set and a test sample set according to a preset division method; the preset division method includes a preset order and a preset ratio.

[0120] The preset division method includes a preset order and a preset ratio. The preset order can be random, sequential, interval, etc. The preset ratio can be 9:1, 8:2, 7:3, 6:4, etc.

[0121] Exemplarily, the landslide sample points and non-landslide sample points in the landslide sample set are labeled, and the labeling method includes: the landslide sample point label is labeled as "1", and the non-landslide sample point label is labeled as "2", which can also be a combination of "1" and "0".

[0122] Step S604: training the gradient boosting tree model according to at least one gradient boosting tree algorithm or a combination algorithm of at least two gradient boosting tree algorithms, a training sample set and a test sample set to obtain a landslide hazard assessment model.

[0123] Among them, the gradient boosting tree algorithm includes but is not limited to: 1) Gradient Boosting Decision Tree (GBDT): a classic gradient boosting decision tree algorithm that optimizes the residual of the model by gradually building multiple decision trees, and each tree learns the error of the previous prediction. GBDT performs well in regression and classification tasks; 2) eXtreme Gradient Boosting (XGBoost): an improved gradient boosting tree algorithm with higher efficiency and scalability. XGBoost prevents overfitting through parallel processing and regularization, and can customize the objective function; 3) Categorical Boosting (Categorical Boosting, CatBoost): a gradient boosting algorithm optimized for categorical features, which processes categorical features through a special target encoding method, can reduce the bias and variance of the model, and prevent overfitting.

[0124] Optionally, for different training tasks and evaluation requirements, a gradient boosting tree algorithm or a combination of multiple gradient boosting tree algorithms is selected to train the gradient boosting tree model to obtain a landslide hazard assessment model constructed based on the gradient boosting tree model.

[0125] In the above-mentioned power line inspection road risk assessment method, by dividing the training sample set and the test sample set, the advantages of the gradient boosting tree algorithm and its combination algorithm in the sample data imbalance scenario are utilized, so that the prediction ability of the landslide hazard assessment model for unbalanced sample data is significantly improved, and the situation where minority samples are ignored is effectively avoided; at the same time, suitable machine learning algorithms or combinations of multiple algorithms are selected for different training tasks, so that the landslide hazard assessment model can be continuously optimized through training, and can perform risk assessment tasks with different requirements, thereby enhancing the comprehensiveness and scalability of risk assessment and improving the accuracy and reliability of prediction.

[0126] In an exemplary embodiment, Figure 7 As shown, step S212, based on the landslide hazard assessment model, risk assessment of the power line inspection road includes:

[0127] Step S702: predicting the landslide hazard index of the road area according to the landslide hazard assessment model, obtaining the landslide hazard index of the road area, and zoning the road area according to the landslide hazard index of the road area.

[0128] Exemplarily, the value range of the landslide hazard index includes 0-1 or other ranges greater than 0 and less than 1; the specific value depends on the calculation result.

[0129] Exemplarily, landslide hazard zoning methods include but are not limited to: natural breakpoint method, which divides the hazard zone into five categories: extremely low hazard zone, low hazard zone, medium hazard zone, high hazard zone and extremely high hazard zone; equal interval classification method, which divides the range of 0-1 into five sections on average.

[0130] Step S704, obtaining the exposure degree of the power line inspection road in the road area and the vulnerability index of the power line inspection road after the disaster.

[0131] The definition factors of road exposure include but are not limited to: geographical location, importance, frequency of use, traffic volume and surrounding environment, etc. These factors are evaluated and assigned values ​​respectively; the exposure (E) is calculated according to the following formula (1):

[0132] (1)

[0133] Among them, E represents exposure, n represents the type of factor, and w i represents the weight of the ith exposure factor, x irepresents the i-th exposure factor.

[0134] The defining factors of road vulnerability include, but are not limited to, geological conditions, topographic factors, climate conditions, degree of aging, etc. Road vulnerability (V) is calculated using the following formula (2):

[0135] (2)

[0136] Among them, V is the road vulnerability value, n represents the factor type, F i is the ith vulnerability factor, w i is the weight of the ith vulnerability factor.

[0137] Step S706, determining the risk index of the target area according to the exposure of the power line inspection road in the road area, the vulnerability index of the power line inspection road after the disaster, and the landslide hazard index of the target area, and completing the risk assessment of the target area.

[0138] Optionally, the risk index calculation method for the power line inspection road area includes but is not limited to:

[0139] 1) Classical product formula (3):

[0140] (3)

[0141] Among them, R represents the regional risk index, H represents the regional hazard index or disaster susceptibility index, E represents exposure, and V represents vulnerability.

[0142] 2) Risk level matrix method: assign threat, exposure and vulnerability values ​​through level classification, and substitute the level values ​​into the formula for calculation. It is suitable for rapid risk screening of large-scale roads.

[0143] 3) Fuzzy comprehensive evaluation method, which processes the membership degree of each factor through fuzzy logic and calculates the comprehensive risk index, is suitable for complex situations that are difficult to accurately quantify. As shown in formula (4):

[0144] (4)

[0145] Among them, μ i (F i ) represents the fuzzy membership of the i-th factor, w i is the corresponding weight.

[0146] The target areas are divided into five geological hazard risk levels according to the risk index: 1-extremely low risk area, 2-low risk area, 3-medium risk area, 4-high risk area and 5-extremely high risk area.

[0147] In the above-mentioned risk assessment method for power line inspection roads, the landslide hazard index is used to zoning the road area for hazard, and the calculation formulas for the exposure and vulnerability indicators of power line inspection roads are given; at the same time, different risk index calculation methods are proposed for conventional line inspection roads, rapid risk screening of large-scale roads, and complex situations that are difficult to accurately quantify. In the face of complex and diverse landslide risks, the accuracy and reliability of the prediction are improved, providing high-quality risk warning information and safety guarantees for power line inspection personnel.

[0148] In another exemplary embodiment, Figure 8 As shown, a method for risk assessment of power line inspection roads is provided, including:

[0149] Step S802, based on the high-resolution, low-cloud coverage optical remote sensing images of the power line inspection road area, historical landslide disaster data and rainfall-triggered landslide disaster data of the target area are obtained to build a landslide database; the landslide database includes meteorological, geological and remote sensing information of the road area.

[0150] Step S804, selecting multiple influencing factors such as geology, topography and meteorology, and then normalizing each landslide influencing factor to establish a landslide influencing factor data set.

[0151] Step S806, select points in the road area as landslide sample points. When the landslide triggering cause is landslide remains, select non-landslide sample points with the same number as the landslide sample points; when the landslide triggering cause is rainfall, select non-landslide sample points based on the landslide area and the number of landslide sample points; the ratio of the number of landslide sample points to the number of non-landslide sample points is equal to the ratio of the landslide area to the non-landslide area.

[0152] Step S808: Analyze the multicollinearity and contribution of each landslide influencing factor based on the landslide influencing factor data set and the selected landslide and non-landslide sample points. Select landslide influencing factors with variance inflation factor (VIF) not greater than 10 to establish a landslide training test sample set.

[0153] Step S810: Based on the established landslide training sample set and test sample set, a landslide hazard assessment model constructed based on the gradient boosting tree XGBoost model is trained.

[0154] Step S812: using the trained landslide hazard assessment model to predict the landslide hazard index in the power line inspection road area.

[0155] Step S814, determining the exposure of the road in the study area and the vulnerability index after being hit by a disaster based on the geographical conditions and road design specifications near the power line inspection road.

[0156] Step S816, calculating the risk index of the power line inspection road area according to the classical product formula of risk index.

[0157] This embodiment is a feasible assessment process for the risk assessment of power line inspection roads in this application, based on the following Fig. 9 The design concept shown in the figure first analyzes and organizes multi-source landslide data to obtain a set of landslide influencing factors, then selects landslide influencing factors through variance inflation factor (VIF), trains a landslide hazard assessment model based on the gradient boosting tree XGBoost model, conducts landslide susceptibility analysis, adopts different assessment schemes for different landslide triggering causes, and finally uses the risk index classic product formula to calculate the risk index of the power line inspection road area to complete the risk assessment of the power line inspection road.

[0158] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0159] Based on the same inventive concept, the embodiment of the present application also provides a power line patrol road risk assessment device for implementing the power line patrol road risk assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power line patrol road risk assessment device embodiments provided below can refer to the limitations of the power line patrol road risk assessment method above, and will not be repeated here.

[0160] In one embodiment, Fig.10 As shown, a power line inspection road risk assessment device is provided, including: a data acquisition module 1002, a data processing module 1004, a sample construction module 1006, a model training module 1008 and a risk assessment module 1010, wherein:

[0161] The data acquisition module 1002 is used to acquire landslide disaster data of the road area according to the remote sensing image of the road area where the power line inspection road is located, and to establish a landslide database according to the landslide disaster data; the landslide database includes meteorological, geological and remote sensing information of the road area.

[0162] The data processing module 1004 is used to obtain a plurality of landslide influencing factors according to the landslide database, and to establish a landslide influencing factor data set according to the plurality of landslide influencing factors.

[0163] The sample construction module 1006 is used to construct a total landslide sample set based on the landslide sample points and non-landslide sample points in the road area; it is also used to select a target landslide influencing factor from multiple landslide influencing factors based on the landslide influencing factor data set and the total landslide sample set, and establish a landslide sample set based on the target landslide influencing factor.

[0164] The model training module 1008 is used to train the gradient boosting tree model based on the training sample set and the test sample set in the landslide sample set to obtain a landslide hazard assessment model.

[0165] The risk assessment module 1010 is used to perform risk assessment on the power line inspection road according to the landslide hazard assessment model.

[0166] In an exemplary embodiment, the sample construction module 1006 is also used to obtain landslide sample points that meet the first preset requirements in the road area; obtain non-landslide sample points based on the landslide triggering cause and the landslide sample points; and construct a total landslide sample set based on the landslide sample points and the non-landslide sample points.

[0167] In an exemplary embodiment, the sample construction module 1006 is also used to select non-landslide sample points with the same number as the landslide sample points when the triggering cause of the landslide is landslide remains; when the triggering cause of the landslide is rainfall, select non-landslide sample points based on the landslide area and the number of landslide sample points; the ratio of the number of landslide sample points to the number of non-landslide sample points is equal to the ratio of the landslide area to the non-landslide area.

[0168] In an exemplary embodiment, the sample construction module 1006 is also used to determine the multicollinearity and importance of each landslide influencing factor based on the landslide influencing factor data set, landslide sample points and non-landslide sample points; select the landslide influencing factor that meets the first preset requirement as the target landslide influencing factor; and establish a landslide sample set based on the target landslide influencing factor.

[0169] In an exemplary embodiment, the model training module 1008 is also used to divide the landslide sample set into a training sample set and a test sample set according to a preset division method; the preset division method includes a preset order and a preset ratio; the gradient boosting tree model is trained according to at least one gradient boosting tree algorithm or a combination algorithm of at least two gradient boosting tree algorithms, the training sample set and the test sample set to obtain a landslide hazard assessment model.

[0170] In an exemplary embodiment, the risk assessment module 1010 is also used to predict the landslide hazard index of the road area where the power line inspection road is located based on the landslide hazard evaluation model, obtain the landslide hazard index of the road area, and perform hazard zoning on the road area based on the landslide hazard index of the road area; obtain the exposure of the power line inspection road in the road area and the vulnerability index of the road area after the disaster; determine the risk index of the road area based on the exposure of the power line inspection road in the road area, the vulnerability index of the road area after the disaster, and the landslide hazard index of the road area, and complete the risk assessment of the power line inspection road.

[0171] Each module in the above-mentioned power line inspection road risk assessment device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0172] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a power line inspection risk assessment method is implemented.

[0173] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0174] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the above method embodiment are implemented:

[0175] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method embodiment are implemented.

[0176] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the steps of the above method embodiment when executed by a processor.

[0177] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0178] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0179] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0180] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for risk assessment of power line inspection roads, characterized in that: The method comprises: According to the remote sensing image of the road area where the power line inspection road is located, the landslide disaster data of the road area is obtained, and a landslide database is established according to the landslide disaster data; the landslide database includes meteorological, geological and remote sensing information of the road area; According to the landslide database, a plurality of landslide influencing factors are acquired, and a landslide influencing factor data set is established according to the plurality of landslide influencing factors; Constructing a total landslide sample set according to the landslide sample points and the non-landslide sample points in the road area, including: acquiring landslide sample points that meet the first preset requirement in the road area; acquiring non-landslide sample points according to the landslide triggering cause and the landslide sample points; constructing a total landslide sample set according to the landslide sample points and the non-landslide sample points; According to the landslide impact factor data set and the landslide total sample set, a target landslide impact factor is selected from a plurality of landslide impact factors, and a landslide sample set is established according to the target landslide impact factor; Based on the training sample set and the test sample set in the landslide sample set, a gradient boosting tree model is trained to obtain a landslide hazard assessment model; A risk assessment is performed on the power line inspection road according to the landslide hazard assessment model.

2. A power line inspection road risk assessment method according to claim 1, characterized in that: The obtaining of non-landslide sample points according to the landslide triggering cause and the landslide sample points comprises: In the case where the triggering cause of the landslide is a landslide relic, the same number of non-landslide sample points as the landslide sample points are selected; When the landslide is triggered by rainfall, non-landslide sample points are selected according to the landslide area and the number of landslide sample points; the ratio of the number of landslide sample points to the number of non-landslide sample points is equal to the ratio of the landslide area to the non-landslide area.

3. A method for risk assessment of power line inspection roads according to claim 1, characterized in that: The step of selecting a target landslide impact factor from a plurality of landslide impact factors according to the landslide impact factor data set and the landslide total sample set, and establishing a landslide sample set according to the target landslide impact factor comprises: Based on the landslide influencing factor data set, the landslide sample points and the non-landslide sample points, determining the multicollinearity and importance of each of the landslide influencing factors; Selecting the landslide impact factor that meets the first preset requirement as the target landslide impact factor; A landslide sample set is established according to the target landslide influencing factors.

4. A power line inspection road risk assessment method according to claim 1, characterized in that: The training of the gradient boosting tree model based on the training sample set and the test sample set in the landslide sample set to obtain the landslide hazard assessment model includes: According to a preset division method, the landslide sample set is divided into a training sample set and a test sample set; the preset division method includes a preset order and a preset ratio; According to at least one gradient boosting tree algorithm or a combination algorithm of at least two gradient boosting tree algorithms, the training sample set and the test sample set, the gradient boosting tree model is trained to obtain a landslide hazard assessment model.

5. A power line inspection road risk assessment method according to claim 1, characterized in that: The risk assessment of the power line inspection road according to the landslide hazard assessment model includes: According to the landslide hazard assessment model, a landslide hazard index is predicted for the road area where the power line inspection road is located to obtain the landslide hazard index of the road area, and a hazard zoning is performed on the road area according to the landslide hazard index of the road area; Obtaining the exposure degree of the power line inspection road in the road area and the vulnerability index of the road area after the disaster; According to the exposure of the power line inspection road in the road area, the vulnerability index of the road area after the disaster and the landslide hazard index of the road area, the risk index of the road area is determined to complete the risk assessment of the power line inspection road.

6. A power line inspection road risk assessment device, characterized in that: The device comprises: A data acquisition module, for acquiring landslide disaster data of the road area according to the remote sensing image of the road area where the power line inspection road is located, and establishing a landslide database according to the landslide disaster data; the landslide database includes meteorological, geological and remote sensing information of the road area; A data processing module, used for acquiring a plurality of landslide influencing factors according to the landslide database, and establishing a landslide influencing factor data set according to the plurality of landslide influencing factors; The sample construction module is used to construct a total landslide sample set according to the landslide sample points and non-landslide sample points in the road area, including: obtaining landslide sample points that meet the first preset requirement in the road area; obtaining non-landslide sample points according to the landslide triggering cause and the landslide sample points; and constructing a total landslide sample set according to the landslide sample points and the non-landslide sample points; It is also used to select a target landslide impact factor from a plurality of landslide impact factors according to the landslide impact factor data set and the landslide total sample set, and establish a landslide sample set according to the target landslide impact factor; A model training module is used to train a gradient boosting tree model based on a training sample set and a test sample set in the landslide sample set to obtain a landslide hazard assessment model; The risk assessment module is used to perform risk assessment on the power line inspection road according to the landslide hazard assessment model.

7. A power line inspection road risk assessment device according to claim 6, characterized in that: The risk assessment module is further used to predict the landslide hazard index of the road area where the power line inspection road is located according to the landslide hazard assessment model, obtain the landslide hazard index of the road area, and perform hazard zoning on the road area according to the landslide hazard index of the road area; Obtain the exposure of the power line inspection road in the road area and the vulnerability index of the road area after the disaster; determine the risk index of the road area according to the exposure of the power line inspection road in the road area, the vulnerability index of the road area after the disaster and the landslide hazard index of the road area, and complete the risk assessment of the power line inspection road.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images