Power transmission channel risk determination method and device, storage medium and electronic equipment

Abstract

The invention discloses a power transmission channel risk determination method and device, a storage medium and electronic equipment. The method comprises the steps that remote sensing information is acquired, and the remote sensing information at least comprises a power transmission channel and a detection area located in a preset range of the power transmission channel; performing feature extraction based on the remote sensing information, and determining a vegetation classification result in the detection area; according to a vegetation classification result, determining a target combustible carrying capacity in the detection area; and determining the risk level of the power transmission channel according to the target combustible load and the power level of the power transmission channel, the power level being in direct proportion to the influence of the power transmission channel on the operation of the power grid. The technical problem that the accuracy of power transmission channel risk assessment is not ideal in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of risk assessment of power transmission channels, and in particular, to a method, device, storage medium and electronic device for determining risk of power transmission channels. Background Art

[0002] In the power grid system, the safety and stability of transmission and distribution lines are key factors in maintaining the safe operation of the power grid system and reliable power supply. However, with the acceleration of urbanization and the increase in vegetation coverage, the accumulation of combustibles such as vegetation around transmission lines has significantly increased the risk of fire, endangering the safe operation of the power grid and causing serious impacts on the lives of residents and the normal operation of urban functions. Tree species identification and combustible load assessment of traditional transmission channels are mainly manual inspections and ground surveys, with limited coverage and low inspection efficiency. It is difficult to conduct comprehensive inspections of large-area transmission channels, and there are differences in the accuracy and consistency of data collection, which reduces the consistency and reliability of the test results, resulting in technical problems such as poor accuracy of risk assessment results.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method, device, storage medium and electronic device for determining risk of a power transmission channel, so as to at least solve the technical problem of unsatisfactory accuracy of risk assessment of power transmission channels existing in the related art.

[0005] According to one aspect of an embodiment of the present application, a method for determining the risk of a power transmission channel is provided, comprising: acquiring remote sensing information, wherein the remote sensing information includes at least a power transmission channel and a detection area within a predetermined range of the power transmission channel; performing feature extraction based on the remote sensing information to determine a vegetation classification result in the detection area; determining a target combustible load in the detection area based on the vegetation classification result; determining a risk level of the transmission channel according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid.

[0006] Optionally, the remote sensing information includes spectral images and three-dimensional point cloud data, and feature extraction is performed based on the remote sensing information to determine the vegetation classification results in the detection area, including: performing feature extraction based on the spectral image to determine the spectral features used to characterize the association between vegetation type and vegetation density; performing feature extraction based on the three-dimensional point cloud data to determine the structural features used to characterize the vegetation structure; and determining the vegetation classification results according to the spectral features and structural features.

[0007] Optionally, based on the vegetation classification results, the target combustible load in the detection area is determined, including: based on the vegetation classification results, determining a target model from multiple predetermined models, wherein the multiple predetermined models correspond to different classification results respectively; using the target model, processing based on vegetation density, to determine the target combustible load.

[0008] Optionally, the risk level of the transmission channel is determined according to the target combustible load and the power level of the transmission channel, including: determining a sampling location in the detection area; determining the underground litter reserve based on the ground measured data corresponding to the sampling location; correcting the target combustible load according to the underground litter reserve to obtain a corrected target combustible load; and determining the risk level based on the corrected target combustible load and the power level.

[0009] Optionally, the target combustible load is corrected according to the underground litter reserves to obtain a corrected target combustible load, including: determining the estimated biomass in the detection area based on the vegetation radius and vegetation height indicated by the ground measured data; determining the carbon coefficient in the detection area based on the estimated biomass; determining the measured combustible load at the sampling site based on the carbon coefficient; correcting the target combustible load according to the measured combustible load and the underground litter reserves to obtain a corrected target combustible load.

[0010] Optionally, acquiring remote sensing information includes: acquiring initial acquisition information; correcting the initial acquisition information using a predetermined correction method to obtain remote sensing information, wherein the predetermined correction method includes at least one of the following: radiation correction for eliminating sensor errors, geometric correction for calibrating with the geographic coordinates of the detection area, and atmospheric correction for reducing scattering and absorption effects.

[0011] Optionally, the method further includes: determining the power level according to the load capacity of the transmission channel and the topological position of the transmission channel in the power grid.

[0012] According to another aspect of an embodiment of the present application, a transmission channel risk determination device is provided, including: an information acquisition module for acquiring remote sensing information, wherein the remote sensing information at least includes a transmission channel and a detection area within a predetermined range of the transmission channel; a feature extraction module for performing feature extraction based on the remote sensing information to determine a vegetation classification result in the detection area; a combustible load determination module for determining a target combustible load in the detection area based on the vegetation classification result; and a risk level determination module for determining the risk level of the transmission channel according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid.

[0013] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the methods for determining risk of a power transmission channel.

[0014] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the transmission channel risk determination methods.

[0015] In the embodiment of the present application, remote sensing information is obtained, wherein the remote sensing information at least includes a transmission channel and a detection area within a predetermined range of the transmission channel; feature extraction is performed based on the remote sensing information to determine the vegetation classification result in the detection area; based on the vegetation classification result, the target combustible load in the detection area is determined; according to the target combustible load and the power level of the transmission channel, the risk level of the transmission channel is determined, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid. The purpose of efficiently obtaining vegetation conditions using remote sensing information and then determining the risk conditions of the area surrounding the transmission channel is achieved, and the technical effect of improving the accuracy of transmission channel risk assessment is achieved, thereby solving the technical problem of unsatisfactory accuracy of transmission channel risk assessment existing in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a flow chart of an optional method for determining risk of a power transmission channel provided according to an embodiment of the present application;

[0018] Figure 2 is a block diagram of an optional method for determining risk of a power transmission channel provided according to an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of an optional method for determining risk of a power transmission channel provided according to an embodiment of the present application;

[0020] Figure 4 is a combustible load estimation flow chart of an optional transmission channel risk determination method provided in an embodiment of the present application;

[0021] Figure 5 is a schematic diagram of an optional transmission channel risk determination device provided according to an embodiment of the present application; DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0025] Remote sensing technology is a technology that collects surface or atmospheric information from the air or space through sensors without direct contact with the target object. This information is often captured in the form of electromagnetic radiation, including visible light, infrared, ultraviolet, microwaves, etc., and plays an important role in environmental monitoring and risk management.

[0026] Deep Convolutional Neural Network (DCNN) is a neural network model widely used in the field of deep learning. When processing input data with a grid structure, the network can automatically learn spatial hierarchical feature representations, so it has a wide range of applications in the field of computer vision.

[0027] The linear regression model is a statistical prediction model used to analyze the linear relationship between one or more independent variables and the dependent variable. It is simple and computationally efficient and is suitable for large-scale data processing problems.

[0028] The neural network model (CNN) is a computational model that imitates the structure and function of neurons in the human brain. The network has the advantages of high accuracy, strong flexibility and self-learning, and can be used to process nonlinear and prediction problems of complex data.

[0029] Support Vector Regression (SVR) is a regression analysis method based on the principle of Support Vector Machine (SVM). It is mainly used to solve regression prediction problems with small sample data, nonlinear relationships and high-dimensional feature space. Its core idea is to find an optimal decision boundary.

[0030] Allometric equations are mathematical models that describe the growth relationship between different parts of an organism (such as trunks, branches, leaves, and roots). They can be used to detect carbon storage and calculate fuel load. The equation provides a non-destructive method to determine biomass and plays an important role in forest management and ecological research.

[0031] According to an embodiment of the present application, a method embodiment for determining the risk of a power transmission channel is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 1 is a flow chart of a method for determining transmission channel risk according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0033] Step S102, acquiring remote sensing information, wherein the remote sensing information at least includes a power transmission channel and a detection area within a predetermined range of the power transmission channel;

[0034] It can be understood that the detection area required for the risk assessment is determined according to the location of the transmission channel, and remote sensing technology is used to obtain remote sensing information of the detection area. Remote sensing technology can cover the detection area more comprehensively and obtain more comprehensive remote sensing information. At the same time, the remote sensing information has high accuracy and can provide a more accurate data set for subsequent risk assessment, thereby improving the accuracy of risk assessment results.

[0035] In an optional embodiment, acquiring remote sensing information includes: acquiring initial acquisition information; using a predetermined correction method to correct the initial acquisition information to obtain remote sensing information, wherein the predetermined correction method includes at least one of the following: radiation correction for eliminating sensor errors, geometric correction for calibrating with the geographic coordinates of the detection area, and atmospheric correction for reducing scattering and absorption effects.

[0036] It can be understood that after obtaining the initial acquisition information, the initial acquisition information needs to be preprocessed, and the preprocessing methods may include data correction and image fusion. Data correction may include radiation correction, geometric correction, and atmospheric correction. Among them, radiation correction is used to eliminate sensor errors, geometric correction is used to calibrate with the geographic coordinates of the detection area, and atmospheric correction is used to reduce the effects of scattering and absorption. Image fusion can fuse spectral images and three-dimensional point cloud data, combine spectral features and structural features, and obtain a comprehensive remote sensing data set, that is, remote sensing information. By preprocessing the spectral image through one or more of the above three correction methods, the consistency and accuracy of the data are improved, providing an accurate and reliable data set for subsequent feature extraction.

[0037] Optionally, the above-mentioned radiation correction is used to eliminate or reduce the radiation error caused by factors such as sensors, atmosphere and lighting conditions during the image acquisition process, thereby converting the digital value of the image into a physical quantity close to the actual reflectivity or brightness temperature of the surface. When comparing different images or analyzing long time series, the accuracy and reliability of the data can be effectively guaranteed, which is helpful for the extraction of image features and the accuracy of vegetation classification. The above-mentioned geometric correction is used to correct the geometric deformation in the image so that the image can accurately match the ground real coordinate system or map, improve the positioning accuracy of the image, and ensure that the vegetation in the detection area can be accurately located. The above-mentioned atmospheric correction is used to eliminate or reduce the influence of atmospheric scattering and absorption on the spectral value of the image, ensure that the image can accurately reflect the real spectral characteristics of the detection target, so as to ensure the accuracy of the image characteristics of the subsequent extracts. Using the above-mentioned correction method, the spectral image can more accurately reflect the spectral characteristics of the ground target and improve the reliability of remote sensing information.

[0038] Step S104, performing feature extraction based on remote sensing information to determine the vegetation classification result in the detection area;

[0039] It can be understood that based on the remote sensing information of the detection area obtained, artificial intelligence models such as deep convolutional neural networks can be used for processing to obtain vegetation classification results for the detection area, thereby improving the classification accuracy and processing efficiency of remote sensing data.

[0040] In an optional embodiment, the remote sensing information includes a spectral image and three-dimensional point cloud data, and feature extraction is performed based on the remote sensing information to determine the vegetation classification result in the detection area, including: performing feature extraction based on the spectral image to determine the spectral features used to characterize the association between vegetation type and vegetation density; performing feature extraction based on the three-dimensional point cloud data to determine the structural features used to characterize the vegetation structure; and determining the vegetation classification result according to the spectral features and the structural features.

[0041] It can be understood that the remote sensing information obtained includes spectral images and three-dimensional point cloud data of vegetation, and the spectral images and three-dimensional point cloud data are used to extract features of the vegetation in the detection area. Among them, the spectral characteristics of the vegetation in the detection area can be obtained according to the spectral image of the detection area, and then the vegetation type and vegetation density information can be obtained; the structural characteristics of the detection area can be obtained according to the three-dimensional point cloud data of the detection area, and then the vegetation height and vegetation canopy density information can be obtained. Based on the spectral characteristics and structural characteristics of the above-mentioned vegetation, a deep convolutional neural network is used to obtain the vegetation classification results of the detection area. Combining the spectral characteristics provided by the spectral image with the structural characteristics provided by the three-dimensional point cloud data can improve the accuracy and efficiency of classification, provide accurate data for the risk assessment of the transmission channel, and effectively support the safe operation of the power grid and the protection of the ecological environment.

[0042] Optionally, the above spectral features can be multiple, for example, the Normalized Difference Vegetation Index (NDVI), the Enhanced Vegetation Index (EVI), and the Soil Adjusted Vegetation Index (SAVI). Among them, the Normalized Difference Vegetation Index (NDVI) is used to evaluate the health status and vegetation coverage of surface vegetation, which is calculated by the radiation values ​​of the near-infrared band and the red light band reflected by the surface. The Enhanced Vegetation Index (EVI) is used to obtain the health status and biomass information of the detected vegetation. By adjusting the influence of the red light band, reducing the interference of the atmospheric background, and enhancing the vegetation signal, the measurement results in densely vegetated areas are more reliable. The Soil Adjusted Vegetation Index (SAVI) is an improved vegetation index that can reduce the influence of the soil background on the calculation of the vegetation index. By extracting the above three spectral features, rich vegetation information in the detection area can be obtained. Combining these three spectral features for analysis, the vegetation status of the transmission channel and its surrounding areas can be comprehensively evaluated, which is of great significance for vegetation classification, evaluation of combustible load, and formulation of effective risk prevention and control strategies.

[0043] Optionally, multispectral or hyperspectral satellite images and LiDAR data are used to obtain remote sensing information of the transmission channel area. The multispectral or hyperspectral satellite images include Landsat, Sentinel-2, etc., which are used to obtain spectral images. The above-mentioned LiDAR data provides high-precision three-dimensional point cloud data. Among them, Landsat and Sentinel-2 are earth observation satellite projects initiated by different organizations, which are used to detect environmental resources on the earth's surface. LiDAR (Light Detection and Ranging) data is a remote sensing technology that measures distance, shape and terrain through laser beams. It generates a high-precision surface model by emitting laser pulses and measuring their return time.

[0044] Optionally, the data set based on the spectral characteristics and structural characteristics of the above-mentioned vegetation is divided into a training set and a validation set, and the constructed deep convolutional neural network is trained using the training set data. During the training process, the error between the predicted results and the actual results is reduced by minimizing the loss function, and the network parameters are optimized so that the pre-classified results gradually approach the actual results, thereby improving the accuracy of the network classification results. The performance of the deep convolutional neural network is verified using the validation set data to evaluate the classification performance of the network, and the network is optimized and adjusted in combination with the ground measured data and the validation results, so that the model is continuously updated and calibrated. By dividing the data set into a training set and a validation set, the deep convolutional neural network can continuously learn and optimize, becoming a reliable and high-precision tool, thereby improving the accuracy of the tree species classification results and the accuracy of the combustible load estimation results in the transmission channel detection area.

[0045] Step S106, determining the target combustible load in the detection area according to the vegetation classification result;

[0046] It can be understood that based on the above vegetation classification results, a suitable inversion model is selected, and the target combustible load in the detection area is calculated using the selected inversion model. Selecting a suitable inversion model based on the vegetation classification results can significantly improve the accuracy and practicality of combustible load estimation and fire risk assessment, and provide support for the safe operation of the transmission channel.

[0047] In an optional embodiment, the target combustible load in the detection area is determined based on the vegetation classification result, including: determining a target model from multiple predetermined models based on the vegetation classification result, wherein the multiple predetermined models correspond to different classification results respectively; using the target model to perform processing based on vegetation density to determine the target combustible load.

[0048] It can be understood that different vegetation types and structural characteristics have different effects on the safe management of transmission channels. According to different classification results, selecting a suitable model from multiple predetermined inversion models as the target model helps to simplify the data processing process, reduce the consumption of computing resources, and improve the efficiency of data processing and analysis. At the same time, it avoids the generalization problem of a single model on different vegetation types and enhances the applicability and effectiveness of the model. Based on the selected target model and the vegetation density of the classification target, the combustible load of the classification target is obtained. The use of an inversion model specific to the vegetation type can more accurately estimate the combustible load, thereby improving the accuracy of the risk assessment results and providing more detailed and hierarchical data support for the safe management of transmission channels.

[0049] Optionally, collect and preprocess ground measured data, and divide the ground measured data into a training set and a validation set; select a suitable inversion model based on different classification results; use the training set data to train the selected target inversion model, and use the loss function of the target inversion model to adjust the model parameters, reduce the error between the predicted results and the measured results, and improve the accuracy of the predicted results; use the validation set data to evaluate the prediction performance of the target inversion model, and evaluate the accuracy and reliability of the model based on the error between the predicted results and the measured results. Continuously collecting ground measured data to update and calibrate the model can ensure the long-term effectiveness of the model and provide solid data support for transmission channel risk assessment.

[0050] Optionally, the above-mentioned multiple inversion models include a linear regression model, a neural network model and a support vector regression model. The above-mentioned linear regression model can process the linear relationship between data and can be used to process continuous data variables; the above-mentioned neural network model can process the complex nonlinear relationship between data and can be used to process the prediction and classification problems of complex data. The support vector regression model can process the nonlinear relationship between data, and its complexity depends on the selection of kernel functions and the tuning of parameters. It has high flexibility and is used to process the nonlinear regression problems of medium and small sample data. For the estimation of combustible load, a linear regression model can be used to establish the mathematical relationship between the combustible load and variables such as vegetation density and tree species type. However, vegetation growth and environmental conditions are complex, and the data to be processed also have complex nonlinear relationships. It is necessary to combine other nonlinear models to establish the mathematical relationship between the combustible load and variables such as vegetation density and tree species type to ensure the accuracy and reliability of the prediction results. Selecting different inversion models based on different vegetation classification results can improve the efficiency of data processing and the accuracy of vegetation combustible load estimation.

[0051] Step S108, determining the risk level of the transmission channel according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid.

[0052] It can be understood that the risk level of the transmission channel is determined based on the target combustible load calculated according to the vegetation classification results and the power level of the transmission channel. Through the above processing, the importance of the transmission channel itself in the power grid is combined with the target combustible load of the surrounding detection area for risk assessment, which is conducive to better assessing the risk level of the transmission channel to maintain stable operation.

[0053] In an optional embodiment, the risk level of the transmission channel is determined according to the target combustible load and the power level of the transmission channel, including: determining a sampling location in the detection area; determining the underground litter reserve based on the ground measured data corresponding to the sampling location; correcting the target combustible load according to the underground litter reserve to obtain a corrected target combustible load; and determining the risk level based on the corrected target combustible load and the power level.

[0054] It can be understood that the power level of the transmission channel is determined, the sampling location of the ground measured data is determined in the detection area determined by the transmission channel, and the underground litter storage in the target area is determined based on the ground measured data collected at the sampling location. The underground litter storage is used to correct the target combustible load calculated according to the vegetation classification results to obtain the corrected target combustible load. Based on the corrected target combustible load and the power level of the transmission channel, the risk level of the transmission channel is determined. By comprehensively analyzing the impact of the above factors on the transmission channel, a more comprehensive and accurate risk assessment result can be obtained to ensure the safety and stability of the transmission channel.

[0055] Optionally, a risk assessment model can be used to determine the risk level based on the corrected target combustible load and the power level of the transmission channel. The above risk assessment model can be of various types, such as: a logistic regression model, which is used to process linear relationships between variables; a decision tree model, which can intuitively display the decision-making process and is used to process discrete variables; a random forest model, in which the model decision process has high transparency and is used to process high-dimensional feature space variables; a support vector machine model, which is used to process problems with high feature dimensions and a small number of samples; a deep learning model, which can process a large number of high-dimensional, unstructured variables; an integrated learning model, which has high model accuracy and is used to process problems that require high accuracy to reduce bias and variance; and a time series analysis model, which is used to process variables that change over time. Selecting a suitable assessment model based on the characteristics of the assessment data consisting of the corrected target combustible load and the power level of the transmission channel, the complexity of the problem, and the required prediction accuracy can improve data processing efficiency and the accuracy of prediction results.

[0056] In an optional embodiment, the target combustible load is corrected according to the underground litter reserves to obtain a corrected target combustible load, including: determining the estimated biomass in the detection area based on the vegetation radius and vegetation height indicated by the ground measured data; determining the carbon coefficient in the detection area based on the estimated biomass; determining the measured combustible load at the sampling location based on the carbon coefficient; correcting the target combustible load according to the measured combustible load and the underground litter reserves to obtain a corrected target combustible load.

[0057] It can be understood that measured vegetation information including vegetation radius and vegetation height is collected at the sampling site determined by the transmission channel, and the estimated biomass and carbon coefficient in the detection area are determined based on the collected measured information. Based on the above estimated biomass and carbon coefficient, the measured combustible load at the sampling site is determined. Based on the measured combustible load and underground litter reserves, the target combustible load determined by the inversion model is corrected to determine the corrected target combustible load. Using the measured combustible load and underground litter reserves to correct the target combustible load can comprehensively consider the accuracy of the ground measured data and the richness of remote sensing information, make up for the shortcomings of a single data source, and improve the reliability of the target combustible load estimation.

[0058] Optionally, the carbon coefficient refers to the proportion of carbon content in vegetation or soil. By collecting ground measured data, including tree species, vegetation diameter at breast height (i.e., vegetation radius) and vegetation height, the biomass of the detection area is determined using the allometric equation. Based on the biomass (i.e., estimated biomass), the carbon coefficient and carbon content of the detection area are determined. Based on the above biomass, carbon coefficient and carbon content, the combustible load of the detection area is obtained. The combustible load is the measured combustible load. The measured combustible load is compared with the target combustible load estimated by the inversion model, which can be used to verify and correct the inversion model, ensure the accuracy of the inversion model, and obtain the corrected target combustible load, thereby improving the reliability and effectiveness of the risk assessment of the transmission channel.

[0059] In an optional embodiment, the method further includes: determining the power level according to the load capacity of the transmission channel and the topological position of the transmission channel in the power grid.

[0060] It can be understood that the power level of the transmission channel is determined based on the load capacity of the transmission channel, that is, the maximum power that the transmission line can safely and stably transport and its topological position in the power grid. The transmission channel is risk assessed based on the power level and combustible load. Based on the results of the risk assessment, corresponding risk management and prevention and control strategies are adopted for the transmission channel, including but not limited to preventive maintenance, technology upgrades, and redundant design. Through the implementation of these strategies, the fire risk of the transmission channel can be effectively reduced, ensuring the safe and reliable operation of the transmission channel.

[0061] Optionally, the power level of a transmission channel refers to the rated voltage level of a transmission line, including low voltage transmission, medium voltage transmission, high voltage transmission, ultra-high voltage transmission, UHV transmission, direct current transmission and alternating current transmission, which determines the extent of the impact of the transmission line on the normal operation of the power grid. Transmission channels with different power levels and the same target combustible load have different risk levels. The higher the power level, the higher the risk level. At the same time, the higher the power level of a transmission line, the greater the impact on the safety of the power grid after a failure. When conducting risk assessments on it, higher accuracy is required to ensure the safe and reliable operation of the power grid.

[0062] Optionally, the corresponding risk management and prevention strategies for the transmission channel based on the above risk assessment results can be multiple, for example, preventive maintenance, that is, regular inspection and maintenance of transmission lines to prevent failures and accidents; technical upgrades, that is, updating aging equipment to improve the durability and reliability of transmission lines; redundant design, that is, designing multiple transmission lines to ensure that other lines can take over the power supply when one line fails; geographical diversification, that is, avoiding concentrating all transmission lines in one area to reduce the impact of natural disasters or man-made damage. Based on different risk assessment results, selecting different risk management strategies can provide more sophisticated, efficient and targeted risk prevention and control measures, improve fire prevention in transmission channels, and ensure the safety of the power grid.

[0063] Through the above step S102, remote sensing information is obtained, wherein the remote sensing information at least includes the transmission channel and the detection area within the predetermined range of the transmission channel; step S104, feature extraction is performed based on the remote sensing information to determine the vegetation classification result in the detection area; step S106, the target combustible load in the detection area is determined according to the vegetation classification result; step S108, the risk level of the transmission channel is determined according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid. The purpose of accurately obtaining the combustible information of the transmission channel and improving the efficiency of risk management can be achieved, and the technical effect of accurately conducting risk assessment on the transmission channel is achieved, thereby solving the technical problem of unsatisfactory accuracy of risk assessment of the transmission channel existing in the related technology.

[0064] Based on the above embodiments and optional embodiments, the present application proposes an optional implementation method for risk assessment of power transmission channels. Figure 2 is a block diagram of an optional method for determining transmission channel risk according to an embodiment of the present application, according to Figure 2 It can be seen that in the implementation of this application, the risk determination of the transmission channel is mainly divided into S1 data collection, S2 data preprocessing, S3 feature extraction, S4 tree species classification, S5 combustible load estimation, S5 risk assessment and S6 result verification.

[0065] Figure 3 is a schematic diagram of an optional method for determining transmission channel risk according to an embodiment of the present application, according to Figure 3 It can be seen that the detection area required for the risk assessment is determined according to the location of the transmission channel, and remote sensing information of the detection area is obtained using remote sensing technology. The acquired remote sensing information includes spectral images and three-dimensional point cloud data of vegetation. In order to make the image information more accurately reflect the vegetation information of the detection area, the acquired remote sensing information needs to be preprocessed.

[0066] Preprocessing methods include data correction and image fusion. Data correction includes radiation correction, geometric correction and atmospheric correction. Among them, radiation correction is used to eliminate sensor errors; geometric correction is used to calibrate with the geographic coordinates of the detection area; atmospheric correction is used to reduce the effects of scattering and absorption. Image fusion can fuse spectral images and three-dimensional point cloud data, combining spectral features and structural features to obtain a comprehensive remote sensing data set.

[0067] Based on the acquired remote sensing information, the vegetation in the detection area is feature extracted. The spectral characteristics of the vegetation in the detection area can be obtained based on the spectral image of the detection area, and then the vegetation type and vegetation density information can be obtained; the structural characteristics of the detection area can be obtained based on the three-dimensional point cloud data of the detection area, and then the vegetation height and vegetation canopy density information can be obtained.

[0068] Based on the above feature extraction, a deep convolutional neural network is used to obtain the vegetation classification results of the detection area. When using a deep convolutional neural network to classify vegetation, the data set based on the spectral characteristics and structural characteristics of the above vegetation is divided into a training set and a validation set. The constructed deep convolutional neural network is trained using the training set data. During the training process, the error between the predicted results and the actual results is reduced by minimizing the loss function, and the network parameters are optimized so that the classification results gradually approach the actual results, thereby improving the accuracy of the network classification results. The performance of the deep convolutional neural network is verified using the validation set data to evaluate the classification performance of the network, and the network is optimized and adjusted in combination with the ground measured data and the verification results, so that the model is continuously updated and calibrated.

[0069] According to different classification results, select a suitable model from multiple predetermined inversion models as the target model. Collect and preprocess ground measured data, and divide the ground measured data into training set and validation set; select a suitable inversion model according to different classification results; use the training set data to train the selected target inversion model, and use the loss function of the target inversion model to adjust the model parameters, reduce the error between the predicted results and the measured results, and improve the accuracy of the predicted results; use the validation set data to evaluate the prediction performance of the target inversion model, and evaluate the accuracy and reliability of the model based on the error between the predicted results and the measured results. Input the vegetation classification results obtained by deep convolutional neural network into the trained inversion model to obtain the combustible load of the classification target. Continuously collect ground measured data to update and calibrate the model to ensure the long-term effectiveness of the model.

[0070] At the sampling location determined by the transmission channel, measured vegetation information including vegetation radius and vegetation height is collected, and the estimated biomass and carbon coefficient in the detection area are determined based on the collected measured information. Based on the above estimated biomass and carbon coefficient, the measured combustible load at the sampling location is determined. Based on the measured combustible load and underground litter storage, the target combustible load determined by the inversion model is corrected to determine the corrected target combustible load.

[0071] The power level of the transmission channel is determined based on the load capacity of the transmission channel, i.e., the maximum power that the transmission line can safely and stably transport, and its topological position in the power grid. Based on the corrected target combustible load and the power level of the transmission channel, the risk level of the transmission channel is determined using a risk assessment model. Based on the results of the risk assessment, appropriate risk management and prevention and control strategies are adopted for the transmission channel, including but not limited to preventive maintenance, technology upgrades, and redundant design, to ensure the safe and reliable operation of the transmission channel.

[0072] Figure 4 is a combustible load estimation flow chart of an optional transmission channel risk determination method provided in an embodiment of the present application, such as Figure 4As shown in the figure, a typical plot is selected in the collection area to collect measured vegetation information, including tree height, number, diameter at breast height, tree species and biomass under the tree. Based on the above measured vegetation information, the measured fuel load is obtained by using the fuel load inversion model and the allometric growth model. Multi-source remote sensing data is used to obtain remote sensing information of the detection area. The remote sensing information can include data from different earth observation projects (such as high-resolution series data and Sentinel-2 data), and the remote sensing information is preprocessed to obtain a land cover classification map and NDVI data. Through the process of feature extraction and obtaining tree species classification, the vegetation classification results are obtained based on the remote sensing information. Based on the vegetation classification results, the target fuel load is obtained by using the fuel load inversion model. Based on the measured fuel load and the target fuel load, the corrected target fuel load is determined. Digital elevation data and weather station data can also be used to correct the inversion model of combustible load, and the missing parts of digital elevation data and weather station data can be filled by spatial interpolation to obtain the average monthly temperature, average monthly precipitation, average monthly solar radiation, etc. Based on the above average monthly temperature, average monthly precipitation, and average monthly solar radiation, the correction processing of the inversion model of combustible load is performed. Combined with the error between the measured combustible load and the target combustible load, the accuracy of the inversion model of combustible load can be determined, and the model can be updated and calibrated.

[0073] Using this method, different areas within the region can be divided into low-risk areas, medium-risk areas and high-risk areas according to the size of the risk. By adopting different risk management and prevention and control strategies for transmission channels in areas with different risk levels, the efficiency of risk management can be improved, providing strong support for the safe operation of the power system.

[0074] The above optional implementation methods achieve at least the following effects: data correction and image fusion technology are used to improve the accuracy of remote sensing data sets, and then based on the data sets, deep convolutional neural networks are used to classify tree species, and the classification results are verified and corrected in combination with ground measured data. This combination of technology improves the accuracy of vegetation classification; combining ground sample data and tree species classification results, an inversion model is used to quantitatively estimate the combustible load of different tree species and vegetation densities, providing scientific and accurate combustible load data for risk assessment, improving the accuracy of risk assessment results, and providing support for effective transmission channel risk prevention and control.

[0075] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0076] In this embodiment, a transmission channel risk determination device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0077] According to an embodiment of the present application, there is also provided an apparatus embodiment for implementing a method for determining risk of a power transmission channel. Figure 5 is a schematic diagram of a transmission channel risk determination device according to an embodiment of the present application, such as Figure 5 As shown, the above-mentioned transmission channel risk determination device includes an information acquisition module 702, a feature extraction module 704, a combustible load determination module 706, and a risk level determination module 708. The device is described below.

[0078] An information acquisition module 702 is used to acquire remote sensing information, wherein the remote sensing information at least includes a power transmission channel and a detection area within a predetermined range of the power transmission channel;

[0079] The feature extraction module 704 is connected to the information acquisition module 702 and is used to extract features based on remote sensing information to determine the vegetation classification result in the detection area;

[0080] The combustible load determination module 706 is connected to the feature extraction module 704 and is used to determine the target combustible load in the detection area according to the vegetation classification result;

[0081] The risk level determination module 708 is connected to the combustible load determination module 706, and is used to determine the risk level of the transmission channel according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid.

[0082] In a transmission channel risk determination device provided by an embodiment of the present application, an information acquisition module 702 is set to obtain remote sensing information, wherein the remote sensing information at least includes the transmission channel and the detection area within the predetermined range of the transmission channel; a feature extraction module 704 is connected to the information acquisition module 702, and is used to perform feature extraction based on the remote sensing information to determine the vegetation classification result in the detection area; a combustible load determination module 706 is connected to the feature extraction module 704, and is used to determine the target combustible load in the detection area according to the vegetation classification result; a risk level determination module 708 is connected to the combustible load determination module 706, and is used to determine the risk level of the transmission channel according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid. The purpose of accurately obtaining the combustible information of the transmission channel and improving the efficiency of risk management is achieved, and the technical effect of accurately performing risk assessment on the transmission channel is achieved, thereby solving the technical problem of unsatisfactory accuracy of transmission channel risk assessment existing in the related art.

[0083] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0084] It should be noted that the above information acquisition module 702, feature extraction module 704, combustible load determination module 706, and risk level determination module 708 correspond to steps S102 to S108 in the embodiment, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules can be run in a computer terminal as part of the device.

[0085] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0086] The above-mentioned transmission channel risk determination device may also include a processor and a memory. The information acquisition module 702, the feature extraction module 704, the combustible load determination module 706, the risk level determination module 708, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0087] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0088] An embodiment of the present application provides a non-volatile storage medium having a program stored thereon, which implements a method for determining risks of a power transmission channel when the program is executed by a processor.

[0089] The embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program stored in the memory and can be run on the processor. When the processor executes the program, the following steps are implemented: obtaining remote sensing information, wherein the remote sensing information at least includes a power transmission channel and a detection area within a predetermined range of the power transmission channel; performing feature extraction based on the remote sensing information to determine the vegetation classification result in the detection area; determining the target combustible load in the detection area based on the vegetation classification result; determining the risk level of the power transmission channel according to the target combustible load and the power level of the power transmission channel, wherein the power level is proportional to the impact of the power transmission channel on the operation of the power grid. The device in this article can be a server, a PC, etc.

[0090] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining remote sensing information, wherein the remote sensing information at least includes a transmission channel and a detection area within a predetermined range of the transmission channel; performing feature extraction based on the remote sensing information to determine a vegetation classification result in the detection area; determining a target combustible load in the detection area based on the vegetation classification result; determining a risk level of the transmission channel according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid.

[0091] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0092] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0097] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0100] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining transmission channel risk, characterized in that: include: Acquiring remote sensing information, wherein the remote sensing information at least includes a power transmission channel and a detection area within a predetermined range of the power transmission channel; Perform feature extraction based on the remote sensing information to determine the vegetation classification result in the detection area; Determining the target combustible load in the detection area according to the vegetation classification result; The risk level of the transmission channel is determined according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid.

2. The method according to claim 1, characterized in that The remote sensing information includes spectral images and three-dimensional point cloud data, and the feature extraction based on the remote sensing information to determine the vegetation classification result in the detection area includes: Extracting features based on the spectral image to determine spectral features for characterizing the association between vegetation type and vegetation density; Performing feature extraction based on the three-dimensional point cloud data to determine structural features for characterizing vegetation structure; The vegetation classification result is determined according to the spectral characteristics and the structural characteristics.

3. The method according to claim 1, characterized in that Determining the target combustible load in the detection area according to the vegetation classification result includes: Determining a target model from a plurality of predetermined models according to the vegetation classification result, wherein the plurality of predetermined models correspond to different classification results respectively; The target model is used to perform processing based on vegetation density to determine the target combustible load.

4. The method according to claim 1, characterized in that: Determining the risk level of the power transmission channel according to the target combustible load and the power level of the power transmission channel includes: determining sampling locations within the detection area; Determine the underground litter storage based on the ground measured data corresponding to the sampling location; According to the underground litter storage, the target combustible material load is corrected to obtain a corrected target combustible material load; The risk level is determined based on the corrected target combustible load and the power level.

5. The method according to claim 4, characterized in that The target combustible load is corrected according to the underground litter storage to obtain a corrected target combustible load, including: Determining an estimated biomass in the detection area based on the vegetation radius and vegetation height indicated by the ground measured data; determining a carbon index in the detection area based on the estimated biomass; Determining the measured combustible load at the sampling location based on the carbon coefficient; According to the measured combustible load and the underground litter reserve, the target combustible load is corrected to obtain the corrected target combustible load.

6. The method according to claim 1, characterized in that The obtaining of remote sensing information comprises: Obtain initial collection information; The initially collected information is corrected using a predetermined correction method to obtain the remote sensing information, wherein the predetermined correction method includes at least one of the following: radiation correction for eliminating sensor errors, collective correction for calibration with the geographic coordinates of the detection area, and atmospheric correction for reducing scattering and absorption effects.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: The power level is determined according to the load capacity of the transmission channel and the topological position of the transmission channel in the power grid.

8. A transmission channel risk determination device, characterized in that: include: An information acquisition module, used to acquire remote sensing information, wherein the remote sensing information at least includes a power transmission channel and a detection area within a predetermined range of the power transmission channel; A feature extraction module, used to extract features based on the remote sensing information and determine the vegetation classification result in the detection area; A combustible load determination module, used to determine the target combustible load in the detection area according to the vegetation classification result; A risk level determination module is used to determine the risk level of the transmission channel according to the target combustible load and the power level of the transmission channel, wherein the power level is proportional to the impact of the transmission channel on the operation of the power grid.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method for determining the risk of a power transmission channel according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the transmission channel risk determination method described in any one of claims 1 to 7.

Images