Power grid emergency disposal method for risk assessment

Abstract

The invention provides a power grid emergency disposal method for risk assessment, relates to the technical field of image processing, and is used for improving the safe operation capability of a power grid in a mountain environment. The risk assessment and power grid emergency disposal method specifically comprises the following steps: regularly collecting overhead transmission line video images in the mountain environment, and constructing a transmission line video set; performing change analysis on the power transmission line video set to obtain a newly added vegetation coverage area, a vegetation degradation area and a crack extension area; obtaining the water content change and the area coverage type of each area according to the three areas obtained in the step S2; the landslide risk is predicted according to the water content of each area and the area coverage type, and an emergency disposal scheme is generated, through the steps, the landslide risk can be evaluated, and early warning and countermeasures are taken before the risk occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a risk assessment method for emergency disposal of a power grid, which is used to improve the safe operation capability of a power grid in a mountain environment. Background Art

[0002] With the rapid development of tourism, the construction of scenic area infrastructure is becoming more and more perfect. As an indispensable and important energy network in the infrastructure of scenic areas, the power grid plays a vital role in the daily operation of scenic areas and the safety experience of tourists. The reliability of the power grid is directly related to the power supply guarantee and operation efficiency of the scenic area. However, due to the complex terrain and special environment of mountain scenic areas, the layout of the power grid usually adopts the overhead transmission method to adapt to the needs of rugged terrain and irregular terrain. Compared with the layout of power grids in plain areas, the layout of power grids in mountain scenic areas is more expensive and more difficult to construct. At the same time, it also faces more technical and economic challenges in the operation and maintenance process. Although this overhead transmission method solves the restrictions of complex terrain on power grid layout to a certain extent, it also makes the transmission line more susceptible to external environmental factors, such as natural disasters and foreign invaders. How to ensure the safe operation of the power grid in mountain scenic areas has become one of the important issues restricting the sustainable development of scenic spots.

[0003] In the prior art, the maintenance of the power grid in mountain scenic areas mainly adopts the mode of post-maintenance, that is, the overhead transmission lines are inspected and handled by manual inspection. When the transmission lines are affected by foreign invaders (such as bird nests, garbage and branches discarded by tourists) or extreme weather (such as ice and snow, strong winds), they are usually discovered, cleaned and repaired manually. Although this method can solve the problem to a certain extent, its limitations are very obvious. First, the manual inspection cycle is long and potential hidden dangers cannot be discovered in real time; secondly, for emergencies caused by extreme weather or natural disasters (such as heavy rain and snow), the lag of manual maintenance may cause the interruption of power grid operation, and even cause greater economic losses and safety hazards. Especially in the mountain environment, due to the special natural conditions of high altitude, low temperature and windy, the transmission lines are exposed to the wind and sun for a long time, and the deterioration rate of the lines and the surrounding environment is much higher than that in the plains. In addition, the geological structure of the mountain is complex, and factors such as loose soil and broken rocks can easily cause large and small landslides. The impact of such geological disasters on the power grid is often devastating, and may cause the overall collapse of the transmission line or even a large-scale power outage. The existing post-maintenance model is obviously unable to cope with this problem. Therefore, there is an urgent need for a technology that can conduct risk assessment on disasters such as landslides and emergency disposal plans to achieve pre-prediction and prevention of potential risks, thereby ensuring the safe operation of the power grid in mountain scenic areas.

[0004] In recent years, with the rapid development of artificial intelligence technology, especially the widespread application of machine vision technology, it has demonstrated mature application value and technical advantages in medical diagnosis, autonomous driving, industrial inspection and other fields. Through image processing, pattern recognition and deep learning technologies, machine vision can efficiently and accurately analyze dynamic changes in complex scenes, providing important support for the intelligent upgrading of various industries. However, in the field of risk assessment of power grid operation in mountainous environments, the application of machine vision technology is still a blank. The transmission lines in mountainous scenic areas are often located in areas with steep terrain and harsh environments. Traditional monitoring and evaluation methods are difficult to meet the requirements of efficiency and accuracy. By collecting image data of the mountain environment and conducting intelligent analysis, the risks of geological disasters such as landslides can be identified and dynamically monitored early, thereby realizing the transformation from "post-maintenance" to "pre-prediction".

[0005] Based on this, the present invention proposes a risk assessment method for emergency disposal of power grids, which assesses the risk of landslides and takes early warning and response measures before the risk occurs. Summary of the invention

[0006] The present invention provides a risk assessment method for emergency disposal of power grid, which specifically comprises the following steps:

[0007] S1: Regularly collect video images of overhead power transmission lines in mountainous environments and construct a transmission line video set;

[0008] S2: performing change analysis on the transmission line video set to obtain newly added vegetation coverage areas, vegetation degradation areas, and crack extension areas;

[0009] S3: Obtain the water content change and regional coverage type of each region according to the three regions obtained in step S2;

[0010] S4: Predict landslide risks and generate emergency response plans based on the moisture content of each area and the area coverage type.

[0011] The present invention provides a risk assessment power grid emergency disposal system, the system comprising:

[0012] Image acquisition equipment: The image acquisition equipment regularly acquires video images of overhead power transmission lines in a mountain environment and constructs a transmission line video set;

[0013] Change analysis module: the change analysis module performs change analysis on the transmission line video set to obtain newly added vegetation coverage areas, vegetation degradation areas and crack extension areas;

[0014] Moisture content analysis module: the moisture content analysis module obtains the moisture content change and regional coverage type of each region according to the three regions obtained;

[0015] Comprehensive determination module: The comprehensive determination module predicts the landslide risk and generates an emergency disposal plan based on the water content of each area and the area coverage type.

[0016] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned risk assessment method for emergency disposal of power grid when executing the computer program.

[0017] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned risk assessment method for emergency handling of a power grid.

[0018] Compared with the prior art, the present invention proposes a risk assessment method for emergency disposal of power grids, which identifies risk areas through image detection technology. During the detection process, the extracted features are enhanced and weakened. While extracting potential different features, the connection between shallow and deep features is enhanced to guide target segmentation. Based on the risk area, the type and water content of the risk area are identified. Through comprehensive judgment of these two key factors, the present invention can identify high-risk areas around transmission lines where landslides may occur, and provide scientific early warning basis for relevant departments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is the network structure diagram in this application. DETAILED DESCRIPTION

[0021] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0022] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0023] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0024] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the examples can be practiced without these specific details.

[0025] The embodiment of this specification proposes a risk assessment method for emergency disposal of a power grid, which specifically includes the following steps:

[0026] S1: Regularly collect video images of overhead power transmission lines in mountainous environments and construct a transmission line video set;

[0027] S2: performing change analysis on the transmission line video set to obtain newly added vegetation coverage areas, vegetation degradation areas, and crack extension areas;

[0028] S3: Obtain the water content change and regional coverage type of each region according to the three regions obtained in step S2;

[0029] S4: Predict landslide risks and generate emergency response plans based on the moisture content of each area and the area coverage type.

[0030] In one implementation, video images of overhead power transmission lines in a mountain environment are collected periodically, and a transmission line video set is constructed;

[0031] The environment and video target for the collection are mountain overhead power transmission lines. Before video collection, the length of the transmission line area needs to be determined. The transmission lines cross multiple mountains, some of which may be eroded by strong winds all year round, and the mountain stability is poor, especially prone to landslides. In order to determine the risk of landslides in complex environments, this plan determines the collection cycle to be once a week. The selection of a one-week cycle is mainly based on the characteristics of geological changes in the mountain environment. It not only avoids the omission of geological change details due to a long data collection cycle, but also takes into account inspection efficiency and resource utilization. At the same time, each collection task is selected as much as possible under rainless and windless weather conditions to ensure the flight stability of the drone and the quality of image acquisition. In addition, due to the frequent strong winds and high wind speeds in mountainous areas, weather conditions need to be strictly monitored, and collection tasks are preferably carried out in the morning or afternoon when the wind speed is lower.

[0032] The implementation of the collection task is based on the core design idea of ​​segmented inspection of key areas. Specifically, the transmission line is divided into multiple continuous key inspection areas, each of which contains multiple transmission towers and mountains along the line. The drone needs to complete the inspection of all areas in a predetermined order in each mission, and the inspection flight path of each area remains fixed to ensure that the image data of different time periods can correspond to the same geographical location one by one. For the flight path design of each section of the transmission line, it is preferred to use the transmission tower as a node and adopt a straight-line flight mode from one transmission tower to the next, while covering the mountain areas above and around the line where landslides may occur, such as steep slopes, fault zones with exposed rocks, etc.

[0033] Industrial-grade drones are preferred, such as the Autel EVO Max series, which have strong wind resistance and long endurance, and are suitable for operations in high wind speed environments. The flight altitude is set according to the location of the power transmission network and the height of vegetation to ensure safety, while avoiding interference with flight caused by mountain vegetation or sudden changes in wind speed. Combined with the undulating characteristics of the mountain environment, the drone can dynamically adjust the flight altitude through the built-in lidar module to ensure an appropriate relative distance from the mountain surface, thereby obtaining clear images of mountain details. Set a fixed flight speed to balance image stability and acquisition efficiency, so as to ensure that a single flight can complete the acquisition task of a key area.

[0034] The drone equipment is also equipped with a multispectral camera and a high-precision inertial navigation system, which can simultaneously collect visible light and multispectral image data, providing a comprehensive analysis basis for the mountain environment and vegetation coverage. During the flight, the drone transmits the multispectral image to the ground monitoring station in real time. The power grid equipment inspection personnel can check the data integrity in real time based on the quality of each spectral image. If the vegetation reflectance data is missing, the image contrast is poor, or some areas are not covered, the flight route or parameters can be adjusted immediately for supplementary collection. Since strong winds or air pressure fluctuations often occur along the high mountains, the drone needs to have the function of stable spectral data collection, automatically correcting the image offset caused by wind speed changes, so as to ensure the clarity and accuracy of the multispectral data.

[0035] After the acquisition is completed, the acquired visible light video images are grouped and processed according to the sections of the power transmission line. Finally, the grouped visible light video images in multiple cycles are obtained to construct a power transmission line video set, in which each sample in the power transmission line video set is a plurality of video clips acquired in multiple cycles of the same section of the power transmission line, that is, a plurality of visible light video images acquired at different times on the same power transmission line.

[0036] In addition, the present invention also performs group processing on the multispectral image data collected simultaneously and aligns them with corresponding video frames in the visible light video image to obtain a multispectral image set after group processing in multiple cycles.

[0037] In order to achieve emergency treatment of the power grid, the present invention also requires a change analysis of the transmission line video set;

[0038] The change analysis is implemented by a change region segmentation network, which is composed of an encoding module, a multi-scale fusion module and a decoding module;

[0039] The encoding module is composed of three residual networks connected in sequence, and the residual network is composed of a skip connection network and a feature stacking network connected in sequence;

[0040] The skip connection network includes an input layer, an intermediate layer and an output layer, wherein the input layer and the output layer are each provided with a skip connection; the input layer, the intermediate layer and the output layer are respectively defined as:

[0041]

[0042] in, are the input and output of the input layer, respectively. Represents the output of the intermediate layer and the output layer, Conv(), Conv 2 () represent one and two convolution calculations respectively, Represents two separable convolution calculations;

[0043] The feature overlay network consists of an enhanced overlay network and a weakened overlay network. The enhanced overlay network is used to enhance the local detail features extracted from the feature map. The enhanced local detail features are used to guide segmentation in the decoding module. The enhanced overlay network is defined as:

[0044]

[0045] in, represents the input feature map of the enhanced stacking network, Indicates that the input feature map After extracting k regions in the width direction, the 1st, 2nd, and kth regions are constructed into region vectors using k region feature maps σ is the activation function, F EN To enhance the output of the overlay network;

[0046] Attenuation superposition is used to attenuate the extracted local detail features to prevent the feature map process of the next feature extraction layer from over-relying on the local detail features extracted by the previous feature extraction layer. In this way, the three residual networks and subsequent residual networks are not overly affected by the feature extraction of the previous residual network, which is conducive to extracting detail features of more areas. The attenuation superposition network is defined as:

[0047]

[0048] Among them, F DE To weaken the output of the superposition network; the F calculated by the feature superposition network in each previous residual network DE As the input feature map of the skip connection network input layer in the subsequent residual network, the input feature map of each feature stacking network is the output feature map of the skip connection network output layer in the residual network to which the feature stacking network belongs. The three outputs of the enhanced superposition network in the three residual networks are used as the input feature maps of the multi-scale fusion module, and defined Represents the three outputs of the enhanced overlay network;

[0049] In the process of feature extraction by neural network, the expressive ability of features gradually transitions from shallow texture features to deep semantic features as the number of network layers increases. The extraction of deep features depends largely on the basis provided by shallow features, so the quality of shallow features directly affects the expression of deep features. However, shallow features are not always the optimal feature basis. They may interfere with the extraction of deep features due to containing too much redundant information or irrelevant content, limiting the network's ability to accurately identify targets. In response to this problem, the present invention proposes an innovative feature processing method, which performs differentiated processing on the extracted features by designing a dual-path structure, thereby optimizing the transmission and utilization of features. Specifically, the method processes the extracted features through two independent paths: in the first path, the features are enhanced to make them more prominent and clear, so as to provide more accurate feature expression for the subsequent target detection module and improve the accuracy of target detection; in the second path, the extracted features are weakened, and the weakened features are superimposed back on the original feature map. In this way, through the processing of the second channel, the interference of shallow features on deep feature extraction can be effectively suppressed, forcing the deep neural network to dig out other potential and more discerning deep features while relying less on shallow features, thereby capturing richer semantic information of the target. The core of this dual-channel structural design is to balance the correlation and independence between shallow features and deep features: on the one hand, it provides stronger support for deep feature extraction by enhancing shallow features, and on the other hand, it creates conditions for independent extraction of deep features by weakening the influence of shallow features.

[0050] The multi-scale fusion module includes three parallel fusion networks, where the input of the first fusion network is and The input of the second fusion network is and The input of the third fusion network is and

[0051] The fusion process includes:

[0052] Step (1): Calculate each fusion network input feature map and Similarity feature map F s , the similarity feature map F s Each element of is defined as:

[0053]

[0054] in, is the pixel value of the first input feature map of the fusion network at (c,u,v). The scale of the first input feature map is Channel*W1*H1. is the pixel value of the second input feature map of the fusion network at (c,x,y). The scale of the second input feature map is Channel*W2*H2. The similarity feature map F s The scale is 1*(W1*H1)*(W2*H2);

[0055] Step (2): Based on the similarity feature graph F s , for input and The similar features of the enhanced output are obtained and The similarity feature enhancement calculation is:

[0056]

[0057]

[0058] in, and Represents the enhanced input feature map;

[0059] Step (3): Fusion is performed based on the similar enhanced outputs obtained from each fusion network:

[0060]

[0061]

[0062]

[0063]

[0064] in, and Respectively and The output features after similar features are enhanced by the first fusion network, and Respectively and The output features are enhanced by similar features of the second fusion network. and Respectively and Output features enhanced by similar features through the third fusion network;

[0065] In the process of feature map fusion, in order to more efficiently mine and utilize key information from feature maps of different depths, the present invention proposes a fusion branch design. The design constructs three branches, and inputs three feature maps of different depths respectively. Each branch selects two feature maps as input and performs similarity calculation on them. Through similarity calculation, the same feature parts in feature maps of different depths can be extracted. These similar features reflect the information that can still be stably retained in the process of multi-layer feature extraction and layer-by-layer feature suppression. This stable existence of similar features shows that it has a high degree of relevance and importance in the multi-layer expression of the network, and can therefore be considered as a key feature that needs to be focused on in the target detection task. Based on this analysis, the present invention further uses these similar features to enhance the two related feature maps to ensure that these key information can be expressed more prominently. Afterwards, by fusing the enhanced feature maps, the overall expression ability of the features can be significantly improved in the fusion process, providing more effective input support for subsequent target detection.

[0066] The decoding module includes 4 upsampling stages:

[0067]

[0068] Among them, i∈{1,2,3}, Conv_De represents the deconvolution calculation, and represents the deconvolution feature map and up-sampled feature map of the i-th layer of the decoding module, F out Output image showing segmentation of vegetation covered areas, vegetation degraded areas, and crack extension areas.

[0069] According to the three regions obtained in step S2, the moisture content change and regional coverage type of each region are obtained:

[0070] Setting vegetation degraded area masks and vegetation covered area masks according to the segmented vegetation degraded areas and vegetation covered areas, and using the above masks to clip the visible light image and multispectral image corresponding to the vegetation degraded area, as well as the visible light image and multispectral image corresponding to the vegetation covered area;

[0071] The soil type of the vegetation degraded area is determined based on the visible light image corresponding to the vegetation degraded area, and the water content change of the vegetation degraded area is calculated based on the multispectral image corresponding to the vegetation degraded area;

[0072] The vegetation type of the vegetation covered area is determined based on the visible light image corresponding to the vegetation covered area, and the change in water content in the degraded area is calculated based on the multispectral image.

[0073] In the process of determining the soil type of the vegetation degraded area according to the visible light image corresponding to the vegetation degraded area, the soil type is sandy soil, loam, and clay, and the image features include color and texture features, and a support vector machine is used as a classification model;

[0074] The changes in water content in vegetation-degraded areas and vegetation-covered areas are calculated based on multispectral images. NDWI and NDVI are calculated based on multispectral images:

[0075]

[0076] Water content T =α·NDWI 2 +β·NDVI+γ;

[0077] Among them, ρ green , NIR , RED They represent the green light band, near-infrared band, and red light band respectively. α, β, and γ are weight parameters. α is 0.6-0.8, and β is 0.2-0.4. The NDWI of soil and vegetation is between [-1,1]. The higher the moisture, the closer the NDWI is to 1, and vice versa. Considering the saturation effect of NDWI, when NDWI is close to 1, the sensitivity to moisture decreases. In the vegetation coverage area, the higher the NDVI, the healthier the vegetation, which indirectly reflects that the soil has sufficient moisture.

[0078] Calculate the difference in water content between the first and last acquisition time of the target area to obtain the change in water content of the target area;

[0079] In the process of determining the vegetation type of the vegetation covered area according to the visible light image corresponding to the vegetation covered area, the soil types are grassland, shrubs and trees, and image features including RGB mean and method, normalized color index and HIS color features are used, and random forest is used as the classification model;

[0080] Grassland generally presents a more uniform green color, with a higher reflectivity of the green channel (G), a lower RGB mean, and a consistent hue. At the same time, the hue (Hue) of the grass is concentrated in the green area, with a higher saturation (Saturation), and a higher and uniform brightness (Intensity). The green reflectivity of shrubs is high, but due to the density of vegetation and the complex structure of leaves, the mean and variance of RGB are larger than those of grass. In addition, shrubs have a higher saturation and a slightly lower brightness. The color of trees varies greatly (canopy shadows are mixed with leaves), and the RGB variance is larger. At the same time, the brightness distribution of trees is uneven, and the canopy shadows cause large changes in saturation and brightness.

[0081] Predict landslide risks and generate emergency response plans based on the moisture content of each area and the area coverage type;

[0082] Landslide risk: R_total = w1·R soil +w2·R veg +w3·R crack ;

[0083] w1, w2 and w3 are the weight scores of the branch lines respectively; R total takes a value between 0 and 1;

[0084] For low-risk areas with R total < 0.4, water content and crack dynamics are continuously monitored, and weekly inspections of power grid safety are carried out and data are updated;

[0085] For medium-risk areas with 0.4≤R total<0.8, monitor the moisture content and crack expansion every three days and notify the grid operation and maintenance department to start backup circuit dispatch preparations;

[0086] For high-risk areas with R total ≥ 0.8, the moisture content and crack expansion are monitored daily, the drainage system is urgently cleared, the soil moisture content is reduced, retaining walls or landslide protection nets are set up in crack or landslide warning areas, and at the same time, the backup circuit is immediately started and the power supply line is switched to ensure power supply.

[0087]

[0088] ΔW soil represents the change of water content in vegetation degradation area, W soil_critical Indicates the critical value of water content change corresponding to the soil type (80% for sandy soil, 70% for loam, 60% for clay).

[0089]

[0090] ΔW veg represents the change in water content in the vegetation coverage area, W veg_critical Indicates the critical value of water content change corresponding to the vegetation coverage area (the soil type in the vegetation coverage area is usually loam or clay, and the average value W veg_critical =65%),

[0091] S veg Indicates the stability score of vegetation type, grassland: S veg =0.3, shrubs: S veg =0.6, tree: S veg =0.9; S max Indicates the highest stability score of vegetation type (take S max =0.9 for trees);

[0092] When the vegetation type is less stable (such as grassland) and the water content varies greatly, R veg→1 (high risk), when the vegetation type is stable (such as trees) and the water content changes little, R veg →0 (low risk);

[0093]

[0094] Among them, Length and Width are the longest and widest values ​​of the crack extension area, L_max and W_max represent the crack extension warning length and width, w_L and w_W represent the weight parameters of length and width, R crack The value is between 0 and 1;

[0095] In order to accurately predict whether a landslide will occur near a transmission line, the present invention fully considers the two key natural factors affecting landslides - mountain type and water content, and determines the risk of landslides through phased detection and analysis. First, the present invention uses visible light video images to conduct the first phase of monitoring of the area around the transmission line, focusing on analyzing the changes in vegetation coverage, the degree of vegetation degradation, and the distribution characteristics of new cracks over a period of time. By detecting these surface features, potential risk areas can be preliminarily identified, and their types can be classified in combination with the geomorphic features of the mountain. This stage of detection can not only quickly lock in areas where there may be a risk of landslides, but also provide geographical and geological background information for subsequent in-depth analysis.

[0096] After completing the initial risk identification in the first stage, the present invention further uses multispectral images to detect the moisture content of the above-mentioned potential risk areas. Multispectral images have the characteristics of high spectral resolution and can sensitively capture the distribution of moisture content in soil and rock mass. Through reflectivity analysis of specific bands, the moisture level of the risk area can be accurately assessed. Moisture content is an important inducing factor of landslides. Therefore, the present invention further improves the assessment of potential landslide risk areas through quantitative detection of moisture content.

[0097] Based on the detection results of the above two stages, the present invention jointly analyzes the mountain type and water content information to construct a landslide risk prediction model. The mountain type determines the geological characteristics and stability of the mountain, while the water content reflects the dynamic impact of external environmental changes on the stability of the mountain. Through the comprehensive judgment of these two key factors, the present invention can identify high-risk areas around the transmission line where landslides may occur, and provide scientific early warning basis for relevant departments.

[0098] The present invention provides a risk assessment power grid emergency handling system, the system comprising:

[0099] Image acquisition equipment: The image acquisition equipment regularly acquires video images of overhead power transmission lines in a mountain environment and constructs a transmission line video set;

[0100] Change analysis module: the change analysis module performs change analysis on the transmission line video set to obtain newly added vegetation coverage areas, vegetation degradation areas and crack extension areas;

[0101] Moisture content analysis module: the moisture content analysis module obtains the moisture content change and regional coverage type of each region according to the three regions obtained;

[0102] Comprehensive determination module: The comprehensive determination module predicts the landslide risk and generates an emergency disposal plan based on the water content of each area and the area coverage type.

[0103] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned risk assessment method for emergency disposal of power grid when executing the computer program.

[0104] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned risk assessment method for emergency handling of a power grid.

[0105] 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 memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0106] In this specification, the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the partial description of the previous embodiments.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A risk assessment method for emergency disposal of power grid, characterized in that: The method specifically comprises the following steps: S1: Regularly collect video images of overhead power transmission lines in mountainous environments and construct a transmission line video set; S2: performing change analysis on the transmission line video set to obtain newly added vegetation coverage areas, vegetation degradation areas, and crack extension areas; S3: Obtain the water content change and regional coverage type of each region according to the three regions obtained in step S2; S4: Predict landslide risks and generate emergency response plans based on the moisture content of each area and the area coverage type.

2. A risk assessment method for emergency disposal of power grid according to claim 1, characterized in that: The change analysis is implemented through a change region segmentation network, which consists of an encoding module, a multi-scale fusion module and a decoding module.

3. A risk assessment method for emergency disposal of power grid according to claim 2, characterized in that: The encoding module is composed of three residual networks connected in sequence, and the residual network is composed of a skip connection network and a feature superposition network connected in sequence; the feature superposition network is composed of an enhanced superposition network and a weakened superposition network, wherein the enhanced superposition network is used to enhance the local detail features extracted from the feature map, and the enhanced local detail features are used to guide segmentation in the decoding module. The enhanced superposition network is defined as: in, represents the input feature map of the enhanced stacking network, Indicates that the input feature map After extracting k regions in the width direction, the 1st, 2nd, and kth regions are constructed into region vectors using k region feature maps σ is the activation function, F EN To enhance the output of the overlay network.

4. A risk assessment power grid emergency handling method according to claim 3, characterized in that: The weakened overlay network is defined as: Among them, F DE To weaken the output of the overlay network.

5. The method for emergency disposal of power grid based on risk assessment according to claim 2, characterized in that: The multi-scale fusion module includes three parallel fusion networks, where the input of the first fusion network is and The input of the second fusion network is and The input of the third fusion network is and 6. A risk assessment method for emergency disposal of power grid according to claim 5, characterized in that: The fusion process includes: Step (1): Calculate each fusion network input feature map and Similarity feature map F s , the similarity feature map F s Each element of is defined as: in, is the pixel value of the first input feature map of the fusion network at (c,u,v). The scale of the first input feature map is Channel*W1*H1. is the pixel value of the second input feature map of the fusion network at (c,x,y). The scale of the second input feature map is Channel*W2*H2. The similarity feature map F s The scale is 1*(W1*H1)*(W2*H2); Step (2): Based on the similarity feature graph F s , for input and The similar features of the enhanced output are obtained and The similarity feature enhancement calculation is: Step (3): Fusion is performed based on the similar enhanced outputs obtained from each fusion network: in, and Respectively and The output features after similar features are enhanced by the first fusion network, and Respectively and The output features are enhanced by similar features of the second fusion network. and Respectively and The output features are enhanced by similar features through the third fusion network.

7. A risk assessment method for emergency disposal of power grid according to claim 1, characterized in that: The soil type of the vegetation degraded area is determined based on the visible light image corresponding to the vegetation degraded area, and the water content change of the vegetation degraded area is calculated based on the multispectral image corresponding to the vegetation degraded area; The vegetation type of the vegetation covered area is determined based on the visible light image corresponding to the vegetation covered area, and the water content change in the degraded area is calculated based on the multispectral image.

8. A risk-assessed power grid emergency handling system, used to execute a risk-assessed power grid emergency handling method as claimed in any one of claims 1 to 7, characterized in that The system comprises: an image acquisition device: the image acquisition device regularly acquires video images of overhead power transmission lines in a mountain environment and constructs a transmission line video set; Change analysis module: the change analysis module performs change analysis on the transmission line video set to obtain newly added vegetation coverage areas, vegetation degradation areas and crack extension areas; Moisture content analysis module: the moisture content analysis module obtains the moisture content change and regional coverage type of each region according to the three regions obtained; Comprehensive determination module: The comprehensive determination module predicts the landslide risk and generates an emergency disposal plan based on the water content of each area and the area coverage type.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a risk assessment method for emergency handling of a power grid as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a risk assessment method for emergency handling of a power grid according to any one of claims 1 to 7.

Images