Ultra-high voltage maintenance safety distance assessment method, device, equipment and storage medium

Abstract

The present invention relates to the technical field of ultra-high voltage maintenance, and discloses an ultra-high voltage maintenance safety distance assessment method, device, equipment and storage medium. The method pre-processes a point cloud data set based on a preset rarefaction and registration algorithm to obtain a point cloud data set for preset point cloud feature extraction network training to obtain a point cloud classification model; inputs the point cloud data to be classified into the model to output a point cloud classification result; judges the point cloud classification result based on a deep learning model to determine the straight tower point cloud; and judges whether it is safe by comparing the target distance between the operator of the soft ladder and the target conductor and the tower based on the point cloud of the straight tower and the cylinder to simulate the soft ladder. The present invention quickly processes massive point cloud data through rarefaction and registration without segmenting and extracting features from the point cloud data set. For ultra-high voltage maintenance using the soft ladder method, a straight tower is selected and then the operation simulation is performed through a cylinder, so that the distance calculation is more accurate and the accuracy of safety judgment is improved.

Description

Technical Field

[0001] The present invention relates to the field of ultra-high voltage maintenance technology, and in particular to an ultra-high voltage maintenance safety distance assessment method, device, equipment and storage medium. Background Art

[0002] Overhead ultra-high voltage transmission lines are an important way of power transmission in the power industry. The safe and stable operation of transmission lines directly affects the high reliability and stable power supply of the power system. Therefore, regular and effective inspection and maintenance of transmission lines has become an important task for the power industry. At present, the inspection of overhead ultra-high voltage transmission lines mainly relies on manual and mechanical operations. Transmission line inspection must ensure that the various distances between transmission conductors and line corridors meet the requirements of safety distance regulations, especially the safety of maintenance personnel in manual operations.

[0003] The traditional safety distance assessment method requires the use of image recognition, analysis, and calculation techniques to obtain assessment results, which involves complex calculations such as ground filtering, DEM construction, object classification, and wire fitting. There is a possibility of data deviation and it is not accurate enough, which will affect the accuracy of the judgment results. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for ultra-high voltage maintenance safety distance assessment, aiming to solve the technical problems such as safety hazards existing in the maintenance process of existing overhead ultra-high voltage transmission lines, and the low accuracy of existing safety assessment methods and the possibility of misjudgment.

[0005] To achieve the above object, the present invention provides a method for evaluating the safety distance of ultra-high voltage maintenance, comprising:

[0006] Acquire a point cloud data set of an ultra-high voltage transmission channel, and pre-process the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set;

[0007] Training a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model;

[0008] Inputting the point cloud data to be classified into the point cloud classification model to output the point cloud classification result;

[0009] The point cloud classification result is judged based on the deep learning model to determine the straight tower point cloud whose tower type is a straight tower;

[0010] Simulating the target distance between the ladder operator and the target conductor and the tower according to the linear tower point cloud and the cylinder;

[0011] Whether the operator is safe is determined based on the comparison result between the target distance and the preset safety threshold.

[0012] In some embodiments, the step of training a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model includes:

[0013] Extracting a tower point cloud from the laser point cloud of the target point cloud data set;

[0014] Normalizing and marking the coordinate points of the pole tower point cloud to obtain a pole tower point cloud data set; wherein the pole tower point cloud data set includes pole tower data, power line and wire data, and insulator data;

[0015] A preset point cloud feature extraction network is trained based on the tower point cloud data set to obtain a trained point cloud classification model.

[0016] In some embodiments, the judging of the point cloud classification result based on the deep learning model to determine the straight tower point cloud of the tower type being a straight tower includes:

[0017] Extracting an insulator point cloud from the point cloud classification result;

[0018] Constructing a first deep learning model, and inputting the insulator point cloud into the first deep learning model to output an insulator state label;

[0019] A second deep learning model is constructed, and the insulator state and point cloud features are input into the second deep learning model to determine a straight tower point cloud of a tower type that is a straight tower.

[0020] In some embodiments, the simulation of the target distance between the ladder operator and the target wire and the tower according to the linear tower point cloud and the cylinder includes:

[0021] Extracting a cross arm point cloud from the straight tower point cloud based on a deep learning algorithm, and determining a suspension point of the soft ladder according to the cross arm point cloud;

[0022] determining a minimum distance between the suspension point and the target conductor;

[0023] Based on the minimum distance, a cylinder is used to simulate the target distance between the operator and the target conductor and the tower;

[0024] Whether the operator is safe is determined based on the comparison result between the target distance and the preset safety threshold.

[0025] In some embodiments, the simulating the target distance between the operator and the target wire and the tower through a cylinder based on the minimum distance includes:

[0026] The minimum distance is taken as the length of the ladder;

[0027] After determining the length of the flexible ladder, simulating the first shortest distance between the operator and the target wire by a cylinder;

[0028] The second shortest distance between the operator and the tower is simulated by a cylinder;

[0029] The sum of the first shortest distance and the second shortest distance is used as the target distance between the operator and the target conductor and tower.

[0030] In some embodiments, the step of acquiring a point cloud dataset of an ultra-high voltage power transmission channel and preprocessing the point cloud dataset based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud dataset includes:

[0031] Acquire a point cloud data set of an ultra-high voltage transmission channel, and resample the point cloud data set based on a preset spatial distance thinning algorithm to obtain a subset of the point cloud data set;

[0032] Point cloud registration is performed on a subset of the point cloud dataset according to an ICP algorithm to obtain a target point cloud dataset.

[0033] In some embodiments, the step of acquiring a point cloud dataset of an ultra-high voltage power transmission channel and resampling the point cloud dataset based on a preset spatial distance thinning algorithm to obtain a subset of the point cloud dataset includes:

[0034] Obtain a point cloud data set of oblique photography of an ultra-high voltage transmission channel by a drone; wherein the point density of the point cloud data set is in 50m-2las format;

[0035] Constructing an octree structure based on the data of the point cloud data set according to a preset spatial distance thinning algorithm;

[0036] The data foot points in the octree structure are resampled based on a nearest neighbor search algorithm to obtain a subset of the point cloud data set.

[0037] In addition, to achieve the above purpose, the present invention also proposes an ultra-high voltage maintenance safety distance assessment device, comprising:

[0038] A point cloud processing module, used to obtain a point cloud data set of the ultra-high voltage transmission channel, and pre-process the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set;

[0039] A model training module, used for training a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model;

[0040] A point cloud classification module, used for inputting the point cloud data to be classified into the point cloud classification model to output a point cloud classification result;

[0041] A tower judgment module, used to judge the point cloud classification result based on a deep learning model to determine the straight tower point cloud whose tower type is a straight tower;

[0042] A distance calculation module, used for simulating the target distance between the ladder operator and the target conductor and the tower according to the linear tower point cloud and the cylinder;

[0043] The safety judgment module is used to judge whether the operator is safe based on the comparison result of the target distance and the preset safety threshold.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes an ultra-high voltage maintenance safety distance assessment device, which includes: a memory, a processor, and an ultra-high voltage maintenance safety distance assessment program stored in the memory and executable on the processor, and the ultra-high voltage maintenance safety distance assessment program is configured to implement the ultra-high voltage maintenance safety distance assessment method described above.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, which stores an ultra-high voltage maintenance safety distance assessment program, and the ultra-high voltage maintenance safety distance assessment program is used to enable the processor to implement the ultra-high voltage maintenance safety distance assessment method described above when executing it.

[0046] The present invention obtains a point cloud data set of an ultra-high voltage transmission channel, pre-processes the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set; trains a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model; inputs the point cloud data to be classified into the point cloud classification model to output a point cloud classification result; judges the point cloud classification result based on a deep learning model to determine a straight tower point cloud whose tower type is a straight tower; simulates the target distance between a soft ladder operator and a target conductor and a tower based on the straight tower point cloud and a cylinder; and judges whether the operator is safe based on the comparison result of the target distance and a preset safety threshold. In the present invention, a certain point or certain points can be quickly located in a massive amount of point cloud data through a preset thinning algorithm and a registration algorithm, which is convenient for subsequent processing, and there is no need to segment and extract features from the point cloud data set. For the ultra-high voltage maintenance method based on the soft ladder method, a straight tower is selected according to the point cloud classification model, and then the operation simulation is carried out through a cylinder to make the distance calculation more accurate, thereby further improving the distance judgment accuracy, thereby improving the accuracy of safety judgment, and solving the safety hazards in the existing overhead ultra-high voltage transmission line maintenance process, and the technical problems such as the low accuracy of the existing safety assessment method and the possibility of misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1A schematic diagram of the structure of an ultra-high voltage maintenance safety distance assessment device in a hardware operating environment according to an embodiment of the present invention;

[0048] Figure 2 A schematic diagram of a process flow of an embodiment of an ultra-high voltage maintenance safety distance assessment method of the present invention;

[0049] Figure 3 A schematic diagram of an octree storage structure of an ultra-high voltage maintenance safety distance assessment method according to an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of a spherical nearest neighbor search for an ultra-high voltage maintenance safety distance assessment method according to an embodiment of the present invention;

[0051] Figure 5 A schematic diagram of point cloud classification of an ultra-high voltage maintenance safety distance assessment method according to an embodiment of the present invention;

[0052] Figure 6 A schematic diagram of a classification model training process for an ultra-high voltage maintenance safety distance assessment method according to an embodiment of the present invention;

[0053] Figure 7 A schematic diagram of an insulator according to an embodiment of the present invention involving a method for evaluating a safe distance for ultra-high voltage maintenance;

[0054] Figure 8 This is a structural block diagram of an embodiment of an ultra-high voltage maintenance safety distance assessment device of the present invention.

[0055] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0058] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0059] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of the ultra-high voltage maintenance safety distance assessment equipment in the hardware operating environment involved in the embodiment of the present invention.

[0060] like Figure 1 As shown, the ultra-high voltage maintenance safety distance assessment device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM memory) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0061] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the ultra-high voltage maintenance safety distance assessment equipment, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0062] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and an ultra-high voltage maintenance safety distance assessment program.

[0063] exist Figure 1 In the ultra-high voltage maintenance safety distance assessment device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the ultra-high voltage maintenance safety distance assessment device of the present invention can be set in the ultra-high voltage maintenance safety distance assessment device, and the ultra-high voltage maintenance safety distance assessment device calls the ultra-high voltage maintenance safety distance assessment program stored in the memory 1005 through the processor 1001, and executes the ultra-high voltage maintenance safety distance assessment method provided by the embodiment of the present invention.

[0064] The present invention provides an ultra-high voltage maintenance safety distance assessment method, device, equipment and storage medium.

[0065] The embodiment of the present invention provides a method for evaluating the safety distance of ultra-high voltage maintenance, referring to Figure 2 , Figure 2 The present invention is a flowchart of an embodiment of a method for evaluating the safety distance for ultra-high voltage maintenance.

[0066] like Figure 2 As shown, the ultra-high voltage maintenance safety distance assessment method includes:

[0067] Step S100: acquiring a point cloud data set of an ultra-high voltage transmission channel, and preprocessing the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set;

[0068] Step S200: training a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model;

[0069] Step S300: inputting the point cloud data to be classified into the point cloud classification model to output the point cloud classification result;

[0070] Step S400: judging the point cloud classification result based on the deep learning model to determine the straight tower point cloud whose tower type is a straight tower;

[0071] Step S500: simulating the target distance between the ladder operator and the target conductor and the tower according to the linear tower point cloud and the cylinder;

[0072] Step S600: judging whether the operator is safe based on the comparison result between the target distance and the preset safety threshold.

[0073] It should be noted that the executing entity in this embodiment may be an ultra-high voltage maintenance safety distance assessment device, which may be a computer device with data processing functions, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for explanation.

[0074] It should be noted that this embodiment uses the method of ultra-high voltage maintenance based on the soft ladder method as an example to illustrate. Specifically, the process of simulating an operator descending to a suitable position along a soft ladder hung on a tower and then swinging onto the conductor is used to determine the safety of the operation.

[0075] It can be understood that the core steps of the ultra-high voltage maintenance safety distance assessment method proposed in this embodiment include: Step 1: Point cloud thinning: resampling the original point cloud data to improve the point cloud processing efficiency without losing key features; Step 2: Point cloud alignment: aligning multiple segments of point cloud data according to feature points to ensure that there is no data offset; Step 3: Point cloud classification (tower body, conductor, ground wire, insulator); Step 4: Determine whether it is a straight tower or a tension tower based on the insulator shape; Step 5: Select a straight tower based on the judgment result, and extract the crossarm from the tower body; Step 6: Operation simulation.

[0076] In one embodiment, a point cloud dataset of an ultra-high voltage power transmission channel is obtained, and the point cloud dataset is preprocessed based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud dataset, including: obtaining a point cloud dataset of an ultra-high voltage power transmission channel, resampling the point cloud dataset based on a preset spatial distance thinning algorithm to obtain a subset of the point cloud dataset; performing point cloud registration on the subset of the point cloud dataset according to an ICP algorithm to obtain a target point cloud dataset. Point cloud thinning: obtaining a point cloud dataset of oblique photography of an ultra-high voltage power transmission channel by a drone, the point density of the point cloud dataset being in a 50m-2las format; constructing an octree structure based on the data of the point cloud dataset according to a preset spatial distance thinning algorithm; and resampling the data footers in the octree structure based on a nearest neighbor search algorithm to obtain a subset of the point cloud dataset.

[0077] Specifically, a point cloud dataset of oblique photography of an ultra-high voltage transmission channel by a drone is obtained. Exemplarily, the point cloud dataset is an original point cloud dataset, which can be an original point cloud dataset with a point density of 50m-2las format obtained by oblique photography of the transmission channel by a drone. The original point cloud dataset covers various types of poles and wires of different voltage levels in plateau areas and plain areas. For example, the poles include more than 1,000 towers, including dry-shaped towers, drum-shaped towers, wine glass-shaped towers, etc., and the wires include plain sections and mountain sections totaling 500km.

[0078] Specifically, the preset spatial distance thinning algorithm can also be referred to as spatial thinning. The principle of this algorithm is to quickly construct an octree structure for massive point cloud data, and combine it with the nearest search method (nearest neighbor algorithm / K nearest neighbor algorithm / KNN) to determine whether to keep or remove data foot points, thereby achieving the purpose of point cloud data thinning. It is a simple and effective point cloud thinning algorithm. The spatial thinning algorithm can sample high-density, high-redundancy point clouds at a certain interval distance, so that the thinned data foot points maintain an equal interval distance and are evenly distributed, effectively removing redundant point clouds, while also retaining the original feature points of the point cloud as much as possible. The octree structure used in spatial distance thinning is to recursively divide the three-dimensional space in a regular manner. Each node of the octree represents a volume element of a cube, and each node has 8 child nodes (such as Figure 3 As shown in Figure 1.1.1.1, the initial cube bounding box of the point cloud is continuously divided into 8 equal cube units, and this splitting process is repeated recursively for each cube. The stopping condition is that there are no more points (such as 3 points) in the cube unit or when a maximum preset condition is reached. By constructing an octree structure for point cloud data, it is beneficial to data management and processing. This structure can quickly determine the points in a specific cube unit and cube triple. For example, one or some points can be quickly located in a massive amount of point cloud data, which is convenient for subsequent processing.

[0079] In one example, the data foot points in the octree structure are resampled based on a nearest neighbor search algorithm to obtain a subset of the point cloud data set, including: determining a specified interval distance based on a nearest neighbor search algorithm; searching for the nearest neighbor points of the data points in the octree structure in sequence according to the specified interval distance; when the point cloud foot points with the specified interval distance are found, the foot points other than the point cloud foot points in the spherical area are removed to obtain a subset of the point cloud data set after the point cloud is thinned.

[0080] Specifically, after the octree is constructed, the optimal tree depth (layer) is calculated according to the specified minimum distance to speed up the neighboring search efficiency. According to the specified interval distance (radius), the nearest neighbor points of the data points are searched in turn to find the point cloud foot points at a given distance, and the remaining foot points in the spherical area are removed, so as to achieve the purpose of point cloud data thinning. Spatial thinning is to uniformly sample the point cloud according to a certain minimum spatial interval (sampling interval) to simplify the original discrete redundant point cloud into a uniformly distributed point cloud, while achieving the purpose of data thinning. It should be noted that spatial thinning does not generate new point cloud data, and the point cloud obtained after thinning is a subset of the original point cloud. In addition, spatial thinning will only selectively eliminate points within the spherical search area, and outliers that exceed the sampling interval will be retained (such as Figure 4 shown).

[0081] It can be understood that given a multidimensional space D, a vector in D is labeled as a sample point or data point. The finite set of sample points in D is called a sample set. Given a sample set E and a sample point d, the nearest neighbor of d is any sample point d′∈E that satisfies None-nearer(E, d, d′). None-nearer is defined as:

[0082] The distance metric is the Euclidean distance

[0083] In one example, a subset of the point cloud data set is aligned according to the ICP algorithm to obtain a target point cloud data set. Specifically, the ICP algorithm is essentially an optimal match of a least squares algorithm. The rotation and translation matrices are calculated by finding the closest point pair in the two point clouds, and the iteration is performed until a certain threshold accuracy is reached. Each iteration process can be divided into two steps: searching for the closest point pair of the two point clouds and solving the transformation matrix. The specific process is as follows:

[0084] 1) For point p in the source point cloud P i , both search for the point q closest to the point in the target point cloud Q j , forming a corresponding point set.

[0085] 2) Solve the rotation matrix R and translation vector T between the source point cloud P and its nearest point set according to the transformation matrix calculation method.

[0086] 3) Use the rotation and translation matrix calculated in 2) to perform a rotation transformation on the source point cloud and calculate the relative distance error between the transformed point cloud and the target point cloud:

[0087] e k =Σ(Rp i +Tq i ) 2

[0088] 4) Set the iteration stop condition, if |e k -e k+1 |<ε, stop the calculation, and the current rotation matrix R and translation vector T are the final registration parameter matrix; otherwise return to 1) and continue the iterative calculation.

[0089] It is understandable that the ICP algorithm is simple and intuitive to calculate and has good registration accuracy, and is the most widely used method in the fine registration algorithm. However, the convergence of the algorithm to the global optimum depends largely on the distance of the initial position and the quality of the corresponding relationship during the iteration process. Therefore, this embodiment can also provide other coarse registration algorithms to find accurate corresponding point pairs to ensure that the algorithm does not fall into a local minimum.

[0090] In this embodiment, the advantages of using the ICP algorithm are as follows: there is no need to segment and extract features from the point cloud set; when the initial value is good, good algorithm convergence can be obtained. However, there are also some disadvantages: when searching for corresponding points, the amount of calculation is large and the calculation speed is slow; at the same time, the algorithm has certain requirements for the initial position of the registration point cloud, and an unreasonable initial position will cause the algorithm to fall into a local optimum; when the ICP algorithm is looking for corresponding points, the model will take the point with the closest Euclidean distance between any two point clouds as the corresponding point, and this assumption will produce a certain number of erroneous corresponding points.

[0091] In one embodiment, a preset point cloud feature extraction network is trained based on the target point cloud data set to obtain a point cloud classification model, including: extracting a tower point cloud from the laser point cloud of the target point cloud data set; normalizing and marking the coordinate points of the tower point cloud to obtain a tower point cloud data set; wherein the tower point cloud data set includes tower data, power line and wire data, and insulator data; and training a preset point cloud feature extraction network based on the tower point cloud data set to obtain a trained point cloud classification model.

[0092] For example, point cloud classification is usually achieved through supervised learning methods, including traditional supervised machine learning and deep learning, which is to label each point or each group after segmentation with a certain class and give it certain semantics. Therefore, point cloud classification is also called point cloud semantic segmentation or point labeling.

[0093] Specifically, the preset point cloud feature extraction network can use PointNet. In this embodiment, PointNet realizes the classification of objects by learning the features of the global point cloud. It has a good classification effect and a fast reasoning speed for the point cloud of the power tower, and can also meet the classification requirements for the tower body, insulators, conductors, and ground wires.

[0094] For example, the workflow design is as follows: the point cloud after the laser radar scan is a continuous piece. First, the point cloud of the tower part is classified. The tower part can be extracted by manual marking, and the point cloud of the tower part is divided into 7 categories (each type of point cloud is as follows Figure 5 As shown in the figure, in this embodiment, 01 is used for pole tower, 02 is used for power line and ground line, and 03 is used for insulator. Then, the pole tower point cloud is manually labeled to construct a pole tower point cloud dataset, which includes but is not limited to the pole tower point cloud dataset, the power line and ground line point cloud dataset, and the insulator point cloud dataset. Then, PointNet is used for training to obtain a trained point cloud classification model, which can be used to classify other types of point clouds (such as Figure 6 It should be noted that the trained point cloud classification model includes but is not limited to a tower point cloud classification model, a power line and ground line point cloud classification model, and an insulator point cloud classification model.

[0095] It can be understood that the tower point cloud classification model obtained by training the tower point cloud data set is taken as an example for explanation here, and the training process of the power line and ground line point cloud and the insulator point cloud can refer to the tower point cloud embodiment.

[0096] Specifically, construct a tower point cloud dataset. First, deduct the tower from the overall point cloud and normalize the coordinate points of each tower:

[0097] Xmin(x1,…,x)

[0098]

[0099] The above is to normalize the x coordinate. Similarly, the same operation is performed on the y and z coordinates. Then the tower data is manually marked and each point is labeled as a tower point cloud dataset.

[0100] Specifically, to train PointNet, 90% of the tower point cloud dataset is divided as a training set, and the remaining 10% is used as a test set.

[0101] Specifically, component point (e.g. insulator) extraction: through spatial geometric relationship and clustering methods, tower components can be extracted separately, such as Figure 7 The figure shows the separated insulator. The ground wire point cloud is sliced ​​and layered in the vertical direction with a suitable thickness. The top layer of the ground wire point cloud slice is the ground wire point cloud, and the remaining slices are the conductor point cloud.

[0102] In one embodiment, judging the point cloud classification result based on the deep learning model to determine the straight tower point cloud whose tower type is a straight tower includes: extracting the insulator point cloud from the point cloud classification result; constructing a first deep learning model, and inputting the insulator point cloud into the first deep learning model to output the insulator state label; constructing a second deep learning model, and inputting the insulator state and point cloud features into the second deep learning model to determine the straight tower point cloud whose tower type is a straight tower. It should be noted that the point cloud classification result includes but is not limited to the tower point cloud classification result, the power line and ground line point cloud classification result, and the insulator point cloud classification result.

[0103] It can be understood that the type of pole tower is determined based on the state of the insulator: 1) Insulator state identification: The state of the insulator can be used to determine the type of the pole tower, and the state of the insulator is identified using deep learning technology. By building a deep learning model (i.e., the first deep learning model), the point cloud data (insulator point cloud obtained by the classification model) is used as input, and the label of the insulator state is output. 2) Feature extraction: Features are extracted from the point cloud data, which can be used to identify the type of pole tower. Feature extraction can use various methods, including shape descriptors, point cloud feature extraction networks (such as PointNet, PointNet++, PoinSet, etc.) or other point cloud processing technologies. 3) Pole tower type classification: A deep learning model (second deep learning model) or a machine learning model is constructed, and the insulator state and point cloud features are used as input to determine the type of pole tower. This can be a classification task, and the model should be able to identify different types of pole towers, such as straight towers, tension towers, etc. 4) Training and validation: The second deep learning model is trained using a labeled training data set, and then the validation set is used to evaluate the performance of the second deep learning model. The training and tuning of the second deep learning model may require multiple rounds of iterations. 5) Testing and Evaluation: An independent test dataset is used to evaluate the performance of the model to ensure that the model can accurately identify the tower type and take into account the insulator condition information.

[0104] Exemplarily, for the second deep learning model, training and verification are specifically:

[0105] a. Model architecture: Uses Convolutional Neural Network (CNN): 3 convolutional layers, each containing 64, 128, and 256 filters. Each convolutional layer is followed by a max pooling layer. Fully connected layer: contains 256 neurons.

[0106] b. Data preprocessing: Point cloud resizing: Limit the point cloud volume of a single object to 1,000,000 points.

[0107] c. Loss function: binary cross entropy loss.

[0108] d. Optimizer: Adam optimizer, with an initial learning rate of 0.001.

[0109] e. Batch size: Select a batch size of 64 and adjust it based on your hardware resources and dataset size.

[0110] f. Number of training epochs: The initial setting is 10 epochs, and whether more epochs are needed can be determined based on the performance of the validation set.

[0111] g. Data augmentation: Random rotation angle between [-15, 15] degrees. Random horizontal flipping.

[0112] h. Weight initialization: Use Xavier initialization.

[0113] In one embodiment, the target distance between a ladder operator and a target conductor and a pole tower is simulated based on the straight tower point cloud and the cylinder, including: extracting a cross arm point cloud from the straight tower point cloud based on a deep learning algorithm, and determining the suspension point of the ladder based on the cross arm point cloud; determining the minimum distance between the suspension point and the target conductor; simulating the target distance between the operator and the target conductor and the pole tower through a cylinder based on the minimum distance; and judging whether the operator is safe based on a comparison result between the target distance and a preset safety threshold.

[0114] It should be noted that based on the deep learning cross-arm extraction technology: in the classified tower point cloud, the straight tower point cloud is extracted. Specifically, the cross-arm point cloud is extracted based on the deep learning algorithm:

[0115] 1) Feature extraction: Extract features for classification from point cloud data. These features can include: Normal vector: used to describe the direction of surface normals to help identify the shapes of different objects. Point coordinates and color information: used to distinguish objects of different materials and colors. Point density: used to detect density changes of objects. Point histogram or histogram descriptor: used to describe local features.

[0116] 2) Training data collection: Collect labeled training data for insulators and other objects. This data includes labels of point clouds to indicate which points belong to crossarms. Usually, some data needs to be manually labeled as training sets.

[0117] 3) Point cloud classification algorithm: Select an appropriate point cloud classification algorithm, usually a deep learning model (such as convolutional neural network, CNN) or a traditional machine learning algorithm (such as support vector machine, SVM).

[0118] 4) Model training:

[0119] a. Model architecture: PointNet is used as the basic network for point cloud processing. The input layer is the (x, y, z) coordinates of each point. Multiple MLP layers (multi-layer perceptrons) are used to extract features from each point. The final fully connected layer outputs a binary value indicating whether each point belongs to the cross-arm structure.

[0120] b. Data preparation: Each point in the dataset is represented by its (x, y, z) coordinates and is accompanied by a binary label indicating whether the point is a cross-arm structure.

[0121] c. Data preprocessing: denoise, filter, and normalize the point cloud to the range of [-1, 1]. Divide the point cloud into small batches for training.

[0122] d. Loss function: Choose binary cross entropy loss since the task is binary classification.

[0123] e. Optimizer: Use Adam optimizer and the initial learning rate is set to 0.001.

[0124] f. Batch size: Set the batch size to 32, which is a common starting value and can be adjusted based on hardware resources.

[0125] g. Number of training epochs: Initially set to 10 epochs, but more epochs may be required based on validation set performance.

[0126] h. Weight initialization: Use Xavier initialization.

[0127] i. Data augmentation: Randomly rotate, translate, and scale point clouds to increase the diversity of training data.

[0128] j. Model training: Use the training set to train the model. At the end of each epoch, monitor the model performance through the validation set and adjust the learning rate or stop training early if necessary to prevent overfitting.

[0129] k. Model evaluation: Use the test set to evaluate the performance of the model, including indicators such as accuracy, precision, and recall.

[0130] l. Hyperparameter Tuning: Adjust hyperparameters such as learning rate, batch size, model complexity, etc. to optimize performance.

[0131] m. Model saving: Save the trained model for deployment in actual applications.

[0132] 5) Validation and evaluation: Validate and evaluate the trained model to ensure that it can accurately classify the crossarms in the point cloud. This may require splitting the dataset into training and test sets and using some performance metrics to evaluate the performance of the model.

[0133] 6) Classification: Apply the trained model to the actual point cloud data to classify the crossarms. The model will identify the points in the point cloud that belong to the crossarms.

[0134] 7) Post-processing: Post-process the classification results to further improve accuracy. This includes removing misclassified points or merging adjacent crossarm points to form larger objects.

[0135] 8) Visualization and Analysis: Visualize and analyze the classification results to ensure accuracy.

[0136] In one embodiment, simulating the target distance between the operator and the target conductor and the pole tower through a cylinder based on the minimum distance includes: taking the minimum distance as the length of the soft ladder; after determining the length of the soft ladder, simulating the first shortest distance between the operator and the target conductor through a cylinder; simulating the second shortest distance between the operator and the pole tower through a cylinder; and taking the sum of the first shortest distance and the second shortest distance as the target distance between the operator and the target conductor and the pole tower.

[0137] Specifically, live simulation work. Horizontal limitation: When selecting the hanging point for soft ladder work, it is required to keep a certain distance between the hanging point and the conductor or insulator. This is caused by the following reasons:

[0138] ① Risk of electric shock: The main function of insulators is to prevent the current on the power line from flowing to the ground through the supporting structure (crossarm or tower), thereby protecting the safety of personnel. If the operator is too close to the insulator, there is a risk of electric shock, especially when the insulator or the power line itself fails.

[0139] ② Arc risk: Arc is a discharge phenomenon that may occur in high-voltage systems, which can generate extremely high temperatures and energy. If workers are close to insulators, arc events may be triggered, which poses a major threat to their safety.

[0140] ③Insulator design and function: Insulators are usually carefully designed to ensure that they can effectively isolate the current on the conductor. Being too close to the insulator may damage the structure of the insulator or cause the insulator to lose its isolation function, which increases the risk of electric shock and arcing.

[0141] ④ Regulations and standards: The power industry is usually regulated by strict regulations and standards, which are designed to ensure the safety of power maintenance workers. These regulations may include clearly defining the minimum distance between workers and insulators (i.e., a preset safety threshold).

[0142] Therefore, power inspection and maintenance workers need to follow safe operating procedures to ensure that they maintain adequate distance when interacting with power lines, insulators and supporting structures to reduce the risk of electric shock and arcing. This includes using appropriate personal protective equipment and following industry best practices to ensure the safety of maintenance work.

[0143] Specifically, the length of the adaptive soft ladder. Based on the deep learning algorithm, the cross arm point cloud is extracted, and the points in the point cloud belonging to the cross arm are identified. One of the points of the cross arm can be selected as the suspension point. After the suspension point and the target wire are determined, the shortest path from the suspension point to the target wire point cloud can be automatically calculated according to the following algorithm. The specific algorithm is as follows:

[0144] Determine the coordinates of the suspension point and the wire point cloud: First, determine the coordinates of the suspension point (point A) and other points (point B1, point B2, point B3, and so on) whose distance is to be calculated.

[0145] Calculate the distance: For each point B1, B2, B3, and so on, use the Euclidean distance method to calculate the distance between them and the target point A. The distance calculation formula can be expressed as:

[0146]

[0147] Among them, (A x , A y , A z ) and (B x , B y , B z ) are the coordinates of point A and point B respectively.

[0148] Find the minimum distance: traverse all calculated distances and find the minimum distance and the corresponding point. This point is the minimum distance from the suspension point A to the wire point cloud.

[0149] Specifically, the distance from the simulated cylinder to the two types of point clouds is calculated. After determining the length of the soft ladder, use the cylinder to simulate the human body and calculate the distance to the conductor and the tower. The specific method is as follows:

[0150] To find the shortest distance from a point on the cylinder to a set of discrete points, you can use the following steps:

[0151] 1) Cylinder parameters: Get the parameters of the cylinder, including the coordinates of the center point of the bottom surface (C x , C y , C z ), radius R and height H.

[0152] 2) Point cloud data: Get point cloud data, which is a set of coordinates of a group of points. These points represent the positions of discrete points, and it is necessary to find the point with the shortest distance from these points to the cylinder.

[0153] 3) Calculate the shortest distance: For each point, perform the following steps:

[0154] a. Coordinate transformation: transform the coordinates of the point from the global coordinate system to the cylindrical coordinate system. This can be achieved by subtracting the coordinates of the center point of the cylinder from the coordinates of the point. The coordinates of the point in the cylindrical coordinate system (P x ', P y ', P z ').

[0155] b. Horizontal distance calculation: Calculate the coordinates of the horizontal projection point on the bottom surface of the cylinder (P x ', Py ', 0), where the Z coordinate is 0. The horizontal distance is equal to the two-dimensional Euclidean distance from the point to the projection point, that is,

[0156]

[0157] c. Vertical distance calculation: Calculate the vertical distance from the point to the horizontal projection point on the bottom of the cylinder. This can be achieved by calculating the Euclidean distance between the two points, that is,

[0158] H′=abs(P′ z -C′ z )

[0159] d. Calculation of the shortest distance point: The shortest distance point is the projection point of the point on the surface of the cylinder. It can be calculated by adding the horizontal distance R and the vertical distance to the coordinates of the center point of the bottom surface of the cylinder. The coordinates of the shortest distance point are (C x , C y ,0)+(R,0,H').

[0160] 4) Find the point with the minimum distance: In step 3), the shortest distance from each point to the cylinder is calculated. Finally, the point with the minimum distance is found among these calculation results. This point is the point on the cylinder closest to the point in the point cloud, and is also the point on the cylinder closest to the point cloud.

[0161] It should be noted that the above calculation of the distance between the simulated cylinder and the two types of point clouds can effectively find the point on the cylinder with the minimum distance from a group of points, no matter how these points are distributed. After obtaining the distance between the cylinder and the wire and the tower, the distance between the cylinder and the wire (the first shortest distance) and the distance between the cylinder and the tower (the second shortest distance) are combined, that is, the first shortest distance and the second shortest distance are summed to obtain the target distance. The threshold can be used to determine whether the operator is safe, that is, the comparison result between the target distance and the preset safety threshold can be used to determine whether the operator is safe.

[0162] In this embodiment, a point cloud data set of an ultra-high voltage transmission channel is obtained, and the point cloud data set is pre-processed based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set; a preset point cloud feature extraction network is trained based on the target point cloud data set to obtain a point cloud classification model; the point cloud data to be classified is input into the point cloud classification model to output a point cloud classification result; the point cloud classification result is judged based on a deep learning model to determine a straight tower point cloud whose tower type is a straight tower; the target distance between the operator of the soft ladder and the target conductor and the tower is simulated according to the straight tower point cloud and the cylinder; and whether the operator is safe is judged according to the comparison result of the target distance and the preset safety threshold. In this embodiment, a certain point or certain points can be quickly located in a massive amount of point cloud data through a preset thinning algorithm and a registration algorithm, which is convenient for subsequent processing, and there is no need to segment and extract features from the point cloud data set. Regarding the soft ladder method for ultra-high voltage maintenance, a straight tower is selected according to the point cloud classification model, and then the operation simulation is carried out through a cylinder to make the distance calculation more accurate, thereby further improving the accuracy of distance judgment, thereby improving the accuracy of safety judgment, and solving the safety hazards in the existing overhead ultra-high voltage transmission line maintenance process, and the technical problems such as the low accuracy of existing safety assessment methods and misjudgment.

[0163] In addition, an embodiment of the present invention also proposes a storage medium, on which an ultra-high voltage maintenance safety distance assessment program is stored. When the ultra-high voltage maintenance safety distance assessment program is executed by a processor, the steps of the ultra-high voltage maintenance safety distance assessment method described above are implemented.

[0164] Reference Figure 8 , Figure 8 This is a structural block diagram of an embodiment of an ultra-high voltage maintenance safety distance assessment device of the present invention.

[0165] like Figure 8 As shown, the ultra-high voltage maintenance safety distance assessment device comprises:

[0166] The point cloud processing module 10 is used to obtain a point cloud data set of the ultra-high voltage transmission channel, and pre-process the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set;

[0167] A model training module 20 is used to train a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model;

[0168] The point cloud classification module 30 is used to input the point cloud data to be classified into the point cloud classification model to output the point cloud classification result;

[0169] A tower judging module 40 is used to judge the point cloud classification result based on a deep learning model to determine a straight tower point cloud whose tower type is a straight tower;

[0170] A distance calculation module 50 is used to simulate the target distance between the ladder operator and the target wire and the tower according to the linear tower point cloud and the cylinder;

[0171] The safety judgment module 60 is used to judge whether the operator is safe according to the comparison result between the target distance and the preset safety threshold.

[0172] The present embodiment proposes an ultra-high voltage maintenance safety distance assessment device, including: a point cloud processing module 10, used to obtain a point cloud data set of an ultra-high voltage transmission channel, and pre-process the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set; a model training module 20, used to train a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model; a point cloud classification module 30, used to input the point cloud data to be classified into the point cloud classification model to output a point cloud classification result; a tower judgment module 40, used to judge the point cloud classification result based on a deep learning model to determine a straight tower point cloud whose tower type is a straight tower; a distance calculation module 50, used to simulate the target distance between a soft ladder operator and a target conductor and a tower according to the straight tower point cloud and a cylinder; a safety judgment module 60, used to judge whether the operator is safe according to the comparison result between the target distance and a preset safety threshold. In this embodiment, a certain point or certain points can be quickly located in a large amount of point cloud data by presetting a rarefaction algorithm and a registration algorithm, which is convenient for subsequent processing, and there is no need to segment and extract features from the point cloud data set. In the method of ultra-high voltage maintenance using the soft ladder method, a straight tower is selected according to the point cloud classification model, and then the operation simulation is performed through a cylinder to make the distance calculation more accurate, thereby further improving the distance judgment accuracy, thereby improving the accuracy of safety judgment, and solving the safety hazards in the existing overhead ultra-high voltage transmission line maintenance process, and the technical problems such as the low accuracy of the existing safety assessment method and the existence of misjudgment.

[0173] In addition, technical details that are not described in detail in the embodiment of the ultra-high voltage maintenance safety distance assessment device can be referred to the ultra-high voltage maintenance safety distance assessment method described above provided in any embodiment of the present invention, and will not be repeated here.

[0174] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0175] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0176] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0177] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0178] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0179] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for evaluating the safety distance of ultra-high voltage maintenance, characterized in that: The ultra-high voltage maintenance safety distance assessment method comprises: Acquire a point cloud data set of an ultra-high voltage transmission channel, and pre-process the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set; Training a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model; Inputting the point cloud data to be classified into the point cloud classification model to output the point cloud classification result; The point cloud classification result is judged based on the deep learning model to determine the straight tower point cloud whose tower type is a straight tower; Simulating the target distance between the ladder operator and the target conductor and the tower according to the linear tower point cloud and the cylinder; Determining whether the operator is safe based on a comparison result between the target distance and a preset safety threshold; Among them, simulating the target distance between the operator and the target wire and the pole tower on the ladder according to the straight tower point cloud and the cylinder includes: extracting the cross arm point cloud from the straight tower point cloud based on the deep learning algorithm, and determining the suspension point of the ladder according to the cross arm point cloud; determining the minimum distance between the suspension point and the target wire; simulating the target distance between the operator and the target wire and the pole tower through the cylinder based on the minimum distance; judging whether the operator is safe according to the comparison result between the target distance and the preset safety threshold; Based on the minimum distance, a target distance between an operator and the target conductor and a pole tower is simulated through a cylinder, including: taking the minimum distance as the length of a soft ladder; after determining the length of the soft ladder, simulating a first shortest distance between an operator and the target conductor through a cylinder; simulating a second shortest distance between an operator and a pole tower through a cylinder; and taking the sum of the first shortest distance and the second shortest distance as the target distance between an operator and the target conductor and a pole tower.

2. The ultra-high voltage maintenance safety distance assessment method according to claim 1, characterized in that: The step of training a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model includes: Extracting a tower point cloud from the laser point cloud of the target point cloud data set; Normalizing and marking the coordinate points of the pole tower point cloud to obtain a pole tower point cloud data set; wherein the pole tower point cloud data set includes pole tower data, power line and wire data, and insulator data; A preset point cloud feature extraction network is trained based on the tower point cloud data set to obtain a trained point cloud classification model.

3. The ultra-high voltage maintenance safety distance assessment method according to claim 1, characterized in that: The step of judging the point cloud classification result based on the deep learning model to determine the straight tower point cloud of the tower type being a straight tower includes: Extracting an insulator point cloud from the point cloud classification result; Constructing a first deep learning model, and inputting the insulator point cloud into the first deep learning model to output an insulator state label; A second deep learning model is constructed, and the insulator state and point cloud features are input into the second deep learning model to determine a straight tower point cloud of a tower type that is a straight tower.

4. The ultra-high voltage maintenance safety distance assessment method according to claim 1, characterized in that: The step of obtaining a point cloud data set of the ultra-high voltage transmission channel and preprocessing the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set includes: Acquire a point cloud data set of an ultra-high voltage transmission channel, and resample the point cloud data set based on a preset spatial distance thinning algorithm to obtain a subset of the point cloud data set; Point cloud registration is performed on a subset of the point cloud dataset according to an ICP algorithm to obtain a target point cloud dataset.

5. The ultra-high voltage maintenance safety distance assessment method according to claim 4, characterized in that: The step of acquiring a point cloud data set of the ultra-high voltage transmission channel and resampling the point cloud data set based on a preset spatial distance thinning algorithm to obtain a subset of the point cloud data set includes: Obtain a point cloud data set of oblique photography of an ultra-high voltage transmission channel by a drone; wherein the point density of the point cloud data set is in 50m-2las format; Constructing an octree structure based on the data of the point cloud data set according to a preset spatial distance thinning algorithm; The data foot points in the octree structure are resampled based on a nearest neighbor search algorithm to obtain a subset of the point cloud data set.

6. An ultra-high voltage maintenance safety distance assessment device, characterized in that: The ultra-high voltage maintenance safety distance assessment device comprises: A point cloud processing module, used to obtain a point cloud data set of the ultra-high voltage transmission channel, and pre-process the point cloud data set based on a preset thinning algorithm and a preset registration algorithm to obtain a target point cloud data set; A model training module, used for training a preset point cloud feature extraction network based on the target point cloud data set to obtain a point cloud classification model; A point cloud classification module, used for inputting the point cloud data to be classified into the point cloud classification model to output a point cloud classification result; A tower judgment module, used to judge the point cloud classification result based on a deep learning model to determine the straight tower point cloud whose tower type is a straight tower; A distance calculation module, used for simulating the target distance between the ladder operator and the target conductor and the tower according to the linear tower point cloud and the cylinder; A safety judgment module, used to judge whether the operator is safe according to the comparison result between the target distance and the preset safety threshold; Among them, simulating the target distance between the operator and the target wire and the pole tower on the ladder according to the straight tower point cloud and the cylinder includes: extracting the cross arm point cloud from the straight tower point cloud based on the deep learning algorithm, and determining the suspension point of the ladder according to the cross arm point cloud; determining the minimum distance between the suspension point and the target wire; simulating the target distance between the operator and the target wire and the pole tower through the cylinder based on the minimum distance; judging whether the operator is safe according to the comparison result between the target distance and the preset safety threshold; Based on the minimum distance, a target distance between an operator and the target conductor and a pole tower is simulated through a cylinder, including: taking the minimum distance as the length of a soft ladder; after determining the length of the soft ladder, simulating a first shortest distance between an operator and the target conductor through a cylinder; simulating a second shortest distance between an operator and a pole tower through a cylinder; and taking the sum of the first shortest distance and the second shortest distance as the target distance between an operator and the target conductor and a pole tower.

7. An ultra-high voltage maintenance safety distance assessment device, characterized in that: The ultra-high voltage maintenance safety distance assessment device includes: a memory, a processor, and an ultra-high voltage maintenance safety distance assessment program stored in the memory and executable on the processor, wherein the ultra-high voltage maintenance safety distance assessment program is configured to implement the ultra-high voltage maintenance safety distance assessment method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores an ultra-high voltage maintenance safety distance assessment program, and the ultra-high voltage maintenance safety distance assessment program is used to enable the processor to implement the ultra-high voltage maintenance safety distance assessment method as described in any one of claims 1 to 5 when executing.

Images