Transmission conductor sag measurement method and device and computer program product

Abstract

The invention discloses a power transmission conductor sag measurement method and device and a computer program product, and the method comprises the steps: S1, carrying out the cruise sampling along a power transmission line, and obtaining the laser point cloud data corresponding to a power transmission conductor in the power transmission line; s2, carrying out preprocessing operation on the laser point cloud data; s3, based on the preprocessed laser point cloud data, extracting a lead skeleton area through density field estimation and a space attention mechanism; s4, constructing a flexible catenary morphological model on the basis of the lead skeleton area and in combination with physical constraints of the power transmission lead; and S5, calculating the sag value of the transmission conductor according to the flexible catenary form model. According to the method, the stability of key point position extraction is greatly improved, and the accuracy of sag calculation in different operation states, topographic conditions and meteorological environments is further remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and device for measuring the sag of a transmission line, and a computer program product. Background Art

[0002] In recent years, with the continuous development of lidar technology, high-performance drone platforms and point cloud intelligent analysis algorithms, three-dimensional perception methods based on drones equipped with lidar have shown great application potential in the field of power inspection.

[0003] However, traditional methods for measuring transmission line sag typically rely on manual measurement, fixed-point observation with a rangefinder, and image recognition to obtain conductor posture information, which is then used to calculate conductor sag. These methods suffer from low data acquisition efficiency, limited coverage, strong environmental dependence, and insufficient three-dimensional accuracy. This is particularly problematic in real-world inspection scenarios, such as those with rugged terrain, obstructed vision, or unstable climates. This makes it difficult to accurately and continuously measure conductor sag along the entire line, resulting in unstable extraction of key point locations and a significant reduction in the accuracy of conductor sag calculations. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide a transmission line sag measurement method, device and computer program product to improve the accuracy of sag calculation under different operating conditions, terrain conditions and meteorological environments.

[0005] In order to solve the above technical problems, the present invention provides a method for measuring the sag of a transmission line, comprising:

[0006] Step S1, performing cruise sampling along the transmission line to obtain laser point cloud data corresponding to the transmission wires in the transmission line;

[0007] Step S2, performing a preprocessing operation on the laser point cloud data;

[0008] Step S3, based on the pre-processed laser point cloud data, the wire skeleton area is extracted through density field estimation and spatial attention mechanism;

[0009] Step S4: constructing a flexible catenary morphology model based on the conductor skeleton area and in combination with the physical constraints of the transmission line;

[0010] Step S5: Calculate the sag value of the transmission line according to the flexible catenary morphology model.

[0011] Preferably, the step S1 specifically includes:

[0012] A drone equipped with a lidar is controlled to cruise and sample along the three-dimensional direction of the transmission line to obtain laser point cloud data of the transmission line. The drone route is planned based on a three-dimensional geographic information model and a multi-objective path optimization algorithm, and the flight attitude and scanning angle are dynamically adjusted through real-time environmental monitoring.

[0013] Preferably, in step S2, the preprocessing operation is to perform a first preprocessing operation and a second preprocessing operation on the laser point cloud data, wherein the first preprocessing operation is used to improve the segmentation accuracy of the area corresponding to the transmission line in the laser point cloud data, and the second preprocessing operation is used to eliminate background noise and abnormal areas in the laser point cloud data.

[0014] Preferably, the first preprocessing operation on the laser point cloud data specifically includes:

[0015] Obtaining visible light images and infrared thermal images by using a dual-spectrum camera carried by the drone;

[0016] Acquire texture features in the visible light image and temperature distribution features in the infrared thermal image, and construct a texture feature vector and a temperature distribution feature vector;

[0017] Assigning the texture feature vector to the corresponding point in the laser point cloud data to obtain first enhanced point cloud data, and assigning the temperature distribution feature vector to the corresponding point in the laser point cloud data to obtain second enhanced point cloud data;

[0018] Performing feature fusion on the first enhanced point cloud data and the second enhanced point cloud data to construct a multimodal feature fusion graph;

[0019] According to the multimodal feature fusion map, the spatial recognition of the area corresponding to the transmission line is enhanced through a first preprocessing model.

[0020] Preferably, the second preprocessing operation on the laser point cloud data specifically includes:

[0021] Input the laser point cloud data into a large model based on the Transformer architecture, and use the large model in combination with the contextual attention mechanism to identify the spatial feature area corresponding to the transmission line;

[0022] Inputting the spatial feature area into a second preprocessing model, and removing background noise points and obstacle occlusion points in the laser point cloud data through the second preprocessing model;

[0023] Based on the high frequency spectrum dynamic information in the infrared thermal imaging, the abnormal area caused by the thermal airflow disturbance is eliminated through the second preprocessing model.

[0024] Preferably, the step S4 specifically includes:

[0025] Obtaining environmental parameters and material parameters corresponding to the transmission line, the environmental parameters including wind speed parameters, air temperature parameters, and solar radiation parameters, and the material parameters including wire diameter parameters, unit length mass parameters, elastic modulus parameters, and thermal expansion coefficient parameters;

[0026] Based on the wire skeleton area, and by taking the material parameters and the environmental parameters as the physical constraints, the flexible catenary morphology model is constructed.

[0027] Preferably, in step S5, the sag corresponding to the transmission line is calculated using the following formula:

[0028]

[0029] Wherein, f is the sag corresponding to the transmission line, z(x) represents the height coordinate of the transmission line at the horizontal position x, [x1, x2] is the horizontal projection coordinate range of the two suspension supports of the transmission line, z1 and z2 are the heights of the supports at both ends of the transmission line, w is the unit length weight of the transmission line, x0 is the horizontal position of the lowest point of the catenary of the transmission line, T0 is the initial horizontal tension of the transmission line, Δz T is the thermal expansion correction term, calculated from the material parameters, Δz w is the wind load correction term, which is calculated from the wind speed parameters.

[0030] The present invention also provides a transmission line sag measuring device, comprising:

[0031] An acquisition module, configured to perform cruise sampling along the transmission line to acquire laser point cloud data corresponding to the transmission conductors in the transmission line;

[0032] A processing module is configured to perform preprocessing operations on the laser point cloud data; extract a conductor skeleton region based on the preprocessed laser point cloud data through density field estimation and a spatial attention mechanism; construct a flexible catenary morphology model based on the conductor skeleton region and in combination with physical constraints of the transmission line; and calculate the sag value of the transmission line based on the flexible catenary morphology model.

[0033] The present invention also provides a transmission line sag measuring device, comprising:

[0034] one or more processors;

[0035] Memory;

[0036] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the transmission line sag measurement method.

[0037] The present invention also provides a computer program product, comprising computer instructions, wherein the computer instructions instruct a computer device to execute operations corresponding to the method.

[0038] The implementation of the present invention has the following beneficial effects: autonomous path planning and cruise sampling are carried out along the transmission line by using a drone equipped with a laser radar, and the flight attitude and scanning angle are dynamically adjusted in combination with a three-dimensional geographic information model and a multi-objective optimization algorithm to ensure the spatial uniformity and integrity of the laser point cloud data in complex terrain and multi-tower crossing environments; multi-modal feature fusion segmentation and dual preprocessing operations are used to accurately extract the conductor area and eliminate background noise and thermal disturbance anomalies, significantly improving the geometric continuity and structural purity of the point cloud data; based on density field estimation and spatial attention mechanism, a high-reliability conductor skeleton is extracted, and a flexible catenary morphology model is constructed in combination with physical parameter constraints, and the sag value is accurately calculated by integrating material properties, environmental parameters and dynamic correction terms, effectively solving the problems of unstable key point extraction and poor environmental adaptability of traditional methods, and greatly improving the accuracy and robustness of sag measurement under different terrain and meteorological conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 The present invention is a flowchart of a method for measuring the sag of a transmission line according to a first embodiment of the present invention.

[0041] Figure 2 It is a structural schematic diagram of a transmission line sag measuring device according to a second embodiment of the present invention.

[0042] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following descriptions of the embodiments refer to the accompanying drawings to illustrate specific embodiments in which the present invention may be implemented.

[0044] Please refer to Figure 1 As shown, the first embodiment of the present invention provides a method for measuring the sag of a transmission line, comprising:

[0045] Step S1, performing cruise sampling along the transmission line to obtain laser point cloud data corresponding to the transmission wires in the transmission line;

[0046] Step S2, performing a preprocessing operation on the laser point cloud data;

[0047] Step S3, based on the pre-processed laser point cloud data, the wire skeleton area is extracted through density field estimation and spatial attention mechanism;

[0048] Step S4: constructing a flexible catenary morphology model based on the conductor skeleton area and in combination with the physical constraints of the transmission line;

[0049] Step S5: Calculate the sag value of the transmission line according to the flexible catenary morphology model.

[0050] Specifically, in step S1, the UAV's flight starting point, flight direction, cruising altitude, and lateral offset distance are determined based on the transmission line's path coordinates, direction type, and terrain along the line. A multi-objective path optimization algorithm is then used to determine the optimal route, while meeting operational safety interval requirements, electromagnetic interference avoidance, and radar field of view coverage. The UAV is controlled to fly at a constant speed and equipped with a high-frequency scanning LiDAR system. This system features multi-echo capabilities and an expanded vertical field of view, enabling repeated scanning of conductors at different spatial angles to ensure the density and structural continuity of the conductor point cloud. High-precision GNSS-RTK and a six-degree-of-freedom IMU are used to collaboratively calculate the spatial coordinates and attitude information of the LiDAR point cloud in real time, and time synchronization and frame-level registration are performed to construct a precise and unified three-dimensional point cloud.

[0051] During flight, the aircraft dynamically adjusts its altitude and scanning angle based on real-time environmental monitoring information. For example, when crossing tall towers, crossing valleys, or encountering areas of electromagnetic interference, the autonomous obstacle avoidance algorithm adjusts its trajectory to keep the LiDAR within the conductor's field of view, preventing loss of the conductor point cloud due to occlusion or reflection interference. To enhance the integrity of the conductor point cloud, the drone conducts multi-angle round-trip scanning on both sides of the conductor, forming the basis for multi-perspective reconstruction. An inertia compensation algorithm also stabilizes the laser emission direction despite fluctuations in flight attitude, ensuring the accuracy and uniformity of the conductor point cloud.

[0052] In one possible implementation, step S1 includes: controlling a drone equipped with a lidar to cruise and sample along the transmission line, that is, controlling the drone through an autonomous path planning algorithm to cruise and sample along the three-dimensional direction of the transmission line while meeting safety spacing constraints and visual coverage requirements.

[0053] Specifically, the autonomous path planning algorithm is used to control the drone to cruise and sample along the three-dimensional direction of the transmission line while meeting the safety distance constraints and visual coverage requirements. Specifically, by constructing a three-dimensional geographic information model that includes the tower coordinates, the wire suspension height, and the surrounding terrain, combined with the geometric centerline and spatial distribution range of the line path, the optimal flight altitude and horizontal offset trajectory within the drone's operating area are calculated. Safety distance constraint rules are introduced during the path planning process to ensure that the drone always maintains a set minimum safety distance from the transmission lines, towers, and ground structures to avoid potential collision risks. At the same time, based on the laser radar's scanning field of view parameters, installation posture, and optimal pitch angle settings, the optimal visual coverage range of each flight segment is calculated, and the track tilt design is performed according to the structural characteristics of the wire, so that the laser beam can obtain sufficient reflection points above, below, and to the sides of the wire, thereby improving the density and continuity of the wire point cloud.

[0054] To improve path robustness and execution efficiency, an improved 3D A* algorithm or Bezier curve smoothing path planning method is used to generate a feasible trajectory that meets the aircraft's dynamic and environmental constraints. Obstacle avoidance nodes and alternative paths are preset to accommodate non-ideal factors such as sudden wind disturbances, electromagnetic interference, or field of view obstruction. One calculation method can refer to the following formula:

[0055] C total =ω d ·D(p i ,p j )+ω s ·Δθ+ω e ·E(p j )+ω c ·C clearance

[0056] Among them, C total From the current node p i Go to the next node p j The total cost function value is used to guide the path search; D(p i ,p j ) represents the Euclidean distance between nodes, reflecting the geometric length of the path; Δθ represents the heading deflection angle between nodes, which is used to control the flight smoothness and attitude change cost; ω(p j ) represents the complexity index of the target point's environment, including electromagnetic interference intensity, obstacle density or wind field change; C clearance Indicates the minimum safe distance from the current path to the nearest obstacle or wire, used to assess flight risk; ω d ,ω s ,ω e ,ω c: They are the weight coefficients of the above four items respectively, which are dynamically set according to the actual flight mission requirements to achieve comprehensive optimization of the shortest distance, high safety and stable attitude in path planning. During the flight execution, the real-time attitude and spatial positioning information of the UAV is obtained based on the fusion solution of GNSS / RTK and IMU, and the flight attitude and speed are adjusted in real time through the closed loop of the flight control system, so that the UAV always maintains a stable flight attitude according to the planned path. If an offset between the flight trajectory and the theoretical path is detected in the actual flight, the adaptive path correction module is triggered to dynamically update the flight track to ensure the quality of data collection. Finally, during the entire flight process, the lidar continuously collects three-dimensional spatial information around the wire. After covering all wire spans and suspension structures, it forms high-integrity and high-consistency original point cloud data, providing high-precision, full-coverage three-dimensional geometric input for subsequent processing processes.

[0057] Step S2 performs preprocessing operations on the laser point cloud data to segment, enhance and denoise the laser point cloud data.

[0058] Specifically, the preprocessing operation is to perform a first preprocessing operation and a second preprocessing operation on the laser point cloud data. The first preprocessing operation is used to improve the segmentation accuracy of the area corresponding to the transmission line in the laser point cloud data, and the second preprocessing operation is used to eliminate background noise and abnormal areas in the laser point cloud data.

[0059] In one possible implementation, performing a first preprocessing operation on the laser point cloud data specifically includes: acquiring a visible light image and an infrared thermal image using a dual-spectrum camera carried by a drone;

[0060] Acquire texture features in visible light images and temperature distribution features in infrared thermal imaging, and construct texture feature vectors and temperature distribution feature vectors; assign texture feature vectors to corresponding points in laser point cloud data to obtain first enhanced point cloud data, and assign temperature distribution feature vectors to corresponding points in laser point cloud data to obtain second enhanced point cloud data; perform feature fusion on the first enhanced point cloud data and the second enhanced point cloud data to construct a multimodal feature fusion graph; based on the multimodal feature fusion graph, enhance the spatial recognition of the corresponding area of the transmission line through the first preprocessing model, thereby completing the first preprocessing operation.

[0061] Specifically, texture features are image structure information extracted from visible light images. The texture feature vector is constructed based on the local directional gradient, edge response and texture consistency of the image, including grayscale change rate, directional gradient intensity, edge clarity index and texture repeatability. A multi-scale sliding window is used in combination with Gabor filter and local binary pattern analysis to construct a texture response map. Through the calibrated geometric mapping relationship between the image and the point cloud, the texture features corresponding to each pixel are accurately mapped to the spatial coordinate points of the three-dimensional point cloud to form a point-level texture feature vector. In this way, each point cloud point not only has geometric information but also carries a visual texture expression consistent with the image structure.

[0062] The temperature distribution feature is the thermal response pattern extracted from the infrared thermal imaging image. The temperature distribution feature vector is obtained by performing absolute temperature normalization, regional temperature difference calculation and time stability analysis on the infrared thermal image. It includes pixel temperature value, neighborhood temperature difference gradient, thermal field change frequency and thermal response persistence index. The time series difference method is used to construct a thermal stability zone map and eliminate transient thermal interference. The area with high stability and high temperature gradient concentration is regarded as the potential conductor area. The temperature distribution feature vector is accurately mapped to a three-dimensional space point consistent with the laser point cloud coordinates through image reprojection, thereby obtaining the second enhanced point cloud data with complete thermal distribution semantics.

[0063] To construct the multimodal feature fusion map, the first and second enhanced point cloud data are fused at the feature level, point by point. Point-level features are concatenated and normalized to form a joint vector. Each point is assigned a fused multimodal representation, while maintaining its original spatial coordinates. The fusion map incorporates not only raw radar attributes such as geometric coordinates and reflection intensity, but also features from image texture and thermal response dimensions, providing semantically rich, modally complementary information for subsequent point cloud recognition.

[0064] The first preprocessing model is a lightweight multimodal feature enhancement network. It combines a multi-scale spatial attention mechanism to perform preliminary processing on the multimodal feature fusion map, identifying high-confidence wire candidate regions in the point cloud. Guided by edge consistency and directional continuity in texture features, and supported by thermal stability and gradient significance in temperature distribution features, this model combines the original density, normal vector, and local curvature metrics of the point cloud to construct a multi-channel attention map. This creates high-responsive regions at the locations of wire structural features, thereby enhancing the spatial recognition of wire regions, suppressing features in background areas, and enhancing the foreground of the overall point cloud structure. This provides a clear and semantically explicit input foundation for the second-stage fine segmentation model.

[0065] In a possible implementation, step S2 further includes: inputting the laser point cloud data into a large model based on the Transformer architecture, and using the large model in combination with the contextual attention mechanism to identify the spatial feature area corresponding to the transmission line; inputting the spatial feature area into a second preprocessing model, and using the second preprocessing model to eliminate background noise points and obstacle occlusion points in the laser point cloud data; based on the high-frequency spectrum dynamic information in infrared thermal imaging, using the second preprocessing model to eliminate abnormal areas caused by thermal airflow disturbances, thereby completing the second preprocessing operation.

[0066] Specifically, the large model based on the Transformer architecture builds a multi-layer self-attention mechanism to model global dependencies on the input 3D point cloud data, dynamically discriminating the semantic attribution of each point based on its contextual relationship within the spatial structure. The model extracts multi-scale features from the point cloud's spatial adjacency, local geometry, fused modal features, and contextual semantics, outputting high-response regions with wire structural characteristics, known as spatial feature regions. These regions exhibit typical wire characteristics, such as linear continuity, local density consistency, and modal feature coupling.

[0067] Subsequently, the spatial feature area is input into the second preprocessing model, which is a noise and occlusion removal network built based on a graph convolution structure or a voxel clustering enhancement module. This model combines the geometric features of the point cloud with the spatial attention distribution provided by the Transformer, and comprehensively considers the point cloud density, normal mutation, boundary fluctuation and feature differences between adjacent points. Through point-level confidence judgment and cluster consistency analysis, it removes isolated points, stray points and non-structural object reflection points in the background area. At the same time, it identifies and filters out local non-conductor interference points caused by high-altitude structure occlusion such as poles and crossing objects, so that the conductor body area is clearer and more continuous in space.

[0068] Furthermore, combined with the high-frequency dynamic information in infrared thermal imaging, a point-level thermal response change map is constructed to dynamically identify point sets with abnormal temperature fluctuations, unstable thermal gradients, or background thermal disturbances within a certain time window. The second preprocessing model determines the boundaries of the thermal disturbance area based on this map, and clusters and removes abnormal points through temperature change rate, time response persistence, and surrounding thermal consistency indicators to eliminate point cloud disturbance areas caused by factors such as local airflow, sunlight reflection, or thermal wave refraction, ensuring that the complete geometric form of the real wire structure is retained. Ultimately, through this second preprocessing operation, fine purification of the wire area in the laser point cloud data is achieved, providing a high-purity, high-structural consistency point cloud foundation for subsequent skeleton extraction and morphological modeling.

[0069] In step S3, the laser point cloud data, after undergoing the first and second preprocessing operations, is first spatially gridded. The 3D point cloud is divided into voxel units based on a set resolution. The density of the points within each voxel is calculated to form a 3D density field model, which characterizes the density and connectivity trends of local structures in the point cloud. Using the density value as a preliminary saliency indicator, linear regions with a density exceeding a set threshold are spatially screened, eliminating low-density background points and initially focusing on continuous, high-density channels that may contain conductive structures. Furthermore, a spatial attention mechanism is introduced to enhance the response to regions with conductive morphological characteristics. This attention mechanism, based on the principle of self-attention in the Transformer model, utilizes the geometric similarity, density gradient consistency, texture direction correlation, and thermal response synergy between each point and its neighboring points to construct an inter-point correlation matrix and calculate the importance weight of each point relative to its neighboring points. Higher weights indicate a point's likelihood of belonging to a structurally continuous conductive region. By incorporating these weights into the density field, the response to regions with skeleton-like characteristics is enhanced while the response to non-conductive regions is suppressed. Subsequently, a multi-scale attention fusion strategy was implemented, integrating density and attention response results at different scales to extract candidate spatial skeleton regions that simultaneously meet the requirements of high density, directional continuity, thermal stability, and geometric consistency. The principal axis of the conductor trajectory was then extracted using a shortest path connectivity graph or principal direction fitting algorithm. This process also combined the directional consistency of normal vectors in the point cloud with the symmetry of the conductor's vertical projection to perform structural optimization and morphological smoothing on the candidate skeleton regions. Isolated fragments were removed and broken regions were connected. Ultimately, a conductor skeleton region with clear structure, coherent trajectory, and stable point density was obtained, providing a precise structural framework for subsequent flexibility modeling and sag calculations.

[0070] In step S4, the environmental parameters and material parameters corresponding to the transmission line are first obtained. The environmental parameters are used to characterize the influence of external natural conditions on the stress and deformation state of the line. The environmental parameters include but are not limited to wind speed parameters, temperature parameters, solar radiation parameters, etc.; the material parameters are used to describe the mechanical and thermal properties of the line body. The material parameters include but are not limited to wire diameter parameters, unit length mass parameters, elastic modulus parameters, thermal expansion coefficient parameters, etc.

[0071] Then, based on the wire skeleton area, a flexible catenary morphology model is constructed by taking material parameters and environmental parameters as physical constraints:

[0072] Based on the conductor skeleton area extracted in step S3, that is, the spatial principal axis curve of the conductor, a flexible catenary morphological model is constructed. The model takes the skeleton coordinate points as the structural basis, and uses the catenary function or its numerical approximate solution to describe the real spatial morphology of the conductor under the combined action of gravity, tension and environmental disturbances. In the modeling process, the material parameters and environmental parameters are embedded in the model structure as physical constraints, so that the model can reflect the non-ideal bending response of the conductor under wind load, thermal expansion and tension changes while fitting the direction of the skeleton. Specifically, by substituting the unit gravity distribution and the initial tension into the static equilibrium equation of the catenary model, the theoretical curve is iteratively optimized in combination with the thermal expansion correction term and the wind pressure offset term to form a dynamically adjusted flexible fitting function.

[0073] In step S5, a non-ideal catenary model under three-dimensional variable tension is constructed based on the high-precision laser point cloud data, conductor skeleton area, physical parameter constraints, and flexible modeling results obtained in steps S1 to S4. Based on this model, the actual sag value of the transmission line under the current environment and operating conditions is accurately derived:

[0074]

[0075] Where: z(x) is the height coordinate of the transmission line at the horizontal position x, T0 is the initial horizontal tension of the transmission line, w is the unit length weight of the transmission line, x0 is the horizontal position of the lowest point of the catenary, Δz T is the vertical offset compensation due to thermal expansion, Δz w is the vertical correction term due to lateral wind load.

[0076] The thermal expansion correction term Δz T It can be calculated from the change in effective length of the transmission line caused by thermal expansion effect:

[0077] ΔL T =αL0ΔT

[0078]

[0079] Where: α is the thermal expansion coefficient of the transmission line, L0 is the initial horizontal distance between the two supports, and ΔT is the temperature rise of the transmission line, which is estimated by the following radiation-convection balance:

[0080]

[0081] Where: Q solar is the solar radiation power absorbed by the transmission line per unit length, I is the line current, R is the resistance of the transmission line per unit length, h is the convection heat transfer coefficient, and A is the surface area of the transmission line.

[0082] Wind load correction term Δz wIt represents the additional sag increase caused by the lateral wind load and its expression is:

[0083]

[0084] in: is the wind load per unit length, ρ is the air density, C d is the drag coefficient of the transmission line, and v is the wind speed.

[0085] Finally, the transmission line sag value f is defined as the vertical deviation of the lowest point of the transmission line relative to the midpoint of the two support points, which can be expressed as:

[0086]

[0087] Where: z1 and z2 are the heights of the two end supports of the transmission line respectively, and [x1, x2] is the projection coordinate range of the two suspension supports of the transmission line in the horizontal direction.

[0088] The embodiment of the present invention uses a model-driven and data-driven fusion approach, combined with point cloud spatial structure continuity, conductor body feature recognition, and physical modeling parameter feedback, to accurately perceive the conductor sag along the entire line, greatly improving the stability of key point position extraction, and thus significantly improving the accuracy of sag calculation under different operating conditions, terrain conditions, and meteorological environments.

[0089] Please refer to Figure 2 As shown, the second embodiment of the present invention provides a transmission line sag measuring device, including an acquisition module 21 and a processing module 22, wherein:

[0090] An acquisition module 21 is configured to perform cruise sampling along the transmission line to acquire laser point cloud data corresponding to the transmission conductors in the transmission line;

[0091] The processing module 22 is used to perform preprocessing operations on the laser point cloud data; based on the preprocessed laser point cloud data, extract the wire skeleton area through density field estimation and spatial attention mechanism; based on the wire skeleton area and in combination with the physical constraints of the transmission line, construct a flexible catenary morphology model; and calculate the sag value of the transmission line according to the flexible catenary morphology model.

[0092] It should be noted that the devices provided in the above embodiments are only illustrated by the division of the above functional modules when implementing their functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0093] Corresponding to the transmission line sag measurement method described in the first embodiment of the present invention, the third embodiment of the present invention further provides a transmission line sag measurement device, comprising:

[0094] one or more processors;

[0095] Memory;

[0096] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the transmission line sag measurement method described in the aforementioned embodiment 1 of the present invention.

[0097] Corresponding to the transmission line sag measurement method described in the aforementioned embodiment 1 of the present invention, embodiment 4 of the present invention also provides a computer program product, including computer instructions, which instruct the computer device to perform operations corresponding to the transmission line sag measurement method described in the aforementioned embodiment 1 of the present invention.

[0098] Preferably, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor. The processor is the control center of the device, and various parts of the device are connected using various interfaces and lines.

[0099] The memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application program required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card, etc., or the memory can also be other volatile solid-state storage devices.

[0100] It should be noted that the above-mentioned device may include but is not limited to a processor and a memory, which can be understood by those skilled in the art.

[0101] like Figure 3 As shown, an embodiment of the present invention further provides an electronic device, including: at least one processor 301 , at least one communication bus 302 , a user interface 303 , at least one network interface 304 , and a memory 305 .

[0102] The communication bus 302 is used to implement the connection and communication between these components.

[0103] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0104] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0105] The processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and lines to connect various parts of the entire server. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and calling data stored in the memory 305, the processor 301 performs various server functions and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display; and the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 301 and may be implemented separately on a single chip.

[0106] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a transmission line sag measurement application based on stress analysis.

[0107] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the transmission line sag measurement application stored in the memory 305. When executed by one or more processors 301, the electronic device executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited to the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present invention.

[0108] For the working principle and process of the above embodiment, please refer to the description of the above embodiment of the present invention, which will not be repeated here.

[0109] From the above description, it can be seen that compared with the existing technology, the beneficial effects of the present invention are: autonomous path planning and cruise sampling are carried out along the transmission line by using a drone equipped with a laser radar, and the flight attitude and scanning angle are dynamically adjusted in combination with a three-dimensional geographic information model and a multi-objective optimization algorithm to ensure the spatial uniformity and integrity of the laser point cloud data in complex terrain and multi-tower crossing environments; multi-modal feature fusion segmentation and double preprocessing operations are used to accurately extract the conductor area and eliminate background noise and thermal disturbance anomalies, significantly improving the geometric continuity and structural purity of the point cloud data; based on density field estimation and spatial attention mechanism, a high-reliability conductor skeleton is extracted, and a flexible catenary morphology model is constructed in combination with physical parameter constraints. The sag value is accurately calculated by integrating material properties, environmental parameters and dynamic correction terms, effectively solving the problems of unstable key point extraction and poor environmental adaptability of traditional methods, and greatly improving the accuracy and robustness of sag measurement under different terrain and meteorological conditions.

[0110] The above disclosure is merely a preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for measuring sag of a transmission line, characterized in that: include: Step S1, performing cruise sampling along the transmission line to obtain laser point cloud data corresponding to the transmission wires in the transmission line; Step S2, performing a preprocessing operation on the laser point cloud data; Step S3, based on the pre-processed laser point cloud data, the wire skeleton area is extracted through density field estimation and spatial attention mechanism; Step S4: constructing a flexible catenary morphology model based on the conductor skeleton area and in combination with the physical constraints of the transmission line; Step S5: Calculate the sag value of the transmission line according to the flexible catenary morphology model.

2. The method according to claim 1, characterized in that The step S1 specifically includes: A drone equipped with a lidar is controlled to cruise and sample along the three-dimensional direction of the transmission line to obtain laser point cloud data of the transmission line. The drone route is planned based on a three-dimensional geographic information model and a multi-objective path optimization algorithm, and the flight attitude and scanning angle are dynamically adjusted through real-time environmental monitoring.

3. The method according to claim 1, characterized in that In step S2, the preprocessing operation is to perform a first preprocessing operation and a second preprocessing operation on the laser point cloud data, wherein the first preprocessing operation is used to improve the segmentation accuracy of the area corresponding to the transmission line in the laser point cloud data, and the second preprocessing operation is used to eliminate background noise and abnormal areas in the laser point cloud data.

4. The method according to claim 3, characterized in that The first preprocessing operation on the laser point cloud data specifically includes: Obtaining visible light images and infrared thermal images by using a dual-spectrum camera carried by the drone; Acquire texture features in the visible light image and temperature distribution features in the infrared thermal image, and construct a texture feature vector and a temperature distribution feature vector; Assigning the texture feature vector to the corresponding point in the laser point cloud data to obtain first enhanced point cloud data, and assigning the temperature distribution feature vector to the corresponding point in the laser point cloud data to obtain second enhanced point cloud data; Performing feature fusion on the first enhanced point cloud data and the second enhanced point cloud data to construct a multimodal feature fusion graph; According to the multimodal feature fusion map, the spatial recognition of the area corresponding to the transmission line is enhanced through a first preprocessing model.

5. The method according to claim 4, characterized in that The second preprocessing operation on the laser point cloud data specifically includes: Input the laser point cloud data into a large model based on the Transformer architecture, and use the large model in combination with the contextual attention mechanism to identify the spatial feature area corresponding to the transmission line; Inputting the spatial feature area into a second preprocessing model, and removing background noise points and obstacle occlusion points in the laser point cloud data through the second preprocessing model; Based on the high frequency spectrum dynamic information in the infrared thermal imaging, the abnormal area caused by the thermal airflow disturbance is eliminated through the second preprocessing model.

6. The method according to claim 1, characterized in that The step S4 specifically includes: Obtaining environmental parameters and material parameters corresponding to the transmission line, the environmental parameters including wind speed parameters, air temperature parameters, and solar radiation parameters, and the material parameters including wire diameter parameters, unit length mass parameters, elastic modulus parameters, and thermal expansion coefficient parameters; Based on the wire skeleton area, and by taking the material parameters and the environmental parameters as the physical constraints, the flexible catenary morphology model is constructed.

7. The method according to claim 6, characterized in that In step S5, the sag corresponding to the transmission line is calculated using the following formula: Wherein, f is the sag corresponding to the transmission line, z(x) represents the height coordinate of the transmission line at the horizontal position x, [x1, x2] is the horizontal projection coordinate range of the two suspension supports of the transmission line, z1 and z2 are the heights of the supports at both ends of the transmission line, w is the unit length weight of the transmission line, x0 is the horizontal position of the lowest point of the catenary of the transmission line, T0 is the initial horizontal tension of the transmission line, Δz T is the thermal expansion correction term, calculated from the material parameters, Δz w is the wind load correction term, which is calculated based on the wind speed parameters.

8. A transmission line sag measuring device, characterized in that: include: An acquisition module, configured to perform cruise sampling along the transmission line to acquire laser point cloud data corresponding to the transmission conductors in the transmission line; A processing module, used for performing pre-processing operations on the laser point cloud data; Based on the preprocessed laser point cloud data, the conductor skeleton area is extracted through density field estimation and spatial attention mechanism. Based on the conductor skeleton area and combined with the physical constraints of the transmission line, a flexible catenary morphology model is constructed. The sag value of the transmission line is calculated according to the flexible catenary morphology model.

9. A transmission line sag measuring device, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the transmission line sag measurement method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions instruct a computer device to perform operations corresponding to the method according to any one of claims 1 to 7.

Images