Power transmission line project acceptance method, system and device based on unmanned aerial vehicle

Abstract

The invention relates to a power transmission line project acceptance method, system and device based on an unmanned aerial vehicle, and relates to the technical field of power transmission lines. The method comprises the following steps: acquiring measurement task data for acceptance of a power transmission line, and determining target obstacle characteristics, target electromagnetic interference source position characteristics and target meteorological change characteristics of the power transmission line based on the measurement task data; determining flight control data of the unmanned aerial vehicle through a trained deviation value prediction model of the measurement result of the unmanned aerial vehicle based on the three characteristics; transmitting the flight control data to the unmanned aerial vehicle to control the flight state and the data acquisition state of the unmanned aerial vehicle; receiving flight path information returned by the unmanned aerial vehicle and a measurement result for the to-be-measured data, transmitting the flight path information and the measurement result to a visual terminal, and displaying an acceptance result of the power transmission line project in a map of the visual terminal; deviation in the measurement task execution process of the unmanned aerial vehicle for power transmission line acceptance is reduced, and the measurement accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission lines, and in particular to a method, system and device for power transmission line project acceptance based on drones. Background Art

[0002] The acceptance of transmission line projects is a key task for comprehensive and detailed inspection of the results of transmission line construction. The acceptance work comprehensively uses a variety of technologies and professional means, involving various components of the transmission line, from tower foundation to conductor erection, from insulator performance to lightning protection and grounding. The acceptance of transmission line projects involves the measurement of vertical span, sag, distance from the tension tower line to the tower body, tree barriers in the transmission channel, cross-overs, distances to buildings, etc. Traditional methods usually require manual climbing of poles or use of telescopes for observation and calculation on the ground. At present, most of them use drone laser point cloud technology instead of traditional methods. For example, when measuring vertical span, laser scanning is used to obtain point cloud data of transmission lines and towers. After data processing, the three-dimensional coordinates of the lowest point of the conductor between adjacent towers are identified, and then the vertical distance between the two points is calculated.

[0003] The accuracy of laser point cloud data used to assist engineering acceptance using drone laser point cloud technology is easily affected by environmental factors. For example, under some special weather conditions, the propagation of lasers will be hindered, causing noise, blur or reduced accuracy in the collected data. On the other hand, when drones are collecting data, the laser radar may have scanning blind spots. For obscured transmission line parts, such as wires obscured by dense branches or buildings, it is difficult to obtain complete point cloud data, resulting in missing data and inaccurate measurements. Summary of the invention

[0004] Based on this, it is necessary to provide a UAV-based transmission line project acceptance method, system, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of UAV-based detection of constructed transmission lines in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a transmission line project acceptance method based on a drone, comprising:

[0006] Acquire measurement task data for the acceptance of the transmission line, and determine the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and preset data to be measured;

[0007] Based on the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics, the flight control data of the UAV is determined by using a trained deviation value prediction model of the UAV measurement results;

[0008] Transmitting the flight control data to the UAV to control the flight state and data collection state of the UAV;

[0009] Receive the flight path information sent back by the UAV and the measurement results for the data to be measured, and transmit the flight path information and the measurement results to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the UAV.

[0010] In one embodiment, the method further comprises:

[0011] Acquire historical obstacle characteristics, historical electromagnetic interference source location characteristics, and historical meteorological change characteristics associated with the transmission line;

[0012] After preprocessing, the historical obstacle characteristics, the historical electromagnetic interference source location characteristics and the historical meteorological change characteristics are input into a pre-built neural network model for training to obtain the deviation values ​​of the measurement results of the UAV in different environments; the deviation values ​​are used to train the neural network model in combination with the corresponding real deviation values.

[0013] In one embodiment, it also includes:

[0014] The training process of the neural network model is evaluated and optimized based on a preset loss function and an optimization algorithm to obtain a deviation value prediction model for the trained UAV measurement results.

[0015] In one of the embodiments, the method further includes: pre-processing the historical obstacle features, the historical electromagnetic interference source location features, and the historical meteorological change features to obtain a training set;

[0016] The training process of the neural network model is evaluated and optimized based on a preset loss function and an optimization algorithm to obtain a deviation value prediction model of the trained UAV measurement result, including:

[0017] Inputting a batch of data in the training set into the pre-built neural network model, and obtaining a deviation value of the predicted UAV measurement result by calculating a process from the input layer of the neural network model through the hidden layer to the output layer; the training set includes multiple batches of data;

[0018] Calculating a loss value using the loss function according to the predicted deviation value and the actual deviation value; and calculating the gradient of the loss function for each weight and bias based on the chain rule;

[0019] According to the calculated gradient, the weight and the bias are updated using the optimization algorithm to obtain a trained neural network model, and the trained neural network model is used as the deviation value prediction model for the UAV measurement result.

[0020] In one of the embodiments, the preset data to be measured includes measurement type, measurement parameters and measurement time;

[0021] The flight control data of the UAV includes a target flight path of the UAV;

[0022] The method further comprises:

[0023] Constructing a genetic algorithm mathematical model based on the measurement type, the measurement parameters, the measurement time, the line design data and the environmental data;

[0024] For the preset initial path and fitness function of the UAV, a selection operation, a crossover operation and a mutation operation are performed to obtain a first candidate path corresponding to the initial path;

[0025] Based on the particle swarm optimization algorithm, the speed and position of the first candidate path are updated to obtain a second candidate path corresponding to the first candidate path;

[0026] The first candidate path and the second candidate path corresponding to the initial path are obtained by alternate iteration until the maximum value of the preset number of the alternate iterations is reached, so as to output the second candidate path obtained by the last iteration as the target flight path of the UAV.

[0027] In one of the embodiments, the fitness function is determined based on indicator data for measuring flight path safety, measurement coverage factor data, indicator data related to energy consumption, and weight coefficients corresponding to the three.

[0028] In one embodiment, determining the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data includes:

[0029] Based on the measurement task data, determining at least one of peak information, mountain range information, tree information, building information, communication tower information, and utility pole information of the transmission line as a target obstacle feature;

[0030] Based on the measurement task data, determine at least one of the electromagnetic interference source positioning information, interference source transmission power information, interference source operating frequency information, and interference source modulation mode information of the transmission line as the target electromagnetic interference source position feature;

[0031] Based on the measurement task data, at least one of the temperature parameters, humidity parameters, air pressure parameters, wind speed parameters, severe weather warning information, and information on the degree of impact of different meteorological conditions on flight performance, communication systems, and measurement equipment of the transmission line is determined as the target meteorological change characteristics.

[0032] In a second aspect, the present application provides a transmission line project acceptance system based on a drone, the system comprising a visualization terminal, an acceptance terminal and a drone; the acceptance terminal is respectively connected to the visualization terminal and the drone for communication;

[0033] The acceptance terminal is used to obtain measurement task data for the acceptance of the transmission line, and determine the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and pre-set data to be measured; based on the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics, the flight control data of the UAV is determined through the deviation value prediction model of the trained UAV measurement results; the flight control data is transmitted to the UAV to control the flight state and data collection state of the UAV; the flight path information transmitted back by the UAV and the measurement results for the data to be measured are received, and the flight path information and the measurement results are transmitted to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the UAV.

[0034] In a third aspect, the present application also provides a transmission line project acceptance device based on a drone, comprising:

[0035] A data acquisition module is used to acquire measurement task data for the acceptance of a transmission line, and determine target obstacle characteristics, target electromagnetic interference source location characteristics, and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data, and preset data to be measured;

[0036] A flight control data determination module, used to determine the flight control data of the UAV based on the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics through a trained deviation value prediction model of the UAV measurement results;

[0037] A data acquisition module, used to transmit the flight control data to the UAV to control the flight state and data acquisition state of the UAV;

[0038] The result output module is used to receive the flight path information transmitted back by the UAV and the measurement results of the data to be measured, and transmit the flight path information and the measurement results to the visualization terminal to display the acceptance results of the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the UAV.

[0039] In a fourth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the first aspect when executing the computer program.

[0040] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in the first aspect when executed by a processor.

[0041] In a sixth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps in the first aspect when executed by a processor.

[0042] The present application provides a transmission line project acceptance method, system, device, computer equipment, computer-readable storage medium and computer program product based on drones, wherein the transmission line project acceptance method based on drones obtains measurement task data for transmission line acceptance, and determines the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and pre-set data to be measured; based on the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics, the flight control data of the drone is determined through a deviation value prediction model of the trained drone measurement results; the flight control data is transmitted to the drone to control the flight state and data collection state of the drone; the flight path information transmitted back by the drone and the measurement results for the data to be measured are received, and the flight path information and the measurement results are transmitted to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the drone. This application is based on the measurement task data of the power transmission line acceptance. Through the deviation value prediction model of the trained UAV measurement results, the flight control data of the UAV is determined, which is conducive to reducing the deviation of the UAV in the process of performing the measurement task of the power transmission line acceptance, thereby providing an effective data basis for the UAV measurement and improving the accuracy of the measurement under the influence of multiple factors. At the same time, the UAV flight path planned based on various factors can ensure that the UAV can effectively avoid obstacles, electromagnetic interference sources and other unfavorable factors when performing the measurement task, and fly along the optimal route in a complex environment, ultimately greatly improving the accuracy and efficiency of the measurement, so as to facilitate the high-quality completion of the entire measurement task. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 FIG. 1 is an application environment diagram of a power transmission line project acceptance method based on a drone in one embodiment;

[0045] Figure 2 A schematic diagram of a flow chart of a transmission line project acceptance method based on a drone in one embodiment;

[0046] Figure 3 A schematic diagram of a transmission line project acceptance system based on a drone in one embodiment;

[0047] Figure 4 A schematic diagram of a flow chart of a power transmission line project acceptance method based on a drone in another embodiment;

[0048] Figure 5 A schematic diagram of a process for determining an optimal flight path for a drone in one embodiment;

[0049] Figure 6 A schematic diagram of a process for determining an optimal flight path for a drone in another embodiment;

[0050] Figure 7 It is a structural block diagram of a transmission line project acceptance device based on a drone in one embodiment;

[0051] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] The transmission line project acceptance method based on drone provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the visualization terminal 101 and the acceptance terminal 102 are communicatively connected, and the acceptance terminal 102 and the drone 103 are communicatively connected. Both the visualization terminal 101 and the acceptance terminal 102 can communicate with the server through the network. Among them, the visualization terminal 101 and the acceptance terminal 102 can be but not limited to various personal computers, laptops, smart phones, tablet computers, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. Furthermore, the acceptance terminal 102 can have a server with a corresponding communication connection, that is, an acceptance terminal server, and the acceptance terminal server can also replace Figure 1 The function of the acceptance terminal 102 is to realize the processing of the data interacting with the visualization terminal 101 and the drone 103 respectively.

[0054] In an exemplary embodiment, Figure 2 As shown in the figure, a transmission line project acceptance method based on drone is provided. Figure 1 Taking the acceptance terminal server corresponding to the acceptance terminal 102 in the example as an example, the method includes the following steps 201 to 204. Among them:

[0055] Step 201, obtaining measurement task data for transmission line acceptance, and determining target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and preset data to be measured.

[0056] Among them, the acceptance of transmission line projects may include, for example, measurement tasks such as vertical span, sag, distance from the tension tower line to the tower body, tree barriers in the transmission channel, crossovers, and distance from buildings.

[0057] The target obstacle features may include natural obstacles and artificial obstacles; natural obstacles include, for example, peaks, mountains, and trees, and artificial obstacles include, for example, buildings, communication towers, and utility poles.

[0058] The target electromagnetic interference source location characteristics may include electromagnetic interference source positioning and interference source parameters, wherein the interference source parameters include transmission power, operating frequency, modulation mode, etc.

[0059] The target meteorological change characteristics may include the changing trends of parameters such as temperature, humidity, air pressure, wind speed, etc., and may further include severe weather warnings and the impact of different meteorological conditions on flight performance, communication systems, measurement equipment, etc.

[0060] The line design data may be the design data of the transmission line to be inspected before construction. The environmental data may be evaluated and set by the inspection personnel according to the actual conditions of the measurement site. The preset data to be measured may also be evaluated and set by the inspection personnel according to the actual conditions of the measurement site.

[0061] Exemplarily, the line design data, environmental data and pre-set data to be measured for the transmission line acceptance project can be obtained first, and then, based on the acquired data, the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics corresponding to the transmission line can be determined.

[0062] Step 202, based on the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target weather change characteristics, the flight control data of the UAV is determined through the deviation value prediction model of the trained UAV measurement results.

[0063] Among them, the trained deviation value prediction model of the drone measurement results is a deviation value prediction model of the drone measurement results that has been trained in advance, and can be trained before the execution of step 201 in the drone-based transmission line project acceptance method provided in the present application.

[0064] For example, the determined target obstacle features, target electromagnetic interference source location features, and target meteorological change features can be input into the deviation value prediction model of the UAV measurement results that has been trained in advance, and the deviation value of the predicted UAV measurement results can be obtained through the forward propagation calculation of the deviation value prediction model. Based on this deviation value, the measurement results of the UAV can be corrected or used as a basis for evaluating the reliability of the measurement, which is conducive to improving the accuracy of the actual flight control data determined for the UAV.

[0065] Step 203, the flight control data is transmitted to the UAV to control the flight state and data collection state of the UAV.

[0066] The flight status of the UAV may include the flight speed, flight altitude, flight pitch angle, flight roll angle, flight yaw angle, and specific flight path of the UAV.

[0067] The data acquisition status includes, for example, image acquisition or video acquisition for a measurement target, and may further include data acquisition time, data acquisition direction, etc. for a measurement target.

[0068] For example, after determining the flight control data that can control the UAV to collect data on targets in the power transmission line, the flight control data can be transmitted to the UAV to control the specific flight state and data collection state of the UAV.

[0069] Step 204, receiving the flight path information sent back by the drone and the measurement results for the data to be measured, and transmitting the flight path information and the measurement results to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the drone.

[0070] Among them, the flight path information transmitted back by the drone is the actual flight path information during the entire process of measuring the measurement target of the transmission line; for example, it may include the actual flight speed, actual flight altitude, actual flight pitch angle, actual flight roll angle, actual flight yaw angle, and actual flight path of the drone.

[0071] The measurement result at least includes the collected image data or video data associated with the measurement target; it may further include the location information of the measurement target, etc.

[0072] Exemplarily, the acceptance terminal server will also receive the flight path information sent back by the drone, as well as the measurement results for the data to be measured, and then transmit the acquired information to the visualization terminal connected to the communication, so that the visualization terminal can present the complex and abstract measurement data in the form of intuitive graphics, images, maps, etc. For example, a detailed report will be generated for the results of the measurement task planning, and the report will list the start and end time, flight path coordinate points, measurement equipment parameters and other information of each measurement task in a table. The results of the measurement task planning are visualized through a graphical interface. The flight path, obstacles, electromagnetic interference sources, measurement targets and other information of the drone are displayed on the map to intuitively present the planning scheme.

[0073] Furthermore, operators can view planning details through the visual interface of the visual terminal and make necessary adjustments and optimizations.

[0074] It should be noted that this application uses the application of the drone-based transmission line project acceptance method to the acceptance terminal server corresponding to the acceptance terminal 102 as an example. This is only an optional implementation method provided by this application. When the acceptance terminal 102 has good computing power, the drone-based transmission line project acceptance method provided by this application can also be applied to the acceptance terminal 102.

[0075] The above-mentioned UAV-based transmission line project acceptance method provided in the present application obtains measurement task data for transmission line acceptance, and determines the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and pre-set data to be measured; based on the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics, the flight control data of the UAV is determined through the trained deviation value prediction model of the UAV measurement results; the flight control data is transmitted to the UAV to control the flight status and data collection status of the UAV; the flight path information transmitted back by the UAV and the measurement results for the data to be measured are received, and the flight path information and measurement results are transmitted to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results include at least the flight path, obstacles, electromagnetic interference sources and measurement targets of the UAV. This application is based on the measurement task data of the power transmission line acceptance. Through the deviation value prediction model of the trained UAV measurement results, the flight control data of the UAV is determined, which is conducive to reducing the deviation of the UAV in the process of performing the measurement task of the power transmission line acceptance, thereby providing an effective data basis for the UAV measurement and improving the accuracy of the measurement under the influence of multiple factors. At the same time, the UAV flight path planned based on various factors can ensure that the UAV can effectively avoid obstacles, electromagnetic interference sources and other unfavorable factors when performing the measurement task, and fly along the optimal route in a complex environment, ultimately greatly improving the accuracy and efficiency of the measurement, so as to facilitate the high-quality completion of the entire measurement task.

[0076] In an exemplary embodiment, the UAV-based transmission line project acceptance method provided in the present application further includes a training process of a deviation value prediction model of the UAV measurement results, and the training process can be completed in the preparation stage, for example, before the execution of step 201 of the UAV-based transmission line project acceptance method provided in the present application. The relevant training process may include, for example, steps 211 and 212, wherein:

[0077] Step 211, obtaining historical obstacle characteristics, historical electromagnetic interference source location characteristics and historical meteorological change characteristics associated with the transmission line;

[0078] Step 212, after preprocessing the historical obstacle characteristics, historical electromagnetic interference source location characteristics and historical meteorological change characteristics, input them into the pre-built neural network model for training to obtain the deviation values ​​of the measurement results of the UAV in different environments; the deviation values ​​are used to train the neural network model in combination with the corresponding real deviation values ​​(the relevant content is explained in the postscript).

[0079] Exemplarily, the historical obstacle features may include natural obstacles and artificial obstacles; natural obstacles include, for example, peaks, mountains and trees, and artificial obstacles include, for example, buildings, communication towers and telephone poles. The historical electromagnetic interference source location features may include electromagnetic interference source positioning and interference source parameters, wherein the interference source parameters include transmission power, operating frequency, modulation mode, etc. The historical meteorological change features may include the change trends of parameters such as temperature, humidity, air pressure, wind speed, etc., and may further include severe weather warnings and the impact of different meteorological conditions on flight performance, communication systems, measurement equipment, etc.

[0080] One implementation method provided by the present application is to obtain historical obstacle characteristics of historical transmission lines, historical electromagnetic interference source location characteristics and historical meteorological change characteristics, and then train a neural network model to be trained based on at least these three historical characteristics to obtain deviation values ​​of measurement results of the drone in different environments output by the neural network model to be trained.

[0081] In an exemplary embodiment, the training process of the deviation value prediction model of the drone measurement results provided in the present application also includes: evaluating and optimizing the training process of the neural network model based on a preset loss function and optimization algorithm to obtain a trained deviation value prediction model of the drone measurement results.

[0082] Exemplarily, after obtaining the deviation values ​​of the measurement results of the UAV in different environments output by the neural network model to be trained, the training process of the neural network model can be further evaluated and optimized through a preset loss function and optimization algorithm to improve the accuracy of the neural network model in processing data. When the optimized neural network model meets the training completion conditions, the training of the neural network model is terminated, and the trained neural network model is used as a deviation value prediction model for the trained UAV measurement results.

[0083] The trained deviation value prediction model of the UAV measurement results can be used to output the deviation value for adjusting the UAV's flight control data when receiving the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics.

[0084] In an exemplary embodiment, the training process of the deviation value prediction model of the drone measurement results provided in the present application also includes: preprocessing historical obstacle characteristics, historical electromagnetic interference source location characteristics and historical meteorological change characteristics to obtain a training set; further, a verification set and a test set can also be obtained at the same time.

[0085] The above-mentioned evaluation and optimization process of the training process of the neural network model based on the preset loss function and optimization algorithm to obtain the deviation value prediction model of the trained drone measurement results can be implemented by executing the following steps, including:

[0086] Input a batch of data in the training set into the pre-built neural network model, and obtain the deviation value of the predicted UAV measurement result by calculating the process from the input layer of the neural network model through the hidden layer to the output layer; the training set includes multiple batches of data;

[0087] The loss function is used to calculate the loss value based on the predicted deviation value and the actual deviation value; and the gradient of the loss function for each weight and bias is calculated based on the chain rule;

[0088] According to the calculated gradient, the optimization algorithm is used to update the weights and biases to obtain a trained neural network model, and the trained neural network model is used as a deviation value prediction model for the UAV measurement results.

[0089] Exemplarily, after preprocessing historical obstacle features, historical electromagnetic interference source location features, and historical meteorological change features, the resulting training set may include multiple batches of data, and each time the data is input into a pre-built (to be trained) neural network model, it may be a batch of data; that is, all the data in the training set does not need to be input into the pre-built neural network model at once.

[0090] Therefore, a batch of data in the training set can be selected to be input into the pre-built neural network model, and the deviation value of the predicted UAV measurement result can be obtained by calculating the process from the input layer through the hidden layer to the output layer of the neural network model; then the deviation value of the predicted UAV measurement result and the actual deviation value of the corresponding batch data in history are obtained, and the loss value is calculated for the predicted deviation value and the actual deviation value using a preset loss function, and the gradient of the loss function for each weight and bias is further calculated based on the chain rule; then, based on the calculated gradient, the preset optimization algorithm can be called to update the weights and biases, thereby obtaining a trained neural network model.

[0091] In an exemplary embodiment, the preset data to be measured includes measurement type, measurement parameters and measurement time; and the flight control data of the UAV includes the target flight path of the UAV.

[0092] The transmission line project acceptance method based on drone provided in this application may further include:

[0093] The genetic algorithm mathematical model is constructed based on the measurement type, measurement parameters, measurement time, route design data and environmental data; the selection operation, crossover operation and mutation operation are performed for the preset initial path and fitness function of the UAV to obtain the first candidate path corresponding to the initial path; the speed and position of the first candidate path are updated based on the particle swarm optimization algorithm to obtain the second candidate path corresponding to the first candidate path; the first candidate path and the second candidate path corresponding to the initial path are obtained by alternating iteration until the maximum value of the preset number of alternating iterations is reached, and the second candidate path obtained by the last iteration is output as the target flight path of the UAV. Among them, the fitness function is determined based on the indicator data for measuring the safety of the flight path, the measurement coverage factor data, the indicator data related to energy consumption, and the weight coefficients corresponding to the three.

[0094] For example, the flight environment can be abstracted into a mathematical model for algorithm processing. A two-dimensional or three-dimensional grid can be used to represent the environment. Each grid cell represents a location or area. The measurement type, measurement parameters, measurement time, line-related information, and environment-related information are marked in the grid. A cost is assigned to each grid cell to reflect the difficulty of passing through the cell. For example, the grid cell where the obstacle is located can be set to a high cost, the area with strong electromagnetic interference also has a high cost, and the area with open, safe and good weather conditions has a low cost.

[0095] Here, a data structure of a sequence of coordinate points is used to represent the flight path of the drone, and each coordinate point represents the position of the drone at a certain location. Each flight path is encoded as a chromosome, which can be a one-dimensional array, where each gene represents a node or action instruction in the path.

[0096] Furthermore, the initial path and fitness function are set, and selection, crossover and mutation operations are performed according to the set initial path and fitness function to obtain a new path; specifically, the population size can be adjusted according to the complexity of the problem and computing resources, generally between dozens and hundreds of chromosomes. For each chromosome (path) in the initial population, the fitness value is calculated. Here, the fitness function is an indicator to measure the quality of the path, which takes into account factors such as the path security, measurement coverage, and energy consumption.

[0097] The selection operation is to select excellent chromosomes from the current population according to the fitness value for breeding the next generation. The crossover operator performs a crossover operation on the selected chromosomes to generate new chromosomes. The mutation operator performs a mutation operation on the newly generated chromosomes to increase the diversity of the population.

[0098] Then, the particle swarm optimization algorithm is used to update the speed and position of the new path to obtain the updated path, and the fitness value is calculated based on the updated path; for each particle in the particle swarm optimization algorithm, it is updated according to its speed and position update formula.

[0099] For the updated particle (path), recalculate its fitness value. If the new fitness value is better than the particle's historical optimal fitness value, update the particle's historical optimal position; if the new fitness value is better than the group's global optimal fitness value, update the group's global optimal position.

[0100] When the number of iterations reaches the maximum, the optimal path for the UAV to fly is output. That is, the genetic algorithm operation and the particle swarm optimization algorithm operation are performed alternately for multiple iterations. In each iteration, the genetic algorithm selection, crossover and mutation operations are first performed to generate a new chromosome population; then the particle swarm optimization algorithm speed and position update operations are performed to optimize the position (path) of the particles. When the stopping condition is met, the algorithm stops running and outputs the global optimal position of the group, that is, the optimal flight path.

[0101] In an exemplary embodiment, the determination of target obstacle characteristics, target electromagnetic interference source location characteristics, and target meteorological change characteristics of the transmission line based on the measurement task data in step 201 may be achieved by executing the following steps, including:

[0102] Based on the measurement task data, at least one of peak information, mountain information, tree information, building information, communication tower information and utility pole information of the transmission line is determined as a target obstacle feature;

[0103] Based on the measurement task data, determine at least one of the electromagnetic interference source location information, interference source transmission power information, interference source operating frequency information, and interference source modulation mode information of the transmission line as the target electromagnetic interference source location feature;

[0104] Based on the measurement mission data, determine at least one of the temperature parameters, humidity parameters, air pressure parameters, wind speed parameters, severe weather warning information of the transmission line, and the degree of impact of different meteorological conditions on flight performance, communication systems, and measurement equipment as the target meteorological change characteristics.

[0105] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0106] Based on the same inventive concept, the embodiment of the present application also provides a transmission line project acceptance system based on a drone, such as Figure 1 As shown, the system includes a visualization terminal 101, an acceptance terminal 102 and a drone 103; the acceptance terminal 102 is communicatively connected with the visualization terminal 101 and the drone 103 respectively.

[0107] The visualization terminal 101 and the acceptance terminal 102 may be, but are not limited to, various personal computers, laptop computers, smart phones, tablet computers, etc. Further, the acceptance terminal 102 may have a corresponding communication connection server, that is, an acceptance terminal server, which may also replace Figure 1 The function of the acceptance terminal 102 is to process the data interacted with the visualization terminal 101 and the drone 103. The acceptance terminal server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0108] Among them, the acceptance terminal 102 or the acceptance terminal server is used to obtain measurement task data for the acceptance of the transmission line, and determine the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and pre-set data to be measured; based on the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics, the flight control data of the drone is determined through the deviation value prediction model of the trained drone measurement results; the flight control data is transmitted to the drone to control the flight status and data collection status of the drone; the flight path information sent back by the drone and the measurement results for the data to be measured are received, and the flight path information and measurement results are transmitted to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the drone.

[0109] For the transmission line project acceptance system based on drones provided in this application, this application also provides an optional implementation method, in which the visualization terminal can choose to use a mobile terminal, such as a mobile phone, tablet computer, notebook and other portable mobile devices; the acceptance terminal can, for example, choose to use an acceptance terminal server to process and further transmit the received data. By directly using the acceptance terminal server, the processing capability of the received data can be improved compared to using the acceptance terminal; the drone specifically used to implement the relevant acceptance function can be the drone control terminal. That is, if Figure 3 As shown, the UAV-based power transmission line project acceptance system may include a mobile terminal 1, an acceptance terminal server 2 and a UAV control terminal 3, and the acceptance terminal server 2 is communicatively connected to the mobile terminal 1 and the UAV control terminal 3 respectively.

[0110] For the mobile terminal 1, the acceptance terminal server 2 and the drone control terminal 3 included in the acceptance system, optional implementation modes are provided respectively, wherein:

[0111] The mobile terminal 1 includes a measurement task request module 11 and a measurement result visualization module 12; the measurement task request module 11 is used to send the key information of the measurement task set by the user to the acceptance terminal server, and the measurement result visualization module 12 is used to visualize the measurement results fed back by the acceptance terminal server.

[0112] The acceptance terminal server 2 includes an event analysis and processing module 21, a measurement task planning module 22, a task progress update module 23 and a measurement result feedback module 24; the event analysis and processing module 21 is used to analyze and process the key information in the received measurement task request, the measurement task planning module 22 is used to set the UAV flight parameters, set the measurement target and plan the UAV flight path, the task progress update module 23 is used to update the progress of the UAV flight in real time, and the measurement result feedback module 24 is used to correct the measurement results sent by the UAV control terminal 3 and feed them back to the mobile terminal 1.

[0113] The drone control terminal 3 includes a data acquisition communication module 31 and a flight control module 32; the data acquisition communication module 31 is used to collect the captured video image data and send the data to the acceptance terminal server 2, and the flight control module 32 is used to control the flight altitude, flight speed and flight attitude of the drone.

[0114] In an exemplary embodiment, the measurement task request module 11 is used to send the key information of the measurement task set by the user to the acceptance terminal server 2, including:

[0115] Obtain key information of the measurement task set by the user; the key information of the measurement task includes measurement type, measurement parameters, measurement time, line related information and environment related information;

[0116] The key information of the measurement task is sent to the acceptance terminal server 2 based on the preset communication protocol.

[0117] Exemplarily, the acceptance personnel first set some key information of the measurement tasks of the acceptance work through the mobile terminal 1. The measurement types here include, for example, vertical span measurement, sag measurement, distance measurement from the tension tower line to the tower body, transmission channel tree barrier measurement, cross-over measurement, building distance measurement, etc. The measurement type can be set according to the actual measurement requirements of the acceptance personnel. The measurement parameters and measurement time are set according to the measurement type, which are also set by the acceptance personnel. The line-related information and environment-related information are evaluated and set by the acceptance personnel based on the actual situation of the measurement site. After the acceptance personnel fill in the information, the mobile terminal 1 sends the information to the acceptance terminal server 2 after encapsulating and encrypting the information and establishing a network connection with the acceptance terminal server 2.

[0118] Furthermore, the measurement result feedback module 24 corrects the measurement result sent by the drone control terminal 3 and feeds it back to the mobile terminal 1, so that the mobile terminal 1 can present complex and abstract measurement data in the form of intuitive graphics, images, maps, etc. through the measurement result visualization module 12. For example, a detailed report is generated for the results of the measurement task planning, and the start and end time, flight path coordinate points, measurement equipment parameters and other information of each measurement task are listed in the report in a table. The results of the measurement task planning are visualized through a graphical interface. For example, it can be displayed as displaying the flight path, obstacles, electromagnetic interference sources, measurement targets and other information of the drone on the map, and the planning scheme is intuitively presented. The operator can view the planning details through the visualization interface and make necessary adjustments and optimizations.

[0119] Furthermore, the mission progress update module 23 can be used to update the progress of the UAV flight, for example, it may include updating the UAV flight position, flight mission phase progress, measurement mission progress, and equipment status progress related to the flight mission; wherein the UAV flight position includes geographic coordinates and relative position, the flight mission phase progress includes take-off and landing phase, and cruising phase, the measurement mission progress includes data collection and data transmission, and the equipment status progress related to the flight mission includes power consumption accuracy and equipment working status progress.

[0120] In an exemplary embodiment, the data acquisition communication module 31 in the drone control terminal 3 provided by the present application may be integrated with advanced image sensors and video acquisition equipment to capture high-resolution, high-quality video images. During the acquisition process, acquisition parameters such as resolution, frame rate, exposure time, etc. are automatically adjusted according to different measurement tasks and environmental conditions to ensure that the acquired data not only meets the measurement accuracy requirements, but also can adapt to various complex environments.

[0121] Furthermore, the data acquisition communication module 31 can be configured to support a variety of wireless communication technologies, such as Wi-Fi, Bluetooth, 4G / 5G, etc. Among them, the data acquisition communication module 31 can be configured to automatically select the best communication method according to the actual situation to ensure that the data can be quickly and stably transmitted to the acceptance terminal server. During the data transmission process, the module can further encrypt and authenticate the data to ensure the security and confidentiality of the data.

[0122] In an exemplary embodiment, the flight control module 32 in the drone control terminal 3 provided in the present application can be used to control the flight altitude of the drone, including adjusting the ascent or descent speed of the drone to ensure that the drone remains stably within a specified flight altitude range; controlling the flight speed of the drone, including receiving data from airspeed sensors, GPS (Global Positioning System) and other devices to determine the current flight speed of the drone; controlling the flight attitude includes using sensors such as gyroscopes and accelerometers to monitor the attitude information of the drone, including pitch angle, roll angle and yaw angle.

[0123] The UAV-based transmission line project acceptance system provided in the above embodiment can realize efficient operation of the whole process from task initiation, planning to execution and acceptance through close cooperation between the mobile terminal 1, the acceptance terminal server 2 and the UAV control terminal 3; it is conducive to improving the efficiency and accuracy of the acceptance work, reducing manual intervention and errors, and providing strong technical support for various measurement and acceptance tasks.

[0124] like Figure 4 As shown, the event analysis and processing module 21 in the acceptance terminal server 2 in the present application is used to analyze and process the key information in the received measurement task request, and may optionally include the following steps S21-S26, wherein:

[0125] S21, determining target obstacle characteristics and target electromagnetic interference source location characteristics based on line-related information, and determining target meteorological change characteristics based on environment-related information.

[0126] Exemplarily, by obtaining the layout diagram of the transmission line, including the direction of the line, the location distribution of the towers, etc., combined with the Geographic Information System (GIS) data, the geographical environment in which the transmission line is located can be clarified. According to the voltage level, conductor type, tower height and other specification information of the transmission line; the obstacles encountered in the previous construction and maintenance process are determined through the construction and maintenance records of the line. The target obstacle characteristics include natural obstacles and artificial obstacles; among which, natural obstacles include, for example, peaks, mountains and trees, and artificial obstacles include, for example, buildings, communication towers and electric poles. The target electromagnetic interference source location characteristics include electromagnetic interference source positioning and interference source parameters, among which the interference source parameters include transmission power, operating frequency, modulation mode, etc. The target meteorological change characteristics include the change trends of parameters such as temperature, humidity, air pressure, wind speed, etc., and can further include severe weather warnings and the impact of different meteorological conditions on flight performance, communication systems, measurement equipment, etc.

[0127] S22, respectively collecting historical obstacle feature data corresponding to the measurement type, measurement parameters and measurement time, historical electromagnetic interference source location feature data, historical meteorological change feature data and historical UAV measurement result deviation value data.

[0128] Exemplarily, information about obstacles is obtained in a variety of ways; for example, for buildings in urban environments, geographic information system data can be used to obtain information such as the location, height, and area of ​​the buildings; for obstacles such as trees and mountains in natural environments, satellite image analysis can be used in combination with field surveys to obtain their location, density, and other characteristics. For determining the location of the electromagnetic interference source, the coordinate position of interference sources such as communication base stations, high-voltage wires, and radar facilities can be identified by electromagnetic spectrum monitoring equipment, and parameters such as their transmission power and frequency range can be measured at the same time. These parameters can be selected to be combined into a vector form to represent the characteristics of the electromagnetic interference source. Data such as temperature, humidity, wind speed, and air pressure are collected from meteorological stations or meteorological sensors installed on drones, and the data collection time is recorded at the same time to capture the dynamic changes in the weather. By comparing with a high-precision reference measurement method, the deviation value of the measurement results of the drone in different environments is obtained. For example, in a measurement, the distance value measured by the drone is d1, and the accurate distance value measured on the ground is d2, then the deviation value is d1-d2.

[0129] S23, preprocessing the collected data, including data cleaning, data normalization and data segmentation.

[0130] Exemplarily, the data preprocessing here includes at least data cleaning, data normalization and data segmentation. Data cleaning is used to remove outliers and erroneous data in the data; data normalization is used to normalize input feature data of different ranges to the same range; data segmentation is used to divide the data set into training set, validation set and test set according to a certain ratio.

[0131] S24, the preprocessed data (training set) is used as an input sample and input into the constructed deep neural network model for training, and the number of input layer neurons, the number of hidden layers and the number of neurons in each hidden layer are determined according to the historical obstacle characteristics, the historical electromagnetic interference source location characteristics and the historical meteorological change characteristics. The deep neural network model includes an input layer, a hidden layer and an output layer.

[0132] Exemplarily, the input layer: the number of input layer neurons is determined according to the number of input features. Assume that obstacle features are represented by 5 neurons, such as obstacle density in different directions, maximum obstacle height, etc.; electromagnetic interference source location features are represented by 3 neurons, such as the x, y coordinates and power of the interference source; meteorological change features are represented by 4 neurons, such as temperature, humidity, wind speed, and air pressure; then the number of input layer neurons is 5+3+4=12.

[0133] Hidden layers: Choose the number of hidden layers and the number of neurons in each hidden layer based on the complexity of the problem. You can start with a simple structure, such as setting 2 to 3 hidden layers, with the number of neurons in each hidden layer gradually decreasing.

[0134] Output layer: The output layer has only one neuron, which is used to output the deviation value of the drone's measurement results.

[0135] The weights and biases of the neural network are randomly initialized based on the network structure determined above.

[0136] S25, selecting a loss function and an optimization algorithm to evaluate and optimize the training process, and obtaining a deviation value prediction model for the trained UAV measurement results.

[0137] For example, the loss function: ; Where: is the mean square error, is the sum of the squares of all samples.

[0138] Exemplarily, the optimization algorithm: ; Where: is the learning rate, For the current Parameters, and is the training sample.

[0139] Input a batch of data from the training set into the neural network, and obtain the predicted deviation value by calculating the process from the input layer through the hidden layer to the output layer; calculate the loss using the above loss function based on the predicted value and the true deviation value; use the chain rule to calculate the gradient of the loss function for each weight and bias; and use the above optimization algorithm to update the weights and biases based on the calculated gradient.

[0140] S26, inputting the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics into the trained prediction model to obtain the prediction deviation value of the UAV measurement result.

[0141] Exemplarily, the above-determined target obstacle features, target electromagnetic interference source location features, and target meteorological change features are finally processed according to the above-mentioned preprocessing method during training, and then input into the trained model. Through the forward propagation calculation of the model, the deviation value of the predicted UAV measurement result is obtained. According to this deviation value, the measurement result of the UAV can be corrected or used as a basis for evaluating the reliability of the measurement. The preprocessing method during training at least includes the above-mentioned data cleaning, data normalization, and data segmentation.

[0142] See also Figure 5 The measurement task planning module 22 in the transmission line project acceptance system based on drones of the present application is used to set drone flight parameters, set measurement targets and plan drone flight paths, and may optionally include the following steps S31-S33, wherein:

[0143] S31, determining the measurement range and measurement accuracy of the UAV according to the measurement type, measurement parameters, measurement time, target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics.

[0144] For example, the measurement range is to clearly define the spatial range of the measurement target. If it is a linear target, such as a power transmission line, the starting and ending points of the line and the area it passes through must be determined; for regional targets, such as mapping a forest, the boundary range of the forest must be clearly defined. The measurement accuracy is based on the accuracy of the measurement requirements.

[0145] S32, determining the measurement target type, task sequencing and time allocation according to the measurement type, measurement parameters and measurement time respectively.

[0146] Exemplarily, task sorting includes measurement task priority sorting, and sorting considering environmental and resource factors. Multiple measurement tasks can be prioritized, and the priority can be determined by considering factors such as the urgency and importance of the task. Tasks can also be sorted in combination with factors such as weather conditions, availability of drones and measurement equipment, etc.

[0147] Time allocation includes allocating flight time, data collection time, reserved emergency time and equipment maintenance time. Flight time depends on the length of the flight path and the flight speed of the drone; data collection time is related to factors such as the collection frequency of the measurement equipment and the number of measurement points. Reserved emergency time can deal with emergencies such as equipment failure and sudden weather changes. Routine maintenance time for equipment includes regular inspections, software updates, etc. to ensure that the equipment is always in good working condition.

[0148] S33, determining the optimal flight path of the UAV according to the measurement type, measurement parameters, measurement time, target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics.

[0149] See also Figure 6 For step S33, the optimal path of the UAV flight is determined according to the measurement type, measurement parameters, measurement time, target obstacle characteristics, target electromagnetic interference source location characteristics and target weather change characteristics, which can be achieved by executing steps S331 to S334, wherein:

[0150] S331, constructing a genetic algorithm mathematical model according to the measurement type, measurement parameters, measurement time, line-related information, and environment-related information, and determining the data structure of the mathematical model.

[0151] Exemplarily, a two-dimensional or three-dimensional grid represents the environment, each grid cell represents a location or area, and the measurement type, measurement parameters, measurement time, line-related information, and environment-related information are marked in the grid. A cost is assigned to each grid cell, reflecting the difficulty of passing through the cell. For example, the grid cell where the obstacle is located can be set to a high cost, the area with strong electromagnetic interference also has a high cost, and the area with open, safe and good weather conditions has a low cost.

[0152] Here, we can choose to use a data structure of a sequence of coordinate points to represent the flight path of the drone, where each coordinate point represents the specific location information of the drone at a certain location. Each flight path is encoded as a chromosome, which can be a one-dimensional array, where each gene represents a node or action instruction in the path.

[0153] S332, setting an initial path and a fitness function, and performing a selection operation, a crossover operation, and a mutation operation according to the set initial path and the fitness function to obtain a new path.

[0154] For example, the population size can be adjusted according to the complexity of the problem and the computing resources, and is generally between dozens and hundreds of chromosomes. For each chromosome (path) in the initial population, the fitness value is calculated. Here, the fitness function is an indicator to measure the quality of the path, which takes into account factors such as the safety of the path, measurement coverage, and energy consumption.

[0155] Among them, the fitness function can be: ; Where: is the fitness value, , and are weight coefficients, As an indicator to measure the safety of flight paths, To measure the coverage factor, An indicator related to energy consumption.

[0156] The selection operation is to select excellent chromosomes from the current population according to the fitness value for breeding the next generation. The crossover operator performs a crossover operation on the selected chromosomes to generate new chromosomes. The mutation operator performs a mutation operation on the newly generated chromosomes to increase the diversity of the population.

[0157] S333, using a particle swarm optimization algorithm to update the speed and position of the new path to obtain an updated path, and calculating a fitness value based on the updated path;

[0158] For each particle in the particle swarm optimization algorithm, update it according to its velocity and position update formula. Among them: ; ; Where: For path The velocity vector, is the inertia weight, and is the learning factor, and is a random number, For path The optimal position vector of For path The current position vector of is the global optimal position vector of the group, For path The updated position vector of .

[0159] For the updated particle (path), recalculate its fitness value. If the new fitness value is better than the particle's historical optimal fitness value, update the particle's historical optimal position; if the new fitness value is better than the group's global optimal fitness value, update the group's global optimal position.

[0160] S334, when the number of iterations reaches the maximum number, the optimal flight path of the UAV is output.

[0161] Exemplarily, genetic algorithm operations and particle swarm optimization algorithm operations are performed alternately for multiple iterations. In each iteration, the genetic algorithm selection, crossover and mutation operations are first performed to generate a new chromosome population; then the particle swarm optimization algorithm speed and position update operations are performed to optimize the position (path) of the particles. When the stop condition is met, the algorithm stops running and outputs the global optimal position of the population, that is, the optimal flight path.

[0162] The above embodiment utilizes a hybrid algorithm of a genetic algorithm and a particle swarm optimization algorithm to effectively plan a safe and efficient flight path for the UAV that meets the measurement requirements.

[0163] Based on the same inventive concept, the embodiment of the present application also provides a transmission line project acceptance device based on drones for implementing the above-mentioned transmission line project acceptance method based on drones. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the transmission line project acceptance device based on drones provided below can refer to the limitations of the transmission line project acceptance method based on drones above, and will not be repeated here.

[0164] In an exemplary embodiment, Figure 7 As shown, a transmission line project acceptance device 700 based on a UAV is provided, comprising: a data acquisition module 71, a flight control data determination module 72, a data acquisition module 73 and a result output module 74, wherein:

[0165] The data acquisition module 71 is used to acquire measurement task data for the acceptance of the transmission line, and determine the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and preset data to be measured;

[0166] A flight control data determination module 72, for determining the flight control data of the UAV based on target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics through a trained deviation value prediction model of the UAV measurement results;

[0167] The data acquisition module 73 is used to transmit the flight control data to the UAV to control the flight state and data acquisition state of the UAV;

[0168] The result output module 74 is used to receive the flight path information sent back by the drone, as well as the measurement results for the data to be measured, and transmit the flight path information and the measurement results to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the drone.

[0169] In an exemplary embodiment, the data acquisition module 71 is also used to obtain historical obstacle characteristics, historical electromagnetic interference source location characteristics and historical meteorological change characteristics associated with the transmission line; the UAV-based transmission line engineering acceptance device 700 also includes a model training module, which is used to pre-process the historical obstacle characteristics, historical electromagnetic interference source location characteristics and historical meteorological change characteristics, and input them into a pre-built neural network model for training to obtain the deviation value of the measurement results of the UAV in different environments; the deviation value is used to train the neural network model in combination with the corresponding real deviation value.

[0170] In an exemplary embodiment, the model training module is also used to evaluate and optimize the training process of the neural network model based on a preset loss function and optimization algorithm to obtain a deviation value prediction model for the trained drone measurement results.

[0171] In an exemplary embodiment, the model training module is also used to pre-process historical obstacle features, historical electromagnetic interference source location features and historical meteorological change features to obtain a training set; evaluate and optimize the training process of the neural network model based on a preset loss function and optimization algorithm to obtain a deviation value prediction model for the trained UAV measurement results, including: inputting a batch of data in the training set into a pre-built neural network model, and obtaining the predicted deviation value of the UAV measurement results by calculating the process from the input layer of the neural network model through the hidden layer to the output layer; the training set includes multiple batches of data; according to the predicted deviation value and the actual deviation value, the loss value is calculated using the loss function; and the gradient of the loss function for each weight and bias is calculated based on the chain rule; according to the calculated gradient, the weights and biases are updated using the optimization algorithm to obtain the trained neural network model, and the trained neural network model is used as the deviation value prediction model for the UAV measurement results.

[0172] In an exemplary embodiment, the preset data to be measured include measurement type, measurement parameters and measurement time; the flight control data of the UAV include the target flight path of the UAV; the flight control data determination module 72 is also used to construct a genetic algorithm mathematical model based on the measurement type, measurement parameters, measurement time, line design data and environmental data; for the preset initial path and fitness function of the UAV, selection operations, crossover operations and mutation operations are performed to obtain a first candidate path corresponding to the initial path; based on the particle swarm optimization algorithm, the speed and position of the first candidate path are updated to obtain a second candidate path corresponding to the first candidate path; the first candidate path and the second candidate path corresponding to the initial path are obtained by alternating iterations until the maximum value of the preset number of alternating iterations is reached, so as to output the second candidate path obtained in the last iteration as the target flight path of the UAV.

[0173] In an exemplary embodiment, the fitness function is determined based on index data for measuring flight path safety, measurement coverage factor data, index data related to energy consumption, and weight coefficients corresponding to the three.

[0174] In an exemplary embodiment, the data acquisition module 71 is used to determine the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data, and is specifically used to determine at least one of the peak information, mountain range information, tree information, building information, communication tower information and telephone pole information of the transmission line as the target obstacle characteristics based on the measurement task data; determine at least one of the electromagnetic interference source positioning information, interference source transmission power information, interference source operating frequency information and interference source modulation mode information of the transmission line as the target electromagnetic interference source location characteristics based on the measurement task data; determine at least one of the temperature parameters, humidity parameters, air pressure parameters, wind speed parameters, severe weather warning information of the transmission line, and the degree of influence of different meteorological conditions on flight performance, communication systems and measurement equipment as the target meteorological change characteristics based on the measurement task data.

[0175] Each module in the above-mentioned UAV-based power transmission line project acceptance device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0176] In an exemplary embodiment, a computer device is provided. The computer device may be a server, such as an acceptance terminal server. The internal structure diagram thereof may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store measurement task data, flight control data, etc. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a transmission line engineering acceptance method based on an unmanned aerial vehicle is implemented.

[0177] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0178] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, any step in the UAV-based transmission line project acceptance method is implemented.

[0179] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any step in the transmission line project acceptance method based on a drone is implemented.

[0180] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements any step in a transmission line project acceptance method based on a drone.

[0181] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0182] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0183] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0184] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A transmission line project acceptance method based on drones, characterized in that: The method comprises: Acquire measurement task data for the acceptance of the transmission line, and determine the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data and preset data to be measured; Based on the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics, the flight control data of the UAV is determined by using a trained deviation value prediction model of the UAV measurement results; Transmitting the flight control data to the UAV to control the flight state and data collection state of the UAV; Receive the flight path information sent back by the UAV and the measurement results for the data to be measured, and transmit the flight path information and the measurement results to the visualization terminal to display the acceptance results for the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the UAV.

2. The method according to claim 1, characterized in that The method further comprises: Acquire historical obstacle characteristics, historical electromagnetic interference source location characteristics, and historical meteorological change characteristics associated with the transmission line; After preprocessing, the historical obstacle characteristics, the historical electromagnetic interference source location characteristics and the historical meteorological change characteristics are input into a pre-built neural network model for training to obtain the deviation values ​​of the measurement results of the UAV in different environments; the deviation values ​​are used to train the neural network model in combination with the corresponding real deviation values.

3. The method according to claim 2, characterized in that Also includes: The training process of the neural network model is evaluated and optimized based on a preset loss function and an optimization algorithm to obtain a deviation value prediction model for the trained UAV measurement results.

4. The method according to claim 3, characterized in that Also includes: After preprocessing the historical obstacle features, the historical electromagnetic interference source location features, and the historical meteorological change features, a training set is obtained; The training process of the neural network model is evaluated and optimized based on a preset loss function and an optimization algorithm to obtain a deviation value prediction model of the trained UAV measurement result, including: Inputting a batch of data in the training set into the pre-built neural network model, and obtaining a deviation value of the predicted UAV measurement result by calculating a process from the input layer of the neural network model through the hidden layer to the output layer; the training set includes multiple batches of data; Calculating a loss value using the loss function according to the predicted deviation value and the actual deviation value; and calculating the gradient of the loss function for each weight and bias based on the chain rule; According to the calculated gradient, the weight and the bias are updated using the optimization algorithm to obtain a trained neural network model, and the trained neural network model is used as the deviation value prediction model for the UAV measurement result.

5. The method according to claim 1, characterized in that The preset data to be measured include measurement type, measurement parameters and measurement time; The flight control data of the UAV includes a target flight path of the UAV; The method further comprises: Constructing a genetic algorithm mathematical model based on the measurement type, the measurement parameters, the measurement time, the line design data and the environmental data; For the preset initial path and fitness function of the UAV, a selection operation, a crossover operation and a mutation operation are performed to obtain a first candidate path corresponding to the initial path; Based on the particle swarm optimization algorithm, the speed and position of the first candidate path are updated to obtain a second candidate path corresponding to the first candidate path; The first candidate path and the second candidate path corresponding to the initial path are obtained by alternate iteration until the maximum value of the preset number of the alternate iterations is reached, so as to output the second candidate path obtained by the last iteration as the target flight path of the UAV.

6. The method according to claim 5, characterized in that The fitness function is determined based on index data for measuring flight path safety, measurement coverage factor data, index data related to energy consumption, and weight coefficients corresponding to the three.

7. The method according to claim 1, characterized in that The determining of target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data includes: Based on the measurement task data, determining at least one of peak information, mountain range information, tree information, building information, communication tower information, and utility pole information of the transmission line as a target obstacle feature; Based on the measurement task data, determine at least one of the electromagnetic interference source positioning information, interference source transmission power information, interference source operating frequency information, and interference source modulation mode information of the transmission line as the target electromagnetic interference source position feature; Based on the measurement task data, at least one of the temperature parameters, humidity parameters, air pressure parameters, wind speed parameters, severe weather warning information, and information on the degree of impact of different meteorological conditions on flight performance, communication systems, and measurement equipment of the transmission line is determined as the target meteorological change characteristics.

8. A transmission line project acceptance system based on drones, characterized in that: The system includes a visualization terminal, an acceptance terminal and a drone; the acceptance terminal is respectively connected to the visualization terminal and the drone for communication; The acceptance terminal is used to obtain measurement task data for the acceptance of the transmission line, and determine the target obstacle characteristics, target electromagnetic interference source location characteristics and target meteorological change characteristics of the transmission line based on the measurement task data; The measurement task data includes line design data, environmental data and preset data to be measured; based on the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics, the flight control data of the UAV is determined through the trained deviation value prediction model of the UAV measurement results; the flight control data is transmitted to the UAV to control the flight status and data collection status of the UAV; the flight path information sent back by the UAV and the measurement results for the data to be measured are received, and the flight path information and the measurement results are transmitted to the visualization terminal to display the acceptance results of the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the UAV.

9. A transmission line project acceptance device based on drones, characterized in that: The device comprises: A data acquisition module is used to acquire measurement task data for the acceptance of a transmission line, and determine target obstacle characteristics, target electromagnetic interference source location characteristics, and target meteorological change characteristics of the transmission line based on the measurement task data; the measurement task data includes line design data, environmental data, and preset data to be measured; A flight control data determination module, used to determine the flight control data of the UAV based on the target obstacle characteristics, the target electromagnetic interference source location characteristics and the target meteorological change characteristics through a trained deviation value prediction model of the UAV measurement results; A data acquisition module, used to transmit the flight control data to the UAV to control the flight state and data acquisition state of the UAV; The result output module is used to receive the flight path information transmitted back by the UAV and the measurement results of the data to be measured, and transmit the flight path information and the measurement results to the visualization terminal to display the acceptance results of the transmission line project in the map of the visualization terminal; wherein the acceptance results at least include the flight path, obstacles, electromagnetic interference sources and measurement targets of the UAV.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images