Method and device for determining position of unmanned aerial vehicle and electronic equipment

Abstract

The invention discloses a method and device for determining the position of an unmanned aerial vehicle and electronic equipment. The method relates to the field of artificial intelligence or other related fields, and comprises the following steps: obtaining first position information of N pieces of power equipment, and determining M pieces of second position information of M pieces of unmanned aerial vehicle equipment according to the N pieces of first position information; acquiring equipment parameters of each unmanned aerial vehicle equipment, and constructing an unmanned aerial vehicle energy consumption model according to the second position information and the equipment parameters of the unmanned aerial vehicle equipment; constructing a distance matrix according to the N pieces of first position information and the M pieces of second position information, and constructing a first objective function according to the distance matrix and the M unmanned aerial vehicle energy consumption models; and performing optimization processing on the first target function by using a genetic algorithm to obtain a second target function, and determining target position information of the M unmanned aerial vehicle devices based on function parameters in the second target function. Through the method and the device, the problems of low detection efficiency and high detection cost when the unmanned aerial vehicle equipment is used for detecting the power equipment in related technologies are solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence or other related fields, and specifically, to a method, device and electronic device for determining the position of a drone. Background Art

[0002] With the continuous advancement of science and technology, drone technology is increasingly being used in various fields, especially in the fields of electric power, energy, and agriculture, showing great potential. Drones have the advantages of high flexibility, low cost, rapid deployment, and high safety, making them play an important role in the inspection of power equipment and agricultural monitoring. However, in complex scenarios, how to safely and efficiently implement tasks such as monitoring of power transmission and distribution equipment and emergency response to disasters is an urgent problem to be solved.

[0003] For example, as the scale of power grid transmission equipment is getting larger and larger, its position in the energy supply security system is becoming increasingly important. With global climate change, natural disasters are frequent in coastal areas. When disasters strike, the operating conditions of the power grid or equipment will deteriorate, which will lead to electrical accidents and huge losses of life and property. When a disaster occurs, timely understanding of the disaster situation is of great significance for the deployment of disaster emergency response measures. Therefore, it is essential to monitor power equipment and facilities regularly. Compared with technical solutions such as manual field surveys and satellite image analysis, the application of drone disaster survey is an efficient and low-cost solution. Drone inspection is more efficient than manual inspection, with lower operating costs and higher data quality. However, due to the limitations of drone battery capacity and communication distance, the drone's endurance and flight distance are limited. The efficiency of a single drone disaster survey is relatively low, and the timeliness cannot meet the application requirements. At this time, multiple different drones can be set up to achieve rapid survey of the disaster area. However, how to reasonably arrange multiple drones to achieve optimal coverage of the disaster area by multi-machine collaboration is an important problem that needs to be solved.

[0004] At present, there is no mature automated solution for route planning for multi-UAV collaborative operations in the industry. It is necessary to manually allocate survey areas for multiple UAVs to achieve coverage of the overall survey area. When applying manual route planning, if it is necessary to comprehensively consider the selection of UAV take-off and landing points, flight capability differences, and coverage area allocation, it is highly dependent on manual experience and generally cannot maximize the use of resources. To achieve automated multi-UAV collaborative coverage deployment, three methods can be used in related technologies: the site selection method based on geographic information system, the site selection method based on the superior and inferior solution distance method, and the optimal set coverage method. First, the site selection method based on geographic information system can intuitively present the terrain and landform environment around the surface coverage area through computers. Undoubtedly, this requires a lot of data support. The sophistication and quality of the data directly determine the quality of the site selection results. Although this method is more scientific, the large amount of data required requires professional instruments and professional technical engineers to collect, monitor and analyze, and the cost is difficult to reduce; at the same time, the above method does not consider external conditions other than data in the site selection process, which will produce a considerable deviation from the actual optimal site selection result; the superior and inferior solution distance method is a commonly used analysis method. Its main idea is to measure the quality of the decision result by calculating the similarity between the optimal solution and the worst solution of the decision plan. Although this method is simple, it is relatively cumbersome and requires high standardization. Optimal set coverage is a classic method. In this scenario, it uses the minimum number of drones under the premise of meeting the coverage area. This method will have different strategy models in different scenarios, but this method makes the entire monitoring process inefficient and affects the timeliness of the survey. That is, the above method does not take into account the impact of the drone and the sensors it carries and the surrounding terrain conditions on the inspection task, and it is difficult to use efficiently in actual scenarios.

[0005] With regard to the problems of low detection efficiency and high detection cost when using drone equipment to detect power equipment in related technologies, no effective solution has been proposed so far. Summary of the invention

[0006] The main purpose of this application is to provide a method, device and electronic device for determining the position of a drone, so as to solve the problems of low detection efficiency and high detection cost when using drone equipment to detect power equipment in related technologies.

[0007] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for determining the position of a drone is provided. The method includes: obtaining the first position information of N power devices, determining the initial positions of M drone devices according to the N first position information, and obtaining M second position information, wherein M and N are positive integers; for a drone device, obtaining the device parameters of the drone device, and constructing a drone energy consumption model according to the second position information and the device parameters of the drone device; constructing a distance matrix according to the N first position information and the M second position information, and constructing a first objective function by the distance matrix and the M drone energy consumption models, wherein the distance matrix includes first-class elements and second-class elements, each first-class element represents the distance between every two power devices in the N power devices, and each second-class element represents the distance between the power device and the drone device; optimizing the first objective function by using a genetic algorithm to obtain a second objective function, determining the target position information of the M drone devices based on the function parameters in the second objective function, wherein the M drone devices are operated based on the target position information of the M drones.

[0008] Furthermore, determining the initial positions of M drone devices based on N first position information to obtain M second position information includes: filtering the position information that allows the drone device to be turned on from the N first position information to obtain Y preset position information, inputting the Y preset position information into the positioning planning algorithm to obtain D candidate position information, wherein D is less than or equal to Y, D is greater than or equal to M, and Y and D are positive integers; obtaining the flight time data of the M drone devices, constructing constraints for each drone device based on the M flight time data to obtain M constraints; and filtering the D candidate position information based on the M constraints to obtain M second position information.

[0009] Furthermore, constructing a drone energy consumption model based on the second position information and device parameters of the drone device includes: for a drone device, extracting horizontal field of view angle data and preset distance data from the device parameters, and calculating the scanning width data based on the horizontal field of view angle data and the preset distance, wherein the preset distance data refers to the distance data between the drone device and the preset point of the boundary where the scanning width data is located; using the device parameters to calculate to obtain the preset parameters, and calculating based on the scanning width data and the preset parameters to obtain the energy consumption time data of the drone device; calculating the collection capability index of the drone device based on the energy consumption time data and the device parameters, wherein the collection capability index is used to characterize the state of each drone device collecting the device image of an electrical device; and constructing a drone energy consumption model of the drone device based on the energy consumption time data and the collection capability index.

[0010] Furthermore, constructing the first objective function by the distance matrix and M UAV energy consumption models includes: obtaining the historical operation data of each UAV device in the historical time period to obtain M historical operation data, calculating the historical mission data of each UAV device based on the M historical operation data to obtain M historical mission data; calculating the total voyage cost data of the M UAV devices based on the M historical operation data to obtain the total voyage cost data, and calculating the balanced workload data of the M UAV devices based on the M historical operation data; processing based on the M historical mission data, the total voyage cost data and the balanced workload data to obtain the first objective function.

[0011] Furthermore, the total flight cost data of M UAV devices is calculated based on the M historical operation data, and the total flight cost data includes: extracting the flight data of the historical time period from the historical operation data of each UAV device to obtain M historical flight data; summing the M historical flight data to obtain the total flight data, and normalizing the total flight data to obtain the total flight cost data.

[0012] Furthermore, the first objective function is optimized using a genetic algorithm to obtain a second objective function, including: constructing and processing the M second position information based on a genetic algorithm to obtain a resource task matching matrix and a regional center distance matrix, wherein the elements in the resource task matching matrix are used to characterize the static allocation probability of the M UAV devices, and the elements in the regional center distance matrix are used to characterize the planned paths of the M UAV devices; using the resource task matching matrix and the regional center distance matrix to determine a genetic operator, and optimizing the first objective function according to the genetic operator to obtain a second objective function, wherein, in the optimization process, the resource task matching matrix is ​​used to determine whether the M UAV devices meet the regional task requirements and task quantity constraints, and the regional task requirements are used to characterize the requirements of the M UAV devices for the area where the N power equipment are located.

[0013] Further, determining the target position information of M unmanned aerial vehicle devices based on the function parameters in the second objective function includes: determining the updated position information of the M unmanned aerial vehicle devices according to the function parameters of the second objective function to obtain M updated position information; calculating the updated energy consumption time data and the updated collection capability index of each unmanned aerial vehicle device according to each updated position information and the M device parameters to obtain M updated energy consumption time data and M updated collection capability indexes; obtaining iteration requirements, and when the M updated energy consumption time data and the M updated collection capability indexes meet the iteration requirements, determining the M updated position information as the target position information of the M unmanned aerial vehicle devices; when the M updated energy consumption time data and the M updated collection capability indexes do not meet the iteration requirements, obtaining Z preset unmanned aerial vehicle devices, wherein the Z preset unmanned aerial vehicle devices refer to unmanned aerial vehicle devices whose updated energy consumption time data and updated collection capability index do not meet the iteration requirements, and Z is a positive integer; decomposing the updated position information of each preset unmanned aerial vehicle device to obtain Z decomposed position information, and the target position information of the M unmanned aerial vehicle devices is constituted by the Z decomposed position information and the T updated position information, wherein T=MZ, and T is a positive integer.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for determining the position of a drone is provided. The device includes: a first acquisition unit, which is used to acquire the first position information of N power devices, determine the initial positions of M drone devices according to the N first position information, and obtain M second position information, wherein M and N are positive integers; a second acquisition unit, which is used to acquire the equipment parameters of a drone device for a drone device, and construct a drone energy consumption model according to the second position information and equipment parameters of the drone device; a construction unit, which is used to construct a distance matrix according to the N first position information and the M second position information, and construct a first objective function by the distance matrix and the M drone energy consumption models, wherein the distance matrix includes first-class elements and second-class elements, each first-class element represents the distance between every two power devices in the N power devices, and each second-class element represents the distance between the power device and the drone device; a processing unit, which is used to optimize the first objective function using a genetic algorithm to obtain a second objective function, and determine the target position information of the M drone devices based on the function parameters in the second objective function, wherein the M drone devices are operated based on the target position information of the M drones.

[0015] According to another aspect of an embodiment of the present invention, an electronic device is also provided, comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is used to run the computer-readable instructions, wherein a method for determining the position of a drone is executed when the computer-readable instructions are run.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, a method for determining a position of a drone is executed.

[0017] Through the present application, the following steps are adopted: obtaining the first position information of N power devices, determining the initial positions of M drone devices according to the N first position information, and obtaining M second position information, wherein M and N are positive integers; for a drone device, obtaining the device parameters of the drone device, and constructing a drone energy consumption model according to the second position information and the device parameters of the drone device; constructing a distance matrix according to the N first position information and the M second position information, and constructing a first objective function by the distance matrix and the M drone energy consumption models, wherein the distance matrix includes first-class elements and second-class elements, each first-class element represents the distance between every two power devices in the N power devices, and each second-class element represents the distance between the power device and the drone device; optimizing the first objective function by using a genetic algorithm to obtain a second objective function The target function is used to determine the target position information of M UAV devices based on the function parameters in the second objective function, wherein the M UAV devices are operated based on the target position information of the M UAVs, which solves the problems of low detection efficiency and high detection cost when using UAV devices for power equipment detection in the related technology. The first position information of the power equipment is obtained, the initial position of the UAV device is determined according to the first position information, the second position information is obtained, and a UAV energy consumption model is constructed according to the second position information and the equipment parameters of the UAV device. The first objective function is constructed based on the model. After optimizing the function by using a genetic algorithm, the target position information of the UAV device is determined according to the optimized second objective function, thereby achieving the effect of improving the detection efficiency of the UAV equipment, reducing the detection cost of the UAV equipment, and realizing the collaborative coverage of multiple UAVs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a flow chart of a method for determining a drone position according to an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of a method for determining second location information provided in an embodiment of the present application;

[0021] Figure 3 This is a front view of the scanning area of ​​the drone provided according to an embodiment of the present application;

[0022] Figure 4is a side view of a scanning area of ​​a drone provided according to an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of coverage of a drone scanning area provided according to an embodiment of the present application;

[0024] Figure 6 is a schematic diagram of a method for updating a drone position according to an embodiment of the present application;

[0025] Figure 7 is a schematic diagram of an optional method for determining the position of a drone provided in an embodiment of the present application;

[0026] Figure 8 is a schematic diagram of a device for determining a position of a drone provided in an embodiment of the present application;

[0027] Fig. 9 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0032] It should be noted that the collected information used in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse to use it.

[0033] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a method for determining the position of a drone according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0034] Step S101, obtaining first position information of N power devices, determining the initial positions of M drone devices according to the N first position information, and obtaining M second position information, wherein M and N are positive integers.

[0035] Specifically, in order to detect the power transmission grid in a certain area, multiple drones can be deployed for coordinated detection. When deploying drones, in order to maximize the use of drone resources, the location information of each drone can be adjusted and established on a suitable site. At this time, the location information of drones that meet the deployment requirements can be preliminarily screened by combining high-resolution satellite images, the distribution of power equipment to be monitored, and the maximum flight distance and time of drones.

[0036] It should be noted that since some areas where the transmission grid is set up may cross rivers or mountainous areas with steep terrain, satellite data such as satellite maps can be obtained to determine the specific locations of all power equipment in the transmission grid, that is, to obtain multiple first position information, and then determine the initial take-off positions of all drone equipment based on the first position information, that is, to determine multiple second position information.

[0037] Step S102: for a UAV device, obtain device parameters of the UAV device, and build a UAV energy consumption model according to the second position information and the device parameters of the UAV device.

[0038] Specifically, after determining the initial take-off position of the UAV equipment, that is, determining the second position information, in order to maximize the resources of the UAV equipment and meet the low-cost requirements, the equipment parameters of all UAV equipment can be obtained, and then a UAV energy consumption model is constructed using the equipment parameters of each UAV equipment and the second position information. The position of the UAV equipment is further adjusted based on the UAV energy consumption model, wherein the equipment parameters of the UAV equipment may include the flight speed, flight altitude, horizontal field of view angle, vertical field of view angle, UAV pitch angle, UAV imaging sensor installation angle and other parameters of the UAV equipment.

[0039] Step S103, construct a distance matrix based on N first position information and M second position information, and construct a first objective function by the distance matrix and M UAV energy consumption models, wherein the distance matrix includes first-category elements and second-category elements, each first-category element represents the distance between every two power devices among N power devices, and each second-category element represents the distance between a power device and a UAV device.

[0040] Specifically, after constructing the drone energy consumption model of each drone device, in order to optimize and adjust the second position information of the drone device, a distance matrix can be constructed according to the first position information of the power equipment and the second position information of the drone device.

[0041] It should be noted that since the deployment of multiple drone equipment is more complicated, it cannot be simply defined as a set coverage problem. Although the traditional optimization method can cover all the monitored areas, this method makes the entire survey process inefficient and affects the timeliness of disaster survey. In actual application scenarios, in addition to using the minimum number of drones to achieve full coverage, there are many goals that need to be optimized. For example, in the process of using drone equipment to monitor power equipment, the energy consumption of the equipment can be used as an important optimization goal. Therefore, the first objective function can also be constructed based on the determined distance matrix and the drone energy consumption model of all drone equipment, and then the first objective function can be used to optimize the position of the drone equipment.

[0042] Step S104, optimizing the first objective function by using a genetic algorithm to obtain a second objective function, and determining the target position information of the M drone devices based on the function parameters in the second objective function, wherein the M drone devices are operated based on the target position information of the M drones.

[0043] Specifically, after constructing the first objective function based on the distance matrix and the drone energy consumption model of all drone devices, since the first objective function is an underdetermined system, the function can be iteratively optimized at this time, that is, the genetic algorithm can be used to improve the first objective function from three aspects: encoding and decoding, construction of fitness function, and parent selection, crossover and mutation in genetic operations, and then obtain the second objective function containing an approximate solution. Finally, the final location information of the drone device can be determined according to the function parameters of the second objective function, that is, the target location information is determined, and then the location information is used to deploy and operate the drone device, thereby achieving the purpose of multi-drone collaborative optimal coverage.

[0044] It should be noted that when using a traditional genetic algorithm, there are a large number of solutions that do not meet the constraints in its evolutionary population. These solutions that do not meet the constraints affect the optimization speed of the algorithm and may even prevent the convergence of the algorithm. The genetic algorithm in this embodiment can use a conflict mediation mechanism to determine whether the drone device meets the task sequence according to the constraints and adjust the conflicting tasks that do not meet the constraints. In addition, this embodiment also designs a crossover operator and a mutation operator with a conflict mediation mechanism to improve the performance of the dual chromosome encoding method.

[0045] The method for determining the position of a drone provided in an embodiment of the present application obtains the first position information of N power devices, determines the initial positions of M drone devices according to the N first position information, and obtains M second position information, wherein M and N are positive integers; for a drone device, obtains the device parameters of the drone device, and constructs a drone energy consumption model according to the second position information and the device parameters of the drone device; constructs a distance matrix according to the N first position information and the M second position information, and constructs a first objective function by the distance matrix and the M drone energy consumption models, wherein the distance matrix includes first-class elements and second-class elements, each first-class element represents the distance between every two power devices in the N power devices, and each second-class element represents the distance between the power device and the drone device; optimizes the first objective function using a genetic algorithm, A second objective function is obtained, and the target position information of M UAV devices is determined based on the function parameters in the second objective function. M UAV devices are operated based on the target position information of the M UAVs, which solves the problems of low detection efficiency and high detection cost when using UAV equipment for power equipment detection in related technologies. The first position information of the power equipment is obtained, and the initial position of the UAV device is determined according to the first position information to obtain the second position information. A UAV energy consumption model is constructed according to the second position information and the equipment parameters of the UAV device, and a first objective function is constructed based on the model. After optimizing the function using a genetic algorithm, the target position information of the UAV device is determined according to the optimized second objective function, thereby achieving the effect of improving the detection efficiency of the UAV equipment, reducing the detection cost of the UAV equipment, and realizing the collaborative coverage of multiple UAVs.

[0046] Optionally, in the method for determining the position of a drone provided in an embodiment of the present application, the initial positions of M drone devices are determined based on N first position information to obtain M second position information, including: filtering the position information that allows the drone device to be turned on from the N first position information to obtain Y preset position information, inputting the Y preset position information into a positioning planning algorithm to obtain D candidate position information, wherein D is less than or equal to Y, D is greater than or equal to M, and Y and D are positive integers; obtaining the flight time data of the M drone devices, constructing constraints for each drone device based on the M flight time data, and obtaining M constraints; filtering the D candidate position information based on the M constraints to obtain M second position information.

[0047] It should be noted that when using the first position information of the power equipment to determine the initial take-off position of the UAV equipment (that is, the second position information), the initial take-off position of the UAV equipment can be determined based on the coverage of the satellite map, DEM and other satellite data, where DEM (Digital Elevation Model) is a digital model used to represent ground height data, which can be used in terrain analysis, map making, and geographic information fields. DEM can provide accurate data support for terrain visualization and analysis by storing ground height information in a regular grid form.

[0048] Specifically, Figure 2 is a schematic diagram of a method for determining second location information provided in an embodiment of the present application, such as Figure 2 As shown, a geographic information system tool for capturing, storing, analyzing and displaying geospatial data can be used to import high-resolution satellite images, power equipment distribution location information (i.e., first location information), and digital surface model data, and obtain the endurance data of all drone equipment, and build constraints based on the endurance data to achieve maximum coverage and minimize the number of drones. Finally, the candidate location information is screened according to the constraints, and the screening can be performed by weighting the distance between the drone equipment and the power equipment to obtain the second location information of each drone equipment, wherein the average distance and average time of the drone equipment from the power equipment can be calculated through all the second location information, and then the drone energy consumption model can be calculated based on the average distance and average time.

[0049] For example, if the power transmission grid is set up near a river or in a mountainous area with steep terrain, and the UAV equipment cannot take off in the river or in the mountainous area with steep terrain, then the location information that allows the UAV equipment to be turned on can be screened from the first location information of all power equipment, that is, based on the distribution location of the power equipment, a strategy of using the minimum UAV to achieve the maximum coverage is used to obtain multiple preset location information, and then these preset location information are input into the positioning planning algorithm, and the algorithm determines the candidate location of each UAV equipment, that is, multiple candidate location information is obtained. At this time, the UAV equipment uses the candidate location information to connect to a certain power equipment in a straight line, indicating that the power equipment can be detected by the UAV equipment from the candidate location information.

[0050] It should be noted that when selecting candidate areas for achieving maximum coverage and minimum number of drones, the above-mentioned maximum coverage refers to the need to select multiple drone devices under certain restrictions to cover all or the maximum number of power equipment that needs to be monitored, and maximize the use of drone resources. Certain restrictions refer to the location where the drone equipment is deployed, which is open and not subject to signal interference, away from man-made buildings and water bodies, with flat terrain, and limits the maximum flight time or maximum flight distance of the drone equipment (that is, the selected drone equipment deployment location needs to satisfy the flight time or flight distance of each drone to the power equipment that is less than the given maximum flight time or maximum flight distance); the minimum number of drones refers to the need to limit the number of drone equipment under external factors such as cost, so that the minimum number of drones required to cover all or the maximum number of power equipment that needs to be monitored under certain restrictions. This embodiment determines the second location information of the drone equipment by using the location information of the power equipment and the positioning planning algorithm, thereby laying the foundation for the subsequent optimization of the location of the drone equipment.

[0051] In order to analyze the energy consumption of the drone equipment, optionally, in the method for determining the drone position provided in the embodiment of the present application, constructing a drone energy consumption model based on the second position information and equipment parameters of the drone equipment includes: for a drone equipment, extracting horizontal field of view angle data and preset distance data from the equipment parameters, and calculating the scanning width data based on the horizontal field of view angle data and the preset distance, wherein the preset distance data refers to the distance data between the drone equipment and the preset point of the boundary where the scanning width data is located; using the equipment parameters to calculate to obtain the preset parameters, and calculating based on the scanning width data and the preset parameters to obtain the energy consumption time data of the drone equipment; calculating the collection capability index of the drone equipment based on the energy consumption time data and the equipment parameters, wherein the collection capability index is used to characterize the state of each drone equipment collecting the equipment image of an electric power equipment; and constructing a drone energy consumption model of the drone equipment based on the energy consumption time data and the collection capability index.

[0052] Specifically, after obtaining the second position information of the UAV device, an energy consumption model that characterizes the UAV's acquisition capability and energy consumption information when performing tasks can be constructed based on the second position information and device parameters. Figure 3 is a front view of the drone scanning area provided according to an embodiment of the present application, such as Figure 3 As shown in the figure, this is a schematic diagram of the drone scanning area, AA 1 B 1 B is the drone scanning area, where AA 1 is the back scan boundary, BB 1 is the front scan boundary, and vertex O is the area where the drone is located; Figure 4 is a side view of a scanning area of ​​a drone provided in an embodiment of the present application, such as Figure 4 As shown, this figure is a side view of the area scanned by the drone; Figure 5 is a schematic diagram of the coverage of the drone scanning area provided in the embodiment of the present application, such as Figure 5 As shown, this figure is a drone scanning area coverage map, and the drone coverage range is AA 1 B 1 B, the area to be scanned is AA 1 C 1 C, front scanning area width f, rear scanning area width b, scanning area length l, UAV speed v, flight altitude height, horizontal field of view angle α, vertical field of view angle θ, UAV pitch angle γ, UAV imaging sensor installation angle β and other data, OC is the angle bisector of angle AOB, β refers to the angle between the angle bisector OC and the UAV equipment body.

[0053] In order to better monitor the target area, the scan width data b can be calculated at this time, that is, the horizontal field of view angle α, the UAV device O and the rear scan boundary AA are obtained from the equipment parameters of each UAV device. 1 Center Point A * After the distance (that is, the preset distance data) is determined, the scan width data b is calculated using the following formula:

[0054]

[0055] Furthermore, if Figure 5 As shown, Figure 5 The area to be scanned by the drone is covered in the map. The area to be scanned is AA 1 C 1 C. If a single UAV device is to scan the area to be covered, then line segment m is a feasible route. At this time, a UAV device U can be set i The width of the front scanning area is f i , the width of the rear scanning area is b i , the flight speed of the drone equipment is v i 、Flight altitude is height i , the pitch angle during flight is γ i 、UAV sensor installation angle β i , horizontal field of view angle α i , the vertical field of view angle θ of the imaging sensor i , the time for multiple drones to perform tasks is t, and the area to be scanned is area(S). Then, the equation for the preset parameters can be obtained based on the above equipment parameters:

[0056]

[0057] When calculating the energy consumption time data of the drone equipment based on the sweep width data and preset parameters, it can be calculated by the above formula, that is, first substitute the formula of the sweep width data b into the equation for calculating the preset parameters, and the following formula can be obtained:

[0058]

[0059] The energy consumption time data can be derived from the above formula:

[0060]

[0061] Finally, the acquisition capability index of the state of the UAV equipment collecting equipment images of the power equipment can be calculated based on the energy consumption time data and equipment parameters:

[0062]

[0063] Finally, the energy consumption time data and the collection capability index are used to construct the drone energy consumption model of the drone equipment. This embodiment uses the equipment parameters of the drone equipment to calculate, thereby determining the energy consumption time data and the collection capability index, and finally determines the drone energy consumption model of each drone equipment based on the energy consumption time data and the collection capability index, and also provides data support for optimizing the location information of the drone equipment.

[0064] In order to optimize the position of the UAV equipment, a first objective function can be constructed first. Optionally, in the method for determining the position of the UAV provided in the embodiment of the present application, constructing the first objective function by the distance matrix and M UAV energy consumption models includes: obtaining the historical operation data of each UAV equipment in the historical time period to obtain M historical operation data, calculating the historical mission data of each UAV equipment according to the M historical operation data to obtain M historical mission data; calculating the total voyage cost data of the M UAV equipment according to the M historical operation data to obtain the total voyage cost data, and calculating the balanced workload data of the M UAV equipment according to the M historical operation data; processing based on the M historical mission data, the total voyage cost data and the balanced workload data to obtain the first objective function.

[0065] Specifically, after constructing the UAV energy consumption model, the first objective function can be constructed based on the distance matrix and the UAV energy consumption model. For the goal of multi-UAV coordinated optimal coverage, the first objective function can be established to evaluate the decision variable matrix of the system. It takes into account the time cost and flight cost of the drone system and balances the workload of the drone. Before calculating the time cost, flight cost and balancing the workload of the drone, it is necessary to first calculate the distance matrix, which can be calculated through the location information of the electrical equipment. The matrix can include the distance between the electrical equipment and the distance between the electrical equipment and the drone. The distance matrix, the operation of the drone equipment in the historical time period and the drone energy consumption model can determine the historical operation data of the drone equipment. Furthermore, when calculating the time cost of the drone, that is, the historical task data of each drone equipment to complete the task, it can be calculated by the following formula:

[0066]

[0067] Among them, N U Represents the number of drone devices, N T Indicates the number of power devices, maxR i Indicates the maximum range of the drone device in the historical period, Represents the historical operation data of a certain UAV device in the historical time period, v i Represents the flight speed of the i-th UAV device. Then the total flight cost data of all UAV devices (that is, the total energy consumption of the UAV system) is calculated using the historical operation data.

[0068] In order to prevent the exhaustion of resources of a single drone device and ensure the efficient operation of the drone device, it is also necessary to calculate the balanced workload data of each drone device based on historical data. At this time, the balanced workload data of the drone device can be calculated from the historical operation data, where the balanced workload data represents the sum of the standard deviations of the drone energy consumption ratio. The above data can be calculated by the following formula:

[0069]

[0070] Finally, in order to minimize costs, maximize task completion rate, and take into account the efficiency and maintenance requirements of equipment, the historical task data, total voyage cost data, and balanced workload data can be processed based on preset weight parameters to construct the first objective function maxJ:

[0071]

[0072] Among them, ω2-ω4 represent the weight parameters of historical mission data, total voyage cost data and balanced workload data, ω1 is C V The weight parameter, C V Refers to the regional value reward data, which is the regional value multiplied by the task execution success rate, which can be calculated by the following formula:

[0073]

[0074] in, This embodiment constructs the first objective function by using the distance matrix and the drone energy consumption model of the drone equipment, and can also provide a scientific basis for position optimization, thereby improving the operation and maintenance efficiency of the entire drone system.

[0075] Optionally, in the method for determining the position of a drone provided in an embodiment of the present application, total flight cost data of M drone devices is calculated based on M historical operation data, and the total flight cost data is obtained, including: extracting the flight data of a historical time period from the historical operation data of each drone device to obtain M historical flight data; summing the M historical flight data to obtain total flight data, and normalizing the total flight data to obtain total flight cost data.

[0076] Specifically, when calculating the total flight cost data, the flight data of the historical time period can be obtained first, where the flight data can include the flight distance, time, and energy consumed by the drone equipment, etc., and then the historical flight data is summed to obtain the total flight data of the total distance flown by all drone equipment. In order to make the data comparable, the total flight data is finally normalized to obtain the total flight cost data, and the total flight cost data can be calculated by the following formula:

[0077]

[0078] Among them, N U Indicates the number of drone devices, maxR i Indicates the maximum range of the drone device in the historical period, Represents the historical operation data of a certain UAV device in the historical time period, v i Indicates the flight speed of the i-th UAV device. This embodiment extracts valuable information from historical operation data, conducts in-depth analysis of the flight cost of the UAV, obtains total flight cost data, and then uses the total flight cost data to optimize the flight position of the UAV device, thereby improving the overall performance.

[0079] In order to optimize the first objective function and generate reasonable multi-UAV deployment positions, optionally, in the method for determining the UAV position provided in the embodiment of the present application, a genetic algorithm is used to optimize the first objective function to obtain a second objective function, including: constructing and processing the M second position information based on the genetic algorithm to obtain a resource task matching matrix and a regional center distance matrix, wherein the elements in the resource task matching matrix are used to characterize the static allocation probability of the M UAV devices, and the elements in the regional center distance matrix are used to characterize the planned paths of the M UAV devices; using the resource task matching matrix and the regional center distance matrix to determine the genetic operator, and optimizing the first objective function according to the genetic operator to obtain the second objective function, wherein, in the optimization process, the resource task matching matrix is ​​used to determine whether the M UAV devices meet the regional task requirements and task quantity constraints, and the regional task requirements are used to characterize the requirements of the M UAV devices for the area where the N power equipment are located.

[0080] Specifically, when optimizing the first objective function using a genetic algorithm, a conflict mediation mechanism can be used first. The genetic algorithm is a search and optimization technology that simulates natural selection and genetic mechanisms. It can simulate the biological evolution process to solve complex optimization problems. The conflict mediation mechanism is derived from a distributed negotiation allocation method. This method designs an additional objective function to guide the sequence adjustment based on the matching relationship between the drone and the task and the system's interests, and obtains a feasible solution that meets all constraints. Based on the prior information of the given constraints, it is necessary to calculate the resource-task matching matrix and evolve the population in the set of feasible solutions, which significantly improves the performance of the genetic algorithm. The resource-task matching matrix is ​​also called the allocation probability matrix. It is calculated from the system model and constraints, and can determine whether the drone meets the regional mission requirements, range requirements, and task quantity constraints.

[0081] First, in order to allocate one or more power devices to each UAV device, so as to achieve effective utilization of the UAV device, the second position information can be constructed and processed based on the genetic algorithm to obtain the resource task matching matrix PS ij :PS ij =(ZP ij ·ZPr ij ·ZPd ij ); and the resource task allocation matrix is ​​composed of ZP ij , ZPr ij , ZPd ij Composition, among which, ZPr ij Represents the static allocation probability used to calculate the UAV equipment (independent of the task sequence), including detection resolution, front overlap rate and preset success rate parameters ZP ijThis indicates that the more tasks assigned to UAV equipment, the less likely it is to continue to be assigned tasks; ZPd ij It is used to calculate the range of drone equipment that meets the newly allocated area. It should be noted that ZP ij , ZPr ij , ZPd ij It can be calculated by the following formula:

[0082]

[0083]

[0084] in, Indicates capacity parameter, Prh i Indicates drone U i Hl i Resolution during flight, OL ij Indicates drone U i In T j The ratio of the overlapping parts between the two photos in the field of view is the front overlap rate, RL i It's a drone i The remaining task space, N si is assigned to the UAV U i The number of tasks, L i Indicates the upper limit of the target quantity. Indicates the difficulty coefficient, It is task T j Join UAV i The approximate scope of the task sequence, OL j Also represents the positive overlap rate, each element (i, j) in the resource-task matching matrix represents the matching probability between the i-th UAV equipment and the j-th power equipment.

[0085] In order to further plan a reasonable path for the UAV equipment and achieve efficient scheduling of the UAV equipment when performing tasks, when constructing the regional center distance matrix based on the second position information based on the genetic algorithm, the conflict mediation mechanism precedes the path planning. Therefore, the connection path Transpath between the two regions before the task sequence ij，k It cannot be uniquely determined because each region has four possible endpoints. However, there is a coupling problem between task allocation and path planning, that is, the judgment of task sequence must be based on the result of path planning. Therefore, in the conflict mediation mechanism, the distance matrix of the region center is calculated to approximate the connection path matrix, thereby avoiding the waste of computing resources caused by repeated path planning, and then preliminarily satisfying the path constraints.

[0086] The Euclidean distance between two region center coordinates is calculated as:

[0087]

[0088] Among them, D j，k is the preset distance parameter.

[0089] Furthermore, genetic operators can be constructed based on the idea of ​​adaptive settings of genetic operations. Genetic operators can include crossover operators and mutation operators, which work together on individuals in the population to achieve population optimization, thereby meeting the optimization scheduling needs of UAV equipment in power inspection tasks. Among them, the mutation operator is an important mechanism to prevent the population from falling into the local minimum and improve the global convergence of the genetic algorithm. The crossover operator generates a pair of offspring chromosomes by partially exchanging genes of a pair of parent chromosomes. Due to the encoding strategy, the second layer of all individuals is the same, so the crossover operator only needs to consider the gene exchange of the first layer.

[0090] The first objective function is optimized according to the genetic operator to obtain the second objective function. In the optimization process, the resource task matching matrix is ​​used to determine whether the UAV equipment meets the regional task requirements and the task quantity constraints. That is, it is necessary to ensure that each UAV equipment can meet the requirements of the area where the power equipment is located when performing tasks, and the number of tasks of each UAV equipment does not exceed its maximum capacity. Then, a UAV equipment scheduling plan that meets all constraints can be obtained, and the optimal scheduling and efficient operation of UAVs in power inspection tasks can be achieved.

[0091] It should be noted that the function expression of the adaptive setting method is as follows, where N g and N iter denote the total number of iterations and the current number of iterations respectively. round[·] is a rounding function. According to the chromosome encoding strategy, the crossover and mutation operators will also be modified.

[0092]

[0093] N mu =N p -N e -N cr ;

[0094] Then, the first objective function is optimized according to the genetic operator to obtain the second objective function. This embodiment constructs and processes the second position information based on the genetic algorithm to achieve optimal scheduling of the UAV in the power inspection task, thereby achieving efficient operation of the UAV equipment in the power inspection task, which not only improves the utilization rate of the UAV equipment, but also ensures the efficiency and reliability of the UAV equipment when performing tasks.

[0095] In order to obtain the location information of the drone equipment, the optimal location information of each drone equipment can be gradually optimized to achieve the coordinated optimal coverage of the entire drone equipment. Optionally, in the method for determining the drone position provided in the embodiment of the present application, determining the target location information of M drone equipment based on the function parameters in the second objective function includes: determining the updated location information of the M drone equipment according to the function parameters of the second objective function to obtain M updated location information; calculating the updated energy consumption time data and the updated collection capability index of each drone equipment according to each updated location information and the M device parameters to obtain M updated energy consumption time data and M updated collection capability indexes; obtaining the iteration requirement, and obtaining the updated energy consumption time data and the updated collection capability indexes in the M updated energy consumption time data. When the energy consumption time data and the M updated acquisition capability indexes meet the iteration requirements, the M updated location information are determined as the target location information of the M UAV devices; when the M updated energy consumption time data and the M updated acquisition capability indexes do not meet the iteration requirements, Z preset UAV devices are obtained, wherein the Z preset UAV devices refer to the UAV devices whose updated energy consumption time data and updated acquisition capability index do not meet the iteration requirements, and Z is a positive integer; the updated location information of each preset UAV device is decomposed to obtain Z decomposed location information, and the target location information of the M UAV devices is constituted by the Z decomposed location information and the T updated location information, wherein T=MZ, and T is a positive integer.

[0096] Specifically, in order to achieve collaborative optimal coverage, the location information of the UAV device can be updated according to the function parameters of the second objective function to obtain the updated location information, and then the distance matrix is ​​calculated according to each updated location information, and the updated collection capability index and updated energy consumption time data of each UAV device are calculated according to the distance matrix and the device parameters to obtain the updated collection capability index and updated energy consumption time data, where the updated energy consumption time data t and the updated collection capability index P i It can be calculated by the following formula:

[0097]

[0098] Furthermore, after obtaining the iteration requirements, it is determined whether the updated energy consumption time data and the updated acquisition capability index meet the iteration requirements. If they do, the updated position information can be determined as the target position information, and the optimization process ends; otherwise, if the iteration requirements are not met, the updated position information of each drone device that does not meet the iteration requirements is decomposed, and the target position information is formed by the decomposed position information and the updated position information of the drone devices that meet the iteration requirements.

[0099] For example, Figure 6 is a schematic diagram of a method for updating the position of a drone provided in an embodiment of the present application, such as Figure 6 As shown, if the area that can be collected corresponding to the updated collection capability index calculated based on the updated position information is less than the area that the drone device needs to cover, the updated position information needs to be decomposed at this time; if the area that can be collected corresponding to the updated collection capability index is larger than the area that the drone device needs to cover, there is no need to decompose the position information at this time, and the updated position information can be used to calculate the energy consumption time data. If the updated energy consumption time data calculated based on the updated position information is greater than the preset energy consumption in the iteration requirement, the updated position information needs to be merged at this time, so that when the energy consumption time data is calculated again for the merged position information, the data is less than the preset energy consumption. This embodiment further improves the positioning accuracy of the drone device by gradually optimizing the position information of the drone device in each iteration, and also optimizes its energy consumption and collection capability, thereby providing an effective solution for the collaborative positioning of drone devices.

[0100] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0101] The present application also provides a method for determining the position of a drone. Figure 7 is a schematic diagram of an optional method for determining the position of a drone provided in an embodiment of the present application, such as Figure 7 As shown, the method includes:

[0102] In order to detect the power transmission grid in a certain area, multiple drones can be deployed for coordinated detection. When deploying drones, in order to maximize the use of drone resources, the location information of each drone can be adjusted and established on a suitable site. At this time, the location information of drones that meet the deployment requirements can be preliminarily screened based on the geographic information system in order to combine high-resolution satellite images, the distribution of power equipment to be monitored, and the maximum flight distance and time of drones, thereby achieving the initial deployment of multiple drones.

[0103] Furthermore, after determining the initial take-off position of the UAV equipment, that is, determining the second position information, in order to maximize the resources of the UAV equipment and meet the low-cost requirements, the equipment parameters of all UAV equipment can be obtained, and then a UAV energy consumption model can be constructed using the equipment parameters and the second position information of each UAV equipment. For example, a UAV energy consumption model can be constructed based on the UAV flight characteristics and scanning area characteristics, and then the position of the UAV equipment can be further adjusted based on the UAV energy consumption model.

[0104] After constructing the drone energy consumption model of each drone device, in order to optimize and adjust the second position information of the drone device, the distance matrix and the first objective function can be constructed according to the first position information of the power equipment (that is, the power equipment distribution map) and the second position information of the drone device (that is, the initial deployment of the drone). Finally, the genetic algorithm is used to optimize the first objective function, and finally the second objective function is obtained to achieve optimal coverage of multi-drone collaboration.

[0105] This embodiment obtains the first position information of the power equipment, determines the initial position of the UAV equipment according to the first position information, obtains the second position information, constructs a UAV energy consumption model according to the second position information and the equipment parameters of the UAV equipment, and constructs a first objective function based on the model. After optimizing the function using a genetic algorithm, the target position information of the UAV equipment is determined according to the optimized second objective function, thereby improving the detection efficiency of the UAV equipment, reducing the detection cost of the UAV equipment, and achieving the effect of collaborative coverage of multiple UAVs.

[0106] The embodiment of the present application also provides a device for determining the position of a drone. It should be noted that the device for determining the position of a drone in the embodiment of the present application can be used to execute the method for determining the position of a drone provided in the embodiment of the present application. The device for determining the position of a drone provided in the embodiment of the present application is introduced below.

[0107] Figure 8 is a schematic diagram of a device for determining the position of a drone according to an embodiment of the present application, such as Figure 8 As shown, the device includes: a first acquisition unit 80, a second acquisition unit 81, a construction unit 82, and a processing unit 83.

[0108] The first acquisition unit 80 is used to acquire first position information of N power devices, determine the initial positions of M drone devices according to the N first position information, and obtain M second position information, where M and N are positive integers;

[0109] The second acquisition unit 81 is used to acquire device parameters of a UAV device, and build a UAV energy consumption model according to the second position information and device parameters of the UAV device;

[0110] A construction unit 82 is used to construct a distance matrix according to the N first position information and the M second position information, and to construct a first objective function according to the distance matrix and the M UAV energy consumption models, wherein the distance matrix includes first-class elements and second-class elements, each first-class element represents the distance between every two power devices in the N power devices, and each second-class element represents the distance between the power device and the UAV device;

[0111] The processing unit 83 is used to optimize the first objective function using a genetic algorithm to obtain a second objective function, and determine the target position information of the M drone devices based on the function parameters in the second objective function, wherein the M drone devices are operated based on the target position information of the M drones.

[0112] The device for determining the position of a drone provided in an embodiment of the present application obtains the first position information of N power devices through a first acquisition unit 80, determines the initial positions of M drone devices according to the N first position information, and obtains M second position information, wherein M and N are positive integers; the second acquisition unit 81 obtains the equipment parameters of a drone device for a drone device, and constructs a drone energy consumption model according to the second position information and the equipment parameters of the drone device; the construction unit 82 constructs a distance matrix according to the N first position information and the M second position information, and constructs a first objective function by the distance matrix and the M drone energy consumption models, wherein the distance matrix includes first-class elements and second-class elements, each first-class element represents the distance between every two power devices in the N power devices, and each second-class element represents the distance between the power device and the drone device; the processing unit 83 uses a genetic algorithm The first objective function is optimized to obtain the second objective function, and the target position information of M UAV devices is determined based on the function parameters in the second objective function. The M UAV devices are operated based on the target position information of the M UAVs, which solves the problems of low detection efficiency and high detection cost when using UAV equipment for power equipment detection in related technologies. The first position information of the power equipment is obtained, the initial position of the UAV equipment is determined according to the first position information, the second position information is obtained, and a UAV energy consumption model is constructed according to the second position information and the equipment parameters of the UAV equipment. The first objective function is constructed based on the model. After optimizing the function using a genetic algorithm, the target position information of the UAV equipment is determined according to the optimized second objective function, thereby achieving the effect of improving the detection efficiency of the UAV equipment, reducing the detection cost of the UAV equipment, and realizing the collaborative coverage of multiple UAVs.

[0113] Optionally, in the device for determining the position of a drone provided in an embodiment of the present application, the first acquisition unit 80 includes: a first screening module, used to screen the position information that allows the drone device to be turned on from N first position information, to obtain Y preset position information, and input the Y preset position information into the positioning planning algorithm to obtain D candidate position information, wherein D is less than or equal to Y, D is greater than or equal to M, and Y and D are positive integers; the first acquisition module, used to obtain the flight time data of M drone devices, and construct the constraint conditions of each drone device according to the M flight time data to obtain M constraint conditions; the second screening module, used to screen the D candidate position information according to the M constraint conditions to obtain M second position information.

[0114] Optionally, in the device for determining the position of a drone provided in an embodiment of the present application, the second acquisition unit 81 includes: a first extraction module, which is used to extract horizontal field of view angle data and preset distance data from equipment parameters for a drone device, and calculate the scanning width data based on the horizontal field of view angle data and the preset distance, wherein the preset distance data refers to the distance data between the drone device and a preset point on the boundary where the scanning width data is located; a first calculation module, which is used to use equipment parameters to perform calculations to obtain preset parameters, and to perform calculations based on the scanning width data and the preset parameters to obtain energy consumption time data of the drone device; a second calculation module, which is used to calculate the collection capability index of the drone device based on the energy consumption time data and equipment parameters, wherein the collection capability index is used to characterize the state of each drone device collecting an equipment image of an electrical equipment; a first construction module, which is used to construct a drone energy consumption model of the drone device based on the energy consumption time data and the collection capability index.

[0115] Optionally, in the device for determining the position of a drone provided in an embodiment of the present application, the construction unit 82 includes: a second acquisition module, used to acquire the historical operation data of each drone device in a historical time period to obtain M historical operation data, and calculate the historical mission data of each drone device based on the M historical operation data to obtain M historical mission data; a third calculation module, used to calculate the total voyage cost data of M drone devices based on the M historical operation data to obtain the total voyage cost data, and calculate the balanced workload data of the M drone devices based on the M historical operation data; a processing module, used to perform processing based on the M historical mission data, the total voyage cost data and the balanced workload data to obtain a first objective function.

[0116] Optionally, in the device for determining the position of a drone provided in an embodiment of the present application, the construction unit 82 includes: a second extraction module, used to extract the flight data of a historical time period from the historical operation data of each drone device to obtain M historical flight data; a fourth calculation module, used to sum the M historical flight data to obtain total flight data, and normalize the total flight data to obtain total flight cost data.

[0117] Optionally, in the device for determining the position of the drone provided in the embodiment of the present application, the processing unit 83 includes: a second construction module, used to construct and process the M second position information based on a genetic algorithm to obtain a resource task matching matrix and a regional center distance matrix, wherein the elements in the resource task matching matrix are used to characterize the static allocation probability of the M drone devices, and the elements in the regional center distance matrix are used to characterize the planned paths of the M drone devices; a first determination module, used to determine the genetic operator using the resource task matching matrix and the regional center distance matrix, and optimize the first objective function according to the genetic operator to obtain a second objective function, wherein, in the optimization process, the resource task matching matrix is ​​used to determine whether the M drone devices meet the regional task requirements and task quantity constraints, and the regional task requirements are used to characterize the requirements of the M drone devices for the area where the N power equipment are located.

[0118] Optionally, in the device for determining the position of the drone provided in the embodiment of the present application, the processing unit 83 includes: a second determination module, used to determine the updated position information of the M drone devices according to the function parameters of the second objective function, and obtain M updated position information; a fifth calculation module, used to calculate the updated energy consumption time data and the updated acquisition capability index of each drone device according to each updated position information and the M device parameters, and obtain M updated energy consumption time data and M updated acquisition capability indexes; a third acquisition module, used to obtain the iteration requirement, and when the M updated energy consumption time data and the M updated acquisition capability indexes meet the iteration requirement, the M updated The position information is determined as the target position information of M UAV devices; the fourth acquisition module is used to obtain Z preset UAV devices when the M updated energy consumption time data and the M updated collection capability indexes do not meet the iteration requirements, wherein the Z preset UAV devices refer to the UAV devices whose updated energy consumption time data and updated collection capability index do not meet the iteration requirements, and Z is a positive integer; the decomposition module is used to decompose the updated position information of each preset UAV device to obtain Z decomposed position information, and the target position information of M UAV devices is composed of the Z decomposed position information and the T updated position information, wherein T=MZ, and T is a positive integer.

[0119] The above-mentioned device for determining the position of the drone includes a processor and a memory. The above-mentioned first acquisition unit 80, second acquisition unit 81, construction unit 82, processing unit 83, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0120] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problems of low detection efficiency and high detection cost when using drone equipment for power equipment detection in related technologies.

[0121] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0122] An embodiment of the present invention provides a computer storage medium, which is used to store a program, wherein when the program is running, a device where the computer storage medium is located is controlled to execute a method for determining the position of a drone.

[0123] Fig. 9 is a schematic diagram of an electronic device provided according to an embodiment of the present application, such as Fig. 9 As shown, an embodiment of the present invention provides an electronic device, the electronic device 90 includes a processor, a memory, and a program stored in the memory and executable on the processor, the processor is used to execute computer-readable instructions, wherein the computer-readable instructions execute a method for determining the position of a drone when they are executed. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0124] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of a method for determining the position of a drone in each embodiment of the present application.

[0125] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0126] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0129] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0130] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0131] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0132] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0133] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining the position of a drone, characterized in that: include: Obtaining first position information of N power devices, determining initial positions of M unmanned aerial vehicle devices according to the N first position information, and obtaining M second position information, wherein M and N are positive integers; For a UAV device, obtaining device parameters of the UAV device, and building a UAV energy consumption model according to the second location information of the UAV device and the device parameters; A distance matrix is ​​constructed according to the N first position information and the M second position information, and a first objective function is constructed by the distance matrix and the M UAV energy consumption models, wherein the distance matrix includes first-category elements and second-category elements, each of the first-category elements represents the distance between every two of the N power devices, and each of the second-category elements represents the distance between a power device and a UAV device; The first objective function is optimized by using a genetic algorithm to obtain a second objective function, and the target position information of the M drone devices is determined based on the function parameters in the second objective function, wherein the M drone devices are operated based on the target position information of the M drones.

2. The method according to claim 1, characterized in that Determine the initial positions of M drone devices according to the N first position information, and obtain M second position information including: Filter the location information that allows the UAV device to be turned on from the N first location information to obtain Y preset location information, input the Y preset location information into the positioning planning algorithm to obtain D candidate location information, where D is less than or equal to Y, D is greater than or equal to M, and Y and D are positive integers; Obtaining the flight time data of the M drone devices, and constructing a constraint condition for each drone device according to the M flight time data to obtain M constraint conditions; The D pieces of candidate position information are screened according to the M constraints to obtain the M pieces of second position information.

3. The method according to claim 1, characterized in that Constructing a drone energy consumption model according to the second location information of the drone device and the device parameters includes: For a drone device, extract horizontal field of view angle data and preset distance data from the device parameters, and calculate sweep width data according to the horizontal field of view angle data and the preset distance, wherein the preset distance data refers to the distance data between the drone device and a preset boundary point where the sweep width data is located; Calculating using the equipment parameters to obtain preset parameters, and calculating according to the sweep width data and the preset parameters to obtain energy consumption time data of the UAV equipment; The acquisition capability index of the UAV device is calculated according to the energy consumption time data and the device parameters, wherein the acquisition capability index is used to characterize the state of each UAV device collecting a device image of a power device; A drone energy consumption model of the drone device is constructed based on the energy consumption time data and the acquisition capability index.

4. The method according to claim 1, characterized in that: Constructing the first objective function using the distance matrix and the M drone energy consumption models includes: Obtain historical operation data of each drone device in a historical time period to obtain M historical operation data, and calculate historical mission data of each drone device based on the M historical operation data to obtain M historical mission data; Calculate the total voyage cost data of the M drone devices according to the M historical operation data to obtain the total voyage cost data, and calculate the balance workload data of the M drone devices according to the M historical operation data; The first objective function is obtained by processing the M historical mission data, the total voyage cost data and the balanced workload data.

5. The method according to claim 4, characterized in that The total voyage cost data of the M drone devices are calculated according to the M historical operation data, and the total voyage cost data obtained includes: Extracting the flight data of the historical time period from the historical operation data of each UAV device to obtain M historical flight data; The M historical voyage data are summed up to obtain total voyage data, and the total voyage data are normalized to obtain the total voyage cost data.

6. The method according to claim 1, characterized in that The first objective function is optimized by using a genetic algorithm to obtain a second objective function including: Based on the genetic algorithm, the M second position information is constructed and processed to obtain a resource task matching matrix and a regional center distance matrix, wherein the elements in the resource task matching matrix are used to characterize the static allocation probability of the M unmanned aerial vehicle devices, and the elements in the regional center distance matrix are used to characterize the paths planned by the M unmanned aerial vehicle devices; The genetic operator is determined by using the resource-task matching matrix and the regional center distance matrix, and the first objective function is optimized according to the genetic operator to obtain the second objective function, wherein in the optimization process, the resource-task matching matrix is ​​used to determine whether the M drone devices meet the regional task requirements and task quantity constraints, and the regional task requirements are used to characterize the requirements of the M drone devices for the area where the N power equipment are located.

7. The method according to claim 1, characterized in that Determining the target position information of the M drone devices based on the function parameters in the second objective function includes: Determine the updated position information of the M drone devices according to the function parameter of the second objective function to obtain M updated position information; Calculate the update energy consumption time data and update collection capability index of each UAV device according to each updated position information and M device parameters, and obtain M update energy consumption time data and M update collection capability indexes; Acquire an iteration requirement, and when the M updated energy consumption time data and the M updated acquisition capability indexes meet the iteration requirement, determine the M updated position information as the target position information of the M unmanned aerial vehicle devices; In the case that the M updated energy consumption time data and the M updated acquisition capability indexes do not meet the iteration requirement, Z preset drone devices are obtained, wherein the Z preset drone devices refer to drone devices whose updated energy consumption time data and updated acquisition capability index do not meet the iteration requirement, and Z is a positive integer; The updated position information of each preset UAV device is decomposed to obtain Z decomposed position information, and the target position information of the M UAV devices is constituted by the Z decomposed position information and T updated position information, wherein T=MZ, and T is a positive integer.

8. A device for determining the position of a drone, characterized in that: include: A first acquisition unit is used to acquire first position information of N power devices, determine initial positions of M drone devices according to the N first position information, and obtain M second position information, where M and N are positive integers; A second acquisition unit is used to acquire, for a UAV device, device parameters of the UAV device, and construct a UAV energy consumption model according to the second position information of the UAV device and the device parameters; A construction unit, configured to construct a distance matrix according to the N first position information and the M second position information, and to construct a first objective function according to the distance matrix and the M UAV energy consumption models, wherein the distance matrix includes first-category elements and second-category elements, each of the first-category elements represents a distance between every two of the N power devices, and each of the second-category elements represents a distance between a power device and a UAV device; A processing unit is used to optimize the first objective function using a genetic algorithm to obtain a second objective function, and determine the target position information of the M drone devices based on the function parameters in the second objective function, wherein the M drone devices are operated based on the target position information of the M drones.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining the position of a drone as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the position of the drone as described in any one of claims 1 to 7.

Images