Unmanned aerial vehicle inspection method, system and equipment and storage medium

Abstract

The invention provides an unmanned aerial vehicle inspection method, system and device and a storage medium, and relates to the technical field of unmanned aerial vehicle inspection, and the method comprises the steps: dividing a to-be-inspected fire region into a plurality of sub-regions, and determining the number of unmanned aerial vehicles required by each sub-region and a first inspection route according to the region area and the region feature of each sub-region; according to the fire behavior data of each sub-region, predicting a fire behavior spreading range of each sub-region in a preset duration, and determining a newly added to-be-inspected sub-region of each sub-region; determining a second inspection route of each unmanned aerial vehicle by combining the target region area and the target region feature of the newly added sub-region to be inspected and the residual electric quantity and the target position of each unmanned aerial vehicle; and sending the first inspection route and the second inspection route to each unmanned aerial vehicle, so that each unmanned aerial vehicle performs inspection according to the first inspection route and the second inspection route. The technical effect of the invention is that the monitoring requirement of dynamic spreading of forest fire can be effectively met.

Description

Technical Field

[0001] The present application relates to the field of drone inspection technology, and in particular to a drone inspection method, system, equipment and storage medium. Background Art

[0002] With the rapid development of drone technology, drones have been widely used in the field of forest fire monitoring. In practical applications, due to the large area of ​​the fire area and the complex and changeable fire spread, how to scientifically plan the inspection route of drones to achieve efficient monitoring of the fire area has become a technical problem that needs to be solved urgently.

[0003] At present, the commonly used drone inspection method is to pre-plan a fixed inspection route and let the drone perform periodic inspections along the preset route. Although this method can achieve basic monitoring of the fire area, it cannot adjust the inspection strategy in time according to the real-time changes in the fire. As a result, the drone may repeat inspections in areas where the fire is relatively stable, but lacks effective monitoring of newly spread areas of fire, resulting in an inability to effectively respond to the monitoring needs of the dynamic spread of forest fires. Summary of the invention

[0004] The present application provides an unmanned aerial vehicle inspection method, system, device and storage medium for effectively responding to the monitoring needs of the dynamic spread of forest fires.

[0005] In a first aspect, the present application provides a drone inspection method, the method comprising: dividing a fire area to be inspected into multiple sub-areas, determining the number of drones required for each sub-area and a first inspection route for the drones corresponding to each sub-area based on the area and characteristics of each sub-area; obtaining fire data for each sub-area, predicting the fire spread range of each sub-area within a preset time period based on the fire data, and determining newly added sub-areas to be inspected for each sub-area based on the fire spread range; obtaining the remaining power of each drone after inspection along the first inspection route, and the target position of each drone after inspection along the first inspection route; determining a second inspection route for each drone based on the target area and target area characteristics of the newly added sub-areas to be inspected, and the remaining power and target position of each drone; sending the first inspection route and the second inspection route to each drone so that each drone performs inspections along the first inspection route and the second inspection route.

[0006] By adopting the above technical solution, the fire area to be inspected is divided into multiple sub-areas and the number of drones is configured according to the characteristics of each sub-area. The fire spread range is predicted in combination with the fire data to determine the new sub-areas to be inspected. At the same time, the inspection route is dynamically adjusted considering the remaining power of the drone and the target position, so that the drone can inspect the newly added fire spread areas in a timely manner, avoiding repeated inspections in relatively stable fire areas, improving the utilization efficiency of drone inspection resources, and effectively responding to the monitoring needs of the dynamic spread of forest fires.

[0007] Optionally, the regional characteristics include terrain characteristics, vegetation coverage and weather characteristics, and the method of determining the number of drones required for each sub-area and the first inspection route of the drones corresponding to each sub-area based on the area and regional characteristics of each sub-area includes: determining a baseline number of drones for each sub-area based on the area of ​​each sub-area; determining a regional coefficient for each sub-area based on the terrain characteristics and the vegetation coverage; arithmetically multiplying the baseline number of drones for each sub-area by the corresponding regional coefficient to obtain the number of drones required for each sub-area; determining a feasible flight area for each sub-area based on the weather characteristics; and determining the first inspection route for the drones corresponding to each sub-area based on the feasible flight area of ​​each sub-area.

[0008] By adopting the above technical solution, the regional characteristics are refined into terrain characteristics, vegetation coverage and weather characteristics, and the benchmark number of drones is determined based on the regional area. The regional coefficient is determined and adjusted based on the terrain characteristics and vegetation coverage. At the same time, the feasible flight area is determined by considering the weather characteristics. This makes the configuration number of drones and the planning of inspection routes more in line with actual monitoring needs, thereby improving the rationality of drone inspection resource allocation and the feasibility of inspection route planning.

[0009] Optionally, determining the area coefficient of each sub-area according to the terrain features and the vegetation coverage rate includes: obtaining the terrain slope of each sub-area according to the terrain features, and obtaining the terrain coefficient corresponding to each sub-area from a preset terrain coefficient table according to the terrain slope, the terrain coefficient is positively correlated with the terrain slope; obtaining the vegetation coefficient corresponding to each sub-area from a preset vegetation coefficient table according to the vegetation coverage rate, and the vegetation coefficient is positively correlated with the vegetation coverage rate; arithmetically multiplying the terrain coefficient of each sub-area by a first weight coefficient to obtain a first coefficient; arithmetically multiplying the vegetation coefficient of each sub-area by a second weight coefficient to obtain a second coefficient; and arithmetically adding the first coefficient and the second coefficient to obtain the area coefficient of each sub-area.

[0010] By adopting the above technical solution, by combining the terrain slope and vegetation coverage, the corresponding coefficients are obtained from the preset terrain coefficient table and vegetation coefficient table respectively, and the regional coefficient is obtained by weighted calculation through the weight coefficient. The regional coefficient can more accurately reflect the influence of terrain and vegetation on the spread of fire, so that the number of drones configured is more in line with the actual monitoring difficulty of each sub-area, further improving the scientificity and rationality of drone inspection resource allocation.

[0011] Optionally, the fire data includes fire spread speed, fire spread direction and ambient wind speed data, and predicting the fire spread range of each sub-area within a preset time period based on the fire data, including: determining the real-time spread speed of each sub-area based on the fire spread speed and the ambient wind speed data; calculating the fire spread distance of each sub-area within the preset time period based on the real-time spread speed; taking the fire source point in each sub-area as the starting position and the fire spread distance as the radius, and determining the initial spread area of ​​the fire according to the fire spread direction; performing regional overlap detection on the initial spread area and the boundary of each sub-area, to determine the fire spread range of each sub-area within the preset time period.

[0012] By adopting the above technical solution, by comprehensively considering the fire spread speed, spread direction and environmental wind speed data, the real-time spread speed and fire spread distance are calculated, and the initial spread area is determined with the fire source as the starting position, and then the fire spread range is determined by regional overlap detection. This makes the prediction of the fire spread range more accurate, thereby better guiding the monitoring deployment of drones in newly added areas to be inspected, and improving the predictability and timeliness of fire monitoring.

[0013] Optionally, the second inspection route of each UAV is determined by combining the target area area and target area characteristics of the newly added sub-area to be inspected, and the remaining power and the target position of each UAV, including: determining the number of UAVs required for the newly added sub-area to be inspected based on the target area area and target area characteristics of the newly added sub-area to be inspected; determining the flightable distance of each UAV based on the remaining power of each UAV; taking the target position of each UAV as the starting point, determining the target flight area of ​​each UAV in each newly added sub-area to be inspected in combination with the position of the newly added sub-area to be inspected and the flightable distance of each UAV; and determining the second inspection route of each UAV within the target flight area of ​​each UAV based on the target area characteristics.

[0014] By adopting the above technical solution, the required number of drones is determined by combining the area and characteristics of the newly added sub-area to be inspected, and the flight distance is calculated according to the remaining power of the drone. The target flight area is determined with the current position of the drone as the starting point, and then the second inspection route is planned based on the characteristics of the target area. This realizes the rational use of the remaining resources of the drone, enables the drone to efficiently inspect the newly added area to be inspected within the range allowed by power, and improves the reliability and sustainability of the drone inspection mission.

[0015] Optionally, the method of determining the target flight area of ​​each drone in each newly added sub-area to be inspected by taking the target position of each drone as the starting point and combining the position of the newly added sub-area to be inspected and the flyable distance of each drone includes: taking the target position of each drone as the starting point coordinates of each drone; obtaining the center position coordinates of the newly added sub-area to be inspected; taking the distance between the starting point coordinates and the center position coordinates of each drone as the flight distance of each drone to reach the newly added sub-area to be inspected, and taking drones with a flyable distance greater than the flight distance as candidate drones; determining the flight radius of each candidate drone according to the starting point coordinates and the flyable distance of each candidate drone; dividing the flight coverage area of ​​each candidate drone with the starting point coordinates of each candidate drone as the center and the flight radius of each candidate drone as the radius; judging the overlapping area of ​​the flight coverage area of ​​each candidate drone and the newly added sub-area to be inspected, and determining the coverage area of ​​each candidate drone in the newly added sub-area to be inspected as the target flight area of ​​each candidate drone.

[0016] By adopting the above technical solution, the flight distance is calculated by taking the target position of the UAV as the starting point coordinate and combining it with the center position coordinate of the newly added sub-area to be inspected, and the candidate UAVs are screened based on the flyable distance. The coverage area is determined by the flight radius and the overlapping area is judged. The target flight area of ​​each candidate UAV not only meets its remaining power constraint, but also can achieve effective coverage of the newly added sub-area to be inspected, thereby ensuring the feasibility and coverage integrity of the UAV inspection task.

[0017] Optionally, after determining the second inspection route of each UAV within the target flight area of ​​each UAV according to the characteristics of the target area, the method further includes: if there is an uncovered sub-area to be inspected, additional UAVs are deployed according to the target area area and target area characteristics of the uncovered sub-area to be inspected, and the second inspection route of the additional UAVs is determined.

[0018] By adopting the above technical solution, by detecting the coverage of the newly added sub-areas to be inspected, additional drones are promptly deployed to the uncovered areas and the second inspection route is planned, thereby achieving comprehensive monitoring of the newly added sub-areas to be inspected, effectively avoiding the generation of monitoring blind spots, and further improving the monitoring integrity and reliability of the drone inspection system.

[0019] In a second aspect, the present application provides an inspection system for drones, the system comprising: a first determination module, a second determination module, an acquisition module, a combination module and an output module; wherein the first determination module is used to divide the fire area to be inspected into multiple sub-areas, and determine the number of drones required for each sub-area and the first inspection route of the drones corresponding to each sub-area according to the area and regional characteristics of each sub-area; the second determination module is used to obtain fire data of each sub-area, predict the fire spread range of each sub-area within a preset time length according to the fire data, and determine the number of drones required for each sub-area according to the fire spread range. The newly added sub-area to be inspected in the area; the acquisition module is used to obtain the remaining power of each UAV after inspection along the first inspection route, and the target position of each UAV after inspection along the first inspection route; the combination module is used to combine the target area area and target area characteristics of the newly added sub-area to be inspected, and the remaining power and target position of each UAV, to determine the second inspection route of each UAV; the output module is used to send the first inspection route and the second inspection route to each UAV, so that each UAV performs inspection along the first inspection route and the second inspection route.

[0020] In a third aspect, the present application provides an electronic device that adopts the following technical solution: it includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any of the above-mentioned drone inspection methods.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and execute any of the above-mentioned drone inspection methods.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: By dividing the fire area to be inspected into multiple sub-areas and configuring the number of drones according to the characteristics of each sub-area, the fire spread range is predicted based on the fire data to determine the new sub-areas to be inspected, and the inspection route is dynamically adjusted considering the remaining battery power of the drone and the target position. This allows the drone to inspect the newly added fire spread areas in a timely manner, avoiding repeated inspections in relatively stable fire areas, improving the utilization efficiency of drone inspection resources, and effectively responding to the monitoring needs of the dynamic spread of forest fires. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart of a drone inspection method provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of a drone inspection system provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0024] Description of reference numerals: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "illustrative", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "illustrative", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "illustrative", "for example" or "for example" is intended to present related concepts in a concrete way.

[0027] With the continuous increase of forest resources and the rapid development of urban construction in my country, the prevention and control of forest fires and urban fires are becoming increasingly severe. The traditional manual inspection method has problems such as low inspection efficiency, high personnel safety risks, and limited coverage. UAVs, with their mobility, flexibility, and rapid response, are playing an increasingly important role in the field of fire inspection. However, UAVs are still facing many challenges in the process of fire inspection: First, there is the problem of the number of UAVs allocated. Under complex terrain conditions and different fire conditions, how to reasonably allocate the number of UAVs to achieve the best inspection effect; second, the planning of inspection paths, which requires consideration of multiple influencing factors such as terrain, vegetation, and weather, while also taking into account the endurance of UAVs; third, the real-time monitoring and prediction of fires. The development and spread of fires are highly uncertain, and an accurate prediction model needs to be established to guide the inspection work; finally, there is the problem of multi-machine coordination. How can multiple UAVs cooperate efficiently to avoid repeated inspections and cover blind spots? These are all technical problems that need to be solved urgently. Therefore, it is of great practical significance and application value to develop an intelligent UAV inspection system that can automatically plan inspection paths, dynamically adjust inspection strategies, and realize multi-machine coordination.

[0028] The present invention proposes an intelligent UAV fire inspection method based on multi-parameter joint evaluation to address the above technical problems. This method realizes the intelligence and efficiency of UAV inspection by establishing a scientific evaluation system and an intelligent scheduling strategy, providing strong technical support for fire prevention and control.

[0029] Figure 1 FIG. 1 is a flow chart of a drone inspection method provided in an embodiment of the present application. Figure 1 As shown, the method includes S101-S105: S101, dividing the fire area to be inspected into multiple sub-areas, and determining the number of drones required for each sub-area and the first inspection route of the drones corresponding to each sub-area according to the area and characteristics of each sub-area.

[0030] When the present invention is specifically implemented, it is first necessary to divide the fire area to be inspected into multiple sub-areas. This division method can improve the inspection efficiency and realize the refined management of the area.

[0031] Specifically, a grid division method can be used to divide the fire area to be inspected into square grids of equal size, each grid as a sub-area, and the size of the grid can be adjusted according to the actual situation, for example, it can be set to 500 meters × 500 meters. After the division is completed, it is necessary to obtain the regional area and regional characteristics of each sub-area, where the regional characteristics include terrain characteristics, vegetation coverage and weather characteristics. The terrain characteristics can be obtained through the geographic information system, mainly including parameters such as terrain slope and terrain undulation. The vegetation coverage can be obtained through satellite remote sensing data, and the weather characteristics include meteorological parameters such as wind direction, wind speed, and visibility.

[0032] After obtaining these data, the benchmark number of drones is first determined based on the area of ​​each sub-area. Specifically, the area ratio method can be used, that is, one drone is equipped per square kilometer as a benchmark. Then, the regional coefficient is calculated based on the terrain characteristics and vegetation coverage rate to correct the benchmark number of drones. The regional coefficient is calculated by multiplying the terrain coefficient by the first weight coefficient to obtain the first coefficient, multiplying the vegetation coefficient by the second weight coefficient to obtain the second coefficient, and adding the first coefficient and the second coefficient to obtain the final regional coefficient. The terrain coefficient and the vegetation coefficient can be obtained from the pre-established coefficient comparison table, and the weight coefficient can be adjusted according to actual conditions.

[0033] The terrain coefficient is a technical parameter used to quantitatively evaluate the impact of terrain complexity on the difficulty of drone inspection. In the present invention, the terrain coefficient is mainly determined by the terrain slope. The greater the terrain slope, the greater the inspection difficulty and the more drones required. Specifically, a terrain coefficient table can be set. For example, when the terrain is flat (the slope is less than 5 degrees), the terrain coefficient is 1.0; when the terrain is a gentle slope (the slope is between 5-15 degrees), the terrain coefficient is 1.2; when the terrain is a steep slope (the slope is between 15-30 degrees), the terrain coefficient is 1.5; when the terrain is a rugged terrain (the slope is greater than 30 degrees), the terrain coefficient is 2.0. This setting method fully considers the impact of terrain undulations on drone flight, because in steep terrain areas, drones need to adjust their flight altitude and attitude more frequently, and at the same time avoid mountain obstructions, which not only increases energy consumption, but also prolongs the inspection time. Therefore, more drones need to be invested to ensure the inspection effect. The terrain coefficient is positively correlated with the slope, that is, the greater the slope, the greater the terrain coefficient. This relationship can be reflected by a preset terrain coefficient table, which can be adjusted and optimized according to the actual application scenario, thereby achieving accurate assessment of UAV resource requirements under different terrain conditions.

[0034] After determining the number of drones required for each sub-area, it is necessary to determine the feasible flight area for each sub-area based on weather characteristics. For example, it is necessary to avoid dangerous areas in windy weather and to lower the flight altitude when visibility is low. Finally, the first inspection route of each drone is planned within the feasible flight area. The improved ant colony algorithm can be used for path planning so that the inspection route can cover the entire sub-area while ensuring flight safety and efficiency. In this way, not only can each sub-area be reasonably allocated drone resources, but also the scientificity and feasibility of the inspection route can be ensured, thereby providing reliable data support for subsequent fire monitoring and disposal.

[0035] Based on the above embodiment, as an optional implementation, in S101, the regional characteristics include terrain characteristics, vegetation coverage and weather characteristics. According to the regional area and regional characteristics of each sub-region, the number of drones required for each sub-region is determined, and the first inspection route of the drone corresponding to each sub-region specifically includes S11-S15: S11, determining a baseline number of drones in each sub-area according to the area of ​​each sub-area.

[0036] S12, determining the regional coefficient of each sub-region according to the terrain characteristics and vegetation coverage.

[0037] In the process of forest fire monitoring, in order to accurately assess the fire risk and inspection difficulty of each sub-area, it is necessary to determine the regional coefficient based on the terrain characteristics and vegetation coverage. Taking a specific case as an example, assume that the fire area is divided into three sub-areas: sub-area 1, sub-area 2, and sub-area 3. For each sub-area, its terrain characteristics, including slope, altitude, and terrain undulation, need to be evaluated first. For example, sub-area 1 is a flat terrain with an average slope of 5 degrees and small terrain undulation; sub-area 2 is a hilly area with an average slope of 15 degrees and medium terrain undulation; sub-area 3 is a mountainous area with an average slope of 25 degrees and large terrain undulation. According to these terrain characteristics, the terrain coefficients are assigned respectively: the terrain coefficient of sub-area 1 is 1.0 (indicating a flat terrain), the terrain coefficient of sub-area 2 is 1.3 (indicating a relatively complex terrain), and the terrain coefficient of sub-area 3 is 1.6 (indicating a complex terrain).

[0038] At the same time, it is also necessary to evaluate the vegetation coverage of each sub-area. The vegetation coverage rate of sub-area 1 is 40%, mainly low shrubs; the vegetation coverage rate of sub-area 2 is 65%, mainly trees; the vegetation coverage rate of sub-area 3 is 85%, which is dense forest. Based on this, the vegetation coefficient is determined: the vegetation coefficient of sub-area 1 is 1.1 (sparse vegetation), the vegetation coefficient of sub-area 2 is 1.4 (medium vegetation), and the vegetation coefficient of sub-area 3 is 1.7 (dense vegetation).

[0039] Multiplying the terrain coefficient and the vegetation coefficient, we get the comprehensive regional coefficient of each sub-region: the regional coefficient of sub-region 1 is 1.1 (1.0×1.1), indicating that the inspection difficulty of this region is relatively low; the regional coefficient of sub-region 2 is 1.82 (1.3×1.4), indicating that the inspection difficulty is medium; the regional coefficient of sub-region 3 is 2.72 (1.6×1.7), indicating that the inspection difficulty is relatively high. This regional coefficient calculation method based on terrain characteristics and vegetation coverage can objectively reflect the actual situation of each sub-region.

[0040] Based on the above embodiment, as an optional implementation, in S12, determining the area coefficient of each sub-area according to the terrain characteristics and the vegetation coverage rate specifically includes S121-S124: S121, obtaining the terrain slope of each sub-area according to the terrain characteristics, and obtaining the terrain coefficient corresponding to each sub-area from a preset terrain coefficient table according to the terrain slope, wherein the terrain coefficient is positively correlated with the terrain slope.

[0041] S122, according to the vegetation coverage rate, obtaining the vegetation coefficient corresponding to each sub-area from a preset vegetation coefficient table, where the vegetation coefficient is positively correlated with the vegetation coverage rate.

[0042] S123, arithmetically multiplying the terrain coefficient of each sub-region by the first weight coefficient to obtain the first coefficient; arithmetically multiplying the vegetation coefficient of each sub-region by the second weight coefficient to obtain the second coefficient.

[0043] S124, arithmetically adding the first coefficient and the second coefficient to obtain a region coefficient of each sub-region.

[0044] When determining the regional coefficient of each sub-region, in order to make the calculation more scientific and accurate, a weight-based multi-factor evaluation method is adopted. Taking the three sub-regions as an example, the terrain characteristics need to be evaluated first. Through topographic mapping data, it is obtained that the average terrain slope of sub-region 1 is 5 degrees, the average terrain slope of sub-region 2 is 15 degrees, and the average terrain slope of sub-region 3 is 25 degrees. Referring to the preset terrain coefficient table, a slope of 0-10 degrees corresponds to a terrain coefficient of 1.0, a slope of 11-20 degrees corresponds to a terrain coefficient of 1.3, and a slope of 21-30 degrees corresponds to a terrain coefficient of 1.6. Based on this, the terrain coefficient of sub-region 1 is determined to be 1.0, the terrain coefficient of sub-region 2 is 1.3, and the terrain coefficient of sub-region 3 is 1.6. This corresponding relationship reflects the positive correlation between the terrain coefficient and the terrain slope.

[0045] Next, the vegetation coverage was evaluated. Through remote sensing data analysis, it was found that the vegetation coverage rate of sub-area 1 was 40%, the vegetation coverage rate of sub-area 2 was 65%, and the vegetation coverage rate of sub-area 3 was 85%. According to the preset vegetation coefficient table, the vegetation coverage rate of 30%-50% corresponds to a vegetation coefficient of 1.1, the vegetation coverage rate of 51%-70% corresponds to a vegetation coefficient of 1.4, and the vegetation coverage rate of 71%-90% corresponds to a vegetation coefficient of 1.7. Based on this, the vegetation coefficient of sub-area 1 was determined to be 1.1, the vegetation coefficient of sub-area 2 was 1.4, and the vegetation coefficient of sub-area 3 was 1.7, reflecting the positive correlation between the vegetation coefficient and the vegetation coverage rate.

[0046] Considering the different degrees of influence of terrain features and vegetation coverage on inspection difficulty, weight coefficients are introduced for weighted calculation. The first weight coefficient (terrain weight) is set to 0.6, and the second weight coefficient (vegetation weight) is set to 0.4. For sub-area 1, the terrain coefficient 1.0 is multiplied by the weight 0.6 to obtain the first coefficient 0.6, and the vegetation coefficient 1.1 is multiplied by the weight 0.4 to obtain the second coefficient 0.44; for sub-area 2, the terrain coefficient 1.3 is multiplied by the weight 0.6 to obtain the first coefficient 0.78, and the vegetation coefficient 1.4 is multiplied by the weight 0.4 to obtain the second coefficient 0.56; for sub-area 3, the terrain coefficient 1.6 is multiplied by the weight 0.6 to obtain the first coefficient 0.96, and the vegetation coefficient 1.7 is multiplied by the weight 0.4 to obtain the second coefficient 0.68.

[0047] Finally, the first coefficient and the second coefficient of each sub-area are added to obtain the final regional coefficient: the regional coefficient of sub-area 1 is 1.04 (0.6+0.44), indicating that the inspection difficulty in this area is relatively low; the regional coefficient of sub-area 2 is 1.34 (0.78+0.56), indicating that the inspection difficulty is medium; the regional coefficient of sub-area 3 is 1.64 (0.96+0.68), indicating that the inspection difficulty is relatively high.

[0048] S13, arithmetically multiplying the baseline number of drones in each sub-area by the corresponding regional coefficient to obtain the number of drones required in each sub-area.

[0049] S14, determining feasible flight areas for each sub-area according to weather characteristics.

[0050] S15, determining a first inspection route of the UAV corresponding to each sub-area according to the feasible flight area of ​​each sub-area.

[0051] After determining the regional coefficient of each sub-area, it is necessary to plan a suitable first inspection route for each sub-area to ensure that the drone can complete the inspection task safely and effectively. Taking the actual scenario of the three sub-areas as an example, it is necessary to first analyze the feasible flight area of ​​each sub-area. For sub-area 1 (regional coefficient 1.1), due to the flat terrain and sparse vegetation, its feasible flight area is large, and a relatively simple inspection route can be planned; for sub-area 2 (regional coefficient 1.82), affected by the hilly terrain and medium-density vegetation, it is necessary to consider the restrictions of terrain undulations on flight; and sub-area 3 (regional coefficient 2.72), due to the characteristics of mountainous terrain and dense forests, its feasible flight area is relatively limited, requiring more cautious route planning.

[0052] Based on these conditions, the system plans the first inspection route for sub-area 1 using the conventional "S" scanning method. Drone 1 starts from starting point A, cruises at a speed of 15 m / s, and performs inspections according to preset waypoints BCDE at a cruising altitude of 120 m. The waypoint spacing is set to 200 m, which can effectively cover the entire area. For sub-area 2, considering its undulating terrain, the first inspection route of drone 2 adopts an "improved S" route, that is, adding altitude changes on the basis of the conventional "S" route. Starting from starting point F, passing through waypoints GHIJ, the cruising speed is reduced to 12 m / s, and the cruising altitude is dynamically adjusted between 120 m and 150 m to adapt to terrain changes. The waypoint spacing is reduced to 150 m to ensure monitoring accuracy. For the complex sub-area 3, the first inspection route of UAV 3 adopts an "adaptive S" design, starting from the starting point K and passing through the waypoint LMNO. It not only needs to dynamically adjust the flight altitude (120 meters to 180 meters) according to the terrain undulations, but also needs to reduce the cruising speed to 10 meters / second and further reduce the distance between waypoints to 100 meters to ensure the inspection effect in complex environments.

[0053] S102, obtaining fire data of each sub-area, predicting the fire spread range of each sub-area within a preset time period based on the fire data, and determining new sub-areas to be inspected in each sub-area based on the fire spread range.

[0054] Fire has the characteristics of dynamic development. In order to timely predict the fire spread trend and respond, the present invention needs to obtain the fire data of each sub-area, which includes the fire spread speed, fire spread direction and environmental wind speed data. Among them, the fire spread speed can be obtained by monitoring the temperature change of the fire scene through the infrared thermal imaging equipment carried by the drone, the fire spread direction can be determined by analyzing the heat distribution change trend of continuous multi-frame thermal imaging images, and the environmental wind speed data can be collected in real time through the meteorological sensor carried by the drone.

[0055] After obtaining the above data, it is first necessary to determine the real-time spread speed based on the fire spread speed and the ambient wind speed data. The specific calculation method is to multiply the basic spread speed by the wind speed gain coefficient, where the wind speed gain coefficient increases with the increase of wind speed. For example, when the wind speed is less than 3 meters per second, the gain coefficient is 1.0, and the gain coefficient increases by 0.2 for every 2 meters per second increase in wind speed. After determining the real-time spread speed, multiply it by the preset time length to obtain the fire spread distance. The preset time length can be set according to actual needs, usually 30 minutes to 2 hours. Next, take the fire source point in each sub-area as the starting position, take the fire spread distance as the radius, and determine the initial spread area of ​​the fire according to the direction of fire spread. The initial spread area is usually distributed in a fan shape, and the size of the central angle of the fan is related to the stability of the wind direction. Then, the initial spread area and the boundaries of each sub-area are subjected to regional overlap detection. The overlap detection adopts a polygon intersection algorithm. By calculating the intersection of the initial spread area and the sub-area boundary, the fire spread range of each sub-area within the preset time length can be accurately determined. Finally, the predicted fire spread range is compared with the existing inspection area. If the spread range exceeds the existing inspection area, the exceeding part will be determined as a new sub-area to be inspected.

[0056] Based on the above embodiment, as an optional implementation, in S102, the fire data includes fire spread speed, fire spread direction and ambient wind speed data. According to the fire data, predicting the fire spread range of each sub-area within a preset time period specifically includes S21-S24: S21, determining the real-time spread speed of each sub-area according to the fire spread speed and the ambient wind speed data.

[0057] In the process of forest fire monitoring, in order to accurately predict the development trend of the fire, it is necessary to first determine the real-time spread speed of each sub-area. Taking the three sub-areas as an example, the thermal imaging data obtained by the drone shows that the initial fire spread speed of sub-area 1 is 0.5 m / s, the initial fire spread speed of sub-area 2 is 0.8 m / s, and the initial fire spread speed of sub-area 3 is 1.2 m / s. At the same time, the environmental wind speed data provided by the meteorological station shows that the wind speed of sub-area 1 is 3 m / s, and the angle between the wind direction and the fire spread direction is 30 degrees; the wind speed of sub-area 2 is 4 m / s, and the angle between the wind direction and the fire spread direction is 45 degrees; the wind speed of sub-area 3 is 5 m / s, and the angle between the wind direction and the fire spread direction is 60 degrees.

[0058] In order to calculate the real-time spread speed, it is necessary to consider the boosting effect of wind speed on the spread of fire. According to the angle between the wind direction and the direction of fire spread, the cosine function is used to calculate the component of wind speed in the direction of fire spread. For sub-area 1, the component of wind speed in the direction of fire spread is 3×cos(30°)=2.6 m / s; for sub-area 2, the wind speed component is 4×cos(45°)=2.8 m / s; for sub-area 3, the wind speed component is 5×cos(60°)=2.5 m / s. According to the fire dynamics model, for every increase of 1 m / s in wind speed, the fire spread speed increases by 20%. Therefore, the real-time spreading speed of each sub-area is calculated as follows: the real-time spreading speed of sub-area 1 is 0.5×(1+2.6×0.2)=0.76 m / s, the real-time spreading speed of sub-area 2 is 0.8×(1+2.8×0.2)=1.25 m / s, and the real-time spreading speed of sub-area 3 is 1.2×(1+2.5×0.2)=1.80 m / s.

[0059] S22, calculating the fire spread distance of each sub-area within a preset time period according to the real-time spread speed.

[0060] After determining the real-time spread speed of each sub-area, it is necessary to calculate the fire spread distance within the preset time length to predict the scope of fire development. Taking three sub-areas as an example, the preset time length is set to 30 minutes (1800 seconds). Based on the real-time spread speed calculated above, sub-area 1 is 0.76 m / s, sub-area 2 is 1.25 m / s, and sub-area 3 is 1.80 m / s. Since the fire spread speed will change over time, it is necessary to consider the attenuation effect of terrain and vegetation factors on the spread speed.

[0061] The speed attenuation coefficient is introduced for correction, which is related to the previously calculated regional coefficient. The regional coefficient of sub-region 1 is 1.04, and the corresponding speed attenuation coefficient is 0.95 (indicating a 5% decrease in speed every 10 minutes); the regional coefficient of sub-region 2 is 1.34, and the corresponding speed attenuation coefficient is 0.90 (indicating a 10% decrease in speed every 10 minutes); the regional coefficient of sub-region 3 is 1.64, and the corresponding speed attenuation coefficient is 0.85 (indicating a 15% decrease in speed every 10 minutes). The preset time is divided into three 10-minute periods for calculation, and the average speed of each period is the product of the speed of the previous period and the attenuation coefficient.

[0062] For sub-area 1, the average speed in the first 10 minutes (600 seconds) was 0.76 m / s, and the spread distance was 456 m (0.76×600); the average speed in the second 10 minutes was 0.722 m / s (0.76×0.95), and the spread distance was 433.2 m; the average speed in the third 10 minutes was 0.686 m / s (0.722×0.95), and the spread distance was 411.6 m. The total spread distance was 1300.8 m (456+433.2+411.6).

[0063] For sub-area 2, the average speed in the first 10 minutes was 1.25 m / s, and the spreading distance was 750 m; the average speed in the second 10 minutes was 1.125 m / s (1.25×0.90), and the spreading distance was 675 m; the average speed in the third 10 minutes was 1.013 m / s (1.125×0.90), and the spreading distance was 607.8 m. The total spreading distance was 2032.8 m.

[0064] For sub-area 3, the average speed in the first 10 minutes was 1.80 m / s, and the spreading distance was 1080 m; the average speed in the second 10 minutes was 1.53 m / s (1.80×0.85), and the spreading distance was 918 m; the average speed in the third 10 minutes was 1.30 m / s (1.53×0.85), and the spreading distance was 780 m. The total spreading distance was 2778 m.

[0065] After determining the real-time spread speed of each sub-area, it is necessary to calculate the fire spread distance within the preset time in order to evaluate the fire spread range. Considering the complexity of the actual fire situation, in addition to the theoretical calculation based on the real-time spread speed, it is also necessary to consider the inhibitory effect of firefighting and rescue operations on the spread of fire. Taking the preset time of 30 minutes (1800 seconds) as an example, under the ideal condition of not considering firefighting and rescue, based on the real-time spread speed calculated above, the theoretical spread distance of sub-area 1 is 1368 meters (0.76 meters / second × 1800 seconds), the theoretical spread distance of sub-area 2 is 2250 meters (1.25 meters / second × 1800 seconds), and the theoretical spread distance of sub-area 3 is 3240 meters (1.80 meters / second × 1800 seconds).

[0066] However, considering that the fire brigade has already started the firefighting operation, it is necessary to introduce the fire suppression coefficient to correct the spread distance. According to the deployment of the fire brigade, there are 2 fire brigades in sub-area 1 to extinguish the fire, and its fire suppression coefficient is determined to be 0.6 (indicating that the fire spread rate is reduced by 40%); there is 1 fire brigade in sub-area 2 to extinguish the fire, and the fire suppression coefficient is 0.8 (indicating that the fire spread rate is reduced by 20%); sub-area 3 has not yet deployed firefighting forces due to the complex terrain, and the fire suppression coefficient is 1.0 (indicating no suppression effect). Therefore, after considering the fire rescue factors, the actual fire spread distance of each sub-area within the preset time is: the actual spread distance of sub-area 1 is 820.8 meters (1368 meters × 0.6), the actual spread distance of sub-area 2 is 1800 meters (2250 meters × 0.8), and the actual spread distance of sub-area 3 is still 3240 meters.

[0067] S23, taking the fire source point in each sub-area as the starting position and the fire spread distance as the radius, determine the initial fire spread area according to the fire spread direction.

[0068] S24, performing a region overlap detection on the boundaries of the initial spreading region and each sub-region to determine the fire spreading range of each sub-region within a preset time period.

[0069] After obtaining the fire spread distance of each sub-area, it is necessary to determine the specific fire spread range, which is of great significance for accurately assessing the development trend of the fire and formulating prevention and control measures. Taking the three sub-areas as an example, it is necessary to first determine the initial spread area of ​​the fire. According to the data obtained by the drone thermal imaging system, the location of the fire source in sub-area 1 is the coordinate (X1, Y1), the fire spread direction is 30 degrees east by north, and the spread distance is 820.8 meters; the location of the fire source in sub-area 2 is the coordinate (X2, Y2), the fire spread direction is 45 degrees east by south, and the spread distance is 1800 meters; the location of the fire source in sub-area 3 is the coordinate (X3, Y3), the fire spread direction is 60 degrees east by north, and the spread distance is 3240 meters.

[0070] Based on these data, a fan-shaped area model is used to simulate the spread of fire. Considering the influence of wind direction on the spread of fire, the fan-shaped diffusion angle is set to a range of 120 degrees with the main spread direction as the center line (i.e., 60 degrees on both sides of the main direction). For sub-area 1, with the fire source point (X1, Y1) as the center, 820.8 meters as the radius, and 30 degrees east of the north as the center line, a 120-degree fan-shaped area is drawn as the initial spread area A1; for sub-area 2, with the fire source point (X2, Y2) as the center, 1800 meters as the radius, and 45 degrees east of the south as the center line, a 120-degree fan-shaped area is drawn as the initial spread area A2; for sub-area 3, with the fire source point (X3, Y3) as the center, 3240 meters as the radius, and 60 degrees east of the north as the center line, a 120-degree fan-shaped area is drawn as the initial spread area A3.

[0071] Then, it is necessary to perform regional overlap detection and compare the initial spread area with the boundaries of each sub-area. Through the spatial analysis function of the geographic information system, the part of the initial spread area that exceeds the sub-area boundary can be identified. For sub-area 1, its initial spread area A1 has a 10% overlap with sub-area 2, and the overlapping part needs to be included in the fire spread range of sub-area 2; for sub-area 2, its initial spread area A2 has a 15% and 20% overlap with sub-area 1 and sub-area 3 respectively, and these overlapping parts need to be included in the fire spread range of the corresponding sub-area; for sub-area 3, its initial spread area A3 has a 25% overlap with sub-area 2, and this part also needs to be included in the fire spread range of sub-area 2.

[0072] S103, obtaining the remaining power of each drone after inspection along the first inspection route, and the target position of each drone after inspection along the first inspection route.

[0073] In order to ensure that the drones can continuously perform inspection tasks and realize reasonable scheduling of resources, the present invention needs to grasp the remaining power and location information of each drone in real time.

[0074] Specifically, the remaining battery power data is obtained through the power monitoring module carried by the drone. The module can monitor the battery voltage, current, temperature and other parameters in real time, and calculate the precise remaining power percentage based on these parameters. At the same time, the target position coordinates after completing the first inspection route are obtained through the drone's positioning system. The positioning system uses multi-mode satellite positioning technologies such as GPS and Beidou combined with an inertial navigation system to ensure positioning accuracy and reliability.

[0075] In the process of obtaining this data, the drone transmits the power information and location information to the ground control station in real time through the data link, and the control station processes and stores the received data. The calculation of the remaining power needs to take into account the actual capacity and discharge characteristics of the battery. For example, when the ambient temperature is low, the effective capacity of the battery will decrease accordingly, so it is necessary to introduce a temperature compensation coefficient to correct the remaining power. The target position is represented by three-dimensional coordinates, including longitude, latitude and altitude. This location information will be used for the subsequent second inspection route planning. In addition, the cumulative flight time and flight distance of each drone need to be recorded. These data can be used to evaluate the workload of the drone and predict the remaining executable tasks.

[0076] By keeping track of the remaining battery power and target location information of the drone in real time, accidents caused by running out of battery can be effectively prevented. This can also provide important decision-making basis for subsequent task allocation, thus improving the safety and reliability of the entire inspection system.

[0077] S104, determining a second inspection route for each drone based on the target area and target area characteristics of the newly added sub-area to be inspected, the remaining power of each drone, and the target position.

[0078] During the fire spread, in order to ensure effective monitoring of the newly added sub-areas to be inspected, it is necessary to formulate a second inspection route based on the regional characteristics and the drone status.

[0079] Specifically, it is necessary to first evaluate the inspection demand of the newly added sub-area to be inspected, which is mainly determined by the area of ​​the target area and the characteristics of the target area. The characteristics of the target area include terrain coefficient, vegetation coverage rate and meteorological conditions. The terrain coefficient reflects the complexity of the terrain, the vegetation coverage rate indicates the density of the vegetation, and the meteorological conditions include environmental factors such as wind speed and visibility. For example, when the area of ​​the newly added sub-area to be inspected is 2 square kilometers, the terrain coefficient is 1.2 (indicated as a gentle slope terrain), the vegetation coverage rate is 60%, and the wind speed is 4 meters per second, these characteristics jointly determine the inspection difficulty and the required inspection resources of the area. Next, it is necessary to evaluate the availability of each drone, mainly considering two key indicators: remaining power and target location. The remaining power directly determines whether the drone has sufficient capacity to complete the new inspection task, and the target location affects the time and energy consumption required for the drone to reach the newly added area. In actual operation, a minimum remaining power threshold can be set, such as 40%, and only drones exceeding this threshold will be considered for inspection tasks in the newly added area. At the same time, the distance between the drone and the newly added area will also affect whether it is suitable for the mission. Usually, drones that are closer will be given priority to reduce energy loss. Based on the above evaluation results, a second inspection route is planned for each qualified drone. The route needs to cover the key locations of the newly added sub-areas to be inspected and ensure that the drone has enough power to complete the mission and return safely.

[0080] When a new sub-area to be inspected appears during the spread of the fire, a reasonable second inspection route needs to be formulated. Taking a specific example, suppose a new sub-area A to be inspected is added, and the target area is 1.5 square kilometers. The characteristics of the target area include: the terrain is a hilly area (topography coefficient 1.3), the vegetation coverage rate is 70% (relatively dense), the current wind speed is 5 meters per second (high), and the visibility is 8 kilometers (good). Under such terrain and vegetation conditions, more intensive inspection routes are required to ensure the monitoring effect.

[0081] At the same time, the system shows that 3 drones have completed the first inspection route. Among them, the remaining power of drone 1 is 65%, and its target location is about 1.2 kilometers away from the newly added area A; the remaining power of drone 2 is 45%, and it is about 3 kilometers away from the newly added area A; the remaining power of drone 3 is 75%, and it is about 2 kilometers away from the newly added area A. Considering the power consumption required to fly from the current position to the newly added area A (about 3% power consumption per kilometer), it is estimated that 30% of power will be consumed for inspection in the newly added area A (taking into account the influence of terrain coefficient and vegetation coverage), and 15% of power needs to be reserved for safe return.

[0082] According to the above conditions, it can be determined that UAV 1 and UAV 3 are suitable for the inspection mission of the newly added area A: although UAV 1 has less remaining power than UAV 3, it is the closest, and it only needs to consume about 4% of power to fly to the newly added area, plus 30% for inspection and 15% for safe return, a total of 49% power is required, and its 65% remaining power fully meets the requirements; although UAV 3 is farther away and needs to consume about 6% of power to reach the target area, its 75% remaining power is the most sufficient and is very suitable for performing this mission. The 45% remaining power of UAV 2 is lower than the safety threshold (50%), and it needs to return to charge first.

[0083] Based on this, the second inspection route was planned: Since the newly added area was large and densely vegetated, UAV 1 and UAV 3 were arranged to complete the inspection together. UAV 1 was responsible for the southern part of the area, and UAV 3 was responsible for the northern part of the area. The two UAVs maintained an inspection distance of 200 meters. Considering the wind speed of 5 meters per second, the flight speed was appropriately reduced in the headwind section to maintain stability. This route planning based on actual conditions not only ensures the integrity of the inspection coverage, but also fully considers the capacity limitations of each UAV, and can effectively complete the monitoring tasks of the newly added area.

[0084] Based on the above embodiment, as an optional implementation, in S104, combining the target area and target area characteristics of the newly added sub-area to be inspected, and the remaining power and target position of each drone, determining the second inspection route of each drone specifically includes S41-S44: S41, determining the number of drones required for the newly added sub-area to be inspected according to the target area area and target area characteristics of the newly added sub-area to be inspected.

[0085] S42, determining the flight distance of each drone according to the remaining power of each drone.

[0086] S43, taking the target position of each drone as the starting point, combining the position of the newly added sub-area to be inspected and the flyable distance of each drone, determining the target flight area of ​​each drone in each newly added sub-area to be inspected.

[0087] In the process of dynamic fire monitoring, in order to efficiently use drone resources to cover the newly added sub-areas to be inspected, it is necessary to reasonably divide the target flight area according to the current status of each drone. Take two drones covering three newly added sub-areas to be inspected as an example. Assume that drone 1 is currently located at coordinates (X1, Y1) with a remaining flight distance of 8,000 meters, and drone 2 is currently located at coordinates (X2, Y2) with a remaining flight distance of 6,000 meters. The center position of the newly added sub-area A to be inspected is the coordinates (XA, YA), with an area of ​​4 square kilometers; the center position of sub-area B is the coordinates (XB, YB), with an area of ​​3 square kilometers; the center position of sub-area C is the coordinates (XC, YC), with an area of ​​5 square kilometers.

[0088] First, we need to calculate the straight-line distance from each drone to the center point of each sub-area to be inspected. Using the Euclidean distance formula, we can calculate that the distance from drone 1 to sub-area A is 2000 meters, the distance to sub-area B is 3500 meters, and the distance to sub-area C is 4000 meters; the distance from drone 2 to sub-area A is 3000 meters, the distance to sub-area B is 2500 meters, and the distance to sub-area C is 3500 meters. Considering that drones need to be able to fly back and forth during the inspection process, the actual flight distance that can be used for inspection should be half of the remaining flight distance, that is, the effective inspection radius of drone 1 is 4000 meters, and the effective inspection radius of drone 2 is 3000 meters.

[0089] Based on the distance calculation results and the performance limitations of the drones, the target flight area of ​​each drone is determined by the principle of nearest allocation. For drone 1, since it has the shortest distance to sub-area A (2000 meters) and is within the effective inspection radius (4000 meters), the 2.5 square kilometers in the north of sub-area A is divided into the target flight area of ​​drone 1; at the same time, considering that its remaining flight capacity is still sufficient, it can cover the 2 square kilometers in the east of sub-area C. For drone 2, it has the shortest distance to sub-area B (2500 meters) and is within the effective inspection radius (3000 meters), so the entire 3 square kilometers of sub-area B and the 1.5 square kilometers in the south of sub-area A are divided into the target flight area of ​​drone 2. The remaining 3 square kilometers of sub-area C will be covered by drone 1 after completing the inspection of sub-area A.

[0090] Based on the above embodiment, as an optional implementation, in S43, taking the target position of each drone as the starting point, combining the position of the newly added sub-area to be inspected and the flyable distance of each drone, determining the target flight area of ​​each drone in each newly added sub-area to be inspected specifically includes S431-S436: S431, taking the target position of each UAV as the starting point coordinate of each UAV.

[0091] S432, obtaining the center position coordinates of the newly added sub-area to be inspected.

[0092] S433, taking the distance between the starting point coordinates and the center position coordinates of each drone as the flight distance of each drone to reach the newly added sub-area to be inspected, and taking the drones whose flight distance is greater than the flight distance as candidate drones.

[0093] S434, determining the flight radius of each candidate UAV according to the starting point coordinates and the flyable distance of each candidate UAV.

[0094] S435 , dividing the flight coverage area of ​​each candidate UAV by taking the starting point coordinates of each candidate UAV as the center of the circle and the flight radius of each candidate UAV as the radius.

[0095] S436, determining the overlapping area between the flight coverage area of ​​each candidate UAV and the newly added sub-area to be inspected, and determining the coverage area of ​​each candidate UAV in the newly added sub-area to be inspected as the target flight area of ​​each candidate UAV.

[0096] In the process of fire monitoring, in order to scientifically and reasonably allocate UAV inspection resources, a series of precise spatial calculations are required to determine the target flight area of ​​each UAV. Taking three UAVs covering two newly added sub-areas to be inspected as an example, the starting point coordinates of each UAV need to be determined first: UAV 1 is currently located at coordinates (1000, 2000) and can fly a distance of 10,000 meters; UAV 2 is currently located at coordinates (2000, 3000) and can fly a distance of 8,000 meters; UAV 3 is currently located at coordinates (3000, 4000) and can fly a distance of 6,000 meters.

[0097] The center coordinates of the newly added sub-areas to be inspected are obtained through the positioning system carried by the drone: the center coordinates of sub-area D are (4000, 5000), with an area of ​​6 square kilometers; the center coordinates of sub-area E are (5000, 6000), with an area of ​​4 square kilometers. In order to determine which drones are suitable for performing inspection tasks, it is necessary to calculate the flight distance of each drone from the starting point to the sub-area to be inspected. Using the Euclidean distance formula, it is calculated that the distance from drone 1 to sub-area D is 4242 meters, and the distance to sub-area E is 5657 meters; the distance from drone 2 to sub-area D is 3606 meters, and the distance to sub-area E is 5000 meters; the distance from drone 3 to sub-area D is 2236 meters, and the distance to sub-area E is 3606 meters.

[0098] The flyable distance of each drone is compared with the calculated flight distance to determine the candidate drones: for sub-area D, the flyable distances of the three drones are all greater than the required flight distance, so they can all be used as candidate drones; for sub-area E, the flyable distances of drone 1 and drone 2 are greater than the required flight distance, while the flyable distance of drone 3 is less than the required flight distance, so only drone 1 and drone 2 can be used as candidate drones.

[0099] Considering that the drone needs to ensure the ability to fly back and forth during the inspection process, half of the flight distance of each candidate drone is used as its flight radius: the flight radius of drone 1 is 5000 meters, the flight radius of drone 2 is 4000 meters, and the flight radius of drone 3 is 3000 meters. The starting point coordinates of each candidate drone are used as the center of the circle and the flight radius is used as the radius to define the flight coverage area. In this way, multiple circular theoretical coverage ranges can be formed: a circular area A1 with a center of (1000, 2000) and a radius of 5000 meters; a circular area A2 with a center of (2000, 3000) and a radius of 4000 meters; a circular area A3 with a center of (3000, 4000) and a radius of 3000 meters.

[0100] The overlapping areas of these circular coverage areas and the sub-areas to be inspected are judged to determine the actual target flight areas of each drone. For sub-area D, the overlapping area of ​​drone 1's coverage area A1 is 3 square kilometers, the overlapping area of ​​drone 2's coverage area A2 is 2 square kilometers, and the overlapping area of ​​drone 3's coverage area A3 is 1 square kilometer. For sub-area E, the overlapping area of ​​drone 1's coverage area A1 is 2.5 square kilometers, and the overlapping area of ​​drone 2's coverage area A2 is 1.5 square kilometers.

[0101] S44, within the target flight area of ​​each UAV, determine a second inspection route for each UAV according to the characteristics of the target area.

[0102] After determining the second inspection route of each UAV according to the characteristics of the target area within the target flight area of ​​each UAV, the method also includes: if there is an uncovered new sub-area to be inspected, additional UAVs are deployed according to the target area area and target area characteristics of the uncovered new sub-area to be inspected, and the second inspection route of the additional UAVs is determined.

[0103] In the process of dynamic fire monitoring, in order to ensure that the newly added sub-areas to be inspected are fully covered, it is necessary to conduct additional monitoring of the areas not covered by the existing drones. Based on the above embodiment, it is assumed that after the task allocation of the existing drones is completed, there is still an area of ​​2 square kilometers in sub-area D that is not covered (located in the northeast of the area, the terrain is a hilly area), and there is still an area of ​​1 square kilometer in sub-area E that is not covered (located in the southwest of the area, the terrain is a plain area).

[0104] In order to effectively monitor these uncovered areas, the system deploys additional drone resources from the backup drone library. Considering that the terrain characteristics of the uncovered part of sub-area D are hilly, it is necessary to deploy drone 4 with a strong power system (currently located at coordinates (6000,7000) with a flight range of 5000 meters). This drone has strong climbing ability and wind resistance. The uncovered part of sub-area E has flat terrain, so drone 5 with standard configuration (currently located at coordinates (7000,8000) with a flight range of 4000 meters) can be deployed for monitoring.

[0105] For UAV 4, considering the terrain characteristics of the hilly area, a zigzag inspection route is adopted to increase the monitoring density: starting from its current position (6000,7000), it first flies to the northwest corner of the uncovered area of ​​sub-area D, and then flies back and forth in the east-west direction at intervals of 500 meters, gradually advancing to the south to ensure full coverage of the hilly area. This inspection route design can help UAV 4 maintain stable flight in complex terrain and improve monitoring accuracy.

[0106] For UAV 5, since the terrain of the monitored area is flat, a spiral inspection route is adopted: starting from its current position (7000, 8000), it first flies to the geometric center of the uncovered area of ​​sub-area E, and then performs a spiral scan with this point as the center, and the spiral radius gradually increases until the entire unmonitored area is covered. This inspection route can ensure that UAV 5 achieves uniform coverage on flat terrain and improve monitoring efficiency.

[0107] S105, sending the first inspection route and the second inspection route to each drone, so that each drone performs inspection according to the first inspection route and the second inspection route.

[0108] In order to ensure that each drone can accurately perform the inspection task, the planned first inspection route and second inspection route need to be sent to each drone in a timely manner.

[0109] Taking the actual application scenario as an example, the ground control station sends the inspection route information to each drone through the data link. Each inspection route contains complete flight parameters: waypoint coordinate sequence, flight altitude, flight speed, etc. For example, the first inspection route of drone 1 contains the waypoint sequence from the take-off point to the first target area, the flight altitude is maintained at 100 meters, and the cruising speed is set to 15 meters / second; after executing the first inspection route, drone 1 needs to execute the second inspection route. At this time, the system has sent the new waypoint sequence and adjusted flight parameters to drone 1. Similarly, other drones will also receive their own inspection route information.

[0110] In the process of sending route information, a segmented sending strategy is adopted, that is, the first inspection route is sent first, and the second inspection route is sent after the drone confirms receipt and starts execution, so as to ensure the reliability of data transmission. After each route information is sent, the drone will return confirmation information, including the integrity check result of the route data. Once a data transmission error is found, the system will automatically resend it until it is ensured that the drone correctly receives all route information. Through this reliable route information transmission mechanism, each drone can perform inspection tasks in an orderly manner according to the predetermined plan, and realize continuous and effective monitoring of the fire area.

[0111] For example, after a forest fire occurs, three drones are deployed to perform inspection tasks. First, the ground control station needs to send the first inspection route to each drone. Taking drone 1 as an example, its first inspection route contains the following specific information: starting from take-off point A, passing through waypoints B, C, and D in sequence, and finally reaching target area E, with the cruising altitude set to 120 meters and the cruising speed set to 15 meters per second. Similarly, drone 2 and drone 3 also received the corresponding first inspection route information.

[0112] During the execution of the first inspection route, the fire spread and the system planned a second inspection route. At this time, the ground control station sent the second inspection route information of UAV 1: starting from the current position E, passing through the newly added waypoints F and G, and arriving at the newly added sub-area to be inspected H. Considering the wind speed of 5 meters / second at that time, the cruising speed was adjusted to 12 meters / second, and the original cruising altitude was maintained at 120 meters.

[0113] During the transmission process, the ground control station adopts a segmented transmission strategy. For example, when sending the first inspection route of UAV 1, the route segment from take-off point A to waypoint B is sent first, and after receiving the confirmation information returned by UAV 1, the subsequent route segments are sent. If there is an error in the data transmission of a route segment (for example, the data packet verification of waypoint C fails), the system will immediately resend the data segment to ensure that the UAV obtains accurate route information.

[0114] The same method is also applicable to the sending of the second inspection route. When UAV 1 completes the first inspection route and arrives at point E, the system starts sending the second inspection route. Every time a new route data is sent, it will wait for UAV 1 to return confirmation information to ensure the accuracy of data transmission. This sending mechanism ensures that the UAV can accurately receive and execute all the scheduled inspection routes, and realize continuous and effective monitoring of the fire scene and the newly added areas.

[0115] Based on the above method, the present application also discloses a drone inspection system, such as Figure 2 As shown, Figure 2 : is a structural diagram of a drone inspection system provided by an embodiment of the present application, the system includes: a first determination module, a second determination module, an acquisition module, a combination module and an output module; wherein, The first determination module is used to divide the fire area to be inspected into multiple sub-areas, and determine the number of drones required for each sub-area and the first inspection route of the drones corresponding to each sub-area according to the area and characteristics of each sub-area; the second determination module is used to obtain the fire data of each sub-area, and predict the fire spread range of each sub-area within a preset time period according to the fire data, and determine the newly added sub-areas to be inspected in each sub-area according to the fire spread range; the acquisition module is used to obtain the remaining power of each drone after inspection along the first inspection route, and the target position of each drone after inspection along the first inspection route; the combination module is used to determine the second inspection route of each drone by combining the target area and target area characteristics of the newly added sub-area to be inspected, and the remaining power and target position of each drone; the output module is used to send the first inspection route and the second inspection route to each drone, so that each drone conducts inspection according to the first inspection route and the second inspection route.

[0116] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0117] See also Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0118] The communication bus 1002 is used to realize the connection and communication between these components.

[0119] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0120] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0121] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0122] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally also be at least one storage device located away from the aforementioned processor 1001. As Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for an unmanned aerial vehicle inspection method.

[0123] exist Figure 3 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call an application program for a drone inspection method stored in the memory 1005. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0124] An electronic device readable storage medium stores instructions, which, when executed by one or more processors, enable the electronic device to execute one or more of the methods described in the above embodiments.

[0125] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0126] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0131] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A drone inspection method, characterized in that: The method comprises: Divide the fire area to be inspected into multiple sub-areas, and determine the number of drones required for each sub-area and the first inspection route of the drones corresponding to each sub-area according to the area and characteristics of each sub-area; Obtaining fire data of each of the sub-areas, predicting the fire spread range of each of the sub-areas within a preset time period based on the fire data, and determining a newly added sub-area to be inspected in each of the sub-areas based on the fire spread range; Obtaining the remaining power of each drone after inspection along the first inspection route, and the target position of each drone after inspection along the first inspection route; Determine a second inspection route for each drone based on the target area and target area characteristics of the newly added sub-area to be inspected, the remaining power of each drone, and the target position; The first inspection route and the second inspection route are sent to each of the drones, so that each of the drones performs inspections according to the first inspection route and the second inspection route.

2. The inspection method of a drone according to claim 1, characterized in that: The regional characteristics include terrain characteristics, vegetation coverage and weather characteristics. The number of drones required for each sub-region and the first inspection route of the drones corresponding to each sub-region are determined according to the regional area and regional characteristics of each sub-region, including: Determine the number of baseline drones in each of the sub-areas according to the area of ​​each of the sub-areas; Determining a regional coefficient of each of the sub-regions according to the terrain features and the vegetation coverage rate; Arithmetically multiplying the reference number of drones in each sub-area by the corresponding regional coefficient to obtain the number of drones required in each sub-area; Determining feasible flight areas for each of the sub-areas according to the weather characteristics; According to the feasible flight area of ​​each sub-area, a first inspection route of the drone corresponding to each sub-area is determined.

3. The inspection method of a drone according to claim 2, characterized in that: The determining of the area coefficient of each sub-area according to the terrain characteristics and the vegetation coverage rate includes: According to the terrain features, the terrain slope of each sub-area is obtained, and according to the terrain slope, the terrain coefficient corresponding to each sub-area is obtained from a preset terrain coefficient table, wherein the terrain coefficient is positively correlated with the terrain slope; According to the vegetation coverage rate, a vegetation coefficient corresponding to each of the sub-areas is obtained from a preset vegetation coefficient table, wherein the vegetation coefficient is positively correlated with the vegetation coverage rate; Arithmetically multiplying the terrain coefficient of each sub-area by a first weight coefficient to obtain a first coefficient; Arithmetically multiplying the vegetation coefficient of each sub-area by a second weight coefficient to obtain a second coefficient; The first coefficient and the second coefficient are arithmetically added to obtain a region coefficient of each of the sub-regions.

4. The inspection method of a drone according to claim 1, characterized in that: The fire data includes fire spread speed, fire spread direction and ambient wind speed data. The fire spread range of each sub-area within a preset time period is predicted based on the fire data, including: Determine the real-time spread speed of each of the sub-areas according to the fire spread speed and the ambient wind speed data; Calculating the fire spread distance of each of the sub-areas within the preset time period according to the real-time spread speed; Taking the fire source point in each sub-area as the starting position and the fire spreading distance as the radius, determine the initial fire spreading area according to the fire spreading direction; The initial spreading area and the boundaries of each sub-area are subjected to regional overlap detection to determine the fire spreading range of each sub-area within a preset time period.

5. The inspection method of a drone according to claim 1, characterized in that: The determining of the second inspection route of each drone based on the target area and target area characteristics of the newly added sub-area to be inspected, the remaining power of each drone and the target position includes: Determine the number of drones required for the newly added sub-area to be inspected according to the target area and target area characteristics of the newly added sub-area to be inspected; Determining a flight distance of each of the drones according to the remaining power of each of the drones; Taking the target position of each drone as a starting point, combining the position of the newly added sub-area to be inspected and the flyable distance of each drone, determine the target flight area of ​​each drone in each newly added sub-area to be inspected; In the target flight area of ​​each of the UAVs, a second inspection route of each of the UAVs is determined according to the characteristics of the target area.

6. The inspection method of a drone according to claim 5, characterized in that: The method of determining the target flight area of ​​each drone in each of the newly added sub-areas to be inspected by taking the target position of each drone as the starting point and combining the position of the newly added sub-areas to be inspected and the flyable distance of each drone comprises: Taking the target position of each drone as the starting point coordinates of each drone; Obtaining the center coordinates of the newly added sub-area to be inspected; The distance between the starting point coordinates and the center position coordinates of each drone is used as the flight distance of each drone to reach the newly added sub-area to be inspected, and the drone whose flyable distance is greater than the flight distance is used as a candidate drone; Determine the flight radius of each candidate drone according to the starting point coordinates and the flyable distance of each candidate drone; Taking the starting point coordinates of each candidate drone as the center of the circle and the flight radius of each candidate drone as the radius, dividing the flight coverage area of ​​each candidate drone; The overlapping area between the flight coverage area of ​​each candidate UAV and the newly added sub-area to be inspected is judged, and the coverage area of ​​each candidate UAV in the newly added sub-area to be inspected is determined as the target flight area of ​​each candidate UAV.

7. The inspection method of a drone according to claim 5, characterized in that: After determining the second inspection route of each drone in the target flight area of ​​each drone according to the characteristics of the target area, the method further includes: If there is an uncovered newly added sub-area to be inspected, an additional drone is deployed according to the target area and target area characteristics of the uncovered newly added sub-area to be inspected, and a second inspection route of the additional drone is determined.

8. A drone inspection system, characterized in that: The system comprises: a first determination module, a second determination module, an acquisition module, a combination module and an output module; wherein, The first determination module is used to divide the fire area to be inspected into multiple sub-areas, and determine the number of drones required for each sub-area and the first inspection route of the drones corresponding to each sub-area according to the area and characteristics of each sub-area; The second determination module is used to obtain the fire data of each of the sub-areas, predict the fire spread range of each of the sub-areas within a preset time period according to the fire data, and determine the newly added sub-areas to be inspected in each of the sub-areas according to the fire spread range; The acquisition module is used to acquire the remaining power of each drone after inspection along the first inspection route, and the target position of each drone after inspection along the first inspection route; The combining module is used to combine the target area and target area characteristics of the newly added sub-area to be inspected, the remaining power of each drone and the target position, to determine the second inspection route of each drone; The output module is used to send the first inspection route and the second inspection route to each of the drones, so that each of the drones performs inspections according to the first inspection route and the second inspection route.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images