Autonomous optimization and intelligent monitoring system and method for unmanned aerial vehicle

Abstract

The invention discloses an autonomous optimization and intelligent monitoring system and method for an unmanned aerial vehicle, and relates to the technical field of unmanned aerial vehicle scheduling. The method comprises the following steps: firstly, collecting environment data and state parameters of a flight area to which an unmanned aerial vehicle belongs, analyzing and processing to obtain a task scheduling coincidence value of each unmanned aerial vehicle, and distributing each unmanned aerial vehicle to perform tasks in combination with the environment data and the task scheduling coincidence value of each unmanned aerial vehicle; in the task execution process of each unmanned aerial vehicle, the fuzzy logic parameters of the sensor are received, the scheduling process is optimized through the preset rule, the execution effect of the scheduling process is analyzed, and the experience database is updated, so that the task execution flexibility and accuracy can be improved, the decision-making ability in a complex environment is enhanced, the resource configuration is optimized, and the task execution efficiency is improved. The task execution time and cost are reduced, and meanwhile, the intelligent level and the adaptive capacity of the system are continuously improved through continuous data feedback and experience updating.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle dispatching, and in particular to an autonomous optimization and intelligent monitoring system and method for unmanned aerial vehicles. Background Art

[0002] Traditional drone dispatching often relies on clear algorithms and rules, while fuzzy artificial intelligence can handle uncertainty and ambiguity, allowing drones to self-adjust according to real-time data and environmental changes when performing tasks. This technology is widely used in fields such as agricultural monitoring, disaster management and urban traffic monitoring, improving the intelligence level of drones and the efficiency of mission execution.

[0003] For example, the invention patent with announcement number CN115713222B announces a utility-driven UAV perception network charging scheduling method, including: obtaining a set of UAVs, charging facilities and points of interest based on the operating status of the UAV, and building a UAV perception network model; building a perception value model based on the perception data quality of the UAV perception network model and a charging billing cost model based on the charging power of the charging facilities; formalizing the perception utility maximization problem under the UAV perception network system cycle; calling the utility-driven UAV perception network charging scheduling algorithm to obtain a scheduling plan for each UAV and realize the charging scheduling of the UAV.

[0004] For example, the invention patent with announcement number CN116933980B announces a method for command, control and dispatching of unmanned aerial vehicle clusters, including: a ground control station sets up multiple cluster monitoring seats, and each cluster monitoring seat deploys cluster comprehensive monitoring software; the cluster comprehensive monitoring software of each cluster monitoring seat is configured in sequence according to the seat number, and the seat number is unique; the priority of the cluster monitoring seats is arranged in order from small to large according to the seat number, and the priority of the cluster monitoring seats with a small seat number is greater than the priority of the cluster monitoring seats with a large seat number; the cluster unmanned aerial vehicle control right dispatching method is set according to the seat number of the cluster comprehensive monitoring software of each cluster monitoring seat; and the cluster unmanned aerial vehicle control right dispatching switching is performed using the cluster unmanned aerial vehicle control right dispatching method.

[0005] Based on the above findings, the existing technical solutions have the problem of being unable to make timely and accurate adjustments when facing complex and changing environments, which may lead to unreasonable scheduling of UAV tasks and the inability to effectively perform tasks under conditions such as severe weather and complex terrain. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides an autonomous optimization and intelligent monitoring system and method for a UAV, which solves the problems designed in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an autonomous optimization and intelligent monitoring system for drones, including a data acquisition module, which is used to collect environmental condition data of the flight area to which each drone belongs and the status parameters of each drone in each preset monitoring period.

[0008] The initial mission planning module is used to process and analyze the environmental condition data of the flight area to which each UAV belongs and the status parameters of each UAV, obtain the task scheduling compliance value of each UAV, and assign each UAV to perform tasks according to the task scheduling compliance value of each UAV.

[0009] The fuzzy reasoning module is used to receive and analyze the environmental information from the sensors during the execution of each UAV's mission, and obtain the scheduling process of each UAV based on preset fuzzy rules.

[0010] The fuzzy logic application summary module is used to collect and analyze the expected completion data of each drone task, obtain the execution effect value of each drone's scheduling task, analyze the execution effect of each drone's scheduling process and update it to the experience database.

[0011] Furthermore, the environmental condition data of the flight area to which each UAV belongs includes the wind speed, humidity, temperature, visibility index and the height of each obstacle and the straight-line distance between each UAV and the mission point.

[0012] The status parameters of each drone include the battery power, signal strength, flight altitude, flight speed, and the distance between each drone and each obstacle.

[0013] Furthermore, when each UAV receives a mission instruction, the wind speed and visibility index of the flight area to which each UAV belongs at that moment, as well as the battery power, signal strength, and straight-line distance between each UAV and the mission point are monitored and collected, and the mission scheduling compliance value of each UAV is processed. The mission instruction includes the mission start time, the number of UAVs required for the mission, the longitude and latitude of the mission point, and the altitude of the mission point. The mission scheduling compliance value of each UAV is used to evaluate the matching degree between the task and each UAV, and obtain the expected mission completion data of each UAV for each mission.

[0014] Furthermore, the task scheduling compliance values ​​of the drones are sorted from large to small, and starting from the first ranked drone, the drone with the number of drones required by the task instruction is selected to perform the task.

[0015] Furthermore, environmental information on the flight path of each UAV in each monitoring period is collected, wherein the environmental information includes the relative angle between the UAV and each obstacle, the size of each obstacle, and the height of each obstacle, and the flight path of each UAV is planned based on the collected environmental information.

[0016] The height of each obstacle on the flight path of each UAV in each monitoring period is extracted, and the distance between each UAV and each obstacle at that moment in each monitoring period is monitored. Combined with the average flight speed of each UAV in each monitoring period, the obstacle hazard assessment value on the flight path of each UAV in each monitoring period is obtained. The obstacle hazard assessment value on the flight path of each UAV in each monitoring period is used to assess the hazard level of obstacles on the flight path of the UAV.

[0017] The average wind speed, average humidity and average temperature of the area to which each drone belongs in each monitoring period are extracted, and the environmental safety value of each drone in each monitoring period is obtained by processing. The environmental safety value of each drone in each monitoring period is used to quantitatively evaluate the safe flight degree of the environment of the area to which each drone belongs.

[0018] Furthermore, the obstacle hazard assessment value on the flight path of each drone in each monitoring period, the specific analysis conditions are as follows: ; In the formula, represents the obstacle hazard assessment value on the flight path of the i-th UAV in the j-th monitoring period, represents the height of the qth obstacle on the flight path of the ith UAV in the jth monitoring period, represents the distance between the ith UAV and the qth obstacle at this moment in the jth monitoring cycle, represents the average flight speed of the ith UAV in the jth monitoring period, Indicates the optimal flight altitude of the drone. Indicates the reference value of the distance between the drone and the obstacle. Indicates the reference value of the flight speed of the drone. The weight factor representing the height of obstacles on the set UAV flight path, Represents the weight factor of the distance between the drone and the obstacle. Represents the weight factor of the set UAV flight speed, , i represents the number of the drone, n represents the total number of drones, , j represents the number of the monitoring cycle, m represents the total number of monitoring cycles, , q represents the number of obstacles, and g represents the total number of obstacles.

[0019] Furthermore, the preset fuzzy rules include obstacle risk level matching rules and execution effect matching rules of the UAV scheduling process.

[0020] The obstacle hazard assessment value on the flight path of each UAV in each monitoring period is extracted, and the obstacle hazard assessment value on the flight path of each UAV in each monitoring period is matched with the hazard degree corresponding to each interval of the obstacle hazard assessment value on the flight path of the UAV in the database to obtain the hazard degree of each UAV flight path in each monitoring period, and the hazard degree of each UAV flight path in each monitoring period is input into the obstacle risk level matching rule for matching to obtain the fuzzy hazard level on the flight path of each UAV in each monitoring period.

[0021] The fuzzy danger level on the flight path of each UAV in each monitoring period includes low risk, medium risk, and high risk. When the fuzzy danger level is low risk, the flight direction of each UAV is maintained unchanged. When the fuzzy danger level is medium risk, each UAV is controlled to avoid obstacles. When the fuzzy danger level is high risk, each UAV is controlled to land safely.

[0022] The environmental safety value of each drone in each monitoring period is extracted, and the safe flight degree of the environment of the area to which each drone belongs is matched. The safe flight degree of the environment of the area to which each drone belongs includes good safety, general safety, and poor safety. When the safe flight degree of the environment of the area to which each drone belongs is poor safety, the flight speed and flight altitude of each drone are reduced. When the safe flight degree of the environment of the area to which each drone belongs is general safety, the flight speed and flight altitude of each drone remain unchanged. When the safe flight degree of the environment of the area to which each drone belongs is good safety, the flight speed and flight altitude of each drone are increased.

[0023] Furthermore, expected task completion data of each mission of each drone is extracted, wherein the expected task completion data of each mission of each drone includes expected task completion time and expected battery power consumption of the drone.

[0024] The actual time for completing each task of each drone is divided by the expected time for completing the task of the drone to obtain the time efficiency of each task of each drone, and the actual battery power consumption of each drone for each task and the expected battery power consumption of the drone are combined to obtain the scheduling task execution effect value of each drone. The scheduling task execution effect value of each drone is used to evaluate the scheduling effect of each drone.

[0025] Furthermore, the scheduling task execution effect value of each UAV is extracted, and the scheduling effects of the UAVs in each interval of the scheduling task execution effect value of the UAVs in the database are matched to obtain the scheduling effect of each task of each UAV, and the scheduling effect of each task of each UAV is input into the execution effect matching rule of the UAV's scheduling process to obtain the execution effect of the scheduling process of each UAV. The execution effect of the scheduling process of each UAV includes poor task completion, general task completion, and successful task completion. The execution effect of the scheduling process of each UAV is updated to the experience database.

[0026] To achieve the above objectives, the present invention is implemented through the following technical solutions: an autonomous optimization and intelligent monitoring method for drones, including collecting environmental condition data of the flight area to which each drone belongs and the status parameters of each drone in each preset monitoring period.

[0027] The environmental condition data of the flight area to which each UAV belongs and the status parameters of each UAV are processed and analyzed to obtain the task scheduling compliance value of each UAV, and each UAV is assigned to perform tasks according to the task scheduling compliance value of each UAV.

[0028] When each UAV is performing its mission, the environmental information received from the sensor is analyzed, and the scheduling process of each UAV is obtained based on the preset fuzzy rules.

[0029] Collect and analyze the expected completion data of each drone task, obtain the execution effect value of each drone's scheduling task, analyze the execution effect of each drone's scheduling process and update it to the experience database.

[0030] The present invention has the following beneficial effects: (1) The present invention discloses an autonomous optimization and intelligent monitoring system and method for unmanned aerial vehicles. First, environmental data and state parameters of the flight area to which the unmanned aerial vehicles belong are collected, and the task scheduling compliance value of each unmanned aerial vehicle is obtained by analysis and processing. The task is assigned to each unmanned aerial vehicle in combination with the environmental data and the task scheduling compliance value of each unmanned aerial vehicle. During the execution of the task by each unmanned aerial vehicle, the fuzzy logic parameters of the sensor are received, the scheduling process is optimized by preset rules, the execution effect of the scheduling process is analyzed, and the experience database is updated. This can improve the flexibility and accuracy of task execution, enhance the decision-making ability in complex environments, optimize resource allocation, and reduce the time and cost of task execution. At the same time, through continuous data feedback and experience updating, the intelligence level and adaptability of the system are continuously improved.

[0031] (2) The present invention monitors the environmental condition data of each drone's flight area within a preset monitoring period, collects drone status parameters, processes them to obtain the task scheduling compliance value of each drone, and selects drones to perform tasks according to the compliance value from high to low, thereby ensuring the effective allocation and task execution of drones, optimizing the use of drones, and avoiding waste of resources.

[0032] (3) The present invention receives and processes sensor data such as the height, distance, and flight speed of obstacles on the flight path of the drone, evaluates the danger level of the obstacles, and matches them with preset fuzzy rules to determine the obstacle risk level, help adjust the flight mode and path of the drone, dynamically adjust the flight plan according to the state of the drone and the completion of the mission, make timely adjustments to the flight path, and reduce the risk of accidents; it also considers environmental factors and the state of the drone to evaluate the feasibility of the mission. When the drone is in poor condition or the mission completion is not ideal, the system will decide whether to return or adjust the flight parameters based on the evaluation results to ensure the safety of the drone and the smooth progress of the mission, ensure the efficient execution of the mission, and avoid unnecessary mission interruptions.

[0033] (4) The present invention calculates the time efficiency of each drone, and combines the actual battery power consumption and the expected battery power consumption to obtain the task execution loss value of each drone. Combined with the time efficiency, the dispatch task execution effect value of the drone is evaluated, and the fuzzy matching technology is used to judge the execution effect of the dispatch process; the drones are divided into the situations of successful dispatch, and the dispatch process of the drones evaluated as general or poor is deeply analyzed, and the results are stored in the experience database to provide a reference for future dispatch.

[0034] (5) The present invention obtains the task scheduling compliance value of each UAV to assign a suitable UAV to perform the task, obtains the obstacle hazard assessment value on the flight path of each UAV and the environmental safety value of each UAV in each monitoring period to adjust the flight attitude of the UAV, and obtains the task execution efficiency and task completion status of each UAV according to the task adjustment assessment value of each UAV. Through the quantitative evaluation of each step, the status of the UAV and the task completion status can be clarified, which can significantly improve the task execution efficiency and task completion status of the UAV, and ensure the safe and efficient completion of various tasks.

[0035] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The figure is a flow chart of the autonomous optimization and intelligent monitoring system of the UAV of the present invention.

[0037] Figure 2 It is the mission scheduling compliance value curve of the UAV of the present invention.

[0038] Figure 3 The figure is a flow chart of the autonomous optimization and intelligent monitoring method of the UAV of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "all around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0041] See also Figure 1 The embodiment of the present invention provides a technical solution: an autonomous optimization and intelligent monitoring system for unmanned aerial vehicles, including a data acquisition module, which is used to collect environmental status data of the flight area to which each unmanned aerial vehicle belongs and the status parameters of each unmanned aerial vehicle in each preset monitoring period.

[0042] The initial mission planning module is used to process and analyze the environmental condition data of the flight area to which each UAV belongs and the status parameters of each UAV, obtain the task scheduling compliance value of each UAV, and assign each UAV to perform tasks according to the task scheduling compliance value of each UAV.

[0043] The fuzzy reasoning module is used to receive and analyze the environmental information from the sensors during the execution of each UAV's mission, and obtain the scheduling process of each UAV based on preset fuzzy rules.

[0044] The fuzzy logic application summary module is used to collect and analyze the expected completion data of each drone task, obtain the execution effect value of each drone's scheduling task, analyze the execution effect of each drone's scheduling process and update it to the experience database.

[0045] It should be noted that the data acquisition module is responsible for collecting the environmental data of the flight area where each UAV is located and the status parameters of each UAV; the task initial planning module analyzes the environmental data of the flight area where each UAV is located and the status parameters of each UAV and performs task scheduling; the fuzzy reasoning module obtains the obstacle hazard assessment value on the flight path of each UAV and the environmental safety value of each UAV in each monitoring period through fuzzy logic parameter processing fed back by the sensor, and adjusts the scheduling process of each UAV; the fuzzy logic application summary module continuously optimizes the scheduling strategy by analyzing the scheduling effect and updating the experience database, and can adaptively adjust the task scheduling process of the UAV to improve the efficiency and adaptability of the UAV in executing tasks.

[0046] Specifically, the environmental condition data of the flight area to which each UAV belongs includes the wind speed, humidity, temperature, visibility index of the flight area to which each UAV belongs, the height of each obstacle, and the straight-line distance between each UAV and the mission point.

[0047] The status parameters of each drone include the battery power, signal strength, flight altitude, flight speed, and the distance between each drone and each obstacle.

[0048] It should be noted that the wind speed of each drone's flight area is measured by the drone anemometer using the ultrasonic measurement principle; the humidity of each drone's flight area is monitored by a humidity sensor; the temperature of each drone's flight area is measured by a temperature sensor; the visibility index of each drone's flight area is measured by a visibility detector using a scattering method or a transmission method to measure the visibility in the atmosphere; the battery power of each drone is obtained by directly reading the remaining battery power; the signal strength of each drone is measured by a signal measuring device; each drone uses a GPS measurement system to measure the flight altitude of the drone and locate the drone, and at the same time extracts the latitude and longitude of the mission point and the altitude of the mission point, and processes the distance between each drone and each obstacle; the flight speed of each drone is accurately measured by a radar speed meter; the height of the obstacle on the flight path of each drone and the distance between each drone and the obstacle are detected by a laser radar emitting a laser beam to accurately measure the height information of the obstacle and the distance between the drone and the obstacle.

[0049] Specifically, when each UAV receives a mission instruction, it monitors and collects the wind speed and visibility index of the flight area to which each UAV belongs at that moment, as well as the battery power, signal strength, and straight-line distance between each UAV and the mission point, and processes the collected data to obtain the mission scheduling compliance value of each UAV. The mission instruction includes the mission start time, the number of UAVs required for the mission, the longitude and latitude of the mission point, and the altitude of the mission point. The mission scheduling compliance value of each UAV is used to evaluate the matching degree between the mission and each UAV, and to obtain the expected mission completion data of each UAV for each mission.

[0050] It should be noted that when each UAV receives a mission instruction, the sensor monitors the wind speed and visibility index of the flight area to which each UAV belongs at the moment of receiving the mission instruction, and reads the battery power, signal strength, and straight-line distance between each UAV and the mission point at that moment.

[0051] It should be noted that the task scheduling of each drone meets the value, and the specific analysis process is as follows: ; In the formula, represents the mission scheduling compliance value of the i-th UAV, represents the wind speed of the flight area of ​​the i-th UAV, represents the visibility index of the flight area to which the i-th UAV belongs, represents the battery power of the ith drone, represents the signal strength of the i-th drone, represents the straight-line distance between the ith UAV and the mission point, represents the wind speed threshold, represents the visibility index threshold, Indicates the optimal battery power value for the drone to perform the mission. Indicates the signal strength reference value of the drone. The reference value of the straight-line distance between the UAV and the mission point, Indicates the correction factor for the set wind speed, Indicates the correction factor of the set visibility index, Indicates the correction factor of the battery power of the set drone. Indicates the correction factor of the signal strength of the set drone, Indicates the correction factor of the straight-line distance between the set UAV and the mission point.

[0052] like Figure 2 As shown, Figure 2It represents the mission scheduling compliance value of the UAV, where the horizontal axis represents the wind speed of the flight area of ​​the ith UAV in meters per second (m / s), and the vertical axis represents the mission scheduling compliance value of the ith UAV. Three different sets of example parameters are defined in the figure, corresponding to different situations of the three curves, represented by solid lines, dashed lines and dotted lines, respectively. The corresponding curve labels are a, b, and c, respectively. Assume that the battery power of the ith UAV is 20000 (Coulomb), the signal strength of the i-th drone = 2.0 (GHz), the straight-line distance between the ith UAV and the mission point =30 (meters), wind speed threshold (meters per second), visibility index threshold 5 (km), the optimal battery power value for drones to perform missions , UAV signal strength reference value =2.4 (GHz), the reference value of the straight-line distance between the drone and the mission point =15 (m), correction factor for set wind speed , set the correction factor for the visibility index , set the correction factor of the battery power , set the correction factor of the drone's signal strength =0.2, the correction factor of the straight-line distance between the drone and the mission point =0.7, when the visibility index of the flight area to which the i-th UAV belongs is 3 meters, the schematic diagram of the task scheduling compliance value of the i-th UAV is shown in curve a, when the visibility index of the flight area to which the i-th UAV belongs is 8 meters, the schematic diagram of the task scheduling compliance value of the i-th UAV is shown in curve b, and when the visibility index of the flight area to which the i-th UAV belongs is 10 meters, the schematic diagram of the task scheduling compliance value of the i-th UAV is shown in curve c.

[0053] As shown in Table 1, Table 1 is example data of obstacle hazard assessment values ​​on the flight path of the UAV, which lists the mission scheduling compliance value of the UAV and the wind speed of the flight area to which the UAV belongs.

[0054] Table 1 Example data of drone task scheduling compliance values As shown in Table 1, in a specific embodiment, assuming that the battery power of the i-th drone is 20000 (Coulomb), the signal strength of the i-th drone = 2.0 (GHz), the straight-line distance between the ith UAV and the mission point =30 (meters), wind speed threshold (meters per second), visibility index threshold 5 (km), the optimal battery power value for drones to perform missions , UAV signal strength reference value =2.4 (GHz), the reference value of the straight-line distance between the drone and the mission point =15 (m), correction factor for set wind speed , set the correction factor for the visibility index , set the correction factor of the battery power , set the correction factor of the drone's signal strength =0.2, the correction factor of the straight-line distance between the drone and the mission point =0.7, the mission scheduling compliance value of the UAV is determined by the wind speed and visibility index of the flight area to which each UAV belongs, the battery power and signal strength of each UAV, and the straight-line distance between each UAV and the mission point.

[0055] It should be noted that there is a correlation between the wind speed and visibility index of the drone's flight area. Generally speaking, wind speed and visibility are usually positively correlated. As the wind speed increases, pollutants and particulate matter in the atmosphere are more easily blown away, so that the visibility index will increase; the battery power of the drone decreases, which may cause the drone's transmission signal to become weaker, the drone's signal strength also decreases, and the straight-line distance between the drone and the mission point decreases, indicating that the drone's battery power is low; by comprehensively processing environmental data and the drone's own status parameters, the drone's endurance in the environment can be evaluated, and tasks can be accurately allocated to reduce resource waste.

[0056] The wind speed correction factor set in the database indicates the degree of correction of the wind speed to the UAV's task scheduling compliance value. When used, the wind speed correction factor can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the wind speed and the wind speed correction factor set in the database form a mapping set, and the real-time wind speed is input into the mapping set to obtain the wind speed correction factor. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0057] The correction factor of the visibility index set in the database indicates the degree of correction of the visibility index to the mission scheduling compliance value of the UAV. When used, the correction factor of the visibility index can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the visibility index and the correction factor of the visibility index set in the database form a mapping set. The real-time visibility index is input into the mapping set to obtain the correction factor of the visibility index. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0058] The correction factor of the battery power of the drone set in the database indicates the degree of correction of the drone's battery power to the drone's task scheduling compliance value. When used, the correction factor of the drone's battery power can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the drone's battery power and the correction factor of the drone's battery power set in the database form a mapping set. The real-time drone's battery power is input into the mapping set to obtain the correction factor of the drone's battery power. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0059] It is the correction factor of the signal strength of the drone set in the database, which indicates the numerical value of the correction degree of the drone's signal strength to the drone's task scheduling compliance value. When used, the correction factor of the drone's signal strength can be directly obtained from the database. Its corresponding relationship can be a pre-set mapping relationship. For example, the signal strength of the drone and the correction factor of the signal strength of the drone set in the database form a mapping set, and the real-time drone signal strength is input into the mapping set to obtain the correction factor of the drone's signal strength. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0060] It is the correction factor of the straight-line distance between the UAV and the task point set in the database, which indicates the degree of correction of the straight-line distance between the UAV and the task point to the task scheduling compliance value of the UAV. When used, the correction factor of the straight-line distance between the UAV and the task point can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the straight-line distance between the UAV and the task point and the correction factor of the straight-line distance between the UAV and the task point set in the database form a mapping set. The real-time straight-line distance between the UAV and the task point is input into the mapping set to obtain the correction factor of the straight-line distance between the UAV and the task point. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0061] It should be noted that the expected task completion data of each UAV for each task is obtained by the following specific process: extracting the task scheduling compliance value of each UAV and matching it with the task completion prediction data of each UAV corresponding to each interval of the task scheduling compliance value of each UAV in the database. The UAV task completion prediction data is preset in the database. When in use, the UAV task completion prediction data can be directly obtained from the database. The corresponding relationship can be a preset mapping relationship. For example, the task scheduling compliance value of each UAV and the UAV task completion prediction data in the database form a mapping set, and the real-time task scheduling compliance value of each UAV is input into the mapping set to obtain the expected task completion data of each UAV for each task. The mapping relationship can be a one-to-one corresponding relationship. The expected task completion data of each UAV for each task includes the expected task completion time of each UAV for each task and the expected battery power consumption of each UAV for each task.

[0062] Specifically, the task scheduling compliance values ​​of each drone are sorted from large to small, and starting from the first ranked drone, the drone with the number of drones required by the task instruction is selected to perform the task.

[0063] Collect environmental information on the flight path of each UAV in each monitoring period, the environmental information including the relative angle between the UAV and each obstacle, the size of each obstacle, and the height of each obstacle, and plan the flight path of each UAV based on the collected environmental information.

[0064] It should be noted that the task scheduling compliance values ​​of each drone are sorted from large to small to select the drone to perform the task. For example, if the task requires five drones to perform, the drones ranked first to fifth are selected to perform the task, ensuring that the selected drones are highly matched with the task requirements, thereby improving the accuracy and efficiency of task execution.

[0065] It should be noted that the UAV is equipped with a laser radar, and the laser beam can scan the surrounding environment to generate high-precision three-dimensional point cloud data, so as to accurately identify the location and size of obstacles; the obstacle height is extracted using satellite remote sensing images, and satellite communication equipment is installed on the UAV to directly receive obstacle height data from satellite remote sensing images. The Dijkstra algorithm (shortest path algorithm) can be used to plan the shortest path by modeling the direction, size and height of the obstacle as a graph, where nodes represent feasible positions and edges represent feasible paths connecting these positions. Starting from the location of the UAV, the distance of each obstacle is initialized, the obstacle with the smallest current distance is selected, and the directions of its adjacent obstacles are traversed to update the distance of the feasible path, and finally the shortest path from the UAV location to the mission location is obtained. According to the obstacle direction, obstacle size, and obstacle height, it is modeled as a graph, with nodes representing positions and edges representing feasible paths, and the flight path is planned by calculating the shortest path.

[0066] Specifically, the height of each obstacle on the flight path of each UAV in each monitoring period is extracted, and the distance between each UAV and each obstacle at that moment is monitored in each monitoring period. Combined with the average flight speed of each UAV in each monitoring period, the obstacle hazard assessment value on the flight path of each UAV in each monitoring period is processed to obtain the obstacle hazard assessment value on the flight path of each UAV in each monitoring period. The obstacle hazard assessment value on the flight path of each UAV in each monitoring period is used to assess the hazard level of obstacles on the flight path of the UAV.

[0067] The average wind speed, average humidity and average temperature of the area to which each drone belongs in each monitoring period are extracted, and the environmental safety value of each drone in each monitoring period is obtained by processing. The environmental safety value of each drone in each monitoring period is used to quantitatively evaluate the safe flight degree of the environment of the area to which each drone belongs.

[0068] It should be noted that multiple anemometers, hygrometers and thermometers are arranged in the UAV flight area, including anemometers, hygrometers and thermometers at different heights. At the same time, monitoring time points are set in each monitoring period, wind speed, humidity and temperature are monitored at each monitoring time point, and the average is calculated to obtain the average wind speed, average humidity and average temperature in a monitoring period. The UAV receives the average wind speed, average humidity and average temperature monitored by each thermometer, hygrometer and anemometer in the area within a monitoring period, and calculates the average value to obtain the average wind speed, average humidity and average temperature of the area to which the UAV belongs. For example, the UAV receives the data monitored by each thermometer, hygrometer and anemometer in an area with a radius of 10 meters with itself as the center, and calculates the average value to obtain the average wind speed, average humidity and average temperature of the area to which each UAV belongs in each monitoring period.

[0069] It should be noted that the environmental safety value of each drone in each monitoring period is used to quantitatively evaluate the safe flight level of the regional environment to which each drone belongs. The specific analysis process of the environmental safety value of each drone in each monitoring period is as follows: ; In the formula, represents the environmental safety value of the i-th drone in the j-th monitoring period, represents the average wind speed of the i-th UAV’s region in the j-th monitoring period, represents the average humidity of the area to which the i-th UAV belongs during the j-th monitoring period, represents the average temperature of the area to which the ith UAV belongs during the jth monitoring period, The most suitable wind speed for drone flight is indicated. It indicates that the humidity is most suitable for drone flight. Indicates the most suitable temperature for drone flight. Indicates the correction factor of the average wind speed in the area where the drone belongs. Indicates the correction factor of the average humidity of the area to which the drone belongs. Indicates the correction factor of the average temperature of the area to which the drone belongs. , i represents the number of the drone, n represents the total number of drones, , j represents the number of the monitoring cycle, and m represents the total number of monitoring cycles.

[0070] It should be noted that there is a correlation between the average wind speed in the area where the drone belongs, the average humidity between the drone and the mission point, and the average temperature in the area where the drone belongs. When the average temperature rises, the average wind speed may show a downward trend. When the average temperature rises, the water vapor content in the air may increase, and the average humidity will increase. The environmental safety value of each drone in each monitoring period is obtained based on the average wind speed in the area where the drone belongs, the average humidity between the drone and the mission point, and the average temperature in the area where the drone belongs, which helps to ensure that the drone can still perform its mission safely in bad weather or extreme environments.

[0071] It is the correction factor of the average wind speed of the drone's affiliated area set in the database, which indicates the degree of correction of the average wind speed of the drone's affiliated area to the drone's environmental safety value. When used, the correction factor of the average wind speed of the drone's affiliated area can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the average wind speed of the drone's affiliated area and the correction factor of the average wind speed of the drone's affiliated area set in the database form a mapping set. The real-time average wind speed of the drone's affiliated area is input into the mapping set to obtain the correction factor of the average wind speed of the drone's affiliated area. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0072] It is the correction factor of the average humidity of the drone's affiliated area set in the database, which indicates the degree of correction of the average humidity of the drone's affiliated area to the drone's environmental safety value. When used, the correction factor of the average humidity of the drone's affiliated area can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the average humidity of the drone's affiliated area and the correction factor of the average humidity of the drone's affiliated area set in the database form a mapping set. The real-time average humidity of the drone's affiliated area is input into the mapping set to obtain the correction factor of the average humidity of the drone's affiliated area. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0073] It is the correction factor of the average temperature of the drone's affiliated area set in the database, which indicates the degree of correction of the average temperature of the drone's affiliated area to the drone's environmental safety value. When used, the correction factor of the average temperature of the drone's affiliated area can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the average temperature of the drone's affiliated area and the correction factor of the average temperature of the drone's affiliated area set in the database form a mapping set. The real-time average temperature of the drone's affiliated area is input into the mapping set to obtain the correction factor of the average temperature of the drone's affiliated area. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0074] Specifically, the obstacle hazard assessment value on the flight path of each drone in each monitoring period, the specific analysis conditions are as follows: ; In the formula, represents the obstacle hazard assessment value on the flight path of the i-th UAV in the j-th monitoring period, represents the height of the qth obstacle on the flight path of the ith UAV in the jth monitoring period, represents the distance between the ith UAV and the qth obstacle at this moment in the jth monitoring cycle, represents the average flight speed of the ith UAV in the jth monitoring period, Indicates the optimal flight altitude of the drone. Indicates the reference value of the distance between the drone and the obstacle. Indicates the reference value of the flight speed of the drone. The weight factor representing the height of obstacles on the set UAV flight path, Represents the weight factor of the distance between the drone and the obstacle. Represents the weight factor of the set UAV flight speed, , i represents the number of the drone, n represents the total number of drones, , j represents the number of the monitoring cycle, m represents the total number of monitoring cycles, , q represents the number of obstacles, and g represents the total number of obstacles.

[0075] It should be noted that there is a correlation between the height of the obstacle on the drone's flight path, the distance between the drone and the obstacle, and the drone's flight speed. When the distance between the drone and the obstacle decreases, the drone needs to reduce its flight speed to avoid collision with the obstacle; when the height of the obstacle on the drone's flight path is high, the drone needs to slow down and climb to a certain height to avoid the obstacle.

[0076] It is the correction factor of the height of the obstacle on the UAV flight path set in the database, which indicates the degree of correction of the obstacle height on the UAV flight path to the obstacle hazard assessment value. When used, the correction factor of the height of the obstacle on the UAV flight path can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the height of the obstacle on the UAV flight path and the correction factor of the height of the obstacle on the UAV flight path set in the database form a mapping set. The height of the obstacle on the real-time UAV flight path is input into the mapping set to obtain the correction factor of the height of the obstacle on the UAV flight path. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0077] It is the correction factor of the distance between the drone and the obstacle set in the database, which indicates the degree of correction of the distance between the drone and the obstacle to the obstacle hazard assessment value. When used, the correction factor of the distance between the drone and the obstacle can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the distance between the drone and the obstacle and the correction factor of the distance between the drone and the obstacle set in the database form a mapping set. The real-time distance between the drone and the obstacle is input into the mapping set to obtain the correction factor of the distance between the drone and the obstacle. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0078] It is the correction factor of the flight speed of the drone set in the database, which indicates the degree of correction of the obstacle hazard assessment value by the flight speed of the drone. When used, the correction factor of the flight speed of the drone can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the flight speed of the drone and the correction factor of the flight speed of the drone set in the database form a mapping set. The real-time flight speed of the drone is input into the mapping set to obtain the correction factor of the flight speed of the drone. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0079] Specifically, the preset fuzzy rules include obstacle risk level matching rules and execution effect matching rules of the UAV scheduling process.

[0080] The obstacle hazard assessment value on the flight path of each UAV in each monitoring period is extracted, and the obstacle hazard assessment value on the flight path of each UAV in each monitoring period is matched with the hazard degree corresponding to each interval of the obstacle hazard assessment value on the flight path of the UAV in the database to obtain the hazard degree of each UAV flight path in each monitoring period, and the hazard degree of each UAV flight path in each monitoring period is input into the obstacle risk level matching rule for matching to obtain the fuzzy hazard level on the flight path of each UAV in each monitoring period.

[0081] The fuzzy danger level on the flight path of each UAV in each monitoring period includes low risk, medium risk, and high risk. When the fuzzy danger level is low risk, the flight direction of each UAV is maintained unchanged. When the fuzzy danger level is medium risk, each UAV is controlled to avoid obstacles. When the fuzzy danger level is high risk, each UAV is controlled to land safely.

[0082] It should be noted that fuzzy rules are rules that use fuzzy set theory to describe and reason about uncertainty and fuzzy knowledge. They are usually expressed in the form of "if-then" and can handle imprecise, incomplete or ambiguous information, thereby achieving effective decision-making and control in a variety of application scenarios.

[0083] It should be noted that fuzzy rules, by processing the uncertainty of environmental data, enable UAVs to realize intelligent perception of complex environments, flexible task planning and scheduling, effective obstacle avoidance and risk control, and adaptive control strategy adjustment, thereby improving the autonomous navigation and mission execution capabilities of UAVs.

[0084] It should be noted that the fuzzy danger level on the flight path of each UAV in each monitoring period is obtained by matching the danger degree of obstacles on the flight path of the UAV with the obstacle risk level matching rules; the execution effect matching rules of the UAV's scheduling process are input into the UAV's scheduling effect, and the execution effect of the UAV's scheduling process is matched to obtain the execution effect of the UAV's scheduling process.

[0085] It should be noted that the danger level of each drone flight path in each monitoring period is input into the obstacle risk level matching rule for matching, and the fuzzy danger level on each drone flight path in each monitoring period is obtained. The obstacle danger assessment value on each drone flight path in each monitoring period is extracted and matched with the obstacle danger level corresponding to each interval of each monitoring period in the obstacle danger assessment value in the database. The obstacle danger level is preset in the database. When used, the obstacle danger level can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the obstacle danger assessment value on each drone flight path in each monitoring period and the obstacle danger level in the database form a mapping set. The real-time obstacle danger assessment value on each drone flight path in each monitoring period is input into the mapping set to obtain the obstacle danger level. The mapping relationship can be a one-to-one corresponding relationship. The obstacle danger level includes extremely low danger, low danger, medium danger, high danger, and extremely high danger. The obstacle danger level is matched according to the obstacle risk level matching rule in the fuzzy rule. Extremely low danger and low danger correspond to low risk, medium danger and high danger correspond to medium risk, and extremely high danger corresponds to high risk.

[0086] It should be noted that the obstacle hazard level is a key indicator for assessing the potential risks on the UAV flight path. The fuzzy hazard level classifies the obstacle hazard level. Its main purpose is to simplify the complex hazard level information into easy-to-understand and process level information, which helps the UAV system to quickly identify and deal with different levels of risks, so as to adopt corresponding control strategies.

[0087] It should be noted that when the fuzzy danger level is low risk, the drone continues to monitor obstacles to ensure that its danger level has not changed, while reducing the flight speed and planning the flight path to bypass obstacles; when the fuzzy danger level is medium risk, the drone quickly adjusts the flight attitude and changes the flight direction to avoid collision with obstacles; when the fuzzy danger level is high risk, the drone starts the safe landing procedure and selects a safe location to land.

[0088] Specifically, the environmental safety value of each UAV in each monitoring period is extracted, and the safe flight degree of the environment of the area to which each UAV belongs is matched to obtain the safe flight degree of the environment of the area to which each UAV belongs. The safe flight degree of the environment of the area to which each UAV belongs includes good safety level, general safety level, and poor safety level. When the safe flight degree of the environment of the area to which each UAV belongs is poor safety level, the flight speed and flight altitude of each UAV are reduced. When the safe flight degree of the environment of the area to which each UAV belongs is general safety level, the flight speed and flight altitude of each UAV remain unchanged. When the safe flight degree of the environment of the area to which each UAV belongs is good safety level, the flight speed and flight altitude of each UAV are increased.

[0089] It should be noted that the environmental safety value of each drone in each monitoring period is extracted and matched to obtain the safe flight degree of the environment of the area to which each drone belongs. The environmental safety value of each drone in each monitoring period is extracted and matched with the safe flight degree of the environment of the drone area corresponding to each interval of the drone environmental safety value in the database. The safe flight degree of the environment of the area to which the drone belongs is preset in the database. When in use, the safe flight degree of the environment of the area to which the drone belongs can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the environmental safety value of each drone in each monitoring period and the safe flight degree of the environment of the drone area in the database form a mapping set. The real-time environmental safety value of each drone in each monitoring period is input into the mapping set to obtain the safe flight degree of the environment of the drone area. The mapping relationship can be a one-to-one corresponding relationship. The flight speed and flight altitude of each drone are subtracted from the flight speed reference value and the optimal flight altitude set by the drone to obtain each drone. The flight speed and flight altitude adjustment values ​​of the drones: when the safety level of the regional environment of each drone is poor, the flight speed and flight altitude of each drone are reduced according to the flight speed and flight altitude adjustment values ​​of each drone; when the safety level of the regional environment of each drone is fair, the flight speed and flight altitude of each drone remain unchanged; when the safety level of the regional environment of each drone is good, the flight speed and flight altitude of each drone are increased according to the flight speed and flight altitude adjustment values ​​to reduce the flight risks caused by environmental factors and ensure that the drones can complete their flight missions more safely and stably.

[0090] Specifically, the expected task completion data of each mission of each drone is extracted, and the expected task completion data of each mission of each drone includes the expected task completion time of the drone and the expected battery power consumption.

[0091] The actual time for completing each task of each drone is divided by the expected time for completing the task of the drone to obtain the time efficiency of each task of each drone, and the actual battery power consumption of each drone for each task and the expected battery power consumption of the drone are combined to obtain the scheduling task execution effect value of each drone. The scheduling task execution effect value of each drone is used to evaluate the scheduling effect of each drone.

[0092] Extract the scheduling task execution effect value of each UAV, match the scheduling effect of the UAV in each interval of the scheduling task execution effect value of the UAV in the database, obtain the scheduling effect of each task of each UAV, input the scheduling effect of each task of each UAV into the execution effect matching rule of the UAV scheduling process to obtain the execution effect of the scheduling process of each UAV, the execution effect of the scheduling process of each UAV includes poor task completion, general task completion, and successful task completion, and update the execution effect of the scheduling process of each UAV to the experience database.

[0093] It should be noted that when the status of each drone in each monitoring cycle is poor, the drone will return. When the status of each drone in each monitoring cycle is excellent or good, the obstacle direction, obstacle size, and obstacle height in the flight area to which the drone belongs are extracted, and the flight path is replanned.

[0094] It should be noted that the time efficiency of each drone for each mission is , Indicates the actual time of completion of each mission of each drone, Indicates the expected mission completion time of the drone, , i represents the number of the drone, , z represents the number of the task, and R represents the total number of tasks.

[0095] It should be noted that the number of tasks performed by each drone and the number of completed tasks are recorded as , , and process to obtain the task completion rate of each drone , , i represents the number of the drone.

[0096] It should be noted that the actual battery power consumption of each drone is obtained by subtracting the battery power of each drone before performing the mission from the battery power after performing the mission.

[0097] It should be noted that the specific analysis process of the dispatch task execution effect value of each drone is as follows: ; In the formula, represents the execution effect value of the scheduling task of the i-th UAV, represents the time efficiency of the i-th UAV in the z-th mission, represents the mission completion rate of the i-th UAV, represents the actual battery power consumption of the ith drone, represents the expected battery consumption of the drone for the zth mission, Represents the weight factor corresponding to the set UAV time efficiency, Indicates the weight factor corresponding to the battery power consumption of the set drone, Indicates the weight factor corresponding to the mission completion rate of the set UAV, , i represents the number of the drone, n represents the total number of drones, , z represents the number of the task, and R represents the total number of tasks.

[0098] It should be noted that there is a correlation between the drone's time efficiency, the drone's battery power consumption and the mission completion rate. The higher the drone's time efficiency, the lower the battery power consumption. The drone's time efficiency and power consumption ratio can evaluate the drone's comprehensive performance. A high mission completion rate means that the drone has high time efficiency.

[0099] The weight factor corresponding to the time efficiency of the drone set in the database represents the degree of correction of the drone's time efficiency to the execution effect value of the drone's scheduling task. When used, the correction factor of the drone's time efficiency can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the drone's time efficiency and the correction factor of the drone's time efficiency set in the database form a mapping set. The real-time drone's time efficiency is input into the mapping set to obtain the correction factor of the drone's time efficiency. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0100] The weight factor corresponding to the battery power consumption of the drone set in the database represents the degree of correction of the drone's battery power consumption on the drone's scheduling task execution effect value. When used, the correction factor of the drone's battery power consumption can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the drone's battery power consumption and the correction factor of the drone's battery power consumption set in the database form a mapping set, and the real-time drone's battery power consumption is input into the mapping set to obtain the correction factor of the drone's battery power consumption. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0101] The weight factor corresponding to the mission completion rate of the drone set in the database represents the degree of correction of the drone's mission completion rate on the execution effect value of the drone's scheduling task. When used, the correction factor of the drone's mission completion rate can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the drone's mission completion rate and the correction factor of the drone's mission completion rate set in the database form a mapping set. The real-time drone's mission completion rate is input into the mapping set to obtain the correction factor of the drone's mission completion rate. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0,1].

[0102] It should be noted that the execution effect value of each UAV scheduling task is extracted, and the scheduling effect of each UAV in each interval of the scheduling task execution effect value of the UAV in the database is matched to obtain the scheduling effect of each UAV, and the scheduling effect of each UAV is matched with the scheduling effect of each UAV corresponding to each interval of the scheduling task execution effect value of the UAV in the database. The scheduling effect of the UAV is preset in the database, and the scheduling effect of the UAV can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship, for example, the scheduling task execution effect value of each UAV forms a mapping set with the scheduling effect of the UAV, and the real-time scheduling task execution effect value of each UAV is input into the mapping set to obtain the scheduling effect of the UAV, wherein the mapping relationship can be a one-to-one corresponding relationship. The scheduling effect of the UAV includes unfinished, partially completed, nearly completed, and completed. The obtained UAV scheduling effect is input into the execution effect matching rule of the UAV scheduling process for fuzzy matching. When the scheduling effect of the UAV is unfinished, the matching result is that the task completion is poor, when the scheduling effect of the UAV is partially completed or nearly completed, the matching result is that the task completion is general, and when the scheduling effect of the UAV is completed, the matching result is that the task completion is successful.

[0103] It should be noted that the execution effect value of the drone task scheduling is extracted and matched with the effect value interval in the database to obtain the scheduling effect, and then the matching rules are entered to obtain the execution effect (poor, general, successful), and updated to the experience database. When formulating the scheduling plan later, refer to the historical cases and analysis results in the experience database to optimize the scheduling process.

[0104] Specifically, the environmental condition data of the flight area to which each UAV belongs and the status parameters of each UAV are collected in each preset monitoring period.

[0105] The environmental condition data of the flight area to which each UAV belongs and the status parameters of each UAV are processed and analyzed to obtain the task scheduling compliance value of each UAV, and each UAV is assigned to perform tasks according to the task scheduling compliance value of each UAV.

[0106] When each UAV is performing its mission, the environmental information received from the sensor is analyzed, and the scheduling process of each UAV is obtained based on the preset fuzzy rules.

[0107] Collect and analyze the expected completion data of each drone task, obtain the execution effect value of each drone's scheduling task, analyze the execution effect of each drone's scheduling process and update it to the experience database.

[0108] It should be noted that the data acquisition module is responsible for collecting the environmental data of the flight area where each UAV is located and the status parameters of each UAV; the task initial planning module analyzes the environmental data of the flight area where each UAV is located and the status parameters of each UAV and performs task scheduling; the fuzzy reasoning module obtains the obstacle hazard assessment value on the flight path of each UAV and the environmental safety value of each UAV in each monitoring period through fuzzy logic parameter processing fed back by the sensor, and adjusts the scheduling process of each UAV; the fuzzy logic application summary module continuously optimizes the scheduling strategy by analyzing the scheduling effect and updating the experience database, and can adaptively adjust the task scheduling process of the UAV to improve the efficiency and adaptability of the UAV in executing tasks.

[0109] It should be noted that the autonomous optimization and intelligent monitoring system of the drone also includes a database for storing and managing the environmental status data and flight parameters of the drone's flight area. In this embodiment, the database is used to store the set optimal flight altitude of the drone, the reference value of the distance between the drone and the obstacle, the set reference value of the flight speed of the drone, the set weight factor of the height of the obstacle on the flight path of the drone, the set weight factor of the distance between the drone and the obstacle, the set weight factor of the flight speed of the drone, the wind speed threshold, the visibility index threshold, the optimal battery power value for the drone to perform the mission, the reference value of the signal strength of the drone, the reference value of the straight-line distance between the drone and the mission point, the set correction factor of the signal strength of the drone, and the set distance between the drone and any task point. The correction factor of the straight-line distance to the service point, the correction factor of the set wind speed, the correction factor of the set visibility index, the correction factor of the set battery power of the UAV, the most suitable wind speed for UAV flight, the most suitable humidity for UAV flight, the most suitable temperature for UAV flight, the correction factor of the set average wind speed of the UAV's affiliated area, the correction factor of the set average humidity of the UAV's affiliated area, the correction factor of the set average temperature of the UAV's affiliated area, the weight factor corresponding to the set time efficiency of the UAV, the weight factor corresponding to the set battery power consumption of the UAV, the weight factor corresponding to the set task completion rate of the UAV, the degree of obstacle danger, the safe flight degree of the UAV's affiliated area environment, the UAV's scheduling effect, and the UAV task completion prediction data.

[0110] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0111] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Autonomous optimization and intelligent monitoring system of drones, It is characterized in that include: The data collection module is used to collect the environmental condition data of the flight area to which each UAV belongs and the status parameters of each UAV in each preset monitoring period; The initial mission planning module is used to process and analyze the environmental status data of the flight area to which each UAV belongs and the status parameters of each UAV, obtain the mission scheduling compliance value of each UAV, and assign each UAV to perform tasks according to the mission scheduling compliance value of each UAV; The fuzzy reasoning module is used to receive and analyze the environmental information from the sensors during the execution of each UAV's mission, and obtain the scheduling process of each UAV based on the preset fuzzy rules; The fuzzy logic application summary module is used to collect and analyze the expected completion data of each drone task, obtain the execution effect value of each drone's scheduling task, analyze the execution effect of each drone's scheduling process and update it to the experience database.

2. The autonomous optimization and intelligent monitoring system of the UAV according to claim 1, Features: The environmental condition data of the flight area to which each UAV belongs includes the wind speed, humidity, temperature, visibility index, the height of each obstacle, and the straight-line distance between each UAV and the mission point in the flight area to which each UAV belongs; The status parameters of each drone include the battery power, signal strength, flight altitude, flight speed, and the distance between each drone and each obstacle.

3. The autonomous optimization and intelligent monitoring system of the UAV according to claim 2, Features: The environmental condition data of the flight area to which each UAV belongs and the state parameters of each UAV are processed and analyzed to obtain the task scheduling compliance value of each UAV. The specific analysis is as follows: When each UAV receives a mission instruction, it monitors and collects the wind speed and visibility index of the flight area to which each UAV belongs at that moment, as well as the battery power, signal strength, and straight-line distance between each UAV and the mission point, and processes the collected data to obtain the mission scheduling compliance value of each UAV. The mission instruction includes the mission start time, the number of UAVs required for the mission, the longitude and latitude of the mission point, and the altitude of the mission point. The mission scheduling compliance value of each UAV is used to evaluate the matching degree between the mission and each UAV, and obtain the expected mission completion data of each UAV for each mission.

4. The autonomous optimization and intelligent monitoring system of the UAV according to claim 1, Features: The task scheduling compliance value of each drone is used to assign each drone to perform tasks. The specific analysis is as follows: The task scheduling compliance values ​​of each UAV are sorted from large to small, and starting from the first ranked UAV, the UAV with the number of task required UAVs in the task instruction is selected to perform the task.

5. The autonomous optimization and intelligent monitoring system of the UAV according to claim 1, Features: The environmental information received from the sensors during the mission execution of each UAV is analyzed, and the specific analysis is as follows: Collect environmental information on the flight path of each UAV in each monitoring period, the environmental information including the relative angle between the UAV and each obstacle, the size of each obstacle, and the height of each obstacle, and plan the flight path of each UAV based on the collected environmental information; Extract the height of each obstacle on the flight path of each UAV in each monitoring period, and monitor the distance between each UAV and each obstacle at that moment in each monitoring period. Combined with the average flight speed of each UAV in each monitoring period, the obstacle hazard assessment value on the flight path of each UAV in each monitoring period is obtained. The obstacle hazard assessment value on the flight path of each UAV in each monitoring period is used to assess the hazard level of obstacles on the flight path of the UAV. The average wind speed, average humidity and average temperature of the area to which each drone belongs in each monitoring period are extracted, and the environmental safety value of each drone in each monitoring period is obtained by processing. The environmental safety value of each drone in each monitoring period is used to quantitatively evaluate the safe flight degree of the environment of the area to which each drone belongs.

6. The autonomous optimization and intelligent monitoring system for drones according to claim 5, Features: The obstacle hazard assessment value on the flight path of each drone in each monitoring period, the specific analysis conditions are as follows: ； In the formula, represents the obstacle hazard assessment value on the flight path of the i-th UAV in the j-th monitoring period, represents the height of the qth obstacle on the flight path of the ith UAV in the jth monitoring period, represents the distance between the ith UAV and the qth obstacle at this moment in the jth monitoring cycle, represents the average flight speed of the ith UAV in the jth monitoring period, Indicates the optimal flight altitude of the drone. Indicates the reference value of the distance between the drone and the obstacle. Indicates the reference value of the flight speed of the drone. The weight factor representing the height of obstacles on the set UAV flight path, Represents the weight factor of the distance between the drone and the obstacle. Represents the weight factor of the set UAV flight speed, , i represents the number of the drone, n represents the total number of drones, , j represents the number of the monitoring cycle, m represents the total number of monitoring cycles, , q represents the number of obstacles, and g represents the total number of obstacles.

7. The autonomous optimization and intelligent monitoring system for drones according to claim 5, Features: The scheduling process of each drone is obtained based on the preset fuzzy rules, and the specific analysis is as follows: The preset fuzzy rules include obstacle risk level matching rules and execution effect matching rules of the UAV scheduling process; Extract the obstacle hazard assessment value on the flight path of each UAV in each monitoring period, match the obstacle hazard assessment value on the flight path of each UAV in each monitoring period with the hazard degree corresponding to each interval of the obstacle hazard assessment value on the flight path of the UAV in the database, obtain the hazard degree of each UAV flight path in each monitoring period, input the hazard degree of each UAV flight path in each monitoring period into the obstacle risk level matching rule for matching, and obtain the fuzzy hazard level on the flight path of each UAV in each monitoring period; The fuzzy risk level on the flight path of each drone in each monitoring period includes low risk, medium risk, and high risk. When the fuzzy risk level is low risk, the flight direction of each drone is maintained unchanged. When the fuzzy risk level is medium risk, each drone is controlled to avoid obstacles. When the fuzzy risk level is high risk, each drone is controlled to land safely. The environmental safety value of each drone in each monitoring period is extracted, and the safe flight degree of the environment of the area to which each drone belongs is matched. The safe flight degree of the environment of the area to which each drone belongs includes good safety, general safety, and poor safety. When the safe flight degree of the environment of the area to which each drone belongs is poor safety, the flight speed and flight altitude of each drone are reduced. When the safe flight degree of the environment of the area to which each drone belongs is general safety, the flight speed and flight altitude of each drone remain unchanged. When the safe flight degree of the environment of the area to which each drone belongs is good safety, the flight speed and flight altitude of each drone are increased.

8. The autonomous optimization and intelligent monitoring system of a drone according to claim 1, Features: The above-mentioned dispatching task execution effect value of each UAV is obtained, and the specific analysis is as follows: Extracting expected task completion data of each mission of each drone, wherein the expected task completion data of each mission of each drone includes expected task completion time of the drone and expected battery power consumption; The actual time for completing each task of each drone is divided by the expected time for completing the task of the drone to obtain the time efficiency of each task of each drone, and the actual battery power consumption of each drone for each task and the expected battery power consumption of the drone are combined to obtain the scheduling task execution effect value of each drone. The scheduling task execution effect value of each drone is used to evaluate the scheduling effect of each drone.

9. The autonomous optimization and intelligent monitoring system for a drone according to claim 8, Features: The execution effect of the scheduling process of each drone is analyzed and updated to the experience database. The specific analysis is as follows: Extract the scheduling task execution effect value of each UAV, match the scheduling effect of the UAV in each interval of the scheduling task execution effect value of the UAV in the database, obtain the scheduling effect of each task of each UAV, input the scheduling effect of each task of each UAV into the execution effect matching rule of the UAV scheduling process to obtain the execution effect of the scheduling process of each UAV, the execution effect of the scheduling process of each UAV includes poor task completion, general task completion, and successful task completion, and update the execution effect of the scheduling process of each UAV to the experience database.

10. Autonomous optimization and intelligent monitoring methods of drones, Features: include Collect environmental condition data of the flight area to which each UAV belongs and status parameters of each UAV in each preset monitoring period; Process and analyze the environmental status data of the flight area to which each UAV belongs and the status parameters of each UAV to obtain the task scheduling compliance value of each UAV, and assign each UAV to perform tasks according to the task scheduling compliance value of each UAV; The environmental information received from the sensors is analyzed during the mission execution of each UAV, and the scheduling process of each UAV is obtained based on the preset fuzzy rules; Collect and analyze the expected completion data of each drone task, obtain the execution effect value of each drone's scheduling task, analyze the execution effect of each drone's scheduling process and update it to the experience database.

Images