Unmanned aerial vehicle group cooperative action scheduling method based on distributed calculation

Abstract

The invention relates to the technical field of unmanned aerial vehicle action scheduling, in particular to an unmanned aerial vehicle group cooperative action scheduling method based on distributed computing. The method comprises the following steps: carrying out cooperative task path topological structure analysis on unmanned aerial vehicle group cooperative task data, and carrying out dynamic environment perception to obtain task path dynamic environment perception data; performing path airflow dynamic evolution analysis on the task path dynamic environment sensing data, performing disordered gas field simulation in the flight process of the unmanned aerial vehicle group, and then calculating power required by out-of-order state struggling to obtain power data required by out-of-order struggling; and calculating the struggling force required by the out-of-sequence of the structural points of the unmanned aerial vehicle for the power data required by the out-of-sequence struggling, carrying out attitude cooperative control adjustment, and then carrying out cooperative action scheduling optimization to obtain unmanned aerial vehicle cooperative action scheduling optimization data. According to the invention, the unmanned aerial vehicle action scheduling technology is optimized, so that the unmanned aerial vehicle action scheduling technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) action scheduling, and in particular to a method for scheduling coordinated action of a swarm of unmanned aerial vehicles (UAVs) based on distributed computing. Background Art

[0002] With the rapid development of drone technology, drone swarms are becoming more and more popular in many fields, such as disaster relief, agricultural monitoring, and environmental monitoring. The previous centralized scheduling method is prone to computing resource bottlenecks and single point failures when facing large-scale drone swarms, affecting the reliability and efficiency of task execution. Distributed computing achieves effective utilization of computing resources and load balancing by distributing computing tasks to each drone node. Each drone node not only performs its own tasks, but also participates in collaborative decision-making and information sharing to form a highly autonomous intelligent network system. This method uses a variety of advanced algorithms, such as distributed optimization algorithms, reinforcement learning, and machine learning algorithms, to achieve adaptive scheduling and real-time adjustment of drone swarms to cope with dynamic environments and emergencies. In addition, distributed computing can improve the scalability of the system, allowing the system to easily cope with the increase in the number of drones without reducing performance. In this way, drone swarms can achieve efficient and stable collaborative work in complex and uncertain environments, providing strong technical support for various tasks. However, a traditional method for scheduling coordinated actions of drone swarms based on distributed computing has the problem of being unable to accurately judge the impact of turbulent airflow in the environment and unable to perform attitude adjustment control well. Summary of the invention

[0003] Based on this, it is necessary to provide a method for scheduling coordinated actions of drone swarms based on distributed computing to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for scheduling coordinated actions of drone swarms based on distributed computing is provided, the method comprising the following steps: Step S1: Acquire the UAV swarm collaborative task data; perform collaborative task path topology structure analysis on the UAV swarm collaborative task data to obtain collaborative task path topology structure data; perform dynamic environment perception on the collaborative task path topology structure data to obtain task path dynamic environment perception data; Step S2: Acquire the rotation structure data of the drone; perform rotation inertia characteristic analysis on the rotation structure data of the drone to obtain rotation inertia characteristic data; perform airflow flow and pressure structure analysis on the drone group according to the rotation inertia characteristic data to obtain airflow flow and pressure structure data on the drone group; perform path airflow dynamic evolution analysis on the dynamic environment perception data of the mission path to obtain path airflow dynamic evolution data; perform turbulent air field simulation during the flight of the drone group according to the airflow flow and pressure structure data of the drone group and the path airflow dynamic evolution data to obtain turbulent air field data in the flight state; Step S3: Calculating the power required for breaking free from the disordered state based on the flight state disordered aura data to obtain the power data required for breaking free from the disordered state; Step S4: Based on distributed computing, the power data required for disordered escape is used to calculate the escape force required for disordered structural points of the UAV, and the escape force data required for disordered structural points are obtained; attitude collaborative control adjustment is performed according to the escape force data required for disordered structural points, and attitude collaborative control adjustment data is obtained; collaborative action scheduling optimization is performed according to the attitude collaborative control adjustment data, and the collaborative action scheduling optimization data of the UAV is obtained.

[0005] The present invention can optimize the task path planning by analyzing the topological structure of the UAV group collaborative task data, ensure the shortest path and the most efficient flight route, thereby saving energy and time. Identifying and analyzing the path topological structure can help reduce the risk of collision and conflict between UAVs and improve the safety and reliability of task execution. Dynamic environmental perception of the collaborative task path can respond to environmental changes in a timely manner, such as changes in factors such as wind speed and airflow, so as to adjust the flight strategy and path planning to ensure the stability and success rate of task execution. Acquiring dynamic environmental perception data helps the UAV group adapt to the changing external conditions in a complex environment and improve its adaptability and flexibility. By analyzing the inertial characteristics of the UAV rotating structure, the flight control system of the UAV can be optimized to improve its stability and control accuracy in the air. Understanding the rotational inertial characteristics helps to reduce the control error and flight risk caused by rotational inertia during flight and improve flight safety. Analysis based on the airflow flow pressure structure data can optimize the aerodynamic design of the UAV group, reduce flight resistance, and improve fuel efficiency and endurance. Effective airflow flow pressure structure analysis helps to optimize flight attitude and flight speed, and improve flight efficiency and overall performance. By analyzing the dynamic evolution data of the path airflow, future airflow changes and risks can be predicted, helping the drone group to make real-time adjustments and responses during flight, and reducing the possibility of accidents. Turbulent aura simulation helps to test the flight performance and stability of the drone group under complex airflow conditions in a virtual environment, identify potential flight risks in advance and take preventive measures. By simulating different turbulent aura conditions, flight strategies can be optimized and the response capabilities and adaptability in complex environments can be improved. By analyzing the turbulent aura data of the flight state, it is possible to predict the disorder that the drone may face in a complex environment, such as airflow turbulence or stall, and take preventive and response measures in advance to ensure flight safety. Calculating the power data required for disorder breakaway helps determine how much additional power the drone needs to restore normal flight status under different disorder conditions, thereby avoiding potential accident risks. Based on distributed computing, calculating the breakaway force data required for structural point disorder can help optimize the structural design of the drone and enhance its stability and tolerance under disorder conditions. According to the disorder breakaway force data, attitude collaborative control adjustment is performed, that is, the attitude of the aircraft is adjusted to deal with disorder conditions, thereby improving the control accuracy and stability of the aircraft. According to the attitude collaborative control adjustment data, the coordinated action scheduling of drones is optimized to ensure that the drone swarm can complete the task in the most efficient and safe way in the collaborative mission. Optimized scheduling can reduce the waste of resources such as fuel and time, while maximizing the efficiency and success rate of mission execution.Therefore, the present invention optimizes a traditional method for scheduling coordinated action of drone swarms based on distributed computing, solves the problem that a traditional method for scheduling coordinated action of drone swarms based on distributed computing cannot accurately judge the impact of turbulent airflow in the environment and cannot perform attitude adjustment control well, improves the accuracy of judging the impact of turbulent airflow in the environment and improves the ability to perform attitude adjustment control.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire drone group collaborative task data; Step S12: performing data cleaning on the drone swarm collaborative task data to obtain drone swarm collaborative task cleaning data; Step S13: performing collaborative task path topology structure analysis on the drone swarm collaborative task data according to the drone swarm collaborative task cleaning data to obtain collaborative task path topology structure data; Step S14: Perform dynamic environmental perception on the collaborative task path topological structure data to obtain task path dynamic environmental perception data.

[0007] The present invention collects the original data of the UAV swarm collaborative task, including task objectives, path planning, flight plans, etc., to provide a data basis for subsequent analysis and optimization. Cleaning the UAV swarm collaborative task data can remove duplicate, incomplete or erroneous data, and ensure the data quality reliability of analysis and model establishment. Cleaning data helps to improve the accuracy and consistency of data and reduce interference factors in the subsequent analysis process. Analyzing the collaborative task path topology data can optimize the UAV flight path, reduce flight time and energy consumption, and improve the efficiency of task execution. Through path topology structure analysis, potential flight conflict points are identified, and preventive measures are taken to reduce the risk of collision during the flight of the UAV swarm. Through dynamic environmental perception, real-time monitoring of changes in environmental conditions such as meteorology and aerodynamics of the task path helps to adjust flight strategies and path planning to ensure flight safety and stability. Dynamic environmental perception data improves the adaptability of the UAV swarm in complex environments, enabling it to cope with factors such as changing wind speed and airflow, and ensure the success rate and efficiency of task execution.

[0008] Preferably, step S2 comprises the following steps: Step S21: Acquire the UAV rotation structure data; Step S22: performing rotational inertia characteristic analysis on the rotating structure data of the UAV to obtain rotational inertia characteristic data; Step S23: analyzing the airflow and pressure structure of the drone group according to the rotational inertia characteristic data to obtain the airflow and pressure structure data of the drone group; Step S24: performing path airflow dynamic evolution analysis on the task path dynamic environment perception data to obtain path airflow dynamic evolution data; Step S25: simulate the turbulent air field during the flight of the drone group according to the airflow and pressure structure data of the drone group and the dynamic evolution data of the path airflow to obtain the turbulent air field data in the flight state.

[0009] The present invention obtains data of the rotating structure of the unmanned aerial vehicle, including structural information and parameters of each component of the aircraft, and provides complete basic data for subsequent analysis and simulation. By analyzing the rotational inertia characteristic data, the flight control system of the unmanned aerial vehicle is optimized to improve its stability and control accuracy in the air. Understanding the rotational inertia characteristics helps to reduce the control error and flight risk caused by rotational inertia during flight, and improve flight safety. According to the air flow pressure structure data, the aerodynamic design of the unmanned aerial vehicle group is optimized, the flight resistance is reduced, the fuel efficiency and endurance are improved, and the optimization of the aerodynamic design can effectively reduce energy consumption, extend the flight time of the unmanned aerial vehicle, and improve the efficiency and reliability of task execution. Analyzing the dynamic evolution data of the path airflow helps to predict risks, and adjust the flight path in real time during flight to reduce the risk of encountering adverse airflow conditions. Effective airflow dynamic evolution analysis can help the unmanned aerial vehicle group maintain safe flight in complex environments and reduce the occurrence of accidents. By simulating different turbulent aura conditions, the flight response of the unmanned aerial vehicle in a complex environment is predicted, which helps to optimize the flight strategy and countermeasures. Simulating the turbulent aura helps to identify potential flight risks, take preventive measures, reduce the possibility of accidents, and ensure the smooth completion of flight missions.

[0010] Preferably, step S23 includes the following steps: Step S231: extracting the rotation axis position from the rotation inertia characteristic data to obtain the rotation axis position data; Step S232: performing blade rotation aerodynamic structure simulation on the rotation inertia characteristic data according to the rotation axis position data to obtain blade rotation aerodynamic structure data; Step S233: performing blade rotation unsteady effect analysis on the blade rotation aerodynamic structure data to obtain blade unsteady aerodynamic effect data; Step S234: calculating the aerodynamic load according to the unsteady aerodynamic effect data of the blade to obtain the unsteady aerodynamic load data; Step S235: analyzing the circumferential airflow intensity distribution of the UAV group according to the unsteady aerodynamic load data and the blade rotation aerodynamic structure data to obtain circumferential airflow intensity distribution data; Step S236: Perform airflow flow and pressure structure analysis of the UAV swarm based on the circumferential airflow intensity distribution data, the unsteady aerodynamic load data, and the blade rotation aerodynamic structure data to obtain the airflow flow and pressure structure data of the UAV swarm.

[0011] The present invention extracts the rotation axis position data to help ensure that the subsequent analysis and simulation of the rotation inertia characteristic data is based on the accurate rotation center point, thereby avoiding flight control errors caused by inaccurate axis position. By simulating the aerodynamic structure of blade rotation, the aerodynamic characteristics of the blade during flight can be accurately predicted, the blade design can be optimized, the flight resistance can be reduced, and the flight efficiency can be improved. Understanding the impact of blade rotation on air flow helps to adjust the flight strategy under different environmental conditions and cope with complex flight scenarios. Analyzing the unsteady aerodynamic effects of blade rotation can reduce the negative impact of these effects on the flight stability of the UAV and improve the responsiveness and stability of the flight control system. Adjusting the flight control strategy according to the unsteady effect data can reduce the vibration and dynamic response of the UAV in a complex aerodynamic environment and improve flight safety. Calculating the unsteady aerodynamic load data helps to accurately predict the aerodynamic loads on the blades under different flight conditions and provide basic data for structural design and flight control. Optimizing the blade structure design according to the aerodynamic load data can enhance its load-bearing capacity and wind resistance, extend its service life and reduce maintenance costs. Analyzing the circumferential airflow intensity distribution data can help the UAV group better perceive the surrounding airflow environment, adjust the flight path and attitude in real time, and ensure a stable flight state. Predicting the circumferential airflow intensity distribution helps predict possible flight risks in advance, take preventive measures, and avoid accidents. Based on the analysis of airflow flow pressure structure data, the aerodynamic design of the drone swarm is optimized to reduce flight resistance and improve flight efficiency and energy utilization. Understanding the airflow flow pressure structure helps reduce aerodynamic instability factors during flight and improve the flight safety of drone swarms in complex airflow environments.

[0012] Preferably, step S25 comprises the following steps: Step S251: analyzing the flight axial airflow concentration effect according to the UAV group airflow flow pressure structure data and the path airflow dynamic evolution data to obtain the flight axial airflow concentration effect data; Step S252: Calculating the axial airflow velocity difference on the flight axial airflow gathering effect data to obtain axial airflow velocity difference data; Step S253: performing a three-dimensional spatial vortex structure analysis of the drone group according to the axial airflow velocity difference data and the path airflow dynamic evolution data to obtain spatial vortex structure analysis data; Step S254: performing intermittent vortex aggregation energy scale calculation on the spatial vortex structure analysis data to obtain intermittent vortex aggregation energy scale data; Step S255: simulate the turbulent air field during the flight of the drone group according to the spatial vortex structure analysis data and the intermittent vortex aggregation energy scale data to obtain the turbulent air field data in the flight state.

[0013] By analyzing the flight axial airflow aggregation effect data, the present invention can accurately understand the airflow changes on the flight path and provide a basis for flight path planning and adjustment. Identifying and predicting the axial airflow aggregation effect helps to optimize the route planning of the drone group, ensure that favorable airflow conditions are avoided or utilized during flight, and improve flight efficiency and safety. Calculating the axial airflow velocity difference data helps to accurately evaluate the air flow conditions on the flight path, improve the responsiveness of the drone group to environmental changes, and reduce flight risks. Adjust the flight control strategy according to the velocity difference data to ensure flight stability and control accuracy under different airflow conditions. Analyzing the three-dimensional space vortex structure data helps to deeply understand the complex aerodynamic environment around the flight path of the drone group, including the formation and evolution process of the vortex. Optimize flight path planning based on vortex structure data, reduce energy consumption and risks, and improve flight efficiency and safety. Calculating intermittent vortex aggregation energy scale data helps to predict possible flight risks, including challenges and instabilities that may be encountered in complex vortex structures. Adjust the flight control strategy according to the energy scale data to effectively respond to possible turbulence and improve flight safety and stability. The turbulent air field simulation is carried out based on the spatial vortex structure analysis and vortex aggregation energy scale data to simulate the complex airflow environment that may be encountered during real flight. The simulation of turbulent air field helps to predict and reduce adverse effects during flight, take measures in advance to reduce risks, and optimize flight strategies to ensure the smooth completion of the mission.

[0014] Preferably, performing intermittent eddy aggregation energy scale calculation on spatial eddy structure analytical data comprises the following steps: Perform nonlinear dynamic structural analysis on the spatial vortex structure analytical data to obtain the spatial vortex nonlinear dynamic data; According to the spatial vortex nonlinear dynamic data, the spatial vortex structure analysis data is analyzed for the spatial vortex time series dynamic evolution to obtain the spatial vortex time series dynamic evolution data; Performing dynamic intermittency analysis on the spatial vortex time series dynamic evolution data to obtain the spatial vortex dynamic time series intermittent data; According to the spatial vortex dynamic time series intermittent data, the multi-scale vortex aggregation effect analysis is performed on the spatial vortex time series dynamic evolution data to obtain the dynamic multi-scale vortex aggregation effect data; Based on Lebesgue integral, the dynamic multi-scale eddy aggregation effect data is measured in multi-scale space to obtain dynamic multi-scale space measurement data; The intermittent vortex aggregation energy scale is calculated based on the dynamic multi-scale vortex aggregation effect data and the dynamic multi-scale spatial measurement data to obtain the intermittent vortex aggregation energy scale data.

[0015] The present invention can deeply understand the complex dynamic characteristics of space vortices, including the formation mechanism and nonlinear interaction of vortices, through nonlinear dynamic structure analysis. Obtaining nonlinear dynamic data of space vortices helps to accurately describe the spatiotemporal evolution process of vortices and provide a basis for subsequent analysis. According to the nonlinear dynamic data, the temporal dynamic evolution of space vortices is analyzed to capture the temporal variation characteristics of vortices, including their intensity, position and evolution path. Understanding the dynamic evolution of vortices in different time periods provides detailed information for assessing their potential impact on flight status. Intermittent analysis is performed on the temporal dynamic evolution data of space vortices to identify and quantify intermittent changes in vortex dynamics in time, such as explosive events or periodic changes. Understanding dynamic intermittency helps predict and reduce unstable factors that may be encountered in flight, and improve flight safety and control efficiency. According to dynamic intermittent data, the aggregation effect of vortices at multiple scales, that is, the diffusion and aggregation characteristics of vortices in space and time, is analyzed. Understanding the vortex aggregation effect helps simulate flight challenges in complex environments and optimize flight path planning and control strategies. Based on the Lebesgue integral, the multi-scale vortex aggregation effect data is spatially measured to quantify the vortex distribution and energy distribution at different scales. Providing multi-scale spatial measurement data helps to deeply understand the spatial distribution characteristics of vortices and provide an accurate basis for flight path planning and control strategies. Based on the dynamic multi-scale vortex aggregation effect data and multi-scale spatial measurement data, the intermittent vortex aggregation energy scale is calculated to quantify the energy changes of vortices in time and space. Providing intermittent vortex aggregation energy scale data is helpful for risk management and flight control strategy optimization, reducing possible unstable factors and energy consumption during flight.

[0016] Preferably, step S3 comprises the following steps: Step S31: performing flight power disorder calculation according to the flight state disordered aura data to obtain flight power disorder data; Step S32: performing critical state perception on the flight power disorder data to obtain flight power disorder critical perception data; Step S33: Calculate the power required to break free from the disordered state based on the flight power disorder critical perception data and obtain the power data required to break free from the disordered state.

[0017] The present invention calculates the flight power disorder data based on the flight state disorder aura data, which is helpful for real-time identification of power disorder situations occurring during flight. Providing flight power disorder data can help the UAV system or pilot to respond and adjust the flight strategy in a timely manner to maintain the stability and safety of the flight. The flight power disorder data is subjected to critical state perception, that is, the conditions and characteristics under which the flight power disorder reaches a critical state are identified. Through the critical perception data, an early warning mechanism is established to promptly notify the operator or automatically adjust the system to deal with potential flight disorder risks, thereby ensuring safety and stability during flight. Based on the critical perception data of flight power disorder, the power data required to break free from the disorder state is calculated, that is, the minimum power required to restore normal flight is evaluated. Providing the power data required to break free from the disorder state helps to optimize the flight control strategy and ensure that the normal flight state can be effectively restored when a disorder situation occurs.

[0018] Preferably, step S31 includes the following steps: Step S311: performing an air field pressure fluctuation analysis on the flight state turbulent air field data to obtain turbulent air field pressure fluctuation data; Step S312: Calculating the wind shear intensity of the turbulent air field data in the flight state according to the turbulent air field pressure fluctuation data to obtain the air field wind shear intensity data; Step S313: performing flight attitude instability force simulation according to the air field wind shear intensity data and the turbulent air field pressure fluctuation data to obtain flight attitude instability force data; Step S314: performing flight power disorder calculation according to the aura wind shear intensity data and the flight attitude instability force data to obtain flight power disorder data.

[0019] The present invention performs an aura pressure fluctuation analysis on the turbulent aura data in flight state, which helps to identify and quantify the pressure fluctuations in the aura, such as airflow turbulence or irregular airflow structure. Providing turbulent aura pressure fluctuation data allows the system to more accurately understand and simulate the aerodynamic influence in the flight environment, providing a basis for subsequent analysis. The wind shear intensity, that is, the degree of sudden change in air velocity and direction, is calculated based on the turbulent aura pressure fluctuation data. Providing aura wind shear intensity data helps to analyze its potential impact on the attitude and stability of the aircraft, especially in a complex or unstable airflow environment. Based on the aura wind shear intensity data and the turbulent aura pressure fluctuation data, the attitude instability encountered by the aircraft in an unstable airflow is simulated. The external force and disturbance data received when the flight attitude is unstable are obtained, including the attitude change and force direction of the aircraft, providing key information for evaluating flight safety. The flight power disorder calculation is performed based on the aura wind shear intensity data and the flight attitude instability force data, that is, the power change and adjustment required by the aircraft in the disordered state are evaluated. Providing flight dynamics disorder data helps develop strategies to deal with disorder situations, including automatically adjusting the flight attitude or guiding the aircraft to return to a stable state.

[0020] Preferably, step S33 includes the following steps: Step S331: analyzing the rapid change of power disorder on the flight power disorder critical perception data to obtain the power disorder rapid change data; Step S332: performing stall state identification according to the power disorder rapid change data to obtain power stall state identification data; Step S333: calculating the out-of-control acceleration increment based on the power stall state identification data to obtain the power out-of-control acceleration increment data; Step S334: Calculate the power required to break free from the disordered state based on the flight state disordered aura data according to the power out-of-control acceleration increment data to obtain the power data required to break free from the disordered state.

[0021] The present invention analyzes critical perception data of flight power disorder and identifies the rapid change characteristics of power disorder. The rapid change data of power disorder is obtained, including the rapid change of the power system, such as the sudden change of engine output, thrust or control surface. The early warning and identification capabilities before the occurrence of flight power disorder are provided, so that the system can perceive the potential risk of aircraft power disorder earlier. An accurate data basis is provided for subsequent steps to further identify and respond to the stall state. The stall state is identified according to the rapid change data of power disorder, that is, whether the aircraft has entered the state of power out of control, and the power stall state identification data is obtained, indicating that the aircraft may be in a power disorder state, providing a key basis for judging the stall state, helping the system to quickly identify the safety state of the aircraft, so as to take timely and effective countermeasures, reducing the time delay of stall state identification, and enhancing the system's sensitivity and response to power disorder problems. Based on the power stall state identification data, the out-of-control acceleration increment is calculated, that is, the acceleration change that the aircraft may experience in the stall state, and the power out-of-control acceleration increment data is obtained, which is helpful to quantify the response and stability of the aircraft power system in the out-of-control state. It provides detailed information on the forces and responses of the aircraft power system in the out-of-control state, and provides accurate input for the subsequent out-of-order breakaway calculation. It helps the system understand and evaluate the power out-of-order conditions that may occur in the stall state, and provides an important basis for flight safety assessment. According to the power out-of-control acceleration increment data, the power required for out-of-order breakaway is calculated for the chaotic aura data in the flight state, and the power data required for out-of-order breakaway is obtained, that is, the power adjustment and response capabilities required by the aircraft in the out-of-control state. It provides power adjustment solutions and response strategies for aircraft in the out-of-order state, helps the system optimize the power response capabilities of the aircraft, and ensures that the system can take necessary flight control measures in time during the flight process based on real-time out-of-order state data to ensure the safe flight of the aircraft.

[0022] Preferably, step S4 comprises the following steps: Step S41: Based on distributed computing, the power data required for breaking free from disorder is used to calculate the breaking free force required for the disordered structure points of the UAV, and the breaking free force data required for the disordered structure points are obtained; Step S42: Based on the attention mechanism, the required breakaway force data of the disordered structure points are processed to balance the required breakaway forces of different structure points, so as to obtain the required breakaway force balance data of the structure points; Step S43: performing posture collaborative control adjustment according to the required breakaway force balance data of the structural point to obtain posture collaborative control adjustment data; Step S44: performing coordinated action scheduling optimization according to the required breakaway force balance data of the structural points and the attitude coordinated control adjustment data to obtain the coordinated action scheduling optimization data of the UAV.

[0023] The present invention uses distributed computing technology to calculate the power data required for disordered escape, especially the escape force required for each structure of the drone when it encounters disorder. Through distributed computing, a large amount of data can be processed and complex calculations can be performed, which improves the accuracy and speed of the calculation. The escape force data for the disorder of the drone structure points is provided, which provides key input for the subsequent steps. Based on data-driven calculation, it is ensured that the drone can accurately respond and maintain structural integrity in the case of disorder, and the out-of-control response capability of the aircraft is improved. Based on the attention mechanism, the escape force data required for the disorder of different structural points are balanced, ensuring that each key structural point of the drone can evenly withstand the escape force in the case of disorder, and obtaining the escape force balance data required by the structural point, that is, the balance distribution of the escape force required by each structural point when it is out of order, improving the overall stability and safety of the drone structure when it is out of order, ensuring that the escape force of each structural point can be effectively coordinated and balanced, and reducing the imbalance of the escape force between the structural points through the optimization of the attention mechanism, improving the overall structural strength and response capability of the aircraft, and performing attitude collaborative control adjustment according to the escape force balance data required by the structural point to ensure that the drone can maintain proper flight in the case of disorder. Attitude, get attitude collaborative control adjustment data, that is, the attitude adjustment plan required by the aircraft when it is out of order, improve the flight stability and control accuracy of the UAV in the out-of-order state, ensure that the aircraft can effectively respond to the disorder, and ensure the flight safety and operational stability of the aircraft by adjusting the flight attitude in real time, reduce the potential risks caused by the disorder, combine the balance data of the breakaway force required by the structural point and the attitude collaborative control adjustment data, and optimize the collaborative action scheduling to obtain the UAV collaborative action scheduling optimization data, that is, the optimal action scheduling plan of the aircraft in the out-of-order state, improve the UAV team's collaborative combat capability in complex environments, and ensure that multiple aircraft can effectively coordinate to respond to the disorder. Optimize the allocation and use efficiency of resources, and improve the overall response capability and task completion rate of the UAV team.

[0024] The beneficial effect of the present invention is that by analyzing the topological structure of the collaborative task data of the drone group, the task path planning can be optimized to ensure the shortest path and the most efficient flight route, thereby saving energy and time. Identifying and analyzing the path topological structure can help reduce the risk of collision and conflict between drones and improve the safety and reliability of task execution. Dynamic environmental perception of the collaborative task path can respond to environmental changes in a timely manner, such as changes in factors such as wind speed and airflow, so as to adjust the flight strategy and path planning to ensure the stability and success rate of task execution. Acquiring dynamic environmental perception data helps the drone group adapt to the changing external conditions in a complex environment and improve its adaptability and flexibility. By analyzing the inertial characteristics of the drone's rotating structure, the flight control system of the drone can be optimized to improve its stability and control accuracy in the air. Understanding the rotational inertial characteristics helps to reduce the control error and flight risk caused by rotational inertia during flight, and improve flight safety. Analysis based on the airflow flow pressure structure data can optimize the aerodynamic design of the drone group, reduce flight resistance, and improve fuel efficiency and endurance. Effective airflow flow pressure structure analysis helps to optimize flight attitude and flight speed, and improve flight efficiency and overall performance. By analyzing the dynamic evolution data of the path airflow, future airflow changes and risks can be predicted, helping the drone group to make real-time adjustments and responses during flight, and reducing the possibility of accidents. Turbulent aura simulation helps to test the flight performance and stability of the drone group under complex airflow conditions in a virtual environment, identify potential flight risks in advance and take preventive measures. By simulating different turbulent aura conditions, flight strategies can be optimized and the response capabilities and adaptability in complex environments can be improved. By analyzing the turbulent aura data of the flight state, it is possible to predict the disorder that the drone may face in a complex environment, such as airflow turbulence or stall, and take preventive and response measures in advance to ensure flight safety. Calculating the power data required for disorder breakaway helps determine how much additional power the drone needs to restore normal flight status under different disorder conditions, thereby avoiding potential accident risks. Based on distributed computing, calculating the breakaway force data required for structural point disorder can help optimize the structural design of the drone and enhance its stability and tolerance under disorder conditions. According to the disorder breakaway force data, attitude collaborative control adjustment is performed, that is, the attitude of the aircraft is adjusted to deal with disorder conditions, thereby improving the control accuracy and stability of the aircraft. According to the attitude collaborative control adjustment data, the coordinated action scheduling of drones is optimized to ensure that the drone swarm can complete the task in the most efficient and safe way in the collaborative mission. Optimized scheduling can reduce the waste of resources such as fuel and time, while maximizing the efficiency and success rate of mission execution.Therefore, the present invention optimizes a traditional method for scheduling coordinated action of drone swarms based on distributed computing, solves the problem that a traditional method for scheduling coordinated action of drone swarms based on distributed computing cannot accurately judge the impact of turbulent airflow in the environment and cannot perform attitude adjustment control well, improves the accuracy of judging the impact of turbulent airflow in the environment and improves the ability to perform attitude adjustment control. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of the steps of a method for coordinating actions of drone swarms based on distributed computing; Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0026] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0027] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0028] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0029] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0030] To achieve this, please refer to Figure 1 to Figure 2, a method for scheduling coordinated actions of a drone group based on distributed computing, the method comprising the following steps: Step S1: Acquire the UAV swarm collaborative task data; perform collaborative task path topology structure analysis on the UAV swarm collaborative task data to obtain collaborative task path topology structure data; perform dynamic environment perception on the collaborative task path topology structure data to obtain task path dynamic environment perception data; Step S2: Acquire the rotation structure data of the drone; perform rotation inertia characteristic analysis on the rotation structure data of the drone to obtain rotation inertia characteristic data; perform airflow flow and pressure structure analysis on the drone group according to the rotation inertia characteristic data to obtain airflow flow and pressure structure data on the drone group; perform path airflow dynamic evolution analysis on the dynamic environment perception data of the mission path to obtain path airflow dynamic evolution data; perform turbulent air field simulation during the flight of the drone group according to the airflow flow and pressure structure data of the drone group and the path airflow dynamic evolution data to obtain turbulent air field data in the flight state; Step S3: Calculating the power required for breaking free from the disordered state based on the flight state disordered aura data to obtain the power data required for breaking free from the disordered state; Step S4: Based on distributed computing, the power data required for disordered escape is used to calculate the escape force required for disordered structural points of the UAV, and the escape force data required for disordered structural points are obtained; attitude collaborative control adjustment is performed according to the escape force data required for disordered structural points, and attitude collaborative control adjustment data is obtained; collaborative action scheduling optimization is performed according to the attitude collaborative control adjustment data, and the collaborative action scheduling optimization data of the UAV is obtained.

[0031] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for scheduling coordinated actions of drone swarms based on distributed computing of the present invention. In this example, the method for scheduling coordinated actions of drone swarms based on distributed computing includes the following steps: Step S1: Acquire the UAV swarm collaborative task data; perform collaborative task path topology structure analysis on the UAV swarm collaborative task data to obtain collaborative task path topology structure data; perform dynamic environment perception on the collaborative task path topology structure data to obtain task path dynamic environment perception data; In an embodiment of the present invention, the collaborative task data of the drone group is obtained through the cloud, and the real-time position, speed and attitude data are obtained by installing high-precision GPS and inertial navigation systems on multiple drones. These data are transmitted to the central control system through a wireless communication network to form the collaborative task data of the drone group. The collaborative task path topology structure analysis is performed on the collaborative task data of the drone group, and the communication link, collaborative operation area and task allocation between the drones are modeled and analyzed using a graph theory algorithm. The specific operation includes: according to the real-time position data of the drone, an undirected graph is constructed, the node represents the drone, and the edge represents the communication link between the drones. The Dijkstra algorithm is applied to calculate the shortest path and generate the collaborative task path topology structure data. The collaborative task path topology structure data is dynamically perceived, and the dynamic environment information in the task area is monitored in real time using environmental sensors (such as laser radar, infrared sensor, ultrasonic sensor). The sensor data is transmitted to the central control system through a wireless communication network, and the dynamic environment perception data of the task path is generated in combination with the drone position and task path information. The specific operation includes: the laser radar sensor scans the environment, generates point cloud data, uses the point cloud data to build an environmental map, and matches it with the topology structure data to identify dynamic obstacles and changes in the environment.

[0032] Step S2: Acquire the rotation structure data of the drone; perform rotation inertia characteristic analysis on the rotation structure data of the drone to obtain rotation inertia characteristic data; perform airflow flow and pressure structure analysis on the drone group according to the rotation inertia characteristic data to obtain airflow flow and pressure structure data on the drone group; perform path airflow dynamic evolution analysis on the dynamic environment perception data of the mission path to obtain path airflow dynamic evolution data; perform turbulent air field simulation during the flight of the drone group according to the airflow flow and pressure structure data of the drone group and the path airflow dynamic evolution data to obtain turbulent air field data in the flight state; In an embodiment of the present invention, the rotational structure data of the drone is obtained, and the rotational motion parameters such as the angular velocity, acceleration and angle change of the rotor are recorded in real time by installing a high-precision gyroscope and accelerometer on the rotor of the drone. These data are transmitted to the central control system through a wireless communication network to form the rotational structure data of the drone. The rotational inertia characteristics of the drone rotational structure data are analyzed, and the motion state and force conditions of the drone rotor are calculated and simulated using a multi-body dynamics model and a finite element analysis method. The specific operation includes: constructing a three-dimensional geometric model of the drone rotor, inputting the rotational structure data, applying finite element analysis software (such as ANSYS) to calculate the inertia moment and structural deformation of the rotor at different rotation speeds, and generating rotational inertia characteristic data. The airflow flow and pressure structure of the drone group is analyzed according to the rotational inertia characteristic data, and the airflow field generated by the drone group during flight is simulated and analyzed using computational fluid dynamics (CFD) software (such as Fluent). The specific operation includes: constructing a three-dimensional fluid model of the drone group according to the rotational inertia characteristic data, setting boundary conditions and fluid parameters, running CFD simulation, calculating the airflow velocity field and pressure distribution around the drone group, and generating the airflow flow and pressure structure data of the drone group. The dynamic evolution analysis of the path airflow is performed on the dynamic environmental perception data of the mission path. The environmental change information in the dynamic environmental perception data of the mission path is used in combination with the airflow flow pressure structure data to simulate the evolution of the airflow field of the UAV in a dynamic environment. The specific operations include: inputting the path dynamic environmental perception data, updating the boundary conditions and fluid parameters in the CFD model, running dynamic simulation, calculating the changes in the airflow field of the UAV under different paths and environments, and generating the path airflow dynamic evolution data. The turbulent air field simulation during the flight of the UAV swarm is performed based on the airflow flow pressure structure data of the UAV swarm and the path airflow dynamic evolution data, and the flight state of the UAV swarm in a complex airflow environment is simulated and analyzed using a turbulence model (such as the k-ε model). The specific operations include: inputting the airflow flow pressure structure data and the path airflow dynamic evolution data, setting the turbulence model parameters, running turbulence simulation, calculating the turbulent field distribution and aerodynamic changes of the UAV swarm during flight, and generating the flight state turbulent air field data.

[0033] Step S3: Calculating the power required for breaking free from the disordered state based on the flight state disordered aura data to obtain the power data required for breaking free from the disordered state; In the embodiment of the present invention, the power required to break free from the disordered state is calculated for the flight state disordered aura data, and the flight dynamics characteristics of the UAV in the disordered aura are analyzed and calculated using flight mechanics and control theory. The specific operation includes: first, according to the flight state disordered aura data, a six-degree-of-freedom dynamic model of the UAV is established, and the model contains basic parameters such as the mass, center of gravity position, and inertia matrix of the UAV. Next, the Newton-Euler equation is used to describe the movement of the UAV in three-dimensional space, and the aerodynamic force and aerodynamic moment in the turbulent aura are calculated. These aerodynamic forces and aerodynamic moments include the lift, drag and side force generated by the airflow on the UAV, as well as the pitch, yaw and roll moments generated on the UAV. In order to determine the power required to break free from the disordered state, the robust control method in control theory is applied to design and simulate the flight control system of the UAV. The specific steps include: according to the dynamic model of the UAV, a robust controller adapted to the turbulent aura is designed, and the controller can maintain the stable flight of the UAV in a strong interference environment. Lyapunov stability theory is applied to analyze the stability of the control system, and simulation tools such as MATLAB / Simulink are used to simulate the flight process of the UAV in the turbulent air field, and the thrust and torque required for the UAV to recover from the disordered state to stable flight are calculated. Through multiple simulations and adjustments, the minimum power data required for the UAV to break free from disorder under different turbulent air field conditions is obtained, and a power data report required for the disordered break free is generated.

[0034] Step S4: Based on distributed computing, the power data required for disordered escape is used to calculate the escape force required for disordered structural points of the UAV, and the escape force data required for disordered structural points are obtained; attitude collaborative control adjustment is performed according to the escape force data required for disordered structural points, and attitude collaborative control adjustment data is obtained; collaborative action scheduling optimization is performed according to the attitude collaborative control adjustment data, and the collaborative action scheduling optimization data of the UAV is obtained.

[0035] In an embodiment of the present invention, the power data required for disordered escape is used to calculate the escape force required for the disordered structure points of the UAV based on distributed computing, and the high-performance computing cluster is used to parallelly calculate the escape force required for each structure point of the UAV in the disordered state. The specific operation includes: first, according to the power data required for disordered escape, a finite element model of the UAV is established, and the model contains each structure point of the UAV and its material properties and connection relationship. The model is input into a distributed computing framework (such as Hadoop or Spark), and the stress and strain of each structure point in the disordered state are calculated in parallel through distributed computing nodes to determine the escape force required for each structure point, and generate the escape force data required for disordered structure points. According to the escape force data required for disordered structure points, attitude collaborative control adjustment is performed, and the attitude of the UAV is accurately adjusted by using the attitude control algorithm of the UAV and the multi-sensor data fusion technology. The specific operation includes: inputting the escape force data required for disordered structure points, combining the inertial measurement unit (IMU) data of the UAV, and using the Kalman filter algorithm to estimate and adjust the attitude of the UAV in real time. A method based on model predictive control (MPC) is designed to coordinate the control of the four rotors of the UAV. By adjusting the thrust and speed of each rotor, the purpose of optimizing the attitude is achieved. Finally, the attitude collaborative control adjustment data is generated. The collaborative action scheduling is optimized according to the attitude collaborative control adjustment data, and the action scheduling of the UAV swarm is optimized using operations research and intelligent optimization algorithms. The specific operations include: first, according to the attitude collaborative control adjustment data, an optimization model for the collaborative task of the UAV swarm is established. The model contains constraints such as the task priority, resource allocation, and path planning of each UAV. Genetic algorithm (GA) or particle swarm optimization algorithm (PSO) is used to optimize the task allocation and path planning of the UAV swarm, and determine the optimal action scheduling plan for the UAV swarm when performing collaborative tasks. The effectiveness of the optimization plan is verified by simulation, and the optimization data for the collaborative action scheduling of the UAV is generated.

[0036] Preferably, step S1 comprises the following steps: Step S11: Acquire drone group collaborative task data; Step S12: performing data cleaning on the drone swarm collaborative task data to obtain drone swarm collaborative task cleaning data; Step S13: performing collaborative task path topology structure analysis on the drone swarm collaborative task data according to the drone swarm collaborative task cleaning data to obtain collaborative task path topology structure data; Step S14: Perform dynamic environmental perception on the collaborative task path topological structure data to obtain task path dynamic environmental perception data.

[0037] In an embodiment of the present invention, the drone swarm collaborative task data is obtained through the cloud, and the position information, speed data and attitude parameters of the drone are collected in real time by installing a high-precision GPS and inertial navigation system on the drone. These data are transmitted to the central control system through a wireless communication network to form the drone swarm collaborative task data. During the collection process, multi-sensor fusion technology is used to ensure the accuracy and integrity of the data and to ensure the reliability of the drone collaborative task data in different environments. The acquired drone swarm collaborative task data is cleaned to remove noise and outliers. The specific operation includes: using a data cleaning algorithm (such as a K-means clustering algorithm) to perform cluster analysis on the data to identify and remove abnormal data points. The missing part of the data is filled by an interpolation algorithm (such as linear interpolation) to ensure the continuity and integrity of the data. After the data cleaning is completed, high-quality drone swarm collaborative task cleaning data is obtained. The graph theory algorithm is used to analyze the path topology structure of the cleaned drone swarm collaborative task data. The specific operation includes: constructing an undirected graph based on the real-time position data of the drone, with nodes representing drones and edges representing communication links between drones. The A* algorithm is used to calculate the optimal path, and the Floyd-Warshall algorithm is used to solve the shortest path between each drone to generate the collaborative task path topology data. This data reflects the path planning and topology of the drone group when performing collaborative tasks. The environmental sensors (such as lidar, infrared sensor, ultrasonic sensor) installed on the drone are used to monitor the dynamic environmental information in the mission area in real time. The sensor data is transmitted to the central control system through the wireless communication network, and combined with the drone position and mission path information, the dynamic environmental perception data of the mission path is generated. The specific operations include: the lidar sensor scans the environment, generates three-dimensional point cloud data, and uses the point cloud data to build a real-time environmental map. Through the dynamic matching algorithm, the dynamic obstacles and environmental changes in the mission path are identified to ensure that the drone group can flexibly respond to complex environments.

[0038] Preferably, step S2 comprises the following steps: Step S21: Acquire the UAV rotation structure data; Step S22: performing rotational inertia characteristic analysis on the rotating structure data of the UAV to obtain rotational inertia characteristic data; Step S23: analyzing the airflow and pressure structure of the drone group according to the rotational inertia characteristic data to obtain the airflow and pressure structure data of the drone group; Step S24: performing path airflow dynamic evolution analysis on the task path dynamic environment perception data to obtain path airflow dynamic evolution data; Step S25: simulate the turbulent air field during the flight of the drone group according to the airflow and pressure structure data of the drone group and the dynamic evolution data of the path airflow to obtain the turbulent air field data in the flight state.

[0039] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: Acquire the UAV rotation structure data; In the embodiment of the present invention, a high-precision gyroscope and an accelerometer are installed on the rotor of the drone to collect the rotational motion data such as the angular velocity, angular acceleration and angular displacement of the rotor in real time. These data are transmitted to the central control system through a wireless communication network to form the rotational structure data of the drone. During the collection process, the sensor calibration technology is used to ensure the accuracy and consistency of the data and provide reliable rotational structure information.

[0040] In another embodiment, the data may also be obtained by sorting out the rotation structure data provided by the manufacturer.

[0041] Step S22: performing rotational inertia characteristic analysis on the rotating structure data of the UAV to obtain rotational inertia characteristic data; In the embodiment of the present invention, the rotational inertia characteristics of the UAV rotor are analyzed using multi-body dynamics and finite element analysis methods. The specific operations include: constructing a three-dimensional geometric model of the UAV rotor, inputting the rotational structure data, using finite element analysis software (such as ANSYS) to perform dynamic simulation, calculating the inertia moment, angular acceleration and structural deformation of the rotor at different rotation speeds, and generating rotational inertia characteristic data. These data reflect the dynamic characteristics and force conditions of the rotor.

[0042] Step S23: analyzing the airflow and pressure structure of the drone group according to the rotational inertia characteristic data to obtain the airflow and pressure structure data of the drone group; In an embodiment of the present invention, computational fluid dynamics (CFD) software (such as Fluent) is used to simulate and analyze the airflow field generated by the drone swarm during flight. The specific operations include: constructing a three-dimensional fluid model of the drone swarm based on the rotational inertia characteristic data, setting fluid boundary conditions and fluid parameters, performing CFD simulation, calculating the airflow velocity field, pressure distribution and dynamic pressure distribution around the drone swarm, and generating the drone swarm airflow flow pressure structure data. These data are used to analyze the aerodynamic characteristics of the drone swarm during flight.

[0043] Step S24: performing path airflow dynamic evolution analysis on the task path dynamic environment perception data to obtain path airflow dynamic evolution data; In the embodiment of the present invention, the environmental change information in the dynamic environmental perception data of the mission path is used in combination with the airflow flow and pressure structure data to simulate the evolution of the airflow field of the UAV in a dynamic environment. The specific operations include: inputting the dynamic environmental perception data of the mission path, updating the boundary conditions and fluid parameters in the CFD model, performing dynamic simulation, calculating the changes in the airflow field of the UAV under different paths and environmental conditions, and generating path airflow dynamic evolution data. These data reflect the dynamic airflow environment encountered by the UAV during flight.

[0044] Step S25: simulate the turbulent air field during the flight of the drone group according to the airflow and pressure structure data of the drone group and the dynamic evolution data of the path airflow to obtain the turbulent air field data in the flight state.

[0045] In the embodiment of the present invention, a turbulence model (such as the k-ε model) is used to simulate and analyze the flight state of a swarm of drones in a complex airflow environment. The specific operations include: inputting airflow flow pressure structure data and path airflow dynamic evolution data, setting turbulence model parameters, performing turbulence simulation, calculating the turbulent field distribution and aerodynamic changes generated by the swarm of drones during flight, and generating flight state turbulent air field data. These data are used to analyze the flight stability and aerodynamic characteristics of drones in turbulent airflow.

[0046] Preferably, step S23 includes the following steps: Step S231: extracting the rotation axis position from the rotation inertia characteristic data to obtain the rotation axis position data; Step S232: performing blade rotation aerodynamic structure simulation on the rotation inertia characteristic data according to the rotation axis position data to obtain blade rotation aerodynamic structure data; Step S233: performing blade rotation unsteady effect analysis on the blade rotation aerodynamic structure data to obtain blade unsteady aerodynamic effect data; Step S234: calculating the aerodynamic load according to the unsteady aerodynamic effect data of the blade to obtain the unsteady aerodynamic load data; Step S235: analyzing the circumferential airflow intensity distribution of the UAV group according to the unsteady aerodynamic load data and the blade rotation aerodynamic structure data to obtain circumferential airflow intensity distribution data; Step S236: Perform airflow flow and pressure structure analysis of the UAV swarm based on the circumferential airflow intensity distribution data, the unsteady aerodynamic load data, and the blade rotation aerodynamic structure data to obtain the airflow flow and pressure structure data of the UAV swarm.

[0047] In an embodiment of the present invention, the rotation axis position is extracted by analyzing the rotation inertia characteristic data using image processing technology and mathematical modeling methods. The specific operation includes: using gyroscope and accelerometer data to establish a three-dimensional motion trajectory model of the rotor, and determining the rotation axis position of the rotor through coordinate transformation and data fitting algorithm. The process involves applying the least squares method to fit the data, extracting the accurate rotation axis position, and generating rotation axis position data. These data are used for subsequent aerodynamic structure simulation. The rotating aerodynamic structure of the blade is simulated using computational fluid dynamics (CFD) software (such as Fluent). The specific operation includes: constructing a three-dimensional geometric model of the blade according to the rotation axis position data, setting the rotation boundary conditions and fluid parameters. Input the rotation inertia characteristic data, perform CFD simulation, calculate the aerodynamic pressure distribution and airflow field of the blade at different rotation speeds, and generate the blade rotation aerodynamic structure data. These data are used to analyze the aerodynamic performance of the blade during rotation. The unsteady effect analysis of the blade rotation aerodynamic structure data is performed using the unsteady fluid mechanics theory. The specific operations include: inputting the aerodynamic structure data of blade rotation, applying large eddy simulation (LES) or direct numerical simulation (DNS) methods to analyze the unsteady aerodynamic force and vortex structure of the blade during rotation. Through time-stepping simulation, the aerodynamic changes and unsteady effects of the blade at different time points are calculated to generate the unsteady aerodynamic effect data of the blade. These data are used to further optimize the aerodynamic design and performance improvement of the UAV. Computational fluid dynamics (CFD) software (such as Fluent) and structural mechanics analysis software (such as ANSYS) are used to calculate the aerodynamic loads on the blade during rotation. The specific operations include: inputting the unsteady aerodynamic effect data of the blade, setting the fluid boundary conditions and structural mechanics parameters, and calculating the aerodynamic load distribution of the blade at different rotation speeds and angles through numerical simulation methods. Through finite element analysis, the unsteady aerodynamic load data such as pressure distribution, shear force and lift on the blade surface are obtained. These data are used to analyze the complex aerodynamic forces on the blade during rotation. Using CFD software and data analysis tools, the distribution of the circumferential airflow intensity generated by the UAV group during rotation is analyzed. The specific operations include: inputting unsteady aerodynamic load data and blade rotation aerodynamic structure data, constructing a three-dimensional aerodynamic model of the drone swarm, and setting fluid boundary conditions and rotation parameters. Through CFD simulation, the velocity field, pressure field, and dynamic pressure field of the airflow around the drone swarm are calculated to generate circumferential airflow intensity distribution data. These data reflect the circumferential airflow intensity and distribution generated by the drone swarm during flight. Use CFD software to analyze the airflow flow pressure structure of the drone swarm in detail. The specific operations include: inputting circumferential airflow intensity distribution data, unsteady aerodynamic load data, and blade rotation aerodynamic structure data, setting fluid boundary conditions and model parameters, and calculating the airflow flow pressure structure generated by the drone swarm during flight through CFD simulation.Through multiple iterations of simulation, the velocity field, pressure field and dynamic pressure distribution of the airflow around the drone swarm are obtained, and the airflow dynamic pressure structure data of the drone swarm is generated. These data are used to analyze the flight performance and aerodynamic characteristics of the drone swarm in a complex aerodynamic environment.

[0048] Preferably, step S25 comprises the following steps: Step S251: analyzing the flight axial airflow concentration effect according to the UAV group airflow flow pressure structure data and the path airflow dynamic evolution data to obtain the flight axial airflow concentration effect data; Step S252: Calculating the axial airflow velocity difference on the flight axial airflow gathering effect data to obtain axial airflow velocity difference data; Step S253: performing a three-dimensional spatial vortex structure analysis of the drone group according to the axial airflow velocity difference data and the path airflow dynamic evolution data to obtain spatial vortex structure analysis data; Step S254: performing intermittent vortex aggregation energy scale calculation on the spatial vortex structure analysis data to obtain intermittent vortex aggregation energy scale data; Step S255: simulate the turbulent air field during the flight of the drone group according to the spatial vortex structure analysis data and the intermittent vortex aggregation energy scale data to obtain the turbulent air field data in the flight state.

[0049] In an embodiment of the present invention, computational fluid dynamics (CFD) software is used to analyze the axial airflow aggregation effect generated by the drone swarm during flight. The specific operation includes: inputting the airflow flow pressure structure data of the drone swarm and the dynamic evolution data of the path airflow, and constructing a three-dimensional fluid model of the drone swarm. Through CFD simulation, the axial airflow velocity field and pressure field of the drone under different flight conditions are calculated, the airflow aggregation effect is identified and analyzed, and the flight axial airflow aggregation effect data is generated. These data are used to describe the aggregation characteristics of the axial airflow during flight and the impact on the aerodynamic performance of the drone. The flight axial airflow aggregation effect data is analyzed by a numerical calculation method. The specific operation includes: according to the axial airflow velocity field, the airflow velocity difference of the drone swarm under different flight positions and conditions is calculated. Through velocity gradient analysis, the airflow velocity change at different positions is obtained, and the axial airflow velocity difference data is generated. These data are used to quantify the change of airflow velocity during flight and provide a basis for evaluating the flight stability of the drone. Using CFD software, the three-dimensional space vortex structure formed by the drone swarm during flight is analyzed. The specific operations include: inputting the axial airflow velocity difference data and the path airflow dynamic evolution data, setting the fluid boundary conditions and model parameters, calculating the three-dimensional vortex structure of the UAV under different flight positions and conditions through CFD simulation, and generating spatial vortex structure analytical data. These data are used to describe the formation and evolution of the vortex structure during the flight of the UAV. The large eddy simulation (LES) method is used to perform intermittent vortex aggregation energy scale calculation on the spatial vortex structure analytical data. The specific operations include: inputting the spatial vortex structure analytical data, setting the vortex aggregation model parameters, calculating the vortex aggregation energy at different time points and positions through time stepping simulation, and generating intermittent vortex aggregation energy scale data. These data are used to analyze the energy distribution of the vortex at different time and space scales, and provide a reference for the vortex control and energy management of the UAV. Using turbulence models (such as the k-ε model), the flight state of the UAV group in a complex airflow environment is simulated by a turbulent air field. The specific operations include: inputting spatial vortex structure analysis data and intermittent vortex aggregation energy scale data, setting turbulence model parameters, calculating the turbulence field distribution and aerodynamic changes of the drone group under different flight conditions through turbulence simulation, and generating flight state turbulent air field data. These data are used to analyze the flight stability and aerodynamic characteristics of drones in turbulent airflow.

[0050] Preferably, performing intermittent eddy aggregation energy scale calculation on spatial eddy structure analytical data comprises the following steps: Perform nonlinear dynamic structural analysis on the spatial vortex structure analytical data to obtain the spatial vortex nonlinear dynamic data; According to the spatial vortex nonlinear dynamic data, the spatial vortex structure analysis data is analyzed for the spatial vortex time series dynamic evolution to obtain the spatial vortex time series dynamic evolution data; Performing dynamic intermittency analysis on the spatial vortex time series dynamic evolution data to obtain the spatial vortex dynamic time series intermittent data; According to the spatial vortex dynamic time series intermittent data, the multi-scale vortex aggregation effect analysis is performed on the spatial vortex time series dynamic evolution data to obtain the dynamic multi-scale vortex aggregation effect data; Based on Lebesgue integral, the dynamic multi-scale eddy aggregation effect data is measured in multi-scale space to obtain dynamic multi-scale space measurement data; The intermittent vortex aggregation energy scale is calculated based on the dynamic multi-scale vortex aggregation effect data and the dynamic multi-scale spatial measurement data to obtain the intermittent vortex aggregation energy scale data.

[0051] In an embodiment of the present invention, a nonlinear dynamic structure analysis is performed on the spatial vortex structure analytical data by a nonlinear dynamic method. The specific operation includes: applying a nonlinear dynamic model (such as a Lorenz system) to fit the vortex structure data, and using time series analysis and fractal geometry methods to extract the nonlinear dynamic characteristics in the vortex structure. The spatial vortex nonlinear dynamic data is obtained by calculating the Lyapunov index and fractal dimension. These data are used to describe the chaotic characteristics and nonlinear dynamic behavior in the vortex structure. Using a nonlinear time series analysis method, the spatial vortex structure analytical data is analyzed for the spatial vortex time series dynamic evolution. The specific operation includes: inputting the spatial vortex nonlinear dynamic data, applying a time series dynamic model (such as phase space reconstruction) to analyze the vortex time series, and analyzing the evolution law of the vortex structure in the time dimension by time delay embedding method and phase trajectory reconstruction, and obtaining the spatial vortex time series dynamic evolution data. These data are used to reveal the time series dynamic characteristics of the vortex structure. The spatial vortex time series dynamic evolution data is intermittently analyzed by a dynamic intermittent analysis method. The specific operations include: inputting the time-series dynamic evolution data, applying the intermittent dynamic model (such as the Pomeau-Manneville intermittent model) for analysis, and quantifying the dynamic intermittent characteristics of the vortex structure by calculating the intermittent index and the average residence time, and obtaining the spatial vortex dynamic time-series intermittent data. These data are used to describe the intermittent dynamic behavior in the vortex structure. The multi-scale analysis method is used to analyze the multi-scale vortex aggregation effect of the spatial vortex time-series dynamic evolution data. The specific operations include: inputting the spatial vortex dynamic time-series intermittent data, applying the multi-scale aggregation model (such as wavelet transform or multi-fractal analysis), analyzing the aggregation effect of the vortex structure at different scales, and obtaining the dynamic multi-scale vortex aggregation effect data by calculating the multi-scale vortex aggregation parameters. These data are used to reveal the multi-scale aggregation characteristics of the vortex structure. The Lebesgue integral method is used to perform multi-scale spatial measurement on the dynamic multi-scale vortex aggregation effect data. The specific operations include: inputting multi-scale vortex aggregation effect data, applying Lebesgue integral theory, calculating spatial measurement values ​​at different scales, obtaining the measurement distribution of the vortex structure in multi-scale space through integral calculation, and generating dynamic multi-scale spatial measurement data. These data are used to quantify the aggregation characteristics of the vortex structure in multi-scale space. Using the energy scale calculation method, intermittent vortex aggregation energy scale calculation is performed on the dynamic multi-scale vortex aggregation effect data and the dynamic multi-scale spatial measurement data. The specific operations include: inputting multi-scale vortex aggregation effect data and spatial measurement data, applying the energy scale model, calculating the energy distribution of the vortex structure at different scales, and generating intermittent vortex aggregation energy scale data through numerical integration and multi-scale analysis. These data are used to evaluate the energy aggregation characteristics of vortex structures at different scales, and provide a reference for the aerodynamic design and performance optimization of UAVs.

[0052] Preferably, step S3 comprises the following steps: Step S31: performing flight power disorder calculation according to the flight state disordered aura data to obtain flight power disorder data; Step S32: performing critical state perception on the flight power disorder data to obtain flight power disorder critical perception data; Step S33: Calculate the power required to break free from the disordered state based on the flight power disorder critical perception data and obtain the power data required to break free from the disordered state.

[0053] In an embodiment of the present invention, a dynamic simulation model is used to calculate the flight dynamic disorder of the flight state disordered aura data. The specific operation includes: inputting the flight state disordered aura data into the dynamic model, and determining the influence of the airflow on the flight stability of the drone by calculating the force and motion response of the drone in the turbulent aura. Applying dynamic equations (such as Newton-Euler equations), considering the unevenness of the airflow and the vortex effect, the disorder degree of the drone is calculated. Generate flight dynamic disorder data for quantifying the dynamic disorder phenomenon caused by the aura disorder during flight. Apply the critical state perception method to analyze the flight dynamic disorder data. The specific operation includes: using statistics and data analysis tools to perform time series analysis and feature extraction on the flight dynamic disorder data to identify the critical point in the disorder state. By setting the disorder threshold (such as the maximum deviation value or the critical amplitude), combined with the change trend of the disorder data, the critical state of disorder is determined. Generate flight dynamic disorder critical perception data to describe the disorder critical state during flight, and provide a basis for subsequent control strategies. According to the flight dynamic disorder critical perception data, calculate the power required to break free from the disorder state in the flight state. The specific operations include: inputting flight power disorder critical perception data and flight state disorder aura data into the dynamics model, and calculating the adjustment power required in the critical disorder state by setting the breakaway conditions and control strategies. Applying dynamic control algorithms (such as PID control or robust control) to optimize the adjustment strategy to overcome the disorder state and ensure that the drone can resume stable flight in the disordered aura. Generate the power data required for disorder breakaway for designing the responsiveness and adjustment strategy of the flight control system.

[0054] Preferably, step S31 includes the following steps: Step S311: performing an air field pressure fluctuation analysis on the flight state turbulent air field data to obtain turbulent air field pressure fluctuation data; Step S312: Calculating the wind shear intensity of the turbulent air field data in the flight state according to the turbulent air field pressure fluctuation data to obtain the air field wind shear intensity data; Step S313: performing flight attitude instability force simulation according to the air field wind shear intensity data and the turbulent air field pressure fluctuation data to obtain flight attitude instability force data; Step S314: performing flight power disorder calculation according to the aura wind shear intensity data and the flight attitude instability force data to obtain flight power disorder data.

[0055] In an embodiment of the present invention, the aura pressure fluctuation analysis is performed on the flight state turbulent aura data. The specific operation includes: inputting the aura data in the flight state into high-precision aerodynamic analysis software, and using signal processing tools such as fast Fourier transform (FFT) to perform frequency domain analysis on the pressure changes in the aura data. By calculating the root mean square value (RMS) and standard deviation of the pressure fluctuation, the pressure fluctuation characteristics in the aura are extracted. Turbulent aura pressure fluctuation data are generated, which are used to quantify the pressure instability of the aura in the flight state and its impact on the drone. According to the turbulent aura pressure fluctuation data, the wind shear intensity of the aura data in the flight state is calculated. The specific operation includes: applying a wind shear model (such as a vertical wind shear model or a horizontal wind shear model), combined with the aura pressure fluctuation data, to calculate the change of wind speed at different heights and positions. The wind speed gradient is calculated using the finite difference method to obtain wind shear intensity data. The calculation of wind shear intensity involves accurate measurement and analysis of wind speed distribution to quantify the impact of wind shear on drone flight. The force of flight attitude instability is simulated by using the wind shear intensity data of the aura and the pressure fluctuation data of the turbulent aura. The specific operation includes: inputting the wind shear intensity data and the pressure fluctuation data into the flight dynamics simulation model, and simulating the force of the flight attitude under the condition of a turbulent aura through numerical simulation. Using nonlinear dynamic models (such as six-degree-of-freedom models), the force and dynamic response of the UAV under various flight attitudes are calculated to obtain the force data of flight attitude instability. These data are used to analyze the specific force mechanism and influence degree of flight attitude instability. Based on the wind shear intensity data of the aura and the force data of flight attitude instability, the flight dynamic disorder is calculated. The specific operation includes: inputting the wind shear intensity data and the instability force data into the dynamic analysis tool, and determining the dynamic disorder that occurs during the flight by calculating the dynamic response of the UAV under the condition of a turbulent aura. Using a dynamic model (such as an adaptive control model), considering the influence of wind shear and the role of instability force, the flight dynamic disorder data is calculated. These data are used to evaluate the difficulty of flight control in a complex aura and provide a basis for improving the stability of the UAV.

[0056] Preferably, step S33 includes the following steps: Step S331: analyzing the rapid change of power disorder on the flight power disorder critical perception data to obtain the power disorder rapid change data; Step S332: performing stall state identification according to the power disorder rapid change data to obtain power stall state identification data; Step S333: calculating the out-of-control acceleration increment based on the power stall state identification data to obtain the power out-of-control acceleration increment data; Step S334: Calculate the power required to break free from the disordered state based on the flight state disordered aura data according to the power out-of-control acceleration increment data to obtain the power data required to break free from the disordered state.

[0057] In an embodiment of the present invention, the critical perception data of flight power disorder is analyzed for rapid changes in power disorder. The specific operation includes: first, the critical perception data of flight power disorder is input into a data analysis tool, such as a time series analysis software. The computing tool is used to perform a short-time Fourier transform (STFT) or a Hilbert-Huang transform (HHT) to analyze the instantaneous frequency changes in the data. By processing the time series of the data, the rapid change characteristics of power disorder are extracted. The rapid change data of power disorder generated in this step reveals the changing law of the rapid disorder phenomenon that may occur during flight. The rapid change data of power disorder is used to identify the stall state. The specific operation includes: inputting the rapid change data of power disorder into a stall identification algorithm, such as a threshold-based method or a machine learning model (such as a support vector machine or a neural network). By analyzing the change trend and key features of the data, the possible stall state is identified. The recognition threshold of the stall state (such as the extreme value of acceleration or angular velocity) is set, and whether the stall occurs is determined based on this threshold. Generate power stall state identification data for calibrating the actual occurrence of the stall. The out-of-control acceleration increment is calculated based on the power stall state identification data. The specific operation includes: inputting the power stall state identification data into the dynamic calculation model, and calculating the out-of-control acceleration through the acceleration sensor data or the motion equation. Applying the dynamic equation, the acceleration increment in the out-of-control state is calculated. For example, by comparing the acceleration values ​​in the normal flight state and the out-of-control state, the change in the out-of-control acceleration is obtained. Generate the power out-of-control acceleration increment data for analyzing the acceleration increment characteristics in the out-of-control state. According to the power out-of-control acceleration increment data, the power required for the out-of-control state to break free is calculated for the flight state disorder aura data. The specific operation includes: inputting the power out-of-control acceleration increment data into the control system optimization model, and combining the flight state disorder aura data to calculate the adjustment power required in the out-of-control state. Applying the optimization algorithm (such as genetic algorithm or particle swarm optimization), the control strategy is optimized according to the acceleration increment data to minimize the flight deviation in the out-of-control state. Generate the power data required for the out-of-control break free, and provide the necessary adjustment power calculation basis for the design of the control system.

[0058] Preferably, step S4 comprises the following steps: Step S41: Based on distributed computing, the power data required for breaking free from disorder is used to calculate the breaking free force required for the disordered structure points of the UAV, and the breaking free force data required for the disordered structure points are obtained; Step S42: Based on the attention mechanism, the required breakaway force data of the disordered structure points are processed to balance the required breakaway forces of different structure points, so as to obtain the required breakaway force balance data of the structure points; Step S43: performing posture collaborative control adjustment according to the required breakaway force balance data of the structural point to obtain posture collaborative control adjustment data; Step S44: performing coordinated action scheduling optimization according to the required breakaway force balance data of the structural points and the attitude coordinated control adjustment data to obtain the coordinated action scheduling optimization data of the UAV.

[0059] In an embodiment of the present invention, the power data required for the disordered escape is used to calculate the escape force required for the disordered structure points of the drone. The specific operation includes: first, the power data required for the disordered escape is input into a distributed computing system, which can be a high-performance computing cluster or a distributed computing platform. The disordered conditions of each structural point of the drone are mechanically analyzed using a computational model. A structural mechanics model, such as a finite element analysis (FEA) tool, is used to simulate the force conditions of each structural point. The escape force required for each point in the disordered condition is calculated, and the escape force data required for the disordered structure point is generated. These data provide the force that needs to be applied to the structure point under specific disordered conditions to restore the normal state. Based on the attention mechanism, the escape force data required for the disordered structure point is balanced for the escape force required for different structure points. The specific operation includes: inputting the escape force data required for the disordered structure point into a neural network model, and processing the data using the attention mechanism. The attention mechanism can dynamically focus on the important features in the data and automatically adjust the force values ​​of different structure points to achieve global balance. By training the model, when processing the structure point data, it focuses on the structure point with the greatest impact on the disorder recovery, thereby optimizing the breakaway force of each point. The generated structure point breakaway force balance data ensures the force balance of each structure point of the drone in the disorder state and avoids the overall instability caused by local imbalance. Attitude collaborative control adjustment is performed according to the structure point breakaway force balance data. The specific operation includes: inputting the structure point breakaway force balance data into the attitude control system, which may be a controller based on model predictive control (MPC) or adaptive control strategy. The control system adjusts the attitude control parameters of the drone according to the input data to achieve force balance at each structure point. The control algorithm calculates the required attitude adjustment amount in real time, such as the adjustment amplitude of the pitch angle, roll angle and yaw angle, and performs these adjustments. The generated attitude collaborative control adjustment data provides a specific attitude adjustment strategy to achieve global control optimization. Collaborative action scheduling optimization is performed according to the structure point breakaway force balance data and attitude collaborative control adjustment data. The specific operation includes: inputting the structure point breakaway force balance data and attitude collaborative control adjustment data into the collaborative action scheduling optimization algorithm, such as the optimization algorithm or scheduling algorithm based on reinforcement learning. The algorithm comprehensively considers the control strategies and force balance requirements of all drones and optimizes the coordinated action plan of drones. The algorithm adjusts the motion trajectory and task scheduling of drones to achieve the best coordinated effect. The generated drone coordinated action scheduling optimization data provides the best scheduling strategy and action plan for drone groups when performing tasks.

[0060] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0061] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for scheduling coordinated actions of drone swarms based on distributed computing, characterized in that: The following steps are involved: Step S1: Acquire UAV swarm collaborative mission data; Perform collaborative task path topology structure analysis on the collaborative task data of the drone group to obtain collaborative task path topology structure data; perform dynamic environment perception on the collaborative task path topology structure data to obtain task path dynamic environment perception data; Step S2: Acquire the rotation structure data of the drone; perform rotation inertia characteristic analysis on the rotation structure data of the drone to obtain rotation inertia characteristic data; perform airflow flow and pressure structure analysis on the drone group according to the rotation inertia characteristic data to obtain airflow flow and pressure structure data on the drone group; perform path airflow dynamic evolution analysis on the dynamic environment perception data of the mission path to obtain path airflow dynamic evolution data; perform turbulent air field simulation during the flight of the drone group according to the airflow flow and pressure structure data of the drone group and the path airflow dynamic evolution data to obtain turbulent air field data in the flight state; Step S3: Calculating the power required for breaking free from the disordered state based on the flight state disordered aura data to obtain the power data required for breaking free from the disordered state; Step S4: Based on distributed computing, the power data required for breaking free from disorder is used to calculate the breaking free force required for the disorder of the structure points of the UAV, and the breaking free force data required for the disorder of the structure points is obtained; According to the data of the breakaway force required for the disorder of the structural points, attitude collaborative control adjustment is performed to obtain attitude collaborative control adjustment data; according to the attitude collaborative control adjustment data, collaborative action scheduling optimization is performed to obtain UAV collaborative action scheduling optimization data.

2. The method for scheduling coordinated actions of drone swarms based on distributed computing according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire drone group collaborative task data; Step S12: performing data cleaning on the drone swarm collaborative task data to obtain drone swarm collaborative task cleaning data; Step S13: performing collaborative task path topology structure analysis on the drone swarm collaborative task data according to the drone swarm collaborative task cleaning data to obtain collaborative task path topology structure data; Step S14: Perform dynamic environmental perception on the collaborative task path topological structure data to obtain task path dynamic environmental perception data.

3. The method for scheduling coordinated actions of drone swarms based on distributed computing according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Acquire the UAV rotation structure data; Step S22: performing rotational inertia characteristic analysis on the rotating structure data of the UAV to obtain rotational inertia characteristic data; Step S23: analyzing the airflow and pressure structure of the drone group according to the rotational inertia characteristic data to obtain the airflow and pressure structure data of the drone group; Step S24: performing path airflow dynamic evolution analysis on the task path dynamic environment perception data to obtain path airflow dynamic evolution data; Step S25: simulate the turbulent air field during the flight of the drone group according to the airflow and pressure structure data of the drone group and the dynamic evolution data of the path airflow to obtain the turbulent air field data in the flight state.

4. The method for scheduling coordinated actions of drone swarms based on distributed computing according to claim 3 is characterized in that: Step S23 includes the following steps: Step S231: extracting the rotation axis position from the rotation inertia characteristic data to obtain the rotation axis position data; Step S232: performing blade rotation aerodynamic structure simulation on the rotation inertia characteristic data according to the rotation axis position data to obtain blade rotation aerodynamic structure data; Step S233: performing blade rotation unsteady effect analysis on the blade rotation aerodynamic structure data to obtain blade unsteady aerodynamic effect data; Step S234: calculating the aerodynamic load according to the unsteady aerodynamic effect data of the blade to obtain the unsteady aerodynamic load data; Step S235: analyzing the circumferential airflow intensity distribution of the UAV group according to the unsteady aerodynamic load data and the blade rotation aerodynamic structure data to obtain circumferential airflow intensity distribution data; Step S236: Perform airflow flow and pressure structure analysis of the UAV swarm based on the circumferential airflow intensity distribution data, the unsteady aerodynamic load data, and the blade rotation aerodynamic structure data to obtain the airflow flow and pressure structure data of the UAV swarm.

5. The method for scheduling coordinated actions of drone swarms based on distributed computing according to claim 4 is characterized in that: Step S25 includes the following steps: Step S251: analyzing the flight axial airflow concentration effect according to the UAV group airflow flow pressure structure data and the path airflow dynamic evolution data to obtain the flight axial airflow concentration effect data; Step S252: Calculating the axial airflow velocity difference on the flight axial airflow gathering effect data to obtain axial airflow velocity difference data; Step S253: performing a three-dimensional spatial vortex structure analysis of the drone group according to the axial airflow velocity difference data and the path airflow dynamic evolution data to obtain spatial vortex structure analysis data; Step S254: performing intermittent vortex aggregation energy scale calculation on the spatial vortex structure analysis data to obtain intermittent vortex aggregation energy scale data; Step S255: simulate the turbulent air field during the flight of the drone group according to the spatial vortex structure analysis data and the intermittent vortex aggregation energy scale data to obtain the turbulent air field data in the flight state.

6. The method for scheduling coordinated actions of drone swarms based on distributed computing according to claim 5 is characterized in that: The intermittent eddy aggregation energy scale calculation for spatial eddy structure analysis data includes the following steps: Perform nonlinear dynamic structural analysis on the spatial vortex structure analytical data to obtain the spatial vortex nonlinear dynamic data; According to the spatial vortex nonlinear dynamic data, the spatial vortex structure analysis data is analyzed for the spatial vortex time series dynamic evolution to obtain the spatial vortex time series dynamic evolution data; Performing dynamic intermittency analysis on the spatial vortex time series dynamic evolution data to obtain the spatial vortex dynamic time series intermittent data; According to the spatial vortex dynamic time series intermittent data, the multi-scale vortex aggregation effect analysis is performed on the spatial vortex time series dynamic evolution data to obtain the dynamic multi-scale vortex aggregation effect data; Based on Lebesgue integral, the dynamic multi-scale eddy aggregation effect data is measured in multi-scale space to obtain dynamic multi-scale space measurement data; The intermittent vortex aggregation energy scale is calculated based on the dynamic multi-scale vortex aggregation effect data and the dynamic multi-scale spatial measurement data to obtain the intermittent vortex aggregation energy scale data.

7. The method for scheduling coordinated actions of drone swarms based on distributed computing according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing flight power disorder calculation according to the flight state disordered aura data to obtain flight power disorder data; Step S32: performing critical state perception on the flight power disorder data to obtain flight power disorder critical perception data; Step S33: Calculate the power required to break free from the disordered state based on the flight power disorder critical perception data and obtain the power data required to break free from the disordered state.

8. The method for dispatching coordinated actions of drone swarms based on distributed computing according to claim 7 is characterized in that: Step S31 The following steps are involved: Step S311: performing an air field pressure fluctuation analysis on the flight state turbulent air field data to obtain turbulent air field pressure fluctuation data; Step S312: Calculating the wind shear intensity of the turbulent air field data in the flight state according to the turbulent air field pressure fluctuation data to obtain the air field wind shear intensity data; Step S313: performing flight attitude instability force simulation according to the air field wind shear intensity data and the turbulent air field pressure fluctuation data to obtain flight attitude instability force data; Step S314: performing flight power disorder calculation according to the aura wind shear intensity data and the flight attitude instability force data to obtain flight power disorder data.

9. The method for dispatching coordinated actions of drone swarms based on distributed computing according to claim 7, characterized in that: Step S33 includes the following steps: Step S331: analyzing the rapid change of power disorder on the flight power disorder critical perception data to obtain the power disorder rapid change data; Step S332: performing stall state identification according to the power disorder rapid change data to obtain power stall state identification data; Step S333: calculating the out-of-control acceleration increment based on the power stall state identification data to obtain the power out-of-control acceleration increment data; Step S334: Calculate the power required to break free from the disordered state based on the flight state disordered aura data according to the power out-of-control acceleration increment data to obtain the power data required to break free from the disordered state.

10. The method for scheduling coordinated actions of drone swarms based on distributed computing according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Based on distributed computing, the power data required for breaking free from disorder is used to calculate the breaking free force required for the disordered structure points of the UAV, and the breaking free force data required for the disordered structure points are obtained; Step S42: Based on the attention mechanism, the required breakaway force data of the disordered structure points are processed to balance the required breakaway forces of different structure points, so as to obtain the required breakaway force balance data of the structure points; Step S43: performing posture collaborative control adjustment according to the required breakaway force balance data of the structural point to obtain posture collaborative control adjustment data; Step S44: performing coordinated action scheduling optimization according to the required breakaway force balance data of the structural points and the attitude coordinated control adjustment data to obtain the coordinated action scheduling optimization data of the UAV.

Images