Method and system for dynamically adjusting flight routes of unmanned aerial vehicles

Abstract

The present invention relates to the field of unmanned aerial vehicle control technology, and discloses a method and system for dynamically adjusting the flight route of an unmanned aerial vehicle, including: decomposing the characteristic mode function of the flight environment signal, calculating the atmospheric turbulence influence coefficient and electromagnetic interference intensity of the flight route, constructing a dynamic adjustment mechanism of the unmanned aerial vehicle, using the dynamic adjustment mechanism to generate candidate flight routes of the unmanned aerial vehicle, analyzing the path conflicts in the candidate flight routes, using the path planning module in the unmanned aerial vehicle to perform route optimization processing on the candidate flight routes to obtain an optimized flight route; analyzing the task priority corresponding to the flight mission, calculating the route risk index of the optimized flight route, and generating the global optimal route of the unmanned aerial vehicle; using the global optimal route to dynamically control the flight of the unmanned aerial vehicle to obtain a flight adjustment result. The present invention can improve the dynamic adjustment flexibility of the flight route of the unmanned aerial vehicle.

Description

Technical Field

[0001] The invention relates to a method and a system for dynamically adjusting a flight route of an unmanned aerial vehicle, and belongs to the technical field of unmanned aerial vehicle control. Background Art

[0002] In modern society, the application fields of drones are becoming increasingly wide, covering surveying and mapping, agricultural plant protection, logistics distribution, emergency rescue, film and television shooting and many other aspects. With the continuous expansion of drone usage scenarios, the planning and adjustment of their flight routes have become key issues, which directly affect the efficiency, safety and cost of drone mission execution.

[0003] Most of the existing UAV flight route planning is statically planned before flight based on preset mission objectives and known environmental information. During the planning process, the geographic information system (GIS) is usually used to obtain terrain data, and classic path planning algorithms, such as the Dijkstra algorithm, are used to generate a theoretically more optimized flight route. However, in actual flight, the environment faced by UAVs is complex and changeable.

[0004] On the one hand, meteorological conditions are difficult to predict accurately and change rapidly. For example, in agricultural plant protection operations, originally clear weather may suddenly experience severe weather conditions such as strong winds and rain. Strong winds will affect the flight stability of the drone, increase energy consumption and even cause flight loss of control. Rainfall will obstruct the drone's line of sight, affecting its monitoring of crops and operation results. In logistics and distribution scenarios, foggy weather will reduce the drone's visual range and increase the risk of collision with obstacles. Existing static planning methods cannot respond to these meteorological changes in real time, so when encountering sudden meteorological conditions, the drone may continue to fly along the original route, thereby facing safety hazards or failing to complete the mission normally. Therefore, a method is needed to improve the flexibility of adjusting the drone's flight route. Summary of the invention

[0005] The present invention provides a method and system for dynamically adjusting the flight route of an unmanned aerial vehicle, the main purpose of which is to improve the adjustment flexibility of the flight route of the unmanned aerial vehicle.

[0006] To achieve the above object, the present invention provides a method for dynamically adjusting the flight path of a drone, comprising:

[0007] Acquire the current flight route and flight mission of the UAV, arrange a sensor cluster on the flight route, use the sensor cluster to collect the flight environment signal, flight meteorological data and electromagnetic environment data of the UAV, decompose the characteristic mode function of the flight environment signal, and extract the environmental characteristics of the flight environment signal from the characteristic mode function;

[0008] In combination with the environmental characteristics, the flight meteorological data and the electromagnetic environment data, a preset flight environment analysis model is used to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, a dynamic adjustment mechanism of the UAV is constructed based on the flight mission, and a tuning factor of the dynamic adjustment mechanism is configured according to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity;

[0009] Based on the tuning factor, generating a candidate flight route of the UAV using the dynamic adjustment mechanism, analyzing the path conflicts in the candidate flight routes, and based on the path conflicts, performing route optimization processing on the candidate flight routes using a path planning module in the UAV to obtain an optimized flight route;

[0010] Analyze the task priority corresponding to the flight task, and calculate the route risk index of the optimized flight route. When the route risk index reaches a preset risk threshold, combine the task priority and the optimized flight route to generate a global optimal route for the UAV.

[0011] The global optimal route is used to perform flight dynamic control on the UAV to obtain a flight adjustment result.

[0012] Optionally, the decomposing the characteristic mode function of the flight environment signal includes:

[0013] Performing denoising processing on the flight environment signal to obtain a denoised environment signal;

[0014] Normalizing the denoised environmental signal to obtain a standard environmental signal;

[0015] Performing modal decomposition on the standard environmental signal to obtain initial modal components;

[0016] Calculating the natural modal energy corresponding to the initial modal component;

[0017] Based on the inherent modal energy, the initial modal component is screened to obtain the characteristic modal function of the flight environment signal.

[0018] Optionally, extracting the environmental characteristics of the flight environment signal from the characteristic mode function includes:

[0019] Performing time-frequency analysis on the characteristic mode function to obtain time-frequency distribution characteristics;

[0020] Analyzing energy distribution features corresponding to the time-frequency distribution features, and extracting key energy features from the energy distribution features;

[0021] Performing pattern recognition on the key energy characteristics to obtain an environmental characteristic pattern;

[0022] The environmental characteristic pattern is subjected to characteristic quantification modeling to obtain the final environmental characteristic.

[0023] Optionally, the combining the environmental characteristics, the flight meteorological data and the electromagnetic environment data, and using a preset flight environment analysis model to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route includes:

[0024] Using the data preprocessing layer in the flight environment analysis model to normalize the flight meteorological data and the electromagnetic environment data, respectively, to obtain target meteorological data and target electromagnetic environment data;

[0025] The multi-core convolution layer in the flight environment analysis model is used to extract the features of the target meteorological data and the target electromagnetic environment data respectively, so as to obtain meteorological features and electromagnetic features;

[0026] Using the feature stitching layer in the flight environment analysis model, the meteorological feature and the electromagnetic feature are respectively stitched with the environmental feature to obtain a first stitching feature and a second stitching feature;

[0027] The atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route are calculated by combining the first splicing feature and the second splicing feature and utilizing the integrated learning fusion module in the flight environment analysis model.

[0028] Optionally, constructing a dynamic adjustment mechanism for the UAV based on the flight mission includes:

[0029] Detecting the flight state parameters of the UAV in real time, and determining the parameter type corresponding to the flight state parameters;

[0030] Perform multi-dimensional decomposition processing on the flight mission to obtain decomposed flight missions, and analyze mission performance requirements corresponding to the decomposed flight missions;

[0031] In combination with the flight state parameters, analyzing the synergistic relationship between the mission performance requirements and the parameter types, and extracting key state parameters from the flight state parameters based on the synergistic relationship;

[0032] Based on the key state parameters, a flight adjustment strategy corresponding to the UAV is generated, and based on the flight adjustment strategy, a dynamic adjustment mechanism corresponding to the UAV is constructed.

[0033] Optionally, analyzing the synergistic relationship between the mission performance requirement and the parameter type in combination with the flight status parameter includes:

[0034] Performing weight allocation processing on the task performance requirement and the parameter type respectively to obtain a requirement weight and a type weight;

[0035] Respectively analyzing the semantic information corresponding to the task performance requirement and the parameter type to obtain the performance requirement semantics and the parameter type semantics;

[0036] Calculating the correlation coefficient between the performance requirement semantics and the parameter type semantics, and determining the actual performance value corresponding to the task performance requirement based on the performance requirement semantics;

[0037] Based on the actual performance value and the preset performance target value, calculate the demand satisfaction corresponding to the task performance requirement;

[0038] Combining the type weight, the correlation coefficient, the demand satisfaction and the demand weight, the synergy index between the task performance requirement and the parameter type is calculated by the following formula:

[0039] ;

[0040] Where B represents the synergy index between task performance requirements and parameter types, represents the demand weight corresponding to the ath demand in the task performance requirement, Indicates the type weight corresponding to the bth type in the parameter type. represents the correlation coefficient between the ath requirement in the performance requirement semantics and the bth type in the parameter type semantics, Indicates the demand satisfaction corresponding to the ath demand in the task performance requirement;

[0041] Based on the synergy index, the synergy relationship between the task performance requirement and the parameter type is analyzed.

[0042] Optionally, analyzing the path conflicts in the candidate flight routes includes:

[0043] Acquire the route spatial coordinates and route time series of the candidate flight route, query the flight trajectory information of the surrounding aircraft in the candidate flight route and plan the flight route;

[0044] Constructing a flight area grid of the UAV and the surrounding aircraft, and performing route mapping processing on the flight area grid in combination with the planned flight route and the route spatial coordinates to obtain a mapping area grid;

[0045] Calculate the flight conflict index between the UAV and the surrounding aircraft by combining the route time series, the flight trajectory information and the mapping area grid;

[0046] Based on the flight conflict index, path conflicts in the candidate flight routes are analyzed.

[0047] Optionally, the combining the route time series, the flight trajectory information and the mapping area grid to calculate the flight conflict index between the UAV and the surrounding aircraft includes:

[0048] Based on the mapping area grid, locating the flight distance tangent points between the UAV and the surrounding aircraft, and calculating the tangent point distance values ​​between the flight distance tangent points;

[0049] Based on the route time series and the flight trajectory information, identifying the time overlap interval between the UAV and the surrounding aircraft, and calculating the overlap time length corresponding to the time overlap interval;

[0050] Combining the tangent point distance value and the overlap time length, the flight conflict index between the UAV and the surrounding aircraft is calculated by the following formula:

[0051] ;

[0052] Among them, H represents the flight conflict index between the UAV and surrounding aircraft, L represents the tangent point distance value, Indicates the length of overlap time.

[0053] Optionally, the calculating the route risk index of the optimized flight route includes:

[0054] Determining the route risk factors in the optimized flight route according to a preset risk factor table;

[0055] Performing risk quantification processing on the route risk factors to obtain factor risk values;

[0056] Analyze the interactions between the route risk factors, combine the interactions with the risk values ​​of the factors, and quantitatively adjust the route risk factors to obtain adjusted risk values;

[0057] The route risk index of the optimized flight route is calculated by combining the adjusted risk value and the route risk factor.

[0058] In order to solve the above problems, the present invention also provides a system for dynamically adjusting the flight path of an unmanned aerial vehicle, the system comprising:

[0059] An environmental feature analysis module is used to obtain the current flight route and flight mission of the UAV, arrange a sensor cluster on the flight route, collect the flight environment signal, flight meteorological data and electromagnetic environment data of the UAV using the sensor cluster, decompose the characteristic mode function of the flight environment signal, and extract the environmental features of the flight environment signal from the characteristic mode function;

[0060] A tuning factor configuration module, for calculating the atmospheric turbulence influence coefficient and electromagnetic interference intensity of the flight route by using a preset flight environment analysis model in combination with the environmental characteristics, the flight meteorological data and the electromagnetic environment data, building a dynamic adjustment mechanism for the UAV based on the flight mission, and configuring the tuning factor of the dynamic adjustment mechanism according to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity;

[0061] a flight route optimization module, configured to generate a candidate flight route for the UAV based on the tuning factor and using the dynamic adjustment mechanism, analyze path conflicts in the candidate flight routes, and perform route optimization processing on the candidate flight routes based on the path conflicts using a path planning module in the UAV to obtain an optimized flight route;

[0062] An optimal route generation module, used to analyze the task priority corresponding to the flight task and calculate the route risk index of the optimized flight route, and when the route risk index reaches a preset risk threshold, combine the task priority and the optimized flight route to generate a global optimal route for the UAV;

[0063] The dynamic adjustment module is used to use the global optimal route to dynamically control the flight of the UAV to obtain a flight adjustment result.

[0064] Compared with the problems described in the background technology, the present invention can accurately extract key features in the flight environment by decomposing the characteristic mode function of the flight environment signal, which lays an important foundation for subsequently extracting the environmental features of the flight environment signal from the characteristic mode function. Furthermore, the present invention combines the environmental features, the flight meteorological data and the electromagnetic environment data, and uses a preset flight environment analysis model to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, so as to accurately evaluate the potential risks in the UAV flight environment, thereby providing a scientific basis for constructing a dynamic adjustment mechanism, and improving the flight stability and mission execution efficiency of the UAV. The present invention generates the dynamic adjustment mechanism based on the tuning factor. The candidate flight routes of the drone can generate candidate flight routes that match the drone, providing a basis for the safe and efficient flight of the drone, and by analyzing the path conflicts in the candidate flight routes, further ensuring the smoothness and safety of the drone flight. Furthermore, the present invention can clarify the importance and urgency of different flight tasks by analyzing the task priorities of flight tasks. The present invention can quantify the safety risk level of the optimized flight route by calculating the route risk index of the optimized flight route, thereby facilitating the subsequent generation of the global optimal route of the drone. Furthermore, the present invention can improve the adjustment flexibility of the drone flight route by using the global optimal route to dynamically control the flight of the drone. Therefore, the dynamic adjustment method and system of the drone flight route provided by the embodiment of the present invention can improve the dynamic adjustment flexibility of the drone flight route. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of a flow chart of a method for dynamically adjusting a flight route of a drone provided by an embodiment of the present invention;

[0066] Figure 2 A schematic diagram of a module for implementing a method for dynamically adjusting the flight path of a drone provided in one embodiment of the present invention.

[0067] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0068] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0069] An embodiment of the present application provides a method for dynamically adjusting the flight route of a drone. The execution subject of the method for dynamically adjusting the flight route of the drone includes, but is not limited to, at least one of an electronic device such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for dynamically adjusting the flight route of the drone can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0070] Embodiment 1:

[0071] Referring to Figure 1 As shown, it is a schematic flowchart of the method for dynamically adjusting the flight route of a drone provided by an embodiment of the present invention. In this embodiment, the method for dynamically adjusting the flight route of the drone includes:

[0072] S1. Obtain the current flight route and flight mission of the drone, arrange a sensing cluster for the flight route, use the sensing cluster to collect the flight environment signal, flight meteorological data, and electromagnetic environment data of the drone, decompose the characteristic mode function of the flight environment signal, and extract the environmental characteristics of the flight environment signal from the characteristic mode function.

[0073] By decomposing the characteristic mode function of the flight environment signal, the present invention can accurately extract the key characteristics in the flight environment, laying an important basis for subsequently extracting the environmental characteristics of the flight environment signal from the characteristic mode function. It should be explained that the drone is an aircraft that flies through remote control or an autonomous program, usually equipped with a variety of sensors and actuators to complete specific flight missions; the flight route is the flight path of the drone in the air, usually composed of a series of waypoints; the flight mission is the specific goal that the drone needs to complete during flight, such as aerial photography, monitoring, transportation, etc.; the sensing cluster is multiple sensor nodes arranged on the flight route for real-time collection of relevant data of the drone flight environment; the flight environment signal is the environmental information received by the drone during flight, including terrain, obstacles, airflows, etc.; the flight meteorological data is the meteorological conditions encountered by the drone during flight, such as wind speed, temperature, humidity, etc.; the electromagnetic environment data is information such as electromagnetic interference or signal strength encountered by the drone during flight; the characteristic mode function is the basic component obtained by decomposing the flight environment signal through a signal processing method, used to characterize different characteristics of the signal. Further, the arrangement of the sensing cluster for the flight route can be achieved through manual installation.

[0074] Specifically, the decomposing the characteristic mode function of the flight environment signal includes:

[0075] Performing denoising processing on the flight environment signal to obtain a denoised environment signal;

[0076] Normalizing the denoised environmental signal to obtain a standard environmental signal;

[0077] Performing modal decomposition on the standard environmental signal to obtain initial modal components;

[0078] Calculating the natural modal energy corresponding to the initial modal component;

[0079] Based on the inherent modal energy, the initial modal component is screened to obtain the characteristic modal function of the flight environment signal.

[0080] It should be explained that the denoised environmental signal is the signal obtained after the flight environmental signal is denoised, the standard environmental signal is the signal obtained after the denoised environmental signal is normalized to eliminate the differences between signal amplitudes, the initial modal components are the multiple basic signal components obtained after modal decomposition of the standard environmental signal, and the inherent modal energy is the energy distribution characteristic corresponding to the initial modal component, which is used to characterize the energy proportion of each modal component in the signal and its importance.

[0081] Furthermore, the flight environment signal can be denoised by a wavelet transform method to obtain a denoised environment signal; the denoised environment signal can be normalized by a standardization method (such as minimum-maximum normalization or Z-score normalization) to obtain a standard environment signal; the standard environment signal can be modally decomposed by empirical mode decomposition (EMD) to obtain initial modal components; the inherent modal energy corresponding to the initial modal components can be calculated by an energy integration method; and the initial modal components can be screened by setting an energy threshold and comparing with the inherent modal energy to obtain the characteristic modal function of the flight environment signal.

[0082] By extracting the environmental characteristics of the flight environment signal from the characteristic mode function, the present invention can deeply analyze the details of the flight environment, laying an important basis for the subsequent calculation of the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route. It should be explained that the environmental characteristics are the key information in the characteristic mode function that is representative of the flight environment signal and can reflect the essential attributes and changing laws of the flight environment, such as the frequency characteristics, amplitude characteristics, energy distribution characteristics, etc. of the signal.

[0083] In detail, extracting the environmental characteristics of the flight environment signal from the characteristic mode function includes:

[0084] Performing time-frequency analysis on the characteristic mode function to obtain time-frequency distribution characteristics;

[0085] Analyzing energy distribution features corresponding to the time-frequency distribution features, and extracting key energy features from the energy distribution features;

[0086] Performing pattern recognition on the key energy features to obtain an environmental feature pattern;

[0087] The environmental characteristic pattern is subjected to characteristic quantification modeling to obtain the final environmental characteristic.

[0088] It should be explained that the time-frequency distribution feature is the distribution characteristic of the characteristic modal function in the time and frequency dimensions, the energy distribution feature is the distribution of energy values ​​of the time-frequency distribution feature in each frequency band, the key energy feature is the important frequency band or significant energy component in the energy distribution feature, and the environmental characteristic pattern is the environmental characteristic expression extracted by the key energy feature through pattern recognition.

[0089] Furthermore, the characteristic mode function can be subjected to time-frequency analysis by the short-time Fourier transform (STFT) method to obtain time-frequency distribution characteristics; the energy distribution characteristics corresponding to the time-frequency distribution characteristics can be analyzed by the spectrum analysis method; the key energy characteristics in the energy distribution characteristics can be extracted by principal component analysis (PCA); the key energy characteristics can be subjected to pattern recognition by cluster analysis or machine learning algorithms (such as support vector machines SVM) to obtain environmental characteristic patterns; the environmental characteristic patterns can be subjected to feature quantification modeling by statistical analysis tools (such as regression analysis) to obtain final environmental characteristics.

[0090] S2. In combination with the environmental characteristics, the flight meteorological data and the electromagnetic environment data, a preset flight environment analysis model is used to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, and based on the flight mission, a dynamic adjustment mechanism of the UAV is constructed, and a tuning factor of the dynamic adjustment mechanism is configured according to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity.

[0091] The present invention combines the environmental characteristics, the flight meteorological data and the electromagnetic environment data, and uses a preset flight environment analysis model to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, so as to accurately evaluate the potential risks in the UAV flight environment, thereby providing a scientific basis for constructing a dynamic adjustment mechanism and improving the flight stability and task execution efficiency of the UAV. It should be explained that the environmental characteristics are key information extracted from the flight environment signal, including terrain, obstacles, airflow, etc.; the flight meteorological data are meteorological conditions encountered during the flight of the UAV, such as wind speed, temperature, humidity, etc.; the electromagnetic environment data are information such as electromagnetic interference or signal strength encountered during the flight of the UAV; the flight environment analysis model is a mathematical model for evaluating flight environment risks based on machine learning or physical models, which can quantitatively calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity by inputting environmental characteristics, flight meteorological data and electromagnetic environment data, so as to provide a scientific basis for the dynamic adjustment mechanism of the UAV; the atmospheric turbulence influence coefficient is an indicator for quantifying the influence of atmospheric turbulence on the flight stability of the UAV; the electromagnetic interference intensity is an indicator for quantifying the influence of electromagnetic interference on the communication and navigation systems of the UAV.

[0092] In detail, the combining of the environmental characteristics, the flight meteorological data and the electromagnetic environment data, and using a preset flight environment analysis model to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route include:

[0093] Using the data preprocessing layer in the flight environment analysis model to normalize the flight meteorological data and the electromagnetic environment data, respectively, to obtain target meteorological data and target electromagnetic environment data;

[0094] The multi-core convolution layer in the flight environment analysis model is used to extract the features of the target meteorological data and the target electromagnetic environment data respectively, so as to obtain meteorological features and electromagnetic features;

[0095] Using the feature stitching layer in the flight environment analysis model, the meteorological feature and the electromagnetic feature are respectively stitched with the environmental feature to obtain a first stitching feature and a second stitching feature;

[0096] The atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route are calculated by combining the first splicing feature and the second splicing feature and utilizing the integrated learning fusion module in the flight environment analysis model.

[0097] It should be explained that the data preprocessing layer is a component of the flight environment analysis model that cleans, converts, normalizes and performs other operations on the original data to improve data quality and applicability. It is composed of a data cleaning algorithm, a normalization function, a missing value processing strategy and an outlier detection program. The target meteorological data and the target electromagnetic environment data are respectively the flight meteorological data and the electromagnetic environment data that are suitable for subsequent model processing after key information is extracted. The multi-core convolution layer is a structure in the flight environment analysis model that uses multiple different convolution kernels to extract local features of the data to mine deep-level patterns of the data. It is composed of multiple convolution kernels of different sizes and weights, activation functions and pooling layers. The meteorological features and the electromagnetic features are respectively the target meteorological data. The data and the target electromagnetic environment data are a set of information that can characterize their essential characteristics after feature extraction operations. The feature splicing layer is a link in the flight environment analysis model that combines features from different sources in a specific way to form a more comprehensive feature vector. It is composed of a feature dimension splicing algorithm, a feature order adjustment mechanism, and a fusion weight allocation strategy. The first splicing feature and the second splicing feature are respectively comprehensive feature representations obtained after the meteorological feature and the electromagnetic feature are merged and associated with the environmental feature. The integrated learning fusion module is a component in the flight environment analysis model that integrates the results of multiple basic learners to improve prediction accuracy and stability. It is composed of multiple different types of basic learners, fusion weight calculation methods, and prediction result integration strategies.

[0098] By constructing a dynamic adjustment mechanism for the UAV based on the flight mission, the present invention allows the UAV to self-adjust in real time and accurately in a complex and changeable flight environment, effectively avoid adverse factors such as atmospheric turbulence and electromagnetic interference, ensure flight stability and safety, and greatly expand its mission execution capabilities in different scenarios. It should be explained that the dynamic adjustment mechanism is a dynamic custom control system for the UAV.

[0099] In detail, the dynamic adjustment mechanism of the UAV is constructed based on the flight mission, including:

[0100] Detecting the flight state parameters of the UAV in real time, and determining the parameter type corresponding to the flight state parameters;

[0101] Perform multi-dimensional decomposition processing on the flight mission to obtain decomposed flight missions, and analyze mission performance requirements corresponding to the decomposed flight missions;

[0102] In combination with the flight state parameters, analyzing the synergistic relationship between the mission performance requirements and the parameter types, and extracting key state parameters from the flight state parameters based on the synergistic relationship;

[0103] Based on the key state parameters, a flight adjustment strategy corresponding to the UAV is generated, and based on the flight adjustment strategy, a dynamic adjustment mechanism corresponding to the UAV is constructed.

[0104] It should be explained that the flight state parameters are various real-time operating data of the UAV, such as flight speed, altitude, attitude angle, power, etc., the parameter type is the category division corresponding to the flight state parameters, such as motion parameters, energy parameters, attitude parameters, etc., the decomposed flight mission is the task obtained after the flight mission is carefully decomposed according to dimensions such as stages and goals, the mission performance requirements are the specific requirements for the UAV in terms of speed, accuracy, stability, endurance, etc. corresponding to the decomposed flight mission, the collaborative relationship represents the relationship between the mission performance requirements and the parameter types that cooperate and influence each other to ensure the completion of the mission, the key state parameters are the data in the flight state parameters that play a decisive role in the performance requirements for completing the decomposed flight mission, and the flight adjustment strategy is the specific action plan formulated by the UAV to adjust the flight speed, change the flight altitude, adjust the attitude, etc. according to the changes in the key state parameters to ensure the smooth execution of the mission.

[0105] Furthermore, the flight state parameters of the UAV can be detected in real time by multiple sensors such as an inertial measurement unit (IMU), a global positioning system (GPS), a barometric altimeter, and a battery charge sensor carried by the UAV, and the parameter types corresponding to the flight state parameters can be determined by a preset parameter classification framework and an attribute recognition algorithm; the flight mission can be decomposed in multiple dimensions by a task decomposition model based on multiple dimensions such as mission characteristics, flight phases, and geographic information to obtain a decomposed flight mission, and the task performance requirements corresponding to the decomposed flight mission can be analyzed by a comprehensive analysis system based on flight mechanics principles, industry standards, and mission objectives; based on the synergistic relationship, key state parameters are extracted from the flight state parameters, such as flight altitude, speed, and pesticide spraying flow parameters when performing agricultural plant protection tasks, which directly affect the plant protection effect and operation efficiency; based on the key state parameters, the flight adjustment strategy corresponding to the UAV is generated by means of an intelligent decision-making model that integrates reinforcement learning and expert experience knowledge base, combined with real-time environmental data and historical flight cases, and based on the flight adjustment strategy, the flight control algorithm, hardware execution logic, and feedback optimization process are integrated to construct a dynamic adjustment mechanism corresponding to the UAV.

[0106] Further, as an optional embodiment of the present invention, the analyzing the synergistic relationship between the mission performance requirement and the parameter type in combination with the flight state parameter includes:

[0107] Performing weight allocation processing on the task performance requirement and the parameter type respectively to obtain a requirement weight and a type weight;

[0108] Respectively analyzing the semantic information corresponding to the task performance requirement and the parameter type to obtain the performance requirement semantics and the parameter type semantics;

[0109] Calculating the correlation coefficient between the performance requirement semantics and the parameter type semantics, and determining the actual performance value corresponding to the task performance requirement based on the performance requirement semantics;

[0110] Based on the actual performance value and the preset performance target value, calculate the demand satisfaction corresponding to the task performance requirement;

[0111] Combining the type weight, the correlation coefficient, the demand satisfaction and the demand weight, the synergy index between the task performance requirement and the parameter type is calculated by the following formula:

[0112] ;

[0113] Where B represents the synergy index between task performance requirements and parameter types, represents the demand weight corresponding to the ath demand in the task performance requirement, Indicates the type weight corresponding to the bth type in the parameter type. represents the correlation coefficient between the ath requirement in the performance requirement semantics and the bth type in the parameter type semantics, Indicates the demand satisfaction corresponding to the ath demand in the task performance requirement;

[0114] Based on the synergy index, the synergy relationship between the task performance requirement and the parameter type is analyzed.

[0115] It should be explained that the requirement weight and the type weight are respectively the quantitative values ​​of the importance corresponding to the task performance requirement and the parameter type, which are used to reflect the relative importance of each in the overall analysis; the performance requirement semantics and the parameter type semantics are respectively the meaning and feature descriptions corresponding to the task performance requirement and the parameter type, so as to clarify their specific connotations; the correlation coefficient represents the measurement value of the degree of association between the performance requirement semantics and the parameter type semantics, reflecting the correlation between the two at the semantic level; the actual performance value is the actual achievement value corresponding to the task performance requirement, which is used to compare with the target value to measure the task completion status; the requirement satisfaction represents the quantitative embodiment of the degree of compliance between the actual achievement of the task performance requirement and the target expectation; the synergy index represents a comprehensive quantitative indicator of the degree of synergy between the task performance requirement and the parameter type, which is used to evaluate the pros and cons of the synergy between the two.

[0116] Furthermore, the task performance requirement and the parameter type can be weighted respectively by a multi-criteria decision-making method such as a hierarchical analysis method or an entropy weight method to obtain a requirement weight and a type weight; the semantic information corresponding to the task performance requirement and the parameter type can be analyzed by a semantic analysis method to obtain performance requirement semantics and parameter type semantics; the correlation coefficient between the performance requirement semantics and the parameter type semantics can be calculated by a cosine similarity algorithm or a mutual information algorithm, and the actual performance value corresponding to the task performance requirement is determined based on the performance requirement semantics. For example, when performing a logistics distribution task, the task performance requirement is to deliver the goods on time, and the actual performance value is the actual delivery time; the ratio of the actual performance value to the preset performance target value is calculated to obtain the demand satisfaction corresponding to the task performance requirement; based on the synergy index, the synergy relationship between the task performance requirement and the parameter type is analyzed. For example, a high synergy index indicates that in the surveying and mapping task, the parameter types such as flight altitude and speed are well matched with the task performance requirement of obtaining high-precision images. Otherwise, it indicates that there are problems such as parameter mismatch or unreasonable task planning.

[0117] The present invention configures the tuning factor of the dynamic adjustment mechanism according to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity, thereby facilitating the subsequent related processing of the dynamic adjustment mechanism generating the candidate flight route of the UAV. It should be explained that the tuning factor is the core parameter or key variable of the dynamic adjustment mechanism. Further, according to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity, the tuning factor of the dynamic adjustment mechanism is configured. For example, when the atmospheric turbulence influence coefficient is 0.8 (the full value is 1, indicating that the turbulence influence is large) and the electromagnetic interference intensity is 70dB (80dB is set as the strong interference critical value, 70dB indicates strong interference), the flight speed adjustment coefficient in the tuning factor is increased from the default 0.5 to 0.8, so that the UAV reduces the flight speed and enhances stability; the attitude adjustment sensitivity is increased from 0.3 to 0.6, so as to respond to airflow changes more quickly and maintain balance, thereby adapting to complex flight environments.

[0118] S3. Based on the tuning factor, the dynamic adjustment mechanism is used to generate candidate flight routes for the UAV, and path conflicts in the candidate flight routes are analyzed. Based on the path conflicts, the path planning module in the UAV is used to perform route optimization processing on the candidate flight routes to obtain an optimized flight route.

[0119] The present invention generates a candidate flight route for the UAV based on the tuning factor and using the dynamic adjustment mechanism, so as to generate a candidate flight route that matches the UAV, provide a basis for safe and efficient flight of the UAV, and further ensure the smoothness and safety of the UAV flight by analyzing the path conflicts in the candidate flight routes. It should be explained that the candidate flight route is a preliminary flight path planning generated by the dynamic adjustment mechanism after adjusting the tuning factor, which includes a series of longitude and latitude coordinate points or flight direction, distance and other instructions; the path conflict refers to the spatial position conflict or potential collision risk caused by the candidate flight route and other UAV flight routes, obstacles, no-fly zones, etc. Further, the step of generating the candidate flight route of the UAV by the dynamic adjustment mechanism is: adjusting the flight parameter adjustment strategy, task execution strategy, etc. according to the tuning factor, combining the adjusted strategy and task execution order, resource allocation method, etc., combining the current position of the UAV, the target position and the flight mission requirements, and using the path planning algorithm (such as the A* algorithm) to generate the candidate flight route.

[0120] In detail, the analyzing the path conflicts in the candidate flight routes includes:

[0121] Acquire the route spatial coordinates and route time series of the candidate flight route, query the flight trajectory information of the surrounding aircraft in the candidate flight route and plan the flight route;

[0122] Constructing a flight area grid of the UAV and the surrounding aircraft, and performing route mapping processing on the flight area grid in combination with the planned flight route and the route spatial coordinates to obtain a mapping area grid;

[0123] Calculate the flight conflict index between the UAV and the surrounding aircraft by combining the route time series, the flight trajectory information and the mapping area grid;

[0124] Based on the flight conflict index, path conflicts in the candidate flight routes are analyzed.

[0125] It should be explained that the route spatial coordinates and the route time series are respectively the spatial position information and time node information of the candidate flight route, the flight trajectory information and the planned flight route are respectively the real-time flight paths and preset flight paths of the surrounding aircraft in the candidate flight route, the flight area grid is the shared airspace division between the UAV and the surrounding aircraft, the mapping area grid is the spatial mapping and matching of the planned flight route and the route spatial coordinates in the flight area grid, and the flight conflict index represents the potential collision risk level between the UAV and the surrounding aircraft.

[0126] Furthermore, the route spatial coordinates and route time series of the candidate flight route can be obtained through the high-precision positioning system carried by the UAV itself, such as the Global Satellite Navigation System (GNSS) and the flight data recorder; the flight trajectory information of the surrounding aircraft in the candidate flight route and the planned flight route can be queried through the communication link with the surrounding aircraft, such as the communication system based on the Automatic Dependent Surveillance-Broadcast (ADS-B) technology; the flight area grid of the UAV and the surrounding aircraft can be constructed through a grid division program based on spatial geometry algorithms and geographic information system (GIS) technology, and combined with the planned flight route and the route spatial coordinates, the flight area grid can be route mapped through a spatial mapping algorithm and a coordinate matching program to obtain a mapped area grid; based on the flight conflict index, the path conflict in the candidate flight route is analyzed, such as when the flight conflict index exceeds a preset threshold, it is determined that there is a serious path conflict, and the time and place of the conflict and the surrounding aircraft involved are further analyzed to evaluate the impact of the conflict on the flight mission.

[0127] Further, as an optional embodiment of the present invention, the combining of the route time series, the flight trajectory information and the mapping area grid to calculate the flight conflict index between the UAV and the surrounding aircraft includes:

[0128] Based on the mapping area grid, locating the flight distance tangent points between the UAV and the surrounding aircraft, and calculating the tangent point distance values ​​between the flight distance tangent points;

[0129] Based on the route time series and the flight trajectory information, identifying the time overlap interval between the UAV and the surrounding aircraft, and calculating the overlap time length corresponding to the time overlap interval;

[0130] Combining the tangent point distance value and the overlap time length, the flight conflict index between the UAV and the surrounding aircraft is calculated by the following formula:

[0131] ;

[0132] Among them, H represents the flight conflict index between the UAV and surrounding aircraft, L represents the tangent point distance value, Indicates the length of overlap time.

[0133] Furthermore, the smaller the minimum distance in the above formula, the higher the conflict risk, and the larger its reciprocal, which directly reflects the severity of the spatial conflict. The longer the time overlap interval, the higher the conflict risk, which directly reflects the severity of the temporal conflict.

[0134] It should be explained that the flight distance intersection point is the shortest point in the flight route between the UAV and the surrounding aircraft, the intersection distance value is a description of the distance between the flight distance intersection points, the time overlap interval is the time period during which the UAV and the surrounding aircraft are expected to be in the airspace near the flight distance intersection point at the same time during the flight, and the overlapping time length is the time span corresponding to the time overlap interval, that is, the duration from the start time to the end time of the time period.

[0135] Furthermore, based on the mapping area grid, the flight distance intersection points between the UAV and the surrounding aircraft are located using a spatial coordinate matching algorithm and a search program, and the intersection distance values ​​between the flight distance intersection points can be calculated using the Euclidean distance formula or other algorithms suitable for spatial distance calculation; based on the route time series and the flight trajectory information, a time series analysis algorithm and a cross-comparison method are used to identify the time overlapping interval between the UAV and the surrounding aircraft, and the overlapping time length corresponding to the time overlapping interval is calculated by subtracting timestamps and combining time unit conversion.

[0136] The present invention optimizes the candidate flight route based on the path conflict by using the path planning module in the drone, so as to effectively avoid the risk of collision with other aircraft, obstacles and no-fly areas, ensure the safe and smooth flight of the drone, ensure the efficient and stable execution of the flight mission, and improve the adaptability and reliability of the drone in a complex flight environment. It should be explained that the path planning module is the core software or hardware component in the drone, which is responsible for generating and adjusting the flight route using a specific algorithm according to the flight environment and mission requirements. The optimized flight route is the candidate flight route that is recalculated and corrected by the path planning module based on the path conflict to avoid the conflict area or time period, thereby meeting the new flight route of the safe flight requirements. Further, based on the path conflict, the path planning module in the drone is used to optimize the candidate flight route to obtain an optimized flight route. When it is detected that there is a path conflict between the candidate flight route and the no-fly area, the path planning module calls the A* algorithm to re-plan the route with the constraint of safely avoiding the no-fly area. The new route bypasses the no-fly area and extends in a direction away from the boundary of the no-fly area and close to the destination, and finally obtains an optimized flight route that successfully avoids the conflict.

[0137] S4. Analyze the task priority corresponding to the flight mission and calculate the route risk index of the optimized flight route (obtain the terrain and restrictions of the route, calculate the complexity and the number of obstacles). When the route risk index reaches a preset risk threshold, combine the task priority and the optimized flight route to generate the global optimal route of the UAV.

[0138] The present invention can clarify the importance and urgency of different flight missions by analyzing the task priorities of flight missions. The present invention can quantify the safety risk level of the optimized flight route by calculating the route risk index of the optimized flight route, thereby facilitating the subsequent generation of the global optimal route of the UAV. It should be explained that the task priority is a task level division determined according to factors such as the nature, importance, and timeliness of the flight mission. For example, the priority of performing emergency rescue missions is usually higher than that of ordinary surveying and mapping tasks; the route risk index is a quantitative indicator calculated based on a variety of factors affecting flight safety, and is used to measure the potential risk level of the flight route. Furthermore, the analysis step of the task priority corresponding to the flight mission is: obtaining the task objectives, time requirements, and resource constraints of the flight mission, and analyzing the corresponding task priority according to the importance of the task objectives, the urgency of the time requirements, and the strictness of the resource constraints.

[0139] In detail, the calculating of the route risk index of the optimized flight route includes:

[0140] Determining the route risk factors in the optimized flight route according to a preset risk factor table;

[0141] Performing risk quantification processing on the route risk factors to obtain factor risk values;

[0142] Analyze the interactions between the route risk factors, combine the interactions with the risk values ​​of the factors, and quantitatively adjust the route risk factors to obtain adjusted risk values;

[0143] The route risk index of the optimized flight route is calculated by combining the adjusted risk value and the route risk factor.

[0144] It should be explained that the preset risk factor table is pre-organized and constructed based on historical flight data, industry standards and expert experience, and covers a table of various factors that may affect the risk of the flight route and their related descriptions. The route risk factor is the specific factor in the optimized flight route that is identified by matching with the preset risk factor table and may cause risk to the flight route. The factor risk value is the numerical value of the route risk factor after being processed by a specific quantitative model to measure the degree of influence of the risk factor on the flight route risk. The interaction is the mutual influence and interaction relationship between the route risk factors. This relationship may cause the overall risk to be different from the sum of the effects of each factor alone. The adjusted risk value is the value obtained by correcting and adjusting the original factor risk value of the route risk factor after considering the interaction between the factors. It more accurately reflects its impact on the comprehensive risk of the flight route.

[0145] Further, according to the preset risk factor table, the route risk factors in the optimized flight route are determined by comparing the geographical information, weather forecast, drone status and other relevant data of the optimized flight route with each factor in the table one by one; the quantitative model constructed based on historical data, flight theory and expert experience is used to assign corresponding numerical values ​​according to different types and degrees of risk factors to quantify the risk of the route risk factors and obtain the factor risk value; with the help of Bayesian network analysis, regression analysis and other methods, the interaction between the route risk factors is analyzed in terms of the way and degree of mutual influence between the risk factors, and the route risk factors are quantitatively adjusted in combination with the interaction and the factor risk value to obtain the adjusted risk value. For example, when the two risk factors of strong wind and rainfall interact, the risk values ​​of each factor are increased according to a specific algorithm according to their synergy, so as to obtain the adjusted risk value. For example, when strong wind and rainfall occur at the same time, the impact on the flight safety of drones is not the simple addition of the effects of the two alone, but an exponential growth. The synergistic impact model is constructed using these associations. When multiple risk factors exist at the same time, the factor risk value is adjusted according to the synergistic impact model. For example, the strong wind risk value is 5, and the rainfall risk value is 4. When they exist separately, the simple sum of the two is 9, but after considering the synergistic effect, the risk value is adjusted to 12; according to the importance of each risk factor to flight safety, the importance score corresponding to the route risk factor is assigned, the adjusted risk value and the corresponding importance score are multiplied and summed, and the result is converted into decimal form to obtain the route risk index of the optimized flight route.

[0146] It should be understood that when the route risk index reaches the preset risk threshold, it means that the risk of the current optimized flight route is at a high level, which will pose a serious threat to the flight safety of the UAV and the execution of the mission. The present invention combines the mission priority and the optimized flight route to generate the global optimal route of the UAV. For example, when performing an emergency rescue mission (high priority) and the optimized route passes through a strong wind area (risk index exceeds the threshold), the new route will give priority to ensuring the timeliness of the mission, while avoiding the strong wind area as much as possible, and choosing the path with the shortest distance and relatively stable airflow to quickly reach the rescue site. It should be explained that the preset risk threshold is a pre-set risk assessment standard value.

[0147] S5. Using the global optimal route to perform flight dynamic control on the UAV to obtain a flight adjustment result.

[0148] The present invention can improve the adjustment flexibility of the flight route of the unmanned aerial vehicle by utilizing the global optimal route to perform flight dynamic control on the unmanned aerial vehicle.

[0149] Compared with the problems described in the background technology, the present invention can accurately extract key features in the flight environment by decomposing the characteristic mode function of the flight environment signal, which lays an important foundation for subsequently extracting the environmental features of the flight environment signal from the characteristic mode function. Furthermore, the present invention combines the environmental features, the flight meteorological data and the electromagnetic environment data, and uses a preset flight environment analysis model to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, so as to accurately evaluate the potential risks in the UAV flight environment, thereby providing a scientific basis for constructing a dynamic adjustment mechanism, and improving the flight stability and mission execution efficiency of the UAV. The present invention generates the dynamic adjustment mechanism based on the tuning factor. The candidate flight routes of the drone can generate candidate flight routes that match the drone, providing a basis for the safe and efficient flight of the drone, and by analyzing the path conflicts in the candidate flight routes, further ensuring the smoothness and safety of the drone flight. Furthermore, the present invention can clarify the importance and urgency of different flight tasks by analyzing the task priorities of flight tasks. The present invention can quantify the safety risk level of the optimized flight route by calculating the route risk index of the optimized flight route, thereby facilitating the subsequent generation of the global optimal route of the drone. Furthermore, the present invention can improve the adjustment flexibility of the drone flight route by using the global optimal route to dynamically control the flight of the drone. Therefore, the dynamic adjustment method and system of the drone flight route provided by the embodiment of the present invention can improve the dynamic adjustment flexibility of the drone flight route.

[0150] Embodiment 2:

[0151] like Figure 2 The figure shows a functional module diagram of a dynamic adjustment system for a UAV flight route according to the present invention.

[0152] The dynamic adjustment system 200 of the flight route of a UAV described in the present invention can be installed in an electronic device. According to the functions to be implemented, the dynamic adjustment system of the flight route of a UAV can include an environmental feature analysis module 201, a tuning factor configuration module 202, a flight route optimization module 203, an optimal route generation module 204, and a dynamic adjustment module 205. The module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0153] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0154] The environmental feature analysis module 201 is used to obtain the current flight route and flight mission of the UAV, arrange the sensor cluster of the flight route, collect the flight environment signal, flight meteorological data and electromagnetic environment data of the UAV by using the sensor cluster, decompose the characteristic mode function of the flight environment signal, and extract the environmental feature of the flight environment signal from the characteristic mode function;

[0155] The tuning factor configuration module 202 is used to calculate the atmospheric turbulence influence coefficient and electromagnetic interference intensity of the flight route by using a preset flight environment analysis model in combination with the environmental characteristics, the flight meteorological data and the electromagnetic environment data, and to construct a dynamic adjustment mechanism of the UAV based on the flight mission, and to configure the tuning factor of the dynamic adjustment mechanism according to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity;

[0156] The flight route optimization module 203 is used to generate a candidate flight route of the UAV based on the tuning factor and using the dynamic adjustment mechanism, analyze the path conflicts in the candidate flight routes, and based on the path conflicts, use the path planning module in the UAV to perform route optimization processing on the candidate flight routes to obtain an optimized flight route;

[0157] The optimal route generation module 204 is used to analyze the task priority corresponding to the flight task and calculate the route risk index of the optimized flight route. When the route risk index reaches a preset risk threshold, the global optimal route of the UAV is generated by combining the task priority and the optimized flight route.

[0158] The dynamic adjustment module 205 is used to perform flight dynamic control on the UAV using the global optimal route to obtain a flight adjustment result.

[0159] In detail, each module in the dynamic adjustment system 200 of the flight path of the drone in the embodiment of the present invention is used in the same manner as described above. Figure 1 The technical means are the same as the dynamic adjustment method of the UAV flight route described in, and can produce the same technical effects, so I will not go into details here.

[0160] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for dynamically adjusting the flight route of an unmanned aerial vehicle, characterized in that: The method comprises: Acquire the current flight route and flight mission of the UAV, arrange a sensor cluster on the flight route, use the sensor cluster to collect the flight environment signal, flight meteorological data and electromagnetic environment data of the UAV, decompose the characteristic mode function of the flight environment signal, and extract the environmental characteristics of the flight environment signal from the characteristic mode function; In combination with the environmental characteristics, the flight meteorological data and the electromagnetic environment data, a preset flight environment analysis model is used to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, and based on the flight mission, a dynamic adjustment mechanism of the UAV is constructed, and a tuning factor of the dynamic adjustment mechanism is configured according to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity, wherein the dynamic adjustment mechanism of the UAV is constructed, including: Detecting the flight state parameters of the UAV in real time, and determining the parameter type corresponding to the flight state parameters; Perform multi-dimensional decomposition processing on the flight mission to obtain decomposed flight missions, and analyze mission performance requirements corresponding to the decomposed flight missions; In combination with the flight state parameters, a synergy index between the mission performance requirement and the parameter type is calculated: ； Where B represents the synergy index between task performance requirements and parameter types, represents the demand weight corresponding to the ath demand in the task performance requirement, Indicates the type weight corresponding to the bth type in the parameter type. represents the correlation coefficient between the ath requirement in the performance requirement semantics and the bth type in the parameter type semantics, Indicates the demand satisfaction corresponding to the ath demand in the task performance demand, wherein the performance demand semantics and the parameter type semantics are the meaning and feature description corresponding to the task performance demand and the parameter type respectively; Analyzing the synergy relationship between the task performance requirement and the parameter type based on the synergy index; extracting key state parameters from the flight state parameters based on the collaborative relationship; Based on the key state parameters, a flight adjustment strategy corresponding to the UAV is generated, and based on the flight adjustment strategy, a dynamic adjustment mechanism corresponding to the UAV is constructed; Based on the tuning factor, generating a candidate flight route of the UAV using the dynamic adjustment mechanism, analyzing the path conflicts in the candidate flight routes, and based on the path conflicts, performing route optimization processing on the candidate flight routes using a path planning module in the UAV to obtain an optimized flight route; Analyze the task priority corresponding to the flight task, and calculate the route risk index of the optimized flight route. When the route risk index reaches a preset risk threshold, combine the task priority and the optimized flight route to generate a global optimal route for the UAV. The global optimal route is used to perform flight dynamic control on the UAV to obtain a flight adjustment result.

2. The method for dynamically adjusting the flight path of an unmanned aerial vehicle according to claim 1, characterized in that: The decomposing the characteristic mode function of the flight environment signal comprises: Performing denoising processing on the flight environment signal to obtain a denoised environment signal; Normalizing the denoised environmental signal to obtain a standard environmental signal; Performing modal decomposition on the standard environmental signal to obtain initial modal components; Calculating the natural modal energy corresponding to the initial modal component; Based on the inherent modal energy, the initial modal component is screened to obtain the characteristic modal function of the flight environment signal.

3. The method for dynamically adjusting the flight path of an unmanned aerial vehicle according to claim 1, characterized in that: The step of extracting the environmental characteristics of the flight environment signal from the characteristic mode function comprises: Performing time-frequency analysis on the characteristic mode function to obtain time-frequency distribution characteristics; Analyzing energy distribution features corresponding to the time-frequency distribution features, and extracting key energy features from the energy distribution features; Performing pattern recognition on the key energy characteristics to obtain an environmental characteristic pattern; The environmental characteristic pattern is subjected to characteristic quantification modeling to obtain the final environmental characteristic.

4. The method for dynamically adjusting the flight path of an unmanned aerial vehicle according to claim 1, characterized in that: The combining of the environmental characteristics, the flight meteorological data and the electromagnetic environment data, and using a preset flight environment analysis model to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, includes: Using the data preprocessing layer in the flight environment analysis model to normalize the flight meteorological data and the electromagnetic environment data, respectively, to obtain target meteorological data and target electromagnetic environment data; The multi-core convolution layer in the flight environment analysis model is used to extract the features of the target meteorological data and the target electromagnetic environment data respectively, so as to obtain meteorological features and electromagnetic features; Using the feature stitching layer in the flight environment analysis model, the meteorological feature and the electromagnetic feature are respectively stitched with the environmental feature to obtain a first stitching feature and a second stitching feature; The atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route are calculated by combining the first splicing feature and the second splicing feature and utilizing the integrated learning fusion module in the flight environment analysis model.

5. The method for dynamically adjusting the flight path of an unmanned aerial vehicle according to claim 1, characterized in that: Also includes: Performing weight allocation processing on the task performance requirement and the parameter type respectively to obtain a requirement weight and a type weight; Respectively analyzing the semantic information corresponding to the task performance requirement and the parameter type to obtain the performance requirement semantics and the parameter type semantics; Calculating the correlation coefficient between the performance requirement semantics and the parameter type semantics, and determining the actual performance value corresponding to the task performance requirement based on the performance requirement semantics; Based on the actual performance value and the preset performance target value, the demand satisfaction corresponding to the task performance requirement is calculated.

6. The method for dynamically adjusting the flight path of an unmanned aerial vehicle according to claim 1, characterized in that: The analyzing the path conflicts in the candidate flight routes comprises: Acquire the route spatial coordinates and route time series of the candidate flight route, query the flight trajectory information of the surrounding aircraft in the candidate flight route and plan the flight route; Constructing a flight area grid of the UAV and the surrounding aircraft, and performing route mapping processing on the flight area grid in combination with the planned flight route and the route spatial coordinates to obtain a mapping area grid; Calculate the flight conflict index between the UAV and the surrounding aircraft by combining the route time series, the flight trajectory information and the mapping area grid; Based on the flight conflict index, path conflicts in the candidate flight routes are analyzed.

7. The method for dynamically adjusting the flight path of an unmanned aerial vehicle according to claim 6, characterized in that: The calculating of the flight conflict index between the UAV and the surrounding aircraft by combining the route time series, the flight trajectory information and the mapping area grid includes: Based on the mapping area grid, locate the flight distance tangent point between the UAV and the surrounding aircraft, the flight distance tangent point being the point in the flight path between the UAV and the surrounding aircraft that is closest to each other, and calculate the tangent point distance value between the flight distance tangent points; Based on the route time series and the flight trajectory information, identifying the time overlap interval between the UAV and the surrounding aircraft, the time overlap interval being a time period during which the UAV and the surrounding aircraft are expected to be simultaneously in the airspace near the flight distance intersection point, and calculating the overlap time length corresponding to the time overlap interval; Combining the tangent point distance value and the overlap time length, the flight conflict index between the UAV and the surrounding aircraft is calculated by the following formula: ； Among them, H represents the flight conflict index between the UAV and surrounding aircraft, L represents the tangent point distance value, It represents the overlapping time length. The tangent point distance value is a description of the distance between the flight distance tangent points. The overlapping time length is the time span corresponding to the time overlapping interval, that is, the duration from the start time to the end time of the time period.

8. The method for dynamically adjusting the flight path of an unmanned aerial vehicle according to claim 1, characterized in that: The calculating of the route risk index of the optimized flight route comprises: Determining the route risk factors in the optimized flight route according to a preset risk factor table; Performing risk quantification processing on the route risk factors to obtain factor risk values; Analyze the interactions between the route risk factors, combine the interactions with the risk values ​​of the factors, and quantitatively adjust the route risk factors to obtain adjusted risk values; The route risk index of the optimized flight route is calculated by combining the adjusted risk value and the route risk factor.

9. A dynamic adjustment system for a UAV flight route, characterized in that: The system comprises: An environmental feature analysis module is used to obtain the current flight route and flight mission of the UAV, arrange a sensor cluster on the flight route, collect the flight environment signal, flight meteorological data and electromagnetic environment data of the UAV using the sensor cluster, decompose the characteristic mode function of the flight environment signal, and extract the environmental features of the flight environment signal from the characteristic mode function; A tuning factor configuration module is used to combine the environmental characteristics, the flight meteorological data and the electromagnetic environment data, use a preset flight environment analysis model to calculate the atmospheric turbulence influence coefficient and the electromagnetic interference intensity of the flight route, and build a dynamic adjustment mechanism for the UAV based on the flight mission. According to the atmospheric turbulence influence coefficient and the electromagnetic interference intensity, a tuning factor of the dynamic adjustment mechanism is configured, wherein building the dynamic adjustment mechanism of the UAV includes: Detecting the flight state parameters of the UAV in real time, and determining the parameter type corresponding to the flight state parameters; Perform multi-dimensional decomposition processing on the flight mission to obtain decomposed flight missions, and analyze mission performance requirements corresponding to the decomposed flight missions; In combination with the flight state parameters, a synergy index between the mission performance requirement and the parameter type is calculated: ； Where B represents the synergy index between task performance requirements and parameter types, represents the demand weight corresponding to the ath demand in the task performance requirement, Indicates the type weight corresponding to the bth type in the parameter type. represents the correlation coefficient between the ath requirement in the performance requirement semantics and the bth type in the parameter type semantics, Indicates the demand satisfaction corresponding to the ath demand in the task performance demand, wherein the performance demand semantics and the parameter type semantics are the meaning and feature description corresponding to the task performance demand and the parameter type respectively; Analyzing the synergy relationship between the task performance requirement and the parameter type based on the synergy index; extracting key state parameters from the flight state parameters based on the collaborative relationship; Based on the key state parameters, a flight adjustment strategy corresponding to the UAV is generated, and based on the flight adjustment strategy, a dynamic adjustment mechanism corresponding to the UAV is constructed; a flight route optimization module, configured to generate a candidate flight route for the UAV based on the tuning factor and using the dynamic adjustment mechanism, analyze path conflicts in the candidate flight routes, and perform route optimization processing on the candidate flight routes based on the path conflicts using a path planning module in the UAV to obtain an optimized flight route; An optimal route generation module, used to analyze the task priority corresponding to the flight task and calculate the route risk index of the optimized flight route, and when the route risk index reaches a preset risk threshold, combine the task priority and the optimized flight route to generate a global optimal route for the UAV; The dynamic adjustment module is used to use the global optimal route to dynamically control the flight of the UAV and obtain a flight adjustment result.

Images