Multi-mode adaptive switching control method for unmanned aerial vehicle and unmanned aerial vehicle

Abstract

The invention provides a multi-mode adaptive switching control method for an unmanned aerial vehicle and the unmanned aerial vehicle. The method comprises the following steps: collecting flight parameter information of the unmanned aerial vehicle through a multi-source sensor; the flight mode of the aircraft is judged in real time based on the flight parameter information and a dynamic threshold value, wherein the dynamic threshold value is a threshold value dynamically adjusted through a machine learning algorithm according to the flight parameter information; if it is detected that the flight mode of the aircraft is switched, rotor wing thrust and fixed wing lift force are distributed based on a transition factor of a nonlinear function, and corresponding rotor wing rotating speed and fixed wing control plane deflection angle are calculated and output based on a gain scheduling mechanism. Through the scheme, the thrust and lift force in the flight process of the aircraft can be reasonably distributed, the stability and adaptability of modal switching control are improved, and safe and reliable flight is guaranteed.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) technology, and particularly relates to a multi-modal adaptive switching control method and an UAV for unmanned aerial vehicles. Background Technology

[0002] With the continuous development of UAV technology, compound-wing UAVs have gradually become a research hotspot due to their combination of multi-rotor vertical takeoff and landing capabilities and fixed-wing long-endurance cruise capabilities. However, existing compound-wing UAVs still have shortcomings in multi-mode switching control, especially in terms of stability and adaptability during the switching process, which affects the overall performance and reliability of the aircraft.

[0003] Currently, in existing technical solutions (patent publication number CN113734435B), a method and device for switching between multi-rotor and fixed-wing modes of a compound-wing UAV are disclosed. This method, based on the judgment of flight speed and altitude, uses different deceleration and acceleration curves to adjust the rotor speed and fixed-wing tilt angle, thereby optimizing the mode switching. However, in this solution, the triggering conditions for mode switching depend on preset speed and altitude thresholds, lacking dynamic perception of real-time flight status. This may affect the accuracy of the switching timing, resulting in poor stability and adaptability of aircraft mode switching in complex environments. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a multi-modal adaptive switching control method and an unmanned aerial vehicle (UAV) to solve the problem of poor stability and adaptability of current UAV mode switching.

[0005] In a first aspect of the present invention, a multi-modal adaptive switching control method for an unmanned aerial vehicle is provided, comprising: Flight parameter information of unmanned aerial vehicles is collected through multi-source sensors; The flight mode of the aircraft is determined in real time based on the flight parameter information and dynamic thresholds. The dynamic thresholds are thresholds that are dynamically adjusted according to the flight parameter information through machine learning algorithms. If a flight mode switch is detected, the rotor thrust and fixed-wing lift are allocated based on the transition factor of the nonlinear function, and the corresponding rotor speed and fixed-wing control surface deflection are calculated and output based on the gain scheduling mechanism.

[0006] In a second aspect of the present invention, an aircraft is provided, comprising: The state perception module is used to collect flight parameter information of the unmanned aerial vehicle through multi-source sensors; The status judgment module is used to determine the flight mode of the aircraft in real time based on the flight parameter information and dynamic thresholds. The dynamic thresholds are thresholds that are dynamically adjusted according to the flight parameter information through a machine learning algorithm. The flight control module is used to allocate rotor thrust and fixed-wing lift based on a transition factor of a nonlinear function if a change in the aircraft's flight mode is detected, and to calculate and output the corresponding rotor speed and fixed-wing control surface deflection based on a gain scheduling mechanism.

[0007] In a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect of the present invention.

[0008] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present invention.

[0009] In this embodiment of the invention, a reasonable distribution of rotor thrust and fixed-wing lift is achieved by introducing a transition factor and nonlinear interpolation, thereby improving the stability of aircraft mode switching control, avoiding abrupt changes in aircraft attitude and lift, and enhancing adaptability to complex environments through dynamic threshold updates and adjustments. Simultaneously, it can improve the overall energy efficiency of the aircraft, reduce flight power consumption, and optimize the flight control of the compound-wing UAV. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating a multi-modal adaptive switching control method for an unmanned aerial vehicle provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a compound wing unmanned aerial vehicle provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of multi-mode switching provided in one embodiment of the present invention; Figure 4 This is a schematic diagram of the force under transition mode provided in one embodiment of the present invention; Figure 5 This is a schematic diagram of the thrust and lift versus time curves provided in one embodiment of the present invention; Figure 6 This is a schematic diagram of the velocity versus time curve provided in one embodiment of the present invention; Figure 7 This is a schematic diagram of power consumption versus time provided in one embodiment of the present invention; Figure 8 A schematic diagram of the pitch angle versus time curve provided in one embodiment of the present invention; Figure 9 This is a schematic diagram of the structure of an aircraft according to one embodiment of the present invention; Figure 10 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0012] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0013] It should be understood that the terms "comprising" and other similar expressions in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units and is not limited to the listed steps or units. Furthermore, "first" and "second" are used to distinguish different objects and are not intended to describe a specific order.

[0014] It is understandable that existing compound-wing UAVs suffer from the following problems during mode switching: the thrust and lift distribution is not smooth during switching, easily leading to abrupt attitude changes and instability; mode triggering relies on fixed thresholds, lacking real-time dynamic perception of flight status and environmental factors, resulting in imprecise switching timing; there is a lack of robust compensation and adaptive capabilities against external disturbances (such as sudden gusts, asymmetric load changes, etc.); the control architecture is complex, lacking a simplified parameter scheduling mechanism, and the system has low tolerance for sensor or actuator failures. Therefore, it is necessary to propose a multi-mode switching method based on state perception, adaptive judgment, and hierarchical cooperative control to achieve smooth and safe switching between three flight modes—multi-rotor hovering, transition, and fixed-wing cruise—of compound-wing UAVs, with good adaptability and robustness.

[0015] Please see Figure 1 The present invention provides a flowchart illustrating a multi-modal adaptive switching control method for unmanned aerial vehicles, comprising: S101. Collect flight parameter information of unmanned aerial vehicles through multi-source sensors; The multi-source sensors may include an inertial measurement unit (IMU), GPS, pitot tube, barometer, optical flow / laser ranging, etc., and flight parameter information is obtained through the IMU, GPS, pitot tube, barometer, optical flow / laser ranging, etc. installed on the aircraft.

[0016] The flight parameter information refers to parameters related to the flight status of the aircraft, which may include aircraft speed, attitude, ambient wind direction and speed, etc.

[0017] The flight parameter information includes at least the aircraft attitude, speed, altitude, environmental wind field parameters, and load information.

[0018] S102. Based on the flight parameter information and dynamic threshold, the flight mode of the aircraft is determined in real time. The dynamic threshold is a threshold that is dynamically adjusted according to the flight parameter information through a machine learning algorithm. By comparing flight parameter information with set dynamic thresholds, the flight mode of the aircraft is determined in real time. The flight mode includes at least hovering mode, transition mode, and cruise mode. A determination variable s(t)∈{0,1,2} is introduced to represent hovering mode, transition mode, and cruise mode, respectively. Mode switching conditions can be determined based on a comprehensive assessment of airspeed, dynamic thresholds, and lift-to-drag ratio thresholds. The flight mode of the aircraft is determined based on the air speed, the corresponding dynamic threshold for air speed, and the lift-to-drag ratio threshold in the flight parameter information.

[0019] In the formula, The numbers indicate the flight mode: 0 for hovering mode, 1 for transition mode, and 2 for cruise mode. Indicates air speed, Indicates the first dynamic threshold. The second dynamic threshold is represented by L / D, where L / D is the lift-to-drag ratio of the aircraft, λ represents the lift-to-drag ratio threshold, and L represents lift and drag. , Total aerodynamic drag air density, For flight speed, For wing area, Indicates the angle of attack The varying lift-to-drag ratio.

[0020] An adaptive threshold update strategy is adopted to adjust the dynamic threshold according to the flight status, that is, to dynamically adjust the first dynamic threshold and the second dynamic threshold, so as to achieve real-time adaptation to different environments.

[0021] In some embodiments, the dynamic threshold update formula can be defined as: ; In the formula, To optimize metrics (such as lowest energy consumption / most stable switching). To learn step length.

[0022] Understandably, in hover mode, the rotor provides the main lift, and the fixed wing does not work; in transition mode, the rotor thrust gradually decreases, the wing tilt angle is adjusted from 90° to 0°, and the wing gradually bears the aerodynamic force; in cruise mode, the rotor thrust is only used for compensation, and the main lift comes from the wing.

[0023] S103. If a flight mode switch of the aircraft is detected, the rotor thrust and fixed wing lift are allocated based on the transition factor of the nonlinear function, and the corresponding rotor speed and fixed wing control surface deflection are calculated and output based on the gain scheduling mechanism.

[0024] Once a mode switch is detected, smooth control of the aircraft is required to ensure stable changes in flight attitude and speed. A transition factor μ(t)∈[0,1] is introduced, and a nonlinear function is used to achieve a smooth transition between rotor thrust and fixed-wing lift: Optionally, set a transition factor. Calculate the transition factor according to the formula: ; Based on the transition factor, calculate the rotor thrust and fixed-wing lift separately: ; In the formula, Indicates the transition factor. Indicates the current speed of the aircraft. Indicates the transition center velocity. Indicates the width of the smoothing interval. Indicates rotor thrust. This indicates the maximum thrust of the rotor. Indicates fixed-wing lift. This indicates the maximum lift of the fixed-wing aircraft. This indicates the angle of attack of a fixed-wing aircraft.

[0025] When μ=0, the rotor provides all the lift (hovering); when 0<μ<1, the rotor thrust gradually decreases and the wing lift gradually increases (transition); when μ≈1, the wing lift provides the main load (cruise).

[0026] By utilizing a gain scheduling mechanism, the attitude and velocity control gains are smoothly switched with the transition factor μ, ensuring the continuity of control during the transition period.

[0027] It is understandable that the upper-level controller of the aircraft generates attitude expectations and plans the path based on mission requirements and flight status, while the lower-level controller realizes closed-loop adjustment of rotor thrust, wing deflection angle and servo control based on the distribution of thrust and lift.

[0028] In some embodiments, the attitude control law of the controller is set as follows: ; The speed control law of the controller is set as follows: ; Map the motor execution commands as: ; In the formula, Indicates attitude control variables. Represents the attitude gain matrix. Indicates attitude error. Represents the angular velocity gain matrix. Indicates angular velocity error. This indicates the disturbance compensation term. Indicates speed control quantity. Indicates proportional gain. Indicates actual speed. Indicates the desired speed. Indicates the mass of the aircraft. U represents the desired acceleration, and U represents the aircraft control input. Represents a mapping function. U represents the transition factor, which includes rotor speed, pitch angle, and fixed-wing control surface deflection angle.

[0029] The gain matrix as Scheduling: ; .

[0030] Preferably, a disturbance observer is used to estimate wind disturbance in real time and input it into the control law; When a rotor or sensor malfunction is detected, the system switches to redundant control mode, using the remaining actuators for differential compensation or wing lift sharing. This introduces anti-interference and fault-tolerant mechanisms, reducing the impact of external wind disturbances on the aircraft's flight control while ensuring safe flight based on redundant control.

[0031] In this embodiment, the continuous distribution of rotor and fixed-wing thrust is achieved through transition factors and nonlinear interpolation functions, resulting in a smooth transition, avoiding abrupt changes in attitude and lift, and improving the stability of the aircraft. Through dynamic threshold adjustment, the switching timing is determined by real-time status and optimization indicators, better adapting to complex flight environments. External disturbance prediction compensation and redundant control mechanisms ensure flight safety and have good robustness and fault tolerance. Through smooth control, the overall energy efficiency of the aircraft is improved.

[0032] In some embodiments, an online multimodal estimation model integrating environmental disturbances, flight dynamics, and aerodynamic characteristics is established to provide input data for switching decisions and control.

[0033] The translational dynamics model of the aircraft is represented as follows: ; Among them, the combined efforts of the machine system = Rotor thrust + Fixed wing aerodynamics.

[0034] In the rotor thrust model, the thrust of a single rotor is represented as: ; in, Let be the angular velocity of the i-th rotor. This is the thrust coefficient.

[0035] The lift of a fixed-wing aerodynamic force is expressed as: ; Resistance is expressed as: ; in, , To follow the angle of attack The varying lift-to-drag ratio.

[0036] but .

[0037] The rotational dynamics model is expressed as:

[0038] The rotor torque is:

[0039] in, The distance from the rotor to the center of mass. This is the torque coefficient.

[0040] The aerodynamic moment of a fixed wing is:

[0041] in , , These are the aileron, elevator, and rudder deflection angles, respectively.

[0042] In one embodiment, the structure of the unmanned aerial vehicle is as follows: Figure 2 As shown in the figure, 1 represents the fuselage, 2 represents the fixed wing, 3 represents the front rotor, 4 represents the rear rotor, 5 represents the tilt servo, 6 represents the flight controller, 7 represents the IMU and GPS module, 8 represents the pitot tube, 9 represents the barometer, and 10 represents the optical flow / laser ranging module. The fuselage adopts a quadcopter layout with a pair of tiltable fixed wings. The wingspan is 2.0 meters and the wing area is 0.6 square meters. The first two sets of rotors (3) are linked to the wings through the tilt servo (5) and can be adjusted in angle between 0° and 90°. The last two sets of rotors (4) are installed at the root of the wings and are used for hovering and attitude control.

[0043] The power system consists of a rotor driven by a brushless motor, equipped with an electronic speed controller to adjust the speed; tilt servos are used to achieve the angular rotation of the rotor / wing.

[0044] The sensing and control system includes a flight controller (6), an IMU, a GPS module (7), an airspeed tube (8), a barometer (9), an optical flow / laser ranging module (10), etc., for collecting attitude, speed, altitude and environmental data.

[0045] The communication and mission module is used for information exchange and mission management with the ground station.

[0046] In some embodiments, the multi-mode switching logic is as follows: Figure 3 As shown, it is divided into hovering mode (0), transition mode (1) and cruise mode (2), and the judgment rules are as follows: ; In hover mode, the quadcopter thrust fully supports gravity, and attitude is controlled by differential. In transition mode, the quadcopter thrust gradually decreases, the fixed wing tilt angle gradually retracts, and lift is gradually borne by the fixed wing to ensure a smooth transition. In cruise mode, lift is mainly generated by the fixed wing, forward thrust is provided by the front rotor, and the overall system control law switches to fixed wing mode.

[0047] Among them, such as Figure 4 As shown, in transition mode, lift is generated by the rotor and fixed wing, while thrust is generated by the rotor. The rotor thrust gradually decreases, the fixed wing tilt angle gradually retracts, and lift is gradually borne by the fixed wing. In cruise mode, lift is generated entirely by the wing, while the rotor provides thrust.

[0048] In some embodiments, taking a 10kg unmanned aerial vehicle as an example, a hovering-transition-cruise mission is performed at an altitude of 20m: Initial state: hovering at a height of z=20m, with a velocity V_a=0; Task: Complete a smooth transition from hovering mode to cruise mode within t=0 to t=20s.

[0049] Objective: Cruise speed V_d = 18 m / s; cruise altitude maintained at 20 m; Adaptive thresholds: Stop → Transition trigger speed V_th1 = 5 m / s; Transition → Cruise trigger speed initial value V_th2 = 15 m / s, which can be adjusted in real time according to energy consumption; 0-5s (hovering): Total rotor thrust approximately 98N, wing lift approximately 0, power consumption approximately 1.35kW; 5–15s (transition): The air speed increases from 0 to 15 m / s, and the rotor and wing share the gradually changing lift, each bearing 50% at about 10s; the pitch angle decreases to -7°; 15–20 seconds (cruise): The wing lift bears the main load, the rotor power decreases, and the cruise power consumption is about 0.95 kW, which is about 30% lower than the hovering time; the pitch angle recovers to +4° and stabilizes.

[0050] Changes in thrust and lift are as follows Figure 5 As shown, at t=0: the total thrust of the quadcopter is about 98.1 N, and the lift of the wing is 0; at t=10s, the speed is close to V_a=10m / s: the rotor contributes about 50 N, and the lift of the wing is about 50 N, showing a stable distribution; at t=20s, V_a=18m / s is reached: the lift of the wing is close to 98 N, and the rotor only provides a small amount of forward thrust and attitude adjustment.

[0051] Speed ​​change such as Figure 6 As shown, from t=0 to t=5, the air velocity is 0. Between t=5 and t=15, the air velocity increases from 0 to 15 m / s, and the overall velocity changes at a constant speed.

[0052] During attitude and angular velocity changes, when hovering, the attitude remains horizontal and the angular velocity is close to 0; during transition, the nose is adjusted slightly downward by 5 to 7 degrees to gain acceleration; in cruise mode, it is stabilized at a small angle of attack (about 4 degrees).

[0053] Energy consumption changes such as Figure 7 As shown, the power consumption of the rotor hovering for 20 seconds is approximately P_hover≈1.35kW; after completing the compound transition to cruise, the average power consumption drops to 0.95kW, a reduction of about 30% in energy consumption.

[0054] Pitch angle changes such as Figure 8 As shown, the attitude swing amplitude during the transition is less than 3°; the peak vector acceleration is less than 0.2; the numerical values ​​indicate that the flight transition is smooth and there is no instability.

[0055] like Figures 5-8Simulation results show that the thrust and lift switching is smooth, the speed increases steadily, the power consumption decreases, and the pitch angle change is as expected. Under wind disturbance, the attitude deviation converges to within ±2°, demonstrating good stability and robustness.

[0056] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0057] Figure 9 This is a schematic diagram of the logical structure of an aircraft 90 provided in an embodiment of the present invention. The aircraft 90 includes: The state perception module 910 is used to collect flight parameter information of the unmanned aerial vehicle through multi-source sensors; The flight parameter information includes at least the aircraft attitude, speed, altitude, environmental wind field parameters, and load information.

[0058] The status judgment module 920 is used to determine the flight mode of the aircraft in real time based on the flight parameter information and the dynamic threshold. The dynamic threshold is a threshold that is dynamically adjusted according to the flight parameter information through a machine learning algorithm. Optionally, the real-time determination of the aircraft's flight mode based on the flight parameter information and dynamic thresholds includes: The aircraft's flight mode is determined based on the air speed, the corresponding dynamic threshold for air speed, and the lift-to-drag ratio threshold in the flight parameter information.

[0059] In the formula, The numbers indicate the flight mode: 0 for hovering mode, 1 for transition mode, and 2 for cruise mode. Indicates air speed, Indicates the first dynamic threshold. The second dynamic threshold is represented by L / D, where L / D is the lift-to-drag ratio of the aircraft, λ represents the lift-to-drag ratio threshold, and L represents lift and drag. , Total aerodynamic drag air density, For flight speed, For wing area, Indicates the angle of attack The varying lift-to-drag ratio.

[0060] The flight control module 930 is used to allocate rotor thrust and fixed-wing lift based on a transition factor of a nonlinear function if a flight mode switch of the aircraft is detected, and to calculate and output the corresponding rotor speed and fixed-wing control surface deflection based on a gain scheduling mechanism.

[0061] Among them, setting a transition factor Calculate the transition factor according to the formula: ; Based on the transition factor, calculate the rotor thrust and fixed-wing lift separately: ; In the formula, Indicates the transition factor. Indicates the current speed of the aircraft. Indicates the transition center velocity. Indicates the width of the smoothing interval. Indicates rotor thrust. This indicates the maximum thrust of the rotor. Indicates fixed-wing lift. This indicates the maximum lift of the fixed-wing aircraft. This indicates the angle of attack of a fixed-wing aircraft.

[0062] Optionally, the calculation and output of the corresponding rotor speed and fixed-wing control surface deflection based on the gain scheduling mechanism includes: The attitude control law of the controller is set as follows: ; The speed control law of the controller is set as follows: ; Map the motor execution commands as: ; In the formula, Indicates attitude control variables. Represents the attitude gain matrix. Indicates attitude error. Represents the angular velocity gain matrix. Indicates angular velocity error. This indicates the disturbance compensation term. Indicates speed control quantity. Indicates proportional gain. Indicates actual speed. Indicates the desired speed. Indicates the mass of the aircraft. U represents the desired acceleration, and U represents the aircraft control input. Represents a mapping function. U represents the transition factor, which includes rotor speed, pitch angle, and fixed-wing control surface deflection angle.

[0063] In one embodiment, the aircraft 90 further includes: The anti-interference module is used to estimate wind disturbance in real time using a disturbance observer and input it into the control law; The redundant control module is used to switch to redundant control mode when a rotor or sensor failure is detected, and to perform differential compensation or wing lift sharing through the remaining actuators.

[0064] It is understood that the modules mentioned above represent some of the software functional modules of the aircraft. The aircraft may also include hardware such as the airframe, fixed wings, rotors, tilt servos, flight controllers, and various sensors.

[0065] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0066] Figure 10 This is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device can be a flight controller for a drone, used for flight mode switching control. Figure 10 As shown, the electronic device 10 of this embodiment includes: a memory 1010, a processor 1020, and a system bus 1030. The memory 1010 includes an executable program 1011 stored thereon. As those skilled in the art will understand, Figure 10 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0067] The following is combined with Figure 10 A detailed introduction to each component of the electronic device: The memory 1010 can be used to store software programs and modules. The processor 1020 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 1010. The memory 1010 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cached data), etc. In addition, the memory 1010 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0068] The memory 1010 contains an executable program 1011 for aircraft control methods. This executable program 1011 can be divided into one or more modules / units, which are stored in the memory 1010 and executed by the processor 1020 to implement aircraft mode switching control, etc. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, describing the execution process of the executable program 1011 in the electronic device 10. For example, the computer program 1011 can be divided into functional modules such as a state perception module, a state judgment module, and a flight control module.

[0069] The processor 1020 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 1010, and by calling data stored in the memory 1010, it performs various functions and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 1020 may include one or more processing units; preferably, the processor 1020 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, application programs, etc., and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1020.

[0070] The system bus 1030 is used to connect various functional components inside the computer, transmitting data, address, and control information. Its type can be, for example, a PCI bus, an ISA bus, or a CAN bus. Instructions from the processor 1020 are transmitted to the memory 1010 via the bus, and the memory 1010 sends data back to the processor 1020. The system bus 1030 is responsible for data and instruction exchange between the processor 1020 and the memory 1010. Of course, the system bus 1030 can also connect to other devices, such as network interfaces and display devices.

[0071] In this embodiment of the invention, the executable program executed by the processor 1020 included in the electronic device includes: Flight parameter information of unmanned aerial vehicles is collected through multi-source sensors; The flight mode of the aircraft is determined in real time based on the flight parameter information and dynamic thresholds. The dynamic thresholds are thresholds that are dynamically adjusted according to the flight parameter information through machine learning algorithms. If a flight mode switch is detected, the rotor thrust and fixed-wing lift are allocated based on the transition factor of the nonlinear function, and the corresponding rotor speed and fixed-wing control surface deflection are calculated and output based on the gain scheduling mechanism.

[0072] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0073] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0074] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-modal adaptive switching control method for unmanned aerial vehicles, characterized in that, include: Flight parameter information of unmanned aerial vehicles is collected through multi-source sensors; The flight mode of the aircraft is determined in real time based on the flight parameter information and dynamic thresholds. The dynamic thresholds are thresholds that are dynamically adjusted according to the flight parameter information through machine learning algorithms. If a flight mode switch is detected, the rotor thrust and fixed-wing lift are allocated based on the transition factor of the nonlinear function, and the corresponding rotor speed and fixed-wing control surface deflection are calculated and output based on the gain scheduling mechanism.

2. The method according to claim 1, characterized in that, The flight parameter information includes at least the aircraft attitude, speed, altitude, environmental wind field parameters, and load information.

3. The method according to claim 1, characterized in that, The real-time determination of the aircraft's flight mode based on the flight parameter information and dynamic thresholds includes: The aircraft's flight mode is determined based on the air speed, the corresponding dynamic threshold for air speed, and the lift-to-drag ratio threshold in the flight parameter information. In the formula, The numbers indicate the flight mode: 0 for hovering mode, 1 for transition mode, and 2 for cruise mode. Indicates air speed, Indicates the first dynamic threshold. The second dynamic threshold is represented by L / D, where L / D is the lift-to-drag ratio of the aircraft, λ represents the lift-to-drag ratio threshold, and L represents lift and drag. , Total aerodynamic drag air density, For flight speed, For wing area, Indicates the angle of attack The varying lift-to-drag ratio.

4. The method according to claim 1, characterized in that, The transition factor based on a nonlinear function, which allocates rotor thrust and fixed-wing lift, includes: Set transition factor Calculate the transition factor according to the formula: ； Based on the transition factor, calculate the rotor thrust and fixed-wing lift separately: ； In the formula, Indicates the transition factor. Indicates the current speed of the aircraft. Indicates the transition center velocity, Indicates the width of the smoothing interval. Indicates rotor thrust. Indicates the maximum thrust of the rotor. Indicates fixed-wing lift. This indicates the maximum lift of the fixed-wing aircraft. This indicates the angle of attack of a fixed-wing aircraft.

5. The method according to claim 1, characterized in that, The calculation and output of the corresponding rotor speed and fixed-wing control surface deflection based on the gain scheduling mechanism includes: The attitude control law of the controller is set as follows: ； The speed control law of the controller is set as follows: ； Map the motor execution commands as: ； In the formula, Indicates attitude control variables. Represents the attitude gain matrix. Indicates attitude error. Represents the angular velocity gain matrix. Indicates angular velocity error. This indicates the disturbance compensation term. Indicates speed control quantity. Indicates proportional gain. Indicates actual speed. Indicates the desired speed. Indicates the mass of the aircraft. U represents the desired acceleration, and U represents the aircraft control input. Represents a mapping function. U represents the transition factor, which includes rotor speed, pitch angle, and fixed-wing control surface deflection angle.

6. The method according to claim 1, characterized in that, The calculation and output of the corresponding rotor speed and fixed-wing control surface deflection based on the gain scheduling mechanism also includes: A disturbance observer is used to estimate wind disturbances in real time and input them into the control law; When a rotor or sensor malfunction is detected, the system switches to redundant control mode, using the remaining actuators for differential compensation or wing lift sharing.

7. An aircraft, characterized in that, include: The state perception module is used to collect flight parameter information of the unmanned aerial vehicle through multi-source sensors; The status judgment module is used to determine the flight mode of the aircraft in real time based on the flight parameter information and dynamic thresholds. The dynamic thresholds are thresholds that are dynamically adjusted according to the flight parameter information through a machine learning algorithm. The flight control module is used to allocate rotor thrust and fixed-wing lift based on a transition factor of a nonlinear function if a change in the aircraft's flight mode is detected, and to calculate and output the corresponding rotor speed and fixed-wing control surface deflection based on a gain scheduling mechanism.

8. The aircraft according to claim 7, characterized in that, The real-time determination of the aircraft's flight mode based on the flight parameter information and dynamic thresholds includes: The aircraft's flight mode is determined based on the air speed, the corresponding dynamic threshold for air speed, and the lift-to-drag ratio threshold in the flight parameter information. In the formula, The numbers indicate the flight mode: 0 for hovering mode, 1 for transition mode, and 2 for cruise mode. Indicates air speed, Indicates the first dynamic threshold. The second dynamic threshold is represented by L / D, where L / D is the lift-to-drag ratio of the aircraft, λ represents the lift-to-drag ratio threshold, and L represents lift and drag. , Total aerodynamic drag air density, For flight speed, For wing area, Indicates the angle of attack The varying lift-to-drag ratio.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the multimodal adaptive switching control method for unmanned aerial vehicles as described in any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed, it implements the steps of the multimodal adaptive switching control method for unmanned aerial vehicles as described in any one of claims 1 to 6.

Images