Universal self-learning device and method for ground-air dual-stage flight controller

Abstract

The invention discloses a universal self-learning device and method for a ground-air dual-stage flight controller. The device comprises an array camera visual attitude resolving system, a surrounding type wind field generator, a high-speed camera recording system, a ground four-degree-of-freedom aircraft support, an aircraft, a smoke flow guide pipe, a top truss, a flexible wire and a multi-working-condition simulation spray head. The surrounding type wind field generator comprises three array wind field generating devices perpendicular to the ground, and the wind speed and the wind direction can be self-defined. The aircraft is connected to a vertically telescopic support rod standing on the base through a three-degree-of-freedom spherical hinge, and is used for learning of a ground stage; a hanging type umbilical cord assembly is arranged above the aircraft, is connected with a flexible wire of the truss and is used for learning in the air stage; and a flight controller is arranged at the mass point of the aircraft. The method can be used for controller self-learning design and verification of fixed wing / variable fixed wing aircrafts of any configuration in a real pneumatic environment, and intelligent flight controller attitude and position control under a multi-working-condition wind field condition is simulated.

Description

Technical Field

[0001] The invention relates to a universal self-learning device and method for a ground-to-air dual-stage flight controller, belonging to the field of aircraft intelligent control, flight testing and experimental platform. Background Art

[0002] The control and attitude optimization of aircraft are extremely challenging in complex flight environments, especially when facing uncertain airflow conditions and complex tasks, the design and testing of flight controllers are particularly critical. Most existing flight tests rely on actual flights or wind tunnel experiments, which are costly and cannot run for a long time due to environmental conditions. At the same time, the verification and improvement of flight control simulation algorithms are difficult to fully implement in actual flights, especially the research on adaptive learning and reconstruction of controllers, which requires a more flexible and economical experimental platform. Based on this, the present invention proposes a universal self-learning device and experimental method for a ground-to-air dual-stage flight controller, which can combine the ground and air stages, use a ground simulated wind field generating device, a movable bracket, a small fixed-wing UAV / scaled fixed-wing aircraft, to achieve multi-degree-of-freedom attitude control and adaptive learning, and provide a more feasible and flexible experimental scheme for the development of flight controllers. Summary of the invention

[0003] In order to overcome the deficiencies of the prior art, an object of the present invention is to provide a universal self-learning device and method for a ground-to-air dual-stage flight controller.

[0004] The present invention is achieved through the following technical solutions: A universal self-learning device for a ground-to-air dual-stage flight controller, comprising an array camera visual attitude solving system, a surround wind field generator, a high-speed camera recording system, a ground four-degree-of-freedom aircraft bracket, an aircraft, a smoke flow guide tube, a top truss, a soft wire, and a multi-condition simulation nozzle; The surround wind generator includes three array wind generators perpendicular to the ground, which can customize wind speed and direction; A top truss is provided above the array wind farm generating device, which has multiple hanging points for installing high-speed cameras and multi-condition simulation nozzles; the ground four-degree-of-freedom aircraft bracket includes a three-degree-of-freedom ball joint, a base, and a vertically retractable support rod; rollers are installed at the bottom of the base; The aircraft is connected to a vertically retractable support rod standing on a base through a three-degree-of-freedom spherical joint for learning in the ground phase; A hanging umbilical assembly is installed above the aircraft, which is used to connect to the soft wire of the truss. The soft wire provides external power supply and safe mooring to the aircraft learning to fly. It has certain retractable characteristics and is used for learning in the air. A flight controller is provided at the mass point of the aircraft for autonomous flight control in a wind field environment; The array camera visual attitude solution system includes multiple infrared cameras, which realizes attitude solution within the field of view through attitude algorithm, and is used to calculate the actual attitude angle and position of the aircraft; The high-speed camera recording system includes three altitude cameras with front, top and left viewing angles, which are placed on the front, top and left side of the aircraft respectively, and are used to record relevant data during the aircraft learning process.

[0005] The array wind field generating device includes a smoke flow guide tube and a plurality of rotor propeller modules that can independently adjust the wind speed, and is used to generate a steady / customized unsteady time-varying repeatable low-speed wind field to simulate the air flow of low-altitude flight.

[0006] The array camera visual attitude solution system is composed of an array of infrared cameras surrounding the top of the surround wind farm generator. Each camera actively receives the incident light angle and time to coordinately realize the attitude angle solution of the rigid body envelope within the field of view, and determines the relative position of the observed rigid body within the field of view based on the initial world coordinate calibration. It supports free assembly and addition and deletion of cameras to adjust the effective attitude solution range; it is fixed to the truss, the truss is fixedly connected to the ground, and has no direct connection with the surround wind farm generator.

[0007] The surround wind field generator includes array servo motors, each motor is independently driven by an electric regulator, all servo motors are driven in PWM mode, the pulse modulation range is 1000-2000 ms, the wind speed range is 0-52 m / s, the integrated control mode is web control, and the network communication is via wifi. It supports any device in the local area network to connect to the access control terminal, supports any custom wind field form and time-space sequence setting; supports custom wind field script saving and import; and any module unit supports modular splicing, and supports free assembly into vertical, cylindrical, and trapezoidal surfaces; a single array minimum unit can be equipped with blades of different diameters as needed, with a diameter range of 20mm~180mm, and the minimum units are connected in a mortise and tenon manner. A smoke flow guide tube is provided inside the unit to support controllable smoke flow output for flow field visualization.

[0008] The flight controller, when the precise aerodynamic model and dynamic model of the aircraft are unknown, learns to fly according to the wind field environment simulating the real flow field in the air through the built-in algorithm.

[0009] The top truss includes multiple hanging points, which can realize the installation of cameras, smoke nozzles, rain nozzles, flame nozzles, and mud and sand nozzles, thereby realizing the simulation of multiple working conditions during flight.

[0010] The aircraft includes a set of flight controller hardware and an iterative adaptive learning algorithm, which learns the optimal control law in real time by acquiring real flow field control response data in the ground and air stages.

[0011] A method for using the universal self-learning device of a ground-to-air dual-stage flight controller, wherein the self-learning includes two stages: ground and air. In the ground stage, basic attitude flight control laws are learned, and flight control law parameters under basic flight conditions are continuously learned in real data responses interacting with a wind field, and a stable control law is learned in an online adaptive manner. Physical limitation of attitude angles is achieved through the action of a spherical hinge, and a telescopic support rod is remotely raised and lowered by a worm motor, thereby achieving attitude flight control learning of an aircraft in four degrees of freedom. In the air stage, the neighborhood performance optimal control law is learned to achieve optimal attitude control, and at the same time, the design and optimization of a position controller is achieved in combination with a high-speed camera recording system.

[0012] Beneficial effects of the present invention:

[0013] Firstly, the ground wind field generating device is used to directly simulate the real aircraft flow field, which greatly improves the experimental efficiency compared with the traditional outdoor flight method. Secondly, the open annular wind field can support the control test flight of the real aircraft with a wingspan range of 0.3m-8m, which greatly reduces the experimental cost of the traditional low-altitude wind tunnel. The ground-air two-stage self-learning device and method can realize the full-process whole machine controller design and optimization in the indoor environment, greatly improving the controller design efficiency. In addition, the design also supports rain, smoke, mud, and wind shear flow fields, reducing the dependence on experimental weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the system structure of a universal self-learning device for a ground-phase flight controller.

[0015] Figure 2 It is a system structure diagram of a universal self-learning device for a flight controller in the air phase.

[0016] Figure 3 It is a schematic diagram of the four-degree-of-freedom bracket structure during the ground learning phase.

[0017] Figure 4 It is a flow chart of the self-learning control method of the ground-to-air two-stage aircraft.

[0018] In the figure, there are array camera attitude solving system 1, surround wind field generator 2, rotor propeller module 3, high-speed camera recording system 4, aircraft 5, self-learning flight controller 6, smoke duct 7, top truss 8, soft wire 9, three-degree-of-freedom ball joint 10, base 11, vertically retractable support rod 12, and multi-condition simulation nozzle 13. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] like Figure 1 As shown, a universal self-learning device for a ground-to-air dual-stage flight controller includes a top array camera attitude solving system 1, a surround wind field generator 2, a rotor propeller module 3, a three-viewing angle high-speed camera recording system 4, an aircraft 5, a self-learning flight controller 6, a smoke duct 7, a top truss 8, a soft wire 9, a three-degree-of-freedom ball joint 10, a base 11, a vertically retractable support rod 12, and a multi-condition simulation nozzle 13.

[0021] The surround wind field generator 2 includes three array wind field generating devices perpendicular to the ground. Each array wind field is composed of multiple rotor propeller modules 3 and smoke ducts 7 that can independently adjust the wind speed. The cluster control instructions of all modules are controlled by a web interface deployed in the cloud to generate steady / customized unsteady time-varying repeatable low-speed wind fields to simulate low-altitude flying air flows.

[0022] The three-view high-speed camera recording system 4 includes three height cameras of front, top and left viewing angles, which are respectively placed at the front, top and left sides of the aircraft, and are used to record relevant data during the aircraft learning process.

[0023] The aircraft 5 is fixedly connected to the end of the soft wire 9 hanging down from the top truss 8 (in the air stage), or the aircraft 5 is fixedly connected to the vertically retractable support rod 12 on the base 11 through a three-degree-of-freedom spherical joint 10 (on the ground stage), which is used to realize the virtual flight tethered test in the process of learning the attitude / unknown control law of the aircraft. During the learning process, the power unit and all servo actuators are controlled in real time in the loop.

[0024] The self-learning flight controller 6 is installed at the center of mass of the aircraft and can be used for autonomous flight control in a wind field environment.

[0025] The top truss 8 is placed above the wind farm generator and has multiple hanging points, on which a top-view high-speed camera 4 and a rain and fog generating nozzle 13 can be installed to simulate flight conditions in complex scenes.

[0026] The bottom of the base 11 is equipped with folding rollers to enable movement in a horizontal plane and to adjust the distance between the aircraft and the annular wind field generator.

[0027] like Figure 1As shown, the ground learning stage of the universal self-learning device system of the ground-to-air dual-stage flight controller adopts the layout setting of the surround wind field generator, and any real or scaled model aircraft 5 is fixedly connected to the retractable connecting rod 12 through the ball joint 10, and the connecting rod is placed on the mobile base 11, and the self-learning flight controller is installed at the center of mass of the aircraft 5. Start the aircraft power supply and wind field generator, the aircraft enters the iterative adaptive learning process, and continuously learns and iterates in multiple types of wind fields, learns the adaptive neural network parameters, and reconstructs the control law in real time, and continuously performs performance evaluation through the attitude positioning system to achieve stable attitude flight control in the ground stage.

[0028] like Figure 2 As shown, the air learning stage of the universal self-learning device system for ground-to-air dual-stage flight controller also adopts the layout setting of the surrounding wind field generator. At this time, any real or scaled model aircraft 5 is fixedly connected to the retractable soft rope 9 through the truss 8, and the self-learning flight controller is installed at the center of mass of the aircraft 5. The aircraft power supply and wind field generator are started, and the aircraft enters the iterative adaptive air learning process. Through continuous learning iterations in multiple types of wind fields, the adaptive neural network parameters are learned to reconstruct the control law in real time, and the performance is continuously evaluated through the attitude positioning system to achieve attitude flight control optimization and position controller design optimization in the air stage.

[0029] like Figure 3 As shown, the movable bracket includes a ball joint 10, a base 11, and a telescopic support rod 12, wherein the groove at the upper end of the ball joint fits with the belly, the bottom spherical surface meshes with the groove surface of the telescopic rod 12, and the built-in ball layer reduces sliding friction, and can achieve a pitch of ±50°, a roll of ±50°, and a 360° heading. The rigid telescopic rod is connected to the ground base.

[0030] like Figure 4 As shown, the application process of the ground-to-air two-stage self-learning control device and method in the full-process design of the controller is demonstrated, wherein the second stage ground learning and the third stage air learning correspond to the attitude learning device and method in the above-mentioned ground support wind farm environment, and the attitude control optimization and position controller design device and method in the aerial hanging soft rope wind farm environment, respectively.

[0031] The embodiments described above can be further combined or replaced, and the embodiments are only descriptions of preferred embodiments of the present invention, and do not limit the concept and scope of the present invention. Without departing from the design concept of the present invention, various changes and improvements made by ordinary technicians in this field to the technical solution of the present invention belong to the protection scope of the present invention. The protection scope of the present invention is given by the attached claims and any equivalents thereof.

Claims

1. A universal self-learning device for ground-to-air dual-stage flight controller, characterized in that: It includes an array camera visual attitude solving system (1), a surround wind field generator (2), a high-speed camera recording system (4), a ground four-degree-of-freedom aircraft bracket, an aircraft (5), a smoke flow guide tube (7), a top truss (8), a flexible wire (9), and a multi-condition simulation nozzle (13); The surround wind field generator (2) includes three array wind field generating devices perpendicular to the ground, and the wind speed and wind direction can be customized; A top truss (8) is provided above the array wind field generating device and has a plurality of hanging points for installing a high-speed camera and a multi-condition simulation nozzle (13); The ground four-degree-of-freedom aircraft bracket comprises a three-degree-of-freedom spherical joint (10), a base (11), and a vertically retractable support rod (12); a roller is installed at the bottom of the base (11); The aircraft (5) is connected to a vertically retractable support rod (12) standing on a base (11) through a three-degree-of-freedom spherical joint (10) for learning in the ground phase; A hanging umbilical cord assembly is provided above the aircraft (5) for connecting to a soft wire (9) of the truss (8); the soft wire (9) is used to externally power and safely tether the aircraft for learning to fly, has a retractable characteristic, and is used for learning in the air phase; A flight controller (6) is provided at a mass point of the aircraft (5) for autonomous flight control in a wind field environment; The array camera visual attitude solution system (1) includes a plurality of infrared cameras, which realizes attitude solution within the field of view through an attitude algorithm, and is used to calculate the actual attitude angle and position of the aircraft; The high-speed camera recording system (4) includes three height cameras with front, upper and left viewing angles, which are respectively placed on the front side, upper side and left side of the aircraft, and are used to record relevant data during the aircraft learning process.

2. A universal self-learning device for ground-to-air dual-stage flight controller according to claim 1, characterized in that: The array wind field generating device comprises a smoke flow guide tube (7) and a plurality of rotor propeller modules (3) capable of independently adjusting wind speed, and is used to generate a steady / customized unsteady time-varying repeatable low-speed wind field to simulate low-altitude flying air flow.

3. A universal self-learning device for ground-to-air dual-stage flight controller according to claim 1, characterized in that: The array camera visual attitude solution system (1) is composed of an array of infrared cameras surrounding the top of the surround wind field generator (2). Each camera actively receives the incident light angle and time to coordinately achieve attitude angle solution of the rigid body envelope within the field of view, and determines the relative position of the observed rigid body within the field of view based on the initial world coordinate calibration, and supports free assembly and addition and deletion of cameras to adjust the effective attitude solution range; it is fixed to a truss (8), the truss is fixedly connected to the ground, and has no direct connection with the surround wind field generator (2).

4. A universal self-learning device for ground-to-air dual-stage flight controller according to claim 1, characterized in that: The surround wind field generator (2) comprises an array servo motor, each motor is independently driven by an electric controller, all servo motors are driven in PWM mode, the pulse modulation range is 1000-2000 ms, the wind speed range is 0-52 m / s, the integrated control mode is web control, network communication is via wifi mode, support any device in the local area network to connect to the access control terminal, support any custom wind field form and time-space sequence setting; support custom wind field script saving and import; and any module unit supports modular splicing, and supports free assembly into vertical, cylindrical, and trapezoidal surfaces; a single array minimum unit can be equipped with blades of different diameters according to needs, with a diameter range of 20mm to 180mm, the minimum units are connected in a mortise and tenon manner, and a smoke flow guide tube is provided inside the unit to support controllable smoke flow output for flow field visualization.

5. A universal self-learning device for ground-to-air dual-stage flight controller according to claim 1, characterized in that: The flight controller (6) learns to fly by using an embedded algorithm based on a wind field environment that simulates a real air flow field when the precise aerodynamic model and dynamic model of the aircraft are unknown.

6. The universal self-learning device for ground-to-air dual-stage flight controller according to claim 1, characterized in that: The top truss (8) includes a plurality of hanging points, which can realize the installation of a camera, a smoke nozzle, a rain nozzle, a flame nozzle, and a mud and sand nozzle, thereby realizing the simulation of multiple working conditions during the flight process.

7. The universal self-learning device for ground-to-air dual-stage flight controller according to claim 1 is characterized in that: The aircraft (5) includes a set of flight controller hardware and an iterative adaptive learning algorithm. The optimal control law is learned by acquiring real flow field control response data in the ground and air stages.

8. A method using the universal self-learning device for a ground-to-air dual-stage flight controller according to claim 1, characterized in that: Self-learning includes two stages: ground and air. In the ground stage, the basic attitude flight control law is learned, and the flight control law parameters under basic flight conditions are continuously learned in the real data response of the interaction with the wind field, and a stable control law is learned through online adaptive means. The physical limitation of attitude angle is achieved through the action of spherical hinges, and the telescopic support rod is remotely raised and lowered by a worm motor, thereby realizing attitude flight control learning of the aircraft in four degrees of freedom. In the air phase, the optimal control law for neighborhood performance is learned to achieve optimal attitude control. At the same time, combined with the high-speed camera recording system, the design and optimization of the position controller is realized.

Images