Construction method of robot pilot flight simulation environment and simulation platform

Abstract

The invention relates to the technical field of aircraft semi-physical simulation, in particular to a construction method of a robot pilot flight simulation environment and a simulation platform. The construction method comprises the following steps: configuring the retired aircraft and the original aircraft support equipment; a seat in a cabin of the retired aircraft is detached, and the robot aircraft is installed at the position of a guide rail on the back of the original seat; jacking up the decommissioning aircraft by using the original aircraft support equipment to enable tires to be separated from the ground by a preset distance, and connecting a hydraulic pump and a power supply; carrying a simulation system on the retired aircraft, and establishing communication connection between the simulation system and a robot pilot; the simulation system comprises a simulation computer, a data acquisition assembly, and a data line and a power line which are used for connecting the simulation computer and the data acquisition assembly. The decommissioning aircraft is used for configuring the original aircraft support equipment and carrying the simulation system, a vivid simulation environment can be provided for a robot pilot, and the process of forming the independent driving ability of the robot pilot is shortened. Existing equipment is fully utilized, non-intrusive assembly is adopted, the universality is high, and the cost is low.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft semi-physical simulation, and in particular to a method for constructing a flight simulation environment for a robot pilot and a simulation platform. Background Art

[0002] Realizing unmanned flight without large-scale modification of retired aircraft has important civil and military strategic significance. With the rapid development of robotics technology, it is an advanced and technically feasible option for robot pilots with aircraft driving capabilities to fly retired aircraft.

[0003] The robot pilot needs to have an appearance that is basically the same size as an adult sitting down, so that it can be installed in the cockpit. In addition, the robot pilot should have the ability to obtain, identify, analyze and judge through vision and hearing, as well as the ability to sense three-dimensional position, attitude, speed, angular velocity and overload for decision-making, judgment and control. At the same time, it should also have the ability to operate with hands and feet, replacing humans to complete operations such as pushing and retracting the throttle of the aircraft, controlling the control surfaces, and operating special task buttons.

[0004] Robot pilots are the same as human pilots. Before actually flying an aircraft, they need to undergo modification learning and training in a realistic simulation environment of the aircraft so that they have the driving skills to fly the aircraft. In view of this, the construction of a simulation environment for robot pilots is a necessary condition in the development of robot pilots, which can greatly improve the efficiency of robot pilot development. However, the prior art does not disclose a method for constructing a flight simulation environment for robot pilots. Summary of the invention

[0005] The purpose of the present invention is to provide a method for constructing a robot pilot flight simulation environment and a simulation platform for making full use of retired aircraft to realize physical simulation and improve the efficiency of robot pilot development.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for constructing a robot pilot flight simulation environment, comprising the following steps:

[0008] S10. Configure retired aircraft and original aircraft support equipment;

[0009] S11. Remove the seats in the cockpit of the retired aircraft and install the robot pilot on the original seat back rail position;

[0010] S12. Use the original aircraft support equipment to lift the retired aircraft so that the tires are off the ground by a preset distance, and connect the hydraulic pump and power supply;

[0011] S13. A simulation system is mounted on the retired aircraft, and a communication connection is established between the simulation system and the robot pilot; the simulation system includes a simulation computer, a data acquisition component, and a data cable and a power cable for connecting the simulation system and the robot pilot; wherein the data acquisition component includes an elevator angle collector, a rudder angle collector, an aileron rudder angle collector, a discrete state video collector, and a throttle handle scale video collector installed at a preset position of the retired aircraft; the simulation computer is configured with an aerodynamic force and torque solution model, a dynamic solution model, and a kinematic solution model; the simulation computer receives the elevator angle, rudder angle, aileron rudder angle, throttle handle position, and discrete state information, and solves them in turn using the aerodynamic force and torque solution model, the dynamic solution model, and the kinematic solution model, and obtains the three-dimensional position, three-dimensional speed, three-dimensional angle and angular velocity, weight, and fuel quantity information of the retired aircraft through variable conversion, and outputs the above information to the robot pilot through a data interface.

[0012] As a possible implementation method, before executing the simulation system, the simulation system is initialized, specifically including: collecting the zero position of the elevator, rudder and aileron control surfaces; calibrating the throttle handle position; setting the initial three-dimensional position, three-dimensional speed, three-dimensional angle, angular rate, weight, fuel volume, external plug-in model and quantity of the retired aircraft.

[0013] As a possible implementation method, the aerodynamic force and torque solution model includes a lift solution operator model, a drag solution operator model, a side force solution operator model, a pitch moment solution operator model, a rolling moment solution operator model, a yaw moment sub-model, an engine thrust sub-model, a fuel consumption quantum model, a center of gravity solution operator model, a moment of inertia solution operator model and an atmospheric data solution operator model.

[0014] As a possible implementation method, the lift solver model is:

[0015] Y=qs×C y

[0016]

[0017] Among them, Y is lift; qs is dynamic pressure, which represents the pressure generated when the air flows, and the unit is Pa, qs = ρ × v 2 / 2, ρ is the air density at the flight altitude, υ is the flight speed; C y is the lift coefficient; C y0 , They are zero lift coefficient, angle of attack lift coefficient, and horizontal tail lift coefficient, which are obtained based on the difference of longitudinal aerodynamic parameters; C yjy is the flap lift coefficient. If there are flaps, it takes different values ​​according to the flap angle. The value is calculated based on the wind data or aerodynamic theory. If there are no flaps, C yjy is 0; Cydx is the influence of ground effect. When the height of the aircraft from the ground is less than the height threshold, the ground effect is considered; α is the aircraft angle of attack; δ z is the horizontal tail deflection angle;

[0018] The resistance solution operator model is:

[0019] X=qs×C x

[0020]

[0021] Where X is the resistance; qs is the dynamic pressure; C x is the drag coefficient; C x0 , is the zero-lift drag coefficient and the induced drag coefficient, which are obtained based on the longitudinal aerodynamic parameter difference; α is the aircraft angle of attack; C is the altitude correction for zero lift resistance; xqlj is the landing gear drag coefficient; C xjy is the flap drag coefficient, which takes different values ​​according to the flap angle. The data value is determined based on the wind data or aerodynamic theory. If there is no flap, this value is 0; C xwg is the external drag coefficient, which is calculated based on relevant aerodynamic theories. In addition, when the engine is stopped, the above drag coefficients increase by 0.0074.

[0022] The lateral force solution operator model is:

[0023] Z=qs×C z

[0024]

[0025] Where Z is the lateral force; qs is the dynamic pressure; C z is the lateral force coefficient; is the side force coefficient of the sideslip angle, is the rudder side force coefficient, According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input; C zf is the engine side force coefficient, β is the side slip angle of the aircraft; δ y For the aircraft rudder.

[0026] As a possible implementation method, the pitch moment solver model is:

[0027] M z =qs×b A ×m z

[0028]

[0029] Among them, M z is the pitch moment; qs is the dynamic pressure; b A is the average aerodynamic chord length; m z is the pitch moment coefficient; α is the aircraft angle of attack, δ z is the tail deviation angle of the aircraft, m z0 is the pitch moment coefficient generated by the aircraft shape when the angle of attack is 0°, is the pitch moment coefficient generated by the aircraft's angle of attack; It is the ground effect coefficient caused by the aircraft's angle of attack. According to engineering test data, it is included when the aircraft is less than 2.2 meters above the ground. α is the aircraft angle of attack; is the pitch moment coefficient generated by the rate of change of the aircraft's angle of attack; is the rate of change of the aircraft angle of attack; is the pitch moment coefficient generated by the aircraft elevator; δ z is the horizontal tail deflection angle; is the pitch moment coefficient generated by the pitch angular rate of the aircraft; ω z is the pitch angle rate; m zf is the effect of the aircraft on the pitch moment coefficient, m zs is the moment of lift on the center of gravity; m zwg The data is calculated based on the shape of the plug-in through aerodynamics related theories; m zjy Different values ​​are taken according to the flap angle. The data value is determined according to the wind data or aerodynamic theory calculation. If there is no flap, this value is 0; is the rate of change of the aircraft angle of attack; ω z is the pitch angle rate; b A is the average aerodynamic chord length;

[0030] The rolling moment solver model is:

[0031] M x =qs×l×m x

[0032]

[0033] Among them, M x is the rolling moment; qs is the dynamic pressure; l is the wingspan; m x is the lateral torque coefficient; is the rolling moment coefficient generated by the roll angle; β is the side slip angle of the aircraft; is the rolling moment coefficient generated by the rudder; δ y For aircraft rudder; is the rolling moment coefficient generated by the aileron rudder; δ x It is the aileron rudder of the aircraft; is the rolling moment coefficient generated by the rolling angular rate; ω x is the rolling angular rate; is the rolling moment coefficient generated by the yaw angular rate; ω y is the yaw angular rate; is the rolling moment coefficient generated by the yaw angle acceleration rate; α is the aircraft angle of attack; v is the true airspeed of the flight; According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input; ω y is the yaw rate; l is the wingspan;

[0034] The yaw moment sub-model is:

[0035] M y =qs×l×m y

[0036]

[0037] Among them, M y is the yaw moment; qs is the dynamic pressure; l is the wingspan; m y is the yaw moment coefficient; is the yaw moment coefficient generated by the roll angle; β is the side slip angle of the aircraft; is the yaw moment coefficient generated by the rudder; δ y For aircraft rudder; is the yaw moment coefficient generated by the yaw angular rate; ω y is the yaw angular rate; is the yaw moment coefficient generated by the rolling angular rate; ω x is the rolling angular rate; v is the true airspeed; m yf is the effect of the engine on the yaw moment coefficient, According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input.

[0038] As a possible implementation, the engine thrust submodel is:

[0039] P = k p ×T h

[0040] Where P is the effective thrust of the engine; k p is the inlet loss correction coefficient. According to engineering experience data, when the flight Mach number Ma>0.3, k p=0.905, when Ma≤0.3, k p =0.88+0.0833×Ma; the thrust of the engine is T h , unit is N;

[0041] The fuel consumption quantum model is:

[0042] S cf =k p ×scf

[0043] Among them, S cf is the fuel consumption; k p is the intake duct loss correction factor; the fuel consumption rate is scf;

[0044] The centroid solution operator model is:

[0045] Oil weight(L) 0 620 1360 1600 Center of gravity (%) 43.18 38.45 40.26 38.71 Oil weight(L) 2378 2770 2847 Center of gravity (%) 41.18 40.39 40.17

[0046] The moment of inertia solver model is:

[0047] When two 760-liter auxiliary fuel tanks are hung and the fuel volume is greater than 2,378 liters, the three-axis rotation inertia is:

[0048]

[0049] When two 760-liter auxiliary fuel tanks are hung and the fuel volume is less than 2378 liters and greater than 1600 liters, the three-axis rotation inertia is:

[0050]

[0051] When there is no external plug-in, the moment of inertia of the three axes is:

[0052]

[0053] Among them, I x is the x-axis moment of inertia of the aircraft, I y is the moment of inertia of the aircraft along the y-axis, I z is the moment of inertia of the aircraft along the z axis, I x ,I y ,I z The unit is N·m·s 2 ; G y is the amount of fuel; after the landing gear is lowered, I z Increase 18.5N·m·s 2 ;

[0054] The atmospheric data solution operator model is:

[0055] When the flight altitude is less than 11,000 meters,

[0056] When the altitude is greater than 11,000 meters and less than 20,000 meters,

[0057] Where T is the atmospheric temperature in °C; ρ is the atmospheric density in kg / m 3 ; p is atmospheric pressure, the unit is Pa; v s is the speed of sound, in m / s; h is the flight altitude.

[0058] As a possible implementation method, the dynamics solution model includes a dynamics solution model for an aerial flight segment, a dynamics solution model for a take-off run segment, and a dynamics solution model for a landing run segment;

[0059] Among them, the dynamics solution model of the aerial flight segment is:

[0060]

[0061] The dynamic solution model of the takeoff run is:

[0062]

[0063] Among them, ∑F x is the total resistance; ∑F y is the total lift; ∑F z is the sum of lateral forces; ∑M x is the total rolling moment; ∑M y is the total yaw moment; ∑M z is the total pitch moment; P is the effective thrust of the engine; X is the drag; Y is the lift; Z is the side force; φ e is the angle between the thrust and the aircraft axis; α is the aircraft angle of attack; β is the aircraft sideslip angle; θ is the aircraft pitch angle; γ is the aircraft roll angle; mg is the aircraft gravity; f is the aircraft taxiing resistance; N is the taxiing support force;

[0064] The dynamic solution model of the landing roll phase is:

[0065]

[0066] Among them, ∑F x is the total resistance; ∑F y is the total lift; ∑F z is the sum of lateral forces; ∑M x is the total rolling moment; ∑M y is the total yaw moment; ∑M z is the total pitching moment; v x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft; ω x is the rolling angular rate; ωy is the yaw angular rate; ω z is the pitch angle rate; I x I is the x-axis moment of inertia of the aircraft; y I is the moment of inertia of the aircraft on the y-axis; z I is the moment of inertia of the aircraft on the z axis; xy is the vehicle's moment of inertia.

[0067] As a possible implementation method, the kinematic solution model is:

[0068]

[0069] Among them, γ is the roll angle of the aircraft; φ is the true heading; θ is the pitch angle of the aircraft; ω x is the rolling angular rate; ω y is the yaw angular rate; ω z is the pitch angle rate; is the x-axis component of the aircraft velocity in the earth axis system; is the y-axis component of the aircraft velocity in the earth axis system; v is the z-axis component of the aircraft velocity in the earth axis system; x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft.

[0070] As a possible implementation method, the three-axis speed of the earth axis system and the earth speed are converted into variables in the following way:

[0071]

[0072] Among them, v xg v is the x-axis component of the aircraft velocity in the earth axis system; yg v is the y-axis component of the aircraft velocity in the earth axis system; zg v is the z-axis component of the aircraft velocity in the earth axis system; d is the aircraft ground speed;

[0073] The airspeed is converted into a variable in the following way:

[0074]

[0075] Among them, u x is the x-axis component of wind speed in the body axis system; u y is the y-axis component of wind speed in the body axis system; u z is the z-axis component of wind speed in the body axis system; u xg is the x-axis component of wind speed in the earth axis system; u yg is the y-axis component of wind speed in the earth axis system; u zg is the z-axis component of wind speed in the earth axis system; vx is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft; φ is the true heading; is the pitch angle of the aircraft; γ is the roll angle of the aircraft; v is the true airspeed of the aircraft.

[0076] In a second aspect, a robot pilot flight simulation platform includes a retired aircraft, original aircraft support equipment, and a simulation system; wherein the simulation system is mounted on the retired aircraft and is in communication connection with the robot pilot; the original aircraft support equipment is used to raise the retired aircraft to a certain distance from the ground and provide power for the retired aircraft, the robot pilot, and the simulation system;

[0077] The simulation system includes a simulation computer, a data acquisition component, and a data cable and a power cable for connecting them; wherein the data acquisition component includes an elevator angle collector, a rudder angle collector, an aileron rudder angle collector, a discrete state video collector, and a throttle handle scale video collector installed at a preset position of the retired aircraft; the simulation computer is configured with an aerodynamic force and torque solution model, a dynamic solution model, and a kinematic solution model; the simulation computer receives the elevator angle, rudder angle, aileron rudder angle, throttle handle position and discrete state information, and uses the aerodynamic force and torque solution model, the dynamic solution model, and the kinematic solution model to solve them in turn, and obtains the three-dimensional position, three-dimensional speed, three-dimensional angle and angular velocity, weight and fuel quantity of the retired aircraft through variable conversion, and outputs the above information to the robot pilot through a data interface.

[0078] Compared with the prior art, the beneficial effects of the present invention are:

[0079] 1. The present invention utilizes retired aircraft, configures original aircraft support equipment and carries a simulation system, which can provide a realistic simulation environment for robot pilots and greatly shorten the process of robot pilots forming independent driving capabilities.

[0080] 2. The present invention makes full use of existing equipment and adopts a non-invasive mounting method, which has the advantages of strong versatility, low cost and easy implementation. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0082] Figure 1 A flowchart of a construction method provided by an embodiment of the present invention;

[0083] Figure 2The working principle of the simulation environment provided by the embodiment of the present invention;

[0084] Figure 3 A simulation computer execution flow chart provided for an embodiment of the present invention;

[0085] Figure 4 A schematic diagram of the structure of a simulation platform provided by an embodiment of the present invention;

[0086] Figure 5 A flow chart of the throttle handle scale position recognition provided by an embodiment of the present invention.

[0087] Reference numerals:

[0088] 10- jack, 11- hydraulic pump;

[0089] 20-discrete state video collector, 21-throttle handle scale video collector, 22-elevator angle collector, 23-rudder angle collector, 24-aileron rudder angle collector. DETAILED DESCRIPTION

[0090] In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and their order is not limited. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0091] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0092] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. The following at least one item (items) or similar expressions thereof refer to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one item (items) of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0093] First, see Figures 1 to 4 The present invention provides a method for constructing a robot pilot flight simulation environment, comprising the following steps:

[0094] S10. Configure the retired aircraft and the original aircraft support equipment. A simulation environment close to reality required for the robot pilot to carry out simulation training is established based on the retired aircraft, that is, a real simulation environment is provided for the robot pilot, for example, a real cockpit, joystick, throttle handle, cockpit switches and highly realistic flight dynamics based on the simulation system. The original aircraft support equipment at least guarantees the jack 10, hydraulic pump 11 or power supply, etc., to ensure the normal operation of the retired aircraft joystick, pedals, throttle handle, cockpit switches during the simulation process.

[0095] S11. Remove the seats in the cockpit of the retired aircraft and install the robot aircraft on the original seat back rail position. Alternatively, install the robot pilot in the cockpit by installing a conversion bracket.

[0096] S12. Lift the retired aircraft by the jack 10 so that its tires are a certain distance away from the ground. At the same time, connect the power supply, hydraulic pump 11 and simulation system.

[0097] S13. A simulation system is mounted on the retired aircraft, and a communication connection is established between the simulation system and the robot pilot. The simulation system includes a simulation computer, a data acquisition component, and a data cable and a power cable for connecting them. Among them, the data acquisition component includes an elevator angle collector 22, a rudder angle collector 23, an aileron rudder angle collector 24, a discrete state video collector 20, and a throttle handle scale video collector 21 installed at a preset position of the retired aircraft. The simulation computer is configured with an aerodynamic force and torque solution model, a dynamic equation solution model, and a kinematic equation solution model; the simulation computer receives the elevator angle, rudder angle, aileron rudder angle, throttle handle position and discrete state information, and uses the aerodynamic force and torque solution model, the dynamic equation solution model, and the kinematic equation solution model to solve in turn, and obtains the three-dimensional position, three-dimensional speed, three-dimensional angle and angular velocity, weight and fuel information of the retired aircraft through variable conversion, and outputs the above information to the robot pilot through the data interface.

[0098] The simulation computer consists of hardware and software. The hardware includes a CPU board, a video signal processing board, a discrete quantity board, a power supply board, and a chassis. The aerodynamic force and torque calculation, dynamics calculation, and kinematics calculation are realized by software algorithms.

[0099] The dial, pointer and camera are installed at the fixed end corresponding to the elevator, rudder and aileron. The camera is used to collect the relevant images of the pointer changes on the dial, and then the image processing method is applied to solve the angle values ​​corresponding to the elevator, rudder and aileron, which are used as the input of the aerodynamic force and torque solution model. The angle values ​​of the three rudder surfaces have high requirements for the real-time simulation solution, and the data update rate is required to reach the millisecond level.

[0100] The discrete state video collector 20 is used to collect the status of landing gear retracted or lowered, flaps retracted or lowered, external equipment, etc. Specifically, a camera can be set up on the ground at the tail of the retired aircraft to collect real-time video of the landing gear retracted or lowered, flaps retracted or lowered, and external equipment status, and then the video processing method is used to calculate it. The discrete state update rate requirement is not high, that is, the data update rate can reach the second level.

[0101] As a possible implementation method, the video processing method for the landing gear retracted or extended, flaps retracted or extended, and external hanger presence or absence adopts the YOLOv5 algorithm, which specifically includes the following steps:

[0102] S130. Data collection and preprocessing. Use a binocular camera to collect images of various angles and lighting conditions with the landing gear retracted or extended, flaps retracted or extended, and external attachments present, and annotate them to construct a training data set and test data set.

[0103] S131. Model training and optimization. Use the YOLOv5 framework to train the model and optimize the model's target detection performance by adjusting hyperparameters such as network structure and anchor point size.

[0104] With the above technical solution, the purpose of multi-scale detection enhancement can be achieved. In order to solve the problem that the size of the detected target will change due to the change of the camera installation position, the multi-scale detection characteristics of YOLOv5 are used to enhance the detection capability. It can also optimize the real-time performance, that is, while ensuring the detection accuracy, the model size can be reduced through model pruning, quantization and other technologies, and the reasoning speed can be improved to ensure the real-time performance.

[0105] Throttle handle scale video collector 21: A camera is installed above the throttle handle in the cockpit. The throttle handle scale position is calculated through image processing, and converted into engine speed data through conversion, and converted into engine thrust and fuel consumption rate data. The calculation needs to be combined with the altitude data of the retired aircraft.

[0106] As a possible implementation method, the throttle handle scale position recognition uses a camera to collect the current position image of the throttle handle, and then Figure 5 The steps are processed:

[0107] S140. Pointer extraction, throttle handle position Pointer extraction is to use image processing methods to separate the pointer image from the complete instrument image. Using the difference method to reduce the background can reduce the interference of the dial background on the pointer and improve the accuracy of the pointer reading. The principle of the difference method is to use the image to be tested to subtract a template image with no pointer but only background to achieve the goal of reducing the background. The template image can be obtained by performing an "AND" operation on two dial images with pointers in different positions.

[0108] S141. Preprocessing of pointer image. After the pointer is extracted, it needs to be preprocessed. The goal is to extract the pointer edge from the pointer image to prepare for the subsequent Hough transform to extract the straight line. The methods used in this stage include grayscale, Gaussian smoothing, and binary combined edge detection.

[0109] Among them, the image captured by the camera is in RGB true color format. The color information is not very meaningful for pointer recognition. On the contrary, the true color image will increase the image processing time. Therefore, the image is first grayed out and the grayscale image is used as the basis for the next step of recognition.

[0110] Since digital images will generate noise during the acquisition and transmission process, which will affect the accuracy of pointer recognition, the image needs to be smoothed before further processing. The 5-neighborhood Gaussian filtering algorithm is used to smooth the image.

[0111] After the pointer image is grayed and Gaussian transformed, the pointer part has a higher brightness. At this time, a binarization operation can be performed to remove other useless information, and the binarization threshold is set to 100.

[0112] Edge detection can reduce the number of straight lines found during Hough transform, making the reading calculation results more accurate.

[0113] S142. Hough transform is performed to find the straight line. The Hough transform is performed on the pointer image after edge detection to find the straight line, and the straight line equation of the pointer edge can be obtained.

[0114] S143. Pointer reading: Identify the dial scale by the scale method, read the instrument by the relative position of the pointer and the scale, and finally obtain the throttle handle scale data.

[0115] The installation of each component unit of the simulation system is temporary when in use, without changing the aircraft status, realizing a non-intrusive design.

[0116] The solution cycle of the aerodynamic force and torque solution model, dynamic solution model and kinematic solution model configured by the simulation computer must be guaranteed to reach the millisecond level.

[0117] See also Figure 2 and Figure 3 The data acquisition component sends the elevator angle, rudder angle, aileron angle, throttle handle position and discrete state information to the aerodynamic force and torque solution model configured in the simulation computer, and combines the original aerodynamic data of the retired aircraft to calculate the aerodynamic force and torque of the retired aircraft, including lift, drag, side force, pitch moment, engine thrust, fuel consumption rate, center of gravity, moment of inertia and atmospheric data, etc. Based on this, dynamic and kinematic solutions are performed, and the longitude, latitude, altitude, northeast celestial speed, pitch angle, bank angle, true heading, pitch angle rate, bank angle rate, yaw angle rate and other information of the retired aircraft are obtained through transformation, and sent to the robot pilot. After receiving the command, the robot pilot operates the retired aircraft, and the further data acquisition component collects relevant data in real time before entering the next solution cycle to cycle the above program.

[0118] For ease of understanding, the solution method is described in detail below:

[0119] The lift solution operator model is:

[0120] Y=qs×C y

[0121]

[0122] Among them, Y is lift; qs is dynamic pressure, which represents the pressure generated when the air flows, and the unit is Pa, qs = ρ × υ2 / 2, ρ is the air density at the flight altitude, υ is the flight speed; C y is the lift coefficient; C y0 , They are zero lift coefficient, angle of attack lift coefficient, and horizontal tail lift coefficient, which are obtained based on the difference of longitudinal aerodynamic parameters; C yjy is the flap lift coefficient. If there are flaps, it takes different values ​​according to the flap angle. The value is calculated based on the wind data or aerodynamic theory. If there are no flaps, C yjy is 0; C ydx The ground effect is taken into account when the aircraft height is less than the height threshold. For example, the ground effect is taken into account when the aircraft height is less than 2.2 meters from the ground. The calculation formula is: α is the aircraft angle of attack; δ z is the horizontal tail deflection angle;

[0123] The resistance solution operator model is:

[0124] X=qs×C x

[0125]

[0126] Where X is the resistance; qs is the dynamic pressure; C x is the drag coefficient; C x0 , is the zero-lift drag coefficient and the induced drag coefficient, which are obtained based on the longitudinal aerodynamic parameter difference; α is the aircraft angle of attack; C is the altitude correction for zero lift resistance; xqlj is the landing gear drag coefficient; C xjy is the flap drag coefficient, which takes different values ​​according to the flap angle. The data value is determined based on the wind data or aerodynamic theory. If there is no flap, this value is 0; C xwg is the external drag coefficient, which is calculated based on relevant aerodynamic theories. In addition, when the engine is stopped, the above drag coefficients increase by 0.0074.

[0127] The lateral force solution operator model is:

[0128] Z=qs×C z

[0129]

[0130] Where Z is the lateral force; qs is the dynamic pressure; C z is the lateral force coefficient; is the side force coefficient of the sideslip angle, is the rudder side force coefficient, According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input; C zf is the engine side force coefficient, β is the side slip angle of the aircraft; δ y For the aircraft rudder.

[0131] The pitch moment solver model is:

[0132] M z =qs×b A ×m z

[0133]

[0134] Among them, M z is the pitch moment; qs is the dynamic pressure; b A is the average aerodynamic chord length; m z is the pitch moment coefficient; α is the aircraft angle of attack, δ z is the tail deviation angle of the aircraft, m z0 is the pitch moment coefficient generated by the aircraft shape when the angle of attack is 0°, is the pitch moment coefficient generated by the aircraft's angle of attack; It is the ground effect coefficient caused by the aircraft's angle of attack. According to engineering test data, it is included when the aircraft is less than 2.2 meters above the ground. α is the aircraft angle of attack; is the pitch moment coefficient generated by the rate of change of the aircraft's angle of attack; is the rate of change of the aircraft angle of attack; is the pitch moment coefficient generated by the aircraft elevator; δ z is the horizontal tail deflection angle; is the pitch moment coefficient generated by the pitch angular rate of the aircraft; ω z is the pitch angle rate; m zf is the effect of the aircraft on the pitch moment coefficient, m zs is the moment of lift on the center of gravity; m zwg The data is calculated based on the shape of the plug-in through aerodynamics related theories; m zjy Different values ​​are taken according to the flap angle. The data value is determined according to the wind data or aerodynamic theory calculation. If there is no flap, this value is 0; is the rate of change of the aircraft angle of attack; ω z is the pitch angle rate;

[0135] The rolling moment solver model is:

[0136] M x =qs×l×mx

[0137]

[0138] Among them, M x is the rolling moment; qs is the dynamic pressure; l is the wingspan; m x is the lateral torque coefficient; is the rolling moment coefficient generated by the roll angle; β is the side slip angle of the aircraft; is the rolling moment coefficient generated by the rudder; δ y For aircraft rudder; is the rolling moment coefficient generated by the aileron rudder; δ x It is the aileron rudder of the aircraft; is the rolling moment coefficient generated by the rolling angular rate; ω x is the rolling angular rate; is the rolling moment coefficient generated by the yaw angular rate; ω y is the yaw angular rate; is the rolling moment coefficient generated by the yaw angle acceleration rate; α is the aircraft angle of attack; v is the true airspeed of the flight; According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input;

[0139] The yaw moment sub-model is:

[0140] M y =qs×l×m y

[0141]

[0142] Among them, M y is the yaw moment; qs is the dynamic pressure; l is the wingspan; m y is the yaw moment coefficient; is the yaw moment coefficient generated by the roll angle; β is the side slip angle of the aircraft; is the yaw moment coefficient generated by the rudder; δ y For aircraft rudder; is the yaw moment coefficient generated by the yaw angular rate; ω y is the yaw angular rate; is the yaw moment coefficient generated by the rolling angular rate; ω x is the rolling angular rate; v is the true airspeed; m yf is the effect of the engine on the yaw moment coefficient, According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input.

[0143] The engine thrust submodel is:

[0144] P = k p ×T h

[0145] Where P is the effective thrust of the engine; k p is the inlet loss correction coefficient. According to engineering experience data, when the flight Mach number Ma>0.3, k p =0.905, when Ma≤0.3, k p =0.88+0.0833×Ma; the thrust of the engine is T h , unit is N;

[0146] It needs further explanation that the engine thrust and fuel consumption rate are divided into two states: maximum and rated. The thrust and fuel consumption rate of other throttle states have a certain proportional relationship with the rated state. According to the flight altitude and speed, the difference can be used to obtain the engine thrust and fuel consumption rate in the maximum and rated states, which is recorded as T d 、T e 、scf d 、scf e When the altitude or speed exceeds the range, the difference is calculated based on the three most recent data sets. Assume that the thrust ratios of cruise 1, cruise 2, cruise 3, cruise 4 and other states to the rated thrust are k t1 , k t2 , k t3 , k t4 The ratio of fuel consumption rate to rated fuel consumption rate is k s1 , k s2 , k s3 , k s4 , the thrust and fuel consumption rate of each state are shown in the following table:

[0147] Thrust and fuel consumption table at different throttle states

[0148] Throttle status Thrust(kg) Fuel consumption rate (kg / h) maximum <![CDATA[T d ]]> <![CDATA[scf d ]]> Rated <![CDATA[T e ]]> <![CDATA[scf e ]]> Cruise 1 <![CDATA[k t1 T e ]]> <![CDATA[k s1 scf e ]]> Cruise 2 <![CDATA[k t2 T e ]]> <![CDATA[k s2 scf e ]]> Cruise 3 <![CDATA[k t3 T e ]]> <![CDATA[k s3 scf e ]]> Cruise 4 <![CDATA[k t4 T e ]]> <![CDATA[k s4 scf e ]]> local 70-h / 300 0.167×3600 parking 0 0

[0149] The fuel consumption quantum model is:

[0150] S cf =k p ×scf

[0151] Among them, S cf is the fuel consumption; k p is the intake duct loss correction factor; the fuel consumption rate is scf;

[0152] The center of gravity of a retired aircraft changes continuously as fuel is consumed during flight. The center of gravity of special nodes during the change process is shown in the table below. The change between two adjacent points is linear and can be calculated by difference. The center of gravity solution submodel is:

[0153] Center of gravity changes with fuel consumption

[0154] Oil weight(L) 0 620 1360 1600 Center of gravity (%) 43.18 38.45 40.26 38.71 Oil weight(L) 2378 2770 2847 Center of gravity (%) 41.18 40.39 40.17

[0155] It is important to further explain that when the landing gear is lowered, the center of gravity moves back 0.9. The calculation of the center of gravity also needs to take into account the weight and position of the external attachments.

[0156] The moment of inertia solver model is:

[0157] When two 760-liter auxiliary fuel tanks are hung and the fuel volume is greater than 2,378 liters, the three-axis rotation inertia is:

[0158] When two 760-liter auxiliary fuel tanks are hung and the fuel volume is less than 2378 liters and greater than 1600 liters, the three-axis rotation inertia is:

[0159]

[0160] When there is no external plug-in, the moment of inertia of the three axes is:

[0161]

[0162] Among them, I x is the x-axis moment of inertia of the aircraft, I y is the moment of inertia of the aircraft along the y-axis, I z is the moment of inertia of the aircraft along the z axis, I x ,I y ,I z The unit is N·m·s 2 ; G y is the amount of fuel; after the landing gear is lowered, I z Increase 18.5N·m·s 2 ;

[0163] The atmospheric data solver model is:

[0164] When the flight altitude is less than 11,000 meters,

[0165] When the altitude is greater than 11,000 meters and less than 20,000 meters,

[0166] Where T is the atmospheric temperature in °C; ρ is the atmospheric density in kg / m 3 ; p is atmospheric pressure, the unit is Pa; v sis the speed of sound, in m / s; h is the flight altitude.

[0167] The dynamics solution model includes a dynamics solution model for the aerial flight segment, a dynamics solution model for the take-off run segment, and a dynamics solution model for the landing run segment;

[0168] Among them, the dynamics solution model of the aerial flight segment is:

[0169]

[0170] The dynamic solution model of the takeoff run is:

[0171]

[0172] Among them, ∑F x is the total resistance; ∑F y is the total lift; ∑F z is the sum of lateral forces; ∑M x is the total rolling moment; ∑M y is the total yaw moment; ∑M z is the total pitch moment; P is the effective thrust of the engine; X is the drag; Y is the lift; Z is the side force; φ e is the angle between the thrust and the aircraft axis; α is the aircraft angle of attack; β is the aircraft sideslip angle; θ is the aircraft pitch angle; γ is the aircraft roll angle; mg is the aircraft gravity; f is the aircraft taxiing resistance; N is the taxiing support force;

[0173] The dynamics solution model of the landing roll phase is:

[0174]

[0175] Among them, ∑F x is the total resistance; ∑F y is the total lift; ∑F z is the sum of lateral forces; ∑M x is the total rolling moment; ∑M y is the total yaw moment; ∑M z is the total pitching moment; v x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft; ω x is the rolling angular rate; ω y is the yaw angular rate; ω z is the pitch angle rate; I x I is the x-axis moment of inertia of the aircraft; y I is the moment of inertia of the aircraft on the y-axis; z I is the moment of inertia of the aircraft on the z axis; xy is the vehicle's moment of inertia.

[0176] The kinematic solution model is:

[0177]

[0178] Among them, γ is the roll angle of the aircraft; φ is the true heading; θ is the pitch angle of the aircraft; ω x is the rolling angular rate; ω y is the yaw angular rate; ω z is the pitch angle rate; is the x-axis component of the aircraft velocity in the earth axis system; is the y-axis component of the aircraft velocity in the earth axis system; v is the z-axis component of the aircraft velocity in the earth axis system; x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft.

[0179] The three-axis speed of the earth axis system and the earth speed are converted into variables in the following way:

[0180]

[0181] Among them, v xg v is the x-axis component of the aircraft velocity in the earth axis system; yg v is the y-axis component of the aircraft velocity in the earth axis system; zg v is the z-axis component of the aircraft velocity in the earth axis system; d is the aircraft ground speed;

[0182] The airspeed is converted into a variable in the following way:

[0183]

[0184] Among them, u x is the x-axis component of wind speed in the body axis system; u y is the y-axis component of wind speed in the body axis system; u z is the z-axis component of wind speed in the body axis system; u xg is the x-axis component of wind speed in the earth axis system; u yg is the y-axis component of wind speed in the earth axis system; u zg is the z-axis component of wind speed in the earth axis system; v x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft; φ is the true heading; θ is the pitch angle of the aircraft; γ is the roll angle of the aircraft; and v is the true airspeed of the aircraft.

[0185] See also Figure 3Before the first solution cycle, the simulation system needs to collect the zero position of the three control surfaces to determine the initial attitude and position of the retired aircraft. The throttle handle position is calibrated, and the initial values ​​of the retired aircraft's initial three-dimensional position, three-dimensional speed and angular rate, weight, fuel volume, external model and quantity are set.

[0186] The simulation computer executes the following process in a cycle of 1ms: first, the positions of the three control surfaces and throttle handles are collected, and the landing gear, flaps, and external hanger status are collected to solve the aerodynamic force and torque of the aircraft. The dynamic equations are solved on the ground and in the air, and then the kinematic equations are solved. Finally, the aircraft's three-dimensional position, three-dimensional speed, three-dimensional angle and angular velocity, weight, fuel volume and other information are obtained through variable conversion, and output to the robot pilot through the data interface. After the timing time is up, the new cycle of solution is started. The smaller the solution cycle, the higher the simulation fidelity. This constitutes a closed-loop simulation environment, which provides conditional support for training the driving skills of robot pilots.

[0187] The present invention utilizes retired aircraft, configures original aircraft support equipment and carries a simulation system, which can provide a realistic simulation environment for robot pilots and greatly shorten the process for robot pilots to develop independent driving capabilities.

[0188] The present invention makes full use of existing equipment and adopts a non-invasive mounting method, and has the advantages of strong versatility, low cost and easy implementation.

[0189] See also Figure 4 An embodiment of the present invention further provides a robot pilot flight simulation platform, including a retired aircraft, original aircraft support equipment and a simulation system; wherein the simulation system is mounted on the retired aircraft and is communicatively connected with the robot pilot; the original aircraft support equipment is used to raise the retired aircraft to a certain distance from the ground and provide power for the retired aircraft, the robot pilot and the simulation system. The simulation system includes a simulation computer, a data acquisition component, and a data line and a power line for connecting them; wherein the data acquisition component includes an elevator angle collector 22, a rudder angle collector 23, an aileron rudder angle collector 24, a discrete state video collector 20, and a throttle handle scale video collector 21 installed at a preset position of the retired aircraft; the simulation computer is configured with an aerodynamic force and torque solution model, a dynamic solution model, and a kinematic solution model; the simulation computer receives the elevator angle, rudder angle, aileron rudder angle, throttle handle position and discrete state information, and uses the aerodynamic force and torque solution model, the dynamic solution model, and the kinematic solution model to solve in turn, and obtains the three-dimensional position, three-dimensional speed, three-dimensional angle and angular velocity, weight and oil volume of the retired aircraft through variable conversion, and outputs the above information to the robot pilot through a data interface. The original aircraft support equipment at least includes a jack 10, a hydraulic pump 11, and a power supply.

[0190] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the drawings, etc. In the specification, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit can implement several functions listed in the specification. Certain measures are recorded in different embodiments, but this does not mean that these measures cannot be combined to produce good results.

[0191] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the present invention and its equivalents.

Claims

1. A method for constructing a robot pilot flight simulation environment, characterized in that: The steps include: S10. Configure retired aircraft and original aircraft support equipment; S11. Remove the seats in the cockpit of the retired aircraft and install the robot pilot on the original seat back rail position; S12. Use the original aircraft support equipment to lift the retired aircraft so that the tires are off the ground by a preset distance, and connect the hydraulic pump and power supply; S13. A simulation system is mounted on the retired aircraft, and a communication connection is established between the simulation system and the robot pilot; the simulation system includes a simulation computer, a data acquisition component, and a data cable and a power cable for connecting the system; wherein the data acquisition component includes an elevator angle collector, a rudder angle collector, an aileron rudder angle collector, a discrete state video collector, and a throttle handle scale video collector installed at a preset position of the retired aircraft; the simulation computer is configured with an aerodynamic force and torque solution model, a dynamic solution model, and a kinematic solution model; the simulation computer receives the elevator angle, rudder angle, aileron rudder angle, throttle handle position, and discrete state information, and solves them in turn using the aerodynamic force and torque solution model, the dynamic solution model, and the kinematic solution model, and obtains the three-dimensional position, three-dimensional speed, three-dimensional angle and angular velocity, weight, and fuel quantity information of the retired aircraft through variable conversion, and outputs the above information to the robot pilot through a data interface.

2. The method for constructing a robot pilot flight simulation environment according to claim 1, characterized in that: Before executing the simulation system, the simulation system is initialized, specifically including: Collect the zero position of the elevator, rudder and aileron surfaces; Calibrate the throttle handle position; set the retired aircraft's initial 3D position, 3D speed, 3D angle, angular rate, weight, fuel volume, external plug-in model and quantity.

3. The method for constructing a robot pilot flight simulation environment according to claim 1, characterized in that: The aerodynamic force and moment solution model includes a lift solution operator model, a drag solution operator model, a side force solution operator model, a pitch moment solution operator model, a rolling moment solution operator model, a yaw moment sub-model, an engine thrust sub-model, a fuel consumption quantum model, a center of gravity solution operator model, a moment of inertia solution operator model and an atmospheric data solution operator model.

4. The method for constructing a robot pilot flight simulation environment according to claim 3, characterized in that: The lift solution operator model is: Y=qs×C y Among them, Y is lift; qs is dynamic pressure, which represents the pressure generated when the air flows, and the unit is Pa, qs = ρ × υ 2 / 2, ρ is the air density at the flight altitude, v is the flight speed; C y is the lift coefficient; C y0 , They are zero lift coefficient, angle of attack lift coefficient, and horizontal tail lift coefficient, which are obtained based on the difference of longitudinal aerodynamic parameters; C yjy is the flap lift coefficient. If there are flaps, it takes different values ​​according to the flap angle. The value is calculated based on the wind data or aerodynamic theory. If there are no flaps, C yjy is 0; C ydx is the influence of ground effect. When the height of the aircraft from the ground is less than the height threshold, the ground effect is considered; α is the aircraft angle of attack; δ z is the horizontal tail deflection angle; The resistance solution operator model is: X=qs×C x Where X is the resistance; q s is the dynamic pressure, C x is the drag coefficient; C x0 , is the zero-lift drag coefficient and the induced drag coefficient, which are obtained based on the longitudinal aerodynamic parameter difference; α is the aircraft angle of attack; C is the altitude correction for zero lift resistance; xqlj is the landing gear drag coefficient; C xjy is the flap drag coefficient, which takes different values ​​according to the flap angle. The data value is determined based on the wind data or aerodynamic theory. If there is no flap, this value is 0; C xwg is the external drag coefficient, which is calculated based on relevant aerodynamic theories. In addition, when the engine is stopped, the above drag coefficients increase by 0.0074. The lateral force solution operator model is: Z=qs×C z Where Z is the lateral force; qs is the dynamic pressure; C z is the lateral force coefficient; is the side force coefficient of the sideslip angle, is the rudder side force coefficient, According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input; C zf is the engine side force coefficient, β is the side slip angle of the aircraft; δ y For the aircraft rudder.

5. The method for constructing a robot pilot flight simulation environment according to claim 4, characterized in that: The pitch moment solver model is: M z =qs×b A ×m z Among them, M z is the pitch moment; qs is the dynamic pressure; b A is the average aerodynamic chord length; m z is the pitch moment coefficient; α is the aircraft angle of attack, δ z is the horizontal tail deviation angle of the aircraft, m z0 is the pitch moment coefficient generated by the aircraft shape when the angle of attack is 0°, is the pitch moment coefficient generated by the aircraft's angle of attack; It is the ground effect coefficient caused by the aircraft's angle of attack. According to engineering test data, it is included when the aircraft is less than 2.2 meters above the ground. The height of the aircraft from the ground); α is the aircraft's angle of attack; is the pitch moment coefficient generated by the rate of change of the aircraft's angle of attack; is the rate of change of the aircraft angle of attack; is the pitch moment coefficient generated by the aircraft elevator; δ z is the horizontal tail deflection angle; is the pitch moment coefficient generated by the pitch angular rate of the aircraft; ω z is the pitch angle rate; m zf is the effect of the aircraft on the pitch moment coefficient, m zs is the moment of lift on the center of gravity; m zwg The data is calculated based on the shape of the plug-in through aerodynamics related theories; m zjy Different values ​​are taken according to the flap angle. The data value is determined according to the wind data or aerodynamic theory calculation. If there is no flap, this value is 0; The rolling moment solver model is: M x =qs×l×m x Among them, M x is the rolling moment; qs is the dynamic pressure; l is the wingspan; m x is the lateral torque coefficient; is the rolling moment coefficient generated by the roll angle; β is the side slip angle of the aircraft; is the rolling moment coefficient generated by the rudder; δ y For aircraft rudder; is the rolling moment coefficient generated by the aileron rudder; δ x It is the aileron rudder of the aircraft; is the rolling moment coefficient generated by the rolling angular rate; ω x is the rolling angular rate; is the rolling moment coefficient generated by the yaw angular rate; ω y is the yaw angular rate; is the rolling moment coefficient generated by the yaw angle acceleration rate; α is the aircraft angle of attack; v is the true airspeed of the flight; According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input; The yaw moment sub-model is: M y =qs×l×m y Among them, M y is the yaw moment; qs is the dynamic pressure; l is the wingspan; m y is the yaw moment coefficient; is the yaw moment coefficient generated by the roll angle; β is the side slip angle of the aircraft; is the yaw moment coefficient generated by the rudder; δ y For aircraft rudder; is the yaw moment coefficient generated by the yaw angular rate; ω y is the yaw angular rate; is the yaw moment coefficient generated by the rolling angular rate; ω x is the rolling angular rate; v is the true airspeed; m yf is the effect of the engine on the yaw moment coefficient, According to the original aerodynamic data table obtained from the wind test, the difference is obtained by querying the flight altitude and flight speed as input.

6. The method for constructing a robot pilot flight simulation environment according to claim 5, characterized in that: The engine thrust submodel is: P=k p ×T h Where P is the effective thrust of the engine; k p is the inlet loss correction coefficient. According to engineering experience data, when the flight Mach number Ma>0.3, k p =0.905, when Ma≤0.3, k p =0.88+0.0833×Ma; the thrust of the engine is T h , unit is N; The fuel consumption quantum model is: S cf =k p ×scf Among them, S cf is the fuel consumption; k p is the intake duct loss correction factor; the fuel consumption rate is scf; The centroid solution operator model is: The moment of inertia solver model is: When two 760-liter auxiliary fuel tanks are hung and the fuel volume is greater than 2,378 liters, the three-axis rotation inertia is: When two 760-liter auxiliary fuel tanks are hung and the fuel volume is less than 2378 liters and greater than 1600 liters, the three-axis rotation inertia is: When there is no external plug-in, the moment of inertia of the three axes is: Among them, I x is the x-axis moment of inertia of the aircraft, I y is the moment of inertia of the aircraft along the y-axis, I z is the moment of inertia of the aircraft along the z axis, I x ,I y ,I z The unit is N·m·s 2 ; G y is the amount of fuel; after the landing gear is lowered, I z Increase 18.5N·m·s 2 ; The atmospheric data solver model is: When the flight altitude is less than 11,000 meters, When the altitude is greater than 11,000 meters and less than 20,000 meters, Where T is the atmospheric temperature in °C; ρ is the atmospheric density in kg / m 3 ; p is atmospheric pressure, the unit is Pa; v s is the speed of sound, in m / s; h is the flight altitude.

7. The method for constructing a robot pilot flight simulation environment according to claim 6, characterized in that: The dynamics solution model includes a dynamics solution model for the aerial flight segment, a dynamics solution model for the take-off run segment, and a dynamics solution model for the landing run segment; Among them, the dynamics solution model of the aerial flight segment is: The dynamic solution model of the takeoff run is: Among them, ∑F x is the total resistance; ∑F y is the total lift; ∑F z is the sum of the side forces; P is the effective thrust of the engine; X is the drag; Y is the lift; Z is the side force; φ e is the angle between the thrust and the aircraft axis; α is the aircraft angle of attack; β is the aircraft sideslip angle; θ is the aircraft pitch angle; γ is the aircraft roll angle; mg is the aircraft gravity; f is the aircraft taxiing resistance; N is the taxiing support force; The dynamics solution model of the landing roll phase is: Among them, ∑F x is the total resistance; ∑F y is the total lift; ∑F z is the sum of lateral forces; ∑M x is the total rolling moment; ∑M y is the total yaw moment; ∑M z is the total pitching moment; v x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft; ω x is the rolling angular rate; ω y is the yaw angular rate; ω z is the pitch angle rate; I x I is the x-axis moment of inertia of the aircraft; y I is the moment of inertia of the aircraft on the y-axis; z I is the moment of inertia of the aircraft on the z axis; xy is the vehicle's moment of inertia.

8. The method for constructing a robot pilot flight simulation environment according to claim 7, characterized in that: The kinematic solution model is: Among them, γ is the roll angle of the aircraft; φ is the true heading; θ is the pitch angle of the aircraft; ω x is the rolling angular rate; ω y is the yaw angular rate; ω z is the pitch angle rate; is the x-axis component of the aircraft velocity in the earth axis system; is the y-axis component of the aircraft velocity in the earth axis system; v is the z-axis component of the aircraft velocity in the earth axis system; x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft.

9. The method for constructing a robot pilot flight simulation environment according to claim 8, characterized in that: The three-axis speed of the earth axis system and the earth speed are converted into variables in the following way: Among them, v xg v is the x-axis component of the aircraft velocity in the earth axis system; yg v is the y-axis component of the aircraft velocity in the earth axis system; zg v is the z-axis component of the aircraft velocity in the earth axis system; d is the aircraft ground speed; The airspeed is converted into a variable in the following way: Among them, u x is the x-axis component of wind speed in the body axis system; u y is the y-axis component of wind speed in the body axis system; u z is the z-axis component of wind speed in the body axis system; u xg is the x-axis component of wind speed in the earth axis system; u yg is the y-axis component of wind speed in the earth axis system; u zg is the z-axis component of wind speed in the earth axis system; v x is the horizontal speed of the aircraft; v y is the longitudinal velocity of the aircraft; v z is the lateral velocity of the aircraft; φ is the true heading; θ is the pitch angle of the aircraft; γ is the roll angle of the aircraft; and v is the true airspeed of the aircraft.

10. A robot pilot flight simulation platform, characterized in that: It includes a retired aircraft, original aircraft support equipment and a simulation system; wherein the simulation system is mounted on the retired aircraft and is in communication connection with the robot pilot; the original aircraft support equipment is used to raise the retired aircraft to a certain distance from the ground and provide power for the retired aircraft, the robot pilot and the simulation system; The simulation system includes a simulation computer, a data acquisition component, and a data cable and a power cable for connecting them; wherein the data acquisition component includes an elevator angle collector, a rudder angle collector, an aileron rudder angle collector, a discrete state video collector, and a throttle handle scale video collector installed at a preset position of the retired aircraft; the simulation computer is configured with an aerodynamic force and torque solution model, a dynamic solution model, and a kinematic solution model; the simulation computer receives the elevator angle, rudder angle, aileron rudder angle, throttle handle position and discrete state information, and uses the aerodynamic force and torque solution model, the dynamic solution model, and the kinematic solution model to solve them in turn, and obtains the three-dimensional position, three-dimensional speed, three-dimensional angle and angular velocity, weight and fuel quantity of the retired aircraft through variable conversion, and outputs the above information to the robot pilot through a data interface.

Images