Close air combat simulation method, device, equipment and medium based on maneuver prediction

Abstract

The present application discloses a close-range air combat simulation method, device, equipment and medium based on maneuver prediction, which relates to the field of air combat autonomous decision-making technology, including: using a six-degree-of-freedom nonlinear aircraft model as a fighter model to perform close-range air combat game confrontation environment and fighter initialization configuration; by combining the normal overload and roll angular velocity of the fighter model under each maneuver action to construct a game maneuver library corresponding to the two opposing sides, triggering the evaluation function design operation to obtain the target air combat situation evaluation function; based on the tactical maneuver decision optimal control model, model prediction control strategy, target air combat situation evaluation function and game maneuver library, determine the control decision corresponding to our fighter model; use the target control instruction corresponding to the control decision and the roll angle autopilot and angle of attack autopilot to control the motion of our fighter model to complete the close-range air combat simulation operation. The present application effectively improves the real-time and accuracy of air combat decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous air combat decision-making, and in particular to a close-range air combat simulation method, device, equipment and medium based on maneuver prediction. Background Art

[0002] Autonomous air combat is one of the important ways of future warfare. Unmanned combat aerial vehicles (UCAVs) will gradually upgrade to become one of the main combat equipment that can perform combat missions such as air confrontation, ground fire suppression, and participation in the seizure of air supremacy. The autonomous air combat process can be divided into three stages: situational awareness, autonomous decision-making, and command execution. Among them, autonomous decision-making is the core of the air combat process.

[0003] However, although the performance of UCAV has been greatly improved so far, most tasks in the current decision-making process cannot be separated from human intervention, and controllers need to control the UCAV on the ground through a base station. This control method not only has time delays, but is also susceptible to electromagnetic interference, which will have an adverse effect on the real-time and accuracy of UCAV motion control, and thus easily lead to deduction failures. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a close-range air combat simulation method, device, equipment and medium based on maneuver prediction, which can effectively improve the real-time and accuracy of air combat decision-making without human intervention, thereby improving combat effectiveness and autonomous decision-making level. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a close-range air combat simulation method based on maneuver prediction, comprising:

[0006] By using a six-degree-of-freedom nonlinear aircraft model as a fighter model to initialize the configuration of the environment and fighters for close-range air combat game confrontation, the fighter models of the two opposing sides in the current air combat environment can be obtained;

[0007] By combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, a game maneuver library corresponding to the two opposing parties is constructed, and a corresponding evaluation function design operation is triggered to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function;

[0008] Based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library, maneuver prediction is performed to determine the control decision corresponding to the fighter model of the own side of the confrontation;

[0009] Based on the game maneuver library corresponding to the own side, the target control instruction corresponding to the control decision is determined, and the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot are used to control the motion of the fighter model of the own side to complete the corresponding close-range air combat simulation operation.

[0010] Optionally, the environment and fighter initialization configuration for close-range air combat game confrontation by using a six-degree-of-freedom nonlinear aircraft model as a fighter model includes:

[0011] A six-degree-of-freedom nonlinear aircraft model is used to build a fighter model and a control law structure, and the fighter model body parameters, airborne weapon parameters and initial fighter posture of the two opposing sides in the current air combat environment are initialized and configured to obtain fighter models corresponding to the two opposing sides respectively;

[0012] Initialize and configure the game simulation parameters of close-range air combat game confrontation to obtain the current air combat environment.

[0013] Optionally, before constructing the game maneuver libraries corresponding to the two opposing parties respectively by combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, the method further includes:

[0014] By designing the control laws of the longitudinal channel and the lateral channel, the roll angle autopilot and the angle of attack autopilot of the fighter model are obtained.

[0015] Optionally, the step of constructing a game maneuver library corresponding to each of the two opposing parties by combining the normal overload and the rolling angular velocity of the fighter model under each maneuver comprises:

[0016] Obtaining the normal overload and rolling angular velocity of the fighter models of the opposing two parties under various maneuvers;

[0017] The normal overload and the roll angular velocity are combined, and a maneuver library is constructed using the obtained combination result to obtain a game maneuver library corresponding to the two opposing parties respectively.

[0018] Optionally, the maneuver prediction based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library includes:

[0019] Combining actions based on the game maneuver libraries corresponding to the two opposing parties respectively to construct a corresponding game maneuver matrix;

[0020] Using the target air combat situation assessment function, each action combination in the game maneuver matrix is ​​respectively evaluated for pitch angle situation, yaw angle situation, distance situation and altitude situation, so as to determine a game score matrix corresponding to the game maneuver matrix according to the obtained evaluation results;

[0021] Battlefield situation prediction is performed through the tactical maneuver decision-making optimal control model, the model prediction control strategy, the game score matrix and the state vector information corresponding to the two opposing parties to determine the control decision corresponding to the fighter model of one of the two opposing parties.

[0022] Optionally, the determining a target control instruction corresponding to the control decision based on the game maneuver library corresponding to the own party includes:

[0023] Based on the game maneuver library corresponding to the own side, a normal overload control instruction and a roll angular velocity control instruction corresponding to the control decision are generated.

[0024] Optionally, the using the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot to perform motion control on the fighter model of the own party includes:

[0025] Maintain the throttle lever position of the own fighter model, and input the normal overload control instruction and the roll angular velocity control instruction into the roll angle autopilot and angle of attack autopilot in the own fighter model respectively to complete the corresponding fighter motion control operation.

[0026] In a second aspect, the present application provides a close-range air combat simulation device based on maneuver prediction, comprising:

[0027] An initialization module is used to initialize the configuration of the environment and fighters for close-range air combat game confrontation by using a six-degree-of-freedom nonlinear aircraft model as a fighter model, so as to obtain the fighter models of the two opposing sides in the current air combat environment;

[0028] A function design module is used to construct a game maneuver library corresponding to the two opposing parties by combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, and trigger a corresponding evaluation function design operation to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function;

[0029] A maneuver prediction module is used to perform maneuver prediction based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library to determine the control decision corresponding to the fighter model of the own side of the confrontation;

[0030] The motion control module is used to determine the target control instruction corresponding to the control decision based on the game maneuver library corresponding to the own side, and use the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot to perform motion control on the fighter model of the own side to complete the corresponding close-range air combat simulation operation.

[0031] In a third aspect, the present application provides an electronic device, including:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the steps of the aforementioned close-range air combat simulation method based on maneuver prediction.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the steps of the aforementioned close-range air combat simulation method based on maneuver prediction.

[0035] It can be seen that in the present application, a six-degree-of-freedom nonlinear aircraft model is used as a fighter model to perform an environment and fighter initialization configuration for close-range air combat game confrontation, so as to obtain the fighter models of the opposing sides in the current air combat environment; a game maneuver library corresponding to the opposing sides is constructed by combining the normal overload and roll angular velocity of the fighter model under each maneuver, and the corresponding evaluation function design operation is triggered to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function; based on the tactical maneuver decision optimal control model, the model predictive control strategy, the target air combat situation evaluation function and the game maneuver library, a maneuver prediction is performed to determine the control decision corresponding to the fighter model of one's own side in the opposing side; based on the game maneuver library corresponding to the own side, a target control instruction corresponding to the control decision is determined, and the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot are used to perform motion control on the fighter model of the own side to complete the corresponding close-range air combat deduction operation. That is to say, in this application, a six-degree-of-freedom nonlinear aircraft model is first used to initialize the environment and fighter model of close-range air combat, and then the model prediction control strategy is used, and the battlefield situation and the actions of the opposing sides are predicted, evaluated, and optimal control is solved in combination with the designed target air combat situation evaluation function and the constructed game maneuver library to determine the control decision corresponding to the fighter model of one's own side (our side) in the opposing sides. Then, the control decision and the roll angle autopilot and angle of attack autopilot are used to control the motion of one's own fighter model. In this way, the real-time and accuracy of air combat decisions can be effectively improved without human intervention, thereby improving combat effectiveness and autonomous decision-making level. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] Figure 1 A flow chart of a close-range air combat simulation method based on maneuver prediction provided by this application;

[0038] Figure 2 A flow chart of a specific close-range air combat simulation method based on maneuver prediction provided in this application;

[0039] Figure 3 A schematic diagram of the structure of a close-range air combat simulation device based on maneuver prediction provided in this application;

[0040] Figure 4 A structural diagram of an electronic device provided for this application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0042] However, although the performance of UCAV has been greatly improved so far, most of the tasks in the current decision-making process cannot be separated from human intervention, and the controller needs to control the UCAV on the ground through the base station. This control method not only has time delays, but is also susceptible to electromagnetic interference, which will have an adverse effect on the real-time and accuracy of UCAV motion control, and thus easily lead to deduction failure. To this end, the present application provides a close-range air combat deduction scheme based on maneuver prediction, which can effectively improve the real-time and accuracy of air combat decision-making without human intervention, thereby improving combat effectiveness and autonomous decision-making level.

[0043] See also Figure 1 As shown, an embodiment of the present invention discloses a close-range air combat simulation method based on maneuver prediction, comprising:

[0044] Step S11, by using a six-degree-of-freedom nonlinear aircraft model as a fighter model to perform close-range air combat game confrontation environment and fighter initialization configuration, so as to obtain the fighter models of the two opposing sides in the current air combat environment.

[0045] In this embodiment, it is first necessary to initialize the configuration of the environment and fighter jets for the close-range air combat game confrontation, specifically including: building a six-degree-of-freedom air combat motion model and control law structure for the red and blue confrontation parties; initializing the red and blue fighter jet body parameters and airborne weapon parameters; initializing the red and blue fighter jets' initial posture; and initializing the air combat game system simulation parameters.

[0046] Regarding the fighter model, this embodiment uses a six-degree-of-freedom nonlinear aircraft model as the fighter model and constructs the control law structure of the fighter, that is, the fighter is regarded as an ideal rigid body with bilateral symmetry, and its movement is mainly manifested in the changes of speed and three attitude angles. The control of the fighter mainly depends on the engine thrust and aerodynamic control surfaces. In the inertial coordinate system, the six-degree-of-freedom equations of the aircraft can usually be described as the force equations, torque equations, motion equations and navigation equations in the body coordinate system. The state variables of the six-degree-of-freedom equations of the aircraft are usually: , the state variables are airspeed, angle of attack, sideslip angle, roll angular velocity, pitch angular velocity, yaw angular velocity, roll angle, pitch angle, yaw angle, x-axis position, y-axis position, and z-axis position. The nonlinear six-degree-of-freedom equations for the 12 state variables of the aircraft are as follows (Euclidean coordinate system):

[0047] ;

[0048] ;

[0049] In the formula, are the velocity components of the machine system on the three axes x, y, and z; L, M, and N are the total external moments of the machine system, which are rolling moment, pitching moment, and yaw moment, respectively; It is the reciprocal of the aircraft’s airspeed; It is the inverse of the aircraft’s angle of attack; It is the inverse of the aircraft's sideslip angle; It is the inverse of the aircraft's roll angular velocity; It is the inverse of the aircraft's pitch angular velocity; is the inverse of the aircraft's yaw rate; It is the inverse of the aircraft's roll angle; It is the inverse of the aircraft pitch angle; is the inverse of the aircraft's yaw angle; is the inverse of the x-axis position; is the inverse of the y-axis position; is the inverse of the z-axis position; , , They are the derivatives of the x, y, and z axes velocities of the machine system respectively; the expressions of c1-c9 are shown below respectively.

[0050] ;

[0051] In the formula, represents the moment of inertia about the x-axis; represents the moment of inertia about the y-axis; represents the moment of inertia about the z-axis; and Represents the product of inertia.

[0052] At the same time, this embodiment also initializes the status information and air combat simulation parameters of the red and blue sides. Set the model parameters and airborne weapon parameters of the fighter planes of the opposing sides in the current air combat environment, including: wingspan, fuselage length, maximum flight speed, maximum / minimum altitude limit, onboard radar, cannon, etc. And initialize the initial situation of the fighter planes of the opposing sides, including: position, speed, attitude angle. Then, initialize the air combat game simulation parameters, including: total game time, unit maneuver time, sampling period. The six-degree-of-freedom equation is used to describe the motion state of the fighter plane during maneuver decision-making and simulation. The specific parameters can be as follows: the mass is 3.93kg, the length is 1.47m, and the wing area is 0.2645. , the wingspan is 0.89m and the average aerodynamic chord length is 0.336m.

[0053] In addition, it should be noted that this embodiment designs a multi-channel autopilot for the fighter model to execute instructions. By designing the control laws of the longitudinal channel and the lateral channel, the roll angle autopilot and the angle of attack autopilot of the fighter model are obtained.

[0054] Step S12, constructing a game maneuver library corresponding to the two opposing parties respectively by combining the normal overload and rolling angular velocity of the fighter model under each maneuver, and triggering the corresponding evaluation function design operation to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function.

[0055] In this embodiment, since the fighter model of the air combat is a six-degree-of-freedom nonlinear aircraft model, its control instructions are angle of attack and roll angle instructions. Through the calculation of the tactical planning layer, the candidate maneuvering instructions generated by the decision layer are converted into the control layer instruction form of the six-degree-of-freedom aircraft, and are input into the aircraft's autopilot loop as input information, and the decision model is simplified based on the aircraft center of mass kinematic equations. In order to realize typical tactical maneuvers, the maneuvering instructions such as tangential overload, normal overload, and roll angular velocity generated by the decision layer are used as input and converted into control layer instructions, namely, flight speed, track inclination, and heading angle, to realize the control of the aircraft's motion and trajectory. In actual operation, the idea of ​​realizing a specific maneuvering action is: first determine the required value of the control quantity when completing the maneuvering action, then obtain the actual value of the control quantity according to the constraint conditions, and then substitute the actual control value into the motion equation group to integrate and obtain the motion parameters at different times.

[0056] That is to say, in order to construct the game maneuver library, the corresponding maneuver actions can be achieved through different combinations of normal overload and roll angular velocity. Specifically, the normal overload and roll angular velocity of the fighter models of the opposing sides under each maneuver action are obtained; the normal overload and roll angular velocity are combined, and the maneuver library is constructed using the obtained combination results to obtain the game maneuver library corresponding to the opposing sides. The constructed game maneuver library M can be expressed as:

[0057] ;

[0058] In the formula, represents normal overload, dimension is u; Represents the roll angular velocity vector, with dimension w; and Different values ​​can be combined to form different maneuvers, generating A maneuver.

[0059] Furthermore, according to all the action combinations in the game action library of the two opposing parties, the following game maneuver matrix can be constructed:

[0060] ;

[0061] In the formula, Indicates that the mth maneuver selected by one side in the game maneuver library; Indicates that the enemy has selected the nth maneuver in the game maneuver library. In this way, a game maneuver library with scalability and strong controllability can be constructed.

[0062] Further, regarding the design of the air combat situation assessment function. In this embodiment, considering that the air combat situation is a comprehensive expression of the situation of the two opposing sides, the four components of the air combat situation assessment function are defined, and the specific definitions are as follows: the pitch angle situation function and the yaw angle situation function, the distance situation assessment function and the height situation assessment function, wherein the pitch angle situation function and the yaw angle situation function both belong to the angle situation function. Specifically, the definition of the pitch angle situation function can be shown as follows:

[0063] ;

[0064] In the formula, It represents the pitch angle of the velocity vector relative to the sight vector; Indicates pitch angle situation information.

[0065] The definition of the yaw angle attitude function can be shown as follows:

[0066] ;

[0067] In the formula, It represents the yaw angle of the velocity vector relative to the sight vector; is the yaw angle situation information.

[0068] The definition of distance situation function can be shown as follows:

[0069] ;

[0070] In the formula, for the missile range; is the standard deviation of the attack distance; R is the distance between the two fighter models in the air combat; It is the distance situation information.

[0071] The definition of the height situation function can be shown as follows:

[0072] ;

[0073] In the formula, is the optimal attack height difference of the fighter model to the target; The real-time height difference between the fighter model and the target; is the standard deviation of the optimal attack height; It is the height situation information under real-time height difference.

[0074] In summary, the definition of the air combat situation assessment function can be shown as follows:

[0075] ;

[0076] In the formula, is the weight of each situation in the assessment; For combat aircraft (that is, the aircraft model of the opposing side, also Figure 2 The pitch angle of the own UCAV model in the game; is the yaw angle of the combat aircraft; To attack the target aircraft (that is, the enemy's fighter model in the confrontation, also Figure 2 Target UCAV model in) pitch angle; The yaw angle of the target aircraft; is the height situation information between the two fighter models. In this way, the judgment of whether the air combat is successful can be constructed as:

[0077] ;

[0078] in, is the optimal missile launch distance, , They are the air combat situation assessment function of one's own fighter model and the air combat situation assessment function of the enemy's fighter model. That is to say, the missile launch conditions must be met first, that is, the first three conditions in the above formula; then the air combat situation assessment function of one's own fighter model must be greater than the air combat situation assessment function of the enemy's fighter model in order to win.

[0079] Step S13, performing maneuver prediction based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library to determine the control decision corresponding to the fighter model of one of the two opposing parties.

[0080] In this embodiment, combined with Figure 2 It can be seen that for each step of the state of the two opposing parties, corresponding to the game action library, the situation evaluation function of each maneuver of both parties is calculated respectively, that is, the game score matrix is ​​formed; according to the above situation evaluation function, the score of each action combination adopted by both parties can be calculated respectively, and the game score matrix is ​​obtained It can be as follows:

[0081] .

[0082] In the formula, The evaluation function score when the mth maneuver action in the game maneuver library is selected by the own side and the nth maneuver action in the game maneuver library is selected by the enemy side. That is to say, when performing maneuver prediction, this embodiment uses the target air combat situation evaluation function to perform pitch angle situation evaluation, yaw angle situation evaluation, distance situation evaluation and altitude situation evaluation on each action combination in the game maneuver matrix, so as to determine the game score matrix corresponding to the game maneuver matrix according to the obtained evaluation results; through the tactical maneuver decision optimal control model (i.e. Figure 2 The prediction model in the model prediction control strategy, the game score matrix and the state vector information corresponding to the two opposing sides are used to predict the battlefield situation to determine the control decision corresponding to the fighter model of one's own side in the opposing two sides.

[0083] It is important to understand that the state vector information, that is, the state of the own fighter model and the enemy fighter model in the case of air combat maneuver confrontation, can be described as follows. The state vectors of the two fighter models can be expressed as ,in , B and C represent the enemy and own aircraft models respectively; x and y represent the horizontal coordinates respectively; h represents the height; are pitch angle and heading angle respectively; v represents speed; k represents the kth moment.

[0084] The motion of the fighter model is described by the following differential equation:

[0085] ;

[0086] In the formula, is the time information; u is the control variable. Constraints, state variables are subject to Constraints, these constraints are related to the capability parameters of the fighter model. The state vector of the dynamic system can be expressed as relative situation variables To describe, as follows:

[0087] ;

[0088] In the formula, is the lead angle; is the target entry angle; is the distance between the fighter model and the target; is the height difference; is the velocity angle.

[0089] The optimal control model for tactical maneuver decision-making can be shown as follows:

[0090] ;

[0091] In the formula, for performance measurement; for system dynamics; for The state constraints, and are the initial time and state vector information respectively, for state and input constraints; is the terminal constraint, and They are the ending time and state vector information respectively; is the control matrix. The performance metric is determined by the target air combat situation evaluation function, and the optimization goal of the optimal control is to maximize the air combat situation S.

[0092] It is further understood that regarding the model predictive control strategy. In this embodiment, in the model predictive control, the control is optimized within the prediction interval at each decision moment. The system state is updated by applying the optimal control at the current state. By repeating the calculation at each decision point, a suboptimal solution can be obtained. In this embodiment, the control decision of the fighter model is made at discrete moments. where k is the kth moment and T is the time interval between two consecutive decision moments. and At this moment, the optimal open-loop control of the own fighter model In the interval The following minimize / maximize performance metrics:

[0093] ;

[0094] In the above equation, the integral term It refers to the cumulative value of performance metric J. At the time interval T, V is a cost-to-go function that approximates the state To the final state .

[0095] Step S14, determining the target control instruction corresponding to the control decision based on the game maneuver library corresponding to the own side, and using the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot to perform motion control on the fighter model of the own side to complete the corresponding close-range air combat simulation operation.

[0096] In this embodiment, after the control decision is determined, the normal overload control instruction and the roll angular velocity control instruction corresponding to the control decision are generated based on the game maneuver library corresponding to the own side. Then, the throttle lever position of the own fighter model is kept unchanged, and the normal overload control instruction and the roll angular velocity control instruction are respectively input into the roll angle autopilot and the angle of attack autopilot in the own fighter model to complete the corresponding fighter motion control operation. By looping the above steps, close-range air combat deduction based on maneuver prediction can be realized.

[0097] In summary, the beneficial effects of this embodiment are: 1) the six-degree-of-freedom nonlinear aircraft model is used as the control object, which has more practical application value; 2) the model-based predictive control algorithm can predict future outputs based on historical information and control inputs, effectively improving the predictability of air combat decisions; 3) the rolling optimization characteristics of model prediction can be used to solve the optimal control quantity online, effectively improving the real-time performance of air combat decisions.

[0098] It can be seen that in the embodiment of the present application, a six-degree-of-freedom nonlinear aircraft model is used as a fighter model to perform an environment and fighter initialization configuration for close-range air combat game confrontation, so as to obtain the fighter models of the two opposing sides in the current air combat environment; a game maneuver library corresponding to the two opposing sides is constructed by combining the normal overload and roll angular velocity of the fighter model under each maneuver, and the corresponding evaluation function design operation is triggered to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function; based on the tactical maneuver decision optimal control model, the model predictive control strategy, the target air combat situation evaluation function and the game maneuver library, a maneuver prediction is performed to determine the control decision corresponding to the fighter model of one's own side in the opposing two sides; based on the game maneuver library corresponding to the one's own side, a target control instruction corresponding to the control decision is determined, and the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot are used to perform motion control on the fighter model of the one's own side to complete the corresponding close-range air combat deduction operation. That is to say, in this application, a six-degree-of-freedom nonlinear aircraft model is first used to initialize the environment and fighter model of close-range air combat, and then the model prediction control strategy is used, and the battlefield situation and the actions of the opposing sides are predicted, evaluated, and optimal control is solved in combination with the designed target air combat situation evaluation function and the constructed game maneuver library to determine the control decision corresponding to the fighter model of one's own side in the opposing sides. Then the control decision and the roll angle autopilot and the angle of attack autopilot are used to control the motion of one's own fighter model. In this way, the real-time and accuracy of air combat decisions can be effectively improved without human intervention, thereby improving combat effectiveness and the level of autonomous decision-making.

[0099] See also Figure 3 As shown, the embodiment of the present application also discloses a close-range air combat simulation device based on maneuver prediction, including:

[0100] Initialization module 11 is used to initialize the configuration of the environment and fighters for close-range air combat game confrontation by using a six-degree-of-freedom nonlinear aircraft model as a fighter model, so as to obtain the fighter models of the two opposing sides in the current air combat environment;

[0101] The function design module 12 is used to construct a game maneuver library corresponding to the two opposing parties by combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, and trigger the corresponding evaluation function design operation to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function;

[0102] A maneuver prediction module 13 is used to perform maneuver prediction based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library to determine the control decision corresponding to the fighter model of the own side of the confrontation;

[0103] The motion control module 14 is used to determine the target control instruction corresponding to the control decision based on the game maneuver library corresponding to the own side, and use the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot to perform motion control on the fighter model of the own side to complete the corresponding close-range air combat simulation operation.

[0104] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0105] It can be seen that in this application, a six-degree-of-freedom nonlinear aircraft model is first used to initialize the environment and fighter model of close-range air combat, and then the model prediction control strategy is used, and the battlefield situation and the actions of the opposing sides are predicted, evaluated, and optimal control is solved in combination with the designed target air combat situation evaluation function and the constructed game maneuver library to determine the control decision corresponding to the fighter model of one's own side in the opposing sides. Then the control decision and the roll angle autopilot and the angle of attack autopilot are used to control the motion of one's own fighter model. In this way, the real-time and accuracy of air combat decisions can be effectively improved without human intervention, thereby improving combat effectiveness and autonomous decision-making level.

[0106] In some specific embodiments, the initialization module 11 can be specifically used to use a six-degree-of-freedom nonlinear aircraft model to build a fighter model and a control law structure, and to initialize the fighter model body parameters, airborne weapon parameters and initial fighter situation of the opposing sides in the current air combat environment to obtain the fighter models corresponding to the opposing sides respectively; and to initialize the game simulation parameters of the close-range air combat game confrontation to obtain the current air combat environment.

[0107] In some specific embodiments, the close-range air combat simulation device based on maneuver prediction can also be used to obtain the roll angle autopilot and angle of attack autopilot of the fighter model through the control law design of the longitudinal channel and the lateral channel.

[0108] In some specific embodiments, the function design module 12 can be specifically used to obtain the normal overload and roll angular velocity of the fighter models of the opposing parties under various maneuvers; combine the normal overload and the roll angular velocity, and use the obtained combination result to construct a maneuver library to obtain a game maneuver library corresponding to the opposing parties.

[0109] In some specific embodiments, the maneuver prediction module 13 can be specifically used to combine actions based on the game maneuver libraries corresponding to the two opposing parties to construct a corresponding game maneuver matrix; use the target air combat situation assessment function to perform pitch angle situation assessment, yaw angle situation assessment, distance situation assessment and altitude situation assessment on each action combination in the game maneuver matrix, so as to determine the game score matrix corresponding to the game maneuver matrix according to the obtained assessment results; and predict the battlefield situation through the tactical maneuver decision optimal control model, the model prediction control strategy, the game score matrix and the state vector information corresponding to the two opposing parties to determine the control decision corresponding to the fighter model of one's own side among the two opposing parties.

[0110] In some specific embodiments, the motion control module 14 can be specifically used to generate a normal overload control instruction and a roll angular velocity control instruction corresponding to the control decision based on the game maneuver library corresponding to the own side.

[0111] In some specific embodiments, the motion control module 14 can be specifically used to maintain the throttle lever position of the own fighter model, and input the normal overload control instruction and the roll angular velocity control instruction into the roll angle autopilot and angle of attack autopilot in the own fighter model, respectively, to complete the corresponding fighter motion control operation.

[0112] Furthermore, the present application also discloses an electronic device. Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0113] Figure 4 The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the close-range air combat simulation method based on maneuver prediction disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0114] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0115] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0116] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the close-range air combat simulation method based on maneuver prediction performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0117] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the close-range air combat simulation method based on maneuver prediction disclosed above is implemented. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, and no further description will be given here.

[0118] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0119] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0120] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0121] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0122] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A close-range air combat simulation method based on maneuver prediction, characterized in that: include: By using a six-degree-of-freedom nonlinear aircraft model as a fighter model to initialize the configuration of the environment and fighters for close-range air combat game confrontation, the fighter models of the two opposing sides in the current air combat environment can be obtained; By combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, a game maneuver library corresponding to the two opposing parties is constructed, and a corresponding evaluation function design operation is triggered to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function; Based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library, maneuver prediction is performed to determine the control decision corresponding to the fighter model of the own side of the confrontation; Determine a target control instruction corresponding to the control decision based on the game maneuver library corresponding to the own side, and use the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot to perform motion control on the fighter model of the own side to complete the corresponding close-range air combat simulation operation; The pitch angle situation assessment function is defined as follows: ； In the formula, It represents the pitch angle of the velocity vector relative to the sight vector; Indicates pitch angle situation information; The yaw angle situation assessment function is defined as follows: ； In the formula, It represents the yaw angle of the velocity vector relative to the sight vector; is the yaw angle situation information; The distance situation assessment function is defined as follows: ； In the formula, for the missile range; is the standard deviation of the attack distance; R is the distance between the fighter models of the opposing sides in the current air combat environment; is the distance situation information; The definition of the altitude situation assessment function is as follows: ； In the formula, is the optimal attack height difference of the fighter model to the target; is the real-time height difference between the fighter model and the target; is the standard deviation of the optimal attack height; It is the height situation information under real-time height difference.

2. The close-range air combat simulation method based on maneuver prediction according to claim 1 is characterized in that: The environment and fighter initialization configuration for close-range air combat game confrontation by using a six-degree-of-freedom nonlinear aircraft model as a fighter model includes: A six-degree-of-freedom nonlinear aircraft model is used to build a fighter model and a control law structure, and the fighter model body parameters, airborne weapon parameters and initial fighter posture of the two opposing sides in the current air combat environment are initialized and configured to obtain fighter models corresponding to the two opposing sides respectively; Initialize and configure the game simulation parameters of close-range air combat game confrontation to obtain the current air combat environment.

3. The close air combat simulation method based on maneuver prediction according to claim 1 is characterized in that: Before constructing the game maneuver libraries corresponding to the two opposing parties respectively by combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, the method further includes: By designing the control laws of the longitudinal channel and the lateral channel, the roll angle autopilot and the angle of attack autopilot of the fighter model are obtained.

4. The close air combat simulation method based on maneuver prediction according to claim 1 is characterized in that: The game maneuver library corresponding to the two opposing parties is constructed by combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, including: Obtaining the normal overload and rolling angular velocity of the fighter models of the opposing two parties under various maneuvers; The normal overload and the roll angular velocity are combined, and a maneuver library is constructed using the obtained combination result to obtain a game maneuver library corresponding to the two opposing parties respectively.

5. The close air combat simulation method based on maneuver prediction according to any one of claims 1 to 4, characterized in that: The maneuver prediction based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library includes: Combining actions based on the game maneuver libraries corresponding to the two opposing parties respectively to construct a corresponding game maneuver matrix; Using the target air combat situation assessment function, each action combination in the game maneuver matrix is ​​respectively evaluated for pitch angle situation, yaw angle situation, distance situation and altitude situation, so as to determine a game score matrix corresponding to the game maneuver matrix according to the obtained evaluation results; Battlefield situation prediction is performed through the tactical maneuver decision-making optimal control model, the model prediction control strategy, the game score matrix and the state vector information corresponding to the two opposing parties to determine the control decision corresponding to the fighter model of one of the two opposing parties.

6. The close-range air combat simulation method based on maneuver prediction according to claim 1 is characterized in that: The determining the target control instruction corresponding to the control decision based on the game maneuver library corresponding to the own party includes: Based on the game maneuver library corresponding to the own side, a normal overload control instruction and a roll angular velocity control instruction corresponding to the control decision are generated.

7. The close air combat simulation method based on maneuver prediction according to claim 6 is characterized in that: The using the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot to control the motion of the fighter model of the own side includes: Maintain the throttle lever position of the own fighter model, and input the normal overload control instruction and the roll angular velocity control instruction into the roll angle autopilot and angle of attack autopilot in the own fighter model respectively to complete the corresponding fighter motion control operation.

8. A close-range air combat simulation device based on maneuver prediction, characterized in that: Used to implement the close-range air combat simulation method based on maneuver prediction as described in any one of claims 1 to 7, the device comprises: An initialization module is used to initialize the configuration of the environment and fighters for close-range air combat game confrontation by using a six-degree-of-freedom nonlinear aircraft model as a fighter model, so as to obtain the fighter models of the two opposing sides in the current air combat environment; A function design module is used to construct a game maneuver library corresponding to the two opposing parties by combining the normal overload and the rolling angular velocity of the fighter model under each maneuver, and trigger a corresponding evaluation function design operation to obtain a target air combat situation evaluation function; the target air combat situation evaluation function includes a pitch angle situation evaluation function, a yaw angle situation evaluation function, a distance situation evaluation function and an altitude situation evaluation function; A maneuver prediction module is used to perform maneuver prediction based on the tactical maneuver decision optimal control model, the model prediction control strategy, the target air combat situation assessment function and the game maneuver library to determine the control decision corresponding to the fighter model of the own side of the confrontation; The motion control module is used to determine the target control instruction corresponding to the control decision based on the game maneuver library corresponding to the own side, and use the target control instruction and the corresponding roll angle autopilot and angle of attack autopilot to perform motion control on the fighter model of the own side to complete the corresponding close-range air combat simulation operation.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the close air combat simulation method based on maneuver prediction as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the close-range air combat simulation method based on maneuver prediction as described in any one of claims 1 to 7.

Images