CN113625739A - Expert system optimization method based on heuristic maneuver selection algorithm - Google Patents

Expert system optimization method based on heuristic maneuver selection algorithm Download PDF

Info

Publication number
CN113625739A
CN113625739A CN202110982504.8A CN202110982504A CN113625739A CN 113625739 A CN113625739 A CN 113625739A CN 202110982504 A CN202110982504 A CN 202110982504A CN 113625739 A CN113625739 A CN 113625739A
Authority
CN
China
Prior art keywords
instruction
overload
roll angle
delta
maneuver
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110982504.8A
Other languages
Chinese (zh)
Inventor
张杨
李自强
张秀林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenyang Aircraft Design and Research Institute Aviation Industry of China AVIC
Original Assignee
Shenyang Aircraft Design and Research Institute Aviation Industry of China AVIC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenyang Aircraft Design and Research Institute Aviation Industry of China AVIC filed Critical Shenyang Aircraft Design and Research Institute Aviation Industry of China AVIC
Priority to CN202110982504.8A priority Critical patent/CN113625739A/en
Publication of CN113625739A publication Critical patent/CN113625739A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
    • G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The application provides an expert system optimization method based on a heuristic maneuver selection algorithm, which comprises the following steps: constructing a tentative maneuver instruction set for deducing the air combat situation of the unmanned aerial vehicle after unit time under multiple scenes, wherein the tentative maneuver instruction set comprises maneuver action instructions which can be executed by each scene under multiple scenes; deducing the relationship between the positions and the postures of the enemy and the my after executing all maneuver action instructions in the heuristic maneuver instruction set; and constructing a comprehensive evaluation function based on the relationship between the positions, postures and energy situations of the enemy and the my, evaluating a deduction result through the comprehensive evaluation function, and obtaining an optimal maneuver instruction according to the deduction result so as to control the unmanned aerial vehicle to execute the optimal maneuver. The expert system optimization method based on the heuristic maneuver selection algorithm can make up the situation of decision failure caused by mismatching of the air combat situation and the rules in the autonomous decision making of the traditional expert system, and can improve the air combat capability of the unmanned aerial vehicle.

Description

Expert system optimization method based on heuristic maneuver selection algorithm
Technical Field
The application belongs to the technical field of flight control, and particularly relates to an expert system optimization method based on a heuristic maneuver selection algorithm.
Background
For unmanned aerial vehicle autonomous air combat, a tactical maneuver library needs to be established, an expert system method is generally used for autonomous decision-making of air combat maneuver, and the method has the advantages that the air combat experience and tactics of short-distance air combat are utilized, and the experience and tactics are good choices in the aspect of physical meaning in the face of relevant geometric combat situations. The decision method is simple and effective and is convenient to expand. However, the method has obvious defects, and the problem that the unmanned aerial vehicle cannot timely perform reasonable maneuvering action due to the fact that the current air war situation can not be matched with all rule front parts frequently occurs, so that the problem is at a disadvantage. There is therefore a need for a method to address and improve upon the deficiencies of rule-based decision methods.
Disclosure of Invention
It is an object of the present application to provide a heuristic maneuver selection algorithm based expert system optimization method to solve or mitigate at least one of the problems of the background art.
The technical scheme of the application is as follows: an expert system optimization method based on a heuristic maneuver selection algorithm, comprising:
constructing a tentative maneuver instruction set for deducing the air combat situation of the unmanned aerial vehicle after unit time under multiple scenes, wherein the tentative maneuver instruction set comprises maneuver action instructions which can be executed by each scene under multiple scenes;
deducing the relationship between the positions and the postures of the enemy and the my after executing all maneuver action instructions in the heuristic maneuver instruction set;
and constructing a comprehensive evaluation function based on the relationship between the positions, postures and energy situations of the enemy and the my, evaluating a deduction result through the comprehensive evaluation function, and obtaining an optimal maneuver instruction according to the deduction result so as to control the unmanned aerial vehicle to execute the optimal maneuver.
Further, the heuristic maneuver instruction set includes a safe altitude maneuver instruction set, a safe speed maneuver instruction set, a tracking maneuver instruction set, and a disengagement maneuver instruction set.
Further, the safety height maneuver instruction set includes:
instruction 1, the overload instruction is
Figure BDA0003229647130000021
The roll angle command is 0;
instruction 2, the overload instruction is
Figure BDA0003229647130000022
The roll angle command is 0;
in the formula, DELTA nzIn order to control the command for normal phase overload,
Figure BDA0003229647130000023
the average positive overload change rate per unit time obtained in the climbing overload test is carried out for the airplane,
Figure BDA0003229647130000024
and carrying out instantaneous overload test on the airplane to obtain the average positive overload change rate per unit time.
Further, the safe speed maneuver instruction set includes:
instruction 1, overload instruction 1 +. DELTA.nzThe roll angle command is 0;
instruction 2, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is 0;
instruction 3, the overload instruction is 1, and the roll angle instruction is 0;
instruction 4, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is phi;
instruction 5, overload instruction 1 +. DELTA.nz-0.8△nc,2The roll angle command is phi;
instruction 6, overload instruction 1 +. DELTA.nzThe roll angle command is phi +10 degrees;
instruction 7, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle instruction is phi-10 degrees;
instruction 8, overload instruction 1 +. DELTA.nz-0.8△nc,1And the roll angle command is gamma'c；
Instruction 9, overload instruction is 1, and roll angle instruction is γ'c；
Instruction 10, overload instruction 1 +. DELTA.nz-0.8△nc,1Roll angle commandIs gammac+90°；
Instruction 11, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is gammac；
Instruction 12, overload instruction 1 +. DELTA.nz-0.3, roll angle command is phi;
in the formula, DELTA nzFor normal phase overload control commands, gammacFor roll angle control command, Δ nc,1Average positive overload rate of change per unit time, Δ n, obtained in a steady disk overload test for an aircraftc,2Average positive overload rate of change, Δ n, per unit time obtained in transient overload testing for aircraftc,1And Δ nc,2Are obtained by interpolation according to the current airspeed and altitude of the airplane, and phi is the rolling angle of the airplane at the current moment.
Further, the disengagement maneuver instruction set includes:
instruction 1, overload instruction 1 +. DELTA.nz+0.8△nc,1The roll angle command is 90 degrees;
instruction 2, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is 90 degrees;
instruction 3, overload instruction 1 +. DELTA.nz+0.8△nc,1The roll angle command is-90 degrees;
instruction 4, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is-90 degrees;
instruction 5, overload instruction 1 +. DELTA.nz+0.8△nc,1The roll angle command is gammac+180°；
Instruction 6, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is gammac+180°；
Instruction 7, overload instruction 1 +. DELTA.nz+0.8△nc,1The roll angle command is gammac-180°；
Instruction 8, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is gammac-180°；
In the formula, DELTA nzFor normal phase overload control commands, gammacIs a roll angleControl command, Δ nc,1Average positive overload rate of change per unit time, Δ n, obtained in a steady disk overload test for an aircraftc,2Average positive overload rate of change, Δ n, per unit time obtained in transient overload testing for aircraftc,1And Δ nc,2Are obtained by interpolation according to the current airspeed and altitude of the airplane, and phi is the rolling angle of the airplane at the current moment.
Further, the set of tracking maneuver instructions includes:
instruction 1, overload instruction 1 +. DELTA.nzThe roll angle command is phi;
instruction 2, overload instruction 1 +. DELTA.nzThe roll angle command is 0;
instruction 3, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi;
instruction 4, overload instruction 1 +. DELTA.nz+△nc,2The roll angle command is phi;
instruction 5, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi +10 degrees;
instruction 6, overload instruction 1 +. DELTA.nz+△nc,1The roll angle instruction is phi-10 degrees;
instruction 7, overload instruction Δ nc,1The roll angle command is gammac；
Instruction 8, overload instruction Δ nc,2The roll angle command is gammac；
Instruction 9, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is gammac；
Instruction 10, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is gammac+10°；
Instruction 11, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is gammac-10°；
Instruction 12, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is 90 degrees;
instruction 13, overload instruction 1 +. DELTA.nz+△nc,1Angle of rollThe command is-90 degrees;
instruction 14, overload instruction 1 +. DELTA.nzThe roll angle command is phi +10 degrees;
instruction 15, overload instruction 1 +. DELTA.nzThe roll angle instruction is phi-10 degrees;
instruction 16, overload instruction 1 +. DELTA.nz+0.3, the roll angle command is phi;
instruction 17, overload instruction 1 +. DELTA.nz-0.3, roll angle command is phi;
instruction 18, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi +30 degrees;
instruction 19, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi-30 degrees;
instruction 20, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is gammac+90°；
Instruction 21, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is gammac-90°；
In the formula, DELTA nzFor normal phase overload control commands, gammacFor roll angle control command, Δ nc,1Average positive overload rate of change per unit time, Δ n, obtained in a steady disk overload test for an aircraftc,2Average positive overload rate of change, Δ n, per unit time obtained in transient overload testing for aircraftc,1And Δ nc,2Are obtained by interpolation according to the current airspeed and altitude of the airplane, and phi is the rolling angle of the airplane at the current moment.
Further, the process of deducing the relationship between the position and the speed situation of the friend or foe after executing all the maneuver instructions in the heuristic maneuver instruction set comprises the following steps:
constructing a three-degree-of-freedom dynamic model and a kinematic model of the mass center of the airplane under a track coordinate system, wherein the dynamic model is
Figure BDA0003229647130000051
The kinematic model is
Figure BDA0003229647130000052
In the formula (I), the compound is shown in the specification,
Figure BDA0003229647130000053
is the forward velocity component of the aircraft,
Figure BDA0003229647130000054
is the component of the lateral velocity of the aircraft,
Figure BDA0003229647130000055
is the component of the aircraft lifting speed, V is the aircraft speed, theta is the aircraft pitch angle, psi is the aircraft yaw angle, gammasThe aircraft roll angle is defined, and n is the overload of the aircraft in the corresponding axial direction;
the position vector and the velocity vector of the aircraft at the next decision moment are obtained by taking the position and the velocity vector at the current decision moment as initial values and integrating the three-degree-of-freedom motion equation of the mass center of the aircraft, namely the position vector and the velocity vector of the aircraft at the next decision moment
Figure BDA0003229647130000056
And
Figure BDA0003229647130000057
further, a comprehensive evaluation function based on the relationship between the positions, postures and energy situations of the enemy and the my is constructed as follows: s ═ wgSrange+weSe；
In the formula, wg、weAs a weight, SrangeFor characterizing the distance angle dominance evaluation function of the position and posture of both friend and foe, SeThe energy advantage function of the two parties of the enemy and the my;
further, the distance and angle dominance evaluation function is as follows:
Figure BDA0003229647130000058
in the formula, lambda is a two-machine attitude azimuth angle, and epsilon is a deviation angle;
the energy merit function is:
Figure BDA0003229647130000061
in the formula (I), the compound is shown in the specification,
Figure BDA0003229647130000062
the energy height of the two machines is high,
Figure BDA0003229647130000063
Figure BDA0003229647130000064
is enemy altitude, VrThe enemy plane speed is obtained, and g is gravity acceleration;
Figure BDA0003229647130000065
Figure BDA0003229647130000066
for height of I machine, VbIs the speed of the machine.
Further, the weight value wgAnd weThe following relationship is satisfied:
Figure BDA0003229647130000067
wg＝1-we；
in the formula, coefficient
Figure BDA0003229647130000068
The expert system optimization method based on the heuristic maneuver selection algorithm can make up the situation of decision failure caused by mismatching of the air combat situation and the rules in the autonomous decision making of the traditional expert system, and can improve the air combat capability of the unmanned aerial vehicle.
Drawings
In order to more clearly illustrate the technical solutions provided by the present application, the following briefly introduces the accompanying drawings. It is to be expressly understood that the drawings described below are only illustrative of some embodiments of the invention.
FIG. 1 is a schematic diagram of an expert system optimization method of the present application.
Detailed Description
In order to make the implementation objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the drawings in the embodiments of the present application.
In order to make up for the situation of decision failure caused by mismatching of the air combat situation and the rules in the autonomous decision making of the traditional expert system, the invention provides an expert system optimization method and device based on a heuristic maneuver selection algorithm by optimizing the traditional expert system.
As shown in fig. 1, the expert system optimization method based on the heuristic maneuver selection algorithm provided by the present application includes the following processes:
firstly, a tentative maneuver instruction set under a multi-scenario of air combat decision is constructed, wherein the tentative maneuver instruction set comprises all possible values which can be reached by the control instruction of the airplane from the current flight state within the set tentative maneuver execution time.
The trial maneuver set includes possible values that the control command of the aircraft can reach from the current flight state within the set trial maneuver execution time. These values are typically determined with reference to aircraft maneuverability and agility data, and the maneuvering instructions typically include available overload, overload rate of change, negative overload rate of change, etc. for the aircraft in a given flight condition. And in the execution time of the trial maneuver, the control instruction of the airplane is a fixed value.
In the application, the heuristic maneuver instruction set is divided into four types, namely a safe height maneuver instruction set, a safe speed maneuver instruction set, a tracking maneuver instruction set and a disengagement maneuver instruction set, and the heuristic maneuver selection is determined in which type of heuristic maneuver set the current decision moment is in according to the state of the machine and the relative situation of two machines of the friend and foe.
Wherein the safe altitude maneuver instruction set, the safe speed maneuver instruction set, the tracking maneuver instruction set, and the disengagement maneuver instruction set are as shown in tables 1-4:
table 1 safe altitude maneuver set including two heuristic maneuvers
Figure BDA0003229647130000071
The table contents above indicate the meaning: under the appropriate air war situation, unmanned aerial vehicle can execute any operating instruction of above-mentioned 2 instructions and reach safe height.
Table 2 includes a safe set of 12 heuristic maneuvers
Figure BDA0003229647130000081
The table contents above indicate the meaning: under the appropriate air war situation, unmanned aerial vehicle can execute any one of above-mentioned 12 instructions and reach safe speed.
Table 3 includes a set of 8 heuristic maneuvers of disengaging maneuvers
Figure BDA0003229647130000082
The table contents above indicate the meaning: under the appropriate air war situation, unmanned aerial vehicle can execute arbitrary operating instruction in above-mentioned 8 instructions and reach the disengagement state.
Table 4 tracking maneuver set includes 21 heuristic maneuvers
Figure BDA0003229647130000083
Figure BDA0003229647130000091
The table contents above indicate the meaning: under the appropriate air war situation, the unmanned aerial vehicle can execute any one of the 12 instructions to reach the tracking state.
Interpretation of meanings:
1、△nc,1average positive overload rate of change per unit time, Δ n, obtained in a steady disk overload test for an aircraftc,2Average positive overload rate of change, Δ n, per unit time obtained in transient overload testing for aircraftc,1And Δ nc,2The method is obtained by interpolation according to the current airspeed and altitude of the airplane;
2. by means of the written airplane agility evaluation software, the delta n of the airplane at a series of altitude and speed state points can be obtainedc,1And Δ nc,2；
3. Phi is the rolling angle of the airplane at the current moment;
4. all overload commands are clipped by steady disk overload or instantaneous disk overload in the current state.
And then, predicting the possible geometrical and speed situation relation of the enemy and the my after the decision-making moment in advance by using a fitting extrapolation algorithm.
On the basis of the construction completion of the tentative maneuver instruction set, the position and attitude information of the enemy plane after the unit tentative maneuver execution time and the position and attitude information of the enemy plane after the unit tentative maneuver execution time are determined, so that optimization decision is made.
In a preferred embodiment of the present application, a method for predicting the position and attitude of an aircraft after the aircraft gives a current flight state and executes a certain heuristic maneuver is provided, and the specific process comprises the following steps:
1) the three-degree-of-freedom dynamics and kinematics model of the airplane in the track system is as follows:
dynamic model
Figure BDA0003229647130000092
Kinematic model
Figure BDA0003229647130000093
In the formula (I), the compound is shown in the specification,
Figure BDA0003229647130000101
is the forward velocity component of the aircraft,
Figure BDA0003229647130000102
is the component of the lateral velocity of the aircraft,
Figure BDA0003229647130000103
is the component of the aircraft lifting speed, V is the aircraft speed, theta is the aircraft pitch angle, psi is the aircraft yaw angle, gammasIs the aircraft roll angle, and n is the overload of the aircraft in the corresponding axial direction.
2) The position vector and the velocity vector of the machine at the next decision moment are calculated by taking the position and the velocity vector at the current decision moment as initial values and integrating through the above-mentioned centroid motion three-degree-of-freedom motion equation, namely the position vector and the velocity vector of the machine at the next decision moment
Figure BDA0003229647130000104
And
Figure BDA0003229647130000105
and finally, establishing a comprehensive evaluation function based on the geometric relationship (position and attitude) and the energy relationship, evaluating the tentative maneuver result, and further selecting the optimal maneuver.
After the position and speed of the opponent opposite opponent opposite opponent, opponent opposite is opposite to be opposite to each other opponent, opponent between the opposite to each other opponent opposite to each other opponent opposite to each other, opponent opposite to each other opponent opposite to each other opponent opposite to each other, opponent opposite to: s ═ wgSrange+weSe；
Wherein S israngeIn the short-distance air battle, the distance and angle superiority evaluation function can be regarded as:
Figure BDA0003229647130000106
Sefor the energy advantage function:
Figure BDA0003229647130000107
Figure BDA0003229647130000108
the energy height of two machines is as follows:
Figure BDA0003229647130000109
weight wgAnd weDetermined by the following algorithm:
Figure BDA00032296471300001010
in the formula, coefficient
Figure BDA00032296471300001011
By means of the comprehensive evaluation function, dimensionless values of the air combat situation indexes under the condition of two enemy and my machines can be calculated according to the initial positions (distance and angle) and the energy (height and speed) of the two enemy and my machines. After the decision deduction I machine carries out heuristic maneuver, the position between the two machines is changed, and the air combat situation indexes of the two machines are recalculated through the evaluation function. If the situation indexes of the two machines are reduced, the situation proves that the two machines can achieve a more advantageous air combat situation after maneuvering. After complete air combat decision deduction is carried out, the two-aircraft air combat situation index with the minimum value can be regarded as the most advantageous maneuver decision to be executed.
For example, at the beginning of the prediction deduction, coordinates of two enemy machines are respectively [0, 6000], [ 2000-500,6000 ], the heading angle of the enemy machine is 180 degrees, a 2G overload stable disk is made, the initial speeds of the two machines are both 260m/s, the situation of the two machines is evaluated and calculated to be 0.1, after the deduction, the system obtains that after all heuristic maneuvers are carried out, the minimum evaluation function is 0.03, and therefore the decision is made to execute the maneuver.
The expert system optimization method based on the heuristic maneuver selection algorithm can make up the situation of decision failure caused by mismatching of the air combat situation and the rules in the autonomous decision making of the traditional expert system, and can improve the air combat capability of the unmanned aerial vehicle.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. An expert system optimization method based on a heuristic maneuver selection algorithm, comprising:
constructing a tentative maneuver instruction set for deducing the air combat situation of the unmanned aerial vehicle after unit time under multiple scenes, wherein the tentative maneuver instruction set comprises maneuver action instructions which can be executed by each scene under multiple scenes;
deducing the relationship between the positions and the postures of the enemy and the my after executing all maneuver action instructions in the heuristic maneuver instruction set;
and constructing a comprehensive evaluation function based on the relationship between the positions, postures and energy situations of the enemy and the my, evaluating a deduction result through the comprehensive evaluation function, and obtaining an optimal maneuver instruction according to the deduction result so as to control the unmanned aerial vehicle to execute the optimal maneuver.
2. A heuristic maneuver selection algorithm based expert system optimization method of claim 1, wherein the heuristic maneuver instruction set comprises a safe height maneuver instruction set, a safe speed maneuver instruction set, a tracking maneuver instruction set, and a disengagement maneuver instruction set.
3. The expert system optimization method based on a heuristic maneuver selection algorithm of claim 2, wherein the set of safe height maneuver instructions comprises:
instruction 1, the overload instruction is
Figure FDA0003229647120000011
The roll angle command is 0;
instruction 2, the overload instruction is
Figure FDA0003229647120000012
The roll angle command is 0;
in the formula, DELTA nzIn order to control the command for normal phase overload,
Figure FDA0003229647120000013
the average positive overload change rate per unit time obtained in the climbing overload test is carried out for the airplane,
Figure FDA0003229647120000014
and carrying out instantaneous overload test on the airplane to obtain the average positive overload change rate per unit time.
4. The expert system optimization method based on a heuristic maneuver selection algorithm of claim 2, wherein the set of safe speed maneuver instructions comprises:
instruction 1, overload instruction 1 +. DELTA.nzThe roll angle command is 0;
instruction 2, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is 0;
instruction 3, the overload instruction is 1, and the roll angle instruction is 0;
instruction 4, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is phi;
instruction 5, overload instruction 1 +. DELTA.nz-0.8△nc,2The roll angle command is phi;
instruction 6, overload instruction 1 +. DELTA.nzThe roll angle command is phi +10 degrees;
instruction 7, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle instruction is phi-10 degrees;
instruction 8, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command isγc'；
Instruction 9, overload instruction is 1, and roll angle instruction is γ'c；
Instruction 10, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is gammac+90°；
Instruction 11, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is gammac；
Instruction 12, overload instruction 1 +. DELTA.nz-0.3, roll angle command is phi;
in the formula, DELTA nzFor normal phase overload control commands, gammacFor roll angle control command, Δ nc,1Average positive overload rate of change per unit time, Δ n, obtained in a steady disk overload test for an aircraftc,2Average positive overload rate of change, Δ n, per unit time obtained in transient overload testing for aircraftc,1And Δ nc,2Are obtained by interpolation according to the current airspeed and altitude of the airplane, and phi is the rolling angle of the airplane at the current moment.
5. The expert system optimization method based on a heuristic maneuver selection algorithm of claim 2, wherein the set of maneuver escape instructions comprises:
instruction 1, overload instruction 1 +. DELTA.nz+0.8△nc,1The roll angle command is 90 degrees;
instruction 2, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is 90 degrees;
instruction 3, overload instruction 1 +. DELTA.nz+0.8△nc,1The roll angle command is-90 degrees;
instruction 4, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is-90 degrees;
instruction 5, overload instruction 1 +. DELTA.nz+0.8△nc,1The roll angle command is gammac+180°；
Instruction 6, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is gammac+180°；
Instruction 7, overLoad instruction of 1 +. DELTA.nz+0.8△nc,1The roll angle command is gammac-180°；
Instruction 8, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is gammac-180°；
In the formula, DELTA nzFor normal phase overload control commands, gammacFor roll angle control command, Δ nc,1Average positive overload rate of change per unit time, Δ n, obtained in a steady disk overload test for an aircraftc,2Average positive overload rate of change, Δ n, per unit time obtained in transient overload testing for aircraftc,1And Δ nc,2Are obtained by interpolation according to the current airspeed and altitude of the airplane, and phi is the rolling angle of the airplane at the current moment.
6. The expert system optimization method based on a heuristic maneuver selection algorithm of claim 2, wherein the set of trace maneuver instructions comprises:
instruction 1, overload instruction 1 +. DELTA.nzThe roll angle command is phi;
instruction 2, overload instruction 1 +. DELTA.nzThe roll angle command is 0;
instruction 3, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi;
instruction 4, overload instruction 1 +. DELTA.nz+△nc,2The roll angle command is phi;
instruction 5, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi +10 degrees;
instruction 6, overload instruction 1 +. DELTA.nz+△nc,1The roll angle instruction is phi-10 degrees;
instruction 7, overload instruction Δ nc,1The roll angle command is gammac；
Instruction 8, overload instruction Δ nc,2And the roll angle command is gamma'c；
Instruction 9, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is gammac；
Instruction 10, overload command is 1 +. DELTA.nz+△nc,1The roll angle command is gammac+10°；
Instruction 11, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is gammac-10°；
Instruction 12, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is 90 degrees;
instruction 13, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is-90 degrees;
instruction 14, overload instruction 1 +. DELTA.nzThe roll angle command is phi +10 degrees;
instruction 15, overload instruction 1 +. DELTA.nzThe roll angle instruction is phi-10 degrees;
instruction 16, overload instruction 1 +. DELTA.nz+0.3, the roll angle command is phi;
instruction 17, overload instruction 1 +. DELTA.nz-0.3, roll angle command is phi;
instruction 18, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi +30 degrees;
instruction 19, overload instruction 1 +. DELTA.nz+△nc,1The roll angle command is phi-30 degrees;
instruction 20, overload instruction 1 +. DELTA.nz-0.8△nc,1The roll angle command is gammac+90°；
Instruction 21, overload instruction 1 +. DELTA.nz+0.8△nc,2The roll angle command is gammac-90°；
In the formula, DELTA nzFor normal phase overload control commands, gammacFor roll angle control command, Δ nc,1Average positive overload rate of change per unit time, Δ n, obtained in a steady disk overload test for an aircraftc,2Average positive overload rate of change, Δ n, per unit time obtained in transient overload testing for aircraftc,1And Δ nc,2Are obtained by interpolation according to the current airspeed and altitude of the airplane, and phi is the rolling angle of the airplane at the current moment.
7. A heuristic maneuver selection algorithm based expert system optimization method according to any one of claims 3 to 6, wherein the process of deducing the position-to-speed posture of both the friend and foe after execution of all the maneuver instructions in the set of heuristic maneuver instructions comprises:
constructing a three-degree-of-freedom dynamic model and a kinematic model of the mass center of the airplane under a track coordinate system, wherein the dynamic model is
Figure FDA0003229647120000041
The kinematic model is
Figure FDA0003229647120000042
In the formula (I), the compound is shown in the specification,
Figure FDA0003229647120000043
is the forward velocity component of the aircraft,
Figure FDA0003229647120000044
is the component of the lateral velocity of the aircraft,
Figure FDA0003229647120000045
is the component of the aircraft lifting speed, V is the aircraft speed, theta is the aircraft pitch angle, psi is the aircraft yaw angle, gammasThe aircraft roll angle is defined, and n is the overload of the aircraft in the corresponding axial direction;
the position vector and the velocity vector of the aircraft at the next decision moment are obtained by taking the position and the velocity vector at the current decision moment as initial values and integrating the three-degree-of-freedom motion equation of the mass center of the aircraft, namely the position vector and the velocity vector of the aircraft at the next decision moment
Figure FDA0003229647120000051
And
Figure FDA0003229647120000052
8. as claimed in claim7 the expert system optimization method based on the heuristic maneuver selection algorithm is characterized in that a comprehensive evaluation function based on the relationship between the positions, postures and energy situations of the enemy and the my is constructed as follows: s ═ wgSrange+weSe；
In the formula, wg、weAs a weight, SrangeFor characterizing the distance angle dominance evaluation function of the position and posture of both friend and foe, SeIs an energy advantage function of both friend and foe.
9. The expert system optimization method based on heuristic maneuver selection algorithm of claim 8, wherein the distance angle merit function is:
Figure FDA0003229647120000053
in the formula, lambda is a two-machine attitude azimuth angle, and epsilon is a deviation angle;
the energy merit function is:
Figure FDA0003229647120000054
in the formula (I), the compound is shown in the specification,
Figure FDA0003229647120000055
the energy height of the two machines is high,
Figure FDA0003229647120000056
Figure FDA0003229647120000057
is enemy altitude, VrThe enemy plane speed is obtained, and g is gravity acceleration;
Figure FDA0003229647120000061
Figure FDA0003229647120000062
for height of I machine, VbIs the speed of the machine.
10. The expert system optimization method based on heuristic maneuver selection algorithm of claim 8, wherein the weight wgAnd weThe following relationship is satisfied:
Figure FDA0003229647120000063
wg＝1-we；
in the formula, coefficient
Figure FDA0003229647120000064
CN202110982504.8A 2021-08-25 2021-08-25 Expert system optimization method based on heuristic maneuver selection algorithm Pending CN113625739A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110982504.8A CN113625739A (en) 2021-08-25 2021-08-25 Expert system optimization method based on heuristic maneuver selection algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110982504.8A CN113625739A (en) 2021-08-25 2021-08-25 Expert system optimization method based on heuristic maneuver selection algorithm

Publications (1)

Publication Number Publication Date
CN113625739A true CN113625739A (en) 2021-11-09

Family

ID=78387694

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110982504.8A Pending CN113625739A (en) 2021-08-25 2021-08-25 Expert system optimization method based on heuristic maneuver selection algorithm

Country Status (1)

Country Link
CN (1) CN113625739A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116225049A (en) * 2022-12-21 2023-06-06 中国航空工业集团公司沈阳飞机设计研究所 Multi-unmanned plane wolf-crowd collaborative combat attack and defense decision algorithm

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060142903A1 (en) * 2002-12-05 2006-06-29 Nir Padan Dynamic guidance for close-in maneuvering air combat
CN107390706A (en) * 2017-07-26 2017-11-24 北京航空航天大学 A kind of unmanned plane short range combat decision-making technique based on the motor-driven algorithm of preview
CN108319286A (en) * 2018-03-12 2018-07-24 西北工业大学 A kind of unmanned plane Air Combat Maneuvering Decision Method based on intensified learning
CN111240353A (en) * 2020-01-07 2020-06-05 南京航空航天大学 Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree
CN112284188A (en) * 2020-09-25 2021-01-29 南京航空航天大学 Unmanned aerial vehicle attack and defense decision method based on self-adaptive step discrete wolf cluster algorithm
CN112947581A (en) * 2021-03-25 2021-06-11 西北工业大学 Multi-unmanned aerial vehicle collaborative air combat maneuver decision method based on multi-agent reinforcement learning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060142903A1 (en) * 2002-12-05 2006-06-29 Nir Padan Dynamic guidance for close-in maneuvering air combat
CN107390706A (en) * 2017-07-26 2017-11-24 北京航空航天大学 A kind of unmanned plane short range combat decision-making technique based on the motor-driven algorithm of preview
CN108319286A (en) * 2018-03-12 2018-07-24 西北工业大学 A kind of unmanned plane Air Combat Maneuvering Decision Method based on intensified learning
CN111240353A (en) * 2020-01-07 2020-06-05 南京航空航天大学 Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree
CN112284188A (en) * 2020-09-25 2021-01-29 南京航空航天大学 Unmanned aerial vehicle attack and defense decision method based on self-adaptive step discrete wolf cluster algorithm
CN112947581A (en) * 2021-03-25 2021-06-11 西北工业大学 Multi-unmanned aerial vehicle collaborative air combat maneuver decision method based on multi-agent reinforcement learning

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
ZHANG, YS 等: "Research on Autonomous Maneuvering Decision of UCAV Based on Deep Reinforcement Learning", 《IEEE》 *
傅莉;谢福怀;孟光磊;王东政;: "基于滚动时域的无人机空战决策专家系统", 北京航空航天大学学报, no. 11 *
国海峰;侯满义;张庆杰;唐传林;: "基于统计学原理的无人作战飞机鲁棒机动决策", 兵工学报, no. 01 *
柳嘉润;申功璋;: "自主空战决策中的战术过程评价方法", 火力与指挥控制, no. 04, pages 4 - 6 *
柳嘉润;钟友武;张磊;申功璋;: "自主空战决策的试探机动方法及仿真研究", 系统仿真学报, no. 05 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116225049A (en) * 2022-12-21 2023-06-06 中国航空工业集团公司沈阳飞机设计研究所 Multi-unmanned plane wolf-crowd collaborative combat attack and defense decision algorithm

Similar Documents

Publication Publication Date Title
CN107390706B (en) Unmanned aerial vehicle near combat decision method based on rehearsal maneuver rule system
US7437223B2 (en) Heading reference command and control algorithm and cueing systems and methods for aircraft turn-to-target maneuvers
CN110502027B (en) Four-rotor unmanned aerial vehicle attitude fault-tolerant control method based on self-adaptive terminal sliding mode
US8355861B2 (en) Avoidance manoeuvre generator for an aircraft
US20070032923A1 (en) Heading reference command and control algorithm systems and methods for aircraft turn-to-target maneuvers
CN111650963A (en) Visual cluster formation control method for vertical take-off and landing fixed wing unmanned aerial vehicle
CN114200826B (en) High stability control method for supersonic speed large maneuvering target continuous large overload maneuvering
Fu et al. The overview for UAV air-combat decision method
Li et al. Autonomous maneuver decision-making for a UCAV in short-range aerial combat based on an MS-DDQN algorithm
CN114492805A (en) Air combat maneuver decision design method based on fuzzy reasoning
CN115903865A (en) Aircraft near-distance air combat maneuver decision implementation method
CN108020226A (en) A kind of path planning method of fixed-wing unmanned plane automatic obstacle avoiding
CN115993835A (en) Target maneuver intention prediction-based short-distance air combat maneuver decision method and system
CN115688268A (en) Aircraft near-distance air combat situation assessment adaptive weight design method
CN113625739A (en) Expert system optimization method based on heuristic maneuver selection algorithm
CN114063644A (en) Unmanned combat aircraft air combat autonomous decision method based on pigeon flock reverse confrontation learning
CN115431271A (en) Anti-interference pointing control method for tail end of aircraft mechanical arm
CN114265425A (en) Multi-rotor unmanned aerial vehicle formation anti-collision control method
Moncayo et al. Extended nonlinear dynamic inversion control laws for unmanned air vehicles
CN106363646B (en) A kind of multi-rotor aerocraft and airborne mechanical arm joint Pose Control of view-based access control model servo
CN115268496B (en) Unmanned aerial vehicle air countermeasure maneuvering controller and design method thereof
Lee et al. One-versus-one air-to-air combat maneuver generation based on the differential game
CN116300988A (en) Advanced layout unmanned aerial vehicle anti-interference control strategy based on fractional order sliding mode
CN116203840A (en) Adaptive gain scheduling control method for reusable carrier
Sultan et al. The Reachable Set of a Drone: Exploring the Position Isochrones for a Quadcopter

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination