CN116861645B - Non-linear prediction control-based aircraft beyond-sight air combat maneuver decision-making method - Google Patents
Non-linear prediction control-based aircraft beyond-sight air combat maneuver decision-making method Download PDFInfo
- Publication number
- CN116861645B CN116861645B CN202310771153.5A CN202310771153A CN116861645B CN 116861645 B CN116861645 B CN 116861645B CN 202310771153 A CN202310771153 A CN 202310771153A CN 116861645 B CN116861645 B CN 116861645B
- Authority
- CN
- China
- Prior art keywords
- aircraft
- air combat
- maneuver decision
- decision
- beyond
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000000007 visual effect Effects 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims description 21
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 description 22
- 230000008901 benefit Effects 0.000 description 13
- 230000008859 change Effects 0.000 description 4
- 230000009194 climbing Effects 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 238000011835 investigation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Geometry (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a non-linear prediction control-based maneuvering decision method for an aircraft beyond-sight air combat, which relates to the technical field of maneuvering control of the aircraft and comprises the following steps of: constructing a three-free guidance dynamics model of the aircraft, and dispersing the three-free guidance dynamics model by adopting a fourth-order Dragon-Gregorian tower method to obtain a discrete guidance dynamics model; the self-adaptive weight coefficient is obtained based on the IF-THEN rule of the detour head-on tactics, and an aircraft beyond-sight air combat maneuver decision dominance function is constructed according to the air combat situation data and the self-adaptive weight coefficient; constructing an aircraft beyond visual range air combat maneuver decision model based on nonlinear predictive control according to the discrete guidance dynamics model and the aircraft beyond visual range air combat maneuver decision dominance function; and solving the maneuver decision model of the over-the-horizon air combat of the aircraft to obtain the optimal maneuver decision of the over-the-horizon air combat of the aircraft. The invention has high universality, can be suitable for various models, and is convenient for utilizing the maneuverability of the fighter plane to the greatest extent.
Description
Technical Field
The invention relates to the technical field of maneuvering control of aircrafts, in particular to an aircraft beyond-sight air combat maneuvering decision optimization method based on nonlinear model predictive control.
Background
With the development of modern investigation technology and weapon technology, over-the-horizon air combat with a fourth generation fighter plane as a main angle has become the 'first pass' in air combat, and fighters have the airborne missile attack capability and the airborne radar investigation capability, and the key in over-the-horizon air combat is that weapon firing advantages are obtained through maneuvering decisions, and the attack of enemy missiles is avoided, so that the over-the-horizon air combat is the key to win modern air combat. The situation of the merits in the beyond-sight air combat depends on the use of the missile attack capability, radar investigation capability and self-propulsion capability of two-party fighters, and when the intelligent decision-making capability of the fighters is not greatly different, the fighters utilizing the capability to the greatest extent can often obtain better air combat advantages.
The research on beyond-visual-distance air combat maneuver decision algorithm at home and abroad is mainly focused on decision trees, differential countermeasure methods and reinforcement learning methods. These methods do not achieve a good maneuver decision effect in the following ways: (1) The decision tree algorithm is only suitable for a certain type of fighter, can not directly expand and transplant decision trees, and can not utilize the maneuverability of the fighter to the maximum extent; (2) The maneuvering decision based on the differential countermeasure method is difficult to be suitable for complex air combat environments, is only suitable for ideal air combat environments, cannot be matched with air combat tactics, and can only finish simple air combat tactics such as pursuits, escape and the like; (3) Similar to the disadvantages of decision tree algorithms, reinforcement learning based decision methods are less versatile and require retraining when the fighter model changes, even on-board missile models.
Disclosure of Invention
The invention aims to provide a non-linear prediction control-based aircraft beyond-sight air combat maneuver decision method which can alleviate the problems.
In order to alleviate the problems, the technical scheme adopted by the invention is as follows:
an aircraft beyond visual range air combat maneuver decision method based on nonlinear predictive control comprises the following steps:
s1, constructing a three-free guidance dynamics model of an aircraft, and dispersing the three-free guidance dynamics model by adopting a fourth-order Dragon-Gregory tower method to obtain a discrete guidance dynamics model;
s2, obtaining a self-adaptive weight coefficient based on an IF-THEN rule of a detour head-on tactical method, and constructing an aircraft beyond-sight air combat maneuver decision dominance function according to air combat situation data and the self-adaptive weight coefficient;
s3, constructing an aircraft beyond visual range air combat maneuver decision model based on nonlinear predictive control according to the discrete guidance dynamics model and the aircraft beyond visual range air combat maneuver decision dominance function;
and S4, solving the maneuver decision model of the over-the-horizon air combat of the aircraft to obtain the optimal maneuver decision of the over-the-horizon air combat of the aircraft.
In a preferred embodiment of the present invention, in step S1, the three-freedom guidance dynamics model is:
x(t)＝[χ(t),γ(t),x(t),y(t),z(t),V(t)] T
u(t)＝[n x (t),n(t),μ(t)] T
wherein the state quantity x is yaw angle χ, climbing angle γ, position coordinate (x, y, z) and speed V, and the control quantity u is tangential overload n x Overload n and roll angle μ;
the discrete guidance dynamics model is:
where Δt is the discrete step size.
In a preferred embodiment of the present invention, in step S2, the maneuver decision dominance function of the over-the-horizon air combat of the aircraft is:
R＝α d T d +α φ T φ +α q T q +α h T h
wherein T is d ,T φ ,T q ,T h Are all air combat situation data, namely distance advantage, azimuth angle advantage, entrance angle advantage and altitude advantage, alpha d ,α φ ,α q ,α h Respectively T d ,T φ ,T q ,T h Is used for the adaptive weight coefficient of the (a);
defining the real-time distance between the My aircraft and the enemy aircraft as d, and designing a distance dominance function as follows:
wherein sigma d A proportionality coefficient which is a balance distance unit;
defining an included angle between a velocity vector of the my aircraft and a position vector connecting line of the my aircraft towards the position of the enemy aircraft as an azimuth angle phi, and designing an azimuth angle dominance function as follows:
defining an included angle between an enemy aircraft speed vector and a vector connecting line of the enemy aircraft position towards the enemy aircraft position as an entry angle q, and designing an entry angle dominance function as follows:
defining the altitude of the aircraft relative to the enemy aircraft as dh, and designing an altitude dominance function as follows:
wherein dh is 0 For a relative height that is known to the current time,the lower and upper bounds, respectively, of the optimal relative altitude for the my aircraft.
In a preferred embodiment of the present invention, the method for obtaining the adaptive weight coefficient based on the IF-THEN rule includes: defining the maximum attack distance of a missile non-escapable area of the current moment of the aircraft as followsThe maximum attack distance of the missile escape area of the enemy aircraft is +.>Adaptive weight coefficient a= [ alpha ] d ,α φ ,α q ,α h ] T ，
When (when)When dh < 0, a= [ -0.8.0.0.2]；
When (when)At the time, a= [0.2 0.0.8]；
When (when)At the time, a= [1 00 0 ]]；
When (when)At the time, a= [1 00 0 ]]；
When (when)At the time, a= [ 01 00 ]]。
In a preferred embodiment of the present invention, the objective of the aircraft over-the-horizon air combat maneuver decision optimization problem is to maximize aircraft over-the-horizon air combat maneuver decision optimizationOptimizing time domain t of potential function in future 0 To t f While predictive control is to re-optimize the time-domain t for timely feedback and control of state 0 To t 1 The optimal control quantity at the moment acts on the aircraft to update the state;
in step S3, the maneuver decision model of the aircraft beyond visual range air combat based on nonlinear predictive control is:
x(0)＝x 0
compared with the prior art, the invention has the beneficial effects that:
1) Through the collocation of the self-adaptive weight coefficient and the air combat dominance function in a fixed form, maneuvering decisions under various tactics are realized;
2) Considering the distance and relative high of a time-varying missile attack area, realizing weight self-adaptive selection under a dynamic air combat situation by introducing the relationship between a time-varying missile attack distance parameter and weight coefficient change, so that different weight coefficients are selected when the missile attack distance is dominant, inferior and uniform by the aid of the aircraft, different maneuvering decisions are made, and the air combat situation is gradually improved;
3) The established maneuvering decision optimization problem of the air combat takes into consideration practical maneuvering performance constraints of the aircraft, such as overload, speed, roll angle, climbing angle, change rate constraint thereof and the like, and obtains maneuvering decisions which optimize the situation of the air combat on the premise of meeting the maneuvering performance by solving the optimization problem, so that the maneuvering decision optimization scheme provided by the invention can make better maneuvering decisions of the air combat on the basis of fully playing the maneuvering performance of the aircraft;
4) The objective function of the maneuver decision optimization problem provided by the invention is irrelevant to the model of the aircraft, and is suitable for any model of over-the-horizon air combat aircraft, the constraint in the optimization problem relates to specific parameters such as the maximum overload, the maximum speed and the maximum roll angle of the current aircraft, and corresponding parameter thresholds under the performance constraint exist for any model of aircraft, so that the maneuver decision of different models of aircraft with different maneuver performances can be accepted by the optimization problem in a fixed form, and maneuver decision optimization can be performed by solving the optimization problem as long as the maneuver performance parameter thresholds of the model of aircraft are determined, so that the scheme of the invention has better universality.
In order to make the above objects, features and advantages of the present invention more comprehensible, embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a technical scheme frame diagram of the invention;
FIG. 2 is a flight trajectory of over-the-horizon air combat;
FIG. 3 is a graph of range parameters and azimuth angle changes for a red missile;
fig. 4 is a graph of range parameters and azimuth angle changes for a blue missile.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention.
The invention discloses a non-linear prediction control-based maneuvering decision method for an aircraft beyond-sight air combat, which comprises the following steps:
referring to fig. 1, the invention optimizes the maneuver decision of the aircraft by adopting a nonlinear predictive control method, considers that the desired signal in the actual engineering is a discrete signal, and the guide ring and the control ring are designed separately, and discretizes the maneuver decision optimizing problem based on the three-degree-of-freedom dynamics guidance equation of the aircraft.
Consider the following guidance dynamics equation in the track coordinate axis:
wherein the state quantity x is yaw angle χ, climbing angle γ, position coordinate (x, y, z) and speed V, and the control quantity u is tangential overload n x Overload n and roll angle mu. When the delta t is smaller (the maneuver decision output by the scheme of the invention is an maneuver guidance instruction such as overload, roll angle and the like, and the output frequency is related to the control frequency of the bottom layer actual controller, in the actual aircraft control, the input frequency of the guidance instruction input to the control ring by the guidance ring is generally higher, and the input is a discrete signal, so that the delta t corresponding to the refresh frequency of the actual guidance instruction is smaller), the guidance equation is discretized by a fourth-order Dragon-Gregory tower method:
after the discrete guidance dynamics equation is established, an over-the-horizon air combat situation dominance function is established. According to the air combat situation data of the My aircraft and the enemy aircraft, the following aircraft beyond-sight air combat maneuver decision dominance function is established:
R＝α d T d +α φ T φ +α q T q +α h T h (3)
wherein T is d ,T φ ,T q ,T h Are all air combat situation data, namely distance advantage, azimuth angle advantage, entrance angle advantage and altitude advantage, alpha d ,α φ ,α q ,α h Respectively T d ,T φ ,T q ,T h Is used for the adaptive weight coefficient of the (c).
The specific design of each dominance function is given below.
Defining the real-time distance between the enemy aircraft and the enemy aircraft as d, and enabling the enemy aircraft to gradually enter the attack distance of the enemy weapon by optimizing the distance dominance function to be capable of approaching the distance of the enemy aircraft. Designing a distance dominance function:
σ d and 200 is a proportionality coefficient of the balance distance unit.
An included angle between a speed vector of the aircraft and a direction vector of the aircraft position towards the enemy position is defined as an azimuth angle phi, and the enemy aircraft gradually enters the attack angle of the weapon by reducing the azimuth angle of the aircraft. The design azimuth dominance function is:
an included angle between a speed vector of the enemy aircraft and a vector connecting line of the position of the enemy aircraft towards the enemy position is defined as an entry angle q, and the entry angle of the enemy is reduced to destroy the attack angle condition of the enemy weapon. The designed entry angle dominance function is:
the height of the aircraft relative to the enemy aircraft is defined as dh, and the increase of the aircraft relative height can increase the missile attack distance of the aircraft, so that the advanced attack condition of the weapon is realized. Accordingly, the following height dominance function is designed:
wherein dh is 0 For a relative height that is known to the current time,the lower bound and the upper bound of the optimal relative altitude of the aircraft are respectively, and the aircraft is maintained in a better relative altitude state and cannot be excessively high through the dominant function form and the introduction of the upper bound and the lower bound of the optimal relative altitude.
Next we get the adaptive weight coefficient a= [ α ] based on IF-THEN rule d ,α φ ,α q ,α h ] T . Defining the maximum attack distance of the non-escapable area of the missile on the current moment asThe maximum attack distance of the non-escapable area of the missile of the enemy isThe missile non-escapable maximum attack distance is related to the speed, relative speed, altitude, relative altitude, entry angle and azimuth angle of the my aircraft and the enemy aircraft.
The patent considers the detour head-on tactics, and the weight coefficient IF-THEN rule corresponding to the detour head-on tactics is described as follows: if the distance between the aircraft and the enemy aircraft is far and the aircraft is poor (representing the attack distance of the missile is poor), if the aircraft receives the enemy at the head, the disadvantages of the attack distance of the missile cannot be timely compensated in the process of approaching the enemy, and the aircraft should select the distance to be pulled awayMeanwhile, the missile climbs to make up for the disadvantage of the attack distance of the missile; after the missile attack distance is made up for a period of time after climbing, a head-on receiver can be selected, the aircraft approaches the enemy aircraft at a higher altitude when the distance between the enemy aircraft and the enemy aircraft is longer, and the distance is optimized through full force when the distance is shorter, if the enemy aircraft enters the attack distance of the enemy aircraft, the azimuth angle is optimized through full force so as to simultaneously realize the angle attack condition. Accordingly, the adaptive weight coefficient a= [ α ] d ,α φ ,α q ,α h ] T The values were taken according to the following conditions:
when (when)When dh < 0, a= [ -0.8.0.0.2]；
When (when)At the time, a= [0.2 0.0.8]；
When (when)At the time, a= [1 00 0 ]]；
When (when)At the time, a= [1 00 0 ]]；
When (when)At the time, a= [ 01 00 ]]。
After the dominant function and the weight coefficient IF-THEN rule of the over-the-horizon air combat are designed, modeling and solving are carried out on the maneuver decision optimization problem of the over-the-horizon air combat based on a nonlinear predictive control method.
The thresholds for each state quantity, control quantity, state quantity rate of change, and control quantity rate of change constraint in the optimization problem are dependent on the maneuver performance and control performance of the aircraft. The objective function in the optimization problem is the optimization time domain t of the air combat dominance function designed for maximization in the future 0 To t f Is controlled predictively asTimely feedback and control re-optimization of state, and t is calculated 0 To t 1 The optimal control quantity of the moment acts on the aircraft to update the state. To sum up, the nonlinear predictive control optimization problem is that
x(0)＝x 0
The invention discloses a non-linear prediction control-based aircraft beyond-sight air combat maneuver decision method, which comprises the following steps:
the specific values of each performance parameter and the optimization problem parameter are shown in table 1 under the assumption that the red and blue aircrafts are of the same model, namely the various flying parameters are the same. The simulation environment is Matlab2019a, and the Fmocon is adopted to solve the optimization problem.
TABLE 1 maneuver Performance, radar and missile parameters, optimization problem parameters
Consider a red-blue aircraft performing over-the-horizon air combat, and consider a blue party employing a pursuit strategy, i.e., a blue party making a maneuver decision for retracting as soon as possible from an enemy aircraft. The initial states of the blue machine and the red machine are set as follows:
[χ r ,γ r ,x r ,y r ,z r ,V r ] T ＝[0,0,0,0,5000,90] T
[χ b ,γ b ,x b ,y b ,z b ,V b ] T ＝[π,0,60000,3000,7000,100] T
as can be seen from the air combat trajectory graph 2 of the aircraft, the maximum attack distance parameter variation graph 3 of the red missile and the maximum attack distance parameter variation graph 4 of the blue missile, the red aircraft is climbed while selecting the escape pull-out distance when the initial situation is poor due to the execution of the roundabout head-on tactics, the aircraft is turned to climb after compensating the high disadvantage, the enemy aircraft is hit at head, the distance between the dive acceleration pull-in and the enemy aircraft is selected when the distance is relatively close, and finally the missile attack condition is satisfied in advance by using the attack distance of a larger non-escapable area of the missile. Although the initial poor missile attack area distance is always smaller in the escape process of the my aircraft, the missile attack area distance is gradually increased while the altitude is compensated, and finally exceeds the missile attack distance of the enemy aircraft. The maneuvering decision of the enemy aircraft can not utilize the influence of the height advantage on the distance parameter of the missile attack area due to the fact that the distance between the enemy aircraft and the enemy aircraft is only shortened, the disadvantage is gradually changed under the condition that the maximum attack distance of the initial missile attack area is dominant, and the disadvantage of the missile attack distance is finally attacked in advance by the infrared aircraft although a smaller attack angle is always kept in the process of pursuing.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. The aircraft beyond-sight air combat maneuver decision-making method based on nonlinear predictive control is characterized by comprising the following steps of:
s1, constructing a three-degree-of-freedom guidance dynamics model of an aircraft, and dispersing the three-degree-of-freedom guidance dynamics model by adopting a fourth-order Dragon-Grating tower method to obtain a discrete guidance dynamics model;
s2, obtaining a self-adaptive weight coefficient based on an IF-THEN rule of a detour head-on tactical method, and constructing an aircraft beyond-sight air combat maneuver decision dominance function according to air combat situation data and the self-adaptive weight coefficient, wherein the maneuver decision dominance function comprises the following steps:
R＝α d T d +α φ T φ +α q T q +α h T h
wherein T is d 、T φ 、T q And T h All belong to air combat situation data, in particular T d As a distance dominance function, T φ As azimuth dominance function, T q To enter the angular dominance function, T h As a highly advantageous function, alpha d Is T d Is a φ Is T φ Is a q Is T q Is a h Is T h Is used for the adaptive weight coefficient of the (a);
s3, constructing an aircraft beyond visual range air combat maneuver decision model based on nonlinear predictive control according to the discrete guidance dynamics model and the aircraft beyond visual range air combat maneuver decision dominance function, wherein the aircraft beyond visual range air combat maneuver decision model is constructed by the following steps:
x(0)＝x 0
wherein Δt is the discrete step size;
and S4, solving the maneuver decision model of the over-the-horizon air combat of the aircraft to obtain the optimal maneuver decision of the over-the-horizon air combat of the aircraft.
2. The non-linear predictive control-based aircraft beyond-line-of-sight air combat maneuver decision method as recited in claim 1, wherein in step S1, the three-degree-of-freedom guidance dynamics model is:
x(t)＝[χ(t),γ(t),p x (t),p y (t),p z (t),V(t)] T
u(t)＝[n x (t),n(t),μ(t)] T
wherein n is x For tangential overload, n is overload, μ is roll angle, χ, γ, V are yaw, climb and speed of the aircraft, respectively.
3. The non-linear predictive control-based aircraft beyond-line-of-sight air combat maneuver decision method as recited in claim 2, wherein the discrete guidance dynamics model is:
4. a non-linear predictive control based aircraft beyond-line-of-sight air combat maneuver decision making method as defined in claim 3 wherein the real-time distance between the my aircraft and the enemy aircraft is defined as d and the distance dominance function is designed as:
wherein sigma d A proportionality coefficient which is a balance distance unit;
defining an included angle between a velocity vector of the my aircraft and a position vector connecting line of the my aircraft towards the position of the enemy aircraft as an azimuth angle phi, and designing an azimuth angle dominance function as follows:
defining an included angle between an enemy aircraft speed vector and a vector connecting line of the enemy aircraft position towards the enemy aircraft position as an entry angle q, and designing an entry angle dominance function as follows:
defining the altitude of the aircraft relative to the enemy aircraft as dh, and designing an altitude dominance function as follows:
wherein dh is 0 For a relative height that is known to the current time,the lower and upper bounds, respectively, of the optimal relative altitude for the my aircraft.
5. The non-linear predictive control based aircraft beyond-line-of-sight air combat maneuver decision method as recited in claim 4, wherein the method for obtaining the adaptive weight coefficients based on the IF-THEN rule comprises: defining the maximum attack distance of a missile non-escapable area of the current moment of the aircraft as followsThe maximum attack distance of the missile escape area of the enemy aircraft is +.>Adaptive weight coefficient a= [ alpha ] d ,α φ ,α q ,α h ] T ，
When (when)At the time, a= [ -0.8.0.0.2]；
When (when)At the time, a= [0.2 0.0.8]；
When (when)At the time, a= [1 00 0 ]]；
When (when)At the time, a= [1 00 0 ]]；
When (when)At the time, a= [ 01 00 ]]。
6. The method for maneuver decision making for over-the-horizon air combat of an aircraft based on nonlinear predictive control as recited in claim 5, wherein the objective of the maneuver decision optimization problem for over-the-horizon air combat of an aircraft is to maximize the optimization time domain t of the maneuver decision dominance function for over-the-horizon air combat of an aircraft in the future 0 To t f While predictive control is to re-optimize the time-domain t for timely feedback and control of state 0 To t 1 The optimal control quantity of the (c) is applied to the aircraft for status updating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310771153.5A CN116861645B (en) | 2023-06-27 | 2023-06-27 | Non-linear prediction control-based aircraft beyond-sight air combat maneuver decision-making method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310771153.5A CN116861645B (en) | 2023-06-27 | 2023-06-27 | Non-linear prediction control-based aircraft beyond-sight air combat maneuver decision-making method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116861645A CN116861645A (en) | 2023-10-10 |
| CN116861645B true CN116861645B (en) | 2024-04-16 |
Family
ID=88231431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310771153.5A Active CN116861645B (en) | 2023-06-27 | 2023-06-27 | Non-linear prediction control-based aircraft beyond-sight air combat maneuver decision-making method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116861645B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330582A (en) * | 2022-07-27 | 2022-11-11 | 淮阴工学院 | Reversible watermarking algorithm based on unidirectional extreme value prediction error expansion |
| CN117688727A (en) * | 2023-11-16 | 2024-03-12 | 四川大学 | Short-distance air combat maneuver planning method considering over-stall maneuver of airplane |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666631A (en) * | 2020-06-03 | 2020-09-15 | 南京航空航天大学 | Unmanned aerial vehicle maneuvering decision method combining hesitation fuzzy and dynamic deep reinforcement learning |
| CN114118664A (en) * | 2021-07-21 | 2022-03-01 | 岭南师范学院 | Dynamic decision method for solving complexity of attribute weight and time weight |
| CN114492805A (en) * | 2021-12-17 | 2022-05-13 | 南京航空航天大学 | Air combat maneuver decision design method based on fuzzy reasoning |
| CN115759754A (en) * | 2022-12-06 | 2023-03-07 | 西北工业大学 | Beyond-visual-range air combat simulation target threat assessment method based on dynamic game variable weight |
| CN115903865A (en) * | 2022-09-16 | 2023-04-04 | 中国空气动力研究与发展中心空天技术研究所 | Aircraft near-distance air combat maneuver decision implementation method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095481B (en) * | 2021-04-03 | 2024-02-02 | 西北工业大学 | Air combat maneuver method based on parallel self-game |
-
2023
- 2023-06-27 CN CN202310771153.5A patent/CN116861645B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666631A (en) * | 2020-06-03 | 2020-09-15 | 南京航空航天大学 | Unmanned aerial vehicle maneuvering decision method combining hesitation fuzzy and dynamic deep reinforcement learning |
| CN114118664A (en) * | 2021-07-21 | 2022-03-01 | 岭南师范学院 | Dynamic decision method for solving complexity of attribute weight and time weight |
| CN114492805A (en) * | 2021-12-17 | 2022-05-13 | 南京航空航天大学 | Air combat maneuver decision design method based on fuzzy reasoning |
| CN115903865A (en) * | 2022-09-16 | 2023-04-04 | 中国空气动力研究与发展中心空天技术研究所 | Aircraft near-distance air combat maneuver decision implementation method |
| CN115759754A (en) * | 2022-12-06 | 2023-03-07 | 西北工业大学 | Beyond-visual-range air combat simulation target threat assessment method based on dynamic game variable weight |
Non-Patent Citations (2)
| Title |
|---|
| Situational continuity-based air combat autonomous maneuvering decision-making;Jian-dong Zhang;《Defence Technology》;第66-79页 * |
| 基于战术攻击区的超视距空战态势评估方法;徐安 等;《火力与指挥控制》;第45卷(第9期);第97-102页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116861645A (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116861645B (en) | Non-linear prediction control-based aircraft beyond-sight air combat maneuver decision-making method | |
| CN109884895B (en) | Unmanned aerial vehicle self-adaptive tracking control algorithm based on saturation limited condition | |
| CN112215283A (en) | Close-range air combat intelligent decision method based on manned/unmanned aerial vehicle system | |
| CN108319286A (en) | A kind of unmanned plane Air Combat Maneuvering Decision Method based on intensified learning | |
| CN113093802A (en) | Unmanned aerial vehicle maneuver decision method based on deep reinforcement learning | |
| CN103090728A (en) | Tail angle restraining guidance method based on sliding mode control | |
| CN113268081B (en) | Small unmanned aerial vehicle prevention and control command decision method and system based on reinforcement learning | |
| CN107765553A (en) | For the nonlinear control method of rotor wing unmanned aerial vehicle hanging transportation system | |
| CN114330115B (en) | Neural network air combat maneuver decision-making method based on particle swarm search | |
| CN107203138B (en) | Aircraft robust control method with saturated input and output | |
| CN113282061A (en) | Unmanned aerial vehicle air game countermeasure solving method based on course learning | |
| CN111898201B (en) | High-precision autonomous attack guiding method for fighter in air combat simulation environment | |
| Yeh | Attitude controller design of mini-unmanned aerial vehicles using fuzzy sliding-mode control degraded by white noise interference | |
| CN114492805A (en) | Air combat maneuver decision design method based on fuzzy reasoning | |
| CN107515612A (en) | Elastic vibration suppressing method based on side spray flow control | |
| Santoso et al. | State-of-the-art integrated guidance and control systems in unmanned vehicles: A review | |
| CN115877871B (en) | Non-zero and game unmanned aerial vehicle formation control method based on reinforcement learning | |
| CN115755956B (en) | Knowledge and data collaborative driving unmanned aerial vehicle maneuvering decision method and system | |
| CN114003050A (en) | Active defense guidance method of three-body countermeasure strategy based on differential game | |
| CN104991446B (en) | A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning | |
| CN113671825A (en) | Maneuvering intelligent decision missile avoidance method based on reinforcement learning | |
| Xianyong et al. | Research on maneuvering decision algorithm based on improved deep deterministic policy gradient | |
| CN117452975A (en) | Security performance cooperative formation control design method for four-rotor unmanned aerial vehicle cluster | |
| CN115357051B (en) | Deformation and maneuvering integrated avoidance and defense method | |
| CN116432030A (en) | Air combat multi-intention strategy autonomous generation method based on deep reinforcement learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |