CN116560403A - Intelligent time collaborative guidance method, system and equipment for hypersonic aircraft - Google Patents
Intelligent time collaborative guidance method, system and equipment for hypersonic aircraft Download PDFInfo
- Publication number
- CN116560403A CN116560403A CN202310586938.5A CN202310586938A CN116560403A CN 116560403 A CN116560403 A CN 116560403A CN 202310586938 A CN202310586938 A CN 202310586938A CN 116560403 A CN116560403 A CN 116560403A
- Authority
- CN
- China
- Prior art keywords
- hypersonic aircraft
- guidance
- hypersonic
- collaborative
- time
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 95
- 238000013135 deep learning Methods 0.000 claims abstract description 29
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004907 flux Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 206010048669 Terminal state Diseases 0.000 description 3
- 238000012886 linear function Methods 0.000 description 3
- 241000838698 Togo Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
-
- 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)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent time collaborative guidance method, system and equipment for a hypersonic aircraft, and relates to the field of hypersonic aircraft collaborative guidance, wherein the method comprises the following steps: according to a dynamics model and a kinematic model of the hypersonic aircraft, determining a hypersonic aircraft collaborative time planning target, a flight process constraint condition and a terminal constraint condition; determining course angle corridor and roll angle overturning logic according to the target and the constraint condition; calculating a transverse collaborative time adjustment factor in transverse lateral guidance according to the course angle corridor and the roll angle overturning logic; calculating a roll angle profile in longitudinal guidance according to the transverse cooperative time adjustment factor; determining a deep learning framework based on a Transformer network according to the transverse cooperative time adjustment factor and the roll angle profile; the method can plan the track of the hypersonic aircraft on line and realize intelligent time collaborative guidance of the hypersonic aircraft.
Description
Technical Field
The invention relates to the field of hypersonic aircraft collaborative guidance, in particular to an intelligent time collaborative guidance method, system and equipment for a hypersonic aircraft.
Background
When the hypersonic aircraft flies in the near space, the flying speed can reach more than 5 Mach, and the hypersonic aircraft has the characteristics of high flying speed, long range and strong sudden prevention capability, is applied to the field of rapid remote striking, and has strong strategic deterrent significance. In recent years, the collaborative combat of a plurality of hypersonic aircrafts has become a hot spot problem for research. Reentry guidance of multiple hypersonic aircrafts involves how to guide multiple hypersonic aircrafts to achieve coordinated time attacks on a target under various typical constraints, thereby completing destructive strikes on the target. With the development of artificial intelligence technology, deep learning has become an effective way to solve the calculation delay problem in recent years, and how to solve the hypersonic aircraft online trajectory planning problem by using a deep learning algorithm and shorten the online planning time is also a considerable research hotspot.
Collaborative guidance has been well-established in multi-missile missiles. However, for hypersonic aircrafts, due to their complex nonlinear model, extremely fast flight speeds, fast time-varying flight environments, traditional collaborative guidance control methods cannot be directly applied to reentry flight of hypersonic aircrafts. In recent years, some students have also studied the problem of co-guidance of hypersonic aircrafts. In Jianglong et al, a hypersonic aircraft cooperative guidance strategy is proposed that considers attack time and attack angle, and divides the planning problem into two stages, wherein in the glide reentry stage, the cooperation of attack angle is realized by controlling roll angle, and in the terminal guidance stage, the cooperation of attack time is realized by controlling attack angle. However, the glide reentry phase does not take into account the limitations of the collaborative attack time, and the computing power of the on-board computer severely affects the planning time. Li Zhenhua et al analyzed the time frame of the hypersonic vehicle reentry flight and studied the time coordinated reentry guidance algorithm of the hypersonic vehicle. However, in essence, this approach calculates a coordinated time based on the capabilities of each hypersonic aircraft, and then each hypersonic aircraft individually implements a coordinated time constraint. Once a hypersonic aircraft encounters an unknown disturbance during a mission, the hypersonic aircraft cannot guarantee the same arrival time. In addition, this method is computationally intensive and has a computational delay problem that is difficult to overcome. Therefore, the technical problem to be solved is to study the hypersonic aircraft intelligent collaborative time planning problem and to carry out simulation verification.
Disclosure of Invention
The invention aims to provide an intelligent time collaborative guidance method, system and equipment for a multi-hypersonic aircraft, which can realize online track planning and realize that the multi-hypersonic aircraft simultaneously arrives at a terminal area.
In order to achieve the above object, the present invention provides the following solutions:
in a first aspect, the invention provides an intelligent time collaborative guidance method for a hypersonic aircraft, comprising the following steps:
establishing a dynamic model and a kinematic model of the hypersonic aircraft;
according to the dynamic model and the kinematic model of the hypersonic aircraft, determining a hypersonic aircraft collaborative time planning target, and flight process constraint conditions and terminal constraint conditions;
determining course angle corridor and roll angle overturning logic according to the hypersonic aircraft collaborative time planning target, the flight process constraint condition and the terminal constraint condition;
according to course angle corridor and roll angle overturning logic, calculating a transverse cooperative time adjustment factor in transverse and lateral guidance;
calculating a roll angle profile in longitudinal guidance according to the transverse cooperative time adjustment factor;
determining a deep learning framework based on a transducer network according to a transverse cooperative time adjustment factor in transverse lateral guidance and a roll angle profile in longitudinal guidance; the deep learning framework based on the Transformer network is used for planning hypersonic aircraft tracks on line so as to realize intelligent time collaborative guidance of the hypersonic aircraft.
In a second aspect, the present invention provides an intelligent time collaborative guidance system for a hypersonic aircraft, comprising:
the dynamic model and kinematic model building module is used for building a dynamic model and a kinematic model of the hypersonic aircraft;
the target and constraint condition determining module is used for determining a multi-hypersonic aircraft collaborative time planning target, a flight process constraint condition and a terminal constraint condition according to a dynamics model and a kinematic model of the hypersonic aircraft;
the course angle corridor and roll angle overturning logic determining module is used for determining course angle corridor and roll angle overturning logic according to the hypersonic aircraft collaborative time planning target, flight process constraint conditions and terminal constraint conditions;
the transverse cooperative time adjustment factor calculation module is used for calculating a transverse cooperative time adjustment factor in transverse and lateral guidance according to the course angle corridor and the roll angle overturning logic;
the roll angle profile calculation module is used for calculating a roll angle profile in longitudinal guidance according to the transverse cooperative time adjustment factor;
a deep learning frame determination module based on a transform network, which is used for determining a deep learning frame based on the transform network according to a transverse cooperative time adjustment factor in transverse lateral guidance and a roll angle section in longitudinal guidance; the deep learning framework based on the Transformer network is used for planning hypersonic aircraft tracks on line so as to realize intelligent time collaborative guidance of the hypersonic aircraft.
In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, the memory being configured to store a computer program, the processor being configured to cause the electronic device to perform the method for intelligent time collaborative guidance of a hypersonic aircraft according to the first aspect.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides an intelligent time collaborative guidance method, system and equipment for a multi-hypersonic aircraft, and aims to realize the collaborative of the reentry time of the multi-hypersonic aircraft through transverse lateral guidance and longitudinal guidance by roughly adjusting the reentry time based on a prediction correction guidance method. By taking a traditional prediction correction algorithm as a training set, a neural network based on a transducer is designed, so that the hypersonic aircraft can generate a roll angle control quantity on line through the neural network, and on-line track planning is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an intelligent time collaborative guidance method for a hypersonic aircraft according to an embodiment of the present invention;
FIG. 2 is a diagram of a ground trace of three hypersonic aircrafts provided by an embodiment of the present invention;
FIG. 3 is a graph of altitude versus dimensionalized energy during flight of three hypersonic aircraft according to an embodiment of the present invention;
fig. 4 is a graph of the tilting angle and the dimensionalized energy of three hypersonic aircrafts in the flight process according to the embodiment of the invention;
fig. 5 is a three-dimensional trajectory diagram of three hypersonic aircrafts in the flying process according to the embodiment of the invention;
FIG. 6 is a diagram of a deep learning framework based on a transform network according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a loss function of a training process according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a loss function of a verification process according to an embodiment of the present invention;
FIG. 9 is a ground track diagram of a hypersonic vehicle online track planning using a trained neural network (i.e., a deep learning framework based on a transducer network) according to an embodiment of the present invention;
FIG. 10 is a graph of altitude versus dimensionalized energy for three hypersonic aircraft in an online planning process according to an embodiment of the present invention;
FIG. 11 is a graph showing the roll angle control amount result of a first hypersonic aircraft in the online trajectory planning process and comparing the roll angle control amount result with a conventional prediction correction method;
FIG. 12 is a graph showing the roll angle control amount result of a second hypersonic aircraft in the online trajectory planning process and comparing the roll angle control amount result with the conventional prediction correction method;
fig. 13 is a graph showing the roll angle control amount result of the third hypersonic aircraft in the online trajectory planning process and comparing the roll angle control amount result with the result of the conventional prediction correction method.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Aiming at the problem of online track planning of a gliding section of a hypersonic aircraft with cooperative time constraint, the invention provides an intelligent time cooperative guidance method, system and equipment of the hypersonic aircraft. Considering that the cooperative time of a plurality of hypersonic aircrafts reaches a terminal area, the heat flow constraint, the overload constraint, the dynamic pressure constraint and the quasi-equilibrium gliding constraint are required to be met in the flying process, the online track planning method based on the Transformer neural network is provided, the online planning time is effectively shortened, the method is more robust, the method is more in line with the actual application scene and can be applied to online real-time planning, and a simulation verification experiment under Matlab software is provided, so that the effectiveness of the method is proved.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1
As shown in fig. 1, the main implementation steps of the intelligent time collaborative guidance method for the hypersonic aircraft provided in this embodiment are as follows.
Step 101: and establishing a dynamic model and a kinematic model of the hypersonic aircraft.
The present embodiment selects the CAV-H model to model energy variationsAs an independent variable, a dynamics model of the hypersonic aircraft is established, specifically as follows:
wherein θ, φ represents longitude and latitude of the hypersonic aircraft, V represents the descaled hypersonic aircraft speed, R represents the distance from the descaled hypersonic aircraft to the geocenter, γ represents the ballistic dip angle, ψ represents the heading angle, σ represents the roll angle of the hypersonic aircraft, Ω represents the descaled earth rotation angular speed,representing the descaled hypersonic aircraft acceleration +.>And representing the resistance acceleration of the hypersonic aircraft after the dimensionalization.
Determining a linear function of the hypersonic aircraft attack angle as a speed as a kinematic model of the hypersonic aircraft, wherein the expression is as follows:
wherein alpha is the angle of attack during the flight of the hypersonic aircraft.
To ensure integration accuracy, the variable dimensionality operation is as shown in table 1.
Table 1 operation table for removing dimension of variable
Wherein the earth radius R 0 6378140m, gravitational acceleration g of the earth's surface 0 =9.807m/s 2 Because the variables such as longitude, latitude, course angle, trajectory inclination angle and the like are all in radian units, the dimensionality removal processing is not needed.
Step 102: and determining a hypersonic aircraft collaborative time planning target, a flight process constraint condition and a terminal constraint condition according to the dynamic model and the kinematic model of the hypersonic aircraft.
For a multi-hypersonic aircraft collaborative time planning objective, the definition given is: considering M hypersonic aircrafts, for any ith hypersonic aircraft, if the instant when the ith hypersonic aircraft arrives at the terminal areaIt is considered that M hypersonic aircrafts achieve the goal of time coordination.
Meanwhile, the hypersonic aircraft still needs to meet the flight process constraint conditions in the flight process, specifically, needs to meet the overload constraint conditions, the heat flux density constraint conditions, the dynamic pressure constraint conditions and the quasi-equilibrium gliding constraint conditions, and can be expressed as:
q=0.5ρV 2 ≤q max 。
wherein, the liquid crystal display device comprises a liquid crystal display device,is the heat flux, n is the overload in the flight process, q is the dynamic pressure in the flight process, and ρ is the atmospheric density of the current position of the hypersonic aircraft.
For hypersonic aircrafts, it also needs to satisfy terminal constraint conditions, specifically, it needs to satisfy terminal to-be-flown travel constraint conditions, longitude and latitude constraint conditions, time constraint conditions, altitude constraint conditions and heading angle constraint conditions, namely:
wherein the subscript f, i represents the terminal state of the ith hypersonic aircraft and the superscript x represents the value of the terminal state variable of the ith hypersonic aircraft, e.g. h i (e f,i ) Representing the terminal energy e of the ith hypersonic vehicle f,i The height is below, its expected value isAnd similarly, θ and φ represent longitude and latitude respectively. t, ψ, s togo Respectively represent time,Course angle and course to be flown. Wherein the collaborative time constraint value is represented by the formula +.>Given.
Step 103: and determining course angle corridor and roll angle overturning logic according to the hypersonic aircraft collaborative time planning target, the flight process constraint condition and the terminal constraint condition.
According to the hypersonic aircraft collaborative time planning objective of step 102, and the flight process constraint conditions and the terminal constraint conditions, the following course angle corridor and roll angle overturning logic are designed:
wherein sgn (sigma) i ) As sign of roll angle in current guidance round, Δψ i =ψ i -ψ LOS,i Heading angle deviation of ith hypersonic aircraft, psi i Heading angle psi of ith hypersonic aircraft LOS,i Observing a line of sight angle of a target for an ith hypersonic aircraft;viewing angle, Δψ, of a target for hypersonic aircraft max,i For the upper boundary of the heading angle corridor of the ith hypersonic aircraft, deltapsi min,i Is the lower boundary of the heading angle corridor of the ith hypersonic aircraft, sigma p,i A roll angle in a guidance round on the ith hypersonic vehicle; superscript x is the value of the ith hypersonic aircraft terminal state variable, θ i ,φ i The longitude and latitude of the ith hypersonic aircraft, respectively.
The following gives a design method of course angle corridor.
Step1: determining an initial boundary value Deltapsi for being able to reach the terminal area from the initial state of the hypersonic aircraft init,i Course angle corridor turning point (theta) m,i ,|Δψ m,i |)。
Step2: determining the heading angle of the heading angle corridor terminal according to the heading angle deviation of the terminal, and taking |delta phi (e f,i )|=0.8Δψ error,i ;Δψ(e f,i ) Indicating the expected terminal heading angle, deltapsi, of the ith hypersonic aircraft error,i Representing 0.8 times the desired terminal heading angle for the ith hypersonic vehicle.
Step3: if the current longitude theta of the ith hypersonic aircraft i Less than the course angle corridor turning point (theta) m,i ,|Δψ m,i I), i.e. theta i <θ m,i The heading angle deviation of the corrected heading angle corridor is:
if hypersonic aircraft longitude is greater than heading angle corridor turning point (theta) m,i ,|Δψ m,i I), i.e. theta i >θ m,i The heading angle deviation of the corrected heading angle corridor is:
|Δψ i |=K ρ,i /θ(e i )+|Δψ(e f,i )|-K ρ /θ(e f,i )。
wherein Δψ (e f,i ) Is set to be 0.8 times of the heading angle of the expected terminal, K ρ,i Is the ith hypersonic vehicle lateral coordinated time adjustment factor, designed in step 104.
Step 104: and calculating a transverse cooperative time adjustment factor in transverse and lateral guidance according to the course angle corridor and the roll angle overturning logic.
According to the course angle corridor and roll angle overturning logic in the step 103, calculating a transverse cooperative time adjustment factor K in transverse lateral guidance by utilizing Newton iteration method ρ,i Specifically, the following is described.
In the transverse and lateral guidance, only time is used as an iteration variable, and the established inclination angle amplitude profile is formed by three points { sigma } 0,i (e 0,i ),σ mid,i (e mid,i ),σ f,i (e f,i ) Linear function of }Number, wherein sigma 0,i For the ith hypersonic aircraft initial energy value, σ f,i For the ith hypersonic aircraft terminal energy value, σ mid,i =(σ 0,i +σ f,i )/2。σ i (e i ) The amplitude of the roll angle at energy e for the ith hypersonic aircraft. Sigma of 0,i (e 0,i ) For example, it represents the initial roll angle magnitude of the ith hypersonic vehicle at the initial energy. Defining the transverse cooperative time error of the ith hypersonic aircraft as
Searching for a transverse time adjustment factor K of an ith hypersonic aircraft approximately meeting a coordinated time constraint by utilizing Newton iteration method ρ,i The termination condition of the iteration is thatThe iteration method is as follows:
wherein eta k =1/2 λ (λ=0, 1,2 …) is to satisfyIs used to adjust the iteration factor of (a).
Step 105: a roll angle profile in longitudinal guidance is calculated based on the lateral coordinated time adjustment factor.
In longitudinal guidance, taking the range to be flown, the cooperative time and the course angle as iteration variables, the roll angle amplitude profile established for the ith hypersonic aircraft is formed by five points { sigma } 0,i (e 0,i ),σ 1,i (e 1,i ),σ 2,i (e 2,i ),σ 3,i (e 3,i ),σ f,i (e f,i ) Linear function of }, iteration variable is chosen as sigma 1,i ,σ 2,i ,σ 3,i Whereinj=1, 2,3 denotes three different energy values during the flight of the ith hypersonic aircraft, σ i (e i ) The amplitude of the roll angle at energy e for the ith hypersonic aircraft. Sigma of 0,i (e 0,i ) For example, he represents the initial roll angle magnitude of the ith hypersonic vehicle at the initial energy. Defining the range error to be flown of the ith hypersonic aircraft asDefining heading angle error of ith hypersonic aircraft as G i (σ 1,i ,σ 2,i ,σ 3,i )=ψ i (e f,i )-ψ i * Defining the cooperative time error of the ith hypersonic aircraft as
Searching for a roll angle profile variable sigma of an ith hypersonic aircraft meeting to-be-flown range constraint by utilizing Newton iteration method 1,i ,σ 2,i ,σ 3,i The termination condition of the iteration is F i (σ 1,i ,σ 2,i ,σ 3,i )<t error,i ,J i (σ 1,i ,σ 2,i ,σ 3,i )<s togoerror,i ,G i (σ 1,i ,σ 2,i ,σ 3,i )<ψ error,i Wherein s is togoerror,i 、ψ error,i 、t error,i The maximum flight error, heading angle error and cooperative time error allowed by the ith hypersonic aircraft are calculated by the following iterative method:
. Wherein eta k =1/2 λ (λ=0, 1,2 …) is an iteration adjustment factor to satisfy that the error after the iteration is smaller than before the iteration.
Step 106: determining a deep learning framework based on a transducer network according to a transverse cooperative time adjustment factor in transverse lateral guidance and a roll angle profile in longitudinal guidance; the deep learning framework based on the Transformer network is used for planning hypersonic aircraft tracks on line so as to realize intelligent time collaborative guidance of the hypersonic aircraft.
And training a deep learning network based on a transducer network according to the track generated by the transverse collaborative time adjustment factor in transverse lateral guidance and the tilting angle section in longitudinal guidance as a training set to obtain a deep learning framework based on the transducer network, thereby realizing intelligent online track rapid planning.
In this embodiment, according to the deep learning framework based on the transform network, the Matlab is used to perform numerical simulation to verify the effectiveness of the system, and the planning speed of the system is compared with that of the conventional method.
The invention provides an intelligent time collaborative guidance method for a multi-hypersonic aircraft, which enables the multi-hypersonic aircraft to realize online rapid track planning under the conditions of overload, heat flux density, dynamic pressure, quasi-equilibrium gliding condition constraint and terminal flight waiting constraint. The main advantages of the method are as follows: 1) The method can realize the cooperation of reentry time of the hypersonic aircraft under the condition of meeting the constraint of the attack angle of the terminal. 2) The method can plan a reasonable hypersonic aircraft glide track under the condition of meeting the constraints of overload, heat flux, dynamic pressure and quasi-equilibrium glide conditions, and meets the constraints of a terminal to-be-flown journey. 3) According to the method, the artificial intelligent deep learning network is utilized, so that the ballistic planning speed is effectively improved, the problem of calculation delay of the hypersonic aircraft is solved, and the method has good online planning capacity and strong robustness.
The effectiveness of the method proposed by this embodiment is verified by an example of a specific hypersonic aircraft time co-guidance plan. The specific implementation steps of this example are as follows:
(1) Hypersonic aircraft system setup
Consider hypersonic waves differing by 3 initial conditionsHypersonic aircraft system composed of fast aircraft, hypersonic aircraft model adopting CAV-H model, mass of 907kg, and aerodynamic reference area of 0.484m 2 . They need to fly to the terminal area while meeting the flight process constraint, and at the same time meet the terminal to-be-flown flight constraint. The initial conditions of the hypersonic aircraft are shown in table 2. The constraints of overload, heat flux, dynamic pressure and quasi-equilibrium glide conditions during flight are shown in table 3, where, to facilitate the planning of the roll angle profile, the constraints are converted into constraints for the roll angle and the maximum roll angle constraint is found to be 80 °, which is more stringent than the constraint before conversion. The longitude and latitude of the terminal area is (theta) f ,φ f ) = (94 degrees, 0 degree), the maximum allowable value of the terminal to-be-flown range error is s togoerror =3 km, heading angle error maximum allowable value ψ error Time error maximum allowable value t =3°, time error maximum allowable value t error =5s。
Table 2 hypersonic aircraft initial conditions table
TABLE 3 constraint table of overload, heat flux, dynamic pressure and quasi-equilibrium glide conditions during flight
(2) Collaborative time prediction correction guidance simulation analysis
In this example, let the earth radius R 0 6378140m, gravitational acceleration g of the earth's surface 0 =9.807m/s 2 . The ground track diagram of three hypersonic aircrafts is shown in figure 2. Fig. 3 shows the altitude and the dimensionalized energy profile of three hypersonic aircrafts during the flight. FIG. 4And (5) representing the graphs of the roll angle and the dimensionalized energy of the three hypersonic aircrafts in the flight process. FIG. 5 shows three dimensional trajectory diagrams of three hypersonic aircraft during flight, it can be seen that the hypersonic aircraft reaches the terminal area under the condition of meeting the flight constraint under the algorithm proposed by the invention, and the iteration obtained cooperative time isThe flight error, the course angle error and the cooperative time error are shown in table 4, and the requirements of the maximum flight error, the course angle error and the cooperative time error are met. This example verifies the validity of the proposed method.
TABLE 4 to-be-flown course error, course angle error, and collaborative time error table
Δψ(°) | Δt(s) | Δs togo (km) | Δh(m) | |
Aircraft 1 | -2.31 | 0.03 | 0.45 | -84.42 |
Aircraft 2 | 1.34 | 0.04 | -0.53 | -63.34 |
Aircraft 3 | 2.75 | 0.07 | -1.54 | -91.02 |
(3) Simulation analysis of intelligent online track planning method
In this example, a transducer-based on-line trajectory planning deep learning neural network is designed, and the structural framework of the network is shown in fig. 6. The network input is the state quantity X of three hypersonic aircrafts input The network comprises an input position coding layer, six coding layers and an output layer, the output is the tilting angle control quantity of three hypersonic aircrafts, the loss functions of the training process and the loss functions of the verification process are shown in fig. 7 and 8, the loss functions of the training set can converge to 0.05, the loss functions of the test set can converge to 0.06, fig. 9 shows a ground track diagram of the online track planning of the hypersonic aircrafts by using a trained neural network (namely a deep learning frame based on a transducer network), fig. 10 shows the height and dimensionalized energy graphs of the three hypersonic aircrafts in the online track planning process, and fig. 11-13 respectively show the tilting angle control quantity results of the three hypersonic aircrafts in the online track planning process and compare with the traditional prediction correction method. Table 4 shows the comparison of the planning time of the intelligent online track planning method and the conventional predictive correction track planning method, and it can be seen that the intelligent method can effectively shorten the planning time. The effectiveness and the instantaneity of the online planning method based on the Transformer are verified.
Table 5 is a comparison table of the planning time of the intelligent on-line track planning method and the traditional prediction correction track planning method
Planning average time | Maximum planning time | |
Prediction correction method | 4.79s | 7.96s |
On-line planning method based on Transformer | <0.01s | 0.01s |
Example two
In order to execute the corresponding method of the embodiment to realize the corresponding functions and technical effects, an intelligent time collaborative guidance system of the hypersonic aircraft is provided below.
The embodiment provides a multi-hypersonic aircraft intelligent time collaborative guidance system, includes:
the dynamic model and kinematic model building module is used for building a dynamic model and a kinematic model of the hypersonic aircraft.
The target and constraint condition determining module is used for determining a hypersonic aircraft collaborative time planning target, and a flight process constraint condition and a terminal constraint condition according to a dynamics model and a kinematic model of the hypersonic aircraft.
The course angle corridor and roll angle overturning logic determining module is used for determining course angle corridor and roll angle overturning logic according to the hypersonic aircraft collaborative time planning target, flight process constraint conditions and terminal constraint conditions.
And the transverse cooperative time adjustment factor calculation module is used for calculating the transverse cooperative time adjustment factor in transverse and lateral guidance according to the course angle corridor and the roll angle overturning logic.
And the roll angle profile calculation module is used for calculating the roll angle profile in longitudinal guidance according to the transverse cooperative time adjustment factor.
A deep learning frame determination module based on a transform network, which is used for determining a deep learning frame based on the transform network according to a transverse cooperative time adjustment factor in transverse lateral guidance and a roll angle section in longitudinal guidance; the deep learning framework based on the Transformer network is used for planning hypersonic aircraft tracks on line so as to realize intelligent time collaborative guidance of the hypersonic aircraft.
Example III
The embodiment of the invention provides electronic equipment which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic equipment to execute the intelligent time collaborative guidance method of the hypersonic aircraft.
Alternatively, the electronic device may be a server.
In addition, the embodiment of the invention also provides a computer readable storage medium which stores a computer program, and the computer program realizes the intelligent time collaborative guidance method of the hypersonic aircraft in the first embodiment when being executed by a processor.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (8)
1. An intelligent time collaborative guidance method for a hypersonic aircraft is characterized by comprising the following steps:
establishing a dynamic model and a kinematic model of the hypersonic aircraft;
according to the dynamic model and the kinematic model of the hypersonic aircraft, determining a hypersonic aircraft collaborative time planning target, and flight process constraint conditions and terminal constraint conditions;
determining course angle corridor and roll angle overturning logic according to the hypersonic aircraft collaborative time planning target, the flight process constraint condition and the terminal constraint condition;
according to course angle corridor and roll angle overturning logic, calculating a transverse cooperative time adjustment factor in transverse and lateral guidance;
calculating a roll angle profile in longitudinal guidance according to the transverse cooperative time adjustment factor;
determining a deep learning framework based on a transducer network according to a transverse cooperative time adjustment factor in transverse lateral guidance and a roll angle profile in longitudinal guidance; the deep learning framework based on the Transformer network is used for planning hypersonic aircraft tracks on line so as to realize intelligent time collaborative guidance of the hypersonic aircraft.
2. The method for intelligent time collaborative guidance of multiple hypersonic aircrafts according to claim 1, wherein the goal of collaborative time planning of multiple hypersonic aircrafts is to consider M hypersonic aircrafts, and for any ith hypersonic aircraft, if the ith hypersonic aircraft arrives at a terminal areaTime of day of domainIt is considered that M hypersonic aircrafts achieve the goal of time coordination.
3. The method for intelligent time collaborative guidance of a hypersonic vehicle according to claim 1, wherein the flight process constraints include an overload constraint, a heat flux density constraint, a dynamic pressure constraint, and a quasi-equilibrium glide constraint; the terminal constraint conditions comprise a terminal to-be-flown course constraint condition, a longitude and latitude constraint condition, a time constraint condition, a height constraint condition and a course angle constraint condition.
4. The method for intelligent time collaborative guidance of a hypersonic vehicle according to claim 1 wherein the heading angle corridor and roll angle flipping logic is:
wherein Deltapsi is i =ψ i -ψ LOS,i Heading angle deviation of ith hypersonic aircraft, psi i Heading angle psi of ith hypersonic aircraft LOS,i Viewing angle, Δψ, of an object for an ith hypersonic aircraft max,i As the upper boundary of the heading angle corridor, deltapsi min,i Sigma is the lower boundary of the course angle corridor p,i For the roll angle in the last guidance round, sgn (σ i ) Is the sign of the roll angle in the current guidance round.
5. The method for intelligent time collaborative guidance of a hypersonic vehicle according to claim 1, wherein the calculating of the lateral collaborative time adjustment factor in lateral guidance according to heading angle corridor and roll-over logic comprises:
and calculating a transverse collaborative time adjustment factor in transverse and lateral guidance by utilizing a Newton iteration method according to the course angle corridor and the roll angle overturning logic.
6. The method for intelligent time collaborative guidance of a hypersonic aircraft according to claim 1, characterized in that determining a deep learning framework based on a Transformer network according to a lateral collaborative time adjustment factor in lateral guidance and a roll angle profile in longitudinal guidance, in particular comprises:
and training the deep learning network based on the transducer network according to the transverse collaborative time adjustment factor in transverse lateral guidance and the track generated by the roll angle section in longitudinal guidance as a training set, so as to obtain the deep learning framework based on the transducer network.
7. An intelligent time cooperative guidance system for a hypersonic aircraft, comprising:
the dynamic model and kinematic model building module is used for building a dynamic model and a kinematic model of the hypersonic aircraft;
the target and constraint condition determining module is used for determining a multi-hypersonic aircraft collaborative time planning target, a flight process constraint condition and a terminal constraint condition according to a dynamics model and a kinematic model of the hypersonic aircraft;
the course angle corridor and roll angle overturning logic determining module is used for determining course angle corridor and roll angle overturning logic according to the hypersonic aircraft collaborative time planning target, flight process constraint conditions and terminal constraint conditions;
the transverse cooperative time adjustment factor calculation module is used for calculating a transverse cooperative time adjustment factor in transverse and lateral guidance according to the course angle corridor and the roll angle overturning logic;
the roll angle profile calculation module is used for calculating a roll angle profile in longitudinal guidance according to the transverse cooperative time adjustment factor;
a deep learning frame determination module based on a transform network, which is used for determining a deep learning frame based on the transform network according to a transverse cooperative time adjustment factor in transverse lateral guidance and a roll angle section in longitudinal guidance; the deep learning framework based on the Transformer network is used for planning hypersonic aircraft tracks on line so as to realize intelligent time collaborative guidance of the hypersonic aircraft.
8. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform a method of intelligent time co-guidance of a hypersonic flight vehicle according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310586938.5A CN116560403A (en) | 2023-05-24 | 2023-05-24 | Intelligent time collaborative guidance method, system and equipment for hypersonic aircraft |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310586938.5A CN116560403A (en) | 2023-05-24 | 2023-05-24 | Intelligent time collaborative guidance method, system and equipment for hypersonic aircraft |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116560403A true CN116560403A (en) | 2023-08-08 |
Family
ID=87498037
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310586938.5A Pending CN116560403A (en) | 2023-05-24 | 2023-05-24 | Intelligent time collaborative guidance method, system and equipment for hypersonic aircraft |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116560403A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117786534A (en) * | 2024-01-22 | 2024-03-29 | 哈尔滨工业大学 | Hypersonic aircraft motion behavior recognition method and system based on deep learning |
-
2023
- 2023-05-24 CN CN202310586938.5A patent/CN116560403A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117786534A (en) * | 2024-01-22 | 2024-03-29 | 哈尔滨工业大学 | Hypersonic aircraft motion behavior recognition method and system based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Karimi et al. | Optimal maneuver-based motion planning over terrain and threats using a dynamic hybrid PSO algorithm | |
CN106444799A (en) | Quadrotor unmanned plane control method based on fuzzy expansion state observer and adaptive sliding formwork | |
Hafer et al. | Sensitivity methods applied to orbital pursuit evasion | |
CN114253296B (en) | Hypersonic aircraft airborne track planning method and device, aircraft and medium | |
CN105159305A (en) | Four-rotor flight control method based on sliding mode variable structure | |
Wang et al. | Nonlinear aeroelastic control of very flexible aircraft using model updating | |
CN113126643A (en) | Intelligent robust reentry guidance method and system for hypersonic aircraft | |
CN109871031A (en) | A kind of method for planning track of fixed-wing unmanned plane | |
CN112631316B (en) | Limited time control method of variable-load quad-rotor unmanned aerial vehicle | |
CN110276144A (en) | A kind of VTOL vehicle aerodynamic parameter on-line identification method | |
CN116560403A (en) | Intelligent time collaborative guidance method, system and equipment for hypersonic aircraft | |
CN113268084B (en) | Intelligent fault-tolerant control method for unmanned aerial vehicle formation | |
CN112327926B (en) | Self-adaptive sliding mode control method for unmanned aerial vehicle formation | |
CN111813146A (en) | Reentry prediction-correction guidance method based on BP neural network prediction voyage | |
CN104536448B (en) | Backstepping based control method for unmanned-plane attitude system | |
CN116680509A (en) | Dynamic matching method for multi-spacecraft escape-tracking game task | |
Lyu et al. | Dynamic surface control design of post-stall maneuver under unsteady aerodynamics | |
Wang et al. | Intelligent control of air-breathing hypersonic vehicles subject to path and angle-of-attack constraints | |
US11029709B1 (en) | Adaptive wind estimation, trajectory generation, and flight control for aerial systems using motion data | |
CN106292297A (en) | Based on PID controller and the attitude control method of L1 adaptive controller | |
Yang et al. | Online midcourse guidance method for boost phase interception via adaptive convex programming | |
CN114815878B (en) | Hypersonic aircraft collaborative guidance method based on real-time optimization and deep learning | |
Xian et al. | An Intelligent Attitude Control Method for UAV Based on DDPG Algorithm | |
CN115857548A (en) | Terminal guidance law design method based on deep reinforcement learning | |
CN112506209B (en) | Reentry vehicle prediction control method based on self-adaptive prediction period |
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 |