CN114781275A - Artificial intelligence based fuel control method, device and medium for spacecraft orbit interception - Google Patents

Artificial intelligence based fuel control method, device and medium for spacecraft orbit interception Download PDF

Info

Publication number
CN114781275A
CN114781275A CN202210558104.9A CN202210558104A CN114781275A CN 114781275 A CN114781275 A CN 114781275A CN 202210558104 A CN202210558104 A CN 202210558104A CN 114781275 A CN114781275 A CN 114781275A
Authority
CN
China
Prior art keywords
spacecraft
orbit
sampling moment
maneuvering
information
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.)
Granted
Application number
CN202210558104.9A
Other languages
Chinese (zh)
Other versions
CN114781275B (en
Inventor
吴宝林
丁学良
戴瀚苏
马军
武文斌
许闯
李化义
陈俊宇
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.)
Harbin Institute of Technology
Original Assignee
Harbin Institute of Technology
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 Harbin Institute of Technology filed Critical Harbin Institute of Technology
Priority to CN202210558104.9A priority Critical patent/CN114781275B/en
Publication of CN114781275A publication Critical patent/CN114781275A/en
Application granted granted Critical
Publication of CN114781275B publication Critical patent/CN114781275B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The embodiment of the invention discloses a fuel control method, a device and a medium for spacecraft orbit interception based on artificial intelligence; the method can comprise the following steps: recursion is carried out through a set high-precision orbit dynamics model, and orbit information respectively corresponding to each sampling moment of the task spacecraft and the target spacecraft in a preset time period is obtained; aiming at each sampling moment, calculating by utilizing the Lambert problem under a two-body condition according to the orbit information of the task spacecraft at each sampling moment and the orbit information of the target spacecraft after the transfer time period is added at each sampling moment, and obtaining the orbit maneuvering control pulse corresponding to each sampling moment; constructing a training data set according to the orbit information of the task spacecraft at each sampling moment, the orbit information of the target spacecraft after the transfer time period is increased at each sampling moment and the maneuvering pulse corresponding to each sampling moment; training a preset neural network model by using a training data set to obtain a fitting function of the corresponding relation between the track information and the maneuvering pulse; and calculating to obtain the orbit maneuvering control pulse with the optimal fuel in the set maneuvering time by the on-satellite system of the mission spacecraft according to the fitting function.

Description

Artificial intelligence based fuel control method, device and medium for spacecraft orbit interception
Technical Field
The embodiment of the invention relates to the technical field of spacecraft control, in particular to a fuel control method, a device and a medium for spacecraft orbit interception based on artificial intelligence.
Background
For cooperative or non-cooperative target spacecraft to operate in space, close range observations are often required for them due to mission needs. Such observation tasks often do not require the mission spacecraft and the target spacecraft to be relatively stationary in space, so such observation tasks can be considered essentially an interception problem. Then, for the problem of orbit interception in a specific time period, the conventional scheme adopts a lambert traversal algorithm at present, but the algorithm has the disadvantages of large calculation amount and low calculation efficiency, so that the application is very limited under the condition of low calculation power of an on-satellite system.
Disclosure of Invention
In view of this, embodiments of the present invention are intended to provide a method, an apparatus, and a medium for controlling fuel for spacecraft orbit interception based on artificial intelligence; the calculation amount can be reduced, the calculation efficiency can be improved, and the method is more suitable for a satellite system; in addition, the required maneuvering control pulse can be accurately and reliably obtained to carry out accurate track interception control.
The technical scheme of the embodiment of the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a fuel control method for spacecraft orbit interception based on artificial intelligence, where the method includes:
recursion is carried out through a set high-precision orbit dynamics model, and orbit information respectively corresponding to each sampling moment of the task spacecraft and the target spacecraft in a preset time period is obtained;
aiming at each sampling moment, calculating by utilizing a Lambert problem under a two-body condition according to the orbit information of the mission spacecraft at each sampling moment and the orbit information of the target spacecraft after a transfer time period is added at each sampling moment, and obtaining an orbit maneuvering control pulse corresponding to each sampling moment;
constructing a training data set according to the orbit information of the task spacecraft at each sampling moment, the orbit information of the target spacecraft at each sampling moment after a transfer time period is added, and the maneuvering pulse corresponding to each sampling moment;
training a preset neural network model by using the training data set to obtain a fitting function of the corresponding relation between the track information and the maneuvering pulse;
and the on-satellite system of the mission spacecraft calculates and obtains the orbit maneuvering control pulse with the optimal fuel in the set maneuvering time according to the fitting function.
In a second aspect, an embodiment of the present invention provides a fuel control device based on artificial intelligence spacecraft orbit interception, including: a recursion part, a Lambert resolving part, a construction part, a neural network training part and a calculation part; wherein the content of the first and second substances,
the recursion part is configured to recur through a set high-precision orbit dynamics model to obtain orbit information corresponding to each sampling moment of the task spacecraft and the target spacecraft in a preset time period;
the Lambert resolving part is configured to, for each sampling moment, obtain an orbital maneuver control pulse corresponding to each sampling moment by resolving the Lambert problem under a two-body condition according to the orbit information of the mission spacecraft at each sampling moment and the orbit information of the target spacecraft at each sampling moment after a transfer time period is added;
the construction part is configured to construct a training data set according to the orbit information of the task spacecraft at each sampling moment, the orbit information of the target spacecraft after a transfer time period is added at each sampling moment and the maneuvering pulse corresponding to each sampling moment;
the neural network training part is configured to train a preset neural network model by using the training data set to obtain a fitting function of the corresponding relation between the track information and the maneuvering pulse;
and the calculating part comprises an on-satellite system of the mission spacecraft and is used for calculating and obtaining the orbit maneuvering control pulse with optimal fuel in the set maneuvering time according to the fitting function.
In a third aspect, an embodiment of the present invention provides a computing device, where the computing device includes: a communication interface, a memory, and a processor; wherein, the first and the second end of the pipe are connected with each other,
the communication interface is used for receiving and sending signals in the process of receiving and sending information with other external network elements;
the memory for storing a computer program operable on the processor;
the processor is configured to execute the steps of the artificial intelligence based spacecraft orbit intercept fuel control method of the first aspect when running the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium, where the computer storage medium stores an artificial intelligence based spacecraft orbit interception fuel control program, and when the artificial intelligence based spacecraft orbit interception fuel control program is executed by at least one processor, the steps of the artificial intelligence based spacecraft orbit interception fuel control method in the first aspect are implemented.
The embodiment of the invention provides a fuel control method, a device and a medium for spacecraft orbit interception based on artificial intelligence; pre-calculating according to the orbit information of the task spacecraft and the target spacecraft obtained by high-precision orbit forecasting to obtain a data set; and then, training a neural network by using the data set to obtain a fitting function so as to achieve a high-precision fitting effect, and finally performing orbit interception calculation on the on-board system by using the fitting function, so that complicated and large-calculation-amount Lambert problem calculation does not need to be performed on the on-board system, the calculation efficiency is improved, the calculation amount is reduced, and the required maneuvering control pulse can be accurately and reliably obtained under the condition that the calculation resources of the on-board system are limited so as to perform accurate orbit interception control.
Drawings
Fig. 1 is a schematic flow chart of a fuel control method for spacecraft orbit interception based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a conventional coordinate system provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of a position error corresponding to an x coordinate axis according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a position error corresponding to a y coordinate axis according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a position error corresponding to a z coordinate axis according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a rendezvous process of a spacecraft based on Lambert theory according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an elliptical transfer orbit provided by an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a BP neural network according to an embodiment of the present invention;
FIG. 9 is a graph I of the training effect of the BP neural network model according to the embodiment of the present invention;
fig. 10 is a diagram illustrating a training effect of the BP neural network model according to the embodiment of the present invention;
fig. 11 is a third graph illustrating the training effect of the BP neural network model according to the embodiment of the present invention;
FIG. 12 is a schematic diagram illustrating a control effect after modification according to an embodiment of the present invention;
fig. 13 is a schematic composition diagram of a fuel control device for artificial intelligence-based spacecraft orbit interception according to an embodiment of the present invention;
FIG. 14 is a schematic diagram of another fuel control device based on artificial intelligence spacecraft orbit interception according to an embodiment of the present invention;
fig. 15 is a schematic hardware structure diagram of a computing device according to an embodiment of the present invention.
Detailed Description
The technical solution in 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.
Referring to fig. 1, a fuel control method based on artificial intelligence spacecraft orbit interception provided by an embodiment of the invention is shown, and the method includes:
s101: recursion is carried out through a set high-precision orbit dynamics model, and orbit information respectively corresponding to each sampling moment of the task spacecraft and the target spacecraft in a preset time period is obtained;
s102: aiming at each sampling moment, calculating by utilizing a Lambert problem under a two-body condition according to the orbit information of the mission spacecraft at each sampling moment and the orbit information of the target spacecraft after a transfer time period is added at each sampling moment, and obtaining an orbit maneuvering control pulse corresponding to each sampling moment;
s103: constructing a training data set according to the orbit information of the task spacecraft at each sampling moment, the orbit information of the target spacecraft after a transfer time period is added at each sampling moment and the maneuvering pulse corresponding to each sampling moment;
s104: training a preset neural network model by using the training data set to obtain a fitting function of the corresponding relation between the track information and the maneuvering pulse;
s105: and the on-satellite system of the mission spacecraft calculates and obtains the orbit maneuvering control pulse with the optimal fuel in the set maneuvering time according to the fitting function.
According to the technical scheme, pre-calculation is carried out according to the orbit information of the task spacecraft and the target spacecraft, which is obtained by high-precision orbit forecasting, so that a data set is obtained; and then, training a neural network by using the data set to obtain a fitting function so as to achieve a high-precision fitting effect, and finally using the fitting function to perform orbit interception calculation on the satellite system, so that complicated and large-computation-amount Lambert problem solution is not required to be performed on the satellite system, the calculation efficiency is improved, the computation amount is reduced, and the required maneuvering control pulse can be accurately and reliably obtained under the condition that the computation resources of the satellite system are limited so as to perform accurate orbit interception control.
For the technical solution shown in fig. 1, in some implementations, to further improve the accuracy of the track interception control, the method further includes:
and correcting the rail maneuvering control pulse with the optimal fuel according to the high-precision rail dynamics model so as to improve the accuracy of the intercepting maneuvering control.
For the above technical solution, in some possible implementation manners, the high-precision orbit dynamics model is as shown in formula 1:
Figure BDA0003653133690000051
wherein v isx、vy、vzRespectively representing the speed of the mission spacecraft or the target spacecraft in the directions of x, y and z axes under an earth inertial coordinate system; x, y and z respectively represent the positions of the task spacecraft or the target spacecraft in the directions of the x axis, the y axis and the z axis under the earth inertial coordinate system; a isx、ay、azRespectively representing the mission spacecraft or the target spaceThe acceleration of the device in the directions of x, y and z axes under the earth inertial coordinate system; superscript · denotes the first derivative operator; r represents the distance of the task spacecraft or the target spacecraft centroid to the geocentric; μ represents an earth gravity constant; f. ofx、fy、fzRespectively representing components of acceleration generated by non-conservative force applied to the task spacecraft or the target spacecraft in the directions of x, y and z axes in an earth inertial coordinate system; interference items contained in the non-conservative force borne by the mission spacecraft or the target spacecraft at least comprise perturbation interference of earth aspheric gravitation, perturbation interference of a fourth-order harmonic item and perturbation interference of atmospheric resistance.
For the above implementation, in particular, in general, in the study of spacecraft attitude and orbit dynamics, common coordinate systems include an Earth-Centered Inertial coordinate system (ECI), an Earth-Centered Earth-Fixed coordinate system (ECEF), a spacecraft orbit coordinate system (LVLH), and a spacecraft body coordinate system, where coordinate axes corresponding to the respective coordinate systems are shown in fig. 2. In FIG. 2, XJ、YJ、ZJIs a coordinate axis schematic of an ECI coordinate system which can also be called as a J2000.0 coordinate system; xE、YE、ZEIs indicated by coordinate axes of an ECEF coordinate system; xL、YL、ZLIt is indicated by the coordinate axes of the LVLH coordinate system.
In the embodiment of the present invention, the ECI coordinate system is preferred, and then the orbit dynamics equation of the mission spacecraft or the target spacecraft in the coordinate system is shown in formula 1. For equation 1, in detail, the earth is generally assumed to be a uniform sphere, and at this time, the gravity of the earth on the spacecraft is only inversely proportional to the square of the earth center distance and is independent of the longitude and latitude of the spacecraft. In fact, the mass of the earth is unevenly distributed, it is an irregular oblate spheroid whose equatorial radius is not equal to its polar axis, and the equator is slightly elliptical, resulting in the tangential and normal directions of the spacecraft orbit being simultaneously acted on by gravity, these factors being called the earth's non-spherical gravitational perturbation. Therefore, the equipotential surface of the earth gravity does not coincide with the isocenter surface, and a series of spherical harmonic functions, which are called perturbation functions, need to be added to the gravitational potential function.
For near-earth orbit spacecraft, the perturbation of the earth mainly occurs in the flat shape of the earth, in the earth gravitational potential function, the influence of field harmonic terms is generally ignored, only the gravitational potential function with harmonic terms is considered, and the 4-order harmonic terms (J2, J3, J4) are considered in the embodiment of the invention. Wherein, f can also be usedeRepresenting other disturbances than the perturbation of the harmonic terms.
Secondly, at medium and low orbital altitude, the atmospheric density is lower than that of the earth surface, but when the spacecraft flies in the atmosphere at a higher speed for a long time, the accumulation of atmospheric resistance finally reflects the influence on the orbital perturbation of the spacecraft, thereby causing the divergence of the orbital motion of the spacecraft. According to the embodiment of the invention, a resistance model is established by rubbing the surface of the spacecraft with atmospheric molecules, and the resistance model generated by the atmosphere is obtained as shown in a formula 2:
Figure BDA0003653133690000071
wherein: ρ is the atmospheric density; vRIs the velocity of the atmosphere relative to the spacecraft; cDThe resistance coefficient is generally 2.2-2.6; a. thePIs the area of the incident flow surface; cPThe vector from the center of mass to the center of pressure of the spacecraft; v is the unit vector of the incoming flow direction.
In addition, in the embodiment of the present invention, it is preferable to use the "WGS 84-EGM 96" earth gravitational field model, and the "US Standard 1976" model is used for atmospheric resistance.
Based on the model and the orbit dynamics equation, the orbit information shown in table 1 is taken as an example of the initial orbit parameter of the spacecraft in the embodiment of the present invention.
Initial time UTC 2010-01-01 04：00：00
Rx/km 773.923949
Ry/km -3514.073825
Rz/km 5506.746152
vx/km×s-1 -0.578737
vy/km×s-1 6.580464
vz/km×s-1 4.11792
Based on the initial parameters of the orbit shown in table 1, the orbit information corresponding to each sampling time of the task spacecraft and the target spacecraft in a preset time period can be obtained according to the orbit dynamics equation and the model recursion. If the preset time period is set to be one day, the position errors corresponding to the x, y and z coordinate axes are shown in fig. 3 to 5, respectively, when the orbit information obtained by recursion is compared with the orbit information obtained by simulation of satellite simulation Software (STK). As can be seen from fig. 3 to 5, within one day, the position error between the orbit information obtained by recursion and the orbit information obtained by simulation of satellite simulation Software (STK) is less than 1.5km, and the accuracy requirement is met by the degree of improvement.
For the technical solution shown in fig. 1, in some possible implementations, the obtaining, for each sampling time, the orbital maneuver control pulse corresponding to each sampling time by using lambert problem solution under a two-body condition according to the orbit information of the mission spacecraft at each sampling time and the orbit information of the target spacecraft at each sampling time after a transfer time period is added includes:
for each of the sampling instants, performing the following steps:
taking the orbit information of the task spacecraft at the current sampling moment as an initial starting point P1And increasing the transfer time period t of the target spacecraft at the current sampling momentfThe latter track information is used as an end point P2；
Setting the initial starting point P1And said end point P2Are respectively r1And r2The focus of the elliptical orbit is located at the center of the earth, and the initial starting point P1And said end point P2At times of t respectively1And t2The transfer angle is theta;
according to Lambert's theorem, the transfer time t on the elliptical transfer orbitfSatisfies formula 2:
tf＝F(a,r1+r2,c) (2)
wherein a represents the semi-circumference of the ellipse transfer orbit, c represents the distance between the initial starting point and the end point, r1+r2Representing the sum of the distances from the initial starting point and the end point to the focus of the ellipse transfer track respectively;
from equation 2, the Lambert equation shown in equation 3 is determined as:
Figure BDA0003653133690000081
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003653133690000082
s＝(r1+r2+c)/2；
setting up
Figure BDA0003653133690000083
And let α, β, λ be lagrange parameters, then there are:
Figure BDA0003653133690000084
wherein, tmRepresents the minimum energy transfer time and
Figure BDA0003653133690000085
when a ismWhen the ratio is equal to s/2,
Figure BDA0003653133690000086
based on the parameters and the transformation, the Lambert flight theorem is determined as shown in formula 4:
Figure BDA0003653133690000087
wherein sgn (·) is a sign function;
for a set track transfer time tf1Let f (λ) be tf1-tfSolving the equation f (λ) ═ 0 by using a newton iteration method, an iterative formula can be obtained as shown in formula 5:
Figure BDA0003653133690000091
when | λn+1-λnWhen | < epsilon, the solution lambda of the equation can be obtainedn+1＝λn；
Set f' (λ)n) Is the derivative of f (λ) ═ 0 with respect to λ, where λ ═ λnThe value of (d) is f' (λ)n) The expression is shown in formula 6:
Figure BDA0003653133690000092
based on f (λ) being a monotonic function of λ and the unique solution for equation f (λ) ═ 0, the number of tracks transferred to the track is related to λ by the following equation 7:
Figure BDA0003653133690000093
according to the number of the transfer tracks obtained by the formula 7, calculating to obtain the initial speed v of the aircraft on the transfer tracksr1Combined with known initial start and end velocities v1And calculating according to the formula 8 to obtain the braking speed v as follows:
v＝vr1-v1 (8)
wherein the braking speed is used to determine a maneuvering pulse intercepted by the track.
For the above implementation, the Lambert (Lambert) problem refers in particular to the two-point boundary value problem under fixed time constraints, which is a classical and fundamental problem of spacecraft orbit dynamics, commonly applied in the field of space technology. The specific description of this problem is: in space, the starting point position is recorded as P1The end position is P2Initial position vector r relative to center of gravity1And a terminal position vector r2And (5) determining. Let transfer time tfFixing, finding conic section transfer orbit to make spacecraft from initial point position P1Starting at elapsed time tfThen, just reach the target position P2。
The spacecraft rendezvous process based on the Lambert theory is shown in fig. 6. The starting point of the aircraft is located at the initial orbit P1Along the transfer track, over a time tfFly to P at target orbit2And (4) point. As shown in FIG. 6, the initial starting point P1And end point P2Are respectively r1And r2The focus of the elliptical transfer orbit shown in FIG. 7 is at the geocentric, initial starting point P1And end point P2At times t respectively1And t2The transfer angle is θ. According to Lambert's theorem, as shown in equation 1, on an elliptical transfer trackTwo-point transfer time tfWith only the semi-major axis a of the ellipse, the sum of the radii of the two points (r)1+r2) And the transfer angle theta. Furthermore, for the above implementation, when amWhen s/2, it corresponds to a special ellipse transfer orbit. The values of α and β at this time are: alpha (alpha) ("alpha")mN and
Figure BDA0003653133690000101
it should be noted that, through the implementation manner, the maneuvering pulse corresponding to each sampling moment can be obtained by solving according to the orbit information of the mission spacecraft at each sampling moment and the orbit information of the target spacecraft after the transfer time period is added at each sampling moment. These data can be used as a training data set for subsequently training the neural network.
Based on this, in some examples, the constructing a training data set according to the orbit information of the mission spacecraft at each sampling moment, the orbit information of the target spacecraft at each sampling moment after a transfer time period is added, and the maneuvering pulse corresponding to each sampling moment includes:
constructing an input data set by the orbit information of the task spacecraft at each sampling moment and the orbit information of the target spacecraft at each sampling moment after a transfer time period is added;
and constructing an output data set by the maneuvering pulse corresponding to each sampling moment.
Based on the above examples, in some examples, the training a preset neural network model with the training data set to obtain a fitting function of correspondence between orbit information and maneuvering pulses includes:
initializing a neural network model; the input end of the neural network model is 12-dimensional, and the output end of the neural network model is 3-dimensional;
for each sampling instant, inputting trajectory information in an input dataset to the neural network model to obtain model output data;
comparing the model output data with the maneuvering pulses corresponding to the sampling moments in the output data set, and training parameters of the neural network model according to a comparison result until the comparison result meets a set precision requirement;
and determining the trained neural network model as a fitting function of the corresponding relation between the orbit information and the maneuvering pulse.
For the above example, in particular, the BP neural network is a relatively classical one, which is composed of an input layer, a hidden layer, and an output layer. In the embodiment of the present invention, a typical BP neural network model as shown in fig. 8 is preferably used for training, and for the neural network model, two pieces of information, that is, the orbit information of the mission spacecraft at each sampling time and the orbit information of the target spacecraft at each sampling time after a transfer time period is added, are input, and the maneuvering pulse information obtained through calculation by the neural network is output. In the BP learning algorithm, the weight adjustment formulas of the respective layers are the same in form and are determined by 3 factors, namely: learning rate, error signal output by the layer, and input signal of the layer. The error signal of the input layer is related to the difference between the expected output and the actual output of the network, the output error is directly reflected, and the error signal of each hidden layer is related to the error signal of each previous layer and is transmitted from the output layer to the other layer.
The format of the training data in the training data set is: inputting the orbit information (6 dimensions) of a task spacecraft at a certain moment and the orbit information (6 dimensions) of a target spacecraft after the moment plus a transfer time period; the maneuver pulse (3D) at this time is output. That is, the fitting function corresponding to the neural network model obtained by the final training is a function with 12-dimensional input and 3-dimensional output.
For the above technical solution and implementation and examples thereof, the orbit information of the task spacecraft a and the target spacecraft B is set as shown in table 2:
Figure BDA0003653133690000111
by performing orbit recursion and obtaining a training data set according to S101 in a day, training is performed using the BP neural network model, and the finally obtained training effect graphs are shown in fig. 9 to 11. FIG. 9 shows the training state of the neural network, the first sub-graph represents the descending gradient of the function fitted by the neural network to the training set, the second sub-graph represents the mean square error of the test, and the third sub-graph represents the successful verification round with the fitted neural network; fig. 10 is an error histogram with 20 bins, which is a more common illustration showing training effects in neural network training, and the more concentrated the histogram, the better the proving effect; fig. 11 represents the fitting effect of the fitted neural network function on the test set, and the verification points are combined near the fitting line, which shows that the fitting effect of the neural network fitting function is good.
In some examples, after the maneuver pulse is calculated according to the trained neural network model, the calculation result of the neural network model may be modified in consideration of the high-precision orbit dynamics model, and the control effect of the finally obtained control pulse is shown in fig. 12, which shows a curve of the relative distance between the mission spacecraft (also referred to as a platform) and the target spacecraft (also referred to as a target) as a function of time, and as can be seen from the curve, the minimum distance between the mission spacecraft (also referred to as a platform) and the target spacecraft (also referred to as a target) is only 0.05521 km. The precision requirement of track interception is met.
Based on the same inventive concept of the foregoing technical solution, referring to fig. 13, there is shown a fuel control apparatus 130 based on artificial intelligence spacecraft orbit interception according to an embodiment of the present invention, where the apparatus 130 may include: a recursion part 1301, a Lambert solution part 1302, a construction part 1303, a neural network training part 1304 and a calculation part 1305; wherein, the first and the second end of the pipe are connected with each other,
the recursion part 1301 is configured to recur through a set high-precision orbit dynamics model to obtain orbit information corresponding to each sampling moment of the task spacecraft and the target spacecraft in a preset time period;
the lambert solution part 1302 is configured to, for each sampling time, obtain an orbital maneuver control pulse corresponding to each sampling time by using a lambert problem solution under a two-body condition according to the orbit information of the mission spacecraft at each sampling time and the orbit information of the target spacecraft at each sampling time after a transfer time period is added;
the constructing part 1303 is configured to construct a training data set according to the orbit information of the task spacecraft at each sampling moment, the orbit information of the target spacecraft at each sampling moment after a transfer time period is added, and the maneuvering pulse corresponding to each sampling moment;
the neural network training part 1304 is configured to train a preset neural network model by using the training data set to obtain a fitting function of the corresponding relationship between the orbit information and the maneuvering pulse;
the calculating part 1305, which includes the on-board system of the mission spacecraft, is configured to calculate and obtain a fuel-optimal orbital maneuver control pulse within a set maneuver time according to the fitting function.
In some examples, as shown in fig. 14, the apparatus 130 further includes a correction portion 1306 configured to correct the fuel-optimized rail maneuver control pulse in accordance with the high-precision rail dynamics model to improve the accuracy of the intercept maneuver control.
In some examples, the high-precision orbital dynamics model is shown in equation 1.
In some examples, the lambert resolving portion 1302 is configured to:
for each of the sampling instants, performing the following steps:
taking the orbit information of the task spacecraft at the current sampling moment as an initial starting point P1And increasing the transfer time period t of the target spacecraft at the current sampling momentfThe latter track information being the end point P2；
Setting the initial starting point P1And said end point P2Respectively is r1And r2The focus of the elliptical orbit is located at the geocentric, the initial starting point P1And said end point P2At times t respectively1And t2The transfer angle is theta;
according to Lambert's theorem, the transfer period t on an elliptical transfer orbitfSatisfies formula 2;
according to the formula 2, determining a Lambert formula shown in a formula 3;
setting up
Figure BDA0003653133690000131
And considering α, β, λ as lagrangian parameters, there are:
Figure BDA0003653133690000132
wherein, tmRepresents the minimum energy transfer time and
Figure BDA0003653133690000133
when a ismWhen the ratio is s/2, the ratio is,
Figure BDA0003653133690000134
based on the parameters and the transformation, determining that the Lambert flight theorem is shown as a formula 4;
for a set track transfer time tf1Let f (λ) be tf1-tfSolving the equation f (lambda) to be 0 by using a Newton iteration method to obtain an iteration formula shown in the formula 5;
when lambdan+1-λnWhen | < epsilon, the solution lambda of the equation can be obtainedn+1＝λn；
Set f' (λ)n) Is the derivative of f (λ) ═ 0 with respect to λ, where λ ═ λnThe value of (d) is f' (λ)n) The expression is shown in formula 6;
based on the fact that f (lambda) is a monotonous function of lambda and the equation f (lambda) is 0, the relation between the number of tracks of the transfer track and lambda is shown in the formula 7;
calculating to obtain the initial speed v of the aircraft on the transfer orbit according to the transfer orbit number obtained by the formula 7r1In combination with a known initialVelocity v of the starting and ending points1And calculating the braking speed v as v ═ vr1-v1(ii) a Wherein the braking speed is used to determine a maneuvering pulse intercepted by the track.
In some examples, the build portion 1303 is configured to:
constructing an input data set by using the orbit information of the task spacecraft at each sampling moment and the orbit information of the target spacecraft at each sampling moment after a transfer time period is added;
and constructing an output data set by using the maneuvering pulse corresponding to each sampling moment.
In some examples, the neural network training portion 1304 is configured to:
initializing a neural network model; the input end of the neural network model is 12-dimensional, and the output end of the neural network model is 3-dimensional;
for each sampling instant, inputting trajectory information in an input dataset to the neural network model to obtain model output data;
comparing the model output data with the maneuvering pulses corresponding to the sampling moments in the output data set, and training parameters of the neural network model according to a comparison result until the comparison result meets a set precision requirement;
and determining the trained neural network model as a fitting function of the corresponding relation between the orbit information and the maneuvering pulse.
It is understood that in this embodiment, "part" may be part of a circuit, part of a processor, part of a program or software, etc., and may also be a unit, and may also be a module or a non-modular.
In addition, each component in this embodiment may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware or a form of a software functional module.
Based on the understanding that the technical solution of the present embodiment essentially or partly contributes to the prior art, or all or part of the technical solution may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method of the present embodiment. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Therefore, the present embodiment provides a computer storage medium, which stores a fuel control program based on artificial intelligence spacecraft orbit interception, and when the fuel control program based on artificial intelligence spacecraft orbit interception is executed by at least one processor, the steps of the fuel control method based on artificial intelligence spacecraft orbit interception in the above technical solution are implemented.
Referring to fig. 15, a specific hardware structure of a computing device 150 capable of implementing the above-mentioned fuel control device 130 based on artificial intelligence spacecraft orbit interception according to an embodiment of the present invention is shown, wherein the computing device 150 may be a wireless device, a mobile or cellular phone (including a so-called smart phone), a Personal Digital Assistant (PDA), a video game console (including a video display, a mobile video game device, a mobile video conference unit), a laptop computer, a desktop computer, a television set-top box, a tablet computing device, an e-book reader, a fixed or mobile media player, etc. The computing device 150 includes: a communication interface 1501, a memory 1502, and a processor 1503; the various components are coupled together by a bus system 1504. It is understood that the bus system 1504 is used to enable connected communication between these components. The bus system 1504 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various busses are labeled in fig. 15 as the bus system 1504. Wherein, the first and the second end of the pipe are connected with each other,
the communication interface 1501 is configured to receive and transmit signals in the process of receiving and transmitting information with other external network elements;
the memory 1502 is used for storing a computer program capable of running on the processor 1503;
the processor 1503 is configured to execute the steps of the fuel control method based on artificial intelligence spacecraft orbit interception in the above technical solution when the computer program is run.
It will be appreciated that the memory 1502 in embodiments of the present invention can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of illustration and not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic random access memory (ddr Data Rate SDRAM, ddr SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 1502 of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
The processor 1503 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be implemented by instructions in the form of hardware integrated logic circuits or software in the processor 1503. The Processor 1503 may be a general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 1502, and the processor 1503 reads the information in the memory 1502 and performs the steps of the above method in combination with the hardware thereof.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
It is understood that the above exemplary technical solutions of the fuel control device 130 and the computing device 150 based on artificial intelligence spacecraft orbit interception belong to the same concept as the technical solutions of the fuel control method based on artificial intelligence spacecraft orbit interception, and therefore, the details of the above technical solutions of the fuel control device 130 and the computing device 150 based on artificial intelligence spacecraft orbit interception, which are not described in detail, can be referred to the description of the technical solutions of the fuel control method based on artificial intelligence spacecraft orbit interception. The embodiments of the present invention will not be described in detail herein.
It should be noted that: the technical schemes described in the embodiments of the present invention can be combined arbitrarily without conflict.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (9)

1. A fuel control method based on artificial intelligence spacecraft orbit interception is characterized by comprising the following steps:
recursion is carried out through a set high-precision orbit dynamics model, and orbit information respectively corresponding to each sampling moment of the task spacecraft and the target spacecraft in a preset time period is obtained;
aiming at each sampling moment, calculating by utilizing a Lambert problem under a two-body condition according to the orbit information of the mission spacecraft at each sampling moment and the orbit information of the target spacecraft after a transfer time period is added at each sampling moment, and obtaining an orbit maneuvering control pulse corresponding to each sampling moment;
constructing a training data set according to the orbit information of the task spacecraft at each sampling moment, the orbit information of the target spacecraft after a transfer time period is added at each sampling moment and the maneuvering pulse corresponding to each sampling moment;
training a preset neural network model by using the training data set to obtain a fitting function of the corresponding relation between the track information and the maneuvering pulse;
and the on-satellite system of the mission spacecraft calculates and obtains the orbit maneuvering control pulse with the optimal fuel in the set maneuvering time according to the fitting function.
2. The method of claim 1, further comprising:
and correcting the rail maneuvering control pulse with the optimal fuel according to the high-precision rail dynamics model so as to improve the precision of the interception maneuvering control.
3. The method of any one of claims 1 to 2, wherein the high-precision orbital dynamics model is represented by formula 1:
Figure FDA0003653133680000021
wherein v isx、vy、vzRespectively representing the speed of the mission spacecraft or the target spacecraft in the directions of x, y and z axes under an earth inertial coordinate system; x, y and z respectively represent the positions of the task spacecraft or the target spacecraft in the directions of x, y and z axes under the inertial coordinate system of the earth; a isx、ay、azRespectively representing the acceleration of the task spacecraft or the target spacecraft in the directions of x, y and z axes under an earth inertial coordinate system; superscript · denotes the first derivative operator; r represents the distance of the task spacecraft or the target spacecraft centroid to the geocentric; μ represents an earth gravity constant; f. ofx、fy、fzRespectively representing the acceleration of the mission spacecraft or the target spacecraft caused by non-conservative forces on the earth's inertial seatThe components in the x, y and z axis directions under the mark system; interference items contained in the non-conservative force borne by the mission spacecraft or the target spacecraft at least comprise perturbation interference of earth aspheric gravitation, perturbation interference of a fourth-order harmonic item and perturbation interference of atmospheric resistance.
4. The method according to claim 1, wherein the obtaining, for each sampling time, the orbital maneuver control pulse corresponding to each sampling time by using a Lambert problem solution under a two-body condition according to the orbit information of the mission spacecraft at each sampling time and the orbit information of the target spacecraft at each sampling time after a transfer time period is added comprises:
for each of the sampling instants, performing the steps of:
taking the orbit information of the task spacecraft at the current sampling moment as an initial starting point P1And increasing the transfer time period t of the target spacecraft at the current sampling momentfThe latter track information being the end point P2；
Setting the initial starting point P1And said end point P2Are respectively r1And r2The focus of the elliptical orbit is located at the geocentric, the initial starting point P1And said end point P2At times t respectively1And t2The transfer angle is theta;
according to Lambert's theorem, the transfer period t on an elliptical transfer orbitfSatisfies formula 2:
tf＝F(a,r1+r2,c) (2)
wherein a represents the semi-circumference of the ellipse transfer orbit, c represents the distance between the initial starting point and the end point, r1+r2Representing the sum of the distances from the initial starting point and the end point to the focus of the ellipse transfer orbit respectively;
from equation 2, the Lambert equation shown in equation 3 is determined as:
Figure FDA0003653133680000031
wherein, the first and the second end of the pipe are connected with each other,
Figure FDA0003653133680000032
s＝(r1+r2+c)/2；
setting up
Figure FDA0003653133680000033
And considering α, β, λ as lagrangian parameters, there are:
Figure FDA0003653133680000034
wherein, tmRepresents the minimum energy transfer time and
Figure FDA0003653133680000035
when a ismWhen s/2, αm＝π,
Figure FDA0003653133680000036
Based on the parameters and the transformation, the Lambert flight theorem is determined as shown in formula 4:
Figure FDA0003653133680000037
wherein sgn (·) is a sign function;
for a set track transfer time tf1Let f (λ) be tf1-tfSolving the equation f (λ) by newton iteration to obtain an iterative formula shown in formula 5:
Figure FDA0003653133680000038
when lambdan+1-λnWhen | < epsilon, the solution lambda of the equation can be obtainedn+1＝λn；
Set f' (λ)n) Is the derivative of f (λ) ═ 0 with respect to λ, where λ ═ λnThe value of (b) is then f' (λ)n) The expression is shown in formula 6:
Figure FDA0003653133680000039
based on f (λ) being a monotonic function of λ and the unique solution for equation f (λ) ═ 0, the number of tracks transferred to the track is related to λ by the following equation 7:
Figure FDA0003653133680000041
calculating to obtain the initial speed v of the aircraft on the transfer orbit according to the transfer orbit number obtained by the formula 7r1Combined with known initial start and end velocities v1The braking speed v is calculated according to equation 8 as:
v＝vr1-v1 (8)
wherein the braking speed is used to determine the manoeuvre pulse intercepted by the rail.
5. The method according to claim 1, wherein the constructing a training data set according to the orbit information of the mission spacecraft at each sampling moment, the orbit information of the target spacecraft at each sampling moment after adding a transfer time period, and the maneuvering pulse corresponding to each sampling moment comprises:
constructing an input data set by the orbit information of the task spacecraft at each sampling moment and the orbit information of the target spacecraft at each sampling moment after a transfer time period is added;
and constructing an output data set by using the maneuvering pulse corresponding to each sampling moment.
6. The method according to claim 5, wherein training a predetermined neural network model using the training data set to obtain a fitting function of the correspondence between the orbit information and the maneuver pulse comprises:
initializing a neural network model; the input end of the neural network model is 12-dimensional, and the output end of the neural network model is 3-dimensional;
for each sampling instant, inputting trajectory information in an input dataset to the neural network model to obtain model output data;
comparing the model output data with the maneuvering pulses corresponding to the sampling moments in the output data set, and training parameters of the neural network model according to a comparison result until the comparison result meets a set precision requirement;
and determining the trained neural network model as a fitting function of the corresponding relation between the orbit information and the maneuvering pulse.
7. A fuel control device for artificial intelligence based spacecraft orbit interception, the device comprising: the system comprises a recursion part, a Lambert resolving part, a construction part, a neural network training part and a calculation part; wherein, the first and the second end of the pipe are connected with each other,
the recursion part is configured to recur through a set high-precision orbit dynamics model to obtain orbit information corresponding to each sampling moment of the task spacecraft and the target spacecraft in a preset time period;
the Lambert solution part is configured to obtain an orbital maneuver control pulse corresponding to each sampling moment by utilizing Lambert problem solution under a two-body condition according to the orbit information of the mission spacecraft at each sampling moment and the orbit information of the target spacecraft after a transfer time period is added at each sampling moment;
the constructing part is configured to construct a training data set according to the orbit information of the task spacecraft at each sampling moment, the orbit information of the target spacecraft at each sampling moment after a transfer time period is added, and the maneuvering pulse corresponding to each sampling moment;
the neural network training part is configured to train a preset neural network model by using the training data set to obtain a fitting function of the corresponding relation between the track information and the maneuvering pulse;
and the calculating part comprises an on-satellite system of the mission spacecraft and is used for calculating and obtaining the orbit maneuvering control pulse with optimal fuel in the set maneuvering time according to the fitting function.
8. A computing device, wherein the computing device comprises: a communication interface, a memory, and a processor; wherein, the first and the second end of the pipe are connected with each other,
the communication interface is used for receiving and sending signals in the process of receiving and sending information with other external network elements;
the memory for storing a computer program operable on the processor;
the processor, when running the computer program, is configured to perform the steps of the artificial intelligence based spacecraft orbit intercept fuel control method of any one of claims 1 to 6.
9. A computer storage medium, characterized in that the computer storage medium stores an artificial intelligence based spacecraft orbit intercept fuel control program that, when executed by at least one processor, implements the steps of the artificial intelligence based spacecraft orbit intercept fuel control method of any one of claims 1 to 6.
CN202210558104.9A 2022-05-19 2022-05-19 Fuel control method, device and medium for spacecraft orbit interception based on artificial intelligence Active CN114781275B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210558104.9A CN114781275B (en) 2022-05-19 2022-05-19 Fuel control method, device and medium for spacecraft orbit interception based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210558104.9A CN114781275B (en) 2022-05-19 2022-05-19 Fuel control method, device and medium for spacecraft orbit interception based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN114781275A true CN114781275A (en) 2022-07-22
CN114781275B CN114781275B (en) 2023-04-07

Family

ID=82407788

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210558104.9A Active CN114781275B (en) 2022-05-19 2022-05-19 Fuel control method, device and medium for spacecraft orbit interception based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN114781275B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116202535A (en) * 2022-12-28 2023-06-02 北京理工大学 Initial value intelligent optimized spacecraft angle measurement-only ultrashort arc initial orbit determination method

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109491406A (en) * 2019-01-22 2019-03-19 中国人民解放军战略支援部队航天工程大学 A kind of spacecraft evasion manoeuvre method based on energy consumption
CN110986974A (en) * 2019-10-28 2020-04-10 南京航空航天大学 Multi-spacecraft task intelligent planning and control method oriented to complex dynamic environment
CN111090941A (en) * 2019-12-17 2020-05-01 哈尔滨工业大学 Spacecraft optimal Lambert orbit rendezvous method based on multi-objective optimization algorithm
CN111753244A (en) * 2020-07-01 2020-10-09 哈尔滨工业大学 Newton iteration-based semi-major axis iteration space transfer track calculation method for Lambert orbital transfer problem
CN113060305A (en) * 2021-03-24 2021-07-02 哈尔滨工业大学 Track transfer method and device based on energy optimization and storage medium
CN113591403A (en) * 2021-09-28 2021-11-02 南京航空航天大学 Design method of spacecraft gravity-assist flight orbit
CN113955153A (en) * 2021-12-21 2022-01-21 南京航空航天大学 Continuous low-thrust rail transfer method with optimal fuel
CN114019995A (en) * 2021-11-09 2022-02-08 北京航空航天大学 Different-plane multi-target rapid fly-by trajectory planning method with optimal fuel
CN114355962A (en) * 2021-12-09 2022-04-15 北京航空航天大学 Close-range smooth approaching and maintaining control method for fuel optimization under time constraint
US20220147820A1 (en) * 2020-11-12 2022-05-12 Dalian University Of Technology Optimal rescue orbital elements online decision-making method based on rbfnn for launch vehicles under thrust drop fault

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109491406A (en) * 2019-01-22 2019-03-19 中国人民解放军战略支援部队航天工程大学 A kind of spacecraft evasion manoeuvre method based on energy consumption
CN110986974A (en) * 2019-10-28 2020-04-10 南京航空航天大学 Multi-spacecraft task intelligent planning and control method oriented to complex dynamic environment
CN111090941A (en) * 2019-12-17 2020-05-01 哈尔滨工业大学 Spacecraft optimal Lambert orbit rendezvous method based on multi-objective optimization algorithm
CN111753244A (en) * 2020-07-01 2020-10-09 哈尔滨工业大学 Newton iteration-based semi-major axis iteration space transfer track calculation method for Lambert orbital transfer problem
US20220147820A1 (en) * 2020-11-12 2022-05-12 Dalian University Of Technology Optimal rescue orbital elements online decision-making method based on rbfnn for launch vehicles under thrust drop fault
CN113060305A (en) * 2021-03-24 2021-07-02 哈尔滨工业大学 Track transfer method and device based on energy optimization and storage medium
CN113591403A (en) * 2021-09-28 2021-11-02 南京航空航天大学 Design method of spacecraft gravity-assist flight orbit
CN114019995A (en) * 2021-11-09 2022-02-08 北京航空航天大学 Different-plane multi-target rapid fly-by trajectory planning method with optimal fuel
CN114355962A (en) * 2021-12-09 2022-04-15 北京航空航天大学 Close-range smooth approaching and maintaining control method for fuel optimization under time constraint
CN113955153A (en) * 2021-12-21 2022-01-21 南京航空航天大学 Continuous low-thrust rail transfer method with optimal fuel

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
HONGYU LI 等: "Research on Cooperative Guidance and Control Method of Exoatmospheric Multi Interceptors", 《2021 IEEE INTERNATIONAL CONFERENCE ON UNMANNED SYSTEMS》 *
SIYUAN QIAO 等: "The Analysis of the Midcourse Missile Interception Based on the Microsatellite", 《2018 IEEE CSAA GUIDANCE, NAVIGATION AND CONTROL CONFERENCE》 *
刘二江: "GEO目标接近轨迹规划与控制方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *
王天梦: "空间站共轨飞行器补给任务轨道设计与优化", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *
高晓光 等: "基于混合优化算法的空间拦截轨道优化设计", 《北京航空航天大学学报》 *
黄勇等: "混合遗传算法在最优Lambert轨道转移设计中的应用", 《飞行力学》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116202535A (en) * 2022-12-28 2023-06-02 北京理工大学 Initial value intelligent optimized spacecraft angle measurement-only ultrashort arc initial orbit determination method
CN116202535B (en) * 2022-12-28 2024-01-19 北京理工大学 Initial value intelligent optimized spacecraft angle measurement-only ultrashort arc initial orbit determination method

Also Published As

Publication number Publication date
CN114781275B (en) 2023-04-07

Similar Documents

Publication Publication Date Title
Scorsoglio et al. Image-based deep reinforcement meta-learning for autonomous lunar landing
Xu et al. A cost-effective vehicle localization solution using an interacting multiple model− unscented Kalman filters (IMM-UKF) algorithm and grey neural network
CN110059439B (en) Spacecraft orbit determination method based on data driving
Takahashi et al. Autonomous exploration of a small near-earth asteroid
Ye et al. Single-satellite integrated navigation algorithm based on broadband LEO constellation communication links
CN114781275B (en) Fuel control method, device and medium for spacecraft orbit interception based on artificial intelligence
CN115314101B (en) Low-orbit communication satellite constellation rapid modeling method based on parallel computing
Lee et al. A robust terrain aided navigation using the Rao-Blackwellized particle filter trained by long short-term memory networks
Wang et al. A new tightly-coupled INS/CNS integrated navigation algorithm with weighted multi-stars observations
Liu et al. An ANN-based data fusion algorithm for INS/CNS integrated navigation system
CN115826611A (en) Orbit configuration control method, device and medium for satellite cluster under J2 perturbation
Stojanovski et al. Higher-order unscented estimator
Lu et al. Orbit determination for all-electric GEO satellites based on space-borne GNSS measurements
Li et al. Space noncooperative target trajectory tracking based on maneuvering parameter estimation
Crouse On measurement-based light-time corrections for bistatic orbital debris tracking
Heidrich et al. Optimal information filtering for robust aerocapture trajectory generation and guidance
Wang et al. Robust decentralised state estimation for formation flying spacecraft
Cui et al. Real-time navigation for Mars final approach using X-ray pulsars
Fraser Adaptive extended Kalman filtering strategies for autonomous relative navigation of formation flying spacecraft
Shao et al. Tsinghua scientific satellite precise orbit determination using onboard GNSS observations with antenna center Modeling
Lee et al. Mission design and orbit-attitude control algorithms development of multistatic sar satellites for very-high-resolution stripmap imaging
Cai et al. Modeling birth for the labeled multi-Bernoulli filter using a boundary-value approach
CN113591403B (en) Design method of spacecraft gravity-assist flight orbit
CN115373425A (en) Rail-controlled collision safety analysis method based on formation flying-around model
Xiong et al. Autonomous navigation of unmanned aircraft using space target LOS measurements and QLEKF

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