CN115600051B - Intelligent track maneuvering detection method and device based on short arc space-based optical observation - Google Patents
Intelligent track maneuvering detection method and device based on short arc space-based optical observation Download PDFInfo
- Publication number
- CN115600051B CN115600051B CN202211593968.0A CN202211593968A CN115600051B CN 115600051 B CN115600051 B CN 115600051B CN 202211593968 A CN202211593968 A CN 202211593968A CN 115600051 B CN115600051 B CN 115600051B
- Authority
- CN
- China
- Prior art keywords
- maneuvering
- observation
- arc section
- label
- arc
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 230000003287 optical effect Effects 0.000 title claims abstract description 60
- 230000006872 improvement Effects 0.000 claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 claims description 39
- 238000012549 training Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 14
- 238000007476 Maximum Likelihood Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 230000014509 gene expression Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 230000033001 locomotion Effects 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000004088 simulation Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000005906 menstruation Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/24—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for cosmonautical navigation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The application belongs to the technical field of space situation awareness, and relates to an intelligent detection method and device for orbital maneuver based on short-arc space-based optical observation. The method comprises the following steps: acquiring a plurality of groups of historical observation arc sections belonging to different space targets to obtain an optimal arc section; determining initial tracks of observation arc sections adjacent in time according to the optimized arc sections; performing least square iteration by taking the initial orbit as an initial value to obtain an orbit improvement result; converting the track improvement result into the track number to obtain a maneuvering characteristic parameter; marking a maneuvering label for each maneuvering characteristic parameter, and establishing a label model; obtaining a current observation arc section through short arc space-based optical observation to obtain a current maneuvering label; and dividing the current observation arc sections belonging to the same space target into a maneuvering front observation arc section and a maneuvering rear observation arc section according to the current maneuvering label, estimating maneuvering parameters and finishing the intelligent detection of the rail maneuvering. By adopting the method and the device, maneuvering detection can be performed on the space-based short arc optical observation segment.
Description
Technical Field
The application relates to the technical field of space situation awareness, in particular to a method and a device for intelligently detecting orbital maneuver based on short-arc space-based optical observation.
Background
With the continuous development of the aerospace technology, the maneuvering of the orbiting satellite presents the characteristic of more and more frequent, and the development and implementation of various activities of the orbiting satellite are based on the maneuvering of the satellite orbit, so that the detection of the maneuvering of the orbiting satellite is particularly important, and the method has important application in the aspects of satellite behavior intention identification, abnormal event perception and the like.
If the abnormal maneuvering behavior of the orbit of the target in the gravitational space can be detected early, an imminent approaching event or other threat that may be disadvantageous to the target in the own space can be avoided early, and thus maneuvering detection of the target in the space becomes an important issue.
However, this problem faces two challenges: firstly, for pulse track maneuvering, because the track speed of a space target before and after maneuvering changes to a large extent, the precise track determination of an obtained observation data arc section usually diverges and is difficult to converge, so that the track determination fails; secondly, because the time span of the observation data arc section obtained by single observation of space-based optical observation is short, the time span of the observation data arc section is usually not more than two minutes, even within one minute, the observation data arc section is called as a short arc observation segment, and because the time span of the single short arc observation segment is short, the accuracy of determining the space target track is difficult to ensure. The above two problems lead to the difficulty in the prior art in realizing the orbital pulse maneuver detection of the space-based short arc optical observation data.
Disclosure of Invention
Therefore, it is necessary to provide a method and an apparatus for intelligent detection of track maneuvering based on short arc space-based optical observation, which can perform maneuvering detection on a space-based short arc optical observation segment and simultaneously take account of the calculation efficiency of the algorithm.
The intelligent detection method for the rail maneuvering based on the short arc space-based optical observation comprises the following steps:
acquiring a plurality of groups of historical observation arc sections belonging to different space targets, and fitting and screening the historical observation arc sections by using a quadratic polynomial to obtain an optimal arc section;
arranging observation arc sections belonging to the same space target according to the preferred arc sections according to a time sequence, and determining initial tracks of the observation arc sections adjacent in time;
performing least square iteration by taking the initial orbit as an initial value, and performing orbit improvement on the observation arc sections which belong to the same space target and are adjacent in time to obtain an orbit improvement result;
converting the track improvement result into a track number, and respectively calculating the track number, the previous track number and the variation of the next track number in the semimajor axis, the eccentricity and the track inclination angle to obtain a maneuvering characteristic parameter;
marking a maneuvering label for each maneuvering characteristic parameter, training a neural network according to the maneuvering characteristic parameters and the maneuvering labels, and establishing a label model;
obtaining a current observation arc section through short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model;
dividing the current observation arc sections belonging to the same space target into a maneuvering front observation arc section and a maneuvering rear observation arc section according to the current maneuvering label; and estimating maneuvering parameters and finishing the intelligent detection of the rail maneuvering according to the maneuvering front observation arc section and the maneuvering rear observation arc section.
In one embodiment, a plurality of groups of historical observation arc sections belonging to different space targets are obtained, and a quadratic polynomial is adopted to fit and screen the historical observation arc sections to obtain an optimal arc section, which specifically comprises:
acquiring a plurality of groups of historical observation arc sections belonging to different space targets, wherein the historical observation arc sections comprise: right ascension and declination;
fitting the right ascension and the declination of the historical observation arc section by using a quadratic polynomial to obtain a fitting coefficient of the right ascension and a fitting coefficient of the declination;
obtaining the standard deviation of a historical observation arc section according to the fitting coefficient of the right ascension and the fitting coefficient of the declination;
and screening the historical observation arc sections according to the standard deviation to obtain an optimal arc section.
In one embodiment, fitting the right ascension and the declination of the historical observation arc segment by using a quadratic polynomial to obtain a fitting coefficient of the right ascension and a fitting coefficient of the declination, specifically:
fitting the time-related functional expressions of the right ascension and the declination in each historical observation arc segment by using a quadratic polynomial, and setting the right ascension
And declination
The function over time can be expressed as:
wherein,
，
，
is the fitting coefficient of the right ascension,
，
，
for the declination fitting coefficient, the initial value of each fitting coefficient is taken as:
due to the fact that
For is to
，
，
The partial derivatives of (a) are:
thus, the least square method can be used to obtain pairs
，
，
Improvement of initial value
，
，
Comprises the following steps:
wherein,
is that
The matrix of (a) is,
is composed of
The transposed matrix of (2) is added with mark-1 to represent the inversion operation of the matrix,
is that
The vector of the dimensions is then calculated,
polynomial prediction for right ascension;
then will be
，
，
The updating is as follows:
repeating the process of formula (4) and formula (5) until
The fitting coefficient of the right ascension is obtained when the value is less than the set threshold value
，
，
；
Will declination
The same operation steps are executed to obtain the fitting coefficient of declination
，
，
。
In one embodiment, the standard deviation of the historical observation arc segment is obtained according to the fitting coefficient of the right ascension and the fitting coefficient of the declination, and specifically is as follows:
defining an intermediate time of a historical observation arc as
Wherein
Representing the intermediate row number of the corresponding observation arc, thereby for each historical observation arc
There is a corresponding intermediate time data point:
wherein
The right menstruation is the right menstruation at the middle moment,
the declination at the middle moment is carried out,
the rate of change of the right ascension at the intermediate time,
the rate of change of declination at the intermediate time,
，
the position vector and the velocity vector of the optical observation satellite corresponding to the intermediate time are respectively calculated as follows:
for each observation time, calculating the right declination fitting value of the right ascension at the corresponding time, and comparing the real observation value of the right ascension at the corresponding time with the fitting difference to obtain the residual error of the right ascension declination
And further obtaining the standard deviation:
in the formula,
is shown as
The residual error is calculated according to the difference between the residual error and the reference error,
is the average of the residual errors and is,
is the number of data points.
In one embodiment, a maneuver label is marked on each maneuver characteristic parameter, and a neural network is trained according to the maneuver characteristic parameters and the maneuver labels to establish a label model, specifically:
randomly dividing the maneuvering characteristic parameters in proportion to obtain a training set and a test set of the neural network;
marking a maneuvering label for each maneuvering characteristic parameter;
and carrying out supervised training on the neural network according to the training set, the test set and the maneuvering label to establish a label model.
In one embodiment, a maneuver label is marked on each maneuver characteristic parameter, specifically:
according to the actual maneuvering situation of the corresponding space target, a maneuvering label is marked on each maneuvering characteristic parameter, if the rail maneuvering occurs in a time interval between two observation arc sections of the number of corresponding rails during the calculation of the maneuvering characteristic parameters, the maneuvering characteristic parameters are maneuvering characteristic parameters with maneuvering, and the maneuvering label is set to be 1; otherwise, the maneuvering characteristic parameter is the maneuvering characteristic parameter without maneuvering, and the maneuvering label is set to be 0.
In one embodiment, the current observation arc segment is obtained by short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model, wherein the specific steps are as follows:
obtaining a current observation arc section through short arc space-based optical observation;
fitting and screening the current observation arc section by using a quadratic polynomial, determining an initial orbit of the current observation arc section adjacent in time, improving the orbit of the current observation arc section which belongs to the same space target and is adjacent in time, and obtaining a current maneuvering characteristic parameter;
and inputting the current maneuvering characteristic parameters into the label model to obtain the current maneuvering label of the current observation arc section.
In one embodiment, according to the current maneuvering label, the current observation arc segment belonging to the same space target is divided into a before-maneuvering observation arc segment and an after-maneuvering observation arc segment, specifically:
sequencing the current maneuvering characteristic parameters belonging to the same space target according to the observation time of the first data point of the first observation arc segment of the current maneuvering characteristic parameters, and detecting the current maneuvering label of the current maneuvering characteristic parameters;
if all the current maneuvering labels are 0, the space target does not perform pulse track maneuvering in the whole observation time interval;
if the current maneuvering label is 1, dividing the observation arc section to which the space target belongs into a maneuvering front observation arc section and a maneuvering rear observation arc section by taking two observation arc sections of the number of tracks when the current maneuvering characteristic parameter corresponding to the current maneuvering label is calculated as a boundary point, and defining a time interval between the maneuvering front observation arc section and the maneuvering rear observation arc section as a time interval applied by the estimated pulse maneuvering.
In one embodiment, the maneuvering parameters are estimated and the intelligent detection of the rail maneuvering is completed according to the observation arc section before maneuvering and the observation arc section after maneuvering, which is specifically as follows:
performing least square orbit iteration improvement according to the observation arc section before maneuvering and the observation arc section after maneuvering to obtain an improved result of the orbit before maneuvering and an improved result of the orbit after maneuvering;
traversing the track improvement result before maneuvering and the track improvement result after maneuvering within the time interval of the estimated pulse maneuvering application through track cross prediction to obtain the maximum likelihood moment of the pulse maneuvering application;
and estimating the size and the application direction of the pulse maneuver according to the maximum likelihood moment to finish the intelligent detection of the track maneuver.
The intelligent detection method device for the rail maneuvering based on the short arc space-based optical observation comprises the following steps:
the acquisition module is used for acquiring a plurality of groups of historical observation arc sections belonging to different space targets, and fitting and screening the historical observation arc sections by using a quadratic polynomial to obtain an optimal arc section;
the arrangement module is used for arranging the observation arc sections belonging to the same space target according to the preferred arc sections according to a time sequence and determining the initial tracks of the observation arc sections adjacent in time;
the iteration module is used for performing least square iteration by taking the initial orbit as an initial value, and performing orbit improvement on the observation arc sections which belong to the same space target and are adjacent in time to obtain an orbit improvement result;
the calculation module is used for converting the track improvement result into the number of tracks and respectively calculating the number of the tracks, the number of the previous tracks and the variable quantity of the number of the next tracks in the semimajor axis, the eccentricity and the track inclination angle to obtain maneuvering characteristic parameters;
the modeling module is used for marking each maneuvering characteristic parameter with a maneuvering label, training the neural network according to the maneuvering characteristic parameters and the maneuvering label and establishing a label model;
the label module is used for obtaining a current observation arc section through short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model;
the estimation module is used for dividing the current observation arc sections belonging to the same space target into a before-maneuvering observation arc section and an after-maneuvering observation arc section according to the current maneuvering label; and estimating maneuvering parameters and finishing the intelligent detection of the rail maneuvering according to the maneuvering front observation arc section and the maneuvering rear observation arc section.
The intelligent detection method for the rail motor based on the short arc space-based optical observation obtains a plurality of groups of historical observation arc sections belonging to different space targets, adopts quadratic polynomial to fit and screen the historical observation arc sections, arranges the observation arc sections belonging to the same space target according to a time sequence, determines initial tracks of the observation arc sections adjacent in time, performs least square iteration by taking the initial tracks as initial values, performs track improvement on the observation arc sections which belong to the same space target and are adjacent in time to obtain a track improvement result, converts the track improvement result into track numbers, respectively calculates the track numbers, the previous track numbers and the variable quantity of the next track numbers in a semi-major axis, an eccentricity and a track inclination angle to obtain motor characteristic parameters; marking a maneuvering label for each maneuvering characteristic parameter, training the neural network according to the maneuvering characteristic parameters and the maneuvering labels, and establishing a label model; obtaining a current observation arc section through short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model; dividing the current observation arc sections belonging to the same space target into a maneuvering front observation arc section and a maneuvering rear observation arc section according to the current maneuvering label; and estimating maneuvering parameters and finishing track maneuvering intelligent detection according to the maneuvering front observation arc section and the maneuvering rear observation arc section (the track maneuvering intelligent detection comprises judging that no track maneuvering exists according to maneuvering labels and estimating maneuvering parameters). The method is suitable for space target pulse track maneuvering detection under space-based optical short arc observation conditions, and maneuvering characteristic parameters are constructed by extracting key characteristics of the space target track before and after maneuvering, so that effective training of a neural network is realized, the maneuvering detection threshold design problem is ingeniously avoided, and meanwhile, the calculation efficiency and the calculation accuracy of the pulse track maneuvering detection are considered.
Drawings
FIG. 1 is a diagram of an application scenario of an intelligent detection method for track maneuvers based on short arc space-based optical observation in an embodiment;
FIG. 2 is a schematic flow chart of an intelligent detection method for track maneuvering based on short arc space-based optical observation according to an embodiment;
FIG. 3 is a block diagram of an embodiment of an intelligent detection apparatus for track maneuvering based on short arc space-based optical observation.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that all directional indicators (such as up, down, left, right, front, and back \8230;) in the embodiments of the present application are only used to explain the relative positional relationship between the components, the motion situation, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indicators are correspondingly changed.
In addition, descriptions in this application as to "first", "second", etc. are for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicit to the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plural groups" means at least two groups, e.g., two groups, three groups, etc., unless specifically defined otherwise.
In this application, unless expressly stated or limited otherwise, the terms "connected," "secured," and the like are to be construed broadly, and thus, for example, "secured" may be a fixed connection, a removable connection, or an integral part; the connection can be mechanical connection, electrical connection, physical connection or wireless communication connection; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as the case may be.
In addition, technical solutions in the embodiments of the present application may be combined with each other, but it is necessary to be based on the realization of the technical solutions by a person skilled in the art, and when the technical solutions are contradictory to each other or cannot be realized, such a combination of technical solutions should not be considered to exist, and is not within the protection scope claimed in the present application.
The method provided by the application can be applied to the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through a network, the terminal 102 may include but is not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 104 may be a server corresponding to various portal websites and working system backgrounds.
The application provides an intelligent detection method for track maneuvering based on short arc space-based optical observation, as shown in fig. 2, in an embodiment, taking the application of the method to the terminal in fig. 1 as an example for explanation, the method includes:
step 201, obtaining a plurality of groups of historical observation arc sections belonging to different space targets, and fitting and screening the historical observation arc sections by using a quadratic polynomial to obtain an optimal arc section.
Specifically, the method comprises the following steps:
acquiring a plurality of groups of historical observation arc sections belonging to different space targets, wherein the historical observation arc sections comprise: right ascension and declination; fitting the right ascension and the declination of the historical observation arc section by using a quadratic polynomial to obtain a fitting coefficient of the right ascension and a fitting coefficient of the declination; obtaining the standard deviation of a historical observation arc section according to the fitting coefficient of the right ascension and the fitting coefficient of the declination; and screening the historical observation arc sections according to the standard deviation to obtain a preferred arc section.
More specifically:
step 2011, it is known that long-time optical observation is performed through space-based observation equipment installed on a low-orbit optical observation satellite, and after the arc sections are associated and matched, a plurality of groups of observation arc sections (namely, historical observation arc sections) belonging to different space targets are obtained, wherein each group of observation arc section data includes a plurality of observation data points, and each observation data point is composed of a right ascension, a declination, an observation time of the observed target relative to the low-orbit optical observation satellite, and position and speed information of an observation platform. I.e. space-based angle measurement data
，
，
Wherein
For the purpose of the target number of spaces,
in order to observe the number of arc segments,
，
is a first
A first of space target
Number of data lines, subscripts, of individual observation arcs
Indicating the first in the arc segment
The line data is transmitted to the mobile station,
in order to observe the epoch time,
the number of the red channels is the number of the red channels,
in order to obtain the declination,
and
the position and velocity vectors of the optical observation satellite corresponding to each line of data observation epoch time respectively.
Step 2012, fitting the time-related functional expressions of the right ascension and the declination in each observation arc segment by using a quadratic polynomial, so as to obtain the time-related change rate information of the right ascension and the declination.
Setting the Chijing
And declination
The function over time can be expressed as:
it is composed of
，
，
，
，
，
Is a polynomial undetermined coefficient,
，
，
is a fitting coefficient of the right ascension,
，
，
fitting coefficients for declination, eachThe initial value of the coefficient to be determined may be:
due to the fact that
To pair
，
，
The partial derivatives of (a) are:
thus, the least square method can be used to obtain pairs
，
，
Improvement of initial value
，
，
Comprises the following steps:
wherein
Is that
The matrix of (a) is,
is composed of
The transposed matrix of (2) is added with mark-1 to represent the inversion operation of the matrix,
is that
The vector of the dimensions of the object to be measured,
polynomial prediction for right ascension:
then will be
，
，
The updating is as follows:
repeating the process of formula (4) and formula (5) up to
Less than a set threshold valueCan, generally, be taken as
Finally, the fitting coefficient of the fitted right ascension can be obtained
，
，
(ii) a Will declination
The same operation steps can be carried out to obtain the corresponding fitting coefficient of declination
，
，
。
2013, defining the middle moment of an observation arc segment as
Wherein
Indicating the intermediate row number of the corresponding observation arc, whereby for each observation arc
There is a corresponding intermediate time data point:
wherein
The red channel is at the middle time of the day,
the declination at the middle moment is carried out,
the rate of change of the right ascension at the intermediate time,
the rate of change of declination at the intermediate time,
，
respectively, a position vector and a velocity vector of the optical observation satellite corresponding to the intermediate time. The calculation formula is as follows:
step 2014, for each observation time, obtaining a right ascension declination fitting value at the corresponding time according to the formula (1), and obtaining a residual error of the right ascension declination by using the real observation value and the fitting difference of the right ascension declination at the corresponding time. According to the overall standard deviation calculation formula:
therefore, the standard deviation of the residual error between the fitting value of an arc segment and the actual observed value can be calculated
Wherein
is shown as
The residual error is calculated according to the difference between the residual error and the reference error,
is the average of the residual errors and is,
is the number of data points. If the residual error of a data point is greater than
The point can be considered as a bad point and should be removed, otherwise the accuracy of the subsequent track improvement may be affected and even the track improvement may not converge.
And 202, arranging the observation arc sections belonging to the same space target according to the preferred arc sections according to a time sequence, and determining the initial tracks of the observation arc sections adjacent in time.
Specifically, the method comprises the following steps:
2021, sequencing the observation arcs belonging to the same space target according to the sequence of the observation time of the first data point, and setting the arc of the space-based angle measurement data obtained after sequencing as
，
，
Wherein
The target amount of space is the amount of space,
to observe the number of arc segments.
Step 2022, determining an initial orbit for each two adjacent observation arcs after time sorting, and if it is difficult to determine the initial orbit by combining the two observation arcs due to too large time difference between the two adjacent arcs, using the result obtained by determining the initial orbit for one of the observation arcs as the corresponding initial orbit.
It should be noted that, for the observation data of only the goniometric type, the initial orbit determination algorithm is already a mature algorithm in the field of space dynamics, for example, reference may be made to the initial orbit determination method in the following documents: liulin, husongjie, caohangjian, tomahagn, spacecraft orbital theory and applications [ M ]. Electronics industry press, 2015, beijing.
Let the initial orbit result obtained be
，
，
In which
For the purpose of the target number of spaces,
in order to observe the number of arc segments,
，
the orbit determination epoch time is generally selected as the observation time of the first data point or the middle time of the whole observation arc section,
and with
The position and velocity vectors of the spatial target corresponding to the orbit epoch time, respectively.
And 203, performing least square iteration by taking the initial orbit as an initial value, and performing orbit improvement on the observation arc sections which belong to the same space target and are adjacent in time to obtain an orbit improvement result.
Specifically, the method comprises the following steps:
step 2031, performing least square iterative orbit improvement between every two adjacent observation arc sections after being sorted according to time, wherein the initial iterative value is the initial orbit determination result obtained in step 2022, and the least square iterative orbit improvement algorithm is also a mature algorithm in the field of space dynamics, and for example, reference can be made to an orbit improvement method in the following documents: liulin, husongjie, caohangjian, tomahagn, spacecraft orbital theory and applications [ M ]. Electronics industry press, 2015, beijing.
Step 2032, storing all the obtained track improvement results, and setting the obtained track improvement results as
，
，
Wherein
The target amount of space is the amount of space,
in order to observe the number of arc segments,
，
，
and
and step 2022
，
And
the definitions are the same.
It should be noted that, because the initial orbit determination and the orbit improvement are carried out between every two adjacent observation arc sections, the initial orbit determination and the orbit improvement are carried out for a certain existence
The space target of each observation arc segment only exists
An initial track determination result and a track improvement result.
And 204, converting the track improvement result into a track number, and respectively calculating the track number, the previous track number and the variation of the next track number in the semimajor axis, the eccentricity and the track inclination angle to obtain maneuvering characteristic parameters.
Specifically, the method comprises the following steps:
and converting the track improvement result into track numbers, differentiating the semimajor axis, eccentricity and track inclination of each first group and each second group, the second group and each third group (the track numbers are the second group, the former track number is the first group, and the latter track number is the third group) of each temporally adjacent three groups of track numbers belonging to the same spatial target to respectively obtain the variation of the semimajor axis, the eccentricity and the track inclination, and recording the variation values of the semimajor axis, the eccentricity and the track inclination as a maneuvering characteristic parameter.
More specifically:
step 2041, converting the obtained track improvement result into track number, and setting the obtained track number result as
，
，
Wherein
For the purpose of the target number of spaces,
in order to observe the number of arc segments,
，
the semi-major axis, eccentricity, track inclination, ascension at the ascending intersection, argument of near point and true angle of near point in the number of tracks are respectively corresponded. The calculation formula for calculating the number of the tracks according to the position and the speed of the space target is as follows:
wherein
Is a constant value of the gravity of the earth,
is the amplitude angle of the intersection point.
2042, the semimajor axes, eccentricities and semimajor axes of the first group and the second group, and the second group and the third group of the number of each temporally adjacent three groups of tracksThe track inclination angle is differentiated to obtain two groups of semimajor axes, eccentricity and track inclination angle variation respectively, the absolute values of the two groups of semimajor axes, eccentricity and track inclination angle variation are recorded as a maneuvering characteristic parameter and stored, and the obtained maneuvering characteristic parameter result is set as
，
，
The number of space targets is the number of observation arc segments. The specific definition of the maneuvering characteristic parameter is
Wherein
The amounts of change of the semimajor axis, eccentricity, and track inclination are respectively expressed by the following calculation formulas:
it is noted that for a certain presence
The space target of each observation arc segment is obtained by calculation from step 201 to step 203 and step 2041
The number of the tracks is one, and each adjacent three groups of track numbers can be calculated to obtain a maneuvering characteristic parameter, so that only the space target exists
Strip machine motion characteristic parameters.
Step 205, a maneuver label is marked on each maneuver characteristic parameter, and a neural network is trained according to the maneuver characteristic parameters and the maneuver labels to establish a label model.
Specifically, the method comprises the following steps:
randomly dividing the maneuvering characteristic parameters in proportion to obtain a training set and a test set of the neural network; according to the actual maneuvering situation of the corresponding space target, a maneuvering label is marked on each maneuvering characteristic parameter, if the rail maneuvering occurs in a time interval between two observation arc sections of the number of corresponding rails (namely, the number of the second group of rails) during the calculation of the maneuvering characteristic parameters, the maneuvering characteristic parameters are maneuvering characteristic parameters with maneuvering, the maneuvering label is set to be 1, otherwise, the maneuvering characteristic parameters are maneuvering characteristic parameters without maneuvering, and the maneuvering label is set to be 0; and carrying out supervised training on the neural network according to the training set, the testing set and the maneuvering labels, and establishing a label model.
More specifically:
step 2051, according to the space-based optical observation data (generally not less than 1000 observation arcs, wherein the space-based optical observation data also includes the space object which has undergone the pulse orbit maneuver), the space-based optical observation data is processed according to the previous four steps (step 201-step 204) to finally obtain a plurality of maneuver characteristic parameters.
Step 2052, marking a maneuvering label on each maneuvering characteristic parameter according to the actual maneuvering situation of the corresponding space target, and if the track maneuvering occurs in a time interval between two observation arcs of the second group of track numbers corresponding to the calculation of the maneuvering characteristic parameters, considering the bar maneuvering characteristic parameter as a maneuvering characteristic parameter with maneuvering, and setting the maneuvering label as 1; otherwise, the strip dynamic characteristic parameter is considered to be a non-dynamic characteristic parameter, and the dynamic label is set to be 0.
It should be noted that if the application time of a pulse maneuver of a spatial target is less than 6 time intervals between the first and second observation arcs or the time interval between the last two observation arcs or the number of observation arcs of the spatial target, the maneuver characteristic parameters formed by such spatial target are difficult to provide effective learning samples for the training of the neural network, and such spatial target observation data should be discarded.
And 2053, randomly dividing the obtained large number of maneuvering characteristic parameters according to a proportion to obtain a training set T and a test set D required by neural network training, wherein the division can be performed by a leaving method, a cross-validation method or other division methods.
Step 2054, training a Neural Network, namely performing supervised training by using a feedforward Neural Network model (FNN) by using the training set T and the test set D generated in the step 2053; the Network model recommends adopting a Cascade feedforward Neural Network model (CFNN), and the training target of the Neural Network is to output a maneuvering label (0 or 1) corresponding to each maneuvering characteristic parameter according to the input maneuvering characteristic parameters, namely whether pulse maneuvering is applied in the time interval between two observation arc sections of the second group of track numbers corresponding to the calculation of the maneuvering characteristic parameters.
There are several directly called feedforward Neural Network models in Matlab's own Neural Network Tool kit (Neural Network Tool), and detailed information about cascaded feedforward Neural Network models can be read from the following documents: de Jessus O, hagan M T. Back propagation Algorithms for a Broad Class of Dynamic Networks [ J ]. IEEE Transactions on Neural Networks, 2007, 18 (1): 14-27.
Step 206, obtaining a current observation arc section through short arc space-based optical observation; and obtaining the current maneuvering label of the current observation arc section according to the current observation arc section and the label model.
Specifically, the method comprises the following steps:
obtaining a current observation arc section through short arc space-based optical observation; fitting and screening the current observation arc section by using a quadratic polynomial, determining an initial orbit of the current observation arc section adjacent in time, improving the orbit of the current observation arc section which belongs to the same space target and is adjacent in time, and obtaining current maneuvering characteristic parameters; and inputting the current maneuvering characteristic parameters into the label model to obtain the current maneuvering label of the current observation arc section.
More specifically:
inputting the real maneuvering characteristic parameters to be subjected to maneuvering detection obtained after the real observation data is processed in the steps 201 to 204 into the neural network trained in the step 205, outputting a maneuvering label corresponding to each input real maneuvering characteristic parameter by the trained neural network, and corresponding each input maneuvering characteristic parameter to the corresponding output maneuvering label one by one and recording and storing the maneuvering characteristic parameters.
Specifically, the method comprises the following steps:
sequencing the current maneuvering characteristic parameters belonging to the same space target according to the observation time of the first data point of the first observation arc segment of the current maneuvering characteristic parameters, and detecting the current maneuvering label of the current maneuvering characteristic parameters; if all the current maneuvering labels are 0, the space target does not perform pulse track maneuvering in the whole observation time interval; if the current maneuvering label is 1, dividing the observation arc section to which the space target belongs into a maneuvering front observation arc section and a maneuvering rear observation arc section by taking two observation arc sections of the number of tracks when the current maneuvering characteristic parameter corresponding to the current maneuvering label is calculated as a boundary point, and defining a time interval between the maneuvering front observation arc section and the maneuvering rear observation arc section as a time interval applied by the estimated pulse maneuvering.
Performing least square orbit iteration improvement according to the observation arc section before maneuvering and the observation arc section after maneuvering to obtain an improvement result of the orbit before maneuvering and an improvement result of the orbit after maneuvering; traversing the track improvement result before maneuvering and the track improvement result after maneuvering within the estimated time interval of the application of the pulse maneuvering through track cross prediction to obtain the maximum likelihood time of the application of the pulse maneuvering; and estimating the magnitude and the application direction of the pulse maneuver according to the maximum likelihood moment to finish the intelligent detection of the track maneuver.
More specifically:
step 2071, sequencing the real maneuvering characteristic parameters belonging to the same space target according to the observation time of the first data point of the first observation arc segment, and then sequentially detecting the maneuvering tags of each maneuvering characteristic parameter, wherein if the maneuvering tags are all 0, the target is considered not to be subjected to pulse orbit maneuvering in the whole observation time interval; if the mobile label with the value of 1 exists, two observation arcs corresponding to the second group of track number are used as boundary points when the strip mobile characteristic parameter is calculated, namely the observation arcs to which the space target belongs are divided into observation arcs before mobile operation and observation arcs after mobile operation according to the mobile label with the real mobile characteristic parameter, and a time interval between the two observation arcs is defined as an estimated pulse mobile application time interval.
For example, if 8 observation arcs exist in the observation time interval of a certain space target a, 5 pieces of motion characteristic parameters are obtained through calculation in steps 201 to 204, and it is detected that the motion label corresponding to the third motion characteristic parameter is 1, and the number of the second group of tracks corresponding to the third motion characteristic parameter is obtained through improvement of the third and fourth observation arcs, so that the third and fourth observation arcs are taken as a boundary point, the first to third arcs are divided into observation arcs before motion, the fourth to eighth arcs are divided into observation arcs after motion, and the time interval between the third and fourth observation arcs is an estimated pulse motion application time interval.
Step 2072, combining all the observation arc segments before maneuvering and all the observation arc segments after maneuvering of the same space target to perform least square orbit iterative improvement, so as to obtain two orbit improvement results before maneuvering and after maneuvering for a certain space target considered to possibly have pulse orbit maneuvering, and setting the obtained orbit improvement result as
，
，
Wherein
For the number of spatial targets where pulsed orbital maneuvers are possible,
before the motor-driven vehicle is indicated to move,
after the maneuver is indicated, the vehicle is in motion,
，
，
and
is the same as defined in step 2022; relevant information about the least squares trajectory iterative refinement algorithm is detailed in step 2031.
Step 2073, traversing the orbit improvement result before maneuver and the orbit improvement result after maneuver, which are calculated in the step 2072, within the estimated impulse maneuver applying time interval through orbit cross prediction to find out the maximum likelihood moment of the impulse maneuver applying
In which
，
The definition of the pre-estimated pulsed maneuver application time interval for the number of spatial targets for which pulsed orbital maneuvers may exist is consistent with the definition in step 2071. The track crossing forecast specifically refers toAnd respectively carrying out forward and backward track prediction on the two space target tracks to forecast the same epoch moment. Where the maximum likelihood moment of the maneuver of the pulse is applied
Defined as the time instant when the position distance between the front maneuver track and the rear maneuver track is the minimum in the three-dimensional space. This definition can be improved and expanded, for example, if the orbit deviation information of the pre-maneuver and post-maneuver orbits is known, the maximum likelihood time of the pulsed maneuver application
It can also be defined as the moment when the mahalanobis distance between the front maneuver and the rear maneuver is minimized.
Step 2074, forecasting the improvement result of the orbit before maneuvering and the improvement result of the orbit after maneuvering to the maximum likelihood moment applied by the impulse maneuvering, and performing comparative analysis on the improvement result of the orbit before maneuvering and the improvement result of the orbit after maneuvering to estimate the impulse maneuvering size, the application direction of the impulse maneuvering, and other maneuvering parameters, namely: forecasting backward orbit and forward orbit respectively for the improvement result of the front orbit and the improvement result of the rear orbit, until the maximum likelihood moment applied by the pulse maneuver obtained in step 2073
。
At this time, the track forecast results before maneuvering and after maneuvering are respectively as follows:
and
the applied pulse maneuver pulse may be estimated by:
wherein
Representing an estimate of the impulse maneuvering impulse.
Step 2075, in actual observation, there may be small amount of false detection due to disturbance factors such as observation errors caused by some reasons, so to improve the detection accuracy of the track maneuver, the detection result needs to be screened according to the pulse maneuver impulse estimation value. According to practical experience
When the detection result is false detection with a high probability, the pulse maneuver is not considered to exist.
The intelligent detection method for the rail motor based on the short arc space-based optical observation obtains a plurality of groups of historical observation arc sections belonging to different space targets, adopts quadratic polynomial to fit and screen the historical observation arc sections, arranges the observation arc sections belonging to the same space target according to a time sequence, determines initial tracks of the observation arc sections adjacent in time, performs least square iteration by taking the initial tracks as initial values, performs track improvement on the observation arc sections which belong to the same space target and are adjacent in time to obtain a track improvement result, converts the track improvement result into track numbers, respectively calculates the track numbers, the previous track numbers and the variable quantity of the next track numbers in a semi-major axis, an eccentricity and a track inclination angle to obtain motor characteristic parameters; marking a maneuvering label for each maneuvering characteristic parameter, training the neural network according to the maneuvering characteristic parameters and the maneuvering labels, and establishing a label model; obtaining a current observation arc section through short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model; dividing the current observation arc sections belonging to the same space target into a maneuvering front observation arc section and a maneuvering rear observation arc section according to the current maneuvering label; and estimating maneuvering parameters and finishing the intelligent detection of the rail maneuvering according to the maneuvering front observation arc section and the maneuvering rear observation arc section.
The method is suitable for space target pulse track maneuvering detection under space-based optical short arc observation conditions, a neural network trained by constructing maneuvering characteristic parameters can detect the maneuvering occurring between two observation arc sections, so that the obtained observation arc sections are divided into the observation arc sections before maneuvering and the observation arc sections after maneuvering, and the technical problem that in the prior art, the pulse maneuvering condition is not distinguished, the obtained observation data arc sections are directly subjected to precise track determination, the divergence occurs when the precise track determination is performed on the obtained observation data arc sections, so that maneuvering detection is successfully realized, and the technical problem that the convergence is difficult to achieve due to the divergence occurs when the precise track determination is performed on the obtained observation data arc sections is solved. The structure of the dynamic characteristic parameter in the application adopts calculation the track radical and the previous track radical and the latter track radical are realized in the mode of semimajor axis, eccentricity and track inclination variation, and the structure realization mode enables the observation arc section and the front and back observation arc section to offset each other to a great extent due to the error caused by short arc observation, thereby realizing the dynamic detection under the short arc observation condition. The method extracts three key track root characteristics of a semi-long shaft, an eccentricity and a track inclination angle before and after space target track maneuvering through model design, creatively constructs maneuvering characteristic parameters according to the three key track root characteristics, and in six classical tracks representing the space target movement state, the semi-long shaft and the eccentricity are sensitive to components of the space maneuvering in a track plane, and the track inclination angle is sensitive to components of the space maneuvering perpendicular to the track plane, so that the constructed maneuvering characteristic parameters can reserve maneuvering characteristics of the space target pulse maneuvering to be learned by a neural network to realize effective training of the neural network, the generated neural network can extract differences between maneuvering characteristic parameters and non-maneuvering characteristic parameters, and the method has good generalization performance for space target pulse track maneuvering detection problems under short arc observation conditions, thereby avoiding complex maneuvering detection threshold design problems and improving the calculation efficiency of the pulse track maneuvering detection compared with the traditional method; according to the screening processing of the maneuver estimation result, the accuracy and precision of the maneuver detection of the pulse orbit are further improved by reducing the false alarm rate of the detection.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In a specific embodiment, when a large number of space target space-based optical short arc observation data arc sections exist, the observation arc sections before and after the pulse orbit maneuver are identified and maneuver parameters are estimated through a neural network artificial intelligence algorithm.
Specifically, the method comprises the following steps:
assuming that 50 space targets running on a GEO orbit are subjected to optical observation for 7 days by using a certain low-orbit optical observation satellite running on a sun synchronous orbit with the orbit height of 800km, the angle observation error is 3 arc seconds, and the observation start and stop time is 2019.12.21.12.
The low-orbit optical observation satellite is
The number of tracks at the initial time is:
。
because the observation data of the actual space target is difficult to obtain, a training set T and a testing set D required by neural network training are generated and obtained by adopting a simulation observation mode. Randomly generating 1000 simulation space targets on the GEO orbit, and assuming that the 1000 simulation space targets running on the GEO orbit are subjected to optical observation for 7 days by using a low-orbit optical observation satellite which also runs on a sun synchronous orbit with the orbit height of 800km, wherein the orbit number of the observation starting and ending time and the low-orbit optical observation satellite is the same as that in the step 201. Wherein 50% of simulation targets are selected to randomly add one pulse orbit maneuver within the simulation observation time period, and the impulse of the pulse orbit maneuver is randomly selected between 2m/s and 5 m/s. In order to obtain as many effective learning samples as possible, the application time of the pulse orbit maneuver is random within the range from 2019.12.23.00 to 2019.12.27.00, and then simulation observation is carried out according to the first four steps (step 201-step 204) to finally obtain about 6547 machine maneuver characteristic parameters.
And (2) marking a maneuvering label on each maneuvering characteristic parameter, if the application time of the pulse maneuvering of a certain space target is positioned in the time interval between the first observation arc section and the second observation arc section of the space target or the time interval between the last observation arc section and the second observation arc section or the number of the observation arc sections is less than 6, and because the maneuvering characteristic parameters formed by the space target are difficult to provide effective learning samples for the training of the neural network, the space target should be discarded, and 6382 effective samples are finally left.
Randomly dividing the obtained large amount of maneuvering characteristic parameters, using 80% of sample data as a training set T required by neural network training by a leave-out method, and using 20% of sample data as a test set D required by the neural network training.
The generated training set T and the testing set D are used for supervised training by adopting a feed Forward Neural Network (FNN), and through testing, when the number of hidden layers is 2 and the number of nodes is 7 and 8 respectively, a better training effect can be achieved.
Inputting 562 pieces of dynamic characteristic parameters to be subjected to dynamic detection, which are obtained after the real observation data are processed in the steps 201 to 204, into the neural network trained in the step 205, outputting a dynamic label corresponding to each input dynamic characteristic parameter by the trained neural network, and corresponding each input dynamic characteristic parameter and the corresponding output dynamic label one by one and recording and storing the dynamic characteristic parameters.
Sequencing the maneuvering characteristic parameters belonging to the same space target according to the observation time of the first data point of the first observation arc section, then sequentially detecting the maneuvering labels of the maneuvering characteristic parameters, finding that 29 maneuvering labels which are marked with 1 by a neural network exist in 562 maneuvering characteristic parameters, and dividing the observation arc section to which the space target belongs into a maneuvering front observation arc section and a maneuvering rear observation arc section according to the maneuvering labels.
4 space targets with possible impulse maneuver are subjected to orbit cross prediction calculation, and impulse maneuver impulse estimation values
No maneuvering target should be identified.
The test results of the final examples are shown in table 1 below.
Table 1 table showing the test results of the examples
The present application further provides an intelligent detection device for track maneuvering based on short arc space-based optical observation, as shown in fig. 3, in an embodiment, the detection device includes: an obtaining module 301, a ranking module 302, an iteration module 303, a calculating module 304, a modeling module 305, a labeling module 306, and an estimating module 307, wherein:
the acquisition module 301 is configured to acquire multiple groups of historical observation arc segments belonging to different space targets, and fit and screen the historical observation arc segments by using a quadratic polynomial to obtain an optimal arc segment;
an arranging module 302, configured to arrange observation arc segments belonging to the same space target according to the preferred arc segment in a time sequence, and determine initial tracks of observation arc segments that are adjacent in time;
an iteration module 303, configured to perform least square iteration by using the initial orbit as an initial value, and perform orbit improvement on observation arc segments that belong to the same spatial target and are adjacent in time, to obtain an orbit improvement result;
the calculation module 304 is configured to convert the track improvement result into a track number, and calculate the track number, the previous track number, and the variation of the next track number in the semi-major axis, the eccentricity, and the track inclination angle, respectively, to obtain a maneuvering characteristic parameter;
the modeling module 305 is configured to print a maneuvering label for each maneuvering characteristic parameter, train a neural network according to the maneuvering characteristic parameter and the maneuvering label, and establish a label model;
the label module 306 is used for obtaining a current observation arc section through short-arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model;
the estimation module 307 is used for dividing the current observation arc segment belonging to the same space target into a before-maneuvering observation arc segment and an after-maneuvering observation arc segment according to the current maneuvering label; and estimating maneuvering parameters and finishing the intelligent detection of the rail maneuvering according to the maneuvering front observation arc section and the maneuvering rear observation arc section.
For specific definition of the intelligent detection device for track maneuvering based on short arc space-based optical observation, reference may be made to the above definition of the intelligent detection method for track maneuvering based on short arc space-based optical observation, and details are not repeated here. The various modules in the above-described apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (7)
1. The intelligent detection method for the rail maneuvering based on the short arc space-based optical observation is characterized by comprising the following steps:
acquiring a plurality of groups of historical observation arc sections belonging to different space targets, and fitting and screening the historical observation arc sections by using a quadratic polynomial to obtain an optimal arc section; the method specifically comprises the following steps: acquiring a plurality of groups of historical observation arc sections belonging to different space targets, wherein the historical observation arc sections comprise: right ascension and declination; fitting the right ascension and the declination of the historical observation arc section by using a quadratic polynomial to obtain a fitting coefficient of the right ascension and a fitting coefficient of the declination; obtaining the standard deviation of a historical observation arc section according to the fitting coefficient of the right ascension and the fitting coefficient of the declination; screening the historical observation arc sections according to the standard deviation to obtain a preferred arc section;
arranging observation arc sections belonging to the same space target according to the time sequence according to the preferred arc sections, and determining initial tracks of the observation arc sections adjacent in time;
performing least square iteration by taking the initial orbit as an initial value, and performing orbit improvement on the observation arc sections which belong to the same space target and are adjacent in time to obtain an orbit improvement result;
converting the track improvement result into a track number, and respectively calculating the track number, the previous track number and the variation of the next track number in the semimajor axis, the eccentricity and the track inclination angle to obtain a maneuvering characteristic parameter;
marking a maneuvering label for each maneuvering characteristic parameter, training a neural network according to the maneuvering characteristic parameters and the maneuvering labels, and establishing a label model;
obtaining a current observation arc section through short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model;
dividing the current observation arc sections belonging to the same space target into a maneuvering front observation arc section and a maneuvering rear observation arc section according to the current maneuvering label; estimating maneuvering parameters and completing intelligent detection of the rail maneuvering according to the maneuvering front observation arc section and the maneuvering rear observation arc section;
according to observation arc section before the maneuver and observation arc section after the maneuver, estimating maneuver parameters and completing the intelligent detection of the track maneuver, specifically: performing least square orbit iteration improvement according to the observation arc section before maneuvering and the observation arc section after maneuvering to obtain an improved result of the orbit before maneuvering and an improved result of the orbit after maneuvering; traversing the track improvement result before maneuvering and the track improvement result after maneuvering within the time interval of the estimated pulse maneuvering application through track cross prediction to obtain the maximum likelihood moment of the pulse maneuvering application; estimating the size and the application direction of the pulse maneuver according to the maximum likelihood moment to finish intelligent detection of the track maneuver;
adopting a quadratic polynomial to fit the right ascension and the declination of the historical observation arc section to obtain a fitting coefficient of the right ascension and a fitting coefficient of the declination, and obtaining a standard deviation of the historical observation arc section according to the fitting coefficient of the right ascension and the fitting coefficient of the declination, wherein the fitting coefficient of the right ascension and the fitting coefficient of the declination are specifically as follows:
and respectively fitting the time-related function expressions of the right ascension and the declination in each historical observation arc segment by adopting a quadratic polynomial, and setting the time-related function expressions of the right ascension alpha and the declination delta as follows:
wherein, a 0 ，a 1 ，a 2 As fitting coefficient of the right ascension, b 0 ，b 1 ，b 2 For the declination fitting coefficient, the initial value of each fitting coefficient is taken as:
due to alpha (t) to a 0 ，a 1 ，a 2 The partial derivatives of (a) are:
therefore, the least square method can be used to obtain the pair a 0 ，a 1 ，a 2 Initial improvement amount delta a 0 ，Δa 1 ，Δa 2 Comprises the following steps:
wherein,
is n i,j X 3 matrix, B T Is a transposed matrix of B, the upper label of the transposed matrix is-1 to represent the inversion operation of the matrix,
is n i,j The vector of the dimensions is then calculated,
polynomial prediction for right ascension;
then a will be 0 ，a 1 ，a 2 The updating is as follows:
repeating the process of formula (4) and formula (5) up to
Is less than the set threshold value to obtain the fitting coefficient a of the right ascension 0 ，a 1 ，a 2 ；
The same operation steps are carried out on the declination delta to obtain the fitting coefficient b of the declination 0 ，b 1 ，b 2 ；
For each observation time, calculating a right ascension declination fitting value at the corresponding time, and combining the real observation value of the right ascension declination at the corresponding time with the fitting difference to obtain a residual epsilon of the right ascension declination, and further obtaining a standard deviation sigma:
in the formula, x i Represents the ith residual error, mu is the mean value of the residual errors, and n is the number of data points.
2. The intelligent detection method for track maneuvering based on short arc space-based optical observation according to claim 1, characterized in that the standard deviation of the historical observation arc segment is obtained according to the fitting coefficient of the right ascension and the fitting coefficient of the declination, specifically:
defining an intermediate time of a historical observation arc as
Wherein (int) ((1 + n) i,j ) /2) intermediate row number representing corresponding observation arc, whereby for each historical observation arc
There is a corresponding intermediate time data point:
wherein alpha is the right ascension at the middle time, delta is the declination at the middle time,
the rate of change of the right ascension at the intermediate time,
the rate of change of declination at the intermediate time,
the position vector and the velocity vector of the optical observation satellite corresponding to the intermediate time are respectively calculated as follows:
3. the intelligent detection method for the track maneuver based on the short-arc space-based optical observation according to claim 1 or 2, characterized in that a maneuver label is marked on each maneuver characteristic parameter, and a neural network is trained according to the maneuver characteristic parameters and the maneuver labels to establish a label model, specifically:
randomly dividing the maneuvering characteristic parameters in proportion to obtain a training set and a test set of the neural network;
printing a maneuvering label for each maneuvering characteristic parameter;
and carrying out supervised training on the neural network according to the training set, the test set and the maneuvering label to establish a label model.
4. The intelligent detection method for the track maneuver based on the short-arc space-based optical observation according to claim 3, wherein a maneuver label is marked on each maneuver characteristic parameter, specifically:
according to the actual maneuvering situation of the corresponding space target, a maneuvering label is marked on each maneuvering characteristic parameter, if the rail maneuvering occurs in a time interval between two observation arc sections of the number of corresponding rails during the calculation of the maneuvering characteristic parameters, the maneuvering characteristic parameters are maneuvering characteristic parameters, and the maneuvering label is set to be 1; otherwise, the maneuvering characteristic parameter is the maneuvering characteristic parameter without maneuvering, and the maneuvering label is set to be 0.
5. The intelligent detection method for the track motor based on the short arc space-based optical observation is characterized in that a current observation arc section is obtained through the short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model, wherein the specific steps are as follows:
obtaining a current observation arc section through short arc space-based optical observation;
fitting and screening the current observation arc section by using a quadratic polynomial, determining an initial orbit of the current observation arc section adjacent in time, improving the orbit of the current observation arc section which belongs to the same space target and is adjacent in time, and obtaining a current maneuvering characteristic parameter;
and inputting the current maneuvering characteristic parameters into the label model to obtain the current maneuvering label of the current observation arc section.
6. The intelligent detection method for track maneuvering based on short arc space-based optical observation according to claim 1 or 2, characterized in that, according to the current maneuvering label, the current observation arc segment belonging to the same space target is divided into a maneuvering front observation arc segment and a maneuvering rear observation arc segment, specifically:
sequencing current maneuvering characteristic parameters belonging to the same space target according to the observation time of a first data point of a first observation arc segment of the current maneuvering characteristic parameters, and detecting a current maneuvering label of the current maneuvering characteristic parameters;
if all the current maneuvering tags are 0, the space target does not carry out pulse orbit maneuvering in the whole observation time interval;
if the current maneuvering label is 1, dividing the observation arc section to which the space target belongs into a maneuvering front observation arc section and a maneuvering rear observation arc section by taking two observation arc sections of the number of tracks when the current maneuvering characteristic parameter corresponding to the current maneuvering label is calculated as a boundary point, and defining a time interval between the maneuvering front observation arc section and the maneuvering rear observation arc section as a time interval applied by the estimated pulse maneuvering.
7. Track maneuver intelligent detection device based on short arc sky base optical observation, its characterized in that includes:
the acquisition module is used for acquiring a plurality of groups of historical observation arc sections belonging to different space targets, and fitting and screening the historical observation arc sections by using a quadratic polynomial to obtain an optimal arc section; the method specifically comprises the following steps: acquiring a plurality of groups of historical observation arc sections belonging to different space targets, wherein the historical observation arc sections comprise: right ascension and declination; fitting the right ascension and the declination of the historical observation arc section by using a quadratic polynomial to obtain a fitting coefficient of the right ascension and a fitting coefficient of the declination; obtaining the standard deviation of a historical observation arc section according to the fitting coefficient of the right ascension and the fitting coefficient of the declination; screening the historical observation arc sections according to the standard deviation to obtain an optimal arc section;
the arrangement module is used for arranging the observation arc sections belonging to the same space target according to the preferred arc sections according to a time sequence and determining the initial tracks of the observation arc sections adjacent in time;
the iteration module is used for performing least square iteration by taking the initial orbit as an initial value, and performing orbit improvement on the observation arc sections which belong to the same space target and are adjacent in time to obtain an orbit improvement result;
the calculation module is used for converting the track improvement result into the number of tracks, and respectively calculating the number of tracks, the number of previous tracks and the variation of the number of next tracks in the semimajor axis, the eccentricity and the track inclination angle to obtain maneuvering characteristic parameters;
the modeling module is used for marking each maneuvering characteristic parameter with a maneuvering label, training the neural network according to the maneuvering characteristic parameter and the maneuvering label, and establishing a label model;
the label module is used for obtaining a current observation arc section through short arc space-based optical observation; obtaining a current maneuvering label of the current observation arc section according to the current observation arc section and the label model;
the estimation module is used for dividing the current observation arc sections belonging to the same space target into a before-maneuvering observation arc section and an after-maneuvering observation arc section according to the current maneuvering label; estimating maneuvering parameters and completing intelligent detection of the rail maneuvering according to the maneuvering front observation arc section and the maneuvering rear observation arc section;
according to observation arc section before the maneuver and observation arc section after the maneuver, estimate the maneuver parameter and accomplish the track maneuver intellectual detection, specifically: performing least square orbit iteration improvement according to the observation arc section before maneuvering and the observation arc section after maneuvering to obtain an improvement result of the orbit before maneuvering and an improvement result of the orbit after maneuvering; traversing the track improvement result before maneuvering and the track improvement result after maneuvering within the time interval of the estimated pulse maneuvering application through track cross prediction to obtain the maximum likelihood moment of the pulse maneuvering application; estimating the magnitude and the application direction of the pulse maneuver according to the maximum likelihood moment to finish the intelligent detection of the track maneuver;
adopt quadratic polynomial to the right ascension and the declination of historical observation segmental arc are fitted, obtain the fitting coefficient of right ascension and the fitting coefficient of declination, according to the fitting coefficient of right ascension and the fitting coefficient of declination, obtain the standard deviation of historical observation segmental arc, specifically do:
and respectively fitting the time-related function expressions of the right ascension and the declination in each historical observation arc segment by adopting a quadratic polynomial, and setting the time-related function expressions of the right ascension alpha and the declination delta as follows:
wherein, a 0 ，a 1 ，a 2 Fitting coefficient for the right ascension, b 0 ，b 1 ，b 2 For the declination fitting coefficient, the initial value of each fitting coefficient is taken as:
due to alpha (t) to a 0 ，a 1 ，a 2 The partial derivatives of (a) are:
therefore, the least square method can be used to obtain the pair a 0 ，a 1 ，a 2 Initial improvement Δ a 0 ，Δa 1 ，Δa 2 Comprises the following steps:
wherein,
is n i,j X 3 matrix, B T Is a transposed matrix of B, the upper label-1 represents the inversion operation of the matrix,
is n i,j The vector of the dimensions is then calculated,
is a polynomial forecast of the right ascension;
then a will be 0 ，a 1 ，a 2 The updating is as follows:
repeating the process of formula (4) and formula (5) until
Is less than the set threshold value to obtain the fitting coefficient a of the right ascension 0 ，a 1 ，a 2 ；
The same operation steps are carried out on the declination delta to obtain declinationFitting coefficient b 0 ，b 1 ，b 2 ；
For each observation time, calculating a right ascension declination fitting value of the corresponding time, and combining the real observation value of the right ascension declination of the corresponding time with the fitting difference to obtain a residual epsilon of the right ascension declination, thereby obtaining a standard deviation sigma:
in the formula, x i Represents the ith residual error, mu is the mean value of the residual errors, and n is the number of data points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211593968.0A CN115600051B (en) | 2022-12-13 | 2022-12-13 | Intelligent track maneuvering detection method and device based on short arc space-based optical observation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211593968.0A CN115600051B (en) | 2022-12-13 | 2022-12-13 | Intelligent track maneuvering detection method and device based on short arc space-based optical observation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115600051A CN115600051A (en) | 2023-01-13 |
| CN115600051B true CN115600051B (en) | 2023-02-24 |
Family
ID=84854277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211593968.0A Active CN115600051B (en) | 2022-12-13 | 2022-12-13 | Intelligent track maneuvering detection method and device based on short arc space-based optical observation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600051B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115790607B (en) * | 2023-01-31 | 2023-05-12 | 南京航空航天大学 | Non-cooperative target maneuvering characteristic detection method based on short arc historical data |
| CN115855069B (en) * | 2023-02-28 | 2023-05-05 | 中国人民解放军国防科技大学 | GEO spacecraft maneuver detection and position prediction method based on SCE |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100512552B1 (en) * | 2003-05-15 | 2005-09-05 | 휴먼앤퓨처정보통신(주) | Apparatus and method of detecting a movement by a radar, using finite interval moving slide window impulse filter |
| CN110442831B (en) * | 2019-07-31 | 2023-03-24 | 中国人民解放军国防科技大学 | Space non-cooperative target space-based search method based on nonlinear deviation evolution |
| CN111428365B (en) * | 2020-03-24 | 2021-12-28 | 中国人民解放军32035部队 | Method for distinguishing GEO target by using astronomical measurement data |
| CN111578950B (en) * | 2020-06-09 | 2021-09-21 | 中国人民解放军63921部队 | Space-based optical monitoring-oriented GEO target autonomous arc segment association and orbit determination method |
| CN111551183B (en) * | 2020-06-09 | 2021-12-21 | 中国人民解放军63921部队 | GEO target multi-point preferred short arc orbit determination method based on space-based optical observation data |
| CN111998855B (en) * | 2020-09-02 | 2022-06-21 | 中国科学院国家天文台长春人造卫星观测站 | Geometric method and system for determining space target initial orbit through optical telescope common-view observation |
-
2022
- 2022-12-13 CN CN202211593968.0A patent/CN115600051B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115600051A (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115600051B (en) | Intelligent track maneuvering detection method and device based on short arc space-based optical observation | |
| CN108960303B (en) | Unmanned aerial vehicle flight data anomaly detection method based on LSTM | |
| CN107396322B (en) | Indoor positioning method based on path matching and coding-decoding cyclic neural network | |
| CN108596327B (en) | Seismic velocity spectrum artificial intelligence picking method based on deep learning | |
| CN110770758A (en) | Determining the position of a mobile device | |
| Hu et al. | A framework for probabilistic generic traffic scene prediction | |
| CN105719312A (en) | Multi-target tracking method and tracking system based on sequential Bayes filtering | |
| CN103743401A (en) | Asynchronous fusion method based on multi-model flight path quality | |
| CN111127523A (en) | Multi-sensor GMPHD self-adaptive fusion method based on measurement iteration update | |
| CN109509207B (en) | Method for seamless tracking of point target and extended target | |
| Khlamov et al. | The astronomical object recognition and its near-zero motion detection in series of images by in situ modeling | |
| CN115691134A (en) | Intelligent automobile test scene library construction method based on countermeasure generation network | |
| Revach et al. | RTSNet: Learning to smooth in partially known state-space models | |
| CN112991394B (en) | KCF target tracking method based on cubic spline interpolation and Markov chain | |
| Son et al. | Partial convolutional LSTM for spatiotemporal prediction of incomplete data | |
| CN113156473A (en) | Self-adaptive discrimination method for satellite signal environment of information fusion positioning system | |
| CN111241749B (en) | Permanent magnet synchronous motor chaos prediction method based on reserve pool calculation | |
| CN111340853A (en) | Multi-sensor GMPHD self-adaptive fusion method based on OSPA iteration | |
| CN114818116B (en) | Aircraft engine failure mode identification and life prediction method based on joint learning | |
| Dong et al. | Multi-sensor data fusion using the influence model | |
| CN116523002A (en) | Method and system for predicting dynamic graph generation countermeasure network track of multi-source heterogeneous data | |
| CN114061592B (en) | Adaptive robust AUV navigation method based on multiple models | |
| CN114018250B (en) | Inertial navigation method, electronic device, storage medium and computer program product | |
| CN116026325A (en) | Navigation method and related device based on neural process and Kalman filtering | |
| CN112102399A (en) | Visual mileage calculation method based on generative antagonistic network |
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 |