CN117828999A - Digital twin satellite group intelligent management system and method - Google Patents
Digital twin satellite group intelligent management system and method Download PDFInfo
- Publication number
- CN117828999A CN117828999A CN202410240947.3A CN202410240947A CN117828999A CN 117828999 A CN117828999 A CN 117828999A CN 202410240947 A CN202410240947 A CN 202410240947A CN 117828999 A CN117828999 A CN 117828999A
- Authority
- CN
- China
- Prior art keywords
- satellite
- state
- satellites
- digital twin
- adjustment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000033001 locomotion Effects 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 8
- 230000000007 visual effect Effects 0.000 claims abstract description 8
- 238000007726 management method Methods 0.000 claims description 36
- 238000012544 monitoring process Methods 0.000 claims description 28
- 230000005540 biological transmission Effects 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000013178 mathematical model Methods 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 108091092878 Microsatellite Proteins 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a digital twin satellite group intelligent management system and a method thereof, which relate to the technical field of satellite operation management and useBpAcquiring satellite operation digital twin model output after neural network training, predicting the operation state of the satellite, acquiring corresponding prediction results, summarizing a plurality of prediction results to generate a state prediction set, acquiring the difference value between the satellite operation state parameter and a previous value, generating a satellite variation index, screening out satellites to be adjusted from a plurality of satellites, and confirming corresponding adjustment priority; and matching corresponding adjustment schemes for the states of all satellites in sequence, predicting and acquiring running state data of all satellites after the adjustment schemes are executed, establishing a motion digital twin model of the satellites according to the running state data, and performing visual processing on the motion process predicted and acquired by all satellites. General purpose medicineThe adjustment priority is determined, so that the adjustment process of each satellite can be orderly carried out, and mutual interference among the satellites is avoided.
Description
Technical Field
The invention relates to the technical field of satellite operation management, in particular to an intelligent management system and method for a digital twin satellite group.
Background
The intelligent management of satellite groups refers to complex and accurate maneuvering operation among multiple satellites in an in-orbit satellite constellation through highly-automated intersection and approaching operation so as to realize various tasks including in-orbit service coordination, orbit upgrading and the like.
The digital twin technology is a technology for integrating simulation processes of multiple disciplines, multiple physical quantities, multiple scales and multiple probabilities based on data such as a physical model, sensor update and operation history. The digital twin technique can complete mapping in the virtual space, reflecting the full life cycle process of the corresponding physical equipment. It is considered a digital mapping system of one or more important, mutually dependent equipment systems. Due to the complexity of satellite management tasks, digital twinning techniques are also increasingly being applied in this field.
In the Chinese patent application publication No. CN105049110A, a distributed management system for microsatellite group is disclosed, which comprises a distributed management system for satellite group consisting of multiple microsatellites in close-range networking, and based on space wireless communication technology, the subsystems are connected byWiFiAnd the wireless communication realizes independent data management and inter-satellite data sharing management of each microsatellite. The invention realizes the functions of star remote control, star remote measurement, star clock synchronization, star communication, star program control and the like through the multi-star networking.
In the above application, due toWiFiThe standard high-efficiency network self-organization and quick recovery function are realized, each microsatellite adopts an industrial goods shelf type integrated circuit, so that the star group distributed management system has the characteristics of high instantaneity, strong flexibility, high reliability, low investment cost, reconfigurability and the like, and provides reference value for engineering application of a management system of a future microsatellite group.
However, when the number of satellites is large and the distribution of the satellites in each area is quite uneven, the position and the posture of the satellites need to be adjusted, but in the existing adjustment method, when a plurality of satellites are adjusted, adjustment is usually performed simultaneously, and certain interference is generated between the satellites in the adjustment process, so that the adjustment result may be difficult to reach the expected value, and the actual efficiency of adjustment is low.
Therefore, the invention provides an intelligent management system and method for digital twin satellite groups.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a digital twin satellite group intelligent management system and a digital twin satellite group intelligent management methodBpAcquiring satellite operation digital twin model output after neural network training, predicting the operation state of the satellite, acquiring corresponding prediction results, summarizing a plurality of prediction results to generate a state prediction set, acquiring the difference value between the satellite operation state parameter and a previous value, generating a satellite variation index, screening out satellites to be adjusted from a plurality of satellites, and confirming corresponding adjustment priority; and matching corresponding adjustment schemes for the states of all satellites in sequence, predicting and acquiring running state data of all satellites after the adjustment schemes are executed, establishing a satellite motion model according to the running state data, and performing visual processing on the motion process predicted and acquired by all satellites. The adjustment process of each satellite can be orderly carried out by determining the adjustment priority, so that the mutual interference among the satellites is avoided, and the problems in the background technology are solved.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
an intelligent management method for digital twin satellite group comprises the following steps: comprising the steps of (a) a step of,
dividing a satellite distribution area into a plurality of subareas, acquiring the distribution state and the communication state of satellites in each subarea, establishing an area density set, and generating a density index from the area density setIf the obtained Density index +.>If the density threshold value is exceeded, an adjustment instruction is sent out;
monitoring the running state of each satellite, establishing a satellite running state set, performing feature extraction, constructing a model feature set, and usingBpThe neural network is used for obtaining satellite operation digital twin model output after training, predicting the operation state of the satellite by using the neural network, obtaining corresponding prediction results, and summarizing a plurality of prediction results to generate a state prediction set;
acquiring a plurality of satellite running state parameters in a state prediction set, acquiring the difference value between the satellite running state parameters and a previous value, generating a state variable set after summarizing, and generating a satellite variation index from the state variable setBy satellite variation index->Screening out the satellite to be adjusted from a plurality of satellites, and confirming the corresponding adjustment priority;
wherein the satellite change indexThe acquisition mode is as follows:
the running resistance is adjustedProximity distance->Posture stability->After dimensionless treatment, the method is according to the following formula:
，
the significance of the coefficients is:，/>and->，/>、/>Is a weight coefficient;
the method comprises the steps that the motion state characteristics of the satellite are identified through the operation states of the satellite obtained through prediction, corresponding adjustment schemes are matched for the states of the satellite in sequence, the operation state data of the satellite after the adjustment schemes are executed are obtained through prediction, a motion model of the satellite is built through the operation state data, and visual processing is conducted on the motion process obtained through prediction of the satellite.
Further, determining a satellite orbit coverage area as a monitoring area, dividing the monitoring area into a plurality of sub-areas, numbering each sub-area respectively, and inquiring to obtain the current distribution satellite density in each sub-areaSdWhen the satellites in the current subarea are in a communicable state, the data transmission quantity of each satellite is counted, and the data transmission density is obtainedDnThe method comprises the steps of carrying out a first treatment on the surface of the After the data are summarized, establishing a regional density set; generating a density index from the set of region densitiesIf the obtained Density index +.>And if the density threshold value is exceeded, an adjustment instruction is sent out.
Further, the density indexThe acquisition mode is as follows: density of satellitesSdData transmission densityDnPerforming linear normalization processing and mapping corresponding data values toInterval->And then according to the following formula:
，
wherein,for the mean value of the satellite density in the respective sub-region, < > where>The standard value of the satellite density is qualified,mean value of data transmission density in the respective subregion, < >>Qualified standard value of data transmission density, +.>At satellite density ofiValues in subregion>Data transmission density is atiValues within the subregion; weight coefficient: />，And->，/>，nThe number of subregions is a positive integer greater than 1.
Further, the operation states of all satellites in the monitoring area are monitored, and after operation state data are obtained, a satellite operation state set is built in a summarizing mode; preprocessing each item of data in the satellite running state set, and then extracting features to obtain data features which can be used for model training, and summarizing the data features to construct a model feature set;
usingBpConstructing an initial digital twin model by using a neural network, training and testing the constructed initial digital twin model, obtaining a trained initial digital twin model, and outputting the trained initial digital twin model as a satellite operation digital twin model; and predicting satellite states in the monitoring area by using the trained satellite operation digital twin model, obtaining corresponding prediction results, and generating a state prediction set.
Further, the attitude stability of the satellite is calculated and obtainedZtDetecting and obtaining the current running resistance of the satelliteFoAfter determining the current distance between the satellite and the target satellite, acquiring the adjacent distancePdThe method comprises the steps of carrying out a first treatment on the surface of the Comparing the above parameters with the predicted values respectively, and obtaining the difference values of the two parameters, respectively marked as running resistanceProximity distance->Posture stability->Summarizing the parameters to generate a state variable set;
generating satellite change index from state variable setIf the acquired satellite variation indexIf the change threshold value is exceeded, determining satellites to be adjusted, and marking the corresponding satellites to be adjusted respectively; the satellite change index of each satellite to be adjusted is +.>Is in accordance with the variation thresholdAnd (3) comparing the two, namely obtaining the ratio, sequencing a plurality of ratios from large to small, taking the sequencing as the adjustment priority of a plurality of satellites to be adjusted, and marking the corresponding satellites to be adjusted according to the adjustment priority.
Further, the operation state data of each satellite in the monitoring area obtained by prediction are summarized, the operation state characteristics of each satellite are identified according to the state data, the currently existing satellite adjustment schemes are collected, an adjustment scheme library is formed after the operation state data are summarized, the operation state characteristics of each satellite are combined with the correspondence of the adjustment schemes, and the corresponding adjustment schemes are adjusted and matched for each satellite to be adjusted in sequence according to the adjustment priority.
Further, after a corresponding adjustment scheme is matched with the satellite to be adjusted with the highest adjustment priority, the adjustment scheme is executed as input, the trained satellite operation digital twin model is used for predicting the states of all satellites in the monitoring area, operation state data of all satellites are obtained, and if the execution effect of the adjustment scheme fails to reach the expectation, the satellite operation digital twin model is combined for carrying out one or more corrections on parameters of the adjustment scheme until the adjustment scheme is feasible.
Further, executing the corrected adjustment scheme, predicting the state data of each satellite after execution by using a satellite operation digital twin model, acquiring an adjustment scheme corresponding to the satellite to be adjusted with the secondary priority based on the prediction result, correcting the adjustment scheme when the adjustment scheme is difficult to reach the expectation, and iterating until the corresponding adjustment scheme is matched or corrected for all the satellites to be adjusted, wherein the adjustment scheme is used as a secondary scheme.
Further, the trained satellite operation digital twin model predicts the operation state data of each satellite after the secondary scheme is executed, so as to obtain corresponding prediction results, and a satellite operation state prediction data set is generated after summarization;
acquiring the running state data of each satellite from a satellite running state prediction data set, matching the corresponding mathematical model or algorithm model by the data characteristics of the running state data, and building a satellite motion model after training; and converting the result obtained by calculating the mathematical digital twin model into an image or an animation by using computer graphics and a visualization technology.
An intelligent management system for a digital twin satellite constellation, comprising:
the detection unit is used for establishing a regional density set after acquiring the distribution state and the communication state of the satellites in each sub-region, generating a density index by the regional density set, and sending out an adjustment instruction if the acquired density index exceeds a density threshold value;
model construction unit for monitoring the operation state of each satellite and establishing satellite operation state set, and usingBpAcquiring satellite operation digital twin model output after neural network training, predicting the operation state of the satellite by using the model output, acquiring corresponding prediction results, and summarizing a plurality of prediction results to generate a state prediction set;
the evaluation unit acquires a plurality of satellite running state parameters in the state prediction set, acquires the difference value between the satellite running state parameters and the previous value, generates a state variable set after summarization, generates a satellite variation index from the state variable set, screens out satellites to be regulated, and confirms corresponding regulation priority;
the display unit is used for sequentially matching the states of the satellites with corresponding adjustment schemes, predicting and acquiring running state data of the satellites after the adjustment schemes are executed, establishing a satellite movement digital twin model according to the running state data, and performing visual processing on the movement process predicted and acquired by the satellites.
(III) beneficial effects
The invention provides an intelligent management system and method for a digital twin satellite group, which have the following beneficial effects:
1. by generating a density indexThe current distribution state of each satellite is evaluated, and if the current distribution state of the satellite is very uneven, the situation that at least part of the satellites are required to be defended is describedThe star state is adjusted, so that the satellite operation posture and the satellite operation state are adjusted more pertinently, the invalid investment can be reduced, and the adjustment efficiency is improved.
2. The satellite state in the monitoring area is predicted by using the trained satellite operation digital twin model, the operation state of the next period of the satellite can be obtained, a plurality of satellites with poorer operation states can be screened by predicting the satellite state, and the part to be regulated or corrected in the satellite can be determined, so that the operation state of the satellite is guaranteed.
3. Generating satellite change index from state variable setBy satellite variation index->The prediction states of the satellites are evaluated so as to screen out parts needing to be adjusted from the satellites, the priority of the satellites during adjustment is determined, the workload of adjustment can be reduced when the satellites need to be adjusted, the pertinence during screening is improved, the adjustment process of the satellites can be orderly carried out by determining the adjustment priority, the mutual interference among the satellites is avoided, and efficient management and intelligent management of satellite operation are realized.
4. Corresponding adjustment schemes are matched for each satellite, targeted adjustment is achieved, simulation analysis is conducted on each adjustment scheme on the basis of combining a satellite operation digital twin model, and correction effects are achieved, so that scheme effectiveness is guaranteed; on the basis of establishing a motion digital twin model, the running state and the path of the satellite are visually displayed, and when the running state of the satellite is predicted and adjusted, the satellite is convenient to observe and further adjust, and the management efficiency is improved as a whole.
Drawings
FIG. 1 is a schematic flow chart of a digital twin satellite group intelligent management method of the invention;
FIG. 2 is a schematic diagram of the digital twin satellite constellation intelligent management system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 and 2, the present invention provides an intelligent management method for digital twin satellite group, comprising:
dividing a satellite distribution area into a plurality of subareas, after acquiring the distribution state and the communication state of satellites in each subarea, establishing an area density set, and generating a density index from the area density setIf the obtained Density index +.>If the density threshold value is exceeded, an adjustment instruction is sent out;
the first step comprises the following steps:
step 101, determining a satellite orbit coverage area as a monitoring area, dividing the monitoring area into a plurality of sub-areas, numbering each sub-area respectively, and inquiring to obtain the current distribution satellite density in each sub-areaSdWhen the satellites in the current subarea are in a communicable state, the data transmission quantity of each satellite is counted, and the data transmission density is obtainedDnThe method comprises the steps of carrying out a first treatment on the surface of the After the data are summarized, establishing a regional density set;
step 102, generating a density index from the regional density setThe acquisition mode is as follows: density of satellitesSdData transmission densityDnPerforming linear normalization processing, and mapping corresponding data value to interval +.>And then according to the following formula:
，
wherein,for the mean value of the satellite density in the respective sub-region, < > where>The standard value of the satellite density is qualified,mean value of data transmission density in the respective subregion, < >>Qualified standard value of data transmission density, +.>At satellite density ofiValues in subregion>Data transmission density is atiValues within the subregion; weight coefficient: />，And->，/>，nThe number of subregions is a positive integer greater than 1.
Presetting a density threshold value according to historical data and the expectation of satellite operation states, and if the acquired density indexAnd if the density threshold value is exceeded, an adjustment instruction is sent out.
In use, the contents of steps 101 and 102 are combined:
by querying satellite states in each sub-region, satellite density in each sub-regionSdData transmission densityDnGenerates a density index based on (a)The current distribution state of each satellite is evaluated, if the current distribution state of the satellite is very uneven, the state of at least part of the satellites needs to be adjusted, so that the method has pertinence when the operation posture and the operation state of the satellites are adjusted, the ineffective investment can be reduced, and the adjustment efficiency is improved.
Step two, monitoring the running state of each satellite, establishing a satellite running state set, performing feature extraction, constructing a model feature set, and usingBpThe neural network is used for obtaining satellite operation digital twin model output after training, predicting the operation state of the satellite by using the neural network, obtaining corresponding prediction results, and summarizing a plurality of prediction results to generate a state prediction set;
the second step comprises the following steps:
step 201, monitoring the running state of each satellite in a monitoring area, at least acquiring data such as the position, orbit height, running speed and resistance of Wei Xingyun, the current inclination angle, the distance between adjacent satellites and the like, and after acquiring the running state data, summarizing and establishing a satellite running state set;
preprocessing each item of data in the satellite running state set, and then extracting features to obtain data features which can be used for model training, and summarizing the data features to construct a model feature set;
step 202, useBpThe neural network constructs an initial digital twin model after selecting a corresponding network architecture, and extracts from the model feature setTaking part of characteristic data as a training set and a testing set to train and test the constructed initial digital twin model, obtaining a trained initial digital twin model, and outputting the trained initial digital twin model as a satellite operation digital twin model;
predicting satellite states in a monitoring area by using a trained satellite operation digital twin model, obtaining corresponding prediction results after a prediction period, for example, after a day, and generating a state prediction set after integrating a plurality of prediction results;
in use, the contents of steps 201 and 202 are combined:
on the basis of the current running state of the satellite, the running state of each satellite is predicted, a satellite running state set is obtained, and the method is usedBpThe neural network is used for training and obtaining a satellite operation digital twin model, at the moment, the trained satellite operation digital twin model is used for predicting the satellite state in a monitoring area, so that the operation state of the satellite in the next period can be obtained, a plurality of satellites with poor operation states can be screened through predicting the satellite state, the part to be regulated or corrected in the satellite operation state is determined, and the operation state of the satellite is guaranteed.
Step three, acquiring a plurality of satellite running state parameters in a state prediction set, acquiring the difference value between the satellite running state parameters and a previous value, generating a state variable set after summarizing, and generating a satellite variation index from the state variable setBy satellite variation index->Screening out the satellite to be adjusted from a plurality of satellites, and confirming the corresponding adjustment priority;
the third step comprises the following steps:
step 301, calculating and obtaining the attitude stability of the satelliteZtFor specific ways, reference may be made to the following:
the calculation of the attitude stability of the satellite usually needs to be carried out by means of a specific algorithm and model, and the following two modes are more common: parameters such as angular velocity, acceleration, magnetic field intensity and the like of the satellite are calculated and acquired by utilizing data of attitude sensors such as a gyroscope, an accelerometer and the like through technologies such as data fusion, filtering and the like, and the stability of the attitude of the satellite is judged according to the stability of the parameters;
or simulating the attitude motion of the satellite in the orbit running process by establishing a dynamic model, and evaluating the stability of the satellite attitude according to the comparison of the actual attitude data and the simulation data.
Then, detecting and obtaining the current running resistance of the satelliteFoAfter determining the current distance between the satellite and the target satellite, acquiring the adjacent distancePdThe method comprises the steps of carrying out a first treatment on the surface of the Comparing the above parameters with the predicted values respectively, and obtaining the difference values of the two parameters, respectively marked as running resistanceProximity distance->Posture stability->Summarizing the parameters to generate a state variable set;
step 302, generating satellite change index from state variable setThe acquisition mode is as follows: running resistance +.>Proximity distance->Posture stability->After dimensionless treatment, the method is according to the following formula:
，
the significance of the coefficients is:，/>and->，/>、/>The specific value of the weight coefficient can be set by user adjustment or obtained by mathematical analysis software through simulation analysis;
presetting a change threshold according to satellite state operation data and the expectation of the satellite operation state, and if the acquired satellite change indexIf the change threshold value is exceeded, determining satellites to be adjusted, and marking the corresponding satellites to be adjusted respectively;
step 303, the satellite variation index of each satellite to be adjustedComparing with a variation threshold value, obtaining the ratio of the two, sequencing a plurality of ratios from large to small, taking the sequencing as the adjustment priority of a plurality of satellites to be adjusted, and marking the corresponding satellites to be adjusted by the adjustment priority;
in use, the contents of steps 301 to 303 are combined:
generating satellite variation index from state variable set based on obtaining prediction resultBy satellite variation index->For each ofThe prediction state of the satellite is evaluated so as to conveniently screen out the part needing to be adjusted from a plurality of satellites, further, the priority of each satellite during adjustment is determined, at the moment, through screening, when the plurality of satellites need to be adjusted, the workload of adjustment can be reduced, the pertinence during screening is improved, in addition, the adjustment process of each satellite can be orderly carried out through determining the adjustment priority, the mutual interference among the satellites is avoided, and the efficient management and intelligent management of satellite operation are realized.
Step four, identifying the motion state characteristics of the satellite by the predicted and acquired satellite operation states, sequentially matching corresponding adjustment schemes for each satellite state, predicting and acquiring the operation state data of each satellite after executing the adjustment schemes, establishing a satellite motion model by the operation state data, and carrying out visual processing on the motion process predicted and acquired by each satellite;
the fourth step comprises the following steps:
step 401, summarizing the operation state data of each satellite in the monitoring area obtained by prediction, identifying the operation state characteristics of each satellite according to the state data, collecting the currently existing satellite adjustment schemes, forming an adjustment scheme library after summarizing, and sequentially adjusting and matching the corresponding adjustment schemes for each satellite to be adjusted according to the adjustment priority by combining the correspondence of the operation state characteristics of each satellite and the adjustment schemes;
step 402, after a corresponding adjustment scheme is matched for the satellite to be adjusted with the highest adjustment priority, the adjustment scheme is used as input, the trained satellite operation digital twin model is used for predicting the state of each satellite in the monitoring area, the operation state data of each satellite is obtained, the target state data of each satellite operation is preset to be used as adjustment expectation, if the execution effect of the adjustment scheme fails to reach the expectation, the satellite operation digital twin model is combined for carrying out one or more corrections on the parameters of the adjustment scheme until the adjustment scheme is feasible;
in use, in combination with the contents of steps 401 and 402,
on the basis of the obtained prediction results, identifying and obtaining the running state characteristics of each satellite, so that corresponding adjustment schemes are matched for each satellite, and targeted adjustment is realized; meanwhile, on the basis of combining a satellite operation digital twin model, simulation analysis is carried out on each adjustment scheme, so that the correction effect is realized, and the effectiveness of the scheme can be ensured.
Step 403, executing the revised adjustment scheme, predicting each satellite state data after execution by a satellite operation digital twin model, acquiring an adjustment scheme corresponding to the satellite to be adjusted with the secondary priority based on the prediction result, revising the adjustment scheme when the adjustment scheme is difficult to reach the expectation, and iterating until the corresponding adjustment scheme is matched or revised for all the satellites to be adjusted, and taking the adjustment scheme as a secondary scheme;
step 404, predicting the running state data of each satellite after executing the secondary scheme by the trained satellite running digital twin model to obtain corresponding prediction results, and generating a satellite running state prediction data set after summarizing;
acquiring the running state data of each satellite from a satellite running state prediction data set, matching the corresponding mathematical model or algorithm model by the data characteristics of the running state data, and building a satellite motion model after training and correction; converting the result obtained by calculating the mathematical model into an image or an animation by utilizing computer graphics and a visualization technology;
for example usingOpenGLOr (b)UnitySuch as software to generate three-dimensional graphics and animations, while in order to obtain more realistic and fluent animation effects, optimization of the generated animation is required, including adjusting the frame rate of the animation, smoothing the motion trajectory, adding physical effects, etc.
In use, the contents of steps 403 to 404 are combined:
the method comprises the steps of obtaining an adjustment scheme aiming at each satellite to be adjusted after correction for a plurality of times, obtaining satellite running state data after each adjustment scheme is executed through prediction, and visually displaying the running state and the path of the satellite on the basis of establishing a motion model, so that the method is more convenient to observe and further adjust when the running state of the satellite is predicted and adjusted, and the management efficiency is improved as a whole.
Referring to fig. 1 and 2, the present invention provides an intelligent management system for digital twin satellite group, comprising:
the detection unit is used for establishing a regional density set after acquiring the distribution state and the communication state of the satellites in each sub-region, generating a density index by the regional density set, and sending out an adjustment instruction if the acquired density index exceeds a density threshold value;
model construction unit for monitoring the operation state of each satellite and establishing satellite operation state set, and usingBpAcquiring satellite operation digital twin model output after neural network training, predicting the operation state of the satellite by using the model output, acquiring corresponding prediction results, and summarizing a plurality of prediction results to generate a state prediction set;
the evaluation unit acquires a plurality of satellite running state parameters in the state prediction set, acquires the difference value between the satellite running state parameters and the previous value, generates a state variable set after summarization, generates a satellite variation index from the state variable set, screens out satellites to be regulated, and confirms corresponding regulation priority;
the display unit is used for sequentially matching the states of the satellites with corresponding adjustment schemes, predicting and acquiring the running state data of the satellites after the adjustment schemes are executed, establishing a satellite motion model according to the running state data, and performing visual processing on the motion process predicted and acquired by the satellites.
It should be noted that, as an alternative illustration, the above formulas are all the formulas with dimensions removed and their numerical values calculated, and the formulas are formulas with a large amount of collected data being simulated by software to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application.
Claims (10)
1. An intelligent management method for a digital twin satellite group is characterized by comprising the following steps of: comprises the following steps:
dividing a satellite distribution area into a plurality of subareas, acquiring the distribution state and the communication state of satellites in each subarea, establishing an area density set, and generating a density index from the area density setIf the obtained Density index +.>If the density threshold value is exceeded, an adjustment instruction is sent out;
monitoring the running state of each satellite, establishing a satellite running state set, performing feature extraction, constructing a model feature set, and usingBpThe neural network acquires the output of a satellite operation digital twin model after training, and uses the neural network to perform satellite operationPredicting the running state of the vehicle, acquiring corresponding prediction results, and summarizing a plurality of prediction results to generate a state prediction set;
acquiring a plurality of satellite running state parameters in a state prediction set, acquiring the difference value between the satellite running state parameters and a previous value, generating a state variable set after summarizing, and generating a satellite variation index from the state variable setBy satellite variation indexScreening out the satellite to be adjusted from a plurality of satellites, and confirming the corresponding adjustment priority;
wherein the satellite change indexThe acquisition mode is as follows: running resistance +.>Proximity distance->Posture stability->After dimensionless treatment, the method is according to the following formula:
，
the significance of the coefficients is:，/>and->，/>、/>Is a weight coefficient;
the method comprises the steps that the motion state characteristics of the satellite are identified through the operation states of the satellite obtained through prediction, corresponding adjustment schemes are matched for the states of the satellite in sequence, the operation state data of the satellite after the adjustment schemes are executed are obtained through prediction, a motion digital twin model of the satellite is built through the operation state data, and visual processing is conducted on the motion process obtained through prediction of the satellite.
2. The intelligent management method for digital twin satellite constellation according to claim 1, wherein:
determining a satellite orbit coverage area as a monitoring area, dividing the monitoring area into a plurality of sub-areas, and inquiring and obtaining the current distribution satellite density in each sub-areaSdWhen the satellites in the current subarea are in a communicable state, the data transmission quantity of each satellite is counted, and the data transmission density is obtainedDnThe method comprises the steps of carrying out a first treatment on the surface of the After the data are summarized, a regional density set is established, and a density index is generated from the regional density setIf the obtained Density index +.>And if the density threshold value is exceeded, an adjustment instruction is sent out.
3. The intelligent management method for the digital twin satellite constellation according to claim 2, wherein:
the density indexThe acquisition mode is as follows: density of satellitesSdNumber of timesDensity of data transmissionDnPerforming linear normalization processing, and mapping corresponding data value to interval +.>And then according to the following formula:
，
wherein,for the mean value of the satellite density in the respective sub-region, < > where>Standard value of satellite density, < >>Mean value of data transmission density in the respective subregion, < >>Qualified standard value of data transmission density, +.>At satellite density ofiValues in subregion>Data transmission density is atiValues within the subregion;
weight coefficient:，/>and->，/>，nThe number of subregions is a positive integer greater than 1.
4. The intelligent management method for digital twin satellite constellation according to claim 1, wherein:
monitoring the running states of all satellites in a monitoring area, and after acquiring running state data, summarizing to establish a satellite running state set; preprocessing each item of data in the satellite running state set, and then extracting features to obtain data features which can be used for model training, and summarizing the data features to construct a model feature set;
usingBpConstructing an initial digital twin model by using a neural network, training and testing the constructed initial digital twin model, obtaining a trained initial digital twin model, and outputting the trained initial digital twin model as a satellite operation digital twin model; and predicting satellite states in the monitoring area by using the trained satellite operation digital twin model, obtaining corresponding prediction results, and generating a state prediction set.
5. The intelligent management method for digital twin satellite constellation according to claim 1, wherein:
calculating and obtaining the attitude stability of the satelliteZtDetecting and obtaining the current running resistance of the satelliteFoAfter determining the current distance between the satellite and the target satellite, acquiring the adjacent distancePdComparing the above parameters with the pre-prediction values respectively, and obtaining the difference values of the two parameters, respectively marked as running resistanceProximity distance->Posture stability->Summarizing the parameters to generate a state variable set;
generating satellite change index from state variable setIf the acquired satellite variation index +.>If the change threshold value is exceeded, determining satellites to be adjusted, and marking the corresponding satellites to be adjusted respectively; the satellite change index of each satellite to be adjusted is +.>And comparing with the variation threshold value, acquiring the ratio of the two, sequencing a plurality of ratios from large to small, taking the sequencing as the adjustment priority of a plurality of satellites to be adjusted, and marking the corresponding satellites to be adjusted by the adjustment priority.
6. The intelligent management method for digital twin satellite constellation according to claim 1, wherein:
summarizing the operation state data of each satellite in the monitoring area obtained by prediction, identifying the operation state characteristics of each satellite according to the state data, collecting the currently existing satellite adjustment schemes, forming an adjustment scheme library after summarizing, and sequentially adjusting and matching the corresponding adjustment schemes for each satellite to be adjusted according to the adjustment priority by combining the correspondence of the operation state characteristics of each satellite and the adjustment schemes.
7. The intelligent management method for digital twin satellite constellation according to claim 6, wherein:
after matching the corresponding adjustment scheme for the satellite to be adjusted with the highest adjustment priority, taking the adjustment scheme as input, predicting the state of each satellite in the monitoring area by using the trained satellite operation digital twin model, acquiring the operation state data of each satellite, and if the execution effect of the adjustment scheme fails to reach the expectation, carrying out one or more corrections on the parameters of the adjustment scheme by combining the satellite operation digital twin model until the adjustment scheme is feasible.
8. The intelligent management method for digital twin satellite constellation according to claim 7, wherein:
and executing the revised adjustment scheme, predicting the state data of each satellite after execution by using a satellite operation digital twin model, acquiring an adjustment scheme corresponding to the satellite to be adjusted with the secondary priority based on the prediction result, revising the adjustment scheme when the adjustment scheme is difficult to reach the expectation, and iterating until the corresponding adjustment scheme is matched or revised for all the satellites to be adjusted, and taking the adjustment scheme as a secondary scheme.
9. The intelligent management method for digital twin satellite constellation according to claim 8, wherein:
predicting the running state data of each satellite after the secondary scheme is executed by the trained satellite running digital twin model to obtain a corresponding prediction result, and generating a satellite running state prediction data set after summarizing;
acquiring operation state data of each satellite from a satellite operation state prediction data set, matching corresponding mathematical models by data characteristics of the operation state data, and building a satellite motion model after training; the result of the mathematical model calculation is converted into an image or an animation by using computer graphics and a visualization technology.
10. A digital twin satellite constellation intelligent management system, to which the method according to any one of claims 1 to 9 is applied, characterized in that: comprising the following steps:
the detection unit is used for summarizing and establishing a regional density set after acquiring the distribution state and the communication state of the satellites in each sub-region, generating a density index by the regional density set, and sending out an adjustment instruction if the acquired density index exceeds a density threshold value;
model construction unit for monitoring the operation state of each satellite and establishing satellite operation state set, and usingBpAcquiring satellite operation digital twin model output after neural network training, predicting the operation state of the satellite by using the model output, acquiring corresponding prediction results, and summarizing a plurality of prediction results to generate a state prediction set;
the evaluation unit acquires a plurality of satellite running state parameters in the state prediction set, acquires the difference value between the satellite running state parameters and the previous value, generates a state variable set after summarization, generates a satellite variation index from the state variable set, screens out satellites to be regulated, and confirms corresponding regulation priority;
the display unit is used for sequentially matching the states of the satellites with corresponding adjustment schemes, predicting and acquiring the running state data of the satellites after the adjustment schemes are executed, establishing a satellite motion model according to the running state data, and performing visual processing on the motion process predicted and acquired by the satellites.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410240947.3A CN117828999B (en) | 2024-03-04 | 2024-03-04 | Digital twin satellite group intelligent management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410240947.3A CN117828999B (en) | 2024-03-04 | 2024-03-04 | Digital twin satellite group intelligent management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117828999A true CN117828999A (en) | 2024-04-05 |
| CN117828999B CN117828999B (en) | 2024-05-28 |
Family
ID=90519514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410240947.3A Active CN117828999B (en) | 2024-03-04 | 2024-03-04 | Digital twin satellite group intelligent management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117828999B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2689855A1 (en) * | 1991-12-21 | 1993-10-15 | Deutsche Forsch Luft Raumfahrt | Coordinated position maintenance of geostationary satellite cluster |
| CA2241377A1 (en) * | 1997-07-22 | 1999-01-22 | Lucent Technologies Inc. | Mobile location estimation in a wireless system using designated time intervals of suspended communication |
| KR20010056476A (en) * | 1999-12-15 | 2001-07-04 | 박종섭 | Method for optimally designing low orbit satellite constellation for global mobile personal communication system service |
| CN105049110A (en) * | 2015-07-31 | 2015-11-11 | 上海卫星工程研究所 | Distributed microsatellite group management system |
| CN112381412A (en) * | 2020-11-16 | 2021-02-19 | 北京航空航天大学 | Digital twin satellite pulsating type general assembly distributed management and control system |
| CN115392077A (en) * | 2022-08-16 | 2022-11-25 | 中国人民解放军军事科学院国防科技创新研究院 | Satellite physical field level digital twin model construction method based on deep learning |
| US20230067081A1 (en) * | 2021-08-31 | 2023-03-02 | Vilnius Gediminas Technical University | System and method for real-time creation and execution of a human Digital Twin |
| CN115902953A (en) * | 2022-10-25 | 2023-04-04 | 重庆邮电大学 | Satellite state monitoring method based on digital twins |
| CN116227561A (en) * | 2023-02-17 | 2023-06-06 | 电子科技大学 | Satellite orbit error prediction method based on digital twin and container technology |
-
2024
- 2024-03-04 CN CN202410240947.3A patent/CN117828999B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2689855A1 (en) * | 1991-12-21 | 1993-10-15 | Deutsche Forsch Luft Raumfahrt | Coordinated position maintenance of geostationary satellite cluster |
| CA2241377A1 (en) * | 1997-07-22 | 1999-01-22 | Lucent Technologies Inc. | Mobile location estimation in a wireless system using designated time intervals of suspended communication |
| KR20010056476A (en) * | 1999-12-15 | 2001-07-04 | 박종섭 | Method for optimally designing low orbit satellite constellation for global mobile personal communication system service |
| CN105049110A (en) * | 2015-07-31 | 2015-11-11 | 上海卫星工程研究所 | Distributed microsatellite group management system |
| CN112381412A (en) * | 2020-11-16 | 2021-02-19 | 北京航空航天大学 | Digital twin satellite pulsating type general assembly distributed management and control system |
| US20230067081A1 (en) * | 2021-08-31 | 2023-03-02 | Vilnius Gediminas Technical University | System and method for real-time creation and execution of a human Digital Twin |
| CN115392077A (en) * | 2022-08-16 | 2022-11-25 | 中国人民解放军军事科学院国防科技创新研究院 | Satellite physical field level digital twin model construction method based on deep learning |
| CN115902953A (en) * | 2022-10-25 | 2023-04-04 | 重庆邮电大学 | Satellite state monitoring method based on digital twins |
| CN116227561A (en) * | 2023-02-17 | 2023-06-06 | 电子科技大学 | Satellite orbit error prediction method based on digital twin and container technology |
Non-Patent Citations (1)
| Title |
|---|
| 罗军;唐国金;: "空间监视卫星对特定LEO目标观测的姿态优化", 航天控制, no. 01, 15 February 2017 (2017-02-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117828999B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Heintz et al. | From images to traffic behavior-a uav tracking and monitoring application | |
| JPWO2011158363A1 (en) | Solar radiation intensity prediction system and photovoltaic power generation output prediction system | |
| CN102870137A (en) | Data mining method and system for estimating relative 3D velocity and acceleration projection functions based on 2D motions | |
| CN113344473B (en) | Optimization method and device for ocean target cooperative detection device | |
| CN117575550B (en) | BIM technology-based three-dimensional visual management system for wind farm data | |
| Krzysztofowicz et al. | A methodology for evaluation of flood forecast‐response systems: 2. Theory | |
| CN116627157B (en) | Carrier rocket operation control method, device and equipment | |
| CN113792478A (en) | Heat source layout temperature field reliability analysis method based on integrated depth proxy model | |
| JP2023543647A (en) | Near-space atmospheric state simulation method and device based on quantum walk | |
| CN114167898A (en) | Global path planning method and system for data collection of unmanned aerial vehicle | |
| CN113743019A (en) | Digital twin enhanced complex equipment health monitoring method | |
| CN113778042B (en) | Industrial control equipment instruction simulation operation communication system based on informatization modeling | |
| CN115270404A (en) | Design system and method for space-based information system efficiency simulation architecture | |
| CN117828999B (en) | Digital twin satellite group intelligent management system and method | |
| Gu | On-demand data assimilation of large-scale spatial temporal systems using sequential Monte Carlo methods | |
| CN117556501A (en) | Command scheduling scene simulation method based on CIM model | |
| CN113485438B (en) | Intelligent planning method and system for space monitoring path of unmanned aerial vehicle | |
| CN115414621B (en) | Intelligent control method and related device for fire water monitor | |
| CN111752237B (en) | Automatic process graphics generation | |
| CN108134680B (en) | A kind of systematic survey node optimization configuration method based on Bayesian network | |
| CN115510767A (en) | Regional air temperature prediction method based on deep space-time network | |
| CN113678468B (en) | Machine learning device | |
| CN111950878A (en) | System contribution rate evaluation method and system for ship detection by remote sensing satellite | |
| CN112183921A (en) | Monitoring task planning method and system for remote sensing satellite networking | |
| CN110084358A (en) | A kind of smart home multi-Sensor Information Fusion Approach neural network based |
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 |