CN115758706B - Modeling method, model and acquisition method of satellite east-west maintenance strategy model - Google Patents
Modeling method, model and acquisition method of satellite east-west maintenance strategy model Download PDFInfo
- Publication number
- CN115758706B CN115758706B CN202211408082.4A CN202211408082A CN115758706B CN 115758706 B CN115758706 B CN 115758706B CN 202211408082 A CN202211408082 A CN 202211408082A CN 115758706 B CN115758706 B CN 115758706B
- Authority
- CN
- China
- Prior art keywords
- satellite
- moment
- state
- model
- tangential
- 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
Images
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the aerospace field, and provides a modeling method, a model, an acquisition method, equipment and a medium of a satellite east-west maintenance strategy model, wherein the modeling method comprises the following steps: s1: acquiring a plurality of groups of satellite training state data groups; s2: obtaining all tangential control behaviors and Q values of corresponding outputs after the initial moment; s3: acquiring the satellite state at the current moment and the tangential control behavior executed by the satellite; s4: obtaining rewards and satellite states at the next moment; s5: storing the satellite combination state data set in an experience pool; s6: calculating a target value; s7: calculating an error according to the loss function; s8: updating the Q value; taking the satellite state at the next moment as the satellite state at the current moment; s9: repeating steps S3-S8 of the expected track control times; updating the weight parameters of the target neural network after repeating the steps S3-S8 of the appointed iteration times; s10: steps S2-S9 are repeatedly performed. The scheme can obtain an optimal decision strategy and reduce the consumption of satellite fuel.
Description
Technical Field
The invention relates to the technical field of aerospace, in particular to a modeling method, a modeling model, an acquisition method, equipment and a medium of a satellite east-west maintenance strategy model based on Nature DQN.
Background
With the continuous development of human aerospace activities, more and more remote sensing satellites provide assistance for daily life of people.
The GEO satellite is influenced by the sun and moon gravitation and the non-spherical perturbation of the earth in the running process, so that drifting occurs in the east-west direction, and the GEO three-axis stable satellite has a vital effect on maintaining and controlling the east-west position of the GEO three-axis stable satellite in the aerospace field.
The prior art method firstly analyzes that the horizontal longitude and the eccentricity of the satellite are changed due to the influence of various perturbation forces such as the shape of the earth, the solar pressure and the like on the satellite in the orbit running process, then models according to the perturbation forces and formulates a strategy for maintaining things, and further optimizes the maintaining parameters and calculates the consumption of the propellant. In the prior art, the satellite cannot be accurately modeled due to the complexity of space stress and uncertainty of parameters of the satellite, and the satellite has multiple parameters and complex calculation, so that the accuracy of east-west control of the satellite is influenced, and more fuel can be consumed.
Therefore, there is a need to develop a modeling method, a model, an acquisition method, equipment and a medium for a satellite east-west maintenance strategy model based on Nature DQN, reduce modeling difficulty, and accurately calculate the east-west maintenance strategy.
Disclosure of Invention
The invention aims to provide a modeling method, a modeling model, an acquisition method, equipment and a medium for a satellite east-west maintenance strategy model, which do not need to carry out complex modeling when carrying out east-west position maintenance on a GEO triaxial steady satellite, do not need to consider the complexity of space stress and the uncertainty of the satellite self parameters, have strong behavior decision-making capability in reinforcement learning, can obtain an optimal decision strategy and reduce the consumption of satellite fuel.
In order to solve the above technical problems, as one aspect of the present invention, there is provided a modeling method of a satellite east-west maintenance strategy model based on Nature DQN, comprising the steps of:
s1: initializing a model, and acquiring a plurality of groups of satellite training state data groups, wherein each group of satellite training state data groups comprises an initial state of a satellite, a plurality of expected orbit control moments and expected orbit control times; the initial state of each satellite comprises an initial moment satellite state; satellite states include flat longitude and eccentricity vectors;
s2: inputting an initial time satellite state of a group of satellite training state data sets into the model to obtain all tangential control behaviors and Q values corresponding to the tangential control behaviors after the initial time;
s3: acquiring the satellite state at the current moment, and acquiring tangential control behaviors executed by the satellite according to a greedy strategy;
s4: executing tangential control behavior to obtain satellite state and actual orbit control time at the next moment, and obtaining rewards according to the actual orbit control time and the thing holding strategy rewarding function; the thing retention policy rewards function employs equation 1:
wherein r is t Rewards obtained by tangential control actions for the satellites at the current moment, wherein deltat is a time interval from the actual orbit control moment and is obtained according to the current moment and the actual orbit control moment; the longer Δt, the longer the hold period, the higher the prize; t is t 0 The expected track control time closest to the current time; t is the current moment;
s5: the satellite state at the current moment, the tangential control behavior executed by the satellite, rewards and the satellite state at the next moment are used as a group of satellite combination state data sets to be stored in an experience pool;
s6: taking out a plurality of groups of satellite combination state data sets from the experience pool, and calculating a target value of each satellite combination state data set according to the target neural network weight parameters;
s7: calculating an error according to the loss function, and updating the weight parameter of the current neural network;
s8: updating the Q value according to the value function; taking the satellite state at the next moment as the satellite state at the current moment;
s9: repeating steps S3-S8, the number of times steps S3-S8 are performed being equal to the expected orbit control number of the set of satellite training state data sets; after each repetition of the steps S3-S8 of the appointed iteration times, updating the weight parameters of the target neural network according to the weight parameters of the current neural network;
s10: steps S2-S9 are repeated until all the data of the satellite training state data set has been entered.
According to an exemplary embodiment of the present invention, initializing the model includes defining a loss function in step S1.
According to an exemplary embodiment of the present invention, the input of the model is the satellite state, and the output is the return value (Q value) after the tangential control action performed by the satellite is performed.
According to an example embodiment of the invention, the satellite states include: flat longitude drift rate, eccentricity vector, tilt angle vector and flat longitude. The flat longitude drift rate is denoted by L, the eccentricity vector is denoted by e, the tilt angle vector is denoted by i, and the flat longitude is denoted by R.
According to an exemplary embodiment of the present invention, in step S3, the current satellite state is the initial satellite state at the time of the initial cycle.
According to an exemplary embodiment of the present invention, in step S3, the method for obtaining tangential control actions performed by a satellite according to a greedy strategy includes: the satellite randomly selects tangential control behaviors according to the first specified probability or executes the tangential control behaviors corresponding to the maximum Q value according to the second specified probability; the sum of the first specified probability and the second specified probability is equal to 1.
According to an exemplary embodiment of the present invention, in step S6, the method for calculating the target value of each satellite combination status data set according to the target neural network weight parameter uses formula 2:
wherein y is j Indicating the target value, gamma being the discount value, theta'As the weight parameter of the target neural network,
representing the maximum Q value, s, of a satellite in a set of satellite combination state data sets after the next moment in time the satellite performs tangential control action a j+1 Representing the next moment in the set of satellite combined state data sets, a represents the tangential control behaviour performed by the satellite at the current moment in the set of satellite combined state data sets, r j Representing rewards in a set of satellite combination status data sets.
According to an exemplary embodiment of the present invention, in step S7, the loss function uses formula 3:
wherein y is j Represents the target value, θ is the current neural network weight parameter, Q (s j ，a j The method comprises the steps of carrying out a first treatment on the surface of the θ) represents the current time satellite performing tangential control behavior a in a set of satellite combined state data sets j Q, s after j Representing the current time satellite state, a, in a set of satellite combined state data sets j And representing tangential control actions performed by the satellite at the current moment, wherein m is the number of satellite combined state data sets.
According to an exemplary embodiment of the present invention, in step S8, the method for updating the Q value according to the value function uses formula 4:
Q(s t ，a t )←Q(s t ，a t )+α[r t +γmax Q(s t+1 ，a t )-Q(s t ，a t )] (4)；
wherein Q(s) on the left side of the arrow t ，a t ) The satellite-performed tangential control behaviour a representing the updated current moment t The Q value at the rear, Q(s) at the right side of the arrow t ，a t ) The satellite-executed tangential control behavior a representing the current moment before updating t Q(s) t+1 ，a t ) Satellite execution at the next time representing the current time before updateLine tangential control behavior a t The Q value, alpha is weight, gamma is discount value, s t Representing the satellite state at the current moment, a t Representing the tangential control behavior performed by the satellite at the current moment s t+1 Representing satellite state at next moment of current moment, r t Indicating a reward.
the time t is the current time, and the time t+1 is the time next to the current time.
As a second aspect of the present invention, there is provided a Nature DQN-based satellite east-west maintenance strategy model, which is modeled by a modeling method of the Nature DQN-based satellite east-west maintenance strategy model.
As a third aspect of the present invention, there is provided a method for obtaining an optimal east-west maintenance strategy for a satellite, wherein a modeling method of the east-west maintenance strategy model for a satellite based on Nature DQN is adopted to build the east-west maintenance strategy model for a satellite based on Nature DQN;
obtaining an optimal strategy according to the model;
the method for obtaining the optimal strategy according to the model adopts a formula 5:
wherein pi represents the strategy of tangential control of the satellite, pi * Represents the optimal tangential control strategy learned by the model, namely, the satellite passes through the strategy pi under the condition that the satellite state at the initial moment is s * Yielding the greatest return under control action a.
As a fourth aspect of the present invention, there is provided an electronic apparatus comprising:
one or more processors;
a storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a modeling method of the Nature DQN-based satellite east-west maintenance policy model.
As a fifth aspect of the present invention, there is provided a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements a modeling method of the Nature DQN-based satellite east-west maintenance policy model.
The beneficial effects of the invention are as follows:
according to the scheme, modeling is performed through the neural network, deep reinforcement learning and decision making are performed by utilizing current satellite state data, complex modeling is not needed by utilizing various perturbation forces received by the satellite in the orbit running process, an optimal east-west control strategy can be obtained, consumption of satellite fuel can be reduced, and the method has important significance and value for practical aerospace application.
Drawings
Fig. 1 schematically shows a step diagram of a modeling method of a satellite east-west maintenance strategy model based on Nature DQN.
Fig. 2 schematically shows a block diagram of an electronic device.
Fig. 3 schematically shows a block diagram of a computer readable medium.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present application. One skilled in the relevant art will recognize, however, that the aspects of the application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another element. Thus, a first component discussed below could be termed a second component without departing from the teachings of the present application concept. As used herein, the term "and/or" includes any one of the associated listed items and all combinations of one or more.
Those skilled in the art will appreciate that the drawings are schematic representations of example embodiments, and that the modules or flows in the drawings are not necessarily required to practice the present application, and therefore, should not be taken to limit the scope of the present application.
The scheme obtains observation information from the environment based on the perception capability with strong deep learning, and obtains an expected return value to evaluate the footstock value based on the decision capability with strong reinforcement learning. The entire learning process can be described as: at a certain moment, the satellite interacts with the flying environment to acquire the observation information, the current state information is mapped into corresponding actions (control actions) through the neural network, the environment reacts to the actions to obtain corresponding reward values and next observation information, and the complete interaction information is stored in the experience pool. By continuously cycling the above processes, an optimal strategy for achieving the objective can be finally obtained.
The satellite in the scheme is a GEO triaxial stabilized satellite. Geosynchronous orbit (GEO), which refers to a circular orbit around the earth where satellites travel about 36000 km above the earth's equator. Because satellites synchronize with earth's rotation around the earth's period of travel, satellites that are in a relatively stationary state with respect to the earth are referred to as "geostationary satellites" for short, and are also referred to as "stationary satellites" or "fixed satellites". Triaxial stabilization is that the satellite does not rotate, and the body is stable in the directions X, Y, Z, in other words, maintains a certain attitude relation with the earth.
Deep Q Networks (DQN) algorithms are one type of network in Deep reinforcement learning, which is a combination of Deep learning and Q learning. Since it combines the advantages of reinforcement learning and deep learning, it has been widely used in various fields at present.
Deep reinforcement learning is used as a new research hotspot in the field of artificial intelligence, and combines deep learning and reinforcement learning, so that direct control and decision from original input to output are realized through an end-to-end learning mode. Because the deep learning is based on a neural network structure, the deep learning has stronger perceptibility to the environment, but lacks a certain decision control capability; whereas reinforcement learning happens to have very strong behavioural decision-making capability. Therefore, the deep reinforcement learning combines the perception capability of the deep learning and the decision capability of the reinforcement learning, has complementary advantages, and can directly learn the control strategy from the high-dimensional original data. Since the deep reinforcement learning method is proposed, a substantial breakthrough is made in a plurality of tasks requiring to perceive high-dimensional original input data and decision control, and the deep reinforcement learning can solve the problems of difficult modeling and difficult planning due to the end-to-end learning advantage of the deep learning.
The DQN algorithm uses the same network for calculating the target value and the current value, i.e. the target value is calculated by using parameters in the Q network to be trained currently, and the target value is used for updating the parameters of the network, so that the two are circularly dependent, and the convergence of the algorithm is not facilitated. Compared with the DQN, the Nature DQN is added with a target network, the dependency relationship between the target Q value calculation and the Q network parameters to be updated is reduced through a double-network structure, and the advantages of reinforcement learning and deep learning are integrated, so that the stability of the DQN algorithm is greatly improved.
Nature DQN reduces the correlation between the target value of the calculated target network and the current network parameters by using two independent but identical Q networks (one as the current Q network and the other as the target Q network). The current network updates the target network at intervals of a certain step length C by copying the weight parameters of the current network to the target network, and the target Q value is kept unchanged for a period of time by the double-network structure, so that the correlation between the calculated target Q value and the current network parameters is reduced, and the convergence and stability of the algorithm are improved.
As a first embodiment of the present invention, there is provided a modeling method of a satellite east-west maintenance strategy model based on Nature DQN, as shown in fig. 1, comprising the steps of:
s1: initializing a model to obtain a plurality of groups of satellite training state data sets, wherein each group of satellite psychological state data sets comprises an initial state of a satellite, a plurality of expected orbit control moments and expected orbit control times; the initial state of each satellite comprises an initial moment satellite state; satellite states include flat longitude and eccentricity vectors.
The input of the model is satellite state, and the output is the return value (Q value) after the satellite executes tangential control action.
The satellite states include: flat longitude drift rate, eccentricity vector, tilt angle vector, flat longitude. The flat longitude drift rate is denoted by L, the eccentricity vector is denoted by e, the tilt angle vector is denoted by i, and the flat longitude is denoted by R.
The method for initializing the model comprises the following steps: defining a loss function; initializing the capacity of an experience pool to be N, wherein the experience pool is used for storing training samples; initializing a current neural network weight parameter theta and a target neural network weight parameter theta ', theta' =theta of a network model; the input of the initialization network is satellite state s, and the calculated network output is return value O after the satellite executes tangential control action.
The satellite training state data sets form a data set, the satellite state data in the data set is more than or equal to 100 groups, and the more the satellite state data is, the more accurate the model training result is.
The data of the satellite training state data sets are the data of the training set, and can be simulation data or combination of the simulation data and real data. The time line in a time period comprises a plurality of time points, the states of the satellites at each time point are different, and different effects can be obtained when the orbit control strategy is executed at different time points. According to the scheme, through the plurality of sets of satellite training state data sets, the satellite state of each set of satellite at the initial time corresponds to the satellite state of one time point, and the time points corresponding to the initial time of each set of satellite training state data sets are different, namely the initial time of each set of satellite training state data sets is different.
S2: and inputting an initial time satellite state of a group of satellite training state data sets into the model to obtain all tangential control behaviors and Q values corresponding to the tangential control behaviors after the initial time.
And after the satellite at the initial moment executes tangential control action, obtaining the satellite state at the next moment. And after the satellite at the next moment executes the tangential control action, obtaining the satellite state at the next moment. And the like, the tangential control behaviors at a plurality of next moments are obtained.
S3: and acquiring the satellite state at the current moment, and acquiring tangential control behaviors executed by the satellite according to a greedy strategy.
And in the initial cycle, the satellite state at the current moment is the satellite state at the initial moment.
The method for obtaining the tangential control action executed by the satellite according to the greedy strategy comprises the following steps: the satellite randomly selects tangential control behaviors according to the first specified probability or executes the tangential control behaviors corresponding to the maximum Q value according to the second specified probability; the sum of the first specified probability and the second specified probability is equal to 1.
If the first specified probability is greater than the second specified probability, the method for obtaining tangential control behavior executed by the satellite according to the greedy strategy adopts the following steps: the satellite randomly selects tangential control behaviors with a first specified probability;
if the second specified probability is greater than the first specified probability, the method for obtaining tangential control behavior executed by the satellite according to the greedy strategy adopts the following steps: the satellite executes tangential control behaviors corresponding to the maximum Q value according to the second designated probability;
if the first specified probability is equal to the second specified probability, selecting one of the methods for obtaining tangential control actions executed by the satellite according to a greedy strategy: the satellite randomly selects the tangential control behavior with a first specified probability or executes the tangential control behavior corresponding to the maximum Q value with a second specified probability.
The greedy strategy is epsilon-greedy strategy.
The first specified probability is epsilon, which decreases with increasing iteration number.
The tangential control behavior executed by the satellite at the current moment is a t 。
S4: executing tangential control behavior to obtain satellite states at the next moment and actual orbit control moment; and rewarding according to the actual track control moment and the thing holding strategy rewarding function.
The drift of the satellite in the east-west direction consists of two parts: one is earth shape perturbation to drift the longitude of the satellite, and the other is eccentricity perturbation due to solar pressure to cause the longitude of the satellite to oscillate in a daily cycle. The east-west maintenance of the satellite mainly includes flat longitude maintenance and eccentricity maintenance. The flat longitude maintenance mainly uses east-west maneuver to correct the drift rate of satellites, and one satellite is maintained in a narrower orbit window; in the satellite eccentricity vector maintenance strategy, the sun pointing near-place strategy is a relatively common method, and the method enables the flat eccentricity vector of the satellite to be always maintained in an eccentricity control circle in a control period, and enables the average direction of the connecting line from the center of the control circle to the end point of the flat eccentricity vector to point in the sun direction.
In the two-body problem, the flat longitude (mean longitude) is a longitude value of the movement of the object on an imaginary circular orbit with an orbit inclination of 0.
Eccentricity (Eccentricity) is a mathematical quantity used to describe the shape of a conic track. Defined as the ratio of the distance of the curve to the fixed point (focal point) to the distance to the fixed line (quasi-line). For ellipses, the eccentricity is the ratio of the distance between the two foci (focal length) to the length of the major axis. The eccentricity is generally denoted by e.
The method for obtaining the satellite flat longitude adopts the following formula:
wherein R represents the satellite plane longitude, a s Is the semi-long axis of the geostationary orbit, a 0 Is the orbit semi-long axis of the satellite;
the satellite eccentricity vector obtaining method adopts the following formula:
wherein e represents the eccentricity of the satellite, and the two-dimensional eccentricity vector of the satellite in orbit is (e x ，e y ) Omega represents the satellite rising intersection point right ascent, omega represents the near-place argument.
Tangential thrust and radial thrust both belong to in-plane maneuvers. Maneuver with tangential thrust is called tangential control (also known as east-west control or longitude control) and can change the satellite's flat longitude drift rate and eccentricity vector. The maneuver of the radial thrust only changes the eccentricity vector of the satellite, but the radial thrust with the same magnitude can only achieve half of the tangential thrust. Tangential control is more efficient than radial control. Therefore, the things of the satellite keep maneuvering mainly by tangential thrust, and radial thrust is rarely adopted.
Tangential control refers to the maneuvering of a satellite in the orbital plane along the direction of velocity.
Since tangential maneuvers can not only cause changes in the eccentricity vector, but also in the orbit semi-major axis, to optimize ground measurement and control effort and reduce fuel consumption, the ideal state is maintained by generally keeping the satellite longitude and latitude on the same control period as the eccentricity maintenance period, while maintaining control of the satellite's eccentricity vector and longitude by using the optimal criteria for maneuvering fuel consumption in the plane.
The goal of the satellite east-west maintenance strategy problem is to maintain the satellite east-west position while minimizing fuel consumption as much as possible. The velocity impulse required for the east-west position maintaining control is mainly used for the maintaining control of the state. Considering that a large amount of manual work is required for each control of the satellite, the fewer the number of controls, the lower the risk, which requires a longer period for east-west holding of the satellite.
The control amount of the satellite at time t determines the next time of orbit control on the premise of controlling the same amount of fuel consumed each time. R is R 0 、e 0 Plane longitude and eccentricity, ΔR, respectively, of a nominal track s 、Δe s The circle radius is respectively kept for the flat longitude and the eccentricity, and after the satellite is controlled at the time t (a certain time), the time when the flat longitude or the eccentricity of the satellite exceeds the keeping range is obtained according to the extrapolated ephemeris. Based on the purpose of keeping the satellite flat longitude and the eccentricity long in period, a rewarding strategy at the time t is designed. Thus, the east-west retention policy bonus function employs equation 1:
wherein r is t Rewards obtained by tangential control actions for the satellites at the current moment, wherein deltat is a time interval from the actual orbit control moment and is obtained according to the current moment and the actual orbit control moment; t is t 0 The expected track control time closest to the current time; t is the current time. Obviously, the longer the interval (Δt), the longer the hold period, the higher the prize.
Δt=t1-t; t1 is the actual orbit control time (the time when the tangential control action is needed next time). The actual orbit control time is the time of the tangential control to be performed by extrapolation, i.e. the time when the flat longitude or the eccentricity vector exceeds a predetermined range.
S5: the satellite state at the current moment, the tangential control behavior executed by the satellite, the rewards and the satellite state at the next moment are stored as a set of satellite combination state data sets in an experience pool.
S6: and taking out a plurality of groups of satellite combination state data sets from the experience pool, and calculating the target value of each satellite combination state data set according to the target neural network weight parameter.
The number of satellite combined state data sets is m, m is a natural number greater than 0, and m is less than the number of satellite training state data sets. The m sets of satellite combined state data sets are small batches of state data sets. The number of satellite combined state data sets is determined from the data set of satellite training state data sets.
The method for calculating the target value of each satellite combination state data set according to the target neural network weight parameters adopts a formula 2:
wherein y is j Representing the target value, gamma being the discount value (attenuation factor), theta' being the target neural network weight parameter,
representing the maximum Q value, s, of a satellite in a set of satellite combination state data sets after the next moment in time the satellite performs tangential control action a j+1 Representing the next moment in the set of satellite combined state data sets, a represents the tangential control behaviour performed by the satellite at the current moment in the set of satellite combined state data sets, r j Representing rewards in a set of satellite combination status data sets.
And stopping the task to obtain model convergence or iteration completion. When s is j+1 When model convergence or iteration is completed, y i Equal to r j The method comprises the steps of carrying out a first treatment on the surface of the When s is j+1 When model convergence or iteration is not completed, y i Equal to
The conditions for model convergence are: the error calculated by the loss function is within a specified range.
The iteration is completed under the following conditions: all steps are performed.
S7: and calculating errors according to the loss function, and updating the weight parameters of the current neural network.
The error is also calculated from the target value.
The loss function uses equation 3:
wherein y is j Represents the target value, θ is the current neural network weight parameter, Q (s j ，a j The method comprises the steps of carrying out a first treatment on the surface of the θ) represents the current time satellite execution control behavior a in a set of satellite combination state data sets j Q, s after j Representing the current time satellite state, a, in a set of satellite combined state data sets j Represents the tangential control behavior performed by the satellite at the current moment, r j Representing rewards in a set of satellite combination status data sets; m is the number of satellite combined state data sets.
The error is the result of the loss function calculation using equation 3.
The current neural network weight parameters are updated by a random gradient descent method (SGD).
r t 、a t 、s t 、s t+1 Samples in a dataset representing a satellite training state dataset, r j 、a j 、s j 、s j+1 Representing samples in the experience pool.
And the steps S5-S7 are used for adjusting the parameters of the model, so that the calculation accuracy of the model is higher.
S8: updating the Q value according to the value function; the satellite state at the next moment is taken as the satellite state at the current moment.
The method of updating the Q value according to the value function employs equation 4:
Q(s t ，a t )←Q(s t ，a t )+α[r t +γmax Q(s t+1 ，a t )-Q(s t ，a t )] (4)；
wherein Q(s) on the left side of the arrow t ，a t ) The satellite-performed tangential control behaviour a representing the updated current moment t The Q value at the rear, Q(s) at the right side of the arrow t ，a t ) The satellite-executed tangential control behavior a representing the current moment before updating t Q(s) t+1 ，a t ) The satellite-executed tangential control behavior a representing the next time to the current time before updating t The Q value, alpha is weight, gamma is discount value (attenuation factor), s t Representing the satellite state at the current moment, a t Representing the tangential control behavior performed by the satellite at the current moment s t+1 Representing satellite state at next moment of current moment, r t Indicating a reward.
Wherein alpha and gamma are both in the range of 0 to 1.
S9: repeating steps S3-S8, the number of times steps S3-S8 are performed being equal to the expected orbit control number of the set of satellite training state data sets; and after each step S3-S8 of the appointed iteration times is repeatedly executed, updating the weight parameters of the target neural network according to the weight parameters of the current neural network.
And after each iteration of the designated iteration times is completed, updating the target neural network weight parameter into the current neural network weight parameter.
S10: steps S2-S9 are repeated until all the data of the satellite training state data set has been entered.
According to the modeling method, satellite training state data is used as input of a neural network model, generated return values are used as output, a Nature DQN neural network is adopted, complex modeling is not needed by utilizing various perturbation forces received by satellites in the orbit running process, deep reinforcement learning is directly adopted to learn and make decisions, the DQN algorithm is based on improvement, the modeling method is suitable for training a large-scale neural network, stability of the DQN algorithm is greatly improved, an optimal thing control strategy can be obtained, and consumption of satellite fuel can be reduced.
According to a second specific embodiment of the invention, the invention provides a satellite east-west maintenance strategy model based on Nature DQN, and the modeling method of the satellite east-west maintenance strategy model based on the Nature DQN of the first embodiment is adopted for modeling.
According to a third specific embodiment of the invention, the invention provides a method for acquiring a satellite east-west maintenance optimal strategy, and the method for modeling the satellite east-west maintenance strategy model based on the Nature DQN of the first embodiment is adopted to establish the satellite east-west maintenance strategy model based on the Nature DQN;
and obtaining an optimal strategy according to the model.
The method for obtaining the optimal strategy according to the model adopts the formula 5:
wherein pi represents the strategy of tangential control of the satellite, pi * Represents the optimal tangential control strategy learned by the model, namely, the satellite passes through the strategy pi under the condition that the satellite state at the initial moment is s * Yielding the greatest return under tangential control behavior a.
According to a fourth embodiment of the present invention, an electronic device is provided, as shown in fig. 2, and fig. 2 is a block diagram of an electronic device according to an exemplary embodiment.
An electronic device 200 according to this embodiment of the present application is described below with reference to fig. 2. The electronic device 200 shown in fig. 2 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments herein.
As shown in fig. 2, the electronic device 200 is in the form of a general purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one memory unit 220, a bus 230 connecting the different system components (including the memory unit 220 and the processing unit 210), a display unit 240, and the like.
Wherein the storage unit stores program code that is executable by the processing unit 210 such that the processing unit 210 performs the steps described in the present specification according to various exemplary embodiments of the present application. For example, the processing unit 210 may perform the steps as shown in fig. 1.
The memory unit 220 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 2201 and/or cache memory 2202, and may further include Read Only Memory (ROM) 2203.
The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The electronic device 200 may also communicate with one or more external devices 200' (e.g., keyboard, pointing device, bluetooth device, etc.), devices that enable a user to interact with the electronic device 200, and/or any devices (e.g., routers, modems, etc.) that the electronic device 200 can communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 250. Also, the electronic device 200 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through a network adapter 260. Network adapter 260 may communicate with other modules of electronic device 200 via bus 230. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 200, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware.
Thus, according to a fifth embodiment of the present invention, the present invention provides a computer readable medium. As shown in fig. 3, the technical solution according to the embodiment of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, or a network device, etc.) to perform the above-described method according to the embodiment of the present invention.
The software product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
The computer-readable medium carries one or more programs, which when executed by one of the devices, cause the computer-readable medium to implement the functions of the first embodiment.
Those skilled in the art will appreciate that the modules may be distributed throughout several devices as described in the embodiments, and that corresponding variations may be implemented in one or more devices that are unique to the embodiments. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The modeling method of the satellite east-west maintenance strategy model based on the Nature DQN is characterized by comprising the following steps of:
s1: initializing a model, wherein each set of satellite mental state data set comprises an initial state of a satellite, a plurality of expected orbit control moments and expected orbit control times; the initial state of each satellite comprises an initial moment satellite state; satellite states include flat longitude and eccentricity vectors;
s2: inputting an initial time satellite state of a group of satellite training state data sets into the model to obtain all tangential control behaviors and Q values corresponding to the tangential control behaviors after the initial time;
s3: acquiring the satellite state at the current moment, and acquiring tangential control behaviors executed by the satellite according to a greedy strategy;
s4: executing tangential control behavior to obtain satellite states at the next moment and actual orbit control moment; obtaining rewards according to actual track control and thing holding strategy rewarding functions; the thing retention policy rewards function employs equation 1:
wherein r is t Rewards obtained by tangential control actions for the satellites at the current moment, wherein deltat is a time interval from the actual orbit control moment and is obtained according to the current moment and the actual orbit control moment; t is t 0 The expected track control time closest to the current time; t is the current moment;
s5: the satellite state at the current moment, the tangential control behavior executed by the satellite, rewards and the satellite state at the next moment are used as a group of satellite combination state data sets to be stored in an experience pool;
s6: taking out a plurality of groups of satellite combination state data sets from the experience pool, and calculating a target value of each satellite combination state data set according to the target neural network weight parameters;
s7: calculating an error according to the loss function, and updating the weight parameter of the current neural network;
s8: updating the Q value according to the value function; taking the satellite state at the next moment as the satellite state at the current moment;
s9: repeating steps S3-S8, the number of times steps S3-S8 are performed being equal to the expected orbit control number of the set of satellite training state data sets; after each repetition of the steps S3-S8 of the appointed iteration times, updating the weight parameters of the target neural network according to the weight parameters of the current neural network;
s10: steps S2-S9 are repeated until all the data of the satellite training state data set has been entered.
2. The modeling method of a Nature DQN-based satellite east-west maintenance strategy model according to claim 1, wherein in step S3, the method of obtaining tangential control behavior performed by a satellite according to a greedy strategy comprises: the satellite randomly selects tangential control behaviors according to the first specified probability or executes the tangential control behaviors corresponding to the maximum Q value according to the second specified probability; the sum of the first specified probability and the second specified probability is equal to 1.
3. The modeling method of a Nature DQN-based satellite east-west maintenance strategy model according to claim 1, wherein in step S6, the method of calculating the target value of each satellite combined state data set according to the target neural network weight parameter uses formula 2:
wherein y is j Representing the target value, gamma being the discount value, theta' being the target neural network weight parameter,
representing the maximum Q value, s, of the satellite in the satellite combination state data set after the satellite performs tangential control action a at the next moment j+1 Representing the satellite state at the next moment in a set of satellite combined state data sets, a representing the tangential control behaviour performed by the satellite, r j Representing rewards in a set of satellite combination status data sets.
4. The modeling method of a Nature DQN-based satellite east-west maintenance strategy model according to claim 1, wherein in step S7, the loss function employs formula 3:
wherein y is j Represents the target value, θ is the current neural network weight parameter, Q (s j ，a j The method comprises the steps of carrying out a first treatment on the surface of the θ) represents the current time satellite performing tangential control behavior a in a set of satellite combined state data sets j Q, s after j Representing the current time satellite state, a, in a set of satellite combined state data sets j And representing tangential control actions performed by the satellite at the current moment, wherein m is the number of satellite combined state data sets.
5. The modeling method of a Nature DQN-based satellite east-west maintenance strategy model according to claim 1, wherein in step S8, the method of updating Q value according to a value function uses formula 4:
Q(s t ，a t )←Q(s t ，a t )+α[r t +γmax Q(s t+1 ，a t )-Q(s t ，a t )] (4)；
wherein Q(s) on the left side of the arrow t ，a t ) Indicating the updated current time satellite execution tangential control behavior a t The Q value at the rear, Q(s) at the right side of the arrow t ，a t ) The satellite-executed tangential control behavior a representing the current moment before updating t Q(s) t+1 ，a t ) The satellite-performed tangential control behavior a at the next time representing the current time before updating t The Q value, alpha is weight, gamma is discount value, s t Representing the satellite state at the current moment, a t Representing the tangential control behavior performed by the satellite at the current moment s t+1 Representing satellite state at next moment of current moment, r t Indicating a reward.
6. A Nature DQN-based satellite east-west maintenance strategy model, characterized in that the modeling method of any of claims 1-5 is used to build the model.
7. A method for acquiring a satellite east-west maintenance optimal strategy, which is characterized in that a satellite east-west maintenance strategy model based on Nature DQN is established according to the modeling method of any one of claims 1-5;
obtaining an optimal strategy according to the model;
the method for obtaining the optimal strategy according to the model adopts a formula 5:
wherein pi represents the strategy of tangential control of the satellite, pi * Represents the optimal tangential control strategy learned by the model, namely, the satellite passes through the strategy pi under the condition that the satellite state at the initial moment is s * Yielding the greatest return under tangential control behavior a.
8. An electronic device, comprising:
one or more processors;
a storage means for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-5.
9. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211408082.4A CN115758706B (en) | 2022-11-10 | 2022-11-10 | Modeling method, model and acquisition method of satellite east-west maintenance strategy model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211408082.4A CN115758706B (en) | 2022-11-10 | 2022-11-10 | Modeling method, model and acquisition method of satellite east-west maintenance strategy model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115758706A CN115758706A (en) | 2023-03-07 |
| CN115758706B true CN115758706B (en) | 2023-04-25 |
Family
ID=85369194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211408082.4A Active CN115758706B (en) | 2022-11-10 | 2022-11-10 | Modeling method, model and acquisition method of satellite east-west maintenance strategy model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115758706B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114090537A (en) * | 2022-01-20 | 2022-02-25 | 北京航天驭星科技有限公司 | Real-time analysis method, device, system, equipment and medium for satellite in-orbit state |
| CN114362810A (en) * | 2022-01-11 | 2022-04-15 | 重庆邮电大学 | Low-orbit satellite beam hopping optimization method based on migration depth reinforcement learning |
| CN114802817A (en) * | 2022-05-27 | 2022-07-29 | 中国科学院软件研究所 | Satellite attitude control method and device based on multi-flywheel array |
| CN114933028A (en) * | 2022-07-21 | 2022-08-23 | 北京航天驭星科技有限公司 | Dual-star-orbit control strategy control method and device, electronic equipment and storage medium |
| CN114967453A (en) * | 2022-05-25 | 2022-08-30 | 北京理工大学 | Satellite east-west coordination state initial value estimation method based on neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11574223B2 (en) * | 2019-10-07 | 2023-02-07 | Intelligent Fusion Technology, Inc. | Method and apparatus for rapid discovery of satellite behavior |
-
2022
- 2022-11-10 CN CN202211408082.4A patent/CN115758706B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114362810A (en) * | 2022-01-11 | 2022-04-15 | 重庆邮电大学 | Low-orbit satellite beam hopping optimization method based on migration depth reinforcement learning |
| CN114090537A (en) * | 2022-01-20 | 2022-02-25 | 北京航天驭星科技有限公司 | Real-time analysis method, device, system, equipment and medium for satellite in-orbit state |
| CN114967453A (en) * | 2022-05-25 | 2022-08-30 | 北京理工大学 | Satellite east-west coordination state initial value estimation method based on neural network |
| CN114802817A (en) * | 2022-05-27 | 2022-07-29 | 中国科学院软件研究所 | Satellite attitude control method and device based on multi-flywheel array |
| CN114933028A (en) * | 2022-07-21 | 2022-08-23 | 北京航天驭星科技有限公司 | Dual-star-orbit control strategy control method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115758706A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3688675B1 (en) | Distributional reinforcement learning for continuous control tasks | |
| Zhang et al. | Control of coordinated patterns for ocean sampling | |
| Sullivan et al. | Using reinforcement learning to design a low-thrust approach into a periodic orbit in a multi-body system | |
| CN115795816B (en) | Modeling method, model and acquisition method of satellite east-west maintenance strategy model | |
| CN115758707B (en) | Modeling method, system and acquisition method of satellite east-west maintenance strategy model | |
| CN115795817B (en) | Modeling method, system and acquisition method of satellite east-west maintenance strategy model | |
| Bonasera et al. | Designing impulsive station-keeping maneuvers near a sun-earth l2 halo orbit via reinforcement learning | |
| CN115758706B (en) | Modeling method, model and acquisition method of satellite east-west maintenance strategy model | |
| CN115758705B (en) | Modeling method, system and acquisition method for satellite north-south maintenance strategy model | |
| CN115865166B (en) | Modeling method, system and acquisition method for satellite north-south maintenance strategy model | |
| CN115865167B (en) | Modeling method, system and acquisition method for satellite north-south maintenance strategy model | |
| CN115758704B (en) | Modeling method, system and acquisition method for satellite north-south maintenance strategy model | |
| Fraser | Adaptive extended Kalman filtering strategies for autonomous relative navigation of formation flying spacecraft | |
| Fang et al. | State estimation of double-pyramid tethered satellite formations using only two GPS sensors | |
| CN115806062B (en) | Modeling method, system and acquisition method of satellite relative phase maintaining strategy model | |
| CN115806060B (en) | Modeling method, model and acquisition method of satellite relative phase maintaining strategy model | |
| CN115892516B (en) | Modeling method, model and acquisition method of satellite relative phase maintaining strategy model | |
| Biggs et al. | In-situ tracking of a solar sail’s characteristic acceleration using a robust active disturbance estimator | |
| CN115806061B (en) | Modeling method, model and acquisition method of satellite relative phase maintaining strategy model | |
| Takahashi et al. | Autonomous Reconnaissance Trajectory Guidance at Small Near-Earth Asteroids via Reinforcement Learning | |
| LaFarge | Reinforcement learning approaches for autonomous guidance and control in a low-thrust, multi-body dynamical environment | |
| Geng et al. | Impulsive guidance of optimal pursuit with conical imaging zone for the evader | |
| Bowen | On-board orbit determination and 3-axis attitude determination for picosatellite applications | |
| Wawrzyniak et al. | Look-ahead flight path control for solar sail spacecraft | |
| Sin | Trajectory optimization and control of small spacecraft constellations |
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 |