3612 results about "Spacecraft" patented technology

The invention discloses a mechanical arm digital twinning system for deep space exploration, and relates to the technical field of digital twinning simulation. The mechanical arm comprises a physical layer, a data acquisition and transmission layer, a digital twin model layer and an application layer, the physical layer comprises a mechanical arm body and a sensor network, and the sensor network is used for acquiring operation state information of the mechanical arm body; the data acquisition and transmission layer comprises data acquisition equipment and a data transmission network, wherein the data acquisition equipment is respectively connected with the sensor network and the data transmission network. According to the invention, the physical layer, the data acquisition and transmission layer, the digital twinborn model layer and the application layer of the mechanical arm are constructed, so that the actual mechanical arm body can be guided to perform related actions through virtual simulation data, and virtual and real body configuration comparison can be completed through a visual interface; and the digital twinning requirements of various spacecraft operations in the future deep space exploration field are met.

The invention belongs to the technical field of aerospace equipment, and discloses an unfolding mechanism and a spacecraft, and the unfolding mechanism is used for winding and unwinding a curling arm and comprises a bearing part, a rotating shaft and a plurality of guide parts. The rotating shaft is rotationally arranged on the bearing piece, one end of the curling arm is fixed to the rotating shaft, and the rotating shaft is used for winding and unwinding the curling arm. The multiple guiding parts are distributed on the bearing piece along the periphery of the rotating shaft and used for providing guiding in the winding and unwinding process of the winding arm. The curling arm is wound through the rotating shaft, and the curling arm can be unfolded or folded by rotating the rotating shaft, so that the solar wing adopting the unfolding mechanism is simple in overall structure, small in size and capable of meeting the space requirement of a small spacecraft. Comprising the unfolding mechanism is small in size and can meet the requirement of miniaturization design.

Intelligent optimization of mission planning and execution for spacecraft through intelligent analysis of mission objectives and payload operation is disclosed. Values for mission objectives, payload operation, and / or vehicle conditions may be defined during given time periods, including variable values for repeat operations or other factors. These values may then be used through a vehicle / mission simulation agent to optimize the mission plan through maximizing the mission score according to the values. The simulation agent may identify possible mission plans based on vehicle capability, and then score the mission plan based on the total objective score.

The invention discloses a satellite formation autonomous control method based on relative motion fitting, belongs to the technical field of spacecraft control, and aims to solve the problem that a traditional formation control method cannot meet formation control requirements in an environment with navigation signal deficiency. The method comprises the following steps: step 1, when a main satellite passes through an ascending node, performing relative motion fitting by utilizing inter-satellite spacing and direction of a plurality of discretely distributed sub-satellites relative to the main satellite observed in a previous orbital period so as to obtain coefficients of relative motion functions of the sub-satellites; step 2, obtaining orbit parameter deviation of the child satellites relative to the primary satellite according to the coefficient of the relative motion function of the child satellites; step 3, acquiring a control vector and a control duration required by the formation adjustment of the child satellites according to the orbit parameter deviation; and step 4, each sub-satellite performs autonomous control according to the control vector and the control duration obtained in the step 3. The method is used for satellite formation autonomous control.

The invention provides a spacecraft full-cycle monitoring and operation and maintenance decision-making system based on digital twinning, and belongs to the field of spacecraft full-life-cycle intelligent operation and maintenance. Structural data and environmental data are monitored in real time through a multi-source sensor network deployed on a spacecraft structure; fusing physical entity monitoring data and damage evolution rule virtual data in a twin database, constructing a structure damage resistance and mechanical property evaluation model, and executing geometric modeling, physical attribute analysis, behavior response simulation and damage evolution rule modeling; based on a simulation result of the virtual model, life prediction and reusability evaluation are carried out, and an operation and maintenance decision instruction is generated; and feeding back the operation and maintenance decision instruction to the physical entity to execute control, and updating state data in the twin database to perform iterative optimization. According to the method, full-scene coverage from design demonstration to scrap recovery is supported, the problem of stage splitting in the traditional technology is solved, and a closed-loop optimization mechanism is formed through real-time interaction between the physical entity and the virtual model.

The invention belongs to the technical field of spacecraft pose estimation, and particularly relates to a cross-domain spacecraft pose estimation method based on mask self-distillation domain adaptation, and the method comprises the steps: 1, inputting a complete image, and employing a Faster R-CNN algorithm to position a spacecraft bounding box; the robustness of the model is improved by applying a track environment data enhancement strategy; and extracting a target ROI region as key point regression network input based on the detection frame. 2, dividing ROI (Region of Interest) data of a source domain and a target domain; and optimizing heat map supervision loss learning key point positioning knowledge. 3, inputting random mask enhanced target domain data into the student model; inputting original target domain data into the teacher model; a learnable shared prototype space is constructed, and self-distillation is guided through heat map consistency loss and semantic consistency loss. And 4, jointly optimizing the loss of the key point regression network 3, and realizing progressive migration of source domain annotation knowledge to a target domain. And 5, solving the 6D pose of the spacecraft relative to the camera through the EPnP. According to the invention, robust six-degree-of-freedom pose estimation of the target spacecraft is realized.

The invention discloses a large thin-wall complex component deformation field real-time prediction method based on digital twinning, belongs to the technical field of large thin-wall complex component high-precision machining, and relates to the large thin-wall complex component deformation field real-time prediction method based on digital twinning. The method comprises the following steps: firstly, constructing a large spacecraft cabin digital twin system, then constructing a deformation prediction model based on a multi-dimensional data interpolation algorithm, obtaining workpiece key point deformation through a displacement sensor, giving a deformation correction model based on measured data weighted compensation on the basis of data acquisition, and finally obtaining a deformation prediction model based on measured data weighted compensation. And a large number of high-precision prediction data samples are reduced and then are further corrected to improve the prediction precision and efficiency. According to the invention, a data visualization mode is adopted, the deformation of the component at each rotation angle and temperature is dynamically displayed, and the deformation condition of the to-be-processed surface of the large cabin component can be grasped in advance. And a deformation correction model based on measured data weighted compensation is given, so that the production cost of enterprises is reduced, and the machining precision and efficiency are improved.

The invention relates to a propulsion system, in particular to an air-breathing radio frequency ion electric propulsion system with mixed working medium power and a multi-mode working method thereof, and aims to solve the problems that an existing air-breathing electric propulsion system only takes atmosphere as a single working medium, the atmosphere trapping efficiency is low, and the performance of a spacecraft is affected. The device comprises a propelling and gas trapping unit, a radio frequency neutralizer, a power and control unit and a xenon storage and supply unit, the propelling and gas trapping unit comprises a radio frequency ion thruster and an atmosphere trapping gas inlet channel; the power and control unit comprises a direct current module, a control module and a radio frequency module; the xenon storage and supply unit comprises a xenon bottle and a valve and sensor assembly; the control module and the valve are electrically connected with the sensor assembly. The radio frequency ion thruster is electrically connected with the radio frequency neutralizer through the radio frequency module. The first output end of the xenon storage and supply unit is connected with the gas path input end of the radio frequency neutralizer, and the second output end of the xenon storage and supply unit is connected with the gas path input end of the radio frequency ion thruster.

The invention discloses a cabin butt joint guide rail compensation method based on point cloud, and relates to the technical field of spacecraft cabin automatic butt joint, and the method comprises the following steps: building a system coordinate system, and carrying out initial calibration; carrying out guide rail error modeling; carrying out six-degree-of-freedom platform error correction modeling; point cloud data acquisition and pose measurement; calculating error compensation control; adjusting and closed-loop feedback are executed; according to the cabin butt joint guide rail compensation method based on the point cloud, modeling and real-time compensation control are carried out on pose errors in the cabin butt joint process under guide of the guide rail by fusing the three-dimensional point cloud sensing technology and six-degree-of-freedom platform control; the problems that in the prior art, guide rail errors cannot be automatically corrected, and the butt joint precision is insufficient are solved, and accurate butt joint, safety and reliability of the large cabin section in the automatic assembling process are guaranteed.

The invention discloses an initial orbit determination method for passive angle measurement of a ring fire orbit for Mars sampling return, and the method comprises the steps: building an absolute dynamic model, obtaining an absolute motion state of a spacecraft, and deducing a relative motion state X; constructing a data set by using the measurement quantities H and X of the sensor; a network architecture is designed, input data I are position and speed coordinates of the tracker in a Mars equator inertial coordinate system and angle information converted from H, and output data are X; and finally, adjusting an observation interval dt and times k according to a ring fire observation condition, training a physical information neural network by using limited observation data, defining a total loss function F comprising a loss function FY and a physical law penalty term FD, and optimizing a weight coefficient and bias by minimizing the loss function through an F gradient descent method. According to the method, the neural network is trained offline, a network mapping model from a target line-of-sight angle measurement sequence to a target orbit is constructed, and the network mapping model is solidified on a returner for online use, so that sampler short-arc passive measurement rapid orbit determination is realized.

A method to predict and fit an APC of a LEO satellite considering attitude information is provided, which includes: transforming a spacecraft body-fixed coordinate system, obtaining a transformation matrix from orbital coordinate system to transformed spacecraft body-fixed coordinate system, obtaining rotation angles during a rotation process, obtaining rotation angles in orbit determination time period to predict rotation angles in orbit prediction time period, obtaining a transformation matrix from spacecraft body-fixed coordinate system to Earth-fixed coordinate system of each prediction moment, obtaining a correction vector from a CoM to a phase center of a downlink signal antenna in the Earth-fixed coordinate system at each prediction moment, and obtaining an orbit of the phase center of the downlink signal antenna of a LEO satellite, and performing an ephemeris parameter fitting on the orbit of the phase center of the downlink signal antenna of the LEO satellite in a fitting time period.

The invention provides a spacecraft quartz powder heat insulation tile which is prepared by adopting high-purity quartz powder (SiO2) as a main raw material and combining a high-temperature-resistant ceramic fiber reinforcement and a nano aerogel heat insulation layer through a high-temperature sintering process. The heat insulation tile has the following advantages: 1, the heat insulation tile has excellent high temperature resistance, and can tolerate 1600 DEG C high temperature for a long time and tolerate 1800 DEG C instantaneous thermal shock for a short time; 2, repeated use: the structure is stable, and high strength is still kept after multiple thermal cycles; light weight: the density is low (less than or equal to 0.5 g / cm < 3 >), and the load of a spacecraft is reduced; and 4, the thermal conductivity is low (less than or equal to 0.05 W / m.K), and heat transfer is effectively isolated. The method is suitable for thermal protection systems (TPS) of spacecrafts, such as thermal insulation of reentry capsules and rocket engine nozzles.

The invention discloses a multi-satellite cooperative distributed game control method and device, a computer program and a storage medium, belongs to the technical field of spaceflight, and particularly relates to a satellite attitude control and game control method. The problem that in the prior art, resolving of the overall control quantity depends on a center unit, and constraint processing on the size of the microsatellite control torque is not accurate enough is solved. The method comprises the following steps: S1, according to attitude dynamics modeling and pseudo-linearization processing of the combined spacecraft, obtaining a state dependence coefficient model; s2, obtaining a local optimal control strategy of each satellite in the combined spacecraft through a model prediction control method according to the state dependence coefficient model in combination with a dynamic model in a prediction time domain and flywheel constraint conditions; and S3, obtaining a distributed Nash equilibrium solution through a distributed iteration and global coordination method according to the local optimal control strategy of each satellite in combination with communication topology information. The method is suitable for efficient cooperation tasks of large-scale satellite groups and microsatellite systems.

The invention relates to the technical field of spacecraft on-orbit health monitoring, and particularly discloses a spacecraft appearance damage detection method and system based on multi-modal data fusion, and the method comprises the steps: obtaining the current multi-modal data of an outer surface damage region of a target spacecraft, and carrying out the data preprocessing and cross-modal alignment, and obtaining the target multi-modal data; performing feature extraction on the target multi-modal data to obtain a damage feature of each modal, and performing damage detection on the damage feature of each modal to obtain a damage detection result of each modal; and performing cross-modal feature fusion according to the damage detection result of each modal and the dynamic weight to obtain an appearance damage detection result of the target spacecraft. According to the method, through multi-modal fusion and innovative process design, the accuracy of spacecraft appearance damage detection is improved, the method is particularly suitable for on-orbit service tasks in a complex orbit environment, and an efficient solution is provided for real-time evaluation and autonomous decision making of the health state of the spacecraft.

The invention discloses an on-orbit spacecraft temperature prediction method and device based on a physical information neural network. The method comprises the following steps: S1, constructing an object model and an orbit heat source model according to a spacecraft to be predicted; s2, solving a space external heat flow of the orbit heat source model, and converting the space external heat flow into a volume heat flow of the object model; s3, constructing a physical information neural network; wherein a three-dimensional transient heat conduction equation is embedded in the physical information neural network; s4, designing a total loss function according to the volume heat flow and the physical information neural network; and S5, training the physical information neural network according to the total loss function to obtain a temperature prediction result of the spacecraft to be predicted. According to the method, the situation that model grids need to be divided in traditional finite element simulation is avoided, the calculation efficiency is improved, the calculation time is shortened, the temperature result can be predicted in real time, and the generalization ability and accuracy of the model are improved.

The invention relates to an end-to-end spacecraft pose measurement method based on deep learning, and belongs to the field of spacecraft pose measurement, the method uses a sliding window transformer as a feature extraction backbone network, introduces a multi-layer large kernel convolution module, and is used for enhancing a global receptive field and feature expression ability. A rotating head detection network and a position head detection network are arranged in parallel after the backbone network, a rotating head is used for predicting a 3D key point and a projection weight thereof, a position head is used for predicting a 2D key point, a 2D-3D corresponding relation is sent to a differentiatable EPro-PnP module for pose solving, it is ensured that a gradient can be completely transmitted back to a feature extraction layer, and a feature extraction layer is obtained; therefore, a globally optimal solution is obtained, and integrated network training of feature learning and geometric pose solution is realized. According to the method, a complex loss function is constructed, through multi-angle supervision and complementary optimization, it is ensured that the model can accurately predict the 6D pose of the spacecraft, and robustness and generalization performance in a complex environment are enhanced.

The invention discloses a spacecraft space environment safety guarantee system and method based on three-step calculation, and the system comprises two subsystems: a space environment data service subsystem and a three-step calculation and analysis subsystem, and the three-step calculation and analysis subsystem calls data and an algorithm model from the space environment data service subsystem. The space environment safety guarantee analysis based on the three-step calculation is executed; the space environment data service subsystem comprises a metadatabase and a comprehensive database; the metadatabase comprises space environment space-based monitoring data, space environment foundation monitoring data and data from a specified space environment mechanism; the comprehensive database comprises a space environment numerical calculation model library and a spacecraft business application rule algorithm model library; the three-step calculation and analysis subsystem comprises a sun-earth space environment analysis and calculation module, a spacecraft orbit ring layer environment analysis and calculation module and a spacecraft task influence risk assessment and calculation module, and three-step calculation is executed through the three modules.

The invention discloses an intelligent fusion analysis and decision support system and method for multi-source heterogeneous data of a spacecraft. The intelligent fusion analysis and decision support system for the multi-source heterogeneous data of the spacecraft and the intelligent fusion analysis and decision support method for the multi-source heterogeneous data of the spacecraft are included. The system comprises a dynamic adaptation access layer, a unified semantic modeling layer, a space-time semantic fusion engine, a digital twin collaborative decision-making center, a knowledge enhancement decision-making auxiliary subsystem, a cross-department collaborative interaction platform and a side cloud collaborative intelligent processing framework. The method comprises the steps of multi-source heterogeneous information dynamic access and semantic modeling, space-time and semantic deep fusion, digital twin driven decision deduction, knowledge enhanced decision assistance, cross-department collaborative decision and interaction, edge cloud collaborative intelligent processing and the like. According to the method, the safety, reliability and decision-making efficiency of spacecraft tasks can be remarkably improved, and the method is suitable for development, testing and on-orbit task stages of various spacecrafts.

The invention discloses a large spacecraft lightweight control system based on knowledge distillation, which comprises a spacecraft control knowledge distillation training system and a spacecraft control knowledge graph, and realizes lightweight of a control algorithm by optimizing a knowledge distillation loss function through a dynamic knowledge migration mechanism. According to the method, a lightweight method optimization model based on knowledge distillation is adopted, a dynamic training data set is constructed, and computing resource occupation and power consumption are reduced; the knowledge association precision is enhanced and optimized through the atlas; and meanwhile, the accuracy loss is controlled by adopting attention weighted fusion cross-task knowledge, so that efficient, real-time and low-power-consumption operation and response are realized.

The invention relates to the technical field of spacecrafts, and discloses a satellite solid storage and data transmission integrated system which comprises a data transmission solid storage master control FPGA, an FPGA loading and refreshing system and an ARM system, the FPGA loading and refreshing system and the ARM system are connected with the data transmission solid storage master control FPGA, the ARM system is connected with the FPGA loading and refreshing system, and meanwhile the ARM system is connected with satellite service through a CAN bus; the FPGA loads and refreshes a system, and periodically refreshes rewrite configuration or system reset rewrite configuration to ensure normal operation of the configuration; and the ARM system forwards the satellite remote control instruction received from the CAN bus to the data transmission solid memory master control FPGA and the loading FPGA through the SPI bus. According to the technical scheme, storage and transmission are efficiently integrated, the data storage rate, the data transmission rate and the data transmission capacity are improved, the system architecture is simplified, flexible selection of a data transmission modulation mode and the data transmission rate is achieved, the system reliability is improved, data access and transmission can be more accurately regulated and controlled through control and management of the FPGA, and the system reliability is improved. And the system instability caused by hardware faults or interface problems is effectively reduced.

The invention belongs to the technical field of aerospace engineering, and discloses a flexible radiator which comprises a radiation assembly, the radiation assembly comprises a plurality of radiation plates which are rotationally connected in sequence, each radiation plate comprises a liquid cooling pipe set and a radiation film arranged on the liquid cooling pipe set, and cooling liquid circulates in the liquid cooling pipe set. The material density is low, the structural mass is effectively reduced, a plurality of radiant panels are rotationally connected in sequence, the radiant panels are in a folded state during emission, then a radiator with enough radiation area can be emitted under the condition that the size of a spacecraft is limited, and the heat dissipation requirement of high-power electronic equipment is met.

The invention discloses an adaptive gradient enhanced Kriging agent modeling method suitable for spacecraft heat transfer model correction, and relates to the field of spacecraft heat transfer model correction. The method specifically comprises the following steps: S1, carrying out theoretical derivation construction on a related core function in a self-adaptive gradient enhancement modeling process of a gradient weighted Gaussian process prediction function and a target sample self-adaptive learning function Kriging; and S2, establishing a novel adaptive gradient enhanced Kriging proxy model of the spacecraft heat transfer model through a numerical method based on a proxy model related core function constructed by theoretical derivation in the step S1. The operation complexity that an adjoint function and a Taylor equation need to be solved in traditional gradient enhancement agent modeling is avoided, the gradient enhancement method is embedded into the iteration process of adaptive learning, and efficiency and accuracy are improved.

The invention relates to a simulation test platform for a 1553B bus of a spacecraft, which is suitable for stand-alone test and system test of a 1553B bus interface of a satellite model, and comprises an application layer, a communication layer and a data interface connected with the application layer and the communication layer, the application layer comprises a main control module, a database module and a user interaction module; the communication layer comprises a non-periodic data communication module and a periodic data communication module. The method can be suitable for ground tests of multiple satellite models at the same time, the research and development cost is saved, great convenience is brought to the satellite ground tests, and therefore the development progress of the satellite models is effectively guaranteed.

The invention discloses an on-orbit spacecraft attitude estimation method and system based on ISAR image feature selection, and belongs to the field of aerospace control systems. The method comprises the following steps: acquiring an ISAR image of a spacecraft, and acquiring a complex linear structure set and three-dimensional feature points of an on-orbit spacecraft; then, according to the obtained three-dimensional-two-dimensional projection model, the CRLB of each reference structure in the complex linear structure set is deduced to carry out attitude estimation error analysis; calculating the trace of the CRLB covariance matrix of each reference structure to select an optimal feature structure, correcting the scattering point trace of the optimal feature structure by using polynomial fitting, and switching the reference structures as a new optimal feature structure according to the scattering point loss rate and a preset sequence; and optimizing the spacecraft attitude angle solving function by using a particle swarm and LM hybrid algorithm to obtain attitude angle parameters. The target with high-precision target attitude real-time estimation can be completed aiming at the problems that high-order frequency change in a dynamic environment is difficult to capture and resolution and noise suppression are contradictory due to a fixed window time-frequency analysis method.

The invention discloses an image annotation method, system and device for spacecraft target type and attribute classification and a medium, and belongs to the technical field of image recognition. The method comprises the following steps: constructing a multi-dimensional attribute model based on key elements of a spacecraft image; based on the multi-dimensional attribute model, constructing a reference prompt template, obtaining a preliminary output result through the reference prompt template, and carrying out optimization processing on the reference prompt template and the preliminary output result by adopting few-sample learning to obtain a first output result; performing output supervision on the thinking process of the first output result in combination with the thinking chain, and obtaining a second output result through an optimization prompt template; and according to the first output result, the second output result and the plurality of output results, generating an output result data set, and obtaining an image annotation result. According to the method, through a semi-supervised labeling method combining multi-attribute modeling and context learning, the accuracy and robustness of fine-grained labeling of the spacecraft image in a few-sample scene are improved by utilizing a generative large model.

The invention discloses a spacecraft cluster robust formation control method based on a dynamic event trigger mechanism, which is applied to the technical field of spacecraft cluster formation control, and aims to solve the problem that the prior art still has certain limitations under the complex conditions of limited communication, unknown control input of a virtual leader, external disturbance and the like. The method comprises the following steps: firstly, constructing a six-degree-of-freedom attitude and orbit coupling spacecraft cluster system model influenced by external disturbance and model uncertainty; on the basis, a robust formation control scheme based on a dynamic event trigger communication mechanism is designed, and the scheme comprises three key components, the three mechanisms are respectively a self-adaptive second-order expansion system based on local discontinuous communication, a multi-spacecraft robust formation device based on neural network self-adaptive estimation and a unified dynamic event trigger communication mechanism.

The invention relates to a spacecraft pose estimation method, in particular to a lightweight spacecraft pose estimation method based on a high-resolution network, and solves the technical problem that in an existing spacecraft pose estimation method, key point regression is difficult to meet precision and efficiency requirements at the same time. According to the method, the key point regression model is based on a high-resolution network, depth separable convolution is adopted in the feature extraction process, the parameter quantity and the calculation quantity are greatly reduced, meanwhile, a mixed attention mechanism is combined, the high expression ability is reserved in feature extraction, the lightweight degree is further improved, and the method is suitable for large-scale popularization and application. The balance of precision and efficiency is realized; in the feature fusion process, cavity convolution is adopted to enlarge a receptive field, global information in an image can be captured, the pixel position of an occluded key point can be more accurately deduced, then key local and global features are focused in combination with a mixed attention mechanism, the effectiveness of feature representation is further improved, and the regression precision of the key point is improved.

The invention relates to a spacecraft pose estimation method, in particular to a high-precision spacecraft pose estimation method based on deep learning, and solves the technical problems that a network model of an existing spacecraft pose estimation method is poor in interpretability and generalization ability, or precision is difficult to guarantee. According to the method, the pose estimation task of the spacecraft is decomposed into three-dimensional view reconstruction and key point regression of the spacecraft, the interpretability is high, and the generalization ability is stable; two-dimensional coordinates of key points are predicted through the key point regression initial model, then a predicted pose and a loss function of the spacecraft are calculated in sequence, the gradient of the loss function about model parameters serves as a constraint condition to participate in back propagation of the key point regression initial model, and the pose solving process of the spacecraft participates in updating of the model parameters. The overall integrating degree of the key point regression model obtained through training can be increased, the situation that pose estimation is caught in local optimum is avoided, and the precision of spacecraft pose estimation is improved.

The invention relates to a conduction fusion enhancement method suitable for an earth-moon space high-orbit spacecraft, and the method comprises the steps: transmitting a communication and navigation fusion enhancement signal through a designed and planned HEO satellite constellation, and receiving and processing a Beidou navigation signal and an HEO enhancement signal in a compatible manner on the basis of not changing the hardware structure of an earth-moon space navigation receiver. The number of available navigational stars is increased through an observed quantity combination mode, the geometric distribution of constellations is improved, and the navigation solution accuracy and the positioning precision of earth-moon space are improved. And meanwhile, a communication function of forwarding information such as navigation ephemeris, receiver position and user customized data of uplink injection on the ground through an HEO constellation is supported, auxiliary information is provided for the earth-moon space navigation receiver, the receiving processing performance is improved, and communication and navigation fusion processing is realized. According to the method, the performance and the service capability of the high-orbit satellite navigation receiver can be improved, and the method has certain reference significance for spacecraft conduction fusion and integrated design.

The invention provides a PPO-based spacecraft attitude and orbit integrated game control method and device, and the method comprises the steps: building a spacecraft attitude and orbit integrated model, and carrying out the modeling of the interaction process of a tracking spacecraft and a target spacecraft as a non-cooperative zero-sum game; setting a multi-agent deep reinforcement learning framework, wherein the tracking spacecraft and the target spacecraft are respectively configured with an independent strategy network and an independent value network; training is carried out in a double-agent PPO mode, control instructions of orbit thrust and attitude torque are generated through the strategy network, and the state value is evaluated through the value network; and controlling and guiding the behavior of the spacecraft according to the trained strategy. According to the method, the autonomous decision-making capability and cooperative control performance of the spacecraft in complex tasks are effectively improved, and the method is suitable for high-precision aerospace tasks such as interception of non-cooperative targets, autonomous trajectory planning and attitude control.