Small spacecraft trajectory multi-target optimization method for target spacecraft monitoring

Abstract

The invention relates to the technical field of spacecraft trajectory optimization, and discloses a target spacecraft monitoring-oriented small spacecraft trajectory multi-target optimization method. Acquiring current multi-modal data of the outer surface area of the target spacecraft by using a small spacecraft carrying a multi-modal sensor, and fusing the damage detection result of each modal of the current multi-modal data to obtain a fused damage detection result; constructing a multi-target optimization model for generating an observation path of the small spacecraft, and solving the multi-target optimization model by using an improved NSGA-II algorithm and an entropy weight TOPSIS method to obtain a target observation trajectory of the small spacecraft; and dynamically adjusting the target observation trajectory by using the fused damage detection result to obtain the optimal observation trajectory of the small spacecraft. According to the method, efficient and accurate observation of the small spacecraft in a dynamic environment can be ensured, measurement and control resources are reasonably distributed, and the success rate and efficiency of space task execution are improved.

Description

Background Art

[0002] Spacecraft trajectory optimization is one of the core technologies for on-orbit monitoring of spacecraft. Its goal is to design an optimal observation path through mathematical models and intelligent algorithms, meeting multiple constraint conditions (such as illumination, TT&C resources, resolution) and achieving multi-objective coordination (such as coverage, detection accuracy, fuel efficiency). With the normalization of on-orbit spacecraft operations, trajectory optimization technology has gradually evolved from single-objective static planning to multi-objective dynamic collaborative optimization. The technological development can be divided into three stages:

[0003] 1) Traditional experience-driven stage: Early orbit design relied on Newtonian mechanics and empirical rules, and preliminary orbit transfer design was achieved through manual calculations or simplified models (such as the two-body problem). For example, the impulsive orbit transfer method based on Lambert's theorem solved the transfer velocity increment through a two-point boundary value problem, but disturbance factors such as the Earth's oblateness and atmospheric drag had to be ignored, resulting in large errors in practical applications.

[0004] 2) Single-objective optimization stage: After introducing intelligent optimization algorithms (such as genetic algorithms, particle swarm algorithms), the goal of trajectory optimization focused on a single performance index (such as fuel minimization or time minimization). For example, the particle swarm algorithm (PSO) was used to solve the Lambert two-impulse interception problem, and the global search was used to quickly approximate the optimal solution, but its ability to optimize multi-constraint coordination was limited.

[0005] 3) Multi-objective dynamic optimization stage: With the increase in the complexity of space missions, trajectory optimization needs to take into account the coordination of multiple objectives such as illumination conditions, TT&C resources, and resolution. Multi-objective optimization algorithms (such as NSGA-II) and hybrid strategies (such as the combination of particle swarm and simulated annealing) have become the mainstream, but they still face problems such as poor adaptability to dynamic environments and low computational efficiency.

[0006] The disadvantages of the existing technology are mainly reflected in the following aspects:

[0007] 1) Significant monitoring blind spots: Traditional technologies rely on fixed perspectives or single sensors (such as two-dimensional cameras), resulting in occluded areas on the surface of the target spacecraft that cannot be covered. For example, the back of the solar panel or the connection of the cabin becomes a detection blind spot due to the perspective limitation, and small damages (such as micro-meteorite pits) are easily missed.

[0008] 2) High false alarm rate and insufficient sensitivity: A single data source (such as only two-dimensional images) is difficult to distinguish weak defects (such as scratches, color differences) in complex backgrounds (such as Earth albedo, deep space noise). Traditional algorithms have low recognition accuracy for low-contrast defects, and the false alarm rate can reach more than 30%.

[0009] 3) Low observation efficiency: The unoptimized observation path leads to repeated scans or ineffective data collection, increasing the task duration. For example, traditional methods require multiple flybys to cover different areas, and the resolution is limited by distance, making it difficult to obtain high-definition images of key parts.

[0010] 4) Unreasonable resource allocation: The measurement and control resources (such as communication bandwidth and ground station coverage time) are not dynamically matched with the observation requirements, resulting in resource waste or task interruption. For example, when the lighting conditions are poor, forced observation is still carried out, resulting in low-quality images and the need to repeat the task.

[0011] Therefore, there is an urgent need to provide a technical solution to solve the above problems. Summary of the Invention

[0012] To solve the above technical problems, the present invention provides a multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft.

[0013] In a first aspect, the present invention provides a multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft, and the technical solution of this method is as follows:

[0014] Using a small spacecraft equipped with multi-modal sensors, obtain the current multi-modal data of the outer surface area of the target spacecraft, and fuse the damage detection results of each modality of the current multi-modal data to obtain a fused damage detection result;

[0015] Construct a multi-objective optimization model for generating the observation path of the small spacecraft, and use the improved NSGA-II algorithm and the entropy weight TOPSIS method to solve the multi-objective optimization model to obtain the target observation trajectory of the small spacecraft;

[0016] Use the fused damage detection result to dynamically adjust the target observation trajectory to obtain the optimal observation trajectory of the small spacecraft.

[0017] The beneficial effects of a multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft according to the present invention are as follows:

[0018] The method of the present invention utilizes the detection results of multi-modal sensor fusion to comprehensively and accurately obtain the damage condition of the target spacecraft, avoid monitoring blind spots, and improve the detection accuracy. By combining the improved NSGA-II algorithm with the entropy weight TOPSIS method to construct a multi-objective optimization model, the optimal observation path can be quickly solved, the observation efficiency can be improved, and the repeated scanning and ineffective data acquisition can be reduced. At the same time, the observation trajectory is dynamically adjusted according to the fused damage detection results to further optimize the observation plan, ensuring efficient and accurate observation in a dynamic environment, reasonably allocating TT&C resources, and improving the success rate and efficiency of task execution. The present invention has clear innovation and engineering practical value, providing core technical support for the safety protection of space assets and the improvement of space strategic capabilities.

[0019] Based on the above solutions, the small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring of the present invention can also be improved as follows.

[0020] In an optional manner, the multi-objective optimization model aims at maximizing the image resolution, minimizing the fuel consumption, and maximizing the TT&C resource utilization rate of the small spacecraft, and is constrained by the illumination condition, the minimum resolution, and the TT&C resource occupancy rate.

[0021] In an optional manner, the objective function F of the multi-objective optimization model is:

[0022]

[0023] where, -R represents the negative image resolution of the camera of the small spacecraft, ΔV represents the transfer orbit velocity increment of the small spacecraft, and -η 测控 represents the negative TT&C resource utilization rate of the small spacecraft; f1(x) = min(-R) represents the optimization function corresponding to maximizing the image resolution, f2(x) = min(ΔV) represents the optimization function corresponding to minimizing the fuel consumption, and f3(x) = min(-η 测控 ) represents the optimization function corresponding to maximizing the TT&C resource utilization rate;

[0024] The constraint conditions of the multi-objective optimization model are:

[0025]

[0026] where, θ represents the solar incidence angle, represents the occlusion angle of the earth or the moon to the target spacecraft, and R min is the minimum image resolution constraint value.

[0027] In an optional manner, the adjustment formula for the image resolution of the camera is: Wherein, R represents the image resolution of the camera, n represents the total number of observation points of the target spacecraft, and d i is the distance between the camera and the i-th observation point of the target spacecraft, f is the focal length, h is the pixel height, and p size is the pixel size;

[0028] The calculation formula for the velocity increment of the transfer orbit of the small spacecraft is: ΔV = ‖ΔV1‖ + ‖ΔV2‖; wherein, ΔV1 = V transfer -V initial and ΔV2 = V target -V ′ transfer ; ΔV represents the velocity increment of the transfer orbit, ΔV1 represents the first pulse, ΔV2 represents the second pulse, and V initial represents the initial orbit velocity, V transfer represents the first transfer orbit velocity from the initial orbit to the transfer orbit, and V target represents the target orbit velocity, and V ′ transfer represents the second transfer orbit velocity from the transfer orbit to the target orbit;

[0029] The calculation formula for the utilization rate of TT&C resources of the small spacecraft is: η 测控 is the utilization rate of TT&C resources, ∑t 使用 is the cumulative occupation time of the actual mission, and ∑t 可见 is the cumulative visible time.

[0030] In an optional manner, the multimodal sensor includes: a camera and a lidar; wherein, the camera is used to collect two-dimensional image data, and the lidar is used to collect three-dimensional point cloud data.

[0031] In an optional manner, the current multimodal data includes: current two-dimensional image data and current three-dimensional point cloud data; the fusion damage detection result is a damage confidence map;

[0032] The steps of fusing the damage detection results of each modality of the current multimodal data to obtain the fusion damage detection result include:

[0033] Using the ResNet-50 model to perform damage detection on the current two-dimensional image data to obtain a two-dimensional damage detection result, and using a three-dimensional point cloud model to perform damage detection on the current three-dimensional point cloud data to obtain a three-dimensional damage detection result;

[0034] Using the D-S evidence theory to fuse the two-dimensional damage detection result and the three-dimensional damage detection result to obtain the damage confidence map.

[0035] In an alternative approach, the step of dynamically adjusting the target observation trajectory by using the fusion damage detection result to obtain the optimal observation trajectory of the small spacecraft includes:

[0036] Using the damage confidence map, optimize the accompanying distance and observation angle of the small spacecraft corresponding to the target observation trajectory to obtain the optimal observation trajectory.

[0037] In a second aspect, the present invention provides a multi-objective optimization system for the trajectory of a small spacecraft for monitoring a target spacecraft. The technical solution of this system is as follows:

[0038] It includes: a detection module, a generation module, and an optimization module;

[0039] The detection module is used to: utilize a small spacecraft equipped with multi-modal sensors to obtain the current multi-modal data of the outer surface area of the target spacecraft, and fuse the damage detection results of each modality of the current multi-modal data to obtain a fusion damage detection result;

[0040] The generation module is used to: construct a multi-objective optimization model for generating the observation path of the small spacecraft, and use the improved NSGA-II algorithm and the entropy weight TOPSIS method to solve the multi-objective optimization model to obtain the target observation trajectory of the small spacecraft;

[0041] The optimization module is used to: dynamically adjust the target observation trajectory by using the fusion damage detection result to obtain the optimal observation trajectory of the small spacecraft.

[0042] The beneficial effects of a multi-objective optimization system for the trajectory of a small spacecraft for monitoring a target spacecraft according to the present invention are as follows:

[0043] The system of the present invention uses the fusion detection result of multi-modal sensors to comprehensively and accurately obtain the damage situation of the target spacecraft, avoid monitoring blind spots, and improve the detection accuracy. By combining the improved NSGA-II algorithm and the entropy weight TOPSIS method to construct a multi-objective optimization model, the optimal observation path can be quickly solved, the observation efficiency can be improved, and repeated scanning and invalid data acquisition can be reduced. At the same time, the observation trajectory is dynamically adjusted according to the fusion damage detection result, further optimizing the observation plan to ensure efficient and accurate observation in a dynamic environment, reasonably allocate measurement and control resources, and improve the success rate and efficiency of task execution. The present invention has clear innovation and engineering practical value, providing core technical support for the safety protection of space assets and the improvement of space strategic capabilities.

[0044] In a third aspect, the technical solution of an electronic device according to the present invention is as follows:

[0045] It includes a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements the steps of the small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring according to the present invention.

[0046] In a fourth aspect, the technical solution of a computer-readable storage medium provided by the present invention is as follows:

[0047] Instructions are stored in the computer-readable storage medium. When the computer-readable storage medium reads the instructions, it causes the computer-readable storage medium to execute the steps of the small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring according to the present invention.

[0048] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically given below. Description of the Drawings

[0049] The drawings are only used to illustrate the embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0050] Figure 1 It is a schematic flowchart of an embodiment of a small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring according to the present invention;

[0051] Figure 2 It is a schematic diagram of the principle of dynamically adjusting the trajectory by the closed-loop feedback mechanism;

[0052] Figure 3 It is a schematic structural diagram of an embodiment of a small spacecraft trajectory multi-objective optimization system for target spacecraft monitoring according to the present invention;

[0053] Figure 4 It is a schematic structural diagram of an embodiment of an electronic device according to the present invention. Detailed Embodiments

[0054] Hereinafter, the exemplary embodiments of the present invention will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein.

[0055] Figure 1The figure shows a schematic flowchart of an embodiment of a multi-objective optimization method for the trajectory of a small spacecraft for target spacecraft monitoring. This multi-objective optimization method for the trajectory of a small spacecraft for target spacecraft monitoring can be executed by an electronic device such as a terminal device or a server. Among them, the terminal device can be any fixed or mobile terminal such as a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The server can be a single server or a server cluster composed of multiple servers. Any electronic device can implement the multi-objective optimization method for the trajectory of a small spacecraft for target spacecraft monitoring by the processor calling the computer-readable instructions stored in the memory. As Figure 1 shown, it includes the following steps:

[0056] S1. Use a small spacecraft equipped with multi-modal sensors to obtain the current multi-modal data of the outer surface area of the target spacecraft, and fuse the damage detection results of each modality of the current multi-modal data to obtain a fused damage detection result.

[0057] Among them, the multi-modal sensors include: a camera and a lidar. The camera is used to collect two-dimensional image data, and the lidar is used to collect three-dimensional point cloud data. The current multi-modal data includes: current two-dimensional image data and current three-dimensional point cloud data. The fused damage detection result is defaulted to a damage confidence map.

[0058] Among them, the small spacecraft is the small spacecraft whose trajectory needs to be optimized in this embodiment. In addition to being equipped with a camera (a black and white camera for obtaining high-resolution images and a color camera for texture recognition) and a lidar, the small spacecraft can also be equipped with a navigation sensor for synchronously recording the position, attitude and timestamp of the spacecraft to ensure spatio-temporal consistency.

[0059] In S1, the steps of fusing the damage detection results of each modality of the current multi-modal data to obtain a fused damage detection result include:

[0060] Use the ResNet-50 model to perform damage detection on the current two-dimensional image data to obtain a two-dimensional damage detection result, and use a three-dimensional point cloud model to perform damage detection on the current three-dimensional point cloud data to obtain a three-dimensional damage detection result.

[0061] Among them, the two-dimensional damage detection result includes surface damage probabilities (scratches, oxidation discoloration, coating peeling), that is: the two-dimensional damage detection result P 2D =[p 划痕 , p 氧化 , p 涂层; The three-dimensional damage detection results include the structural damage probability (pit, deformation, abnormal curvature), i.e.: the three-dimensional damage detection result P 3D =[q 凹坑 , q 形变 , q 曲率 .

[0062] Using the D-S evidence theory, fuse the two-dimensional damage detection results and the three-dimensional damage detection results to obtain a damage confidence map.

[0063] Among them, calculate using the fusion formula In the fusion formula, maxP 2D and maxP 3D Take the results with the highest corresponding probabilities. For example, when p 划痕 is the largest, p 划痕 = maxP 2D ; when q 凹坑 is the largest, q 凹坑 = maxP 3D . When outputting the damage confidence map, mark the high-confidence regions (P 融合 ≥0.8).

[0064] It should be noted that in this embodiment, a Bayesian network can be used to replace the D-S evidence theory, and no restrictions are set here.

[0065] S2. Construct a multi-objective optimization model for generating the observation path of the small spacecraft, and use the improved NSGA-II algorithm and the entropy weight TOPSIS method to solve the multi-objective optimization model to obtain the target observation trajectory of the small spacecraft.

[0066] Among them, the multi-objective optimization model aims at maximizing the image resolution of the small spacecraft, minimizing fuel consumption, and maximizing the utilization rate of TT&C resources, and is constrained by the lighting conditions, minimum resolution, and TT&C resource occupancy rate of the small spacecraft.

[0067] Specifically, the objective function F of the multi-objective optimization model is:[[]]

[0068]

[0069] Among them, -R represents the negative image resolution of the camera of the small spacecraft, ΔV represents the transfer orbit velocity increment of the small spacecraft, -η 测控 represents the negative utilization rate of the TT&C resources of the small spacecraft; f1(x) = min(-R) represents the optimization function corresponding to maximizing the image resolution (minimizing the negative image resolution), f2(x) = min(ΔV) represents the optimization function corresponding to minimizing fuel consumption, f3(x) = min(-η 测控) represents the optimization function corresponding to maximizing the utilization rate of TT&C resources (minimizing the negative utilization rate of TT&C resources).

[0070] The constraint conditions of the multi-objective optimization model are as follows:

[0071]

[0072] Among them, θ represents the solar incidence angle, represents the occlusion angle of the Earth or the Moon on the target spacecraft, and R min is the minimum image resolution constraint value.

[0073] It should be noted that: ① The adjustment formula for the image resolution of the camera is: Among them, R represents the image resolution of the camera, n represents the total number of observation points of the target spacecraft, and d i is the distance between the camera and the i-th observation point of the target spacecraft, f is the focal length, h is the pixel height, and p size is the pixel size. Set the minimum resolution R min = 0.1 pixel / mm (scratches ≥ 1 mm can be recognized). ② Minimize the fuel consumption of orbit transfer and attitude adjustment to extend the mission life. Solve the transfer segment ΔV of the Lambert problem based on the double-pulse orbit transfer model (double-pulse orbit transfer is the basic method for spacecraft orbit adjustment, and the transfer from the initial orbit to the target orbit is achieved through two instantaneous velocity increments (ΔV1 and ΔV2)). The calculation formula for the velocity increment of the transfer orbit of a small spacecraft is: ΔV = ‖ΔV1‖ + ‖ΔV2‖; where, ΔV1 = V transfer - V initial , ΔV2 = V target - V ′ transfer ; ΔV represents the velocity increment of the transfer orbit, ΔV1 represents the first pulse, ΔV2 represents the second pulse, V initial represents the initial orbit velocity, V transfer represents the first transfer orbit velocity from the initial orbit to the transfer orbit, V target represents the target orbit velocity, V ′ transfer represents the second transfer orbit velocity from the transfer orbit to the target orbit. ③ The calculation formula for the utilization rate of TT&C resources of the small spacecraft is: η 测控 is the utilization rate of TT&C resources, ∑t 使用 is the cumulative occupied time of the actual mission, and ∑t 可见 is the cumulative visible time. Specifically: First, based on the longitude and latitude of the ground station and the orbit parameters of the spacecraft, calculate the visible time window: t 可见 = f(λ 地面站 , φ 地面站, spacecraft TLE parameters); Use the STK (Systems Tool Kit) simulation tool to generate a coverage schedule. For example, within a certain mission cycle, the spacecraft needs to transmit data to XX Station (116° east longitude, 40° north latitude). The orbital parameters are a low Earth orbit (altitude 500 km, inclination 97°), and the TLE data update period is 1 hour; the bandwidth requirements are 60 Mbps for damaged data, 20 Mbps for regular data, and a total bandwidth of 100 Mbps. STK simulation shows that the daily visibility window of XX Station is 6 times, with an average of 8 minutes each time, so ∑t 可见 = 48 minutes / day. Then, dynamically allocate bandwidth according to data priority (such as high-definition images of damage points > regular inspection data): Define the measurement and control resource utilization rate index: ④ Ensure that the solar incidence angle and occlusion conditions during the observation period meet the imaging requirements of the optical sensor. First, model based on the geometric relationship between the sun - small spacecraft - target spacecraft. Establish an Earth-centered inertial coordinate system (ECI) and calculate the real-time positions of the target spacecraft and the spacecraft. Obtain the solar azimuth vector based on ephemeris data (such as JPL DE430 ephemeris), set the incidence angle threshold (such as θ≥30°) to avoid overexposure or shadow interference caused by direct sunlight, and the formula for calculating the solar incidence angle θ is: represents the normal vector of the observed surface of the target spacecraft, represents the unit vector from the small spacecraft to the sun. ⑤ The occlusion angle of the Earth or the moon on the target spacecraft is calculated by the formula: R 遮挡体 is the radius of the Earth or the moon, and d 遮挡体-目标航天器 is the distance between the occluder and the target spacecraft; when the occlusion angle Ensure that the small spacecraft operates within the effective observation window.

[0074] It should be noted that in this embodiment, combined with the orbital dynamics model (such as SGP4 / SDP4), the solar and occluder azimuths are updated every 5 minutes, and the observation time window is dynamically adjusted to update the dynamic lighting model.

[0075] In S2, the steps of using the improved NSGA-II algorithm and the entropy weight TOPSIS method to solve the multi-objective optimization model to obtain the target observation trajectory of the small spacecraft include:

[0076] 1) Generate a Pareto front solution set covering the multi-objective optimization model through the improved NSGA-II algorithm. The specific steps include:

[0077] ① Initialize the population. Encode the spacecraft trajectory parameters (orbital semi-major axis, eccentricity, observation time window, accompanying distance) as chromosomes (real number encoding or binary encoding), and set the initial population size N (e.g., N = 200). Ensure that the initial solutions satisfy the hard constraints of illumination, TT&C resources, resolution, and fuel consumption.

[0078] ② Non-dominated sorting and crowding degree calculation. For each solution in the population, calculate its dominance relationship on the objective function vector and divide it into non-dominated levels (F1, F2, F3). Within the same non-dominated level, calculate the crowding degree of each solution (the sum of the distances between adjacent solutions in the objective space) to ensure the diversity of solutions.

[0079] ③ Improved selection, crossover, and mutation. The crossover probability p c and the mutation probability p m are dynamically adjusted according to the number of iterations:

[0080]

[0081] where iter is the number of iterations, and iter max is the maximum number of iterations. Emphasize global search (high crossover rate) in the early stage and local optimization (high mutation rate) in the later stage. Use a hybrid crossover strategy, i.e., simulated binary crossover (SBX) for continuous variables and uniform crossover for discrete variables. Introduce a perturbation term to enhance the local search ability. Preferentially select solutions that satisfy all constraints to avoid invalid paths.

[0082] ④ Elite retention and iteration termination. Combine the parent and offspring populations and select the top N optimal solutions to enter the next generation. The termination condition is that the maximum number of iterations iter max = 500.

[0083] 2) Use the entropy weight TOPSIS method to screen the comprehensively optimal target observation trajectory from the Pareto front solution set. The specific steps are as follows:

[0084] ① Construct the decision matrix. Compose the objective function values (resolution, fuel consumption, TT&C resource utilization rate) of the Pareto solution set into the decision matrix D, and generate the Pareto front of the target spacecraft monitoring trajectory, which contains n candidate trajectories:

[0085]

[0086] ② Standardize the decision matrix. Eliminate the dimension difference. For benefit-type indicators (such as resolution, TT&C utilization rate):

[0087]

[0088] For cost-type indicators (such as fuel consumption):

[0089]

[0090] ③ Calculate the entropy weight. For information entropy calculation, e j The smaller it is, the greater the amount of information of index j and the higher the weight:

[0091]

[0092] Determine the weight:

[0093]

[0094] ④ Calculate the closeness degree by TOPSIS method. Construct the weighted decision matrix:

[0095]

[0096] Ideal solution V + (Optimal value of each column):

[0097] V + =(maxV i1 , minV i2 , maxV i3 )

[0098] Negative ideal solution V - (Worst value of each column):

[0099] V - =(minV i1 , max, minV i3 )

[0100] Euclidean distance to the ideal solution:

[0101] Euclidean distance to the negative ideal solution:

[0102] Calculate the closeness degree C i : 0 ≤ C i ≤ 1; The larger C i , the closer the trajectory is to the ideal solution.

[0103] ⑤ Comprehensive optimal trajectory screening. Arrange the candidate trajectories in descending order of C i , and select the trajectory with the largest C i as the comprehensive optimal solution, that is, the target observation trajectory.

[0104] It should be noted that in this embodiment, the decomposition-based multi-objective evolutionary algorithm (MOEA / D) can be used to replace the NSGA-II algorithm without limitation here. The MOEA / D algorithm decomposes the multi-objective optimization problem into multiple single-objective sub-problems (such as weighted sum decomposition, Tchebycheff decomposition). It shares the solution information within the sub-problem neighborhood to improve the convergence speed. The Pareto front is generated by combining the solution sets of the decomposed sub-problems. Its advantages are that it is applicable to high-dimensional multi-objective problems, has high computational efficiency, and the decomposition strategy can be flexibly adjusted to adapt to different task requirements.

[0105] S3. Use the fused damage detection result to dynamically adjust the target observation trajectory to obtain the optimal observation trajectory of the small spacecraft.

[0106] Specifically, use the damage confidence map to optimize the accompanying distance and observation angle of the small spacecraft corresponding to the target observation trajectory to obtain the optimal observation trajectory.

[0107] Among them, the optimization process of the accompanying distance is as follows: For the high-confidence area (P 融合 ≥0.8), shorten the distance to 50 m and improve the resolution to R = 0.2 pixel / mm; for the low-confidence area (P 融合 <0.3): Keep it at 200 m to save fuel; in other confidence areas (0.3 ≤ P 融合 <0.8), keep the distance as: d 新 is the optimized accompanying distance corresponding to other confidence areas, and d 当前 is the accompanying distance before optimization corresponding to other confidence areas. The optimization process of the observation angle is as follows: According to the change of the sun angle, dynamically adjust the yaw angle ψ of the spacecraft to avoid specular reflection interference and ensure that θ ≥ 30°: ψ 当前 is the yaw angle before optimization, and Δψ is the change value of the yaw angle.

[0108] It should be noted that in this embodiment, the rolling horizon optimization method as Figure 2 shown is adopted, and the path is re-planned every 10 minutes to respond to sudden debris threats.

[0109] To better illustrate the technical solution of this embodiment, the following example is used for illustration:

[0110] 1) Health Monitoring and Collision Avoidance of Satellite Constellations. ① Scenario problem: Satellite constellations need to regularly monitor external damage and are simultaneously threatened by space debris. The traditional single-satellite inspection has low efficiency and cannot dynamically respond to sudden collision risks. ② Solution: Multi-satellite collaborative observation. Deploy 2 accompanying satellites to collect data from different perspectives respectively, and synthesize a global damage map through the SLAM algorithm. When a debris is detected approaching, the Receding Horizon Optimization (RHO) adjusts the path, and the response time ≤ 1 minute. ③ Implementation effect: Coverage efficiency: 5 satellites can be monitored in a single mission, with an efficiency increase of 300%; Collision avoidance rate: Increased from 75% to 95%, and fuel consumption reduced by 20%; Data consistency: After multi-source data fusion, the damage location error ≤ 5 cm.

[0111] 2) Remote Damage Diagnosis of Deep Space Probes. ① Scenario problem: Deep space probes (such as Mars rovers) are far from the Earth, with high data transmission delays, and need to autonomously detect external damage and optimize the observation strategy. ② Solution: Autonomous closed-loop feedback. Onboard AI analyzes image and point cloud data in real time, identifies damage and generates a confidence map, dynamically adjusts the accompanying distance (from 1000 m → 200 m), and improves the resolution to 0.05 pixels / mm. ③ Multi-constraint optimization: Integrate illumination (blocked by Martian dust storms), fuel, and resolution requirements to generate a Pareto-optimal path. ④ Implementation effect: Detection delay: Reduced from 20 minutes of Earth commands to 1 minute of on-board autonomous decision-making; Fuel efficiency: Fuel consumption reduced by 30% during the mission cycle; Remote operation and maintenance: Detected and repaired a tear in a solar panel, extending the mission life by 6 months.

[0112] The technical solution of this embodiment uses the fusion detection results of multi-modal sensors to comprehensively and accurately obtain the damage situation of the target spacecraft, avoid monitoring blind spots, and improve the detection accuracy. By combining the improved NSGA-II algorithm and the entropy weight TOPSIS method to construct a multi-objective optimization model, the optimal observation path can be quickly solved, the observation efficiency can be improved, and repeated scanning and invalid data acquisition can be reduced. At the same time, the observation trajectory is dynamically adjusted according to the fusion damage detection results to further optimize the observation plan, ensuring efficient and accurate observation in a dynamic environment, reasonably allocating TT&C resources, and improving the success rate and efficiency of mission execution. The technical solution of this embodiment has clear innovation and engineering practical value, providing core technical support for the safety protection of space assets and the improvement of space strategic capabilities.

[0113] Figure 3 The structural schematic diagram of an embodiment of a small spacecraft trajectory multi-objective optimization system 200 for target spacecraft monitoring provided by the present invention is shown. As Figure 3 shown, the system 200 includes: a detection module 210, a generation module 220, and an optimization module 230;

[0114] The detection module 210 is configured to: obtain the current multi-modal data of the outer surface area of the target spacecraft by using a small spacecraft equipped with multi-modal sensors, and fuse the damage detection results of each modality of the current multi-modal data to obtain a fused damage detection result;

[0115] The generation module 220 is configured to: construct a multi-objective optimization model for generating the observation path of the small spacecraft, and solve the multi-objective optimization model by using an improved NSGA-II algorithm and the entropy weight TOPSIS method to obtain the target observation trajectory of the small spacecraft;

[0116] The optimization module 230 is configured to: dynamically adjust the target observation trajectory by using the fused damage detection result to obtain the optimal observation trajectory of the small spacecraft.

[0117] In an optional manner, the multi-objective optimization model aims at maximizing the image resolution, minimizing the fuel consumption, and maximizing the utilization rate of TT&C resources of the small spacecraft, and is constrained by lighting conditions, minimum resolution, and TT&C resource occupancy rate.

[0118] In an optional manner, the objective function F of the multi-objective optimization model is:

[0119]

[0120] where, -R represents the negative image resolution of the camera of the small spacecraft, ΔV represents the velocity increment of the transfer orbit of the small spacecraft, -η 测控 represents the negative utilization rate of TT&C resources of the small spacecraft; f1(x)=min(-R) represents the optimization function corresponding to maximizing the image resolution, f2(x)=min(ΔV) represents the optimization function corresponding to minimizing the fuel consumption, f3(x)=min(-η 测控 ) represents the optimization function corresponding to maximizing the utilization rate of TT&C resources;

[0121] The constraint conditions of the multi-objective optimization model are:

[0122]

[0123] where, θ represents the solar incidence angle, represents the occlusion angle of the earth or the moon to the target spacecraft, R min is the minimum image resolution constraint value.

[0124] In an optional manner, the adjustment formula for the image resolution of the camera is: where, R represents the image resolution of the camera, n represents the total number of observation points of the target spacecraft, di is the distance between the camera and the i-th observation point of the target spacecraft, f is the focal length, h is the pixel height, and p size is the pixel size;

[0125] The calculation formula for the velocity increment of the transfer orbit of the small spacecraft is: ΔV = ‖ΔV1‖ + ‖ΔV2‖; where, ΔV1 = V transfer -V initial , ΔV2 = V target -V ′ transfer ; ΔV represents the velocity increment of the transfer orbit, ΔV1 represents the first pulse, ΔV2 represents the second pulse, and V initial represents the initial orbit velocity, V transfer represents the first transfer orbit velocity from the initial orbit to the transfer orbit, V target represents the target orbit velocity, V ′ transfer represents the second transfer orbit velocity from the transfer orbit to the target orbit.

[0126] The calculation formula for the utilization rate of TT&C resources of the small spacecraft is: η 测控 is the utilization rate of TT&C resources, ∑t 使用 is the occupied time of the cumulative actual mission, ∑t 可见 is the cumulative visible time.

[0127] In an optional manner, the multi-modal sensor includes: a camera and a lidar; wherein, the camera is used to collect two-dimensional image data, and the lidar is used to collect three-dimensional point cloud data.

[0128] In an optional manner, the current multi-modal data includes: current two-dimensional image data and current three-dimensional point cloud data; the fusion damage detection result is a damage confidence map; the detection module 210 is specifically used for:

[0129] Using the ResNet-50 model, perform damage detection on the current two-dimensional image data to obtain a two-dimensional damage detection result, and use a three-dimensional point cloud model to perform damage detection on the current three-dimensional point cloud data to obtain a three-dimensional damage detection result;

[0130] Using the D-S evidence theory, fuse the two-dimensional damage detection result and the three-dimensional damage detection result to obtain the damage confidence map.

[0131] In an optional manner, the optimization module 230 is specifically used for:

[0132] Using the damage confidence map, the accompanying flight distance and observation angle of the small spacecraft corresponding to the target observation trajectory are optimized to obtain the optimal observation trajectory.

[0133] It should be noted that the beneficial effects of the small spacecraft trajectory multi-objective optimization system 200 for target spacecraft monitoring provided in the above embodiments are the same as those of the small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring, and will not be elaborated here. In addition, when the system provided in the above embodiments realizes its functions, only the division of the above function modules is used for illustration. In practical applications, the above functions can be allocated to different function modules according to needs, that is, the system is divided into different function modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be elaborated here.

[0134] Among them, the small spacecraft trajectory multi-objective optimization system for target spacecraft monitoring of the present invention can be a computer program (including program code) running in a computer device. For example, the small spacecraft trajectory multi-objective optimization system of the present invention is an application software, which can be used to execute the corresponding steps in the small spacecraft trajectory multi-objective optimization method of the present invention.

[0135] In some embodiments, the small spacecraft trajectory multi-objective optimization system of the present invention can be implemented in a combination of software and hardware. As an example, the small spacecraft trajectory multi-objective optimization system of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the small spacecraft trajectory multi-objective optimization method of the present invention. For example, the processor in the form of a hardware decoding processor can use one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs) or other electronic components.

[0136] Among them, the modules involved in the embodiments of the present invention can be implemented by software or by hardware. Among them, the name of the module does not constitute a limitation to the module itself in some cases.

[0137] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft as described in any one of the above is implemented. That is to say, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store a computer program; the processor is used to execute the multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft shown in any embodiment of the present invention by calling the computer program.

[0138] In an alternative embodiment, an electronic device is provided, as Figure 4 shown Figure 4 The electronic device 4000 shown in includes: a processor 4001 and a memory 4003. Among them, the processor 4001 and the memory 4003 are connected, such as connected through a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, and the transceiver 4004 may be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data, etc. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation to the embodiment of the present invention.

[0139] The processor 4001 may be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosure of the present invention. The processor 4001 may also be a combination that realizes a computing function, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0140] The bus 4002 may include a path for transmitting information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture, extended industry standard structure) bus, etc. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation,Figure 4 In the figure, the bus 4002 is represented only by a thick line, but this does not mean that there is only one bus or one type of bus.

[0141] The memory 4003 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0142] The memory 4003 is used to store the application program code (computer program) for implementing the solution of the present invention and is controlled by the processor 4001 for execution. The processor 4001 is used to execute the application program code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0143] Among them, the electronic device can also be a terminal device. The terminal device can be any terminal device that can install an application and access a web page through the application, including at least one of a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart vehicle-mounted device.

[0144] It should be noted that Figure 4 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0145] A computer-readable storage medium according to an embodiment of the present invention has a computer program stored thereon. When the computer program is executed by a processor, it implements any one of the above-mentioned multi-objective optimization methods for the trajectory of a small spacecraft for target spacecraft monitoring.

[0146] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0147] In an exemplary embodiment, a computer program product or a computer program is further provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the small spacecraft trajectory multi-objective optimization method for monitoring a target spacecraft as described above.

[0148] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by connecting through the Internet service provider via the Internet).

[0149] It should be understood that the flowcharts and block diagrams in the drawings illustrate the possible architectures, functions, and operations of the methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0150] The computer-readable storage medium provided by the embodiments of the present invention may be, but is not limited to, a system, device, or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, device, or component.

[0151] The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed by the electronic device, the electronic device is caused to execute the method shown in the above embodiments.

[0152] The above description is only a preferred embodiment of the present invention and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the present invention.

[0153] It should be noted that the terms "first", "second", etc. in the description and claims of this application are used to distinguish similar objects, and represent a limitation on a specific order or sequence. Under appropriate circumstances, the usage order of similar objects can be interchanged so that the embodiments of this application described here can be implemented in an order other than the illustrated or described order.

[0154] Those skilled in the art know that the present invention can be implemented as a system, method, or computer program product. Therefore, the present invention can be specifically implemented in the following forms, that is: it can be completely hardware, can also be completely software (including firmware, resident software, microcode, etc.), and can also be in the form of a combination of hardware and software, which is generally referred to as "circuit", "module", or "system" in this article. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable media contains computer-readable program code.

[0155] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A multi-objective optimization method for the trajectory of small spacecrafts for target spacecraft monitoring, characterized in that, Including: Using a small spacecraft equipped with multi-modal sensors to obtain the current multi-modal data of the outer surface area of the target spacecraft, and fusing the damage detection results of each modality of the current multi-modal data to obtain a fused damage detection result; Constructing a multi-objective optimization model for generating the observation path of the small spacecraft, and using an improved NSGA-II algorithm and entropy weight TOPSIS method to solve the multi-objective optimization model to obtain the target observation trajectory of the small spacecraft; Using the fused damage detection result to dynamically adjust the target observation trajectory to obtain the optimal observation trajectory of the small spacecraft.

2. The multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft according to claim 1, wherein The multi-objective optimization model aims at maximizing the image resolution, minimizing the fuel consumption, and maximizing the utilization rate of TT&C resources of the small spacecraft, and is constrained by lighting conditions, minimum resolution, and TT&C resource occupancy rate.

3. The small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring according to claim 2, wherein The objective function F of the multi-objective optimization model is: Where, -R represents the image negative resolution of the camera of the small spacecraft, ΔV represents the transfer orbit velocity increment of the small spacecraft, -η 测控 represents the negative utilization rate of the TT&C resources of the small spacecraft; f1(x) = min(-R) represents the optimization function corresponding to maximizing the image resolution, f2(x) = min(ΔV) represents the optimization function corresponding to minimizing the fuel consumption, f3(x) = min(-η 测控 ) represents the optimization function corresponding to maximizing the utilization rate of the TT&C resources; The constraint conditions of the multi-objective optimization model are: Where θ represents the solar incidence angle, represents the occlusion angle of the Earth or the Moon with respect to the target spacecraft, and R min is the minimum image resolution constraint value.

4. The small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring according to claim 3, characterized in that The adjustment formula for the image resolution of the camera is as follows: where R represents the image resolution of the camera, n represents the total number of observation points of the target spacecraft, and d i is the distance between the camera and the i-th observation point of the target spacecraft, f is the focal length, h is the pixel height, and p size is the pixel size; The calculation formula for the velocity increment of the transfer orbit of the small spacecraft is: ΔV = ‖ΔV1‖ + ‖ΔV2‖; where, ΔV1 = V transfer - V initial , ΔV2 = V target - V ′ transfer ; ΔV represents the velocity increment of the transfer orbit, ΔV1 represents the first pulse, ΔV2 represents the second pulse, V initial represents the initial orbit velocity, V transfer represents the first transfer orbit velocity from the initial orbit to the transfer orbit, V target represents the target orbit velocity, V ′ transfer represents the second transfer orbit velocity from the transfer orbit to the target orbit; The calculation formula for the utilization rate of TT&C resources of the small spacecraft is as follows: η 测控 is the utilization rate of TT&C resources, ∑t 使用 is the occupied time of the cumulative actual mission, ∑t 可见 is the cumulative visible time.

5. The small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring according to any one of claims 1 to 4, characterized in that The multi-modal sensors include: a camera and a lidar; wherein, the camera is used to collect two-dimensional image data, and the lidar is used to collect three-dimensional point cloud data.

6. The small spacecraft trajectory multi-objective optimization method for target spacecraft monitoring according to claim 5, characterized in that The current multi-modal data includes: current two-dimensional image data and current three-dimensional point cloud data; the fused damage detection result is a damage confidence map; The steps of fusing the damage detection results of each modality of the current multi-modal data to obtain a fused damage detection result include: Using a ResNet-50 model to perform damage detection on the current two-dimensional image data to obtain a two-dimensional damage detection result, and using a three-dimensional point cloud model to perform damage detection on the current three-dimensional point cloud data to obtain a three-dimensional damage detection result; Using the D-S evidence theory to fuse the two-dimensional damage detection result and the three-dimensional damage detection result to obtain the damage confidence map.

7. The multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft according to claim 6, characterized in that, The steps of using the fused damage detection result to dynamically adjust the target observation trajectory to obtain the optimal observation trajectory of the small spacecraft include: Using the damage confidence map to optimize the accompanying distance and observation angle of the small spacecraft corresponding to the target observation trajectory to obtain the optimal observation trajectory.

8. A small spacecraft trajectory multi-objective optimization system for target spacecraft monitoring, characterized in that Including: A detection module, a generation module, and an optimization module; The detection module is used for: using a small spacecraft equipped with multi-modal sensors to obtain the current multi-modal data of the outer surface area of the target spacecraft, and fusing the damage detection results of each modality of the current multi-modal data to obtain a fused damage detection result; The generation module is used for: constructing a multi-objective optimization model for generating the observation path of the small spacecraft, and using an improved NSGA-II algorithm and entropy weight TOPSIS method to solve the multi-objective optimization model to obtain the target observation trajectory of the small spacecraft; The optimization module is used for: using the fused damage detection result to dynamically adjust the target observation trajectory to obtain the optimal observation trajectory of the small spacecraft.

9. An electronic device, characterized in that, The electronic device includes a processor, the processor is coupled to a memory, and at least one computer program is stored in the memory. The at least one computer program is loaded and executed by the processor so that the electronic device implements the multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, At least one computer program is stored in the computer-readable storage medium. The at least one computer program is loaded and executed by a processor so that the computer-readable storage medium implements the multi-objective optimization method for the trajectory of a small spacecraft for monitoring a target spacecraft as described in any one of claims 1 to 7.

Images