With the explosion of the number of meteoroid/orbital debris in terrestrial space in recent years, the detection environment of spacecraft becomes more complex. This phenomenon causes most current detection methods ba...With the explosion of the number of meteoroid/orbital debris in terrestrial space in recent years, the detection environment of spacecraft becomes more complex. This phenomenon causes most current detection methods based on machine learning intractable to break through the two difficulties of solving scale transformation problem of the targets in image and accelerating detection rate of high-resolution images. To overcome the two challenges, we propose a novel noncooperative target detection method using the framework of deep convolutional neural network.Firstly, a specific spacecraft simulation dataset using over one thousand images to train and test our detection model is built. The deep separable convolution structure is applied and combined with the residual network module to improve the network’s backbone. To count the different shapes of the spacecrafts in the dataset, a particular prior-box generation method based on K-means cluster algorithm is designed for each detection head with different scales. Finally, a comprehensive loss function is presented considering category confidence, box parameters, as well as box confidence. The experimental results verify that the proposed method has strong robustness against varying degrees of luminance change, and can suppress the interference caused by Gaussian noise and background complexity. The mean accuracy precision of our proposed method reaches 93.28%, and the global loss value is 13.252. The comparative experiment results show that under the same epoch and batchsize, the speed of our method is compressed by about 20% in comparison of YOLOv3, the detection accuracy is increased by about 12%, and the size of the model is reduced by nearly 50%.展开更多
The shape approximation method has been proven to be rapid and practicable in resolving low-thrust trajectory;however,it still faces the challenges of large deviation from the optimal solution and inability to satisfy...The shape approximation method has been proven to be rapid and practicable in resolving low-thrust trajectory;however,it still faces the challenges of large deviation from the optimal solution and inability to satisfy the specific flight time and fuel mass constraints.In this paper,a modified shape approximation low-thrust model is presented,and a novel constrained optimization algorithm is developed to solve this problem.The proposed method aims at settling the bi-objective optimization orbit involving the twin objectives of minimum flight time and low fuel consumption and enhancing the accuracy of optimized orbit.In particular,a transformed high-order polynomial model based on finite Fourier series is proposed,which can be characterized as a multi-constraint optimization problem.Then,a novel optimization algorithm is specifically developed to optimize the large-scale multi-constraint dynamical equations of shape trajectory.The key performance indicators of the index include minimum flight time,low fuel consumption and bi-objective optimization of the two.Simulation results prove that this approach possesses both the high precision achievable by numerical methods and low computational complexity offered by shape approximation techniques.Besides,the Pareto front of the fuel-time bi-objective optimization orbit is firstly introduced to analyze an intact optimal solution set.Furthermore,we have demonstrated that our proposed approach is appropriate to generate the preliminary orbit for pseudo-spectral method.展开更多
基金supported by the National Natural Science Foundation of China(No.61473100)。
文摘With the explosion of the number of meteoroid/orbital debris in terrestrial space in recent years, the detection environment of spacecraft becomes more complex. This phenomenon causes most current detection methods based on machine learning intractable to break through the two difficulties of solving scale transformation problem of the targets in image and accelerating detection rate of high-resolution images. To overcome the two challenges, we propose a novel noncooperative target detection method using the framework of deep convolutional neural network.Firstly, a specific spacecraft simulation dataset using over one thousand images to train and test our detection model is built. The deep separable convolution structure is applied and combined with the residual network module to improve the network’s backbone. To count the different shapes of the spacecrafts in the dataset, a particular prior-box generation method based on K-means cluster algorithm is designed for each detection head with different scales. Finally, a comprehensive loss function is presented considering category confidence, box parameters, as well as box confidence. The experimental results verify that the proposed method has strong robustness against varying degrees of luminance change, and can suppress the interference caused by Gaussian noise and background complexity. The mean accuracy precision of our proposed method reaches 93.28%, and the global loss value is 13.252. The comparative experiment results show that under the same epoch and batchsize, the speed of our method is compressed by about 20% in comparison of YOLOv3, the detection accuracy is increased by about 12%, and the size of the model is reduced by nearly 50%.
基金supported by the National Natural Science Foundation of China(Nos.61627810,61790562,61403096).
文摘The shape approximation method has been proven to be rapid and practicable in resolving low-thrust trajectory;however,it still faces the challenges of large deviation from the optimal solution and inability to satisfy the specific flight time and fuel mass constraints.In this paper,a modified shape approximation low-thrust model is presented,and a novel constrained optimization algorithm is developed to solve this problem.The proposed method aims at settling the bi-objective optimization orbit involving the twin objectives of minimum flight time and low fuel consumption and enhancing the accuracy of optimized orbit.In particular,a transformed high-order polynomial model based on finite Fourier series is proposed,which can be characterized as a multi-constraint optimization problem.Then,a novel optimization algorithm is specifically developed to optimize the large-scale multi-constraint dynamical equations of shape trajectory.The key performance indicators of the index include minimum flight time,low fuel consumption and bi-objective optimization of the two.Simulation results prove that this approach possesses both the high precision achievable by numerical methods and low computational complexity offered by shape approximation techniques.Besides,the Pareto front of the fuel-time bi-objective optimization orbit is firstly introduced to analyze an intact optimal solution set.Furthermore,we have demonstrated that our proposed approach is appropriate to generate the preliminary orbit for pseudo-spectral method.