检索结果-南通市图书馆

A physics-informed deep learning framework for spacecraft pursuit-evasion task assessment

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第5期37卷 363-376页

作者： Fuyunxiang YANG Leping YANG yanwei zhu College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410073China

Qualitative spacecraft pursuit-evasion problem which focuses on feasibility is rarely studied because of high-dimensional dynamics,intractable terminal constraints and heavy computational *** this paper,A physics-informed framework is proposed for the problem,providing an intuitive method for spacecraft threat relationship determination,situation assessment,mission feasibility analysis and orbital game rules *** the first time,situation adjustment suggestions can be provided for the weak player in orbital ***,a dimension-reduction dynamics is derived in the line-of-sight rotation coordinate system and the qualitative model is determined,reducing complexity and avoiding the difficulty of target set presentation caused by individual ***,the Backwards Reachable Set(BRS)of the target set is used for state space partition and capture zone ***-time analysis can eliminate the influence of changeable initial state and enable the proposed framework to analyze plural situations ***,a time-dependent Hamilton-Jacobi-Isaacs(HJI)Partial Differential Equation(PDE)is established to describe BRS evolution driven by dimension-reduction dynamics,based on level set ***,Physics-Informed Neural Networks(PINNs)are extended to HJI PDE final value problem,supporting orbital game rules summarization through capture zone evolution ***,numerical results demonstrate the feasibility and efficiency of the proposed framework.

关键词： Spacecraft pursuit-evasion Qualitative differential game Physics-Informed Neural Networks(PINNs) Reachability analysis Hamilton-Jacobi-Isaacs(HJI) Partial Differential Equations(PDEs)

A DNN based trajectory optimization method for intercepting non-cooperative maneuvering spacecraft

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2022年第2期33卷 438-446页

作者： YANG Fuyunxiang YANG Leping zhu yanwei ZENG Xin College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410073China

Current successes in artificial intelligence domain have revitalized interest in neural networks and demonstrated their potential in solving spacecraft trajectory optimization problems. This paper presents a data-free deep neural network(DNN) based trajectory optimization method for intercepting noncooperative maneuvering spacecraft, in a continuous low-thrust scenario. Firstly, the problem is formulated as a standard constrained optimization problem through differential game theory and minimax principle. Secondly, a new DNN is designed to integrate interception dynamic model into the network and involve it in the process of gradient descent, which makes the network endowed with the knowledge of physical constraints and reduces the learning burden of the network. Thus, a DNN based method is proposed, which completely eliminates the demand of training datasets and improves the generalization capacity. Finally, numerical results demonstrate the feasibility and efficiency of our proposed method.

关键词： non-cooperative maneuvering spacecraft neural network differential game trajectory optimization

A guidance method for coplanar orbital interception based on reinforcement learning

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2021年第4期32卷 927-938页

作者： ZENG Xin zhu yanwei YANG Leping ZHANG Chengming College of Aeronautics and Astronautics National University of Defense TechnologyChangsha 410073China

This paper investigates the guidance method based on reinforcement learning(RL)for the coplanar orbital interception in a continuous low-thrust *** problem is formulated into a Markov decision process(MDP)model,then a welldesigned RL algorithm,experience based deep deterministic policy gradient(EBDDPG),is proposed to solve *** taking the advantage of prior information generated through the optimal control model,the proposed algorithm not only resolves the convergence problem of the common RL algorithm,but also successfully trains an efficient deep neural network(DNN)controller for the chaser spacecraft to generate the control *** simulation results show that the proposed algorithm is feasible and the trained DNN controller significantly improves the efficiency over traditional optimization methods by roughly two orders of magnitude.

关键词： orbital interception reinforcement learning(RL) Markov decision process(MDP) deep neural network(DNN)

Optimal reconfiguration of constellation using adaptive innovation driven multiobjective evolutionary algorithm

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2021年第6期32卷 1527-1538页

作者： HU Jiaxin YANG Leping HUANG Huan zhu yanwei College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410073China

Constellation reconfiguration is a critical issue to recover from the satellite failure,maintain the regular operation,and enhance the overall *** constellation reconfiguration problem faces the difficulties of high dimensionality of design variables and extremely large decision space due to the great and continuously growing constellation *** solve such real-world problems that can be hardly solved by traditional algorithms,the evolutionary operators should be promoted with available domain knowledge to guide the algorithm to explore the promising regions of the trade *** adaptive innovationdriven multi-objective evolutionary algorithm(MOEA-AI)employing automated innovation(AI)and adaptive operator selection(AOS)is proposed to extract and apply domain *** available knowledge is extracted from the final or intermediate solution sets and integrated into an operator by the automated innovation *** prevent the overuse of knowledgedependent operators,AOS provides top-level management between the knowledge-dependent operators and conventional evolutionary *** evaluates and selects operators according to their actual performance,which helps to identify useful operators from the candidate *** efficacy of the MOEAAI framework is demonstrated by the simulation of emergency *** was verified that the proposed algorithm can discover a non-dominant solution set with better quality,more homogeneous distribution,and better adaptation to practical situations.

关键词： constellation reconfiguration emergency observations rapid response multi-objective optimization

An optimal guidance method for free-time orbital pursuit-evasion game

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2022年第6期33卷 1294-1308页

作者： ZHANG Chengming zhu yanwei YANG Leping ZENG Xin College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410000China

With the development of space rendezvous and proximity operations(RPO)in recent years,the scenarios with noncooperative spacecraft are attracting the attention of more and more researchers.A method based on the costate normalization technique and deep neural networks is presented to generate the optimal guidance law for free-time orbital pursuit-evasion ***,the 24-dimensional problem given by differential game theory is transformed into a three-parameter optimization problem through the dimension-reduction method which guarantees the uniqueness of solution for the specific ***,a close-loop interactive mechanism involving feedback is introduced to deep neural networks for generating precise initial *** the optimal guidance law is obtained efficiently and stably with the application of optimization algorithm initialed by the deep neural ***,the results of the comparison with another two methods and Monte Carlo simulation demonstrate the efficiency and robustness of the proposed optimal guidance method.

关键词： orbital pursuit-evasion differential game dimension-reduction deep neural networks

Dynamics and nonlinear control of space electromagnetic docking

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2013年第3期24卷 454-462页

作者： Yuanwen Zhang Leping Yang yanwei zhu Huan Huang College of Aerospace Science and Engineering National University of Defense Technology

Space electromagnetic docking technology, free of propellant and plume contamination, offers continuous, reversible and synchronous controllability, which is widely applied in the future routine on-orbit servicing missions. Due to the inherent nonlinearities, couplings and uncertainties of an electromagnetic force model, the dynamics and control problems of them are difficult. A new modeling approach for relative motion dynamics with intersatellite force is proposed. To resolve these control problems better, a novel nonlinear control method for soft space electro-magnetic docking is proposed, which combines merits of artificial potential function method, Lyapunov theory and extended state observer. In addition, the angular momentum management problem of space electromagnetic docking and approaches of handling it by exploiting the Earth＇s magnetic torque are investigated. Finally, nonlinear simulation results demonstrate the feasibility of the dynamic model and the novel nonlinear control method.

关键词： space electromagnetic docking dynamic model soft docking control angular momentum management inter-satellite electromagnetic force on-orbit servicing.

Formation keeping control through inter-satellite electromagnetic force

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2013年第5期56卷 1102-1111页

作者： CAI WeiWei YANG LePing zhu yanwei ZHANG YuanWen College of Aerospace Science and Engineering National University of Defense Technology

Satellite formation keeping through inter-satellite electromagnetic force provides an attractive alternative for future space missions due to its distinct advantages of no propellant consumption or plume contamination as compared to conventional ***,the internal force nature as well as the high nonlinearity and coupling of electromagnetic force brings new control challenges for this novel *** this paper,analysis on the dynamics characteristics and special control issues in the presence of electromagnetic force is carried out on the basis of the derived relatively translational *** the model uncertainties,external disturbances and sensor noise,a combined nonlinear control scheme involving feed-forward and feedback control components is proposed for electromagnetic-force-based formation *** feed-forward component is directly obtained through desired configuration and dynamics under nominal conditions while the feedback component is realized utilizing active disturbance rejection control methodology with some reasonable *** simulation is presented to verify the feasibility and validity of the combined control scheme.

关键词： inter-satellite electromagnetic force formation keeping dynamics analysis active disturbance rejection nonlinear control

Neuron-inspired design of hierarchically porous carbon networks embedded with single-iron sites for efficient oxygen reduction

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2022年第7期65卷 1445-1452页

作者： yanwei zhu Xuxu Wang Jianqiao Shi Lang Gan Binbin Huang Li Tao Shuangyin Wang State Key Laboratory of Chemo/Bio-Sensing and Chemometrics College of Chemistry and Chemical EngineeringAdvanced Catalytic Engineering Research Center of the Ministry of EducationHunan UniversityChangsha 410082China College of Environmental science and Engineering Hunan UniversityChangsha 410082China

The rational structure design and active-site regulation of catalysts is crucial for high energy output. Herein, B, F co-doped Fe–N–C embedded in a flexible and free-standing hierarchical porous carbon framework(Fe–SA–FPCS) was reported. Owing to the synergism of optimized intrinsic activity, fast mass transfer and well exposed active sites, the Fe–SA–FPCS exhibits a high halfwave potential(E1/2=0.89 V vs. RHE) and small Tafel slope(66 m V dec^(-1)). Theoretical calculations uncover that B, F co-doping could accelerate the desorption of OH* on Fe sites, which can effectively increase oxygen reduction reaction activity. As the cathode for Zn–air batteries(ZABs), Fe–SA–FPCS demonstrates a high open-circuit voltage(1.51 V), large peak power density(168.4 m W cm^(-2)) and excellent stability. The assembled flexible solid-state ZAB exhibits excellent stability during charge and discharge cycling in the flat/bent state, and is promising for the application of portable and flexible devices. This work provides a new perspective for the fabrication of single-atom electrocatalysts with well-designed structure and excellent electrochemical energy conversion and storage capability.

关键词： Electrospinning single-atom catalysts oxygen reduction reaction hierarchical porous structure zinc–air battery

同方期刊数据库

Understanding the surface segregation behavior of bimetallic CoCu toward HMF oxidation reaction

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2022年第11期31卷 85-90,I0004页

作者： yanwei zhu Jianqiao Shi Yingying Li Yuxuan Lu Bo Zhou Shuangyin Wang Yuqin Zou State Key Laboratory of Chem/Bio-Sensing and Chemometrics Advanced Catalytic Engineering Research Center of the Ministry of EducationCollege of Chemistry and Chemical EngineeringHunan UniversityChangsha 410082HunanChina School of Chemistry and Chemical Engineering Jishou UniversityJishou 416000HunanChina

Surface segregation is ubiquitous in multi-component materials and is of great important for catalysis but little is known on the surface structure under graphene ***,we show that the graphene encapsulated CoCu performs well for the electrocatalytic oxidation of 5-hydroxymethylfurfural(HMF)to2,5-furandicarboxylic acid(FDCA)with the onset potential before 1.23 VRHEand a nearly 100%selectivity of FDCA under 1.4 *** the experimental results,the unprecedented catalytic performance was attributed to local structural distortion and sub-nanometer lattice composition of the CoCu *** accurately show the dispersed Cu doped Co_(3)O_(4) nano-islands with a lot of edge sites on the bimetallic Co-Cu ***,the gradient components effectively facilitate the establishment of built-in electric field and accelerate the charge *** and experimental results reveal that the surface Co and neighbouring Cu atoms in sub-nanometer lattice synergistically promote the catalysis of *** work offers new insights into surface segregation in tuning the element spatial distribution for catalysis.

关键词： CoCu alloy Surface segregation Sub-nanometer lattice Electrocatalysis HMF oxidation