| 1,013 | 11 | 96 |
| Downloads | Citas | Reads |
In view of the real-time trajectory planning requirements of hypersonic vehicles, a real-time trajectory optimization method based on deep neural network is proposed. The trajectory optimization model of the re-entry phase of the hypersonic vehicle is established. Considering the random start and end positions and random threat areas, the pseudo spectral method is used for offline trajectory optimization to obtain a large number of optimal trajectory data samples. A deep neural network model is established with the sequence of state and control quantities of the trajectory as input and the trajectory control at the current moment as output.The parameters of the deep neural network model are trained based on the optimal trajectory data sample library, and the best neural network model that can predict the trajectory control output is obtained. The flight trajectory of the re-entry section of the hypersonic vehicle is validated by Monte Carlo targeting simulation.The simulation results show that the proposed deep learning-based method can achieve fast generation of optimal trajectories for hypersonic vehicles, which indicate the advantages of high computational efficiency and high reliability. Compared with the traditional trajectory optimization algorithms, the proposed method has the generalization capability to meet the accuracy requirements and can meet the requirements of online real-time trajectory optimization.
[1] Mansell J R,Grant M J. Adaptive continuation strategy for indirect hypersonic trajectory optimization[J].Journal of Spacecraft and Rockets, 2018, 55(4):818-828.
[2] Grant M J, Braun R D. Rapid indirect trajectory optimization for conceptual design of hypersonic missions[J]. Journal of Spacecraft and Rockets,2015,52(1):177-182.
[3] Tang G, Jiang F, Li J. Fuel-optimal low-thrust trajectory optimization using indirect method and successive convex programming[J]. IEEE Transactions on Aerospace&Electronic Systems,2018:1-1.
[4] Taheri E, Kolmanovsky I, Atkins E. Enhanced smoothing technique for indirect optimization of minimum-fuel low-thrust trajectories[J]. Journal of Guidance Control&Dynamics, 2016, 39(11):2500-2511.
[5] Hargraves C R,Paris S W. Direct trajectory optimization using nonlinear programming and collocation[J]. Journal of Guidance Control&Dynamics, 1986, 10(4):338-342.
[6] Lekkas A M, Roald A L, Breivik M. Online path planning for surface vehicles exposed to unknown ocean currents using pseudospectral optimal control[C]. IFACPapers OnLine,2016,49(23):1-7.
[7] Bittner M,Fisch F,Holzapfel F. A multi-model Gauss pseudospectral optimization method for aircraft trajectories[C]. AIAA Atmospheric Flight Mechanics Conference,2012.
[8] Wang J, Liang H, Qi Z, et al. Mapped Chebyshev pseudospectral methods for optimal trajectory planning of differentially flat hypersonic vehicle systems[J].Aerospace Science and Technology, 2019, 89(6):420-430.
[9] Wang G, Chu H E, Mirjalili S. Three-dimensional path planning for UCAV using an improved bat algorithm[J]. Aerospace Science and Technology, 2016, 49(2):231-238.
[10] Li Y,Wu Y,Qu X. Chicken swarm-based method for ascent trajectory optimization of hypersonic vehicles[J].Journal of Aerospace Engineering, 2017, 30(5):04017043.
[11] Duan H, Li S. Artificial bee colony-based direct collocation for reentry trajectory optimization of hypersonic vehicle[J]. Aerospace&Electronic Systems IEEE Transactions on,2015,51(1):615-626.
[12] Roh H, Oh Y J, Tahk M J, et al. L1 penalized sequential convex programming for fast trajectory optimization:With application to optimal missile guidance[J]. International Journal of Aeronautical and Space Sciences,2020,21(2):493-503.
[13] Liu C, Zhang C, Jiang H, et al. Online trajectory optimization based on successive convex optimization[C]. 2017 36th Chinese Control Conference(CCC).IEEE,2017:2577-2582.
[14] Vinh N X, Busemann A, Culp R D. Hypersonic and planetary entry flight mechanics[J]. NASA Sti/recon Technical Report A,1980,81.
[15]雍恩米，唐国金，陈磊.基于Gauss伪谱方法的高超声速飞行器再入轨迹快速优化[J].宇航学报，2008,29(6):1766-1772.
Basic Information:
DOI：10.16358/j.issn.1009-1300.20220504
China Classification Code:V249.1;V448
Citation Information:
[1]Wu Yuanpei,Wang Yang,Zhao Aihong ,et al.Obstacle avoidance trajectory planning of hypersonic vehicle based on deep learning network[J].Tactical Missile Technology,2022,No.211(01):53-59.DOI:10.16358/j.issn.1009-1300.20220504.
Fund Information:
国家自然科学基金（62003375）; 青年科学基金项目（62103452）
2022-01-15
2022-01-15