程林 - 北京航空航天大学

个人简介

关于个人经历 2017年11月，博士毕业于北京航空航天大学自动化科学与工程学院，专业是导航、制导与控制专业。 2018年01月，加入清华大学航天航空学院从事博士后工作，专业偏向于航天动力学与控制。期间很荣幸的跟着四位合作导师学习，高山仰止，景行行止，四位导师分别是：李俊峰（万人名师），宝音贺西（杰青），蒋方华（优青），龚胜平（优青）。 2021年01月，全职加入北京航空航天大学宇航学院，准聘副教授。龚胜平老师因工作调动入职北航，与宇航学院师鹏老师(宇航学院副院长)，组成一个新的课题组，合作培养学生。教育经历 2014.9 -- 2017.11 北京航空航天大学控制科学与工程博士研究生毕业工学博士学位 2011.9 -- 2014.4 北京航空航天大学控制科学与工程硕士研究生毕业工学硕士学位 2007.9 -- 2011.6 山东大学控制科学与工程大学本科毕业工学学士学位工作经历 2021.1 -- 2099.1 北京航空航天大学宇航学院副教授副教授 2018.1 -- 2021.1 清华大学航天航空学院博士后合作导师李俊峰、宝音贺西、蒋方华、龚胜平社会兼职《空天防御》青年编委《IEEE Transactions on Neural Networks and Learning Systems》审稿人《Acta Astronautica》审稿人《Aerospace Science and Technology》审稿人《IEEE Transactions on Aerospace and Electronic Systems》审稿人

研究领域

一、航天器动力学与智能控制，包括 (1) 动力学在线辨识与学习：不确定性在线辨识，不确定性边界在线估计，模型在线精确化，动力学智能补偿 (2) 智能自适应控制：控制参数智能调度，弱模型依赖控制，模型参考自适应控制，神经网络自适应控制 (3) 实时最优控制：传统最优控制方法(间接法、凸优化)实时性改良、基于监督学习机制的实时最优控制、基于强化学习机制的实时最优控制、强化学习方法改良、最优自适应控制、随机最优控制二、博弈对抗与智能决策，包括 (1) 单体vs群体博弈对抗与决策：飞行器能力智能预估、单体全飞行过程智能突防、基于微分对策的博弈对抗、Min-Max问题实时性求解 (2) 群体vs群体博弈对抗与决策：攻防对抗评估体系构建、群体对抗目标分配、考虑协同配合的末制导律设计、基于微分对策的多对多博弈对抗建模与求解、多弹协同探测与控制

近期论文

查看导师新发文章（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

Lin Cheng, Zhenbo Wang, Shengping Gong, Adaptive Control of Hypersonic Vehicles with Unknown Dynamics Based on Dual Network Architecture, Acta Astronautica, 2022 Chi Z, Wang Y, Cheng L. Indirect low-thrust trajectory optimization with gridded ion thruster model. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering. October 2021. doi:10.1177/09544100211043846 Di Wu, Lin Cheng, Fanghua Jiang, Junfeng Li, Rapid generation of low-thrust many-revolution earth-center trajectories based on analytical state-based control, Acta Astronautica, Volume 187, 2021, Pages 338-347, ISSN 0094-5765, https://doi.org/10.1016/j.actaastro.2021.05.017. Yu Song, Xinyuan Miao, Lin Cheng, Shengping Gong, The feasibility criterion of fuel-optimal planetary landing using neural networks, Aerospace Science and Technology, Volume 116, 2021, 106860, ISSN 1270-9638, https://doi.org/10.1016/j.ast.2021.106860. Lin CHENG, Peng SHI, Shengping GONG, Zhenbo WANG, Real-time trajectory optimization for powered planetary landings based on analytical shooting equations, Chinese Journal of Aeronautics, 2021,ISSN 1000-9361, https://doi.org/10.1016/j.cja.2021.07.024..[期刊]:Chinese Journal of Aeronautics Lin Cheng, Zhenbo Wang, Fanghua Jiang, Junfeng Li. Multi-Constrained Real-Time Entry Guidance Using Deep Neural Networks[J]. IEEE Transactions on Aerospace and Electronic Systems, 2020. (Q1, 3/31, 3.67) Lin Cheng, Zhenbo Wang, Fanghua Jiang, Junfeng Li.Adaptive Neural Network Control of Nonlinear Systems with Unknown Dynamics[J]. Advances in Space Research, 2020. (Q2, 8/31,2.177) Shanshan Yin, Jian Li, Lin Cheng(通讯). Low-thrust Spacecraft Trajectory Optimization via a DNN-Based Method[J]. Advances in Space Research, 2020. (Q2, 8/31,2.177) Di Wu, Lin Cheng(通讯), Junfeng Li. Warm-Start Multi-Homotopic Optimization for Low-Thrust ManyRevolution Trajectories. IEEE Transactions on Aerospace and Electronic Systems, 2020. (Q1, 3/31, 3.67) 程林, 蒋方华, 李俊峰. 深度学习在飞行器动力学与控制中的应用研究综述 [J]. 力学与实践, 2020, 42(3): 267-276. Lin Cheng, Zhenbo Wang, Fanghua Jiang. Real-time Optimal Entry Guidance based on Deep Reinforcement Learning[C]. 71th International Astronautical Congress. 2020. Lin Cheng, Zhenbo Wang, Fanghua Jiang. Fast Generation of Optimal Asteroid Landing Trajectories Using Deep Neural Networks. IEEE Transactions on Aerospace and Electronic Systems, 2019. (Q1, 3/31, 3.67) Lin Cheng, Zhenbo Wang, Fanghua Jiang. Fast Solution Continuation of Time-Optimal Asteroid Landing Trajectories Using Deep Neural Networks. Acta Astronautica, 2019. (Q1, 4/31, 2.83) Lin Cheng, Zhenbo Wang, Fanghua Jiang. An Identifier-Actor-Indirect Method Policy Learning Architecture for Optimal Control of Continuous-Time Nonlinear Systems. Science China-Physics Mechanics & Astronomy, 2019. (Q1, 11/85, 3.99) Lin Cheng, Zhenbo Wang, Fanghua Jiang. Real-Time Optimal Control for Irregular Asteroid Landings Using Deep Neural Networks. Acta Astronautica, 2019. (Q1, 4/31, 2.83) Lin Cheng, Zhenbo Wang, and Fanghua Jiang. ”Real-time control for fuel-optimal Moon landing based on an interactive deep reinforcement learning algorithm.” Astrodynamics 3.4 (2019): 375-386 Lin Cheng, Qingzhen Zhang, Fanghua Jiang. Multi-constrained compound reentry guidance based on onboard model identification[J]. Journal of Tsinghua University (Science and Technology). 2019, 01, (01). Lin Cheng, Zhenbo Wang, Yu Song, et al. Real-time Optimal Control for Irregular Asteroid Landings Using Deep Neural Networks[C]. 29th AAS/AIAA Space Flight Mechanics Meeting. 2019. Yu Song, Lin Cheng, Shengping Gong. Fast Estimation of Gravitational Field of Irregular Asteroids Based on Deep Learning and Its Applications[C]. 29th AAS/AIAA Space Flight Mechanics Meeting. 2019. Lin Cheng, Zhenbo Wang, Fanghua Jiang. Multi-Constrained Real-Time Entry Guidance Using Deep Neural Networks[C]. 70th International Astronautical Congress. 2019. Lin Cheng, Zhenbo Wang, Fanghua Jiang. Real-Time Optimal Control for Spacecraft Orbit Transfer via Multi-Scale Deep Neural Networks[J]. IEEE Transactions on Aerospace and Electronic Systems, 2018. (Q1, 3/31,3.67) Lin Cheng, Zhenbo Wang, Yang Cheng. Multi-constrained predictor-corrector reentry guidance for hypersonic vehicles[J]. Proceedings of the Institution of Mechanical Engineers - Part G: Journal of Aerospace Engineering, 2017. (Q3, 17/31, 1.1) Lin Cheng, Qingzhen Zhang, Kun Ni, et al. Advanced Reentry Guidance based on On-board Reference Trajectory Reconstruction[C]. Control And Decision Conference (CCDC), 2017. Yang Cheng, Lin Cheng, Qingzhen Zhang. Aircraft predictor-corrector guidance based on online constraint limit enforcement[J]. Journal of Beijing University of Aeronautics and Astronautics, 2017. Lin Cheng, Qingzhen Zhang, Fei Tao. A novel search algorithm based on waterweeds reproduction principle for job shop scheduling problem[J]. International Journal of Advanced Manufacturing Technology, 2016. (Q2, 25/50, 2.63, Publication) Yonglai Kang, Lin Cheng(Corresponding Author), Qingzhen Zhang. Data-driven RLV multi-objective reentry trajectory optimization based on new QABC algorithm[J]. International Journal of Advanced Manufacturing Technology, 2016. (Q2, 25/50, 2.63)