Intelligent Autonomous Decision-Making and Control of Morphing Aircraft

doi:10.3969/j.issn.1009-086x.2020.06.002

Abstract

Abstract: Morphing aircraft can actively change the shape to meet different flight performance requirements,thereby adapting to different flight environments and tasks,so it has extremely high development potential and application value.With the development of artificial intelligence,the future morphing aircraft presents a trend of “intelligence and autonomy”.The intelligent morphing flight technology is one of the technological development trends that is most likely to bring revolutionary changes to future aerospace vehicles.Firstly,combined with the development history of the morphing aircraft,the development trend of the morphing aircraft is analyzed,and it is pointed out that the intelligent morphing aircraft is the development direction of the future aircraft.Secondly,the key issues that need to be solved in the intelligent deformation decision-making process of the morphing aircraft are analyzed.Taking the deep deterministic policy gradient algorithm in the artificial intelligence algorithm as an example,an intelligent,autonomous,and highly adaptable deformation decision-making design plan is proposed.Finally,the current difficulties and hot issues in the control design of the morphing aircraft are analyzed,focusing on the design of highly adaptable and highly autonomous control schemes under the strong coupling and strong uncertainty of the morphing aircraft.A solution for the intelligent autonomous control of the corresponding morphing aircraft is proposed.

Key words: morphing aircraft, artificial intelligence, intelligent deformation decision, intelligent control, autonomous control

摘要： 变体飞行器能够主动改变外形满足不同飞行性能需求,从而适应不同飞行环境和任务,因此具有极高的发展潜力和应用价值。随着人工智能的发展,未来变体飞行器呈现出“智能化、自主化”趋势,智能变体飞行技术是最有可能带来未来航空航天飞行器革命性变化的技术发展趋势之一。首先结合变体飞行器的发展历程,分析了变体飞行器的发展趋势,指出智能变体飞行器是未来飞行器发展的方向。其次,分析了变体飞行器智能变形决策过程中亟待解决的关键问题,并以人工智能算法中的深度确定性策略梯度算法为例,提出了智能、自主、高适应性的变形决策设计方案。最后,针对目前变体飞行器控制设计中存在的难点和热点问题加以分析研究,重点考虑了变体飞行器强耦合、强不确定性等工况下的高适应性、高自主性控制方案设计,并提出了相应的变体飞行器智能自主控制的解决方案。

关键词: 变体飞行器, 人工智能, 智能变形决策, 智能控制, 自主控制

CLC Number:

WANG Qing, LIU Hua-hua. Intelligent Autonomous Decision-Making and Control of Morphing Aircraft[J]. Modern Defense Technology, 2020, 48(6): 5-11.

王青, 刘华华. 变体飞行器智能自主决策与控制[J]. 现代防御技术, 2020, 48(6): 5-11.

References

[1] 白鹏,陈钱,徐国武,等.智能可变形飞行器关键技术发展现状及展望[J].空气动力学学报,2019,37(3):426-443.
BAI Peng,CHEN Qian,XU Guo-wu,et al.Development Status of Key Technologies and Expectation about Smart Morphing Aircraft[J].Acta Aerodynamica Sinica,2019,37(3):426-443.
[2] 陆宇平,何真.变体飞行器控制系统综述[J].航空学报,2009,30(10):1906-1911.
LU Yu-ping,HE Zhen.A Survey of Morphing Aircraft Control Systems[J].Acta Aeronautica et Astronautica Sinica,2009,30(10):1906-1911.
[3] 徐浩桐,翟心蝶,闫浩安,等.飞跳一体智能飞行器设计[J].现代防御技术,2020,48(4):8-15,51.
XU Hao-tong,ZHAI Xin-die,YAN Hao-an,et al.Design of Flying-Jumping Integrated UAV[J].Modern Defence Technology,2020,48(4):8-15,51.
[4] LECUN Y,BENGIO Y,HINTON G.Deep Learning[J].Nature,2015,521(7553):436-444.
[5] LITTMAN M L.Reinforcement Learning Improves Behaviour from Evaluative Feedback[J].Nature,2015,521(7553):445-451.
[6] 董彦非,陈元恺,彭金京.可变后掠翼技术发展与展望[J].飞行力学,2014,32(2):97-100.
DONG Yan-fei,CHEN Yuan-kai,PENG Jin-jing.Development and Prospect of Variable Swept Wing[J].Flight Dynamics,2014,32(2):97-100.
[7] 王晓明,周文雅,吴志刚.压电纤维复合材料驱动的机翼动态形状控制[J].航空学报,2017,38(1):159-167.
WANG Xiao-ming,ZHOU Wen-ya,WU Zhi-gang.Dynamic Shape Control of Wings Using Piezoelectric Fiber Composite Materials[J].Acta Aeronautica et Astronautica Sinica,2017,38(1):159-167.
[8] 赵天,杨智春,刘昊,等.压电陶瓷叠层作动器迟滞蠕变非线性自适应混合补偿控制方法[J].航空学报,2018,39(12):209-220.
ZHAO-Tian,YANG Zhi-chun,LIU Hao,et al.Hysteresis and Creep Nonlinearities Modeling and Adaptive Hybrid Compensation Control of Piezoelectr[J].Acta Aeronautica et Astronautica Sinica,2018,39(12):209-220.
[9] Amanda Lampton,Amanda Niksch,John Valasek.Reinforcement Learning of a Morphing Airfoil-Policy and Discrete Learning Analysis[J].Journal of Aerospace Information Systems,2010,7(8):241-260.
[10] 温暖,刘正华,祝令谱,等.深度强化学习在变体飞行器自主外形优化中的应用[J].宇航学报,2017,38(11):1153-1159.
WEN Nuan,LIU Zheng-hua,ZHU Ling-pu,et al.Deep Reinforcement Learning and Its Application on Autonomous Shape Optimization for Morphing[J].Journal of Astronautics,2017,38(11):1153-1159.
[11] 闫斌斌,李勇,戴沛,等.基于增强学习的变体飞行器自适应变体策略与飞行控制方法研究[J].西北工业大学学报,2019,37(4):656-663.
YAN Bin-bin,LI Yong,DAI Pei,et al.Adaptive Wing Morphing Strategy and Flight Control Method of a Morphing Aircraft Based on Reinforcement Learning[J].Journal of Northwestern Polytechnical University,2019,37(4):656-663.
[12] 王青,王通,董朝阳,等.变体飞行器链式平滑切换控制[J].控制理论与应用,2015,32(7):949-954.
WANG Qing,WANG Tong,DONG Chao-yang,et al.Chained Smooth Switching Control for Morphing Aircraft[J].Control Theory & Applications,2015,32(7):949-954.
[13] WU Zhong-hua,LU Jing-chao,SHI Jing-ping.Adaptive Neural Dynamic Surface Control of Morphing Aircraft with Input Constraints[C]//The 29th Chinese Con-trol and Decision Conference, China Chongqing,2017:7-13.
[14] YANG Yue-neng,YAN Ye.Backstepping Sliding Mode Control for Uncertain Strict-Feedback Nonlinear Systems Using Neural-Network-Based Adaptive Gain Scheduling[J].Journal of Systems Engineering and Electronics,2018,29(3):580-586.
[15] 郭建国,吴林旭,周军.非对称变翼飞行器复合控制系统设计[J].宇航学报,2018,39(1):52-59.
GUO Jian-guo,WU Lin-xu,ZHOU Jun.Compound Control System Design for Asymmetric Morphing-Wing Aircraft[J].Journal of Astronautics,2018,39(1):52-59.