电子电气工程与控制

状态预测神经网络控制应用于小型可回收火箭

  • 陈书钊 ,
  • 楚龙飞 ,
  • 杨秀梅 ,
  • 蔡德淮
展开
  • 1. 翎客航天科技有限公司, 北京 100176;
    2. 昆明理工大学 信息工程与自动化学院, 昆明 650500

收稿日期: 2018-05-07

  修回日期: 2018-07-09

  网络出版日期: 2018-10-31

Application of state prediction neural network control algorithm in small reusable rocket

  • CHEN Shuzhao ,
  • CHU Longfei ,
  • YANG Xiumei ,
  • CAI Dehuai
Expand
  • 1. LinkSpace Aerospace Technology Group, Beijing 100176, China;
    2. The Academic Institute of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China

Received date: 2018-05-07

  Revised date: 2018-07-09

  Online published: 2018-10-31

摘要

随着商业航天的到来,可重复使用运载器的研究受到广泛关注,以SpaceX为代表的商业航天公司研发的部分可回收火箭表现出了前所未有的竞争力。为了研发可回收火箭技术,翎客航天利用民间工业力量研制了RLV-T3小型可回收火箭验证机,并在该验证机上通过数百次试验逐渐掌握了垂直起降(VTVL)技术。主要介绍了翎客航天在VTVL技术中的一项动力控制技术,提出了状态预测神经网络控制(SPNNC)算法。该算法具有鲁棒性强、适用范围广、控制参数易调整等优点。详细地描述了该算法的原理,并通过Simulink对SISO和MIMO 2种系统进行了仿真。同时详细地论述了将状态预测神经网络控制算法应用于RLV-T3小型可回收火箭的飞行及回收的试验,包括RLV-T3小型可回收火箭的基本特点、控制难点、存在的问题,飞行过程中各物理量的曲线和试验结论。经试验验证,状态预测神经网络控制算法具有良好的控制性能,基于该控制技术,即状态预测神经网络控制算法的RLV-T3小型可回收火箭验证机可以安全地实现垂直起飞、弹道飞行、空中悬停、软着陆回收全流程。

本文引用格式

陈书钊 , 楚龙飞 , 杨秀梅 , 蔡德淮 . 状态预测神经网络控制应用于小型可回收火箭[J]. 航空学报, 2019 , 40(3) : 322286 -322286 . DOI: 10.7527/S1000-6893.2018.22286

Abstract

With the advent of commercial aerospace exploration, research on reusable vehicles has received extensive attention. Some reusable rockets developed by commercial space companies represented by SpaceX have exhibited unprecedented competitiveness. To develop reusable rocket technology, LinkSpace has developed a small verifying rocket called RLV-T3, and gradually mastered the Vertical Takeoff and Veratical Landing (VTVL) technology through hundreds of tests on this verification machine. This paper mainly introduces the State Prediction Neural Network Control (SPNNC) algorithm, a thrust control technique in VTVL technology. The algorithm has strong robustness, wide application range, and easy adjustment of control parameters. This paper describes the principle of the algorithm in detail and simulates both SISO and MIMO systems using Simulink. At the same time, this paper discusses in detail the test of the SPNNC applied to the RLV-T3, including the basic characteristics of the small reusable rocket, control difficulties, existing problems, the flight curve of the physical quantities, and test conclusions. It has been verified by experiments that the SPNNC has good control performance, and the small recyclable rocket verification machine named RLV-T3 based on SPNNC can safely implement the whole process of vertical takeoff, ballistic flight, air hovering, and soft landing recovery.

参考文献

[1] 汤一华, 余梦伦, 杨勇, 等. 第二代可重复使用运载器及其再入制导技术[J]. 导弹与航天运载技术, 2010(1):26-31. TANG Y H, YU M L, YANG Y, et al.Second generation reusable launch vehicle and its reentry guidance technologies[J]. Missiles and Space Vehicles, 2010(1):26-31(in Chinese).
[2] 王振国, 罗世彬, 吴建军. 可重复使用运载器研究进展[M]. 长沙:国防科技大学出版社, 2004:1-20. WANG Z G, LUO S B, WU J J. Researchprogress of reusable launch vehicles[M]. Changsha:National University of Defense Technology Press, 2004:1-20(in Chinese).
[3] 冯韶伟, 马忠辉, 吴义田, 等. 国外运载火箭可重复使用关键技术综述[J]. 导弹与航天运载技术, 2014(5):82-86. FENG S W, MA Z H, WU Y T, et al. Survey and review on key technologies of reusable launch vehicle abroad[J]. Missiles and Space Vehicles, 2014(5):82-86(in Chinese).
[4] 徐大富, 张哲, 吴克, 等. 垂直起降重复使用运载火箭发展趋势与关键技术研究进展[J]. 科学通报, 2016, 61(32):3453-3463. XU D F, ZHANG Z, WU K, et al. Research progress on the development trend and key technologies of reusable launch vehicles for VTVL[J]. Chinese Science Bulletin, 2016, 61(32):3453-3463(in Chinese).
[5] BLACKMORE L. Autonomous precision landing of space rockets[J]. The Bridge, 2016, 4(46):15-20.
[6] SCHARF D P, REGEHR M W, VAUGHAN G M, et al. ADAPT demonstrations of onboard large-divert guidance with a VTVL rocket[C]//2014 IEEE Aerospace Conference. Piscataway, NJ:IEEE Press, 2014:1-18.
[7] LU P. Entry guidance and trajectory control for reusable launch vehicle[J]. Journal of Guidance, Control, and Dynamics, 1997, 20(1):143-149.
[8] TSUCHIYA T, MORI T. Optimal conceptual design of two-stage reusable rocket vehicles including trajectory optimization[J]. Journal of Spacecraft and Rockets, 2004, 41(5):770-778.
[9] 柯芳, 涅乌希宾. 飞行器智能控制系统研究进展[J]. 兵工学报, 2010, 31(7):939-949. KE F, NEI W X B. Researchprogress of intelligent control systems of aerocrafts[J]. Acta Armamentarii, 2010, 31(7):939-949(in Chinese).
[10] 李少远, 席裕庚, 陈增强, 等. 智能控制的新进展(I)[J]. 控制与决策, 2000, 15(1):6-12. LI S Y, XI Y G, CHEN Z Q, et al. Thenew progress in intelligent control (I)[J]. Journal of Control and Decision, 2000, 15(1):6-12(in Chinese).
[11] 王永骥, 涂健. 神经元网络控制[M]. 北京:机械工业出版社, 1998:1-3 WANG Y J, TU J. Neuralnetwork control[M]. Beijing:China Machine Press, 1998:1-3(in Chinese).
[12] 王宁, 涂健, 陈锦江. 自适应神经元网络的智能控制[C]//中国自动化学会控制理论及其应用年会. 沈阳:中国科学院沈阳自动化研究所, 1992:235-239. WANG N, TU J, CHEN J J. Intelligentcontrol of adaptive neuron networks[C]//Conference of Control Theory and Applications of CAA. Shenyang:Shenyang Institute of Automation, Chinese Academy of Sciences, 1992:235-239(in Chinese).
[13] 张建明, 王宁. 自适应单神经元控制器的研究[J]. 自动化仪表, 1998(12):4-9. ZHANG J M, WANG N. Studying onself-adaptive single neuron controller[J]. Process Automation Instrumentation, 1998(12):4-9(in Chinese).
[14] RICHARD C D, ROBERT H B. 现代控制系统[M]. 第八版. 谢红卫, 等译. 北京:高等教育出版社, 2015:103-105. RICHARD C D, ROBERT H B. Modern control system[M]. 8th ed. XIE H W, et al, translated. Beijing:Higher Education Press, 2015:103-105(in Chinese).
[15] 王晓哲, 李界家, 吴成东, 等. 多变量系统解耦方法综述[J]. 沈阳建筑大学学报(自然科学版), 2000, 16(2):143-145. WANG X Z, LI J J,WU C D, et al. A summary of multivariable decoupling methods[J]. Journal of Shenyang Jianzhu University (Natural Science), 2000, 16(2):143-145(in Chinese).
[16] 马平, 杨金芳, 崔长春, 等. 解耦控制的现状及发展[J]. 控制工程, 2005, 12(2):97-100. MA P, YANG J F, CUI C C, et al. Current situation and development of decoupling control[J]. Control Engineering of China, 2005, 12(2):97-100(in Chinese).
[17] 戴先中, 张兴华, 刘国海, 等. 感应电机的神经网络逆系统线性化解耦控制[J]. 中国电机工程学报, 2004, 24(1):112-117. DAI X Z, ZHANG X H, LIU G H, et al. Decoupling control of induction motors based on neural network inverse[J]. Proceedings of the CSEE, 2004, 24(1):112-117(in Chinese).
[18] 吴智铭, 许晓鸣, 王伟. 多变量控制系统频域分析和设计的综述[J]. 控制理论与应用, 1986(2):8-18. WU Z M, XU X M, WANG W. Areview of frequency domain analysis and design for multivariable control systems[J]. Control Theory & Applications, 1986(2):8-18(in Chinese).
[19] THAM M T. Multivariable control:An introduction to decoupling control[D]. Newcastle Upon Tyne:University of Newcastle Upon Tyne, 1984.
[20] 陈雪波, 李树生. 多变量系统稳定性分析[J]. 自动化学报, 1987, 13(5):388-392. CHEN X B, LI S S. Stabilityanalysis of multivariable systems[J]. Acta Automatica Sinica, 1987, 13(5):388-392(in Chinese).
[21] 贾杰, 刘连章, 曹琦. 导弹解耦控制方法综述[J]. 航空兵器, 2010(3):18-21. JIA J, LIU L Z, CAO Q. Survey on decoupling control methods for missile[J]. Aero Weaponry, 2010(3):18-21(in Chinese).
[22] 欧阳小平, 李锋, 朱莹, 等. 重载航空负载模拟器非线性最优前馈补偿控制[J]. 航空学报, 2016, 37(2):669-679. OUYANG X P, LI F, ZHU Y, et al.Nonlinear optimal feedforward compensation controller for heavy load aviation load simulator[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(2):669-679(in Chinese).
文章导航

/