空间非合作目标惯性参数的Adaline网络辨识方法
收稿日期: 2015-09-07
修回日期: 2015-09-30
网络出版日期: 2016-01-06
基金资助
国家自然科学基金（51375034，61327809）；上海航天科技创新基金（SAST2015-075）
Adaline network-based identification method of inertial parameters for space uncooperative targets
Received date: 2015-09-07
Revised date: 2015-09-30
Online published: 2016-01-06
Supported by
National Natural Science Foundation of China (51375034,61327809); Shanghai Aerospace Science and Technology Innovation Fundation (SAST2015-075)
空间在轨操作中，航天器在对空间非合作目标的抓捕行动常常导致航天器本体的姿态和空间轨迹发生变化。为克服空间非合作目标对航天器本体动力学、运动学的影响，使控制系统做出精准及时的姿控策略调整，确保航天器正常在轨工作和轨迹姿态的高精度，需对抓捕的非合作目标的惯性参数进行辨识。针对传统辨识方法依赖广义逆求解导致的辨识过程运算量大，且数值容易产生剧烈振荡，造成辨识结果不稳定等不足，采用基于归一化最小均方（NLMS）准则的Adaline神经网络方法进行空间非合作目标惯性参数的辨识。首先，基于动量守恒理论建立抓捕后的航天器—机械臂—空间非合作目标系统模型；然后将辨识方程的系数矩阵作为网络的输入和输出，空间非合作目标的惯性参数作为神经网络的训练权重，基于迭代步长可变的NLMS准则实现对目标惯量参数的快速、准确辨识；最后，在构造的ADAMS/MATLAB联合仿真平台上进行了验证。仿真结果表明，基于NLMS准则的Adaline神经网络是一种快速、准确辨识目标惯量参数的有效方法。
孙俊 , 张世杰 , 马也 , 楚中毅 . 空间非合作目标惯性参数的Adaline网络辨识方法[J]. 航空学报, 2016 , 37(9) : 2799 -2808 . DOI: 10.7527/S1000-6893.2015.0349
During the operation in space, the spacecraft's attitude and trajectory are often affected by capturing the uncooperative target. In order to overcome the influence of uncooperative target on the dynamics and kinematics of spacecraft and ensure the high-precision attitude control strategy to be made and normal in-orbit condition, a process of identifying the inertial parameters of uncooperative targets should be accommodated. In order to avoid a large amount of computation induced by generalized inverse operation of traditional method in the identification process, which also causes severe vibration and unstability to numerical results, an Adaline neural network identification method based on normalized least mean square(NLMS) criterion is adopted. First of all, a system model composed of spacecraft, manipulator and uncooperative target is established based on the theory of momentum conservation. Then the weight parameters of the neural network representing the inertial parameters of uncooperative target are trained by the coefficient matrix of the identification equation as the input and output of the neural network via algorithm of NLMS with variable iterative step, and a fast and accurate process of identification is achieved. Finally, an ADAMS/MATLAB co-simulation platform is established, on which the proposed identification method is verified. The simulation results show that the Adaline neural network based on NLMS criterion is a fast and accurate method for identifying the target's inertia parameters.
Key words： spacecraft; uncooperative target; inertial parameter; neural network; identification
[1] 崔乃刚, 王平, 郭继峰, 等. 空间在轨服务技术发展综述[J]. 宇航学报, 2007, 28(4): 805-811. CUI N G, WANG P, GUO J F, et al. A review of on-orbit servicing[J]. Journal of Astronautics, 2007, 28(4): 805-811 (in Chinese).
[2] 蔡洪亮, 高永明, 邴启军, 等. 国外空间非合作目标抓捕系统研究现状与关键技术分析[J]. 装备指挥技术学院学报, 2010, 21(6): 71-77. CAI H L, GAO Y M, BING Q J, et al. The research status and key technology analysis of foreign non-cooperative target in space capture system[J]. Journal of the Academy of Equipment Command & Technology, 2010, 21(6): 71-77 (in Chinese).
[3] STEVEN D, EVANGELOS P. The kinematics dynamics, and control of free-flying and free-floating space robotic systems[J]. IEEE Transactions on Robotics and Automation, 1993, 9(5): 531-543.
[4] 卢伟, 耿云海, 陈雪芹, 等. 在轨服务航天器对目标的相对位置和姿态耦合控制[J]. 航空学报, 2011, 32(5): 857-865. LU W, GENG Y H, CHEN X Q, et al. Coupled control of relative position and attitude for on-orbit servicing spacecraft with respect to target[J]. Acta Aeronautica et Astronautica Sinica, 2011, 32(5): 857-865 (in Chinese).
[5] YOSHISADA M, KEI S, MITSUHIRO O. Parameter identification of unknown object handled by free-flying space robot[J]. Journal of Guidance, Control, and Dynamics, 1994, 17(3): 488-494.
[6] ROBERTO L, GERHARD H. Modeling and experimental design for the on-orbit inertial parameter identification of free-flying space robots[C]//International Design Engineering Technical Conferences and Computersand Information in Engineering Conference, 2005: 1-10.
[7] THAI CHAU N H, INNA S. Adaptive reactionless motion and parameter identification[J]. Journal of Guidance, Control, and Dynamics, 2013, 36(2): 404-414.
[8] 郭琦, 洪炳镕. 双臂四自由度空间机器人捕捉未知目标的参数辨识[J]. 机器人, 2005, 27(6): 512-516. GUO Q, HONG B R. Parameter identification of unknown object handled by a dual-arm four-degree-of-freedom space robot[J]. Robot, 2005, 27(6): 512-516 (in Chinese).
[9] 田富洋, 吴洪涛, 赵大旭, 等. 在轨空间机器人参数辨识研究[J]. 中国空间科学技术, 2010(1): 10-17. TIAN F Y, WU H T, ZHAO D X, et al. Parameter identification of orbital free-floating space robot[J]. Chinese Space Science and Technology, 2010(1): 10-17 (in Chinese).
[10] 金磊, 徐世杰. 空间机器人抓取未知目标的质量特性参数辨识[J]. 宇航学报, 2012, 33(11): 1570-1576. JIN L, XU S J. Inertial parameter identification of unknown object captured by a space robot[J]. Journal of Astronautics, 2012, 33(11): 1570-1576 (in Chinese).
[11] 张鹏. 基于触觉的空间非合作目标惯性参数辨识研究[D]. 哈尔滨: 哈尔滨工业大学, 2013. ZHANG P. Research on identification of inertial parameters of non-cooperative target with touch[D]. Harbin: Harbin Institute of Technology, 2013 (in Chinese).
[12] 王明, 黄攀峰, 常海涛. 非合作目标航天器质量特性参数辨识[J]. 飞行力学, 2014, 32(6): 536-540. WANG M, HUANG P F, CHANG H T. Identification of mass characteristic parameters for non-cooperative target spacecraft[J]. Flight Dynamics, 2014, 32(6): 536-540 (in Chinese).
[13] 吴倩. 空间非合作目标惯性参数辨识研究[D]. 哈尔滨:哈尔滨工业大学, 2014: 1-21. WU Q. Research on identification of inertial parameters of non-cooperative target[D]. Harbin: Harbin Institute of Technology,2014: 1-21 (in Chinese).
[14] 耿妍, 张端金. 自适应滤波算法综述[J].信息与电子工程, 2008, 6(4): 315-320. GENG Y, ZHANG D J. Survey of adaptive filtering algorithms[J]. Information and Electronic Engineering, 2008, 6(4): 315-320 (in Chinese).
[15] 陈恩伟, 刘正士, 干方建. 机器人末端臂惯性参数辨识的人工神经网络方法[J]. 中国机械工程, 2006, 17(3): 268-271. CHEN E W, LIU Z S, GAN F J. Application of ANN method in inertial parameter identification of the end effector of robot[J]. Chinese Journal of Mechanical Engineering, 2006, 17(3): 268-271 (in Chinese).
[16] SARITA N, MILAN B, DASH P K. Estimation of time varying signal parameters using an improved Adaline learning algorithm[J]. International Journal of Electronics and Communications, 2014, 68(2): 115-129.
[17] MOHAMMED Q, PARAG K, VINOD K. Artificial-neural-network-based phase-locking scheme for active power filters[J]. IEEE Transactions on Industrial Electronics, 2014, 61(8): 3857-3866.
[18] HAMID S, ALI B, DJAFFAR O A, et al. ADALINE approach for induction motor mechanical parameters identification[J]. Mathematics and Computers in Simulation, 2013, 90: 86-97.
[19] WIDROW B, LEHR M A. 30 years of adaptive neural networks perception, madaline, and back propagation [J]. Proceedings of the IEEE, 1990, 78(9): 1415-1442.
[20] 金万敏, 万坤华. 机器人动力学建模[J]. 东南大学学报, 1993, 23(A06): 19-26. JIN W M, WAN K H. The dynamic modeling in robots[J]. Journal of Southeast University, 1993, 23(A06): 19-26 (in Chinese).
[21] 李宁. LMS自适应滤波算法的收敛性能研究与应用 [D]. 哈尔滨: 哈尔滨工程大学, 2009. LI N. Convergence performance analysis and applications of the adaptive least mean square(LMS) algorithm[D]. Harbin: Harbin Engineering University, 2009 (in Chinese).
[22] Basic ADAMS full simulation training guide. Version12.0[EB/OL]. [2015-09-01]. http//www.adams.com.
/
| 〈 |
|
〉 |
CJA