期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

非线性H_∞导弹纵向自动驾驶仪设计

Nonlinear Missile Longitudinal Autopilot Design with Neural Net
在线阅读 下载PDF
导出
摘要 状态相关黎卡提方程(SDRE)需要在每个采样点求解矩阵Riccati方程,计算成本非常高,不利于实时控制器的实现。将SDRE方法与鲁棒H∞方法相结合,针对导弹纵向自动驾驶仪设计SDREH∞控制器,利用一种多层回归神经网络结构来进行在线求解代数Riccati方程,从而获得控制器增益。神经网络学习方法采用常规梯度法。仿真结果表明导弹纵向跟踪控制性能好;神经网络在线求解代数Riccati方程有效降低计算成本,且利用硬件实现神经网络求解器。 The difficulty lies in the implementation of SDRE （State Dependent Riccati Equation） controller is computational cost on solving matrix Riccati Equation in each sample point. A SDRE H∞ controller is designed for missile longitudinal autopilot. A multilayer neural network scheme is used to solve algebraic Riccati equation, resulting from robust H∞ controller design. The simulation results reveal effectiveness of the tracking controllers and efficiency of neural--net scheme for solving Riccati equation. It is convenient to realizing a neural--net solver by hardware.
作者 赵党军 王永骥 谢富强 李传锋
机构地区 华中科技大学控制科学与工程系 武汉工程大学电气信息学院
出处 《计算技术与自动化》 2009年第4期5-8,共4页 Computing Technology and Automation
关键词 鲁棒H∞控制器 多层回归神经网 状态相关黎卡提方程 导弹纵向自动驾驶仪 robust H∞ controller multilayer recurrent neural network state dependent riccati equation missile longitudinal autopilot
分类号 V412 [航空宇航科学与技术—航空宇航推进理论与工程]
  • 相关文献

参考文献6

  • 1XIN M ,BALAKUISHNAN S N. State dependent Riecati equation based spacecraft attitude control[C]. Proceedings of 40 th AIAA Aerospace Sciences Meeting & Exhibit, Reno, NV, 23-25,January, 2002, (1) :2-3.
  • 2ANDREA BRACCI, MARIO INNOCENTI, LORENZO POLLINI. A new algorithm for implementation of SDRE controllers[C]. AIAA Guidance , Navigation, and control Conference and Exhibit, San Franciso, California,2005, (8):15-18.
  • 3MRACEK C P, CLOUTIER J R. State Dependent Riecati Equation Technique: Thero) and Applications[C]. American Control Conference, IEEE, workshops,1998,23(6),.
  • 4WANG J, WU G. A multilayer Neural Network for solving continuous-time Algebraic Riceati Equations [ J ] . IEEE trans. On Neural Networks,1998,(11) :930-950.
  • 5MRACEK C P, CLOUTIER J R. Missile Longitudinal autopilot design using the state dependent riceati method[J]. Proceedings of the First International Conference on Nonlinear Problems in Aviation and Aerospace, Daytona, Beaeh, FL, May, 1996.
  • 6张雨浓,张禹珩,陈轲,蔡炳煌,马伟木.线性矩阵方程的梯度法神经网络求解及其仿真验证[J].中山大学学报（自然科学版）,2008,47(3):26-32. 被引量：8

二级参考文献10

  • 1ZHANG Y, WANG J. Global exponential stability of recurrent neural networks for synthesizing linear feedback control systems via pole assignment [ J ]. IEEE Transactions on Neural Networks, 2002, 13(3) : 633 -644.
  • 2ZHANG Y, JIANG D, WANG J. A recurrent neural network for solving sylvester equation with time - varying coefficients [ J ]. IEEE Transactions on Neural Networks, 2002, 13(5): 1053-1063.
  • 3ZHANG Y. Towards piecewise - linear primal neural networks for optimization and redundant robotics [C]. Proceedings of IEEE International Conference on Networking, Sensing and Control 2006:374 -379.
  • 4LEITHEAD W E, ZHANG Y. O (N^2) - operation approximation of covariance matrix inverse in Gaussian Process regression based on quasi - Newton BFGS methods[J]. Communications in Statistics - Simulation and Computation, 2007, 36(2): 367-380.
  • 5ZHANG Y. Revisit the analog computer and gradient-based neural system for matrix inversion [ C ]. Proceedings of IEEE International symposium on Intelligent Control, 2005 : 1411 - 1416.
  • 6NEAGOE V E. Inversion of the Van der Monde matrix [J]. IEEE Signal Processing Letters, 1996, 3(4) : 119 - 120.
  • 7ZHANG Y, LEITHEAD W E, LEITH D J. Time - series Gaussian process regression based on Toeplitz computa- tion of O(N2) operations and O(N) - level storage [ C].Proceedings of the 44th IEEE Conference on Decision and Control, 2005 : 3711 - 3716.
  • 8WANG J. A recurrent neural network for real - time matrix inversion [ J ]. Applied Mathematics and Computation, 1993, 55 : 89 - 100.
  • 9ZHANG Y, GE S S. Design and analysis of a general recurrent neural network model for time - varying matrix inversion [ J ]. IEEE Transactions on Neural Networks, 2005, 16(6): 1477- 1490.
  • 10李晓东,杨国华.反馈神经网络对非线性时变离散系统的近似[J].中山大学学报（自然科学版）,2002,41(5):28-30. 被引量：2

共引文献7

计算技术与自动化
2009年 第4期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部