计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (34): 5-7.

• 博士论坛 • 上一篇    下一篇

时滞不确定飞行系统神经网络非脆弱H控制

赵振宇1,2,卢广山1   

  1. 1.西北工业大学 电子信息学院,西安 710072
    2.光电控制技术重点实验室,河南 洛阳 471009
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-12-01 发布日期:2011-12-01

Neural network non-fragile H control for time delay uncertain flight system

ZHAO Zhenyu1,2,LU Guangshan1   

  1. 1.School of Electronics and Information,Northwestern Polytechnical University,Xi’an 471009,China
    2.Key Laboratory of Optical-Electrics Control Technology,Luoyang,Henan 471009,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-12-01 Published:2011-12-01

摘要: 针对具有参数摄动和状态时延的时滞不确定飞行系统,提出了一种神经网络非脆弱H控制方案。该方案将鲁棒H控制和神经网络控制结合起来,利用径向基神经网络的非线性逼近能力,对飞行系统的非线性不确定项进行逼近。由线性矩阵不等式(LMI)设计系统标称部分的鲁棒控制器,然后利用神经网络的输出来消除系统控制输入中的不确定部分。Lyapunov稳定性分析中,综合考虑了系统参数摄动、时延和神经网络逼近误差的影响,并证明了在所设计的飞行控制器作用下,闭环系统的稳定性。仿真实例验证了提出的飞行控制方案的可行性和有效性。

关键词: 飞行控制, 神经网络, 时滞, 非脆弱控制, H控制

Abstract: The neural network non-fragile Hcontrol scheme is presented for time-varying uncertain flight systems with parameter perturbation and state time delay.This flight control scheme combines the robust H controller with neural network controller.The Radial Basis Function Neural Network(RBFNN) is adopted to approximate the nonlinear uncertain term of the flight system.The robust controller is designed using Linear Matrix Inequality(LMI) for the nominal linear flight system.And then,the uncertain nonlinear input term is compensated using the neural network.The stability analysis has been given for considering the effects of the parameter perturbation,the time delay and the neural network weight via the Lyapunov analysis.The closed-loop system stability has been proved under the proposed flight control scheme.Simulation results illustrate that the flight control scheme is effective.

Key words: flight control, neural network, time delay, non-fragile control, H control