摘要
针对飞行仿真转台系统的非线性问题 ,提出了基于模糊神经网络的自适应控制方法 ,并且提出了新的推理算法 ,该控制方法结合了神经网络和模糊推理的优点 ,可以更合理地选择初始权值 ,既可提高神经网络的学习过程又可在线寻优模糊规则 ,通过实验表明该控制方法可以明显提高控制系统的跟踪性能 ,并且具有很强的对外干扰和非线性因素的鲁棒性。
A digital tracking controller based on fuzzy-neural network for high precision flight simulator is presented. The article also proposes a new algorithm of the fuzzy-neural network. Since the proposed adaptive controler combines the advantage of neural network and fuzzy reasoning, it can not only reduce the time of neural network learning but also find the optimum rule of fuzzy reasoning. Experimental results demonstrate that the proposed controller can effectively improve tracking performance and has robustness against parameter uncertainty and external disturbance.
出处
《计算机仿真》
CSCD
2004年第1期47-49,115,共4页
Computer Simulation
基金
航空基础科学基金资助项目 (编号 :0 0E5 10 2 2 )
