摘要
针对三自由度直升机飞行控制问题,设计了一种模糊神经网络模型参考自适应逆控制方案。首先利用神经网络结构实现辨识器和控制器模糊推理过程,采用神经网络的连接权重来表示模糊推理的参数;然后利用反向传播算法修正网络连接权重,达到自动辨识模糊模型和调整隶属函数及参数的目的,从而使调整后的自适应逆控制器控制的实际系统输出跟踪上参考模型的输出。最后,基于该方案对三自由度直升机模型进行仿真实验,结果验证了此方法的有效性和可行性。
With reference to flight control problem occurred in 3-DOF helicopter system,Fuzzy neural network model reference adaptive inverse control scheme was designed. First,fuzzy inference process of identifier and controller was achieved by the network structure. The parameters of fuzzy inference were represented by neural network connection weights. Then,that using the back-propagation algorithm amend the network connection weights in order to automati- cally identify the fuzzy models and to adjust its membership functions and parameters. Then the actual system output which adjusted adaptive inverse controller can track the reference model output. Finally,the simulation result of 3- DOF helicopter system based on the scheme shows that the method was effectiveness and feasibility.
出处
《自动化与仪表》
北大核心
2014年第1期11-14,33,共5页
Automation & Instrumentation
基金
中央高校基本科研业务费中国民航大学专项资助项目(ZXH2010C002)
关键词
直升机
模糊神经网络
自适应逆控制
隶属函数
helicopter
fuzzy neural network （FNN）
adaptive inverse control
membership function
