论文部分内容阅读
针对三自由度直升机系统自身MIMO、较高阶次、非线性的特性,提出一种自适应模糊神经网络控制方法。首先运用牛顿-欧拉方程进行了机理模型的构建,利用线性二次型调节器得到控制系统的输出数据,该数据作为训练数据,将神经网络引入到模糊输入信号和模糊权值,应用自适应模糊神经网络推理系统设计控制器。通过Matlab对控制系统进行仿真,得到的仿真曲线与线性二次型调节器控制的仿真曲线作对比。结果显示:控制系统在论文提出的控制算法比LQR控制下能够更快地反馈控制信号,缩短了响应时间,其自主学习能力增加了系统在线控制的稳定性。
Aimed at the self-MIMO of higher-order three-DOF helicopter system and its higher-order and nonlinear characteristics, an adaptive fuzzy neural network control method is proposed. First of all, using the Newton-Euler equation to construct the mechanism model, the linear quadratic regulator is used to obtain the output data of the control system. The data is used as the training data to introduce the neural network into the fuzzy input signal and the fuzzy weight. Fuzzy Neural Network Inference System Design Controller. The control system is simulated by Matlab, and the simulation curve obtained is compared with the simulation curve controlled by linear quadratic regulator. The results show that the control system proposed in this paper can feedback the control signal faster than the LQR control, shortening the response time and increasing the stability of on-line control.