论文部分内容阅读
在三级倒立摆(TIP)系统中, 应用神经网络与模糊控制相结合的自适应神经模糊推理系统(adaptive neural-fuzzy inference system), 根据样本数据调整隶属函数和控制规则参数, 使得训练后ANFIS控制器很好地模拟期望的输入输出数据. 仿真结果表明所设计的ANFIS控制器对三级倒立摆系统的稳定控制是可行的. 与LQR控制相比, 基于ANFIS控制的倒立摆系统具有良好的动态性能和抗干扰性能.
In the three-stage inverted pendulum (TIP) system, an adaptive neural-fuzzy inference system based on neural network and fuzzy control is applied to adjust the membership functions and control rule parameters according to the sample data so that the trained ANFIS The controller well simulates the expected input and output data.The simulation results show that the designed ANFIS controller is feasible for the stable control of the three-stage inverted pendulum system.Compared with the LQR control, the inverted pendulum system based on ANFIS control has good Dynamic performance and anti-jamming performance.