【摘要】 电动舵机是个多变量、非线性、强耦合、时变的复杂系统,传统的PID等控制方法对其进行控制时存在精度低、抗干扰能力差等问题。为解决上述问题,本文设计了一种改进学习算法的补偿模糊神经网络(CFNN)控制器,在补偿模糊神经网络学习算法中加入自适应学习速率因子,使神经网络的学习速率根据当前的学习收敛速度做动态的调整,从而加快学习收敛速度,改善其控制性能。仿真结果表明,采用改进学习算法的补偿模糊神经网络控制的电动舵机系统响应更快,鲁棒性强、位置跟踪精度更高,其控制性能优于传统的PID控制与经典学习算法的补偿模糊神经网络控制。更多还原

【Abstract】 Electric steering gear is a multi- variable,nonlinear,strong coupling,time-varying complex system,there are some problems,such as low precision and poor anti- interference ability with the traditional PID control method to control.In order to solve the above problems,this paper designed an improved learning algorithm of compensation fuzzy neural network controller.An adaptive learning rate factor was added to compensation fuzzy neural network learning algorithm,which makes the learning rate of neural network can be adjusted dynamically according to current learning convergence rate,so as to accelerate the convergent speed and improve the control performance.The simulation results show that electric steering gear system adopted with the improved learning algorithm of compensation fuzzy neural network controller has faster response speed,stronger robustness and higher location tracking precision.更多还原