论文部分内容阅读
提出了一种基于神经网络的迟滞非线性的补偿方法。首先构造一个Duhem逆算子来描述迟滞逆状态。然后利用神经网络来逼近此状态和输出之间的关系来得到神经网络迟滞逆模型,神经网络权值采用反馈误差学习方法来进行在线调整。系统的前馈控制器和反馈控制器分别为逆模型和PID控制器。该方法不需要建立迟滞的正模型,能够在线构造逆模型来实现迟滞补偿。最后通过仿真验证了该方法的有效性。
A nonlinear hysteresis compensation method based on neural network is proposed. First construct a Duhem inverse operator to describe the hysteretic inverse state. Then the neural network is used to approximate the relationship between this state and the output to get the inverse model of the neural network, and the weights of the neural network are adjusted online with feedback error learning method. The system feed-forward controller and feedback controller are inverse model and PID controller respectively. This method does not need to build a positive model of hysteresis and can construct the inverse model online to realize the hysteresis compensation. Finally, the effectiveness of this method is verified by simulation.