基于神经网络的迟滞非线性补偿控制

Non-linear Compensation Control of Hysteresis Based on Neural Networks

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 neural networks based method is proposed to compensate the effect of the hysteresis nonlinearity.Firstly,an inverse Duhem operator is presented to describe the inverse hysteretic state.Then the neural networks can be employed to approximate the relation between the inverse hysteretic state and the output of the inverse hysteresis.The weights of neural networks are adjusted on-line by feedback error learning method.The feed-forward controller and feedback controller are selected as the proposed inverse hys...