论文部分内容阅读
为了消除压电微定位平台的迟滞非线性特性,实现高精度定位控制,采用具有两个隐含层的BP神经网络建立压电微定位平台的迟滞模型,以精确描述驱动电压与输出位移的迟滞关系;设计一种基于BP神经网络迟滞逆模型的前馈控制器,对迟滞非线性进行补偿,将迟滞非线性近似线性化.为进一步提高定位系统的精度,提出基于迟滞逆模型前馈补偿和专家模糊控制的复合控制方法.仿真结果表明,该复合控制方法可以将压电微定位平台的定位误差控制在0.091μm以内,从而有效地消除迟滞非线性对压电微定位平台定位精度的影响.
In order to eliminate the hysteresis nonlinearity of piezoelectric micro-positioning platform and achieve high-precision positioning control, a hysteresis model of piezoelectric micro-positioning platform is established by using BP neural network with two hidden layers to accurately describe hysteresis of driving voltage and output displacement The feedforward controller based on the hysteretic inverse model of BP neural network is designed to compensate hysteresis nonlinearity and approximate hysteresis nonlinearity.In order to further improve the accuracy of the positioning system, a feedforward compensation based on hysteretic inverse model and Expert fuzzy control.The simulation results show that the composite control method can control the positioning error of piezoelectric micro-positioning platform within 0.091μm, so as to effectively eliminate the influence of hysteresis nonlinearity on the positioning accuracy of piezoelectric micro-positioning platform.