X-Y定位平台自适应神经网络的摩擦补偿控制

发布时间：2018-06-12 01:22

  本文选题：神经网络 + X-Y定位平台　； 参考：《机械设计与制造》2015年12期

【摘要】：针对X-Y定位平台中摩擦等非线性部分对控制精度的影响问题,提出了基于自适应神经网络的鲁棒控制策略。设计神经网络控制器对摩擦及干扰等不确定部分进行补偿,其网络逼近误差作为外界扰动通过鲁棒控制器消除,保证X-Y平台的定位精度;设计神经网络参数学习算法,保证权值的在线自适应实时调整。基于H∞的HJI理论证明了控制系统的稳定性,并保证了系统L2增益小于给定的指标。试验结果表明所提控制方法能够很好补偿摩擦模型,提高了定位精度,具有重要工程应用价值。
[Abstract]:A robust control strategy based on adaptive neural network is proposed to solve the problem of the influence of nonlinear parts such as friction on the control accuracy of X-Y positioning platform. The neural network controller is designed to compensate the uncertain parts such as friction and disturbance. The network approximation error is eliminated by the robust controller as the external disturbance to ensure the location accuracy of X-Y platform, and the neural network parameter learning algorithm is designed. Online adaptive real-time adjustment of weights is guaranteed. The HJI theory based on H 鈭，

本文编号：2007599