基于LS-SVM的超磁致伸缩致动器数据驱动建模方法研究

针对超磁致伸缩材料(GMM)的强非线性特征，提出了一种新的超磁致伸缩驱动器(GMA)实验系统及其数据驱动建模方法.实验中的测量数据取自光栅传感器，采用数据驱动原理，基于最小二乘支持向量机(LS-SVM)实现了GMA的非线性建模.对模型性能进行了实验评估，预测了GMM棒的动态特性，并讨论了驱动电压对输出特性的影响.实验结果显示，该模型能较好地预测GMA的制动输出，预测误差在0.05%以内.

Research on data-driven modeling method of giant magnetostrictive actuator based on LS-SVM

Aiming at the strong nonlinear characteristics of Giant Magnetostrictive Material (GMM)， a new experimental system of Giant Magnetostrictive Actuator (GMA) and its data-driven modeling method are proposed. The measured data in the experiment were taken from grating sensors， and the nonlinear modeling of GMA was realized based on the Least Squares Support Vector Machine (LS-SVM) using the data-driven principle. The performance of the model is evaluated experimentally， the dynamic characteristics of the GMM rod are predicted， and the influence of driving voltage on the output characteristics is also discussed. The experimental results show that the model can predict the braking output of GMA well， and the prediction error is within 0.05%.