Fast dynamic hysteresis modeling using a regularized online sequential extreme learning machine with forgetting property
Fast dynamic hysteresis modeling using a regularized online sequential extreme learning machine with forgetting property
复制标题
DOI：
10.1007/s00170-017-0549-x
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
Zelong Wu;Hui Tang;Sifeng He;Jian Gao;Xin Chen;S. To;Yangmin Li;Zhijun Yang
中科院分区：
文献类型：
--
作者：
Zelong Wu;Hui Tang;Sifeng He;Jian Gao;Xin Chen;S. To;Yangmin Li;Zhijun Yang
压电陶瓷（PZT）驱动器以其高分辨率在柔性导向微纳定位中得到了广泛的应用。然而，由于压电陶瓷作动器复杂的滞回非线性效应，实现高精度的定位控制相当困难。为此，提出了一种具有遗忘特性的在线RELM算法（FReOS-ELM）。首先，采用正则化极值学习机（RELM）建立智能滞后模型。该算法的训练只需一步完成，避免了传统基于人工神经网络（ANN）的迟滞模型训练速度慢、容易陷入局部极小的缺点。然后，在正则化在线顺序极限学习机（ReOS-ELM）的基础上，设计了一种具有遗忘特性的在线顺序极限学习机算法（FReOS-ELM），避免了ReOS-ELM在添加新数据进行在线学习过程中的计算负荷。在实验中，采用了实时的变频变幅电压信号，并对微纳定位台的输出位移数据进行了采集和分析。实验结果表明，与传统神经网络相比，基于relm的迟滞建模算法具有更高的效率和更稳定的学习能力和泛化能力。在在线建模方面，FReOS-ELM的迟滞建模效果优于ReOS-ELM。
Piezoelectric ceramics (PZT) actuator has been widely used in flexure-guided micro/nanopositioning stage because of their high resolution. However, it is quite hard to achieve high-rate precision positioning control because of the complex hysteresis nonlinearity effect of PZT actuator. Thus, an online RELM algorithm with forgetting property (FReOS-ELM) is proposed to handle this issue. Firstly, we adopt regularized extreme learning machine (RELM) to build an intelligent hysteresis model. The training of the algorithm is completed only in one step, which avoids the shortcomings of the traditional hysteresis model based on artificial neural network (ANN) that slow training speed and easy to fall into the local minimum. Then, based on the regularized online sequential extreme learning machine (ReOS-ELM), an online RELM algorithm with forgetting property (FReOS-ELM) is designed, which can avoid the computational load of ReOS-ELM in the process of adding new data for learning online. In the experiment, a real-time voltage signal with varying frequencies and amplitudes is adopted, and the output displacement data of the micro/nanopositioning stage is also acquired and analyzed. The experimental results show that the RELM-based hysteresis modeling algorithm has higher efficiency and more stable learning ability and generalization ability than the traditional neural network. In the aspect of online modeling, FReOS-ELM hysteresis modeling can achieve a better result than ReOS-ELM.