全文下载:2012030315
赵彤, 翟亚伟, 禹小姣
(青岛科技大学 自动化与电子工程学院,山东 青岛 266042)
摘要: 利用Backlash描述函数的实部和虚部构造一个函数,将其进行叠加,从而建立了一个新颖的迟滞非线性模型。以所建模型的输出作为神经网络的输入信号之一,建立了一个神经网络迟滞模型。实验结果验证了所提模型的有效性。
关键词: Backlash描述函数; 迟滞非线性; 神经网络
中图分类号: N 93; TP 13文献标志码: A
Neural Network Hysteresis Model Based on the Describing Function of Backlash
ZHAO Tong, ZHAI Ya-wei, YU Xiao-jiao
(College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266042, China)
Abstract:Using the real part and imaginary part of the describing function of backlash, a mathematical formula is constructed. Superimposing on a certain number of the formulas, we establish a novel hysteresis nonlinear model. Applying the output of the model as one of the neural network input signal, we create a neural network hysteresis model. The simulation results verify the effectiveness and feasibility of the method.
Key words: Backlash describing function; hysteresis nonlinearity; neural networks
收稿日期:2011-12-24
基金项目: 山东省自然科学基金资助项目(Y2007G06).
作者简介: 赵彤(1966—),男,教授.