文献类型：期刊文献

中文题名：基于分数阶滤波器的高泛化性神经网络建模

英文题名：High Generalization Neural Network Modeling Based on Fractional Order Filter

作者：刘加存[1];苑增福[2];梅其祥[3]

机构：[1]广东海洋大学电子与信息工程学院;[2]内蒙古根河林业局;[3]广东海洋大学数学与计算机学院

年份：2017

卷号：36

期号：12

起止页码：57

中文期刊名：测控技术

外文期刊名：Measurement & Control Technology

收录：CSTPCD、、CSCD_E2017_2018、CSCD

基金：国家自然科学基金资助项目(61272534)

语种：中文

中文关键词：神经网络;建模;泛化性;分数阶滤波器;盲动粒子群

外文关键词：neural network;modeling;generalization;fractional order filter;blindfold particle swarm

中文摘要：为了显著提高神经网络建模的泛化性,提出了激活函数是分数阶滤波器的神经网络。分数阶滤波器涵盖了Butterworth和Chebyshev滤波器的性能。滤波器集对样本信号进行频率分解,既提升了信息的致密性,也保证了遍历性,更有助于提高神经网络的泛化性。各滤波器参数由盲动粒子群优化算法寻优。神经网络解算时,既采用了线性回归求解神经网络输出层权重,又在有限频段上用线性传递函数模拟替代分数阶传递函数,这两种措施缩短了解算时间。仿真结果表明,线性系统的泛化性精度可达亿分之几,非线性系统可达万分之几,可以离线应用。

外文摘要：In order to improve the generalization of neural network modeling significantly, a neural network that activation function is fractional order filter is proposed. The fractional order filter coveres the properties of Butterworth and Chebyshev filters. Because the signal frequency of the sample is decomposed by the filter set, the information compactness is enhanced and the ergodicity is ensured, which helps to improve the generalization of neural network. The parameters of each filter are optimized by particle swarm optimization with blindfold feature. In order to save the computation time of the network, the linear regression algorithm is used to solve the output layer weight of the neural network, and the linear transfer function is used to replace the fractional order transfer function in the finite frequency band. The simulation results show that the generalization accuracy of the linear system is up to parts per hundred million, and the nonlinear system can be up to parts per ten thousands, so it can be used offline