基于神经网络的Volterra频域核辨识方法  

Identifying of Volterra Frequency-Domain Kernels Based on Neural Network

作　　者：吴世浩 孟亚峰 王超[3] WU Shi-hao;MENG Ya-feng;WANG Chao(Shijiazhuang Campus,Army Engineering University,Shijiazhuang 050003,China;No.63850 Unit of PLA, Baieheng 137000,China;No.65735 Unit of PLA,Dandong 118000,China)

机构地区：[1]陆军工程大学石家庄校区 [2]中国人民解放军63850部队 [3]中国人民解放军65735部队

出　　处：《电光与控制》2019年第2期38-43,共6页Electronics Optics & Control

基　　金：国家自然科学基金(61372039)

摘　　要：针对目前Volterra频域核辨识方法复杂、精度不高等问题,提出一种基于神经网络的Volterra频域核辨识方法。首先选择多组频率基准确测量各阶Volterra频域核的幅值,利用BP神经网络可以任意逼近非线性函数的特点,针对不同阶Volterra频域核设计不同的神经网络模型,进行分阶辨识,最后通过一个非线性电路进行仿真验证。仿真结果表明,该方法可直接辨识频率范围内任意频率对应的Volterra频域核,过程简单、准确度高,易于工程实现。In order to solve the problem of high complexity and low accuracy of the current method for Volterra frequency-domain kernel identification, a method for Volterra frequency-domain kernel identification based on neural network is proposed. Firstly, the amplitude of each Volterra frequency-domain kernel is accurately measured after choosing multiple frequency components. Then, we use the characteristics of BP neural network that it can approximate nonlinear functions to design different models for different-order Volterra frequency-domain kernels, so as to identify each kernel. Finally, a nonlinear circuit is adopted for simulation. The results show that this method can directly identify all the Volterra frequency-domain kernels in the frequency range, and the process is simple with high accuracy, which is suitable for engineering realization.

关 键 词：VOLTERRA级数 非线性 频域核辨识 神经网络 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] TP206.3[自动化与计算机技术—检测技术与自动化装置]