Volterra级数模型辨识算法的改进研究  

The improving study of the Volterra identification algorithm

作　　者：吴立勋[1] Wu Lixun(Department of Avionics and Weapons Engineering,Army Aviation Institute,Beijing,101123)

机构地区：[1]陆军航空兵学院航电和兵器工程系,北京101123

出　　处：《电子测试》2022年第3期101-103,共3页Electronic Test

摘　　要：本文研究了Volterra级数模型全解耦辨识算法,提出Volterra级数模型并行辨识算法的设计思想,设计了并行算法。实验和仿真结果表明,该算法能有效减小模型的在线辨识时间,能有效克服Volterra级数模型辨识中的维数灾难问题,且收敛速度快、稳态精度高,有利于实现工程应用。According to the study of the fully decoupled Volterra identification algorithm,it is firstly put forward that the design idea of the fully decoupled Volterra parallel identification algorithm.A parallel algorithm is designed.Belong to the emulation result,the algorithm of the models,can efficiently hurdle the problem of catastrophic dimension in the course of the Volterra series identification.The speed of its convergence is fast,the stability precision is very high,and then it is more utilizable.

关 键 词：Volterra级数模型 辨识算法 并行算法 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]