航向数据混沌特性分析及预测  

Analysis and prediction for chaotic characteristics of course data

作　　者：黎才鑫 李天伟[1] 郭姣[2] 孟凡军[1] 

机构地区：[1]海军大连舰艇学院航海系,辽宁大连116018 [2]海军大连舰艇学院基础部,辽宁大连116018

出　　处：《现代电子技术》2014年第19期128-131,共4页Modern Electronics Technique

摘　　要：惯导系统输出航向数据具有混沌特性,应用混沌理论对其进行分析,采用C-C方法重构相空间,在此基础上分别通过定性与定量方式分析其混沌特性并计算最大Lyapunov指数。以相空间重构后的时间序列为变量输入,采用RBF神经网络预测航向数据,结果表明其预测精度优于未经相空间重构的直接预测法。Since the course data from INS features chaotic property,the chaos theory is applied to its analysis and C-C method is used for reconstructing the phase space of course data. Based on this,not only different methods are adopted to con-duct qualitative and quantitative analyses of chaos characteristics,but also its maximum Lyapunov exponent is calculated. Taking the time sequence after phase space reconstruction as variable input,RBF neural network is used to predict course data,the test result shows that its prediction accuracy is superior to that of the traditional RBF neural network without the phase space re-constructing.

关 键 词：航向数据 混沌特性分析 相空间重构 RBF神经网络 LYAPUNOV指数 

分 类 号：TN911.734[电子电信—通信与信息系统]