舰船噪声的状态空间重构与特征压缩  

State Space Reconstruction and Feature Reduction of Ship Noise

作　　者：余秋星[1] 李志舜[1] 符新伟[1] 

机构地区：[1]西北工业大学航海工程学院,22陕西西安710072

出　　处：《系统仿真学报》2003年第8期1079-1080,共2页Journal of System Simulation

摘　　要：介绍了以Takens的嵌入定理为基础的状态空间重构混沌信号处理方法,为了降低特征维数、减小特征成分的相关性、突出特征的差异性,同时引入了K-L(Karhunen-Loeve)变换。利用舰船噪声信号的混沌特性,提出了一种基于状态空间重构与K-L变换相结合的特征提取方法,并用此方法对舰船噪声信号进行特征压缩。计算机仿真结果表明该方法具有较好的分类效果。In this paper, the method of chaotic signal processing based on embedding theorem proposed by Takens is illuminated, and K-L (Karhunen-Loeve) transform is introduced to reduce the feature dimensions, decrease the correlation of feature components and increase their difference. Based on the technique of state space reconstruction and K-L transform, a novel method of extracting and reducing the features from ship noise is proposed. The experimental results obtained by using real data show that the method is effective.

关 键 词：状态空间重构 K-L变换 特征提取 舰船噪声 

分 类 号：TN911[电子电信—通信与信息系统]