舰船辐射噪声的非线性特征提取和识别

南京大学学报(自然科学版) ›› 2013, Vol. 49 ›› Issue (1): 64–71.

舰船辐射噪声的非线性特征提取和识别

曹红丽，方世良，罗听炜

出版日期:2015-09-25 发布日期:2015-09-25
作者简介: (东南大学水声信弓处理教育部重点实验室，南京，210096)
基金资助:
National Major Fundamental Research Program of China,National Natural Science Foundation of China
(11104029)

Nonlinear feature extraction and recognition of ship radiated noise*

Cao Hong一Li**,Fang Shi一Lang ,Luo Xin- Wei

Online:2015-09-25 Published:2015-09-25
About author: (Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education,
Southeast University,Nanjing 210096,China)

摘要/Abstract

摘要： 本文研究了一种集相空间重构的几何特征和盒数维为一体的计算复杂度较低的非线性特征
提取方案.首先利用基于统计学方法的C-C方法提取嵌入维和时延，根据舰船辐射噪声的嵌入维确定
维数范围，在维数范围内采用时延法进行相空间重构，将舰船辐射噪声时间序列扩展到高维空间，在高
维空间中计算时间子序列的相关系数，并从相关系数中寻找阂值范围提取具有区分性相似性重复度，将
相似性重复度进行升序重排画相似性重复度曲线，提取相似性重复度平均值这一几何特征，然后从盒子
维的数学分析出发研究盒子维数的简化工程计算模型，三类舰船辐射噪声的盒子维分布图验证盒子维
特征具有一定的区分性，最后设计后传播(BP)神经网络分类器,YP神经网络采用两层结构的批处理模
式.推导特征的类间距离和类内距离，并通过实际海上数据仿真，计算结果表明结合特征的类间距离较
大，类内距离较小，验证结合特征提取方法的有效性，三类目标的识别率表明该方法具有一定的水声目
标识别能力.

Abstract: The mechanism of ship radiated noise is correlated with dynamics system,and the analyzing algorithm of non-
linear time sequence is an effective approach to the signal generated by dynamics system based on the phase space recon-
struction technique. An effective and low-complexity nonlinear feature extraction algorithm is researched in the paper.The
embedded dimension and the time delay arc extracted through C一C method based on the statistical method,the embedded
dimension range of ship radiated noise is determined according to the embedded dimension,the phase space is reconstructed
in the range of embedded dimension,and the correlation coefficient is computed between the time subsequcnce in the high di-
mension space.Then the similar sequence repeatability is extracted from the correlation coefficient under the threshold con-
dition,and the similar sequence repeatability can differ with each other.The similar sequence repeatability is ascending sorted
and the curve of the similar sequence repeatability is depicted.The geometric characteristic of the mean of the similar repcat-
ability is extracted. And then the simple engineering computation model of box-dimension is proposed through its math-
erratic analysis,and the distribution graph of three kinds of ship radiated noise shows the distinguish ability of the box-di-
mension characteristic.ln the end,a back-propagation neural network classifier is designed,the structure of the classifier is
two-layer and the processing model is hatching model.The formulas of the distance between the classes and the innci-class
distance arc deduced,and the simulation result of sea trial data show bigger distance between classes and smaller inner-class
distance.The algorithm combines the geometric feature based on phase space reconstruction technique with box-dimension
fcature,and the results show the good recognition ability and prospective application of the proposed algorithm.

曹红丽，方世良，罗听炜
. 舰船辐射噪声的非线性特征提取和识别[J]. 南京大学学报(自然科学版), 2013, 49(1): 64–71.

Cao Hong一Li**,Fang Shi一Lang ,Luo Xin- Wei. Nonlinear feature extraction and recognition of ship radiated noise*[J]. Journal of Nanjing University(Natural Sciences), 2013, 49(1): 64–71.

参考文献

[1]Henry D l A. Chaos in ocean ambient noise. Jour-nal of the Acoustic Society of Amcrica, 1996，99 (3).1527-1539
[2]Theodore W F, Henry D l A. Nonlicar analysis of environment distortions wave signals in the
ocean. Journal of the Acoustic Society of America, 1996，99(1):139~146.
[3]Hang X H. Chaos in behavior of ship radiated noise. Acta Acusitca, 1999,23(2):134一140.
[4]Gao X,Lu J R. Fractal Brownian motion model of ship radiated noise. Acta Acusitca, 1999，24(1): 19一28.
[5]Chen X D,Gao X，Lu J H.Time domain charac- teristic study of ship radiated noise based on the
similar sequence repeatability. Journal of Southeast University,1998,28(6):17一23.
[6]Chen X D,Gao X,Lu J R.The study of nonlinear features of ship radiated noise based on phase
space reconstruction theory. Acta Acusitca,1999,24(1):12~18.
[7]Song A G,Lu J R. Nonlinear feature analysis and extraction of ship noise signal based on limit
cycle. Acta Acustica,1999,24(4):12一18.
[8]Yang S.Chaos and fractal signal processing and target identification research. Northweastern
Polytechnical University, 1999.
[9]Chen J，Chen K A，Sun J C. A new method for feature extraction in ship noise. Journal of North-
weastern Polytechnical University, 2000，18(2): 241~244.
[10]Passamante A, Bromely D, Farrell M E.Time series characterization using the repeatability of similar se-
quences. Physica D, 1996,96:100一109.
[11]Lv J H, Chen S H. Analysis and application of chaotic time series. Wuhan; Wuhan University Press,2005,57一66.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed