舰船噪声波形结构特征提取及分类研究

The Feature Extraction and Classification of Ocean Acoustic Signals Based on Wave Structure

本文系统深入地分析研究了舰船噪声信号的时域波形结构特征，利用舰船噪声信号的过零点、峰间幅值、波长差、波列面积分布以及时域特性提取技术，将原始舰船噪声信号时域波形分类信息表达成了11维的分类特征向量，同时设计了结构自适应模型聚类神经网络分类器，对提取的舰船噪声分类特征向量进行分类．训练样本集平均识别率达96．72％；测试样本集平均识别率达88．39％。

The method of the feature vector extraction of ocean acoustics signals based on the wave structure is presented. Then the structurally adaptive fuzzy-clustering neural network model is applied to design a new classifier for the ocean acoustics signals. The result shows that the presented method of feature vector extraction of ocean acoustics signals and the designed classifier are satisfactory.