一种基于非线性特征提取的被动声纳目标识别方法研究

目标噪声特征提取是被动声纳目标识别系统的关键技术。首先提出了一种利用从噪声极限环中提取的非线性特征来分析舰船噪声信号的新方法,然后采用基于自适应遗传BP算法的神经网络对提取的特征进行分类。实验结果表明,该系统具有较好的分类效果。

Research on Passive Sonar Target Classification Based On Nonlinear Feature Analysis

Feature extraction and the target classifier are the important compositions of underwater target recognition system.In this paper,a effective signal processing method-nonlinear feature analysis based on ship noise limit cycleis given,and then a neural network target classifier of adaptive real-coded genetic-back propagation algorithm is used to classify.The result of experiment shows that the method this paper provide not only gives a novel effective method for feature extraction of ship noise signals,but a...