基于多尺度排列熵的舰船辐射噪声复杂度特征提取研究

针对复杂海洋环境中舰船辐射噪声的特征提取问题,提出了一种基于多尺度排列熵的舰船辐射噪声复杂度特征提取方法。分别利用基于EEMD的最强固有模态中心频率法、高低频能量差法和基于复杂度的排列熵与多尺度排列熵提取了五种不同类别、一定样本数量的舰船辐射噪声特征,并将四种特征提取方法所提取的舰船特征分别输入概率神经网络进行分类识别。研究发现,多尺度排列熵是一种一致性好、稳定性强的非线性特征参数,能够从多个维度描述信号的复杂度。实验结果表明,多尺度排列熵特征具有很好的可分性,以多尺度排列熵为特征进行舰船分类识别,识别率显著高于其他舰船辐射噪声特征提取算法.

A study on complexity feature extraction of ship radiated signals based on a multi-scale permutation entropy method

In order to solve the problem of feature extraction of ship radiated signals in complex ocean environment, a multi-scale permutation entropy method based the complexity feature extraction method for ship radiated signals was proposed.Firstly, the center frequency of intrinsic mode function with the highest energy, the energy difference between high and low frequency, permutation entropy and multi-scale permutation entropy were respectively used to extracted features of five types of ship radiated signals.Then the extracted ship features by four kinds of methods were respectively sent into a probability neural network for identification.The study discovers that multi-scale permutation entropy is a powerful nonlinear characteristic because it has good consistency and stability and is able to describe a signal over multiple scales.The results indicate that the multi-scale permutation entropy method has a good separability.The identification accuracy is obvious higher than other ship radiated noise feature extraction methods when using multi-scale permutation entropy as the feature.