基于VMD和改进CNN的舰船辐射噪声识别方法

倪俊帅1,2,胡长青1,赵梅1

振动与冲击 ›› 2023, Vol. 42 ›› Issue (5) : 74-82.

PDF(3060 KB)
PDF(3060 KB)
振动与冲击 ›› 2023, Vol. 42 ›› Issue (5) : 74-82.
论文

基于VMD和改进CNN的舰船辐射噪声识别方法

  • 倪俊帅1,2,胡长青1,赵梅1
作者信息 +

Recognition method of ship radiated noise based on VMD and improved CNN

  • NI Junshuai1,2, HU Changqing1, ZHAO Mei1
Author information +
文章历史 +

摘要

针对海上低信噪比舰船目标的识别问题,对传统卷积神经网络进行改进并与变分模态分解相结合,提出了基于VMD和改进CNN的舰船辐射噪声识别方法。应用所提方法对东海试验中12艘辐射噪声信噪比低于5dB的舰船目标进行了识别,平均正确率为98.6%;相比于其他7种识别方法,分别提升了24.8%、17.0%、15.1%、8.0%、13.1%、16.8%、5.2%;改进卷积网络较传统卷积网络在运算量和识别速率方面有明显优势。

Abstract

Aiming at the problem of ship target recognition at sea with low signal-to-noise ratio, the traditional convolutional neural network is improved and combined with variational modal decomposition, a ship radiated noise recognition method based on Variational Modal Decomposition(VMD) and improved Convolutional Neural Network(CNN) is proposed. The proposed method is applied to identify 12 ship targets with radiated noise signal-to-noise ratio lower than 5dB in the East China Sea experiment, and the average accuracy is 98.6%; Compared with the other 7 recognition methods, it increased by 24.8%, 17.0%, 15.1%, 8.0%, 13.1%, 16.8% and 5.2% respectively; Compared with the traditional convolution network, the improved convolution network has obvious advantages in computation and recognition rate.

关键词

舰船辐射噪声 / 变分模态分解 / 卷积神经网络 / 识别

引用本文

导出引用
倪俊帅1,2,胡长青1,赵梅1. 基于VMD和改进CNN的舰船辐射噪声识别方法[J]. 振动与冲击, 2023, 42(5): 74-82
NI Junshuai1,2, HU Changqing1, ZHAO Mei1. Recognition method of ship radiated noise based on VMD and improved CNN[J]. Journal of Vibration and Shock, 2023, 42(5): 74-82

参考文献

[1] 李新欣. 船舶及鲸类声信号特征提取和分类识别研究[D]. 哈尔滨工程大学, 2013.
LI Xinxin. Research on feature extraction, classification and recognition of ship and whale acoustic signals [D]. Harbin Engineering University, 2013.
[2] 杨宏,李亚安,李国辉.基于集合经验模态分解的舰船辐射噪声能量分析[J].振动与冲击,2015,34(16):55-59.
YANG Hong, LI Ya'an, LI Guohui. Energy analysis of ship radiated noise based on ensemble empirical mode decomposition [J]. Vibration and shock, 2015,34 (16): 55-59
[3] Wang J, Chen Z. Feature Extraction of Ship-Radiated Noise Based on Intrinsic Time-Scale Decomposition and a Statistical Complexity Measure[J]. Entropy, 2019, 21(11):1079.
[4] 李余兴,李亚安,陈晓,蔚婧.基于VMD和中心频率的舰船辐射噪声特征提取方法研究[J].振动与冲击,2018,37(23):213-218+285.
LI Yuxing, LI Ya'an, CHEN Xiao, et al. Research on feature extraction method of ship radiated noise based on VMD and center frequency [J]. Vibration and shock, 2018,37 (23): 213-218 + 285
[5] Xie D, Esmaiel H, Sun H, et al. Feature Extraction of Ship-Radiated Noise Based on Enhanced Variational Mode Decomposition, Normalized Correlation Coefficient and Permutation Entropy[J]. Entropy, 2020, 22(468).
[6] 李余兴,李亚安,陈晓,等.基于VMD和SVM的舰船辐射噪声特征提取及分类识别[J].国防科技大学学报,2019,41(01):89-94.
LI Yuxing, LI Ya'an, CHEN Xiao, et al. Feature extraction and classification of ship radiated noise based on VMD and SVM [J]. Journal of National University of defense technology, 2019,41 (01): 89-94
[7] 李余兴, 李亚安, 陈晓. 基于EEMD的舰船辐射噪声特征提取方法研究[J]. 振动与冲击, 2017, 36(5):6.
LI Yuxing, LI Ya'an, CHEN Xiao. Research on feature extraction method of ship radiated noise based on EEMD [J].  Vibration and shock, 2017, 36 (5): 6
[8] Azulay A, Weiss Y. Why do deep convolutional networks generalize so poorly to small image transformations?[J].  2018.
[9] 王小宇, 李凡, 曹琳, 等. 改进的卷积神经网络实现端到端的水下目标自动识别[J]. 信号处理, 2020, 36(6):8.
WANG Xiaoyu, LI Fan, CAO Lin, et al. Improved convolutional neural network to realize end-to-end automatic underwater target recognition [J]. Signal processing, 2020, 36 (6): 8
[10] Li J, Yang H. The underwater acoustic target timbre perception and recognition based on the auditory inspired deep convolutional neural network[J]. Applied Acoustics, 2021, 182(107005):108210.
[11] Wang X, Liu A , Zhang Y , et al. Underwater Acoustic Target Recognition: A Combination of Multi-Dimensional Fusion Features and Modified Deep Neural Network[J]. Remote Sensing, 2019, 11(16):1888-.
[12] Shen S , Yang H, Yao X , et al. Ship Type Classification by Convolutional Neural Networks with Auditory-Like Mechanisms[J]. Sensors (Basel, Switzerland), 2020, 20(1).
[13] 黄擎,曾向阳.小波分解和改进 CNN 相融合的水声目标识别方法[J/OL].哈尔滨工程大学学报.
HUANG Qing, ZENG Xiangyang. Underwater acoustic target recognition method based on wavelet decomposition and improved CNN [J/OL]. Journal of Harbin Engineering University.
[14] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017
[15] Hoang V, Hoang V, Jo K. Realtime Multi-Person Pose Estimation with RCNN and Depthwise Separable Convolution[C]. 2020 RIVF International Conference on Computing and Communication Technologies (RIVF), Ho Chi Minh City, Vietnam, 2020: 1-5.
[16] Bousbai K, Merah M. A Comparative Study of Hand Gestures Recognition Based on MobileNetV2 and ConvNet Models[C]. 2019 6th International Conference on Image and Signal Processing and their Applications (ISPA), Mostaganem, Algeria, 2019:1-6
[17] Xiaoquan, Fei, Yuan, et al. Underwater Acoustic Target Recognition Based on Supervised Feature-Separation Algorithm.[J]. Sensors (Basel, Switzerland), 2018.
[18] Thakkar V, Tewary S, Chakraborty C. Batch Normalization in Convolutional Neural Networks — A comparative study with CIFAR-10 data[C]. 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT), Kolkata, India, 2018:1-5.
[19] Zhang C L , Luo J H , Wei X S, et al. In Defense of Fully Connected Layers in Visual Representation Transfer[C]// Pacific Rim Conference on Multimedia. Springer, Cham, 2017.
[20] Lin M, Chen Q, Yan S. Network In Network[J]. Computer Science, 2013.
[21] 杨路飞、章新华、吴秉坤、李兰瑞. 基于MFCC特征的被动水声目标深度学习分类方法[J]. 舰船科学技术, 2020, 42(10):5.
YANG Lufei, ZHANG Xinhua, WU Bingkun, et al. Depth learning classification method of passive underwater acoustic targets based on MFCC features [J]. Ship science and technology, 2020, 42 (10): 5.
[22] 严韶光, 康春玉, 夏志军,等. 基于深度自编码网络的舰船辐射噪声分类识别[J]. 舰船科学技术, 2019(3):7.
YAN Shaoguang, KANG Chunyu, XIA Zhijun, et al Classification and recognition of ship radiated noise based on depth self coding network [J]. Ship science and technology, 2019 (3): 7.
[23] 刘许, 宋阳. 多特征融合的舰船目标分类研究[J]. 舰船科学技术, 2016(14):3.
LIU Xu, SONG Yang. Research on ship target classification based on multi feature fusion [J]. Ship science and technology, 2016 (14): 3.

PDF(3060 KB)

Accesses

Citation

Detail

段落导航
相关文章

/