|
|
论文:2020,Vol:38,Issue(2):366-376 |
|
|
引用本文： |
|
|
张少康, 王超, 孙芹东. 基于多类别特征融合的水声目标噪声识别分类技术[J]. 西北工业大学学报 |
|
|
ZHANG Shaokang, WANG Chao, SUN Qindong. Underwater Target Noise Recognition and Classification Technology based on Multi-Classes Feature Fusion[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于多类别特征融合的水声目标噪声识别分类技术 |
|
| 张少康1,2,3, 王超1,2, 孙芹东1,2 |
|
1. 海军潜艇学院, 山东 青岛 266000;
2. 青岛海洋科学与技术试点国家实验室, 山东 青岛 266000;
3. 国防大学 联合作战学院, 河北 石家庄 050000 |
| 摘要: |
| 目标噪声信号作为当前水声目标识别的主要信号源之一，由于目标信号来源单一，难以像多传感器探测不同角度表征目标特性，导致目标识别分类正确率低、虚警率高，严重制约水声探测系统功能的发挥。针对这一问题，采用长短时记忆网络，建立多层LSTM水声目标噪声特征提取模型，学习提取目标噪声时域包络、DEMON线谱、梅尔倒谱系数等信息特征，构建多类别特征子集；在此基础之上，建立了基于多类别特征子集的特征级融合识别分类模型和基于D-S证据理论的决策级融合识别分类模型；利用样本库数据对上述模型进行了测试，对比多类别特征融合判别与单一类别特征识别分类的差异，并使用港池相关试验数据对上述模型进行了测试验证。测试结果表明，提出的基于多类别特征融合的水声目标噪声智能识别分类方法判别效果更好，对水声目标噪声信号识别分类的正确率和虚警率等相关指标均优于单一类别特征判别方法。 |
| 关键词:
水声目标识别
水声目标噪声
多类别特征融合
特征级融合
决策级融合
|
|
| Underwater Target Noise Recognition and Classification Technology based on Multi-Classes Feature Fusion |
|
| ZHANG Shaokang1,2,3, WANG Chao1,2, SUN Qindong1,2 |
|
1. Navy Submarine Academy, Qingdao 266000, China;
2. National Laboratory for Marine Science and Technology, Qingdao 266000, China;
3. Joint Operations College, National Defense University, Shijiazhuang 050000, China |
| Abstract: |
| As one of the main signal sources of underwater acoustic target recognition, the target noise signal is difficult to characterize the characteristics of the target from clearly comparing with the multi-sensor detection technology, which may lead to lower recognition rate and higher false alarm rate and seriously restricts the function of underwater acoustic detection system. In order to solve this problem, a multi-layers LSTM underwater acoustic target noise feature extraction model is established by using the long short term memory network. The information features such as time-domain envelope of target noise, Demon line spectrum and Mel frequency cepstrum coefficient are extracted, and a subset of multi-classes features is constructed. On this basis, the feature level fusion recognition and classification model based on the multi-classes features subset and the decision level fusion recognition and classification model based on the D-S evidence theory are established, and the above-mentioned models are tested by using the sample database. The difference of classification result between the multi-classes feature fusion and the single class feature recognition classification is compared, and the above model is tested and verified by using the relevant test data of port basin verification experiment. The correlation results show that the present intelligent recognition and classification method of underwater target noise based on the multi-classes feature fusion is more robust, and the recognition rate and false alarm rate of underwater target are better than those of single category feature discrimination method. |
| Key words:
underwater acoustic target recognition
underwater acoustic target noise
multi-class feature fusion
feature level fusion recognition method
decision level fusion recognition method
|
|
| 收稿日期: 2019-03-14
修回日期:
|
| DOI: 10.1051/jnwpu/20203820366 |
| 基金项目: 水中军用目标特性国防科技重点实验室基金（614240704040317）资助 |
| 通讯作者:
Email： |
| 作者简介: 张少康(1990-),国防大学讲师,主要从事海洋科学研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 张少康 在本刊中的所有文章 |
| 王超 在本刊中的所有文章 |
| 孙芹东 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 王逸林. 希尔伯特黄变换在矢量信号处理中的应用研究[D]. 哈尔滨:哈尔滨工程大学, 2006 WANG Yinlin. Research on the Application of Hilbert-Huang Transformation to Vector Signal Processing[D]. Harbin:Harbin Engineering University, 2006(in Chinese)
[2] 李秀坤, 谢磊, 秦宇. 应用希尔伯特黄变换的水下目标特征提取[J]. 哈尔滨工程大学学报, 2009, 30(5):542-546 LI Xiukun, XIE Lei, QIN Yu. Underwater Target Feature Extraction Using Hibert-Huang Transform[J]. Journal of Harbin Engineering University, 2009, 30(5):542-546(in Chinese)
[3] 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:哈尔滨工程大学, 2012 LI Xinxin. Research on Feature Extraction and Classification of Ship Noise and Whale Sound[D]. Harbin:Harbin Engineering University, 2012(in Chinese)
[4] 韩雪. 基于听觉特征的水中目标辐射噪声特征提取[D]. 哈尔滨:哈尔滨工程大学, 2013 HAN Xue. Feature Extraction of Underwater Target Based on Auditory Features[D]. Harbin:Harbin Engineering University, 2013(in Chinese)
[5] 石超雄, 李钢虎, 何会会, 等. 基于提升小波变换的MFCC在目标识别中的应用[J]. 声学技术, 2014, 33(4):372-375 SHI Chaoxiong, LI Ganghu, HE Huihui,et al. Application of the Lifting Wavelet Transform Based MFCC in Target Identification[J]. Technical Acoustics, 2014, 33(4):372-375(in Chinese)
[6] 程玉胜, 王易川, 史广智, 等. 基于现代信号处理技术的舰船噪声信号DEMON分析[J]. 声学技术, 2006, 25(1):276-281 CHENG Yusheng, WANG Yichuan, SHI Guangzhi, et al. DEMON Analysis of Underwater Target Radiation Noise Based on Modern Signal Processing[J]. Technical Acoustics, 2006, 25(1):276-281(in Chinese)
[7] 葛青. 水下目标识别中的数据融合技术[D]. 哈尔滨:哈尔滨工程大学, 2008 GE Qing. The Information Fusion in Underwater Target Recognition[D]. Harbin:Harbin Engineering University, 2008(in Chinese)
[8] 王杨. 水下目标辐射噪声多维特征分析技术[D]. 哈尔滨:哈尔滨工程大学, 2012 WANG Yang. Underwater Target Multidimensional Radiation Analysis of Characteristics of the Technology[D]. Harbin:Harbin Engineering University, 2012(in Chinese)
[9] 张大伟, 章新华, 付留芳, 等. 基于听觉感知与卷积神经网络识别舰船目标[J]. 声学技术, 2015, 34(6):181-184 ZHANG Dawei, ZHANG Xinhua, Fu Liufang, et al. Recognitiuon of Ships Based on Auditory Sense and Convolutional Neutral Methorks[J]. Technical Acoustics, 2015, 34(6):181-184(in Chinese)
[10] 卢安安. 基于深度学习方法的水下声音目标识别研究[D]. 哈尔滨:哈尔滨工程大学, 2017 LU Anan. Underwater Acoustic Classification Based on Deep Learning[D]. Harbin:Harbin Engineering University, 2017(in Chinese)
[11] VALDENEGRO-TORO M. Improving Sonar Image Patch Matching via Deep Learning[C]//2017 European Conference on Mobile Robots, Paris, 2017
[12] WILLIAMS D P. Underwater Target Classification in Synthetic Aperture Sonar Imagery Using Deep Convolutional Neural Networks[C]//International Conference on Pattern Recognition 2016, Mexico, 2016:2497-2502
[13] 王强,曾向阳. 深度学习方法及其在水下目标识别中的应用[J]. 声学技术, 2015, 34(2):138~140 WANG Qiang, ZENG Xiangyang. Deep Learning Methods and Their Applications in Underwater Targets in Recognization[J]. Technical Acoustics, 2015, 34(2):138-140(in Chinese)
[14] KAMAL S, MOHAMMED S K, PILLAI P R S, et al. Deep learning Architectures for Underwater Target Recognition[C]//Ocean Electronics, 2013:48-54
[15] 杨宏晖, 申昇, 姚晓辉,等. 用于水声目标特征学习与识别的混合正则化深度置信网络[J]. 西北工业大学学报, 2017, 35(2):220-225 YANG Honghui, SHEN Sheng, YAO Xiaohui, et al. Underwater Acoustic Target Feature Learning and Recognition Using Hybrid Regularization Deep Belief Network[J]. Journal of Northwestern Polytechnical University, 2017, 35(2):220-225(in Chinese)
[16] 陈越超, 徐晓男, 姚晓辉, 等. 基于降噪自编码的水中目标识别方法[J]. 声学与电子工程, 2018, 1:30-33 CHEN Yuechao, XU Xiaonan, YAO Xiaohui, et al. Underwater Target Recognition method based on Denoising Auto-Encoder[J]. Acoustics and Electronics Engineering, 2018, 1:30-33(in Chinese)
[17] 刘同明, 夏祖勋, 谢洪成. 数据融合技术及其应用[M]. 北京:国防工业出版社, 1998 LIU Tongming, XIA Zuxun, XIE Hongcheng. Technology and Application of Data Fusion Technicies[M]. Beijing:National Defense Industry Press, 1998(in Chinese)
[18] KLAUS Greff, RUPESH K, SRIVASTAVA, et al. LSTM:a Search Space Odyssey[J]. IEEE Trans on Neural Networks and Learning Systems, 2017, 28(10):2222-2232
[19] ALEX Graves. Learning Precise Timing with LSTM Recurrent Networks[J]. Journal of Machine Learning Research, 2002(3):115-143
[20] WOJCIECH Zaremba. Recurrent Neural Network Regularization[J/OL]. (2015-12-19)[2019-03-01]. https://arxir.org.pdf/1409.2329v5.pdf
[21] NITISH Srivastava, GEOFFREY Hinton, ALEX Krizhevsky, et al. Dropout:a Simple Way to Prevent Neural Networks from Overfitting[J]. Journal of Machine Learning Research, 2014(15):1929-1958
[22] 夏佩伦. 目标跟踪与信息融合[M]. 北京:国防工业出版社, 2010 XIA Peilun. Target Tracking and Information Fusion[M]. Beijing:National Defense Industry Press, 2010(in Chinese)
[23] PETER Flach. 机器学习[M]. 北京:人民邮电出版社, 2016 PETER Flach. Machine Learning[M]. Beijing:Posts & Telecom Press, 2016(in Chinese)
[24] 田坦, 刘国枝, 孙大军. 声纳技术[M]. 哈尔滨:哈尔滨工程大学出版社,1999 TIAN Tan, LIU Guozhi, SUN Dajun. Sonar Technology[M]. Harbin, Harbin Engineering University Press, 1999(in Chinese)
[25] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016 ZHOU Zhihua. Machine Learning[M]. Beijing:Tsinghua University Press, 2016(in Chinese) |
|
|
|
|
|
|
|
