文章摘要
卢佳敏,宋三明,景严,张瑶,谷浪,鲁帆,胡志强,李硕.基于DEMON谱和LSTM网络的水下运动目标噪声基频检测*[J].,2021,40(5):745-753
基于DEMON谱和LSTM网络的水下运动目标噪声基频检测*
Fundamental Frequency Detection of Underwater Target Noises Using DEMON Spectrum and LSTM Network
投稿时间:2021-03-12  修订日期:2021-06-20
中文摘要:
      传统的船舶辐射噪声基频检测方法不仅依赖大量的先验知识,而且对背景噪声非常敏感。为了提高目标识别的稳定性和精确性,本文提出了一种基于深度神经网络的基频检测算法。首先从多通道水听器信号中提取DEMON谱,然后直接将二维谱特征矩阵输入由CNN和LSTM构成的级联网络,最后通过稠密层输出实现对基频的估计。从仿真和外场试验数据得到如下结论:(1)深度网络能够实现无先验知识和不同信噪比条件下的基频检测,具有良好的泛化性能。(2)LSTM网络能够高效地从时序DEMON谱中提取统计特征,提高基频估计精度。(3)输入信号的时间长短会影响网络的检测精度,更长时间的信号能够获得更好的检测结果。
英文摘要:
      The traditional fundamental frequency(F0) detection methods not only rely on prior knowledge, but also are very sensitive to ambient noises. In this paper, a fundamental frequency detection algorithm based on deep neural network is proposed to improve the stability and accuracy of target recognition. The DEMON spectrum matrix, which is composed of spectral vector extracted from each single hydrophone signal, is directly fed into the cascaded network made up of CNN and LSTM networks. Then, with the one-hot vector from the final dense layer, the fundamental frequency is estimated. The following conclusions can be drawn from computer simulation and field experiments: (1) The deep learning-based method works well when no prior knowledge is assumed or SNR varies, having good generalization performance. (2) LSTM network can effectively extract the statistical characteristics from the DEMON spectrum sequence and improve the accuracy of the F0 estimation. (3) The detection precision depends on the input signal length, and a better detection result could be obtained when a longer signal is available.
DOI:10.11684/j.issn.1000-310X.2021.05.013
中文关键词: 基频,深度网络,长短时记忆网络,卷积神经网络,水听器阵列,水下目标噪声
英文关键词: fundamental frequency detection  deep learning  DEMON spectrum, LSTM, hydrophone array, underwater target noises.
基金项目:国家自然科学基金项目(61973297) 、中国科学院先导专项子课题(XDC03060105)、中国科学院青年创新促进会课题(2020209)和机器人学国家重点实验室课题(2017-Z010
作者单位E-mail
卢佳敏 中国科学院沈阳自动化研究所 lujiamin@sia.cn 
宋三明* 中国科学院沈阳自动化研究所 songsanming@sia.cn 
景严 中国科学院沈阳自动化研究所 jingyan@sia.cn 
张瑶 中国科学院沈阳自动化研究所 zhangyao@sia.cn 
谷浪 中国科学院沈阳自动化研究所 gulang@sia.cn 
鲁帆 中国科学院声学研究所 lufan@mail.ioa.ac.cn 
胡志强 中国科学院沈阳自动化研究所 hzq@sia.cn 
李硕 中国科学院沈阳自动化研究所 shuoli@sia.cn 
摘要点击次数: 811
全文下载次数: 1046
查看全文   查看/发表评论  下载PDF阅读器
关闭