| 赵乾坤,刘峰,梁秀兵,汪涛,宋永强.基于时延神经网络模型的舰船辐射噪声目标识别*[J].,2023,42(5):1033-1041 |
| 基于时延神经网络模型的舰船辐射噪声目标识别* |
| Target recognition of ship radiated noise based on time delay neural network model |
| 投稿时间：2023-06-13 修订日期：2023-08-29 |
| 中文摘要: |
| 水声目标被动识别是水声信号处理领域的研究热点之一。海洋环境中存在的不规则噪声干扰,使得基于传统方法的水声目标被动识别技术在实际的应用场景中效果不佳。本文采用一种基于时延网络(Time Delay Neural Network,TDNN)模型的舰船辐射噪声目标识别方法,该方法利用目标的短时平稳特性和长时关联特性对目标的声纹特征进行建模,使用梅尔谱图提取目标信号的初级特征,再通过融合注意力机制和时延神经网络的深度学习模型实现高级特性提取,最后再利用余弦相似度实现不同目标的类别划分。该方法在ShipsEar数据集和自行采集的数据进行测试验证,目标识别准确率分别达到79.2%和73.9%,可证明本文方法的有效性。 |
| 英文摘要: |
| Passive recognition of underwater acoustic targets is one of the research hotspots in the field of underwater acoustic signal processing. The irregular noise interference in the marine environment makes the passive recognition technology of underwater acoustic targets based on traditional methods ineffective in practical application scenarios. This article adopts a ship radiated noise target recognition method based on the TDNN model. This method uses the short-term stationary and long-term correlation characteristics of the target to model the voiceprint features of the target. The Mel spectrum is used to extract the primary features of the target signal, and then advanced feature extraction is achieved through a deep learning model that integrates attention mechanism and time-delay neural network. Finally, cosine similarity is used to achieve classification of different targets. This method was tested and validated on the ShipsEar dataset and self collected data, and the target recognition accuracy reached 79.2% and 73.9%, respectively, demonstrating the effectiveness of the proposed method. |
| DOI：10.11684/j.issn.1000-310X.2023.05.017 |
| 中文关键词: 水声目标识别 舰船辐射噪声 时延神经网络 注意力机制 |
| 英文关键词: Underwater acoustic target recognition Ship radiated noise Time Delay Neural Network Attention mechanism |
| 基金项目:(62201608),国家自然科学基金项目（面上项目，重点项目，重大项目） |
|
| 摘要点击次数: 448 |
| 全文下载次数: 843 |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
