基于神经网络方法的水声信号预测  

Prediction of Underwater Acoustic Signal based on Neural Network

作　　者：吴岳松[1] 李亚安[1] 陈静[1] 

机构地区：[1]西北工业大学航海学院,西安710072

出　　处：《微处理机》2006年第3期47-48,51,共3页Microprocessors

摘　　要：由于海洋环境的复杂性和水声信道复杂的时变、空变特性,使得舰船辐射噪声是一种非平稳、非高斯过程。如能提前预测敌方舰船的辐射噪声,并有效地对敌进行水下对抗,先敌使用武器攻击,是克敌制胜的前提,也是我海军目前各型潜艇和水面舰艇急需解决的关键技术。文章根据水声信号的特点建立了预测模型和网络结构参数的设计。并分别采用BP神经网络和RBF神经网络对仿真信号和实际舰船水声信号进行预测。结果表明,利用神经网络预测水声信号达到了一定的效果,为今后进一步开展水声信号预测研究奠定了基础。The ship - radiated noise is non - stationary and non - Gaussian in the complex ocean environment due to the intricate time - varying and spare - varying of channel. Hence, how to detect the noise of enemy naval vessel has become an urgent problem to be solved in all types of submarines and naval vessels by Chinese navy. In this paper, a new method of underwater acoustic signal predicting with the help of neural network is promoted. This paper is also intended to discuss the establishment of calculating model and the design of network parameter as well. The BP network and the RBF network are applied to calculate the underwater acoustic signal of naval vessels. The study indicates that the underwater acoustics signal predicting with the help of neural network can achieve good results and lays a foundation for further investigations of underwater acoustics signal prediction.

关 键 词：水声信号 神经网络 预测 

分 类 号：TN911.7[电子电信—通信与信息系统]