基于BP神经网络的船舶水压场信号检测

船舶水压场信号总是淹没在大量的海浪杂波中,为了有效地从背景干扰中检测船舶水压场信号,文章籍海浪水压场近似服从正态分布的特性,在对接收到的海浪水压场信号进行AR建模的基础上,提取模型的自回归系数作为特征向量,采用BP神经网络进行信号检测。通过仿真数据对该检测方法进行验证,结果表明该方法简单而且易于实现,在低信噪比条件下,也能够达到较高的检测率。

Ship Hydrodynamic Pressure Field Signal Detection Based on BP Neural Network

In order to effectively detect ship hydrodynamic pressure field signal,which is always submerged in the ocean wave,firstly,an autoregressive model prewhitening filter has been proposed based on the normal distribution characteristic shown by the wave hydrodynamic pressure field signal.Then the coefficient of model taken as the characteristic vetctor into Back-Propagation Network to detecte the target signal.Lastly,the effectiveness of the method is verified by the numerical simulation,the computed result shows that this method is easy realized and by means of this method,it is possible to recognize whether target signal is involved or not in received signal,especially in the high sea state and low signal to noise ratio conditions.