CAJ | 학술논문

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。
선박수압장신호총시엄몰재대량적해랑잡파중,위료유효지종배경간우중검측선박수압장신호,문장적해랑수압장근사복종정태분포적특성,재대접수도적해랑수압장신호진행AR건모적기출상,제취모형적자회귀계수작위특정향량,채용BP신경망락진행신호검측。통과방진수거대해검측방법진행험증,결과표명해방법간단이차역우실현,재저신조비조건하,야능구체도교고적검측솔。
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.