基于AR模型和神经网络的舰船水压信号检测方法

为了有效地从风浪背景中检测舰船水压场信号，根据舰船水压场信号和波浪噪声信号的差异，以时间序列的AR模型理论为依据，采用基于AR模型和神经网络的舰船水压信号检测方法。该检测算法的核心是将检测问题转化为模式识别问题，首先对接收信号建立AR模型并提取AR模型系数作为特征向量，然后利用人工神经网络对信号进行检测。在此基础上，通过不同浪级情况下海浪水压力场的仿真信号数据，对某型目标舰船的水压力信号进行了检测计算，验证了该方法的有效性，尤其是达到了在高海况、低信噪比条件下，对目标信号检测率比较高、虚警率比较低的效果。

Hydraulic Pressure Signal Detection of Ship Under Wind Wave Background Based on AR Model and ANN

To effectively detect the ship hydrodynamic pressure signal from wind wave background,according to the characteristic difference between the ship hydrodynamic pressure signal and the wave noise,a target detection method is used on the AR model and the artificial neural network(ANN).The characteristic is extracted by the AR model coefficient and then be employed to detect the target signal with ANN.By using the method,it is possible to recognize whether target signal is involved or not in received signals.The method is verified by a real target signal with an additive simulated noise signal,especially under the condition of low SNR.