基于GPU的海底混响信号快速仿真方法研究

Research on the reverberation signal fast simulation method based on GPU

在计算海底混响信号时,根据混响产生的物理机理,以射线声学为基础,用Lambert散射定律计算海底反向散射强度,采用单元散射模型建立海底混响信号模型。利用GPU相比于CPU具有更高的浮点运算能力和内存带宽的特点,采用GPU进行计算海底混响信号。通过对仿真混响信号的处理分析,在散射点较少时,混响信号包络更接近于K分布,而随着散射点的增多,混响信号的包络接近于瑞利分布。符合混响信号的一般统计特性。该方法能快速仿真出混响信号,达到高效的目的,为以后混响信号的实时演示验证提供一条可供选择的途径。

According to the physical process of reverberation and the theory of ray acoustics, calculation of sea bottom back scattering intensity with Lambert scattering law is carried out and a model of reverberation signal model is set up by using the cell scattering model. Because GPU has a higher floating-point computing performance and memory bandwidth compared to CPU, fast calculation of the reverberation signal simulate is achieved by using GPU. The results show that the envelope of the reverberation signal is more close to the K distribution with few scatter points and it is close to the Rayleigh distribution with the increase of scattered points which is accord with general statistical characteristics of reverberation signal.