【摘要】 通过传感器获得的水下声场信号含有复杂多样的噪声信号,从收集的信号中提取有用的信号,是盲源信号分离的研究重点。本文针对自然梯度算法在盲源信号分离中的收敛速度慢,误差精度低等问题,利用步长自适应进行改进,通过实验对比结果可以看出,本文所改进的算法收敛速度快,提高了系统的性能,算法简单,推广性强。更多还原

【Abstract】 The underwater acoustic field signal obtained by the sensor has a complex and varied noise signal,which is the key point of blind source separation to extract useful signal from the collected signal. In this paper,the convergence rate of the natural gradient algorithm for blind source separation was slow. And the error accuracy was low. So the step size adaptation was used to improve the algorithm,By comparing the experimental results,we could see that the improved algorithm had fast convergence speed,improved the performance of the system,simpler algorithm,and stronger promotion.更多还原