基于BP神经网络拟合的二次相关时延估计

Second Correlation Time Delay Estimation Based on BP Neural Network Fitting

在TDOA无源时差定位中,外界噪声对定位时延估值精度的影响很大.二次相关时延估计算法虽然具有良好的抗噪能力,但随着信噪比的降低,抗噪性也会下降.将BP神经网络引入二次相关时延估计,基于BP神经网络拟合二次相关时域函数曲线,以提升二次相关时延估计的准确度.仿真结果表明,基于BP神经网络拟合的二次相关时延估计算法在低信噪比条件下具有较高的时延估值精度.

In passive TDOA positioning,the external noise has a great influence on the positioning precision of positioning delay.The second correlation time delay estimation algorithm has good performance for noise suppression,but its anti noise performance declines as the signal to noise ratio(SNR)becomes lower.The BP neural network was introduced into the second correlation time delay estimation and the second correlation time domain function curve was fitted based on the BP neural network to improve the accuracy of second correlation time delay estimation.The simulation results show that the second correlation delay estimation algorithm based on BP neural network has high accuracy of time delay estimation under low SNR condition.