基于RBF神经网络的泰勒级数展开定位算法

泰勒序列展开定位算法在视距（LOS）环境下有着较好的定位精度,但是在非视距（NLOS）环境下,泰勒序列展开定位算法的定位精度大大下降。为了减小NLOS传播的影响,提出了基于RBF神经网络的泰勒序列展开定位算法。利用神经网络较快的学习特性和逼近任意非线性映射的能力,对NLOS传播的误差进行修正,再利用泰勒序列展开定位算法进行定位。仿真结果表明,该算法减小了NLOS传播的影响,在NLOS环境下有较高的定位精度,性能优于泰勒序列展开定位算法、Chan算法和LS算法。

Taylor-series expansion location algorithm based on RBF neural network

In Line-Of-Sight（LOS） environment，Taylor-series expansion location algorithm has goodish location accuracy.But in Non-Line-Of-Sight（NLOS） environment，location accuracy of Taylor’s algorithm degrades greatly.In order to mitigate the effect of NLOS propagation，a Taylor -series expansion location algorithm based on the RBF neural network is proposed.The fast study and non-linear approach capacity of the neural network is made use of to correct the error of NLOS propagation，then position is calculated by Taylor’s algorithm.The simulation results indicate that the effect of NLOS propagation is mitigated by Taylor’s algorithm based on the RBF neural network.Its location accuracy is significantly improved and the performance of this algorithm is better than that of Taylor’s algorithm，Chan’s algorithm and LS’s algorithm in NLOS environment.