基于BP神经网络和多元Taylor级数的混合定位算法

针对多元Taylor级数算法定位精度严重依赖初始值的问题,提出一种新的混合定位算法。通过BP神经网络定位算法提供初始值,提高多元Taylor级数展开法的收敛速度;通过多元Taylor级数展开法,充分利用未知节点之间的距离信息,减小测距误差造成的定位误差。仿真结果表明:混合定位算法的精度更高,并且减少了网格间距对定位精度的影响。

Hybrid localization algorithm based on BP neural network and multivariable Taylor series

The positioning accuracy of the multivariable Taylor series algorithm depended heavily on the initial values, so a novel hybrid localization algorithm was proposed. The initial values offered by back-bropagation(BP) neural network algorithm could improve the convergence speed of multivariable Taylor series expansion method, and the multivariable Taylor series expansion method could reduce the position error caused by distance measurement error through making full use of the distance information of the unknown nodes. Experimental results indicated that the algorithm could improve positioning accuracy and reduced the influence of mesh spacing on location accuracy.