基于BP网络的船舶磁性目标定位方法研究

Research on ship magnetic target location method based on BP neural network

船舶磁性目标定位是海上目标定位系统中重要的方法之一,优点是部署简单、定位精度较高;缺点是定位算法复杂度较高、计算量大,算法较易陷入局部最优解,需要进行改进。神经网络是解决目标最优问题的有效求解手段,利用各神经元权值系数调整能够计算出磁性目标定位的全局最优解。本文研究船舶磁性目标定位的算法结构,针对目标函数,设计基于BP神经网络的定位算法,最后给出基于神经网络算法仿真结果,并与传统算法进行对比。

Ship magnetic target localization is the maritime target system is an important one of the method, has the advantages of simple deployment, high positioning accuracy; its localization algorithm has high complexity, large amount of calculation, and the algorithm of transaction into a local optimal solution needs to be improved. Neural network is an effective solution to the problem of target optimization, and the global optimal solution of magnetic target location can be calculated by adjusting the weights of neurons. This paper studies the ship structure algorithm of magnetic target positioning, target function, design a localization algorithm based on BP neural network, finally gives the simulation results of the neural network algorithm, and compared with the traditional algorithm.