基于RBF神经网络的全姿态磁航向误差建模与补偿

对磁罗盘系统误差和目前多数文献所提出的全姿态磁航向误差补偿方法的不足进行了分析.针对具有一定俯仰角或横滚角的磁罗盘系统磁航向误差建模和补偿问题,提出了基于径向基函数(RBF)神经网络的修正方法,并与BP神经网络方法进行了比较.在分析算法原理的基础上进行了实验仿真,结果表明:采用RBF神经网络在明显提高网络收敛速度的基础上,大大减小了全姿态磁航向误差,校正效果优于BP神经网络.

Modeling and Compensation of AH Attitude Magnetic Heading Error Based on RBF Neural Network

The magnetic compass system errors and the shortage of all attitude magnetic heading error compensation algorithms mentioned in many articles are analyzed.To model and compensate the magnetic heading error of the magnetic compass system which in a carrier with some pitch angle or roll angle,a new deviation compensation algorithm based on RBF(radial basis function) neural network is presented.A BP neural network has been developed to solve the same problem for comparison.The deviation compensation algorithm put forward here is analyzed in theory and the effect of this compensation algorithm is testified based on experimental results that the learning speed of this network can be sped up markedly and all attitude magnetic heading error can be greatly reduced.RBF neural network is quite effective and superior to BP neural network.