改进RBF网络学习算法在卫星姿态控制中的应用

An Improved Algorithm of RBF Neural Networks and Its Application in Attitude Control of Satellite

提出了一种基于神经网络扰动补偿的姿态控制方法。首先 ,针对RBF网络的常用学习算法———正交最小二乘 (OLS)算法 ,提出了改进的规范正交最小二乘 (ROLS)算法 ;然后 ,基于某型小卫星的姿态控制问题 ,设计了高精度定向阶段的神经网络补偿控制器。仿真结果表明 ,改进的ROLS算法是有效的 ,神经网络补偿控制方案是可行的。

This paper presents a control scheme based on NN disturbance compensation for attitude control of satellite. At first, we present an improved algorithm of RBF NN from the general algorithm, regulation orthogonal least square (ROLS). Then, base on the problem of attitude control of a satellite under development, we design a NN compensation controller for high accuracy orientation phase. The simulation results show that the improved algorithm is efficient and the NN compensation scheme is feasible.