【摘要】 现代卫星的姿轨控制面临着挠性附件对本体姿态的耦合作用。本文将卫星太阳帆板挠性结构对本体姿态的影响增广进系统方程 ,在PID控制器控制刚体卫星的基础上 ,设计了模糊神经网络控制器 ,采用反向传播和最小方差估计的学习方法进行模糊规则的学习 ,仿真表明 ,模糊神经网络特有的学习和处理定性与定量知识的优点 ,将使卫星姿态在参数变化与外部干扰情况下具有较好的姿态稳定度与精度。更多还原

【Abstract】 The attitude control of a satellite is faced the challenge of flexural bodies coupled to the center body. This paper proposes a neuro-fuzzy approach to control the complicate dynamics. The flexural model of solar arrays is extended to the satellite attitude equation. To overcome the uncertainties of internal parameters and external disturbances, an adaptive neuro-fuzzy controller is applied to realize the attitude and orbit system (AOCS) control on the base of Proportional-Integral-Differential (PID) . To general optimize the learning error, a least square estimation method is combined with gradient decent learning in the train procedure. Simulation results show the neuro-fuzzy controllers have good performance to the impulse disturbance, fadeless vibration and the inertia parameters changes.更多还原