基于LSSVM的卫星姿态控制系统故障诊断

LSSVM Based Fault Diagnosis for Satellite Attitude Control Systems

提出了一种基于最小二乘支持向量机(LSSVM)非线性观测器的卫星姿态控制系统故障诊断方法。与标准的支持向量机回归算法相比,最小二乘支持向量机回归算法收敛速度快,适用于在线训练。该方法利用其回归逼近非线性函数的能力,设计基于最小二乘支持向量机的非线性系统状态观测器,在线训练最小二乘支持向量机回归,并用于估计卫星姿态控制系统故障。最后,通过仿真验证了这种方法可以快速准确地估计出卫星姿态控制系统的故障。

A fault diagnosis method for satellite attitude control systems is presented based on least squares support vector machine （LSSVM）. Compared with standard support vector machines, LSSVM regressions can always converge rapidly. According to this character, an LSSVM based nonlinear observer is designed to estimate the satellite attitude control system faults, in which LSSVM regressions are on-line trained. The simulation results show the feasibility of the proposed algorithm.