面向故障诊断的航天器遥测数据降维分析技术  

The Dimension Reduction Analysis of Spacecraft's Telemetry Data for Fault Diagnosis

作　　者：柴敏[1,2] 杨悦[3] 徐小辉[2] 王敏[1,2] 杨小燕[2] 

机构地区：[1]宇航动力学国家重点实验室,西安710043 [2]西安卫星测控中心,西安710043 [3]四川大学软件学院,成都610065

出　　处：《弹箭与制导学报》2014年第1期150-153,共4页Journal of Projectiles,Rockets,Missiles and Guidance

基　　金：国家自然科学基金(11026224;61074077)资助

摘　　要：遥测数据反映了航天器有效载荷的状态和航天器的运行情况,基于遥测数据的航天器故障检测具有广泛的工程实用性。针对航天器遥测数据中含有大量冗余信息的实际情况,文中采用主成分分析理论,对高维遥测数据进行降维处理,在保证原始数据信息损失较小的情况下,从初始高维数据集合中提取低维特征组合,并在此基础上设计了航天器故障定位检测算法。仿真结果表明,文中算法在在轨航天器故障诊断中具有实用性和有效性。Telemetry data reflects the spacecraft payload＇ s operational state and the spacecraft＇s operating condition, telemetry data-driven fault detection of spacecraft has great practicability. Considering that a large amount of redundant information contained in the spacecraft te- lemetry data, principal component analysis（PCA） was adopted to deal with high-dimension telemetry data＇ s dimension reduction in this paper and low-dimensional feature combination was extracted from the initial high-dimensional data set combination. Then an algorithm for spacecraft fault detection and loctation was given. Finally, the validity and practicability of the algorithms were sbowed by simu]ation.

关 键 词：航天器 主成分分析 故障检测 

分 类 号：V557[航空宇航科学与技术—人机与环境工程]