空间控制技术与应用2018，Vol.44Issue(2)：42-48,7.DOI:10.3969/j.issn.1674-1579.2018.02.008
基于近邻保持嵌入的卫星姿态控制系统微小故障检测
Incipient Fault Detection Method of Satellite Attitude Control System Based on Neighborhood Preserving Embedding
摘要
Abstract
In this paper, an advanced neighborhood preserving embedding method combined with expo-nentially weighted moving average(EWMA-DNPE)is proposed in incipient fault detection for satellite's attitude control system(ACS).Considering the artificial set of neighborhood parameters in neighborhood preserving embedding(NPE)algorithm, the dynamic neighborhood selection is introduced, so that the weights reconstruction matrix can be selected according to the sample density of the manifold.On the ba-sis of this,the EWMA-DNPE algorithm is used to establish the squared prediction error(SPE)statistic in fault detection(FD)by exponentially weighted moving average(EWMA).The case study on a simu-lated satellite ACS demonstrates the effectiveness and feasibility of the proposed method.关键词
卫星姿态控制系统/微小故障检测/近邻保持嵌入/近邻参数Key words
attitude control system/incipient fault detection/neighborhood preserving embedding/neighborhood parameters分类
航空航天引用本文复制引用
刘敏,陆宁云,肇刚,姜斌..基于近邻保持嵌入的卫星姿态控制系统微小故障检测[J].空间控制技术与应用,2018,44(2):42-48,7.基金项目
航天器在轨故障诊断与维修重点实验室基金和装备预研国防科技重点实验室基金(61422080307).Supported by Key Laboratory of Spacecraft In-Orbit Fault Diagnosis and Maintenance Foundation and Equipment Pre-Research Key Laboratory of National Defense Science and Technology Foundation under Grant(61422080307). （61422080307）
