基于近邻参考集与E2LSH加速的姿态敏感器故障检测  

Real-Time Attitude Sensor Fault Detection Based on Nearest Neighbor Reference Set and E2LSH Acceleration

作　　者：王婵[1] 王慧泉[1] 金仲和[1] 杜超禹 

机构地区：[1]浙江大学微小卫星研究中心,杭州310027

出　　处：《传感技术学报》2017年第9期1359-1363,共5页Chinese Journal of Sensors and Actuators

摘　　要：为满足高维、多状态姿控敏感器遥测数据的实时故障检测,提出了一种基于局部敏感哈希和子空间异常因子的故障检测算法。算法通过局部敏感哈希索引的建立和使用,检测全局故障点;通过子空间异常因子的计算,检测子空间故障点。提出了近似邻近参考集与缓存桶的概念,降低算法的时间复杂度。ZDPS-2卫星的姿控敏感器数据分析结果表明,该方法故障查准率89.3%,查全率100%,且泛化性能优于原始的子空间异常程度算法。该算法解决了原始的子空间异常程度算法实时性低、检测全局故障困难问题,可以满足姿控敏感器实时故障检测需求。Fault detection for satellite attitude sensors are required to handle high-dimensionality telemetry data and to manipulate faults in real-time. A new method based on exact Euclidean locality-sensitive hashing and subspace outlier degree is proposed to satisfy aforementioned requirements. The algorithm detects the global abnormal points by establishing and using the exact Euclidean local sensitive hash index. The subspace abnormal points are detected after calculating the subspace outlier factor. This paper presents the new concepts of approximate reference points and cache bucket to reduce the time complexity. The analysis for ZDPS-2 satellite attitude sensor data shows that,the precision is 89.3% and the recall is 100%. In addition,the algorithm＇s generalization ability is superior to the original subspace outlier degree algorithm. The proposed method solves two problems of the original subspace outlier degree. It can satisfy the real-time and global abnormal points manipulation requirements of attitude sensors for the attitude control system.

关 键 词：姿态敏感器 故障检测 近邻参考集 局部敏感哈希 

分 类 号：V448.2[航空宇航科学与技术—飞行器设计]