Anomaly detection for satellite power subsystem with associated rules based on Kernel Principal Component Analysis

被引：55

作者：

Pan, Dawei ^{[1
]}

Liu, Datong ^{[2
]}

Zhou, Jun ^{[3
]}

Zhang, Guoyong ^{[3
]}

机构：

[1] Harbin Engn Univ, Coll Informat & Commun Engn, Harbin 150001, Peoples R China

[2] Harbin Inst Technol, Dept Automat Test & Control, Harbin 150080, Peoples R China

[3] Shanghai Inst Satellite Engn, Shanghai 200240, Peoples R China

来源：

MICROELECTRONICS RELIABILITY | 2015年 / 55卷 / 9-10期

基金：

中国国家自然科学基金;

关键词：

Anomaly detection; Associated rules; KPCA; Satellite power subsystem;

D O I：

10.1016/j.microrel.2015.07.010

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

080906 [电磁信息功能材料与结构]; 082806 [农业信息与电气工程];

摘要：

The paper presents an implementable method of anomaly detection for satellite power system. Specifically, a data-driven anomaly detection method for sensor data integrated Kernel Principal Component Analysis (KPCA) and association rule mining is demonstrated. Establishing associated rules among sensor monitoring data sets, this approach analyses the structure of measure space via its Eigen matrix with KPCA, and identifies the anomaly. Especially, different anomalies from satellite system and sensors can be distinguished with the changes of association rules. The effectiveness of the method is proved on sensor data from Feng-Yun satellite power subsystem. (C) 2015 Elsevier Ltd. All rights reserved.

引用

页码：2082 / 2086

页数：5

共 13 条

[1]

Easy and Fast Sensor Fault Detection and Isolation Algorithm for Electrical Drives [J].