Proceedings Article10.1109/ISSCAA.2010.5633180
Anomaly detection and fault Diagnosis technology of spacecraft based on telemetry-mining
Quan Li,XingShe Zhou,Peng Lin,Shaomin Li +3 more
- 08 Jun 2010
- pp 233-236
22
TL;DR: This paper first introduces the conventional approaches for AD/FD such as limit-check, expert system and so on, and then describes the characteristics of the spacecraft telemetry data which should be considered in the actual data mining applications.
read more
Abstract: Recent developments in data mining technologies make it possible to use the massive archived spacecraft telemetry data to produce the advanced system health monitoring applications for anomaly detection (AD) and fault Diagnosis (FD). These data driven applications can obtain the knowledge or model from spacecraft telemetry data automatically or semi-automatically. In this paper, we first introduce the conventional approaches for AD/FD such as limit-check, expert system and so on, and then describe the characteristics of the spacecraft telemetry data which should be considered in the actual data mining applications. Finally we propose some feasible approaches using data mining technology for spacecraft AD/FD.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
Kyle Hundman,Valentino Constantinou,Christopher Laporte,Ian Colwell,Tom Soderstrom +4 more
- 19 Jul 2018
TL;DR: The effectiveness of Long Short-Term Memory networks, a type of Recurrent Neural Network, in overcoming issues using expert-labeled telemetry anomaly data from the Soil Moisture Active Passive (SMAP) satellite and the Mars Science Laboratory (MSL) rover, Curiosity is demonstrated.
909
Credit Card Fraud Detection under Extreme Imbalanced Data: A Comparative Study of Data-level Algorithms
TL;DR: Intelligent machine learning based fraudulent transaction detection systems are very effective in real-world scenarios but need more research and development to be able to be truly effective in future.
98
Machine Learning Methods for Spacecraft Telemetry Mining
TL;DR: A comparison between the different machine learning techniques that can be applied for low earth orbit satellite telemetry mining is introduced and the techniques are evaluated on the bases of calculating the prediction accuracy using mean error and correlation estimation.
85
An Unsupervised Anomaly Detection Approach for Spacecraft Based on Normal Behavior Clustering
Yu Gao,Tianshe Yang,Minqiang Xu,Nan Xing +3 more
- 12 Jan 2012
TL;DR: This paper presents a new unsupervised anomaly detection approach for spacecraft based on normal behavior clustering that takes as input a set of unlabelled historical telemetry data and automatically detects anomalies within the data.
45
Fault detection and diagnosis for spacecraft using principal component analysis and support vector machines
Yu Gao,Tianshe Yang,Nan Xing,Minqiang Xu +3 more
- 18 Jul 2012
TL;DR: A new fault detection and diagnosis approach for spacecraft based on Principal Component Analysis (PCA) and Support Vector Machines (SVM) where PCA is used to extract features from input data and reduce the input data to low dimensional feature vectors.
35
References
Characterization of Randomly Time-Variant Linear Channels
TL;DR: Several new canonical channel models are derived in this paper, some of which are dual to those of Kailath, and a model called the Quasi-WSSUS channel is presented to model the behavior of such channels.
2.5K
Fast subsequence matching in time-series databases
Christos Faloutsos,M. Ranganathan,Yannis Manolopoulos +2 more
- 24 May 1994
TL;DR: An efficient indexing method to locate 1-dimensional subsequences within a collection of sequences, such that the subsequences match a given (query) pattern within a specified tolerance.
Finding surprising patterns in a time series database in linear time and space
Eamonn Keogh,Stefano Lonardi,Bill Chiu +2 more
- 23 Jul 2002
TL;DR: A novel technique is introduced that defines a pattern surprising if the frequency of its occurrence differs substantially from that expected by chance, given some previously seen data.
499
Dynamic syslog mining for network failure monitoring
Kenji Yamanishi,Yuko Maruyama +1 more
- 21 Aug 2005
TL;DR: A new methodology of dynamic syslog mining is proposed in order to detect failure symptoms with higher confidence and to discover sequential alarm patterns among computer devices.
252
Aeronautical Channel Characterization
TL;DR: This paper is concerned with characterizing the link between an airplane and a satellite, and attention is focused on the effect of indirect paths scattered from the surface of the earth.
178