Modern Machine Learning Methods for Telemetry-Based Spacecraft Health Monitoring
- 1 August 2021
- journal article
- research article
- Published by Pleiades Publishing Ltd in Automation and Remote Control
- Vol. 82 (8), 1293-1320
- https://doi.org/10.1134/s0005117921080014
Abstract
We survey the progress in data mining methods for spacecraft health monitoring. The main emphasis is placed on the analysis of telemetry data enabling the identification of spacecraft states that are atypical during normal operation and the prediction of possible failures in the operation of the spacecraft or its components. The main stages required for the creation of general-purpose spacecraft state monitoring systems are considered; methods for detecting anomalies in telemetry data taking into account the specific features of the spacecraft are presented in detail; and publications on this topic known to the authors are analyzed. Examples of the implementation of such systems in flight control centers of various countries are given. The promising areas of development of methods for analyzing the technical state of complex systems relevant for solving problems in space technology are discussed, and the main factors that hinder the development of machine learning methods for analyzing telemetry data are noted.Keywords
This publication has 88 references indexed in Scilit:
- General Purpose Data-Driven Monitoring for Space OperationsJournal of Aerospace Information Systems, 2012
- Advanced model-based FDIR techniques for aerospace systems: Today challenges and opportunitiesProgress in Aerospace Sciences, 2012
- Anomaly detectionACM Computing Surveys, 2009
- Neighborhood rough set based heterogeneous feature subset selectionInformation Sciences, 2008
- Discovering cluster-based local outliersPattern Recognition Letters, 2003
- Estimating the Support of a High-Dimensional DistributionNeural Computation, 2001
- Rock: A robust clustering algorithm for categorical attributesInformation Systems, 2000
- Long Short-Term MemoryNeural Computation, 1997
- Mining association rules between sets of items in large databasesACM SIGMOD Record, 1993
- Nonparametric Estimation from Incomplete ObservationsJournal of the American Statistical Association, 1958