A deep auto-encoder satellite anomaly advance warning framework

Purpose The purpose of this paper is to ensure the stable operation of satellites in orbit and to assist ground personnel in continuously monitoring the satellite telemetry data and finding anomalies in advance, which can improve the reliability of satellite operation and prevent catastrophic losses. Design/methodology/approach This paper proposes a deep auto-encoder (DAE) satellite anomaly advance warning framework for satellite telemetry data. Firstly, this study performs grey correlation analysis, extracts important feature attributes to construct feature vectors and builds the variational auto-encoder with bidirectional long short-term memory generative adversarial network discriminator (VAE/BLGAN). Then, the Mahalanobis distance is used to measure the reconstruction score of input and output. According to the periodic characteristic of satellite operation, a dynamic threshold method based on periodic time window is proposed. Satellite health monitoring and advance warning are achieved using reconstruction scores and dynamic thresholds. Findings Experiment results indicate DAE methods can probe that satellite telemetry data appear abnormal, trigger a warning before the anomaly occurring and thus allow enough time for troubleshooting. This paper further verifies that the proposed VAE/BLGAN model has stronger data learning ability than other two auto-encoder models and is sensitive to satellite monitoring data. Originality/value This paper provides a DAE framework to apply in the field of satellite health monitoring and anomaly advance warning. To the best of the authors’ knowledge, this is the first paper to combine DAE methods with satellite anomaly detection, which can promote the application of artificial intelligence in spacecraft health monitoring.

[1]  Wencong Su,et al.  An Evolutionary Deep Learning-Based Anomaly Detection Model for Securing Vehicles , 2021, IEEE Transactions on Intelligent Transportation Systems.

[2]  Po-Ching Lin,et al.  An Unsupervised Deep Learning Model for Early Network Traffic Anomaly Detection , 2020, IEEE Access.

[3]  Wenjing Hu,et al.  Anomaly detection and fault analysis of wind turbine components based on deep learning network , 2018, Renewable Energy.

[4]  Wang Fei,et al.  Anomaly detection of orbit satellite telemetry sequence based on two-window mode , 2018, 2018 Chinese Control And Decision Conference (CCDC).

[5]  Yu Peng,et al.  Optimize the Coverage Probability of Prediction Interval for Anomaly Detection of Sensor-Based Monitoring Series , 2018, Sensors.

[6]  Dechang Pi,et al.  A data-driven method of health monitoring for spacecraft , 2018 .

[7]  Valentino Constantinou,et al.  Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding , 2018, KDD.

[8]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[9]  Jun Zhou,et al.  Anomaly detection for satellite power subsystem with associated rules based on Kernel Principal Component Analysis , 2015, Microelectron. Reliab..

[10]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[11]  Ruiyun Qi,et al.  Feature extraction and fault detection based on telemetry data for Satellite TX-I , 2014, Proceedings of 2014 IEEE Chinese Guidance, Navigation and Control Conference.

[12]  Ruijin Liao,et al.  A cost-effectiveness assessment model using grey correlation analysis for power transformer selection based on life cycle cost , 2014, Kybernetes.

[13]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[14]  Ryan Mackey,et al.  General Purpose Data-Driven Monitoring for Space Operations , 2012, J. Aerosp. Comput. Inf. Commun..

[15]  Jingsong Lin,et al.  Application of Grey Correlation Analysis Based on Entropy Weight for Supplier Selection , 2010 .

[16]  Mark Schwabacher,et al.  Unsupervised Anomaly Detection for Liquid-Fueled Rocket Propulsion Health Monitoring , 2007, J. Aerosp. Comput. Inf. Commun..

[17]  R.A. Martin,et al.  Unsupervised Anomaly Detection and Diagnosis for Liquid Rocket Engine Propulsion , 2007, 2007 IEEE Aerospace Conference.

[18]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[19]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[20]  Raymond T. Ng,et al.  Algorithms for Mining Distance-Based Outliers in Large Datasets , 1998, VLDB.

[21]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[22]  Luigi Portinale,et al.  Dynamic Bayesian Networks for Fault Detection, Identification, and Recovery in Autonomous Spacecraft , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[23]  Jeremy Straub,et al.  Improving Satellite Security Through Incremental Anomaly Detection on Large, Static Datasets , 2015 .