航天器遥测数据的实时异常检测对于航天任务具有重要意义。以往方法大都考虑规则采样且缺失率较低的时序数据，然而航空时序数据具有维度大、噪声多、缺失率高、采样间隔不规则等特点，因此异常检测任务较为困难。针对非规则采样且具有缺失值的多维航空时序数据提出非规则采样多维时序数据异常检测（IMAD）算法。首先，采用带有可训练迟滞项的门控循环单元（GRU-D）对缺失值和非规则采样的时序数据进行建模；然后，采用变分自编码器建立随机性模型，学习正常时序数据的分布，从而对噪声数据具有鲁棒性；最后，利用基于极值理论的自适应阈值确定法确定合适阈值进行异常检测。结果显示，在两个真实航空时序数据集上，IMAD具有超出当前最新异常检测算法的性能；多个实验表明，IMAD在缺失率、参数以及数据集变化时，能够维持较好的异常检测效果，具有较强的鲁棒性。
Real time anomaly detection of spacecraft telemetry data is critical for space mission. Previous methods mostly model the regularly sampled time series data with low missing rates. However, spacecraft telemetry time series data has the characteristics of large dimensions, many noises, high missing rates, irregular sampling intervals, and it is thus more difficult to conduct anomaly detection tasks. An Irregularly sampled Multivariate time series Anomaly Detection (IMAD) algorithm is proposed to model the irregularly sampled multi-dimensional spacecraft time series data with missing values. First, Gated Recurrent Unit with trainable Decays (GRU-D) to model missing values and irregular sampling intervals. Furthermore, the variational autoencoder is used to model the randomness and learn the distribution of normal time series data. Finally, the adaptive threshold determination method based on the extreme value theory is adopted to determine the appropriate threshold for anomaly detection. The experimental results on two real-world spacecraft telemetry datasets show that IMAD outperforms state-of-the-art anomaly detection algorithms. Experiments demonstrate that IMAD is robust to the changes of missing rates, parameters and datasets.
[1] HUNDMAN K, CONSTANTINOU V, LAPORTE C, et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York:ACM, 2018:387-395.
[2] ZIMEK A, SCHUBERT E, KRIEGEL H P. A survey on unsupervised outlier detection in high-dimensional numerical data[J]. Statistical Analysis and Data Mining:The ASA Data Science Journal, 2012, 5(5):363-387.
[3] PANG G, SHEN C, CAO L, et al. Deep learning for anomaly detection:A review[DB/OL]. arXiv preprint:2007.02500,2020.
[4] SANCHEZ F, PANKARTZ C, LINDXHOLM D M, et al. WebTCAD:A tool for Ad-hoc visualization and analysis of telemetry data for multiple missions[C]//2018 SpaceOps Conference. Paris:SpaceOps, 2018:2616.
[5] FUERTES S, PICART G, TOURNERET J Y, et al. Improving spacecraft health monitoring with automatic anomaly detection techniques[C]//14th International Conference on Space Operations. Daejeon:SpaceOps, 2016:2430.
[6] LI Z, ZHAO Y, LIU R, et al. Robust and rapid clustering of KPIs for large-scale anomaly detection[C]//2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS). New York:IEEE Press, 2018:1-10.
[7] YU G, CAI Z, WANG S, et al. Unsupervised online anomaly detection with parameter adaptation for KPI abrupt changes[J]. IEEE Transactions on Network and Service Management, 2019, 17(3):1294-1308.
[8] PARK D, KIM H, HOSHI Y, et al. A multimodal execution monitor with anomaly classification for robot-assisted feeding[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway:IEEE Press, 2017:5406-5413.
[9] RODRIGUEZ A, BOURNE D, MASON M, et al. Failure detection in assembly:Force signature analysis[C]//2010 IEEE International Conference on Automation Science and Engineering. Piscataway:IEEE Press, 2010:210-215.
[10] GUPTA M, GAO J, AGGARWAL C C, et al. Outlier detection for temporal data:A survey[J]. IEEE Transactions on Knowledge and data Engineering, 2013, 26(9):2250-2267.
[11] REN H, XU B, WANG Y, et al. Time-series anomaly detection service at microsoft[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York:ACM, 2019:3009-3017.
[12] LI D, CHEN D, JIN B, et al. MAD-GAN:Multivariate anomaly detection for time series data with generative adversarial networks[C]//International Conference on Artificial Neural Networks. Berlin:Springer, 2019:703-716.
[13] ERGEN T, KOZAT S S. Unsupervised anomaly detection with LSTM neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 31(8):3127-3141.
[14] AHMAD S, LAVIN A, PURDY S, et al. Unsupervised real-time anomaly detection for streaming data[J]. Neurocomputing, 2017, 262:134-147.
[15] YOON S, LEE J G, LEE B S. NETS:Extremely fast outlier detection from a data stream via set-based processing[J]. Proceedings of the VLDB Endowment, 2019, 12(11):1303-1315
[16] MALHOTRA P, RAMAKRISHNAN A, ANAND G, et al. LSTM-based encoder-decoder for multi-sensor anomaly detection[DB/OL]. arXiv preprint:1607.00148,2016.
[17] ZONG B, SONG Q, MIN M R, et al. Deep autoencoding gaussian mixture model for unsupervised anomaly detection[C]//International Conference on Learning Representations. Vancouver:ICLR, 2018.
[18] SCHAFER J L, GRAHAM J W. Missing data:Our view of the state of the art[J]. Psychological Methods, 2002, 7(2):147.
[19] GARCIA-LAENCINA P J, SANCHO-GOMEZ J L, FIGUEIRAS-VIDAL A R. Pattern classification with missing data:A review[J]. Neural Computing and Applications, 2010, 19(2):263-282.
[20] KREINDLER D M, LUMSDEN C J. The effects of the irregular sample and missing data in time series analysis[J]. Nonlinear Dynamics, Psychology, and Life Sciences, 2012, 135(2):187-214.
[21] MONDAL D, PERCIVAL D B. Wavelet variance analysis for gappy time series[J]. Annals of the Institute of Statistical Mathematics, 2010, 62(5):943-966.
[22] REHFELD K, MARWAN N, HEITZIG J, et al. Comparison of correlation analysis techniques for irregularly sampled time series[J]. Nonlinear Processes in Geophysics, 2011, 18(3):389-404.
[23] WHITE I R, ROYSTON P, WOOD A M. Multiple imputation using chained equations:Issues and guidance for practice[J]. Statistics in Medicine, 2011, 30(4):377-399.
[24] CHE Z, PURUSHOTHAM S, CHO K, et al. Recurrent neural networks for multivariate time series with missing values[J]. Scientific Reports, 2018, 8(1):1-12.
[25] KINGMA D P, WELLING M. Auto-encoding variational bayes[DB/OL]. arXiv preprint:1312.6114,2013.
[26] AN J, CHO S. Variational autoencoder based anomaly detection using reconstruction probability[J]. Special Lecture on IE, 2015, 2(1):1-18.
[27] SIFFER A, FOUQUE P A, TERMIER A, et al. Anomaly detection in streams with extreme value theory[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2017:1067-1075.
[28] MALHOTRA P, RAMAKRISHNAN A, ANAND G, et al. LSTM-based encoder-decoder for multisensory anomaly detection[DB/OL]. arXiv preprint:1607.00148, 2016.
CJA