基于噪声元学习的卫星遥测信号异常检测方法

doi:10.12305/j.issn.1001-506X.2025.02.02

摘要/Abstract

摘要：

针对卫星遥测数据先验知识稀缺、常规数据驱动的异常检测方法难以准确辨识异常状态的问题，提出一种基于元学习与动态放缩阈值法的卫星遥测信号异常检测算法。首先，通过元学习算法求解一组具备快速适应小样本任务能力的长短期记忆神经网络初始参数，并在训练过程中为网络权重添加噪声，进一步提升模型泛化性能。其次，采用动态放缩阈值法分析预测误差序列，划定动态变化的异常阈值，标记异常点索引以实现卫星遥测数据异常检测。最后，通过两组卫星遥测信号算例验证所提算法的有效性。仿真结果表明，所提方法能够改善预测模型过拟合现象, 并降低漏警概率。

关键词: 卫星遥测信号, 异常检测, 长短期记忆神经网络, 元学习

Abstract:

Due to the scarcity of prior knowledge in satellite telemetry data, conventional data-driven anomaly detection methods are difficult to accurately identify abnormal states, a satellite telemetry signal anomaly detection algorithm based on meta learning and dynamic scaling threshold method is proposed. Firstly, a set of initial parameters of a long short-term memory (LSTM) neural network with the ability to quickly adapt to small sample tasks is solved through meta learning algorithms. The noise is added to the network weights during the training process to further improve generalization performance of the model. Secondly, the dynamic scaling threshold method is used to analyze the prediction error sequence, define the abnormal threshold for dynamic changes, and mark the index of abnormal points to achieve anomaly detection of satellite telemetry data. Finally, the effectiveness of the proposed algorithm is verified through two sets of satellite telemetry signal examples. The simulation results show that the proposed method can improve the overfitting phenomenon of the prediction model and reduce the probability of missed alarms.

Key words: satellite telemetry signal, abnormal detection, longshort-term memory (LSTM) neural net-work, meta-learning

中图分类号:

V474

郭鹏飞, 靳锴, 陈琪锋, 魏才盛. 基于噪声元学习的卫星遥测信号异常检测方法[J]. 系统工程与电子技术, 2025, 47(2): 352-359.

Pengfei GUO, Kai JIN, Qifeng CHEN, Caisheng WEI. Anomaly detection method of satellite telemetry signal based on noise meta learning[J]. Systems Engineering and Electronics, 2025, 47(2): 352-359.

图/表 9

图1

图2

图3

表1

图4

图5

图6

图7

表2

参考文献 31

1	XU Z P , CHENG Z T , GUO B . A hybrid data-driven framework for satellite telemetry data anomaly detection[J]. Acta Astronautica, 2023, 205, 281- 294. doi: 10.1016/j.actaastro.2023.02.009
2	沈毅, 李利亮, 王振华. 航天器故障诊断与容错控制技术研究综述[J]. 宇航学报, 2020, 41 (6): 647- 656.
	SHEN Y , LI L L , WANG Z H . A review of fault diagnosis and fault-tolerant control techniques for spacecraft[J]. Journal of Astronautics, 2020, 41 (6): 647- 656.
3	何家辉, 程志君, 郭波. 联合字典学习与OCSVM的遥测数据异常检测方法[J]. 航空学报, 2023, 44 (13): 207- 219.
	HE J H , CHENG Z J , GUO B . Telemetry anomaly detection method based on joint dictionary learning and OCSVM[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44 (13): 207- 219.
4	WANG Y , ZHANG T , HUI J J , et al. An anomaly detection me-thod for spacecraft solar arrays based on the ILS-SVM model[J]. Journal of Systems Engineering and Electronics, 2023, 34 (2): 515- 529. doi: 10.23919/JSEE.2023.000011
5	WANG Y K , GONG J L , ZHANG J , et al. A deep learning anomaly detection framework for satellite telemetry with fake anomalies[J]. International Journal of Aerospace Engineering, 2022, 2022, 1676933.
6	XIANG G , LIN R S . Robust anomaly detection for multivariate data of spacecraft through recurrent neural networks and extreme value theory[J]. IEEE Access, 2021, 9, 167447- 167457. doi: 10.1109/ACCESS.2021.3136505
7	PANG G S , SHEN C H , CAO L B , et al. Deep learning for anomaly detection: a review[J]. ACM Computing Surveys, 2021, 54 (2): 1- 38.
8	CHEN J , PI D , WU Z Y , et al. Imbalanced satellite telemetry data anomaly detection model based on Bayesian LSTM[J]. Acta Astronautica, 2021, 180, 232- 242. doi: 10.1016/j.actaastro.2020.12.012
9	MENG H Y, ZHANG Y X, LI Y X, et al. Spacecraft anomaly detection via transformer reconstruction error[C]//Proc. of the International Conference on Aerospace System Science and Engineering, 2020: 351-362.
10	傅晨琦, 季利鹏, 孙伟卿, 等. 基于深度残差网络的模拟电路软故障诊断方法[J]. 飞控与探测, 2021, 4 (4): 74- 81.
	FU C Q , JI L P , SUN W Q , et al. Deep residual learning-based soft fault diagnosis method for analog circuits[J]. Flight Control & Detection, 2021, 4 (4): 74- 81.
11	丁建立, 张琪琪, 王静, 等. 基于Transformer-VAE的ADS-B异常检测方法[J]. 系统工程与电子技术, 2023, 45 (11): 3680- 3689.
	DING J L , ZHANG Q Q , WANG J , et al. ADS-B anomaly detection method based on transformer-VAE[J]. Systems Engineering and Electronics, 2023, 45 (11): 3680- 3689.
12	YU J S , SONG Y , TANG D Y , et al. Telemetry data-based spacecraft anomaly detection with spatial-temporal generative adversarial networks[J]. IEEE Trans. on Instrumentation and Measurement, 2021, 70, 3515209.
13	LEI X , LU N Y , CHEN C , et al. Attention mechanism based multi-scale feature extraction of bearing fault diagnosis[J]. Journal of Systems Engineering and Electronics, 2023, 34 (5): 1359- 1367.
14	张万超, 倪昊, 舒鹏, 等. 基于蚁群优化的长短时神经网络变外形飞行器故障模式识别[J]. 飞控与探测, 2023, 6 (3): 72- 77.
	ZHANG W C , NI H , SHU P , et al. Fault mode recognition for variable shape vehicles based on ACO-LSTM[J]. Flight Control & Detection, 2023, 6 (3): 72- 77.
15	LIU L , TIAN L , KANG Z , et al. Spacecraft anomaly detection with attention temporal convolution networks[J]. Neural Computing and Applications, 2023, 35, 9753- 9761.
16	DOUNIA L , RYAN A , SÉBASTIEN L D . Anomaly detection for data accountability of Mars telemetry data[J]. Expert Systems with Applications, 2022, 189, 116060.
17	YANG L , MA Y , ZENG F , et al. Improved deep learning based telemetry data anomaly detection to enhance spacecraft operation reliability[J]. Microelectronics and Reliability, 2021, 126, 114311.
18	PAN S J , YANG Q . A survey on transfer learning[J]. IEEE Trans. on Knowledge and Data Engineering, 2009, 22 (10): 1345- 1359.
19	刘切, 上官子卓, 李嘉玺. 基于迁移学习的航天器遥测数据异常检测技术[J]. 空间控制技术与应用, 2023, 49 (4): 76- 85.
	LIU Q , SHANGGUAN Z Z , LI J X . Transfer learning based anomaly detection technology for spacecraft telemetry data[J]. Aerospace Control and Application, 2023, 49 (4): 76- 85.
20	WEISS K , KHOSHGOFTAAR T M , WANG D D . A survey of transfer learning[J]. Journal of Big Data, 2016, 3 (1): 1- 40.
21	HOSPEDALES T , ANTONIOU A , MICAELLI P , et al. Meta-learning in neural networks: a survey[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2022, 44 (9): 5149- 5169.
22	BAIK S Y, CHOI J H, KIM H W, et al. Meta-learning with task-adaptive loss function for few-shot learning[C]//Proc. of the IEEE/CVF International Conference on Computer Vision, 2021: 9465-9474.
23	MA M R , HAN L S , ZHOU C J . BTAD: a binary transformer deep neural network model for anomaly detection in multiva-riate time series data[J]. Advanced Engineering Informatics, 2023, 56, 101949.
24	LIN J , SHAO H D , ZHOU X D , et al. Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by hete-rogeneous signals[J]. Expert Systems with Application, 2023, 230, 120696.
25	CHEN J K, QIU X P, LIU P F, et al. Meta multi-task learning for sequence modeling[C]//Proc. of the AAAI Conference on Artificial Intelligence, 2018.
26	YU Y , SI X S , HU C H , et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural Computation, 2019, 31 (7): 1235- 1270.
27	GREFF K , SRIVASTAVA R K , KOUTNÍK J , et al. LSTM: a search space odyssey[J]. IEEE Trans. on Neural Networks and Learning Systems, 58 (10): 2222- 2232.
28	ZHANG S , YE F , WANG B N , et al. Few-shot bearing fault diagnosis based on model-agnostic meta-learning[J]. IEEE Trans. on Industry Applications, 2021, 57 (5): 4754- 4764.
29	HUNDMAN K, CONSTANTINOU V, LAPORTE C, et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding[C]//Proc. of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018.
30	ZENG Z F , JIN G , XU C , et al. Satellite telemetry data ano-maly detection using causal network and feature-attention-based LSTM[J]. IEEE Trans. on Instrumentation and Measurement, 2022, 71, 3507221.
31	SANCHEZ F, PANKRATZ C, LINDHOLM D M, et al. Webtcad: a tool for AD-HOC visualization and analysis of telemetry data for multiple missions[C]//Proc. of the SpaceOps Conference, 2018

模型参数	数值
序列长度	10
训练批次大小	8
隐含层大小	16
网络层数	4

预测算法	窗口阈值法			动态放缩阈值法
预测算法	p_a/%	p_r/%	F₁值	p_a/%	p_r/%	F₁值
DNN	53.8	63.6	0.582 9	58.8	60.6	0.596 9
LSTM	73.5	75.8	0.746 3	77.4	72.7	0.749 8
M-LSTM	76.3	87.9	0.816 9	82.9	84.8	0.838 4
M-LSTM-AN	83.8	93.9	0.885 6	93.8	90.9	0.923 3

[1]	钟罡, 周蒋颖, 杜森, 张洪海, 刘皞. 基于航迹预测的无人机短时航迹偏离检测方法[J]. 系统工程与电子技术, 2024, 46(8): 2696-2708.
[2]	李庚松, 刘艺, 郑奇斌, 秦伟, 李红梅, 任小广, 宋明武. 基于蚁狮算法的元特征选择方法[J]. 系统工程与电子技术, 2023, 45(9): 2831-2842.
[3]	杨丽花, 任露露, 呼博, 邵永琪, 聂倩. 基于元学习的时变信道估计方法[J]. 系统工程与电子技术, 2023, 45(6): 1872-1879.
[4]	沈子涵, 赵修斌, 张闯, 张良, 刘鑫贤. 基于长短期记忆神经网络的自适应容错方法[J]. 系统工程与电子技术, 2023, 45(3): 831-838.
[5]	丁建立, 张琪琪, 王静, 霍纬纲. 基于Transformer-VAE的ADS-B异常检测方法[J]. 系统工程与电子技术, 2023, 45(11): 3680-3689.
[6]	聂倩, 杨丽花, 呼博, 任露露. 基扩展模型下基于LSTM神经网络的时变信道预测方法[J]. 系统工程与电子技术, 2022, 44(9): 2971-2977.
[7]	郭军成, 万刚, 胡欣杰, 严发宝, 王帅. 太阳射电频谱爆发识别的元学习方法[J]. 系统工程与电子技术, 2022, 44(8): 2410-2418.
[8]	康颖, 赵治华, 吴灏, 李亚星, 孟进. 基于Deep SVDD的通信信号异常检测方法[J]. 系统工程与电子技术, 2022, 44(7): 2319-2328.
[9]	孙晶明, 虞盛康, 孙俊. 基于元学习的雷达小样本目标识别方法及改进[J]. 系统工程与电子技术, 2022, 44(6): 1839-1845.
[10]	张心宇, 刘源, 宋佳凝. 基于LSTM神经网络的短期轨道预报[J]. 系统工程与电子技术, 2022, 44(3): 939-947.
[11]	刘旗, 张新禹, 刘永祥. 基于门控多尺度匹配网络的小样本SAR目标识别[J]. 系统工程与电子技术, 2022, 44(11): 3346-3356.
[12]	李睿峰, 许爱强, 孙伟超, 王树友. 基于元学习的航空电子设备特征选择算法推荐方法[J]. 系统工程与电子技术, 2021, 43(7): 2011-2020.
[13]	晏媛, 孙俊, 孙晶明, 于俊朋. 雷达小样本目标识别方法及应用分析[J]. 系统工程与电子技术, 2021, 43(3): 684-692.
[14]	张一迪, 王培志, 陆起涌, 张建秋. 异常数据恒虚警检测的非参数方法[J]. 系统工程与电子技术, 2019, 41(5): 964-971.
[15]	郭鹏程, 刘峥, 罗丁利. 基于两次异常检测的雷达HRRP杂波稳健目标识别方法[J]. 系统工程与电子技术, 2019, 41(10): 2221-2226.