联合字典学习与OCSVM的遥测数据异常检测方法
收稿日期: 2022-08-18
修回日期: 2022-09-05
录用日期: 2022-11-28
网络出版日期: 2022-12-06
基金资助
国家自然科学基金(72071208);湖南省科技创新团队项目(2020RC4046)
Telemetry anomaly detection method based on joint dictionary learning and OCSVM
Received date: 2022-08-18
Revised date: 2022-09-05
Accepted date: 2022-11-28
Online published: 2022-12-06
Supported by
National Natural Science Foundation of China(72071208);Science and Technology Innovation Program of Hunan Province(2020RC4046)
针对航天器遥测数据故障样本少,多参数关联异常缺乏有效检测手段的问题,引入字典学习(DL)改进一类支持向量机(OCSVM)对多参数关联关系异常的识别性能,并提出一种联合优化学习机制,以提升模型的检测效果和泛化能力。首先基于正常遥测数据,构建字典学习与OCSVM的联合学习函数,通过迭代优化的方法获取最优关联关系特征提取字典和异常决策边界;然后测试样本在最优字典下稀疏分解,提取特征输入优化后的OCSVM;最终基于异常决策边界实现异常标记。将所提方法应用于NASA公布的航天器MSL数据集和某卫星天线遥测数据进行验证,结果表明:相比于现有的一类分类异常检测方法,该方法在异常检测率、F1分数和G-mean等性能指标都有所提升,特别是在关联关系异常检测上展现出更优越的性能。
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) : 327931 -327931 . DOI: 10.7527/S1000-6893.2022.27931
To solve the problems of small fault sample size in spacecraft telemetry data and lack of effective detection methods for correlation anomalies of multi-parameters, Dictionary Learning (DL) is introduced to improve the recognition performance of One-Class Support Vector Machine (OCSVM). A jointly optimized mechanism is proposed to improve the detection effect and generalization of the model. Firstly, the joint learning function of dictionary learning and OCSVM is given based on telemetry data in the normal state. The optimal dictionary for extracting correlation features and the decision boundary of anomalies are obtained by iterative optimization. Then, test samples are sparsely decomposed via the optimal dictionary, and the extracted features are input into the optimized OCSVM. Finally, anomalies are labeled based on the decision boundary. The proposed method is applied to the MSL dataset published by NASA and telemetry data of a real satellite antenna. The results show that compared with existing one class classification anomaly detection methods, the proposed method shows improved performance in detection precision, F1-score and G-mean, especially in detection of correlation anomalies.
1 | 彭喜元, 庞景月, 彭宇, 等. 航天器遥测数据异常检测综述 [J]. 仪器仪表学报, 2016, 37(9): 1929-1945. |
PENG X Y, PANG J Y, PENG Y, et al. Review on anomaly detection of spacecraft telemetry data [J]. Chinese Journal of Scientific Instrument, 2016, 37(9): 1929-1945 (in Chinese). | |
2 | 张华, 沈嵘康, 宗益燕, 等. 遥感卫星在轨故障统计与分析 [J]. 航天器环境工程, 2015, 32(3): 324-329. |
ZHANG H, SHEN R K, ZONG Y Y, et al. On-orbit fault statistical analysis for remote sensing satellite [J]. Spacecraft Environment Engineering, 2015, 32(3): 324-329 (in Chinese). | |
3 | CHEN S Y, JIN G, MA X Y. Detection and analysis of real-time anomalies in large-scale complex system [J]. Measurement, 2021, 184: 109929. |
4 | 戴金玲, 许爱强, 申江江, 等. 基于OCKELM与增量学习的在线故障检测方法 [J]. 航空学报, 2022, 43(3): 325121 |
DAI J L, XU A Q, SHEN J J, et al. Online fault detection method based on incremental learning and OCKELM [J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(3): 325121 (in Chinese). | |
5 | JIA S, MA B, GUO W, et al. A sample entropy based prognostics method for lithiumion batteries using relevance vector machine [J]. Journal of Manufacturing Systems, 2021, 61: 773-781. |
6 | ABDELGHAFAR S, DARWISH A, HASSANIEN A E, et al. Anomaly detection of satellite telemetry based on optimized extreme learning machine [J]. Journal of Space Safety Engineering, 2019, 6(4): 291-298. |
7 | 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. London: ACM Press, 2018: 387-395. |
8 | LIU J Q, PAN C L, LEI F, et al. Fault prediction of bearings based on LSTM and statistical process analysis [J]. Reliability Engineering & System Safety, 2021, 214: 107646. |
9 | VOS K, PENG Z X, JENKINS C, et al. Vibration-based anomaly detection using LSTM/SVM approaches [J]. Mechanical Systems and Signal Processing, 2022, 169: 108752. |
10 | 董静怡, 庞景月, 彭宇, 等. 集成LSTM的航天器遥测数据异常检测方法 [J]. 仪器仪表学报, 2019, 40(7): 22-29. |
DONG J Y, PANG J Y, PENG Y, et al. Spacecraft telemetry data anomaly detection method based on ensemble LSTM [J]. Chinese Journal of Scientific Instrument, 2019, 40(7): 22-29 (in Chinese). | |
11 | 闫媞锦, 夏元清, 张宏伟, 等. 一种非规则采样航空时序数据异常检测方法 [J]. 航空学报, 2021, 42(4): 525019. |
YAN T J, XIA Y Q, ZHANG H W, et al. An anomaly detection method for irregularly sampled spacecraft time series data [J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 525019 (in Chinese). | |
12 | YU J, SONG Y, TANG D, et al. Telemetry data-based spacecraft anomaly detection with spatial–temporal generative adversarial networks [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-9. |
13 | ZHANG J T, ZENG B, SHEN W M, et al. A One-class shapelet dictionary learning method for wind turbine bearing anomaly detection [J]. Measurement, 2022,197: 111318. |
14 | SCHO¨LKOPF B, PLATT J C, SHAWE-TAYLOR J, et al. Estimating the support of a high-dimensional distribution [J]. Neural Computation, 2001, 13(7): 1443-1471. |
15 | 罗鹏,王布宏,李腾耀. 基于BiGRU-SVDD的ADS-B异常数据检测模型 [J]. 航空学报, 2020, 41(10): 323878. |
LUO P, WANG B H, LI T Y. ADS-B anomaly data detection model based on BiGRU-SVDD [J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(10): 323878 (in Chinese). | |
16 | HU M, JI Z, YAN K, et al. Detecting anomalies in time series data via a meta-feature based approach [J]. IEEEAccess, 2018, 6: 27760-27776. |
17 | SAARI J, STR?MBERGSSON D, LUNDBERG J, et al. Detection and identification of windmill bearing faults using a one-class support vector machine (SVM) [J]. Measurement, 2019, 137: 287-301. |
18 | LI C, CABRERA D, SANCHO F, et al. From fault detection to one-class severity discrimination of 3D printers with one-class support vector machine [J]. ISA Transactions, 2021, 110: 357-367. |
19 | 段翠英. 基于模式演化的遥测数据建模方法及应用 [D]. 长沙: 国防科学技术大学, 2015. |
DUAN C Y. A satellite telemetry data modeling method based on pattern evolution [D]. Changsha: National University of Defense Technology, 2015 (in Chinese). | |
20 | 董隽硕, 吴玲达, 郝红星. 稀疏表示技术与应用综述 [J]. 计算机系统应用, 2021, 30(7): 13-21. |
DONG J S, WU L D, HAO H X. Survey on sparse representation techniques and applications [J]. Computer Systems & Applications, 2021, 30(7): 13-21 (in Chinese). | |
21 | 练秋生, 石保顺, 陈书贞. 字典学习模型、算法及其应用研究进展 [J]. 自动化学报, 2015, 41(2): 240-260. |
LIAN Q S, SHI B S, CHEN S Z. Research advances on dictionary learning models, algorithms and applications [J]. Acta Automatica Sinica, 2015, 41(2): 240-260 (in Chinese). | |
22 | TAKEISHI N, YAIRI T. Anomaly detection from multivariate time-series with sparse representation [C]∥ Proceedings of the 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).Piscataway: IEEE Press, 2014: 2651-2656. |
23 | DAS S, MATTHEWS B L, SRIVASTAVA A N, et al. Multiple kernel learning for heterogeneous anomaly detection: Algorithm and aviation safety case study [C]∥ Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2010: 47-56. |
24 | PURANIK T G, MAVRIS D N. Anomaly detection in general-aviation operations using energy metrics and flight-data records [J]. Journal of Aerospace Information Systems, 2018, 15(1): 22-36. |
25 | KONG Y, WANG T Y, FENG Z P, et al. Discriminative dictionary learning based sparse representation classification for intelligent fault identification of planet bearings in wind turbine [J]. Renewable Energy, 2020, 152: 754-769. |
26 | ADLER A, ELAD M, HEL-OR Y, et al. Sparse coding with anomaly detection [J]. Journal of Signal Processing Systems, 2015, 79(2): 179-188. |
27 | LIU B, XIE H X, XIAO Y S. Multi-task analysis discriminative dictionary learning for one-class learning [J]. Knowledge-Based Systems, 2021, 227: 107195. |
28 | AHARON M, ELAD M, BRUCKSTEIN A. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J]. IEEE Transactions on Signal Processing, 2006, 54(11): 4311-4322. |
29 | HOU C P, NIE F P, LI X L, et al. Joint embedding learning and sparse regression: A framework for unsupervised feature selection [J]. IEEE Transactions on Cybernetics, 2013, 44(6): 793-804. |
/
〈 |
|
〉 |