基于全生命周期数据驱动的通讯卫星行波管退化评估方法

doi:10.7527/S1000-6893.2024.31376

Abstract

Abstract:

Traveling Wave Tube （TWT） is a key component in communication satellites， typically operating in high-temperature and high-pressure environments for extended periods， making its degradation evaluation particularly important. Traditional mechanism models and threshold rule methods struggle to effectively represent degradation levels under complex electro-thermal coupling effects. To address this challenge， we propose a deep neural network degradation evaluation method based on a Multi-Scale Attention Encoder （MSA-Encoder）. First， the complex characteristics of telemetry data are analyzed in detail， exploring the difficulties these characteristics pose for training deep learning models and providing solutions. Second， the MSA-Encoder network is designed， which precisely captures the temporal and channel dependencies in multi-dimensional telemetry data through auto-correlation and Global-Local Channel Attention （GLCA） mechanisms， respectively， achieving accurate data reconstruction. Third， we propose a TWT degradation index calculation method based on Mahalanobis distance and moving average seasonal decomposition. This method calculates data drift index through reconstruction difference theory， followed by moving average seasonal decomposition to compute the degradation index. Finally， using the full life cycle TWT data from a certain communication satellite， a TWT degradation dataset is constructed， and numerical experiments are conducted on this dataset. The experimental results show that the MSA-Encoder surpasses benchmark models of the same parameter scale in telemetry data extraction capability， proving the reliability of the degradation index calculation.

Key words: traveling wave tube, communication satellite, degradation evaluation, data-driven, full life cycle telemetry data

CLC Number:

V448.2

Haotian ZHAO, Shi QIU, Ming LIU, Qichao GAI, Xibin CAO. Degradation evaluation method for communication satellite traveling wave tubes based on full life cycle data[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(12): 331376.

Figures/Tables 15

Table 1

Characteristics of satellite telemetry data

特性名称	原因及影响	可行解决方法
数据缺失	通信中断、数据丢包、卫星未延时传输数据等原因，导致数据不完整，影响模型对时间序列的学习	采用插值法、预测填补法
采样频率差异	不同传感器采样频率不同导致时间戳不对齐，影响数据结构规范化	进行时间戳对齐、重采样调整
动态特性差异	特征动态变化速度差异，影响深度学习中滑动窗口等超参数的选择	设置合适的滑动窗口长度，利用通道独立方法替代通道非独立方法
存在野值	传感器故障、传输干扰、外界因素等原因。可能干扰数据分布，影响模型训练和预测效果	进行野值检测与剔除
特征量纲差异	不同特征的物理量级不同，影响模型梯度下降过程，导致某些特征的影响被不成比例放大或忽略	进行数据缩放（归一化、标准化等）处理
异质性	同时包含连续变量和离散变量，使得模型难以对所有变量进行统一建模	对离散变量进行直接归一化，或采用独热编码以及其他适配性编码
多模态性	系统在不同状态下的行为差异使统计分布呈现多模态特性，使得传统单峰分布方法具有应用局限性	利用合适的建模方法（如GMM等）处理多模态特征
非平稳性	数据统计特性随时间变化（如均值、方差变化），一些模型难以稳定学习时序依赖，可能导致过拟合或泛化性能下降	进行平稳化处理，或采用专门适配非平稳数据的模型
通道同步性	跨通道特征间存在协同变化关系，其可用于增强对数据通道依赖关系的捕捉	设计能够捕捉通道同步性的网络结构，如通道间注意力机制等
高维度性	卫星包含成百上千条遥测变量，导致维度诅咒问题，数据稀疏化，影响模型的学习效果	进行特征选择，或设计高效适应高维数据的表征模型

Table 1

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Table 2

Training results of MSA-encoder and other baselines （Epoch=10）

模型	MAE	MSE	MBE	RAE	MSLE	$R 2$
LSTM^［30］	0.044 081	0.006 663	-0.012 387	0.208 582	0.003 472	0.896 237
GRU^［31］	0.028 490	0.002 530	-0.003 956	0.134 808	0.001 302	0.960 576
TCN^［32］	0.027 533	0.001 716	0.000 068	0.130 240	0.000 837	0.973 320
Vanilla Transformer Encoder^［33］	0.102 716	0.025 183	0.005 682	0.486 030	0.012 005	0.608 200
Informer Encoder^［34］	0.096 019	0.017 225	-0.018 204	0.454 437	0.009 302	0.731 454
MSA-Encoder	0.025 428	0.001 195	0.000 048	0.119 849	0.000 671	0.992 205

Table 2

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

References 34

[1]	WONG P， ZHANG P， LUGINSLAND J. Recent theory of traveling-wave tubes： A tutorial-review［J］. Plasma Research Express， 2020， 2（2）： 023001.
[2]	FAN Y S， ZHAO Q， LIANG T， et al. Study on reliability of long-HV-OFF-mode of cathode assembly in space traveling wave tube‍［C］‍∥2023 24th International Vacuum Electronics Conference （IVEC）. Piscataway： IEEE Press， 2023.
[3]	LI X， HUANG X J， MATHISEN S， et al. Design of 71-76 GHz double-corrugated waveguide traveling-wave tube for satellite downlink‍［J］. IEEE Transactions on Electron Devices， 2018， 65（6）： 2195-2200.
[4]	LIU S S， XIE Q M， CHEN Z F， et al. High linear power E-band traveling-wave tube for communication applications‍［J］. IEEE Transactions on Electron Devices， 2021， 68（6）： 2984-2989.
[5]	SOCUÉLLAMOS J M， DIONISIO R， LETIZIA R， et al. Experimental validation of phase velocity and interaction impedance of meander-line slow-wave structures for space traveling-wave tubes‍［J］. IEEE Transactions on Microwave Theory and Techniques， 2021， 69（4）： 2148-2154.
[6]	GHOSH S K. Travelling-wave tubes for space application： present and future［C］‍∥2020 URSI Regional Conference on Radio Science （URSI-RCRS）. Piscataway： IEEE Press， 2020.
[7]	HU Q L， SHAO X D， CHEN W H. Robust fault-tolerant tracking control for spacecraft proximity operations using time-varying sliding mode［J］. IEEE Transactions on Aerospace and Electronic Systems， 2018， 54（1）： 2-17.
[8]	HU Q L， SHAO X D， GUO L. Adaptive fault-tolerant attitude tracking control of spacecraft with prescribed performance‍［J］. IEEE/ASME Transactions on Mechatronics， 2018， 23（1）： 331-341.
[9]	HAO Z W， YUE X K， WEN H W， et al. Full-state-constrained non-certainty-equivalent adaptive control for satellite swarm subject to input fault‍［J］. IEEE/CAA Journal of Automatica Sinica， 2022， 9（3）： 482-495.
[10]	ZHANG F， SONG M S， HUANG B X， et al. Adaptive tracking control for tethered aircraft systems with actuator nonlinearities and output constraints‍［J］. IEEE Transactions on Aerospace and Electronic Systems， 2024， 60（3）： 3582-3597.
[11]	QUAN F X， SUN X M， ZHAO H Y， et al. Detection of rotating stall inception of axial compressors based on deep dilated causal convolutional neural networks‍［J］. IEEE Transactions on Automation Science and Engineering， 2024， 21（2）： 1235-1243.
[12]	XIAO B W， YUAN Y B， SUN X M， et al. Fault diagnosis model for accessory gearbox based on deep transfer learning［C］∥2024 39th Youth Academic Annual Conference of Chinese Association of Automation （YAC）. Piscataway： IEEE Press， 2024.
[13]	张永，龚众望，郑英，等. 工业设备的健康状态评估和退化趋势预测联合研究［J］. 中国科学：技术科学， 2022， 52（1）： 180-197.
	ZHANG Y， GONG Z W， ZHENG Y， et al. Joint study on health state assessment and degradation trend prediction of industrial equipment［J］. Scientia Sinica （Technologica）， 2022， 52（1）： 180-197 （in Chinese）.
[14]	ZHANG J S， HUANG C S， CHOW M Y， et al. A data-model interactive remaining useful life prediction approach of lithiumion batteries based on PF-BiGRU-TSAM‍［J］. IEEE Transactions on Industrial Informatics， 2024， 20（2）： 1144-1154.
[15]	李天梅，司小胜，张建勋. 多源传感监测线性退化设备数模联动的剩余寿命预测方法［J］. 航空学报， 2023， 44（8）： 227190.
	LI T M， SI X S， ZHANG J X. Data-model interactive remaining useful life prediction method for multi-sensor monitored linear stochastic degrading devices‍［J］. Acta Aeronautica et Astronautica Sinica， 2023， 44（8）： 227190 （in Chinese）.
[16]	XU J H， WU H X， WANG J M， et al. Anomaly transformer： Time series anomaly detection with association discrepancy‍［DB/OL］. arXiv preprint： 2110.02642， 2021.
[17]	张晟斐，李天梅，胡昌华，等. 基于深度卷积生成对抗网络的缺失数据生成方法及其在剩余寿命预测中的应用［J］. 航空学报， 2022， 43（8）： 225708.
	ZHANG S F， LI T M， HU C H， et al. Missing data generation method and its application in remaining useful life prediction based on deep convolutional generative adversarial network［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（8）： 225708 （in Chinese）.
[18]	牟含笑，郑建飞，胡昌华，等. 基于CDBN与BiLSTM的多元退化设备剩余寿命预测［J］. 航空学报， 2022， 43（7）： 325403.
	MU H X， ZHENG J F， HU C H， et al. Remaining useful life prediction of multivariate degradation equipment based on CDBN and BiLSTM‍［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（7）： 325403 （in Chinese）.
[19]	YAIRI T， TAKEISHI N， ODA T， et al. A data-driven health monitoring method for satellite housekeeping data based on probabilistic clustering and dimensionality reduction［J］. IEEE Transactions on Aerospace and Electronic Systems， 2017， 53（3）： 1384-1401.
[20]	LUO T Y， LIU M， SHI P， et al. A hybrid data preprocessing-based hierarchical attention BiLSTM network for remaining useful life prediction of spacecraft lithium-ion batteries‍［J］. IEEE Transactions on Neural Networks and Learning Systems， 2024， 35（12）：18076-18089.
[21]	HAN D Y， YU J S， GONG M T， et al. A remaining useful life prediction approach based on low-frequency current data for bearings in spacecraft‍［J］. IEEE Sensors Journal， 2021， 21（17）： 18978-18989.
[22]	康玉祥，陈果，尉询楷，等. 深度残差对冲网络及其在滚动轴承故障诊断中的应用［J］. 航空学报， 2022， 43（8）： 625201.
	KANG Y X， CHEN G， WEI X K， et al. Deep residual hedging network and its application in fault diagnosis of rolling bearings‍［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（8）： 625201 （in Chinese）.
[23]	罗东亮，蔡雨萱，杨子豪，等. 工业缺陷检测深度学习方法综述［J］. 中国科学：信息科学， 2022， 52（6）： 1002-1039.
	LUO D L， CAI Y X， YANG Z H， et al. Survey on industrial defect detection with deep learning‍［J］. Scientia Sinica （Informationis）， 2022， 52（6）： 1002-1039 （in Chinese）.
[24]	李全坤，景兴建. 基于传递函数特征的机械结构故障诊断方法新进展［J］. 航空学报， 2021， 42（11）： 524845.
	LI Q K， JING X J. Recent advances of fault diagnosis methods based on transmissibility function for mechanical structures‍［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（11）： 524845 （in Chinese）.
[25]	周治国，马文浩，刘杰强，等. 小卫星健康状态自主模糊综合评估方法［J］. 电子与信息学报， 2022， 44（10）： 3553-3565.
	ZHOU Z G， MA W H， LIU J Q， et al. Autonomous fuzzy comprehensive evaluation method for small satellite health state‍［J］. Journal of Electronics & Information Technology， 2022， 44（10）： 3553-3565 （in Chinese）.
[26]	CHEN J F， PI D C， WU Z Y， et al. Imbalanced satellite telemetry data anomaly detection model based on Bayesian LSTM［J］. Acta Astronautica， 2021， 180： 232-242.
[27]	CUI L F， ZHANG Q Z， SHI Y， et al. A method for satellite time series anomaly detection based on fast-DTW and improved-KNN［J］. Chinese Journal of Aeronautics， 2023， 36（2）： 149-159.
[28]	YANG Y Y， ZHANG C L， ZHOU T， et al. DCdetector： Dual attention contrastive representation learning for time series anomaly detection‍［C］‍∥Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York： ACM， 2023.
[29]	WU H， XU J， WANG J， et al. Autoformer： Decomposition transformers with auto-correlation for long-term series forecasting‍［J］. Advances in neural information processing systems， 2021， 34： 22419-22430.
[30]	KIM J， EL-KHAMY M， LEE J. Residual LSTM： Design of a deep recurrent architecture for distant speech recognition［DB/OL］. arXiv preprint： 1701.03360， 2017.
[31]	CHO K， VAN MERRIENBOER B， GULCEHRE C， et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation‍［DB/OL］. arXiv preprint： 1406. 1078， 2014.
[32]	BAI S J， KOLTER J Z， KOLTUN V， et al. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling‍［DB/OL］. arXiv preprint： 1803. 01271， 2018.
[33]	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］∥Advances in Neural Information Processing Systems. Long Beach： Neural Information Processing Systems Foundation， 2017： 5998-6008.
[34]	ZHOU H Y， ZHANG S H， PENG J Q， et al. Informer： Beyond efficient transformer for long sequence time-series forecasting［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2021， 35（12）： 11106-11115.

Degradation evaluation method for communication satellite traveling wave tubes based on full life cycle data

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 34

Related Articles 13

Recommended Articles

Metrics

Comments

[1]	Yuequn LUO, Dali DING, Mulai TAN, Yidong LIU, Huan ZHOU. A review of autonomous maneuver decision methods for unmanned combat aerial vehicle [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(7): 30877-030877.
[2]	Guanghui WU, Jing WANG, Hairun XIE, Tuliang MA, Qiang MIAO, Jixin XIANG, Miao ZHANG. Data and knowledge-enabled intelligent aerodynamic design for civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(5): 531485-531485.
[3]	Yu ZENG, Hongbo WANG, Chengyue LIAN, Yixin YANG, Dapeng XIONG, Mingbo SUN, Weidong LIU. Applicability analysis of two improved methods of SST turbulence model [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730574-730574.
[4]	Qi WANG, Long WU, Zhen LIU, Jianxia LIU, Liang XIA. Topology optimization design of thermoelastic multi-configuration gradient lattice structures [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(23): 230367-230367.
[5]	Zhanfeng MENG. Design of sun-synchronous and repeating tracking condition elliptical lunar frozen orbits [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(18): 229926-229926.
[6]	Lizhuo DONG, Siqi ZHANG, Zhao ZHANG, Baohai WU. Prediction method of blade machining deformation driven by mechanism⁃data hybrid [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(13): 629037-629037.
[7]	Ximing CUI, Zhipeng QIU, Jia WEI, Chi ZHANG, Kai SONG, Zhe LI, Shupeng WANG. Data-driven method for characterization of structural steel surface stress of magnetic Barkhausen noise [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(8): 427237-427237.
[8]	JIANG Lijian, ZHAO Wenwen, CHEN Weifang, YAO Shaobo. Data-driven rarefied nonlinear constitutive relations based on rotation invariants [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(12): 126256-126256.
[9]	LI Tingwei, ZHANG Mang, ZHAO Wenwen, CHEN Weifang, JIANG Lijian. Machine learning method for correction of rarefied nonlinear constitutive relations [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524386-524386.
[10]	YU Min, LUO Jianjun, WANG Mingming. Real-time motion prediction of space tumbling targets based on machine learning [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(2): 324149-324149.
[11]	ZHANG Yizhi, CHENG Cheng, FAN Yitong, LI Gaohua, LI Weipeng. Data-driven correction of turbulence model with physics knowledge constrains in channel flow [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(3): 123282-123282.
[12]	WU Heng, LI Benwei, ZHANG Yun, YANG Xinyi. Dynamic model identification of starting process of a turbo-shaft engine based on QPSO-ELM [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(11): 322251-322261.
[13]	Wang Yi;Zhou Xingshe;Han Zhaoxuan. STUDY AND DESIGN OF EXECUTIVE SOFTWARE FOR DISTRIBUTED REAL-TIME CONTROL SYSTEMS [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 1990, 11(8): 348-353.