Existing satellite data receiving system fault location methods suffer from the difficulty in obtaining expert knowledge. A generative adversarial network (GAN) sequence method called GANseq is proposed in this paper. According to the feature of fault propagation, the receiving system was first divided into M signal processing unit (SPU) to form a SPU sequence ranked by signal processing order (SPO). The fault location issue then was decomposed into ranked M anomaly detection sub-problems, where the mth sub-problem was the detection of the top m SPUs’ joint state. State parameters GANomaly-based detector was employed in each sub-problem, forming a GAN sequence. The detection results of this sequence on all sub-problems were analyzed to locate fault SPU. The experiment result from practical receiving system shows that GANseq can not only achieve fault location from data-driven perspective, but also reduce fault alarm rate and enhance accuracy level of fault location.
WANG Zhengsheng
,
LI Yalin
,
ZHANG Hongqun
. Satellite data receiving system fault location based on GAN sequence[J]. Journal of University of Chinese Academy of Sciences, 2023
, 40(1)
: 109
-118
.
DOI: 10.7523/j.ucas.2021.0009
[1] 冯钟葵, 张洪群, 王万玉, 等. 遥感卫星数据获取与处理关键技术概述[J]. 遥感信息, 2008, 23(4): 91-97,75.DOI：10.3969/j.issn.1000-3177.2008.04.019.
[2] 朱杰, 林维夏, 赵现纲. 气象卫星数据接收远程故障智能诊断系统开发[C]//中国气象学会. 第35届中国气象学会年会论文集: S21卫星气象与生态遥感. 合肥, 2018: 267-268.
[3] 靳芳, 张洪群, 葛小青. 卫星接收故障诊断专家系统的研究[J]. 微计算机信息, 2009, 25(7): 107-108,99.
[4] 韦春龙. 卫星接收系统故障诊断专家系统的研究[J]. 信息网络安全, 2012(2): 81-83.DOI：10.3969/j.issn.1671-1122.2012.02.024.
[5] 陈丹, 胡涛, 王建涛, 等. 基于CBR和FTA的地面站接收系统故障诊断方法[J]. 太赫兹科学与电子信息学报, 2019, 17(2): 227-233.
[6] 申鸿烨. 基于监测点与自动化测试的接收系统故障诊断[J]. 控制工程, 2016, 23(3): 417-422.DOI：10.14107/j.cnki.kzgc.150486.
[7] 韩威, 路宽, 年昭华, 等. 遥感卫星接收系统故障诊断系统的研究[C]//第四届高分辨率对地观测学术年会论文集. 武汉, 2017: 1153-1165.
[8] 陈丹, 胡涛, 王建涛, 等. 基于故障树与BAM网络的卫星地面站接收系统故障诊断方法[J]. 信息工程大学学报, 2018, 19(3): 301-305.DOI：10.3969/j.issn.1671-0673.2018.03.009.
[9] 蒋超, 张政治. 基于扩展故障树和模糊Petri网的导航地面监测站故障诊断方法[C]//第十一届中国卫星导航年会论文集: S08测试评估技术. 成都, 2020: 78-81.
[10] 郎国伟, 周东方, 胡涛, 等. 基于遗传算法和神经网络的故障诊断研究[J]. 信息工程大学学报, 2017, 18(2): 140-142.DOI：10.3969/j.issn.1671-0673.2017.02.003.
[11] Akcay S, Atapour-Abarghouei A, Breckon T P. GANomaly: semi-supervised anomaly detection via adversarial training[C]//Computer-Vision-ACCV2018.Lecture Notes in Computer Science,2019,11363.DOI：10.1007/978-3-030-20893-6-39. https://arxiv.org/abs/1805.06725.
[12] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020,63(11):139-144.DOI：10.1145/3422622.
[13] 吴春志, 冯辅周, 吴守军, 等. 一种有效的不均衡样本生成方法及其在行星变速箱故障诊断中的应用[J]. 兵工学报, 2019, 40(7): 1349-1357.DOI：10.3969/j.issn.1000-1093.2019.07.003.
[14] Schlegl T, Seeböck P, Waldstein S M, et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery[C]//Information Processing in Medical Imaging. IPMI 2017. Lecture Notes in Computer Science, 10265. DOI：10.1007/978-3-319-59050-9-12.
[15] Donahue J, KrähenbüHl P, Darrell T. Adversarial feature learning[EB/OL]. (2017-04-03)[2020-09-10]. https://www.arxiv.org/abs/1605.09782v7.arXiv:1605.09782.
[16] Zenati H, Foo C S, Lecouat B, et al. Efficient GAN-based anomaly detection[EB/OL]. (2019-05-01)[2020-09-10]. https://arxiv.org/abs/1802.06222.arXiv:1802.06222.
[17] Patel A A. Hands-on unsupervised learning using python: How to build applied machiae learning solutions from unlabeled data[M]. Sebastopol, USA: O’Reilly, 2019: 222-232.
[18] Géron A. Hands-on machine learning with scikit-learn,keras, and TensorFlow:concepts, tools, and techniques to build intelligent systems[M]. Sebastopol, USA: O’Reilly, 2019.
[19] 周炯槃, 庞沁华, 续大我, 等. 通信原理[M]. 4版.北京: 北京邮电大学出版社, 2015.
[20] Chintala S. How to train a GAN? Tips and tricks to make GANs work[EB/OL]. (2020-03-05)[2020-05-30]. GitHub. https://github.com/soumith/ganhacks.
