基于残差网络的航天器测控系统诊断  

Fault diagnosis of spacecraft tracking telemetry andcontrol systems based on residual network

作　　者：魏轩 慕晓冬 曾昭菊 刘伟强 李思凡 WEI Xuan;MU Xiaodong;ZENG Zhaoju;LIU Weiqiang;LI Sifan(Combat Support College,Rocket Force University of Engineering,Xi’an 710025,China;Xi’an Satellite Control Center,Xi’an 710025,China)

机构地区：[1]火箭军工程大学作战保障学院,西安710025 [2]西安卫星测控中心,西安710025

出　　处：《兵器装备工程学报》2023年第3期254-260,共7页Journal of Ordnance Equipment Engineering

摘　　要：针对由于空间环境复杂,航天器遥测信号伴随大量噪声,直接利用原始遥测信号进行故障诊断导致准确率不高的问题,提出了一种基于主成分分析(principal component analysis, PCA)和残差网络(pesidualnetwork, ResNet)的航天器测控系统故障诊断方法。将航天器测控系统遥测信号通过PCA降噪后生成灰度图;将图像输入残差网络提取深层次的特征;利用分类器实现航天器测控系统的故障诊断。结果表明,该方法的诊断准确率达到95.34%,高于其他诊断模型,可用于航天器测控系统的实际故障分类。Due to the complex space environment,spacecraft telemetry signals are accompanied by a large amount of noise,and the accuracy of fault diagnosis is low by directly using the original telemetry signals.In this view,this paper proposes a fault diagnosis method for spacecraft tracking telemetry and control(TT&C)systems based on principal component analysis(PCA)and residual network(ResNet).Firstly,grayscale images are generated by denoising the telemetry signals of the spacecraft TT&C system through PCA.Secondly,the images are input into the residual network to extract deep-level features.Finally,the Softmax classifier is used for classification to realize the fault diagnosis of the spacecraft TT&C system.The research results show that the diagnostic accuracy of the method proposed in this paper reaches 95.34%,which is higher than other diagnostic models,and the method can be used for actual fault classification of the spacecraft TT&C system.

关 键 词：航天器 故障诊断 深度学习 主成分分析 残差网络 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]