基于动态不确定因果图的航天器故障诊断方法  

Dynamic Uncertain Causality Graph-based Methodology for Spacecraft Fault Diagnosis

作　　者：邱瑞[1] 姚全营 刘鹏[1] 张湛 刘超 涂语恒 QIU Rui;YAO Quanying;LIU Peng;ZHANG Zhan;LIU Chao;TU Yuheng(Beijing Institute of Spacecraft System Engineering,Beijing 100094,China;Beijing Yutong Intelligence Technology Co.,Ltd.,Beijing 100084,China;Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China;School of Computer Science,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京空间飞行器总体设计部,北京100094 [2]北京予同智能科技有限公司,北京100084 [3]清华大学计算机科学与技术系,北京100084 [4]北京理工大学计算机学院,北京100081

出　　处：《航天器工程》2024年第5期9-14,共6页Spacecraft Engineering

摘　　要：针对航天器智能化故障诊断的问题,基于动态不确定因果图(Dynamic Uncertain Causality Graph,DUCG)构建诊断模型,克服了基于规则的方法、数据驱动方法存在的诊断正确率低、数据依赖程度高、可解释性差等问题。DUCG基于领域专家的经验知识、以图形化的方式表达航天器遥测参数与可能的故障之间的不确定性知识,不依赖于已有的故障数据,具有诊断正确率高、可解释性强等特征。使用DUCG构建包含42个故障、129个遥测参数的诊断模型,试验结果表明模型的准确率为100%。This Paper addresses the challenge of intelligent fault diagnosis in spacecraft by introducing a diagnostic model based on the Dynamic Uncertain Causality Graph(DUCG).This model surpasses traditional rule-based method and data-driven approaches,which often suffer from low diagnostic accuracy,high data dependency and insufficientinterpretability.DUCG leverages domain experts'experiential knowledge and graphically represents the uncertain relationships between spacecraft telemetry parameters and potential faults.It operates independently of existing fault data,offering high diagnostic accuracy and enhancedinterpretability.The DUCG-basedmodel encompasses 42 faults and 129 telemetry parameters.Experimental validations of the model demonstrat a 100%accuracy rate in fault diagnosis.

关 键 词：航天器 故障诊断 动态不确定因果图 知识表达 概率推理 

分 类 号：V474[航空宇航科学与技术—飞行器设计] TP391[自动化与计算机技术—计算机应用技术]