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.
作者
邱瑞
姚全营
刘鹏
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)
出处
《航天器工程》
CSCD
北大核心
2024年第5期9-14,共6页
Spacecraft Engineering
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
spacecraft
fault diagnosis
Dynamic Uncertain Causality Graph(DUCG)
knowledge expression
probabilistic inference
