导航卫星载荷分系统健康评估方法设计  

Design of Navigation Satellite Payload Subsystem Health Evaluation Method

作　　者：赵欣奕 刘蕾[1] 段思佳 仵博 ZHAO Xinyi;LIU Lei;DUAN Sijia;WU Bo(The 15th Research Institute,China Electronics Technology Group Corporation,Beijing 100083,China;Information Security Office of the Aerospace Systems Equipment Department,Beijing 100094,China)

机构地区：[1]中国电子科技集团第15研究所,北京100083 [2]航天系统部装备部信息保障室,北京100094

出　　处：《计算机测量与控制》2024年第4期322-327,共6页Computer Measurement &Control

基　　金：国防预研项目(GFZX03010105280203)。

摘　　要：面向下一代导航系统结合高中低轨构建导航星座的设想,随着遥测参数数量和种类的激增,针对传统健康评估方法面临的过往专家知识难以适用、故障机理储备难以覆盖全面的问题,提出了基于局部异常因子检测-贝叶斯网络结构学习的导航卫星载荷分系统健康评估方法;通过采集某卫星系统实际故障时间点前后数据,设计实验验证了局部异常因子检测方法能够以粗粒度正确输出单机级的健康状况;分析比较了3种评分函数下,贝叶斯结构学习的效率和模型的准确度;实验结果表明,当评分函数分别选为BDeuScore、K2Score以及BicScore时,学习到的模型对系统的健康评估准确度分别为87.4%、80.5%和85.2%;总结了局部异常因子检测-贝叶斯网络结构学习方法各自的不足,为导航卫星分系统健康评估方法提供了新方向和思路。Envisioning the construction of navigation constellations for the next generation navigation systems combining with high,medium,and low orbits,with the sharp increase in the number and types of remote sensing parameters,traditional health evaluation methods face the problem of insufficient coverage of past expert knowledge and fault mechanism reserves.To address this,a health evaluation method for navigation satellite payload subsystems based on Local Outlier Factor Detection and Bayesian Network Structure Learning is proposed.Through the collected data before and after actual fault occurrences in a satellite system,Experiments is designed and validated the ability of the Local Outlier Factor Detection method to accurately output the health status at a coarse-grained level.The efficiency and accuracy of the Bayesian Network Structure Learning were analyzed and compared using three scoring functions.Experimental results indicate that with scoring functions of BDeuScore,K2Score,and BicScore,the health assessment accuracy of the learned models on the system is 87.4%,80.5%,and 85.2%,respectively.it summarizes the shortages of the Local Outlier Factor Detection and Bayesian Network Structure Learning methods,and provides a new direction and idea for the health assessment of navigation satellite subsystems.

关 键 词：导航卫星 载荷分系统 健康评估 局部异常因子检测 贝叶斯网络结构学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]