基于回归神经网络的卫星信号监测系统健康状态评估模型  

Health Assessment Model for Satellite Signal Monitoring System Based on Regression Neural Network

作　　者：高丽 李洋 田宇[1,2] 翟建勇 麻军伟[1,2] 张伟 GAO Li;LI Yang;TIAN Yu;ZHAI Jianyong;MA Junwei;ZHANG Wei

机构地区：[1]中国电子科技集团公司第二十研究所,西安710068 [2]陕西省组合与智能导航重点实验室,西安710068

出　　处：《现代导航》2024年第4期249-253,267,共6页Modern Navigation

摘　　要：卫星信号地面监测系统无人值守、长期运行的特点,以及设备数量众多、交互复杂的现实状态使得对监测系统健康状态进行评估至关重要。通过对监测系统运行数据进行合理设计和处理,设计并训练回归神经网络学习挖掘监测系统运行数据的内在规律,从而实现监测系统全生命周期内健康状态评估预测,对运行数据表达出系统出现故障隐患的状态进行识别,达到故障预警的效果,从而将监测系统的事后运维方式提前至事前运维,减少监测系统故障发生率,有利于提高监测系统稳定可靠能力。With the characteristics of unmanned,long-term operation,a large number of devices and complex interactions,it is crucial to assess the health of ground-based monitoring system for satellite signal monitoring system.By reasonably designing and processing a large amount of operational data from the monitoring system,a regression neural network to learn is designed and trained and the inherent laws of the monitoring system’s operation data is explored.The enables intelligent monitoring and fault warning throughout the entire lifecycle of the monitoring system,shifting the maintenance mode from post-event to pre-event,reducing the occurrence of monitoring system failures,and improving the stability and reliability of the system.

关 键 词：地面监测系统 健康状态预测 回归神经网络 

分 类 号：TN953[电子电信—信号与信息处理]