航天器自主智能运维技术进展  

Progress in Autonomous Intelligent Maintenance Technologies for Spacecraft

作　　者：王坤朋[1] 杨文昊 李文博[2,3,4] 柴毅 姚娟[1] 黄晓峰 王彤[6] WANG Kunpeng;YANG Wenhao;LI Wenbo;CHAI Yi;YAO Juan;HUANG Xiaofeng;WANG Tong(School of Information Engineering,Southwest University of Science and Technology,Mianyang 621010,China;Beijing Institute of Control Engineering,Beijing 100094,China;National Key Laboratory of Space Intelligent Control,Beijing 100094,China;College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China;College of Automation,Chongqing University,Chongqing 400044,China;Beijing Institute of Spacecraft System Engineering,Beijing 100094,China)

机构地区：[1]西南科技大学信息工程学院,绵阳621010 [2]北京控制工程研究所,北京100094 [3]空间智能控制技术全国重点实验室,北京100094 [4]南京航空航天大学自动化学院,南京211106 [5]重庆大学自动化学院,重庆400044 [6]北京空间飞行器总体设计部,北京100094

出　　处：《宇航学报》2025年第2期215-231,共17页Journal of Astronautics

基　　金：国家重点研发计划(2021YFB1715000);国家自然科学基金项目(62373068,12150007)。

摘　　要：自主智能运维技术作为确保航天器在轨安全可靠、连续稳定运行的关键核心技术之一,是提升航天器自主生存能力和智能运行水平的重点发展方向。首先结合航天器的功能组成、运行环境及工作模式,深入梳理了航天器自主智能运维技术的内涵与独特特点。随后,从自主状态感知、自主故障诊断、自主评估预测、自主运维决策及自主学习更新5个关键维度,系统综述了该技术领域的理论研究现状与实际应用案例。最后,针对当前面临的运维人员不可达、先验知识不完备、资源配置不充分等挑战,提炼并展望了跨时空数据融合、可信任可解释诊断、知识迁移预测、云边协同决策及持续增量学习等未来发展趋势,为航天器自主智能运维技术的进一步创新与应用提供了有力指导。Autonomous intelligent operation and maintenance(O&M)technology is established as one of the essential core technologies that ensure the safe,reliable,and continuously stable operation of spacecraft in orbit.It signifies a vital development direction for enhancing the autonomous survival capability and intelligent operation level of spacecraft.Initially,the connotation and unique characteristics of autonomous intelligent O&M technology for spacecraft are explored by integrating the spacecraft′s functional composition,operational environment,and working modes.Subsequently,a systematic review of the current theoretical research status and practical application cases in this technology field is conducted,covering five key dimensions:autonomous state perception,autonomous fault diagnosis,autonomous assessment and prediction,autonomous O&M decision-making,and autonomous learning and updating.Finally,in light of the challenges posed by current technologies,such as the inaccessibility of O&M personnel,incomplete prior knowledge,and inadequate resource allocation,future development trends are refined and anticipated,including cross-spatiotemporal data fusion,trustworthy and explainable diagnosis,knowledge transfer for prediction,cloud-edge collaborative decisionmaking,and continuous incremental learning.These insights offer robust guidance for the ongoing innovation and application of autonomous intelligent O&M technology for spacecraft.

关 键 词：航天器 自主智能运维 自主状态感知 自主故障诊断 自主评估预测 自主运维决策 自主学习更新 

分 类 号：V448.2[航空宇航科学与技术—飞行器设计] TP277[自动化与计算机技术—检测技术与自动化装置]