摘要
随着飞机飞行安全保障问题的突出和单机寿命监控技术的发展,机群飞行寿命的智能化、精细化管理成为重点关注的问题。针对维修规划和飞行训练规划这两大机群寿命管理中的关键要素,首先基于飞机结构实时健康状态物理信息,以最大化维修资源利用率和机群保有率等为规划目标,以每架飞机结构剩余寿命、同时维修能力等为约束,建立了数字孪生驱动的维修计划规划模型;其次基于寿命损耗信息,以关键部位的寿命损耗平衡、剩余使用寿命等为规划目标,飞机维修时刻、飞行训练任务等为约束,建立了数字孪生驱动的飞行训练规划模型。最后通过整合上述模型,形成了一套机群寿命的高保真、精细化管理方法,并通过构造机群数据展示了该管理方法的实际工程应用。
With the prominence of aircraft flight safety guarantee and the development of single aircraft life monitoring technology,the intelligent and meticulous management of aircraft fleet life has become a key concern.This paper ad-dresses the maintenance planning and flight training planning,the two key elements in the life management of fleet.Firstly,based on the physical information of real-time health status of aircraft structures,a maintenance planning model driven by digital twins is established with the planning objective of maximizing the utilization rate of maintenance resources and fleet retention rate and the constraints of the remaining life and simultaneous maintenance ability of each aircraft structure.Secondly,based on the life loss information,a digital twin-driven flight training planning model is established with the life loss balance and remaining service life of key parts as planning objectives,and the mainte-nance time and flight training tasks of each aircraft as constraints.By integrating the above models,a set of high-fidelity and refined management method of cluster life is formed,and the practical engineering application of this man-agement method is demonstrated by constructing cluster data.
作者
顾宇轩
郭聪
黄蕾
董一飞
董宏达
邓智伦
GU Yuxuan;GUO Cong;HUANG Lei;DONG Yifeil;DONG Hongda;DENG Zhilun(AVIC Shenyang Aircraft Design and Research Institute,Shenyang 110000,China;Key Laboratory of Digital Twin for Aircraft Structural Strength in Liaoning Province,Shenyang 110000,China;School of Mechanics and Aerospace Engineering,Dalian University of Technology,Dalian 116024,China)
出处
《航空学报》
北大核心
2025年第19期130-139,共10页
Acta Aeronautica et Astronautica Sinica
基金
国防基础科研计划(JCKY2021205B003)。
关键词
数字孪生
机群管理
健康监控
非支配排序遗传算法
机群寿命
digital twins
fleet management
health monitoring
non-dominated sorting genetic algorithms
fleet life
