融合多源异构数据的飞机故障诊断方法研究进展  

Research progress of aircraft fault diagnosis method integrating multi-source heterogeneous data

作　　者：马超[1] 邹子炀 顾正柏 赵树杰 MA Chao;ZOU Ziyang;GU Zhengbo;ZHAO Shujie(College of Aeronautical Engineering,Civil Aviation University of China,Tianjin 300300,China;AVIC General Huanan Aircraft Industry Co.,Ltd.,Zhuhai 519090,China)

机构地区：[1]中国民航大学航空工程学院,天津300300 [2]中航通飞华南飞机工业有限公司,珠海519090

出　　处：《航空工程进展》2025年第1期139-150,共12页Advances in Aeronautical Science and Engineering

基　　金：国家自然科学基金—民航联合基金重点项目(U2233207);工信部民机专项(20232k0345)。

摘　　要：随着飞机数字化程度的提高,飞机在全寿命周期内会产生大量的多源异构数据,这些数据为保障飞机的安全提供了重要支持。本文梳理了飞机全寿命周期内常见的数据源类型,包括初始适航设计数据、运营可靠性数据、运行维护数据以及机载设备数据等,结合不同数据源类型的数据特征,介绍了多源异构数据的融合应用措施,详细分析了数据融合技术历经的四个阶段。在此基础上,介绍了融合数据的故障诊断方法,并与传统单一数据来源的故障诊断分析方法对比,得出多源异构数据的融合应用能够更加准确地分析故障成因,起到辅助排故与维修性设计的作用,是飞机故障诊断中数据应用技术的发展趋势。With the improvement of the digitization degree of the aircraft,a large amount of multi-source and heterogeneous data will be generated throughout the full life-cycle of an aircraft,which plays a crucial role in ensuring its safety.This article reviews common types of data sources within the aircraft's life-cycle,including initial airwor⁃thiness design data,operational reliability data,operational maintenance data,and onboard equipment data.By combining the data characteristics of different data source types,the article introduces measures for the fusion appli⁃cation of multi-source heterogeneous data and provides a detailed analysis of the four stages that data fusion technology has undergone.On this basis,the fault diagnosis method of fusion data is introduced.Compared with the fault diagnosis analysis of traditional single data source,it is concluded that the fusion application of multi-source hetero⁃geneous data can analyze the fault causes more accurately,and play a role in assisting troubleshooting and maintain⁃ability design,which is the development trend of data application technology in aircraft fault diagnosis.

关 键 词：飞机 全寿命周期 多源异构 数据 故障诊断 

分 类 号：V267[航空宇航科学与技术—航空宇航制造工程] TP306.3[自动化与计算机技术—计算机系统结构]