民用飞机健康诊断大数据应用研究  

A Study on the Application of Big Data Technologies for Civil Aircraft Health Diagnosis

作　　者：余汇[1] 唐大鹏[1] 姚斌[1] YU Hui;TANG Dapeng;YAO Bin(Shanghai Aircraft Design and Research Institute,Shanghai 201210,China)

机构地区：[1]上海飞机设计研究院,上海201210

出　　处：《民用飞机设计与研究》2018年第3期82-86,共5页Civil Aircraft Design & Research

摘　　要：该文对面向飞机健康诊断的几种大数据技术进行了综述。并行聚类分析方法可以抽取飞机维护系统并行计算机的基本特征,形成飞机各系统历史数据的抽象计算模型;而针对全机状态监控参数中如何从大量飞机参数中挖掘出有价值的信息问题,参数场域挖掘技术发挥了很大的作用;然而在实际应用过程中,经常会遇到多种复杂的故障,这些故障通常具有复杂的非线性关系,而要确定这些非线性相关规则,需要依托大数据技术确定相关的关系;而对于由某一部件失效形成飞机级联故障的链式效应,可利用可视化数据挖掘技术,描述故障数据,结合人类视觉感知能力,加强数据结果处理。The article makes a review of big data technologies in civil aircraft health diagnosis. Parallel clustering analysis could get the basic characteristic of parallel computer to form a computing module of the historical data. The parameter field technology plays an important role in finding valuable parameters in a large number of aircraft parameters. In the actual application process, we will meet with all kinds of complex faults expressed by nonlinear functions. In order to make sure the nonlinear functions, the big data will be used to find out the quantization rela-tionships. For the cascade failure caused by some part’s failure,visualization data mining is used to figure the da-ta, combined with human sense of vision to reinforce the result of data mining.

关 键 词：飞机 健康诊断 大数据 聚类分析 数据挖掘 

分 类 号：V247.5[航空宇航科学与技术—飞行器设计]