Affiliation of Author(s):民航学院
Journal:PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART G-JOURNAL OF AEROSPACE ENGINEERING
Key Words:Aeroengine generative adversarial networks Weibull distribution reliability
Abstract:Evaluating the reliability of aeroengines with few or zero failures through the use of the Weibull distribution has become a key problem in aviation, as the difficulty of obtaining sufficient sample sizes of monitoring data limits the reliability of evaluations. This paper aims to solve this problem by using generative adversarial networks to generate aeroengine condition monitoring data and increase the volume of usable data. The experimental results show that after a large number of network training epochs, the generated data can reflect the regularity of empirical monitoring data. The relationship between monitoring parameters and Weibull distribution parameters is determined, the generated data are used to estimate Weibull parameters, and the Weibull distribution reliability function for aeroengines is established. The results indicate that the combined use of generative adversarial networks and the Weibull distribution reliability function can indeed solve the problem of limited data volume, and that this method can improve the accuracy of aeroengine reliability assessment. The effectiveness of the proposed method is verified by analyzing monitoring data and time on wing data of 30 aeroengines, calculating engine reliability, and comparing the results with those yielded from the generated data.
ISSN No.:0954-4100
Translation or Not:no
Date of Publication:2019-12-01
Co-author:付强,Yan, Xiaojing
Correspondence Author:付强,wanghuawei