Module Failure Feature Detection by Cluster Analysis for Fleets of Civil Aircraft Engines ⁎This research is funded by the Aerospace Technology Institute (ATI) and InnovateUK. Issue 1 (2021)

• Record Type: Journal Article
• Authors: Zhou, Hang; Brintrup, Alexandra; Parlikad, Ajith Kumar
• Is Part Of: IFAC-PapersOnLine. Volume 54:Issue 1(2021)
• Page Start: 31
• Page End: 36
• Publication Date: 2021
• Subjects: cluster analysis -- unsupervised learning -- aerospace engineering -- maintenance; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2021.08.154
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: During the operation of airplanes in the aviation industry, the stochastic environment in which the airplanes are being operated creates high complexity in planning the fleet overhauls for the aircraft engines. In order to perform efficient and cost-effective overhauls, the maintenance approach is to exchange the modules that caused the removal of engines from airplanes. Typical civil aviation engine consists of eight modules, in order to avoid disturbance for engine end users (airlines), all the modules should be available and well planed in any period of time window. This paper aims to provide a module planning solution based on the fleet operational history of aircraft engines, in order to cluster the engine performances into featured zones for overhaul module demand estimation.