A hybrid approach of machine learning and expert knowledge for projection of aircraft operability

Abstract

Aircraft operational performance is a key driving factor to flight punctuality and airline profitability. The ability of a system to meet its operational requirements in terms of reliability, availability and costs is termed as ’Operability’. It is of high importance for aircraft manufacturers to project operability during the early stages of development of an aircraft in order to make trade-off studies. This paper proposes a hybrid approach of using machine learning and expert knowledge to aid the projection of aircraft operational performance during the early design stages. This approach aims to benefit from the huge amount of in-service data available from the current and past fleet of aircraft. Hence, machine learning techniques are used to learn how different technical issues and their associated maintenance activities impact aircraft operations. Expert knowledge is used to establish the default rules of the simulation model used for the operability projection. Results from machine learning are used to improve these rules allowing one to make holistic projections of the operational performance of future aircraft. This approach allows one to estimate the elapsed time in different operational states of an aircraft like flying, turn-around, etc. which can then be used to calculate different operability Key Performance Indicators (KPIs) like aircraft reliability and maintenance unavailability.

A Taxonomy of MBSE Approaches by Languages, Tools and Methods

“…Starting from identified limits and pitfalls of document-centric systems engineering, amongst others the scattering of information, the potential ambiguity in the descriptions, and the absence of a good possibility to perform verification and validation based on such documents, solutions have been investigated and MBSE has opened up promising avenues for systems engineers [1]. With no intent to be exhaustive, application domains of MBSE include railway [2], [3], nuclear plants [4], aircraft operability [5], drones [6], and lunar exploration [7].…”