Unsupervised learning framework for large-scale flight data analysis of cockpit human machine interaction issues
Abstract
As the level of automation within an aircraft increases, the interactions between the pilot and autopilot play a crucial role in its proper operation. Issues with human machine interactions (HMI) have been cited as one of the main causes behind many aviation accidents. Due to the complexity of such interactions, it is challenging to identify all possible situations and develop the necessary contingencies. In this thesis, we propose a data-driven analysis tool to identify potential HMI issues in large-scale Flight Operational Quality Assurance (FOQA) dataset. The proposed tool is developed using a multi-level clustering framework, where a set of basic clustering techniques are combined with a consensus-based approach to group HMI events and create a data-driven model from the FOQA data. The proposed framework is able to effectively compress a large dataset into a small set of representative clusters within a data-driven model, enabling subject matter experts to effectively investigate identified potential HMI issues.
Degree
M.S.A.A.
Advisors
Hwang, Purdue University.
Subject Area
Aerospace engineering|Information science
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.