EURO 2025 Leeds
Abstract Submission

1575. Data Envelopment Analysis of Aircraft Reliability and Preventive Maintenance Plan

Invited abstract in session WB-60: DEA applications in Transportation, stream Data Envelopment Analysis and its applications.

Wednesday, 10:30-12:00
Room: Western LT

Authors (first author is the speaker)

1. Young Chun
College of Business, Louisiana State University
2. Seong-Jong Joo
Operational Sciences, Air Force Institute of Technology

Abstract

Using the maintenance data of 26 airplanes collected during a 38-month period, we consider various prediction models to estimate the failure rate of military aircraft per flight. Based on the estimated reliability of each aircraft, we then rank the 26 aircraft via the data envelopment analysis (DEA).
Specifically, we focus on the failure patterns of a complex electronic and armament system in the military aircraft in the US Air Force. As soon as the system fails, the aircraft aborts a mission and returns to the Air Force base immediately. Under the current reactive or breakdown maintenance plan, the mission-critical system is repaired or replaced only when it fails. In practice, it would be more cost-effective to replace the complex system on a regular basis even before it breaks down. Under the preventive or planned maintenance plan, the system is replaced after a certain number of flights.
The number of flights or sorties is a discrete variable, and we propose a discrete-time survival model and analyze the failure patterns of the system. We fit the military aircraft maintenance data and flight records into a discrete-time Weibull model and estimate its two parameter values. The Weibull model is then used to develop a preventive maintenance plan that minimizes the expected total cost per sortie in the renewal-reward process of system failures.

Keywords

Status: accepted


Back to the list of papers