Maintenance scheduling optimization based on reliability and prognostics information

Abstract

Maintaining a large fleet of aircraft can be very challenging due to the variety of aircraft models, ages, and operating environments. Usually, the maintenance activities are implemented in a few centered facilities with different levels of maintenance capabilities. For instance, the Air Force's Air Logistics Complexes (ALC) are responsible for maintaining the Air Force's aging aircraft fleets. Current static methods for maintenance planning are based on the long-established Programmed Depot Maintenance (PDM) interval method, which can result in schedule delays, low throughput, and aircraft availability shortfalls. The situations are further complicated due to the increasing age of aircraft, high operational demands, and overall lack of fiscal resources. This paper is to propose innovative condition-based maintenance scheduling methodologies by integrating complex data processing, feature extraction, prognostic algorithm, and maintenance scheduling optimization. The proposed framework of prognostic-based maintenance scheduling is able to provide tradeoff analysis in terms of key performance metrics such as command possession rate, cost, and capacity expansion. The optimized maintenance schedule based on fleet health status will lead to higher aircraft availability, lower unscheduled maintenance cost, and meeting the continuous improvement initiatives such as the transitioning from PDM-based maintenance to High Velocity Maintenance (HVM) paradigm. The research outcomes will lead to more predictable and efficient maintenance scheduling capability. A numerical example shows how the aircraft reliability and health information can be integrated into the maintenance scheduling and planning optimization.