A Novel Predictive Selective Maintenance Strategy Using Deep Learning and Mathematical Programming

Abstract

Many systems are required to perform a series of missions with finite breaks between successive missions. For such systems, one of the most widely used maintenance strategies is selective maintenance (SM). Under certain maintenance constraints, the SM problem (SMP) consist in selecting an optimal subset of feasible maintenance actions to maximize the system reliability for the upcoming mission. Almost all SMP models proposed in the literature are focused on traditional physics-based reliability models, where component lifetimes can be modeled using a stochastic process. With the application of new technologies such as wireless sensors and Industrial Internet of Things (IIoT), and the recent advancements in Deep Learning (DL) algorithms for prognostics, predictive maintenance based on data-driven methods has become a very popular maintenance strategy. These data driven methods have shown extreme accuracy in predicting remaining useful life (RUL) of components and systems. The goal of this paper is to introduce a predictive selective maintenance strategy that can be used to solve complex and relatively large multi-component systems. A DL algorithm will be used to estimate the probability that each component will successfully complete the upcoming mission, a selective maintenance optimization model will then be used to identify the maintenance actions that will maximize the system reliability. An efficient solution method is devised to solve the resulting complex optimization problem. The NASA C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset is used to train and evaluate the DL algorithm. The numerical experiments carried out show that the proposed novel predictive maintenance strategy is accurate and yields valid decisions.