This paper presents a novel data-driven predictive maintenance scheduling framework for aircraft engines based on remaining useful life (RUL) prediction. First, a deep learning ensemble model is proposed to effectively predict aircraft engine RUL, including a one-dimensional convolutional neural network (CNN) and a bidirectional long short-term memory network with an attention mechanism (Bi-LSTM-AM). Second, we propose a Bayesian optimization method to optimize the hyperparameters in the deep learning ensemble model to further improve RUL prediction performance. As the aircraft engine RUL decreases over time and eventually triggers a maintenance alarm threshold. The maintenance scheduling task is initiated after the aircraft engine maintenance alert threshold has been triggered. To effectively implement the maintenance scheduling plan, we develop a novel and effective mixed-integer linear programming (MILP) model to cope with aircraft engine maintenance scheduling, which aims to minimize the maximum maintenance time. Finally, experimental results show that our proposed data-driven predictive maintenance scheduling framework can monitor the running status of aircraft engines in real time and reduce their maintenance time.

This article revisits the optimization problems of age-based replacement models for exponential failure distributions. First, we show the steps how an age replacement time goes to an infinite value when the lifetime of a unit has an exponential distribution, and then, we give two discussions of possible replacement times, by introducing a new concept of cost named as deviation cost per unit of time between replacement and failure. Second, similar discussion is given for a random replacement model when the age replacement time is a random variable with a uniform distribution. Third, the models of age-based replacement first and last with deviation costs are discussed when a random replacement is taken into account for an age replacement model. Numerical examples are illustrated to show the results of the analytical discussions. Finally, necessary proofs are provided in the Appendixes.