Modeling and prediction of remaining useful lifetime for maintenance scheduling optimization of a car fleet

Abstract

The remaining useful lifetime (RUL) is the time remaining until an asset no longer meets operational requirements. An accurate estimation of the RUL is central to prognostics and health management systems. However, the RUL of an asset is usually very difficult to estimate and to achieve in any industry. This is because the RUL strongly depends on manufacturing, the operating environment, and the observed condition monitoring. Here, we use physics-based approaches and data-driven approaches to predict the RUL of four essential components of a passenger car, namely engine, brake pads, springs, and tires. Our results show good agreement of both approaches. In addition, we develop a hybrid framework to generate a data set of RULs of a car fleet. This framework can be used to establish an optimal maintenance schedule for a car fleet, such as the fleet of a taxi company.