Modeling Wear in Cylinder Liners

We present and discuss a stochastic model describing the wear process of cylinder liners in a marine diesel engine. The model is based on a stochastic differential equation, and Bayesian inference is illustrated. Corrosive action and measurement error, both quite negligible, are modeled with a Wiener process whereas a jump process is used to describe the contribution of soot particles to the wear process. The model can be used to forecast the wear process and, consequently, plan condition‐based maintenance activities. In the paper, we provide a critical illustration of the mathematical and computational aspects of the model. We propose a strategy that, implemented for simulated and real data, allows for stable parameter estimation and forecasts.