A condition-based maintenance policy and input parameters estimation for deteriorating systems under periodic inspection

We study the problem of proposing Condition-Based Maintenance policies for machines and equipments. Our approach combines an optimization model and input parameters estimation from empirical data. The system deterioration is described by discrete states ordered from the state “as good as new” to the state “completely failed”. At each periodic inspection, whose outcome might not be accurate, a decision has to be made between continuing to operate the system or stopping and performing its preventive maintenance. This decision-making problem is discussed and we tackle it by using an optimization model based on the Dynamic Programming and Optimal Control theory. We then explore the problem of how to estimate the model input parameters, i.e., how to adequate the model inputs to the empirical data available. The literature has not explored the combination of optimization techniques and model input parameters, through historical data, for problems with imperfect information such as the one considered in this work. We develop our formulation using the Hidden Markov Model theory. We illustrate our framework using empirical data provided by a mining company and the results show the applicability of our models. We conclude by pointing out some possible directions for future research on this field.