Optimal prognostic distance to minimize total maintenance cost: The case of the airline industry

Prognostic distance is the time interval needed to gather information to predict a future failure and to take appropriate action. Within the calculated prognostic distance, there is an increased accuracy of a system׳s failure prediction. In such situations, finding an optimal prognostic distance is important to decrease total cost related to the maintenance function. Therefore, this paper considers the problem of finding an optimal length of the prognostic distance to be used in the prognostic health management (PHM) system to minimize the total maintenance cost. By characterizing the relationships of various cost components to the length of the prognostic distance, a general expression for the total maintenance cost is developed as a function of the prognostic distance and the generic constraints are identified. In view of the difficulty to develop an exact form of the mathematical functions and/or a closed form solution for the formulated optimization problem, a practical procedure to find an optimal or near-optimal prognostic distance is then described and illustrated with a case study from the airline industry. The proposed model and practical procedure use all gathered operational and cost parameters from the historical data to determine a near optimal prognostic distance through simulation or an appropriate optimization technique. Our proposed approach leads to a better interpretation of PHM results and thus helps translate PHM information to maintenance actions and policies which can assist in minimizing life cycle costs and maximizing the availability across an airline network.