Using Prognostics and Health Monitoring Data in Load Distribution Optimization Problems

The use of Remaining Useful Life (RUL) predictions as a decision support tool has increased in recent years. The RUL predictions can be obtained from Prognostics and Health Management (PHM) systems that monitor the health status and estimate the failure instant of components and systems. An example of a decision-making problem that can benet from RUL predictions is the load distribution problem, which is a common problem that appears in many industrial applications. It consists in dening how to distribute a task among a set of components. In this paper, a model to solve load distribution optimization problems is proposed. The proposed model considers the RUL prediction of each component in its formulation. Also, the proposed model assumes that the predicted RUL of each component is a function of the load assigned to that component. Thus, it is possible to distribute the load to avoid multiplecomponents to fail in a short interval. An approach based on the MMKP (Multiple-choice Multidimensional Knapsack Problem) is adopted. The proposed model nds a load distribution that minimizes the operational cost subject to a maintenance personnel capacity constraint, i.e. there is a maximum number of components that can be simultaneously on repair. A numerical case study considering a gas compressor station is presented to illustrate the application of theproposed model.