Evaluation of Predictive Maintenance by Marginal Utility: A Case Study on Offshore Wind

This paper investigates the relationship between the benefits achieved by predictive maintenance implementation and the related costs incurred intentionally or not. Specifically, we seek to establish an evaluation method for predictive maintenance that includes prediction model performance, which will better indicate that a predictive maintenance strategy built on the model will succeed in providing benefits compared to a pre-existing maintenance strategy. This will help justifying the costs and complexities of implementing new maintenance procedures and ensure positive financial outcomes. We demonstrate this method with a case study based on scheduled maintenance of an offshore wind farm where a declarative modeling approach is used to simulate service costs and operations, while a deep learning model provides insights on imminent downtime events. The results of this case study show that predictive maintenance is only profitable under specific conditions, such as limited service resources and high prediction model performance, and a profitable performance threshold for the underlying model is obtained.