Authors Marco Borsotti, Rudy R. Negenborn, Xiaoli Jiang
Date March 2025
DOI 10.2139/ssrn.5189581
Abstract
This paper presents a stochastic optimization model for predictive maintenance scheduling in offshore wind farms. The proposed model integrates probabilistic Remaining Useful Life (RUL) prognosis with mathematical optimization and Model Predictive Control (MPC) techniques to dynamically update maintenance decisions. Unlike conventional scheduling methods that rely on static age thresholds, our approach uses real-time prognostics to improve cost efficiency and reduce downtime. A case study on 50 wind turbines demonstrates that dynamically adapting maintenance schedules using prognostics reduces O&M expenses by 8.7%, primarily through significant reductions in downtime, compared to traditional methods.
Link to preprint: