We studied how stationary the long-term damage estimates are when based on only short periods of measurement in offshore wind turbines. Using eight years of real data, we compared many one‑year measurement windows and showed that results can differ strongly depending on which year is used, even when current uncertainty methods suggest high confidence. So short measurements may not represent long-term behaviour, if proper conditioning to environmental and operational conditions is not done.

This study proposes a random-forest-based machine learning (ML) model for fatigue life prediction of offshore wind turbine monopile foundations compared to traditional approaches, using long-term strain data from turbines in the Belgian North Sea. This study shows that the ML model predicts the fatigue life of monopile foundations more reliably when only short-term measurements are available, whereas for longer monitoring periods of greater than 12 months, simpler binning methods perform equally well.