Assessing the Welfare of Technicians during Transits to Offshore Wind Farms

Available decision-support tools rarely account for the welfare of technicians in maintenance scheduling offshore wind farms. This creates uncertainties, especially since current operational limits might make a farm accessible but vibrations from transits be unacceptable to technicians. We explore technician exposure vibration transit based on levels discomfort and likelihood seasickness occurring crew transfer vessels (CTVs). Vessel motion monitoring systems deployed CTVs operating North Sea sea-state data are used machine learning (ML) process model applied modelled proxy variables including composite weighted RMS acceleration (aWRMS) sickness incidence (MSI). The results revealed poor moderate performance predicting proxies selected evaluation criteria, raising possibility more relevant being needed improve performance. Therefore, this research presents framework an ML approach towards accounting wellbeing sailing decisions once highlighted limitations can addressed.