Human factors in the operation and maintenance of offshore wind farms

Current maintenance planning strategies and decision support tools used in the operations and maintenance of offshore wind farms rarely account for the welfare of technicians and their ability to do work upon arrival. This creates uncertainties especially since current operational limits might make a wind farm accessible but vibrations from transits might be unacceptable to technicians. The welfare of technicians is expressed by levels of discomfort and the likelihood of seasickness occurring from the vibrations felt on Crew Transfer Vessels (CTVs) in transit. To explore technician exposure to vibration in transit, acceleration data from vessel motion monitoring systems deployed on CTVs operating in the North Sea was synchronised with sea-state data from an operational oceanographic data service (Copernicus Marine Service). Processes of dimensionality reduction and machine learning were used to model the welfare of technicians from operational limits applied to modelled proxy variables including Composite Weighted RMS Acceleration (aRMS) and Motion Sickness Incidence(MSI).Model results revealed both satisfactory and moderate performance in predicting aRMS and MSI based on model evaluation criteria of R2(0.69 and 0.49) and root mean square error (0.06ms-2and 4%). The results of the models raise the possibility of more relevant variables needed to capture all of the information needed to achieve high predictive accuracy. The proposed model will have applications in maintenance planning for offshore wind farms, able to account for the well-being and the ability to work in technicians in sailing decisions.