A Framework for Reducing O&M Costs at Offshore Wind Farms

Abstract Offshore wind farm operations and maintenance costs are estimated at approximately 30% of its lifetime costs, reducing this share is key for facilitating further deployment of offshore wind developments. This paper presents a three-stage data-driven framework which can be applied to an operational offshore asset. The framework is applied to a case study of an operational offshore wind farm in the UK. In stage 1 of the framework a data analysis of maintenance logs and monitoring data reveals that power converter failures are most costly to the wind farm operator due to high revenue losses associated with turbine downtime. In stage 2 of the framework, artificial neural network-based failure prediction models are applied to the power converters. The models are evaluated using a novel scoring function which estimates a potential 42% reduction in maintenance costs from converter failures. Finally, in the third stage a maintenance scheduling model designed to both minimise the costs of performing maintenance and revenue losses due to maintenance downtime, is presented. This work predicts that up to 50% cost reductions compared to the baseline can be achieved by implementing the scheduling model. The data-driven techniques in this framework offer a promising route to reducing operations and maintenance costs further facilitating the deployment of offshore renewable energy assets.