A feasibility study into prognostics for the main bearing of a wind turbine

Abstract

Maintenance for wind turbines, particularly offshore turbines, presents a significant cost component to wind farm operators. The main bearing, which supports the low-speed shaft, is one of the major wind turbine system components. Since maintenance is confined to suitable weather windows, which are unpredictable, there is a need for decision support tools to ensure that maintenance is carried out in a timely way, but also at minimum cost and with minimum turbine downtime. This paper presents a methodology for the estimation of the remaining useful life (RUL) of the main bearing for a commercial wind turbine. A residual model is used to highlight potentially faulty behaviour, which is then post processed to provide a suitable signal for extrapolation using particle filters. The RUL is then effectively specified as a probability distribution which narrows as the failure point is approached, providing an estimate of RUL and a confidence measure. Our results suggest that RULs beyond 30 days can be reasonably estimated.