This version is available at https://strathprints.strath.ac.uk/28017/ Strathprints is designed to allow users to access the research output of the University of Strathclyde. Unless otherwise explicitly stated on the manuscript, Copyright © and Moral Rights for the papers on this site are retained by the individual authors and/or other copyright owners. Please check the manuscript for details of any other licences that may have been applied. You may not engage in further distribution of the material for any profitmaking activities or any commercial gain. You may freely distribute both the url (https://strathprints.strath.ac.uk/) and the content of this paper for research or private study, educational, or not-for-profit purposes without prior permission or charge.Any correspondence concerning this service should be sent to the
II. INTRODUCTIONEnsuring reliability in the wind energy industry is often extremely difficult due to the stochastic nature of the resource, the isolated locations where the plants are built and the complex forces which interact in unexpected and damaging ways 1 . These conditions have led to high failure rates for various different components in the turbine with the gearbox being the most problematic for various reasons 2,3 . Figure 1 shows the failure frequency and downtime of different wind turbine components. Whilst the failure rate is lower than most components, the downtime is far greater. The component itself is expensive so repairs or replacements within the operational lifetime will impact the operational economics of the wind turbine. An £800 bearing could fail, leading to the replacement of a £300,000 gearbox with a £50,000 per day hired crane, excluding the costs incurred from downed electricity production 5,6 . These problems will be exacerbated when more wind farms are located offshore 7 due to greater forces, more isolated conditions and increased access costs. One method to improve reliability is to monitor the condition of components in the wind turbine using sensors which measure different variables. Using this data with statistical methods, the current and future condition of components may be accurately assessed 8 . This will allow decisions on when maintenance or replacements occur to be made with a higher degree of certainty. According to McMillan and Ault, it is envisioned that this will reduce failure rates, allow an efficient maintenance regime to be established and reduce overall costs that are incurred due to downed wind turbines 9 . The gearbox is an ideal component to monitor for several reasons. The gearbox is responsible for many of the maintenance costs due to repairs, replacements and turbine downtime.There are many different indicators of its condition, such as abnormal vibrations and acoustic emissions 10,11 . However in a wind turbine nacelle these indicators can be influenced by other components such as the generator and wind loads. It is believed that these factors will reduce the overall accuracy of vibration and acoustic emission analysis. Another majo...