Estimation of Wind Turbine Performance Degradation with Deep Neural Networks
Journal article, Peer reviewed
Published version
View/ Open
Date
2022Metadata
Show full item recordCollections
Original version
Mathew, M. S., Kandukuri, S. T. & Omlin, C. W. P. (2022). Estimation of Wind Turbine Performance Degradation with Deep Neural Networks. Proceedings of the European Conference of the Prognostics and Health Management Society, 7(1), 351-359. https://doi.org/10.36001/phme.2022.v7i1.3328Abstract
In this paper, we estimate the age-related performance degradation of a wind turbine working under Norwegian environment, based on a deep neural network model. Ten years of high-resolution operational data from a 2 MW wind turbine were used for the analysis. Operational data of the turbine, between cut-in and rated wind velocities, were considered, which were pre-processed to eliminate outliers and noises. Based on the SHapley Additive exPlanations of a preliminary performance model, a benchmark performance model for the turbine was developed with deep neural networks. An efficiency index is proposed to gauge the agerelated performance degradation of the turbine, which compares measured performances of the turbine over the years with corresponding bench marked performance. On an average, the efficiency index of the turbine is found to decline by 0.64 percent annually, which is comparable with the degradation patterns reported under similar studies from the UK and the US.