Wind turbine gearbox forecast using Gaussian process model

Abstract

For wind farms, wind turbine condition monitoring is important to reduce maintenance costs and improve the competitiveness in the electricity market, particularly for offshore wind farms. This paper seeks to establish wind turbine gearbox temperature model under the normal working state using Gaussian process, the forecast and evaluation of temperature is also described. Within the Bayesian context, the paper aims to training Gaussian process, using the maximum likelihood optimized approach to find the optimal hyperparameters. For large-scale regression tasks, a novel method using Cholesky decomposition to avoid ill-conditioned matrix is described. Another method using matrix caching to speed up the inverse of matrix calculation is proposed. In addition, the optimized Gaussian model is used to predict the gearbox validation data and compare with SVM (support vector machine) and BPNN (neural network) this two methods. By comparing the simulation results, Gaussian process gearbox temperature model demonstrates higher prediction accuracy. The model is a valuable object for condition monitoring.

Using Gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals

“…[16] An essential tool when planning maintenance strategies is information about the probabilities of component failures and Gaussian process (GP) models can be an effective in this regard. GP analysis is a non-parametric machine [6], that is relatively simple conceptually and for this reason is finding favor in a number of application areas including wind farm O&M, see for example [7] and [8].…”