Transferability of Operational Status Classification Models Among Different Wind Turbine Types

Abstract

A detailed understanding of wind turbine performance status classification can improve operations and maintenance in the wind energy industry. Due to different engineering properties of wind turbines, the standard supervised learning models used for classification do not generalize across data sets obtained from different wind sites. We propose two methods to deal with the transferability of the trained models: first, data normalization in the form of power curve alignment, and second, a robust method based on convolutional neural networks and feature-space extension. We demonstrate the success of our methods on real-world data sets with industrial applications.

A Comprehensive Review of Artificial Intelligence and Wind Energy

“…Combinations with other techniques are common to improve performance, such as with Decision Trees [25,26] [113,114] and R 2 adjustment [115,116] are also applied, together with simulations [117][118][119], prototypes [120,121] and online classification systems [122,123]. It is not uncommon to compare different techniques to decide the best choice [124,125]. Comparisons found on the literature are respect to data mining [126] Bayesian classification [127] and other mathematical models [128].…”