Model-free dynamic estimation of fore-aft and side-to-side wind turbine tower deflections

Abstract

This paper presents a novel approach for estimating the fore-aft and side-to-side displacements in wind turbines. The proposed methodologyexploits the capability of Recurrent Neural Networks (RNNs) to capture complex temporal relationships, making them suitable for modelingthe dynamic behavior of the deflections. Unlike traditional analytical estimators, the proposed solution learns the system dynamics directlyfrom operational data, eliminating the necessity for high-fidelity mathematical modeling. In contrast to previous data-driven methods, thisapproach not only considers the dynamics in the data through recurrent structures, but also provides instantaneous deflections estimates,which is critical for real-time load monitoring and control applications. This real-time capability, combined with the dynamic nature of theRNN structure, advances the field by addressing both accuracy and temporal responsiveness in estimation. Based on a meticulous analysis ofthe available signals, a minimum common set of input variables present in the wind turbine control loop is determined by carrying out a correlationanalysis using Spearman’s coefficients and a frequency domain analysis in each of the system’s operating regions. Additionally, Hurstexponents are used to evaluate the persistence of the target variable, providing insights into the conditions under which a RNN estimator outperformsa static neural network estimator. The data used in this study has been generated from the certified simulator FAST (Fatigue,Aerodynamics, Structures, and Turbulence). The results are contrasted with the ones obtained using a technique recently published andexperimentally validated. They demonstrate the effectiveness of the estimators in reconstructing the oscillations throughout the wind turbine’soperating range using only a few input signals.