Estimation of rotor and main bearing loads using artificial neural networks

Abstract

Wind energy is one of the most important technologies for a climate-neutral energy supply. However, the premature failure of wind turbines due to unknown loads leads to a reduction in competitiveness compared to other energy sources. Here, load monitoring systems can make a significant contribution to the prevention of such failures. Most load monitoring systems for wind turbines focus on strain signals of structural components as the tower, main shaft or the rotor blade root. Based on these signals, axial forces, torsion or bending moments, which are acting on these components, are calculated. But this provides only partial information about the complete load situation, as transverse forces are not considered. Other methods use simulation or measurement data to train artificial neural networks (ANN) to estimate damage-equivalent loads acting on a wind turbine. However, this approach is accompanied by a loss of information, because the individual load components are condensed to an equivalent. In this work a method is presented that enables a measurement of rotor and main bearing loads considering all their individual load components. For this purpose, an ANN is trained with elastic multibody simulation (eMBS) data. Based on displacement signals, acting rotor and main bearing loads are estimated. The results show that even with consideration of nonlinearities, including nonlinear stiffness curves and bearing clearances, an appropriate accuracy can be achieved using the method presented.

Scaling Challenges for Conical Plain Bearings as Wind Turbine Main Bearings

“…The producible torque is lowest for a still-standing turbine [11,12]. To assess the torque a turbine can produce for still-standing turbine blades an aero-elastic load calculation with a detailed elastic multibody simulation-model of a WT based on the works of Loriemi et al [27] with a generic rotor design was performed. The reference rotor has a diameter of 140 m. The resulting torque for different wind speeds and pitch angles is depicted in Figure 6.…”

Method to identify insufficient sub-models in MBS models of wind turbine drivetrains

“…The test bench MBS model for which the 𝑀𝑄𝑃𝑠 of individual sub-models were determined is derived from a system MBS model of the MaxCap WT [13], which prototype has been tested on the full-size test bench at CWD. To have a consistent behavior to the test setup, the test bench MBS model has been simplified by removing the rotor and tower sub-models as these components do not exist in the test bench setup.…”