Machine learning based parameter estimation for an adapted finite element model of a blade bearing test bench

Abstract

Improving the reliability of blade bearings is essential for the safe operation of wind turbines. This challenge can be met with the help of virtual testing and digital-twin driven condition monitoring. For such approaches, a precise digital representation of the blade bearing and its test bench is an essential prerequisite. However, various factors prevent the capture of all parameters of the blade bearing and the associated test bench. Parameters such as bearing preload, rolling element and raceway dimensions, and bolt preload during assembly vary with each bearing and test bench setup. As these parameters cannot be measured directly, an alternative solution is required. This article presents a methodology to efficiently estimate non-measurable parameters of the test bench using a combination of model-based and data-driven approaches, improving the detailed and accurate virtual testing of blade bearings. It must be ensured to enable the fastest possible, most computationally efficient estimation of parameters during virtual testing or condition monitoring. The developed methodology is evaluated using the example of bolt preload on the test bench. By employing a random forest model and the strain gauge measurements attached to the blade bearing, the bolt preload parameters are estimated. The results demonstrate that the accuracy of the digital model of the blade bearing test bench is improved by up to 11 % in three out of four test bench setups. The great improvement in the accuracy of the digital model highlights the effectiveness of the proposed methodology in enhancing virtual blade bearing testing and digital-twin driven condition monitoring.