Preprints
https://doi.org/10.5194/wes-2021-84
https://doi.org/10.5194/wes-2021-84

  17 Sep 2021

17 Sep 2021

Review status: this preprint is currently under review for the journal WES.

Model updating of a wind turbine blade finite element beam model with invertible neural networks

Pablo Noever-Castelos1, David Melcher2, and Claudio Balzani1 Pablo Noever-Castelos et al.
  • 1Leibniz University Hannover, Institute for Wind Energy Systems, Appelstr. 9A, Hanover, 30167, Germany
  • 2Fraunhofer IWES, Fraunhofer Institute for Wind Energy Systems, Am Seedeich 45, 27572 Bremerhaven, Germany

Abstract. Digitalization, especially in the form of a digital twin, is fast becoming a key instrument for the monitoring of a product's life cycle from manufacturing to operation and maintenance, and has recently been applied to wind turbine blades. Here, model updating plays an important role for digital twins, in the form of adjusting the model to best replicate the corresponding real-world counterpart. However, classical updating methods are generally limited to a reduced parameter space due to low computational efficiency. Moreover, these approaches most likely lack a probabilistic evaluation of the result.

The purpose of this paper is to extend a previous feasibility study to a finite element beam model of a full blade, for which the model updating process is conducted through the novel approach with invertible neural networks (INNs). This type of artificial neural network is trained to represent an inversion of the physical model, which in general is complex and non-linear. During the updating process, the inverse model is evaluated based on the target model's modal responses, which then returns the posterior prediction for the input parameters. In advance, a global sensitivity study will reduce the parameter space to a significant subset, on which the updating process will focus.

The finally trained INN excellently predicts the input parameters' posterior distributions of the proposed generic updating problem. Moreover, intrinsic model ambiguities, such as material densities of two closely located laminates, are correctly captured. A robustness analysis with noisy response reveals a few sensitive parameters, though most can still be recovered with equal accuracy. And, finally, after the resimulation analysis with the updated model, the modal response perfectly matches the target values. Thus, we successfully confirmed that INNs offer an extraordinary capability for structural model updating of even more complex and larger models of wind turbine blades.

Pablo Noever-Castelos et al.

Status: open (until 29 Oct 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Pablo Noever-Castelos et al.

Pablo Noever-Castelos et al.

Viewed

Total article views: 158 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
110 43 5 158 3 1
  • HTML: 110
  • PDF: 43
  • XML: 5
  • Total: 158
  • BibTeX: 3
  • EndNote: 1
Views and downloads (calculated since 17 Sep 2021)
Cumulative views and downloads (calculated since 17 Sep 2021)

Viewed (geographical distribution)

Total article views: 158 (including HTML, PDF, and XML) Thereof 158 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 17 Oct 2021
Download
Short summary
In the wind energy industry, a digital twin is fast becoming a key instrument for the monitoring of a wind turbine blade's life cycle. Here, our introduced model updating with invertible neural networks provides an efficient and powerful technique to represent the real blade as built. This method is applied to a full finite element beam model of a blade to successfully update material and layup parameters. The advantage over state-of-the-art methods is the established inverse model.