Details
| Original language | English |
|---|---|
| Pages (from-to) | 573-599 |
| Number of pages | 27 |
| Journal | WIND ENERGY |
| Volume | 25 |
| Issue number | 3 |
| Early online date | 21 Oct 2021 |
| Publication status | Published - 10 Mar 2022 |
Abstract
Fabricated wind turbine blades have unavoidable deviations from their designs due to imperfections in the manufacturing processes. Model updating is a common approach to enhance model predictions and therefore improve the numerical blade design accuracy compared to the built blade. An updated model can provide a basis for a digital twin of the rotor blade including the manufacturing deviations. Classical optimization algorithms, most often combined with reduced order or surrogate models, represent the state of the art in structural model updating. However, these deterministic methods suffer from high computational costs and a missing probabilistic evaluation. This feasibility study approaches the model updating task by inverting the model through the application of invertible neural networks, which allow for inferring a posterior distribution of the input parameters from given output parameters, without costly optimization or sampling algorithms. In our use case, rotor blade cross sections are updated to match given cross-sectional parameters. To this end, a sensitivity analysis of the input (material properties or layup locations) and output parameters (such as stiffness and mass matrix entries) first selects relevant features in advance to then set up and train the invertible neural network. The trained network predicts with outstanding accuracy most of the selected cross-sectional input parameters for different radial positions; that is, the posterior distribution of these parameters shows a narrow width. At the same time, it identifies some parameters that are hard to recover accurately or contain intrinsic ambiguities. Hence, we demonstrate that invertible neural networks are highly capable for structural model updating.
Keywords
- Bayesian optimization, blade cross section, invertible neural network, machine learning, model updating, sensitivity analysis, wind turbine rotor blade
ASJC Scopus subject areas
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: WIND ENERGY, Vol. 25, No. 3, 10.03.2022, p. 573-599.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Model updating of wind turbine blade cross sections with invertible neural networks
AU - Noever Castelos, Pablo
AU - Ardizzone, Lynton
AU - Balzani, Claudio
N1 - Funding Information: This work was supported by the compute cluster, which is funded by the Leibniz University Hannover, the Lower Saxony Ministry of Science and Culture (MWK), and the German Research Foundation (DFG). This work was also supported by the Federal Ministry for Economic Affairs and Energy of Germany (BMWi) projects SmartBlades2 (grant number 0324032C) and ReliaBlade (grant number 0324335B).
PY - 2022/3/10
Y1 - 2022/3/10
N2 - Fabricated wind turbine blades have unavoidable deviations from their designs due to imperfections in the manufacturing processes. Model updating is a common approach to enhance model predictions and therefore improve the numerical blade design accuracy compared to the built blade. An updated model can provide a basis for a digital twin of the rotor blade including the manufacturing deviations. Classical optimization algorithms, most often combined with reduced order or surrogate models, represent the state of the art in structural model updating. However, these deterministic methods suffer from high computational costs and a missing probabilistic evaluation. This feasibility study approaches the model updating task by inverting the model through the application of invertible neural networks, which allow for inferring a posterior distribution of the input parameters from given output parameters, without costly optimization or sampling algorithms. In our use case, rotor blade cross sections are updated to match given cross-sectional parameters. To this end, a sensitivity analysis of the input (material properties or layup locations) and output parameters (such as stiffness and mass matrix entries) first selects relevant features in advance to then set up and train the invertible neural network. The trained network predicts with outstanding accuracy most of the selected cross-sectional input parameters for different radial positions; that is, the posterior distribution of these parameters shows a narrow width. At the same time, it identifies some parameters that are hard to recover accurately or contain intrinsic ambiguities. Hence, we demonstrate that invertible neural networks are highly capable for structural model updating.
AB - Fabricated wind turbine blades have unavoidable deviations from their designs due to imperfections in the manufacturing processes. Model updating is a common approach to enhance model predictions and therefore improve the numerical blade design accuracy compared to the built blade. An updated model can provide a basis for a digital twin of the rotor blade including the manufacturing deviations. Classical optimization algorithms, most often combined with reduced order or surrogate models, represent the state of the art in structural model updating. However, these deterministic methods suffer from high computational costs and a missing probabilistic evaluation. This feasibility study approaches the model updating task by inverting the model through the application of invertible neural networks, which allow for inferring a posterior distribution of the input parameters from given output parameters, without costly optimization or sampling algorithms. In our use case, rotor blade cross sections are updated to match given cross-sectional parameters. To this end, a sensitivity analysis of the input (material properties or layup locations) and output parameters (such as stiffness and mass matrix entries) first selects relevant features in advance to then set up and train the invertible neural network. The trained network predicts with outstanding accuracy most of the selected cross-sectional input parameters for different radial positions; that is, the posterior distribution of these parameters shows a narrow width. At the same time, it identifies some parameters that are hard to recover accurately or contain intrinsic ambiguities. Hence, we demonstrate that invertible neural networks are highly capable for structural model updating.
KW - Bayesian optimization
KW - blade cross section
KW - invertible neural network
KW - machine learning
KW - model updating
KW - sensitivity analysis
KW - wind turbine rotor blade
UR - http://www.scopus.com/inward/record.url?scp=85117373982&partnerID=8YFLogxK
U2 - 10.1002/we.2687
DO - 10.1002/we.2687
M3 - Article
AN - SCOPUS:85117373982
VL - 25
SP - 573
EP - 599
JO - WIND ENERGY
JF - WIND ENERGY
SN - 1095-4244
IS - 3
ER -