Operational model updating of low-order horizontal axis wind turbine models for structural health monitoring applications

Velazquez, Antonio; Swartz, R. Andrew

doi:10.1177/1045389x14563864

Cited by 3 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Omenzetter and Turnbull (2018) implemented metaheuristic optimization methods (fireflies and virus optimization) to detect damage in a finite element beam model of a blade and compare the performance to a simplified beam experiment. Other publications cover simplified model updating procedures of low-level wind turbine blade models (Velazquez and Swartz, 2015;Liu et al, 2012;Lin et al, 2018). While most of the referred contributions focus on the field of damage detection, the model updating conducted by Luczak et al (2014) highlights the impact of a flexible support structure of the test setup of modern blades, which was also revealed by Knebusch et al (2020).…”

Section: Model Updating Of Wind Turbine Bladesmentioning

confidence: 99%

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

2022

View full text Add to dashboard Cite

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 Timoshenko 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. It 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.

show abstract

Section: Model Updating Of Wind Turbine Bladesmentioning

confidence: 99%

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

2022

View full text Add to dashboard Cite

show abstract

“…Omenzetter and Turnbull (2018) implemented metaheuristic optimization methods (fireflies and virus optimization) to detect damages in a finite element beam model of a blade and compare the performance to a simplified beam experiment. Other publications cover simplified model updating procedures of low-level wind turbine blade models (Velazquez and Swartz, 2015;Liu et al, 2012;Lin et al, 2018). While most of the referred contributions focus on the field of damage detection, the model updating conducted by Luczak et al (2014) highlights the impact of a flexible support structure of the test setup of modern blades, which was also revealed by Knebusch et al (2020).…”

Section: Model Updating Of Wind Turbine Bladesmentioning

confidence: 99%

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

Noever‐Castelos

Melcher

Balzani

2021

Preprint

View full text Add to dashboard Cite

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.

show abstract

Order-Reduced Modeling-Based Multi-Level Damage Identification Using Piezoelectric Impedance Measurement

2022

View full text Add to dashboard Cite

Operational model updating of low-order horizontal axis wind turbine models for structural health monitoring applications

Cited by 3 publications

References 33 publications

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

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

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

Order-Reduced Modeling-Based Multi-Level Damage Identification Using Piezoelectric Impedance Measurement

Contact Info

Product

Resources

About