Design optimization of a curved wind turbine blade using neural networks and an aero-elastic vortex method under turbulent inflow

Research output: Contribution to journalJournal articleResearchpeer-review

2 Downloads (Pure)

Abstract

This article describes the application of neural networks for the design optimization of a curved wind turbine blade using an aero-elastic simulator with synthetic inflow turbulence. A vortex particle method where the wind turbine blades are represented by lifting-line theory is used, while the wind turbine structural dynamics are modeled using a finite-element multi-body based approach. A neural network together with a gradient-based optimizer allows to quickly design a new curved wind turbine blade in a complex aero-elastic wind-turbine simulation scenario. The blade design found from the neural network has increased pre-bend and sweep compared to the straight blade design. It produces approximately 1% more power on average with a slight increase of mean thrust on the rotor of 0.02% compared to the straight one. This study demonstrates that neural networks can be effective for designing wind turbine rotor blades involving complex aero-elastic simulation scenarios with turbulent inflow conditions. Further work may improve the performance of the neural network's predictive capabilities as well as the optimized design.
Original languageEnglish
JournalRenewable Energy
Volume146
Pages (from-to)1524-1535
Number of pages12
ISSN0960-1481
DOIs
Publication statusPublished - 2020

Keywords

  • Aero-elasticity
  • Aerodynamics
  • Neural network
  • Optimization
  • Vortex particle method
  • Wind turbine blade design

Cite this

@article{14206d8d7052490291f2521086f029f2,
title = "Design optimization of a curved wind turbine blade using neural networks and an aero-elastic vortex method under turbulent inflow",
abstract = "This article describes the application of neural networks for the design optimization of a curved wind turbine blade using an aero-elastic simulator with synthetic inflow turbulence. A vortex particle method where the wind turbine blades are represented by lifting-line theory is used, while the wind turbine structural dynamics are modeled using a finite-element multi-body based approach. A neural network together with a gradient-based optimizer allows to quickly design a new curved wind turbine blade in a complex aero-elastic wind-turbine simulation scenario. The blade design found from the neural network has increased pre-bend and sweep compared to the straight blade design. It produces approximately 1{\%} more power on average with a slight increase of mean thrust on the rotor of 0.02{\%} compared to the straight one. This study demonstrates that neural networks can be effective for designing wind turbine rotor blades involving complex aero-elastic simulation scenarios with turbulent inflow conditions. Further work may improve the performance of the neural network's predictive capabilities as well as the optimized design.",
keywords = "Aero-elasticity, Aerodynamics, Neural network, Optimization, Vortex particle method, Wind turbine blade design",
author = "Matias Sessarego and Ju Feng and {Ramos Garc{\'i}a}, N{\'e}stor and Horcas, {Sergio Gonz{\'a}lez}",
year = "2020",
doi = "10.1016/j.renene.2019.07.046",
language = "English",
volume = "146",
pages = "1524--1535",
journal = "Renewable Energy",
issn = "0960-1481",
publisher = "Pergamon Press",

}

TY - JOUR

T1 - Design optimization of a curved wind turbine blade using neural networks and an aero-elastic vortex method under turbulent inflow

AU - Sessarego, Matias

AU - Feng, Ju

AU - Ramos García, Néstor

AU - Horcas, Sergio González

PY - 2020

Y1 - 2020

N2 - This article describes the application of neural networks for the design optimization of a curved wind turbine blade using an aero-elastic simulator with synthetic inflow turbulence. A vortex particle method where the wind turbine blades are represented by lifting-line theory is used, while the wind turbine structural dynamics are modeled using a finite-element multi-body based approach. A neural network together with a gradient-based optimizer allows to quickly design a new curved wind turbine blade in a complex aero-elastic wind-turbine simulation scenario. The blade design found from the neural network has increased pre-bend and sweep compared to the straight blade design. It produces approximately 1% more power on average with a slight increase of mean thrust on the rotor of 0.02% compared to the straight one. This study demonstrates that neural networks can be effective for designing wind turbine rotor blades involving complex aero-elastic simulation scenarios with turbulent inflow conditions. Further work may improve the performance of the neural network's predictive capabilities as well as the optimized design.

AB - This article describes the application of neural networks for the design optimization of a curved wind turbine blade using an aero-elastic simulator with synthetic inflow turbulence. A vortex particle method where the wind turbine blades are represented by lifting-line theory is used, while the wind turbine structural dynamics are modeled using a finite-element multi-body based approach. A neural network together with a gradient-based optimizer allows to quickly design a new curved wind turbine blade in a complex aero-elastic wind-turbine simulation scenario. The blade design found from the neural network has increased pre-bend and sweep compared to the straight blade design. It produces approximately 1% more power on average with a slight increase of mean thrust on the rotor of 0.02% compared to the straight one. This study demonstrates that neural networks can be effective for designing wind turbine rotor blades involving complex aero-elastic simulation scenarios with turbulent inflow conditions. Further work may improve the performance of the neural network's predictive capabilities as well as the optimized design.

KW - Aero-elasticity

KW - Aerodynamics

KW - Neural network

KW - Optimization

KW - Vortex particle method

KW - Wind turbine blade design

U2 - 10.1016/j.renene.2019.07.046

DO - 10.1016/j.renene.2019.07.046

M3 - Journal article

VL - 146

SP - 1524

EP - 1535

JO - Renewable Energy

JF - Renewable Energy

SN - 0960-1481

ER -