The massive numerical computations for an accurate evaluation of the aerodynamic parameters inhibit multi-objective optimization of wind turbine blade sections from aerodynamic and acoustic aspects. This paper presents a novel approach to mitigate the problem. The method exploits the combination of a neural network-based reduced order modeling and a multi-objective genetic algorithm to optimize an S8xx-series airfoil and accordingly the trailing edge serration geometry for best aerodynamic and aero-acoustic characteristics. The Class-Shape Transformation (CST) was used to parameterize various serrated airfoil geometries. Using the modest amount of computational fluid dynamics (CFD) simulation data, a feed-forward neural network (NN), was trained to predict the airfoil behavior within a certain range. It has been worked out that this method can reduce the overall optimization time by a remarkable amount of about 1/20 using the same hardware while preserving accuracy. In multi-objective optimization of both the airfoil and the serration shapes, 5%–7% improvement in aerodynamic performance and simultaneously 1%–4% reduction in noise was pointed out compared to the benchmark airfoil.
SadeghimalekabadiMDavariAFadaeiM. Noise reduction in small wind turbines with optimized serrated blades. Phys Fluids2024; 36(5): 057135. DOI: 10.1063/5.0202934.
2.
FadaeiMDavariARSabetghadamF. Genetic algorithm optimization of a horizontal axis wind turbine blade section performance equipped with a single dielectric barrier discharge plasma actuator utilizing a direct regression model. Proc IME C J Mech Eng Sci2022; 236(20): 10456–10469. DOI: 10.1177/09544062221104346.
3.
YueQ. Aerodynamic noise prediction and reduction of H-Darrieus vertical axis wind turbine. Aust J Mech Eng2021; 21: 1093–1102.
4.
ChongTPJosephPFGruberM. Airfoil self -noise reduction by non-flat plate type trailing edge serrations. Appl Acoust2013; 74(4): 607–613.
5.
Arce LeónCMerino-MartínezRRagniD, et al.Boundary layer characterization and acoustic measurements of flow-aligned trailing edge serrations. Exp Fluid2016; 57(12): 182.
6.
Arce LeónCRagniDPröbstingS, et al.Flow topology and acoustic emissions of trailing edge serrations at incidence. Exp Fluid2016; 57(5): 91.
7.
MoreauDJDoolanCJ. Noise-reduction mechanism of a flat-plate serrated trailing edge. AIAA J2013; 51(10): 2513–2522.
8.
GruberMJosephPChongT. On the mechanisms of serrated airfoil trailing edge noise reduction. In: 17th AIAA/CEAS aeroacoustics conference (32nd AIAA Aeroacoustics conference), Portland, OR, 05-08 June 2011. DOI: 10.2514/6.2011-2781.
9.
LyuBAzarpeyvandMSinayokoS. Prediction of noise from serrated trailing edges. J Fluid Mech2016; 793: 556–588.
10.
OerlemansS. Reduction of wind turbine noise using blade trailing edge devices. In: 22nd AIAA/CEAS aeroacoustics conference, Lyon, France, 27 May 2016. DOI: 10.2514/6.2016-3018.
11.
AvalloneFArce LeonCPröbstingS, et al.Tomographic-PIV investigation of the flow over serrated trailing-edges. In: 54th AIAA aerospace sciences meeting, San Diego, CA, USA, 2 January 2016. DOI: 10.2514/6.2016-1012.
12.
OerlemansSFisherMMaederT, et al.Reduction of wind turbine noise using optimized airfoils and trailing-edge serrations. AIAA J2009; 47(6): 1470–1481.
13.
AzarpeyvandMGruberMJosephP. An analytical investigation of trailing edge noise reduction using novel serrations. In: 19th AIAA/CEAS aeroacoustics conference, Berlin, Germany, 24 May 2013. DOI: 10.2514/6.2013-2009.
14.
RagniDAvalloneFvan der VeldenWC. Concave serrations on broadband trailing edge noise reduction. In: 23rd AIAA/CEAS aeroacoustics conference,Denver, CO, 2 June 2017. DOI: 10.2514/6.2017-4174.
HerrM.Experimental Study on Noise Reduction through Trailing Edge Brushes. In: RathHJHolzeCHeinemannHJHenkeRHönlingerH. (eds) New Results in Numerical and Experimental Fluid Mechanics V. Notes on Numerical Fluid Mechanics and Multidisciplinary Design (NNFM), 92. Berlin, Heidelberg: Springer, 2006, pp. 365–372. https://doi.org/10.1007/978-3-540-33287-9_45
HoweMS. Noise produced by a Sawtooth trailing edge. J Acoust Soc Am1991; 90(1): 482–487.
19.
TyanMChoiC-KNguyenTA, et al.Rapid airfoil inverse design method with a deep neural network and hyperparameter selection. Int J Aeronaut Space Sci2023; 24(1): 33–46.
20.
MoshtaghzadehMAligoodarzMR. Prediction of wind turbine airfoil performance using artificial neural network and CFD approaches. Int J Eng Technol Innov2022; 12(4): 275–287.
21.
LiuR-LHuaYZhouZ-F, et al.Prediction and optimization of airfoil aerodynamic performance using deep neural network coupled Bayesian method. Phys Fluids2022; 34(11): 117116.
22.
BakarALiKLiuH, et al.Multi-objective optimization of low Reynolds number airfoil using convolutional neural network and non-dominated sorting genetic algorithm. Aerospace2022; 9(1): 35.
23.
DuXHePMartinsJRRA. Rapid airfoil design optimization via neural networks-based parameterization and surrogate modeling. Aero Sci Technol2021; 113: 106701.
24.
OoNLRichardsPJSharmaRN. Ice-induced separation bubble on RG-15 airfoil at low Reynolds number. AIAA J2020; 58(12): 5156–5167.
25.
DucrosFNicoudFPoinsotT. Wall-adapting local eddy-viscosity models for simulations in complex geometries. Numerical Methods for Fluid Dynamics VI1998; 6: 293–299.
26.
Ffowcs WilliamsJEHawkingsDL. Sound generation by turbulence and surfaces in arbitrary motion. Philos Trans R Soc Lond Ser Math Phys Sci1969; 264(1151): 321–342.
27.
SchneehagenEGeyerTFSarradjE, et al.Aeroacoustic noise reduction by application of end plates on wall-mounted finite airfoils. Exp Fluid2021; 62: 106.
28.
PadoisTSt-JacquesJRouardK, et al.Acoustic imaging with spherical microphone array and Kriging. JASA Express Lett2023; 3(4): 042801.
29.
GilquinLLecomtePAntoniJ, et al.Iterative positioning of microphone arrays for acoustic imaging. J Sound Vib2020; 469: 115116.
30.
BouleySVanwynsbergheCLe MagueresseT, et al.Microphone array positioning technique with Euclidean distance geometry. Appl Acoust2020; 167: 107377.
31.
Karl KocurGThalerDMarkertB. Acoustic source localization by deep-learning attention-based modulation of microphone array data. NDT E Int2024; 148: 103233.
32.
AlmohammadiKMInghamDBMaL, et al.Computational fluid dynamics (CFD) mesh independency techniques for a straight blade vertical axis wind turbine. Energy (Calg)2013; 58: 483–493.
33.
GerhardTCarolusTH. Investigation of airfoil trailing edge noise with advanced experimental and numerical. In: The 21st international congress on sound and vibration, Beijing, China, 13–17 July 2014.
34.
ZaideARavehD. Numerical simulation and reduced-order modeling of airfoil gust response. AIAA J2006; 44(8): 1826–1834.
35.
StankiewiczWMorzynskiMRoszakR, et al.Reduced order modelling of a flow around an airfoil with a changing angle of attack. Arch Mech2008; 60: 509–526.
36.
BourguetRBrazaMDervieuxA. Reduced-order modeling for unsteady transonic flows around an airfoil. Phys Fluids2007; 19(11): 111701.
37.
LiKKouJZhangW. Unsteady aerodynamic reduced-order modeling based on machine learning across multiple airfoils. Aero Sci Technol2021; 119: 107173.
38.
CezeMHayashiMVolpeE. A study of the CST parameterization characteristics. In: 27th AIAA applied aerodynamics conference, San Antonio, TX, 22-25 June 2009. DOI: 10.2514/6.2009-3767.
SandbergRDJonesLE. Direct numerical simulations of low Reynolds number flow over airfoils with trailing-edge serrations. J Sound Vib2011; 330(16): 3818–3831.
42.
LiDLiuX. A comparative study on aerodynamic performance and noise characteristics of two kinds of long-eared owl wing models. J Mech Sci Technol2017; 31(8): 3821–3830.
43.
ThomareisNPapadakisG. Effect of trailing edge shape on the separated flow characteristics around an airfoil at low Reynolds number: a numerical study. Phys Fluids2017; 29(1): 014101.
44.
WangZLiAWangL, et al.Aerodynamic coefficients modeling using Levenberg–Marquardt algorithm and network. Aircraft Eng Aero Technol2022; 94(3): 336–350.
45.
AbbaskhahASedighiHAkbarzadehP, et al.Optimization of horizontal axis wind turbine performance with the dimpled blades by using CNN and MLP models. Ocean Eng2023; 276: 114185.
46.
BlickleTThieleL. A comparison of selection schemes used in evolutionary algorithms. Evol Comput1996; 4(4): 361–394.
