Wind turbine airfoil noise prediction using dedicated airfoil database and deep learning technology

Han Yang, Weimin Yuan, Weijun Zhu, Zhenye Sun, Yanru Zhang and Yingjie Zhou

Applied Energy, 2024, vol. 364, issue C, No S0306261924005488

Abstract: Noise emission is a major issue in wind turbine airfoil design, particularly for large scale wind turbines in low wind speed sites adjacent to urban areas. Conventional methods for addressing aerodynamic noise involve computational aeroacoustics or measurements in anechoic wind tunnels, which are both time-consuming and costly. Some surrogate methods can help reducing the cost, but most of them still have the same problems as specific parameterization techniques. In this study, we introduce a data-driven approach for predicting the aerodynamic noise of wind turbine airfoils, utilizing Convolutional Neural Network (CNN) technology. A major issue is the insufficient number of existing wind turbine airfoils to meet the requirements for deep learning training. To establish a dedicated airfoil database, we systematically sampled 11,700 profiles from renowned wind turbine airfoil series, including NREL, NACA, DU, RISØ, etc., utilizing an integrated airfoil approach. The noise performance of each airfoil was determined through a semi-empirical method. After training is finished, our CNN model enables the calculation of sound pressure levels for new airfoils, circumventing the need for computationally intensive physical equations. With a mean absolute percentage error of less than 0.0531%, our results demonstrate the promising predictive ability of the proposed model. This establishes the model as a suitable tool for airfoil noise evaluation and the design of low-noise airfoils.

Keywords: Convolutional neural network; Wind turbine airfoil; Airfoil integrated method; Data-driven approach; Acoustic noise prediction (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261924005488
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:364:y:2024:i:c:s0306261924005488

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2024.123165

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().