Skip to main content
SpringerLink
Log in

Wind turbine airfoils optimization design by generalized regression neural network under small sample

  • Original Article
  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Neural network models can quickly and accurately predict the aerodynamic performance of wind turbine airfoils based on existing data, but the construction of a large number of learning samples requires a high upfront time cost. To address this problem, a generalized regression neural network (GRNN) model of wind turbine airfoils based on a small sample set is established, and an optimal design method for airfoil aerodynamic performance under multiple constraints is proposed. This method is used to improve the prediction accuracy of the model in the optimization process and to solve the problem of insufficient learning caused by poor training data. Based on the established optimal design model, we applied the particle swarm optimization (PSO) algorithm to complete the optimal design of NACA44XX series airfoils and obtained the optimized airfoils with maximum relative thicknesses of 15 %, 18 %, 21 %, and 24 %, respectively. The aerodynamic characteristics of the new airfoils were analyzed in comparison with the baseline airfoils. The results show that the aerodynamic properties of the new airfoils are significantly improved, with the maximum lift coefficient and maximum lift-to-drag ratio increasing by up to 16.93 % and 10.41 %. Moreover, the optimization efficiency of the method is much higher than that of the traditional one. Thus, it was verified that the method is feasible and effective.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Abbreviations

C max :

Maximum relative camber

T max :

Maximum relative thickness

x C :

Maximum relative camber position

x T :

Maximum relative thickness position

R le :

Leading edge radius

Re :

Reynolds number

Ma :

Mach number

C L :

Lift coefficient

C D :

Drag coefficient

C L/C D :

Lift-drag ratio

References

  1. M. G. Fernandez, C. Park, N. H. Kim and R. T. Haftka, Issues in deciding whether to use multifidelity surrogates, AIAA Journal, 57 (5) (2019) 2039–2054.

    Article  Google Scholar 

  2. C. Park, R. T. Haftka and N. H. Kim, Remarks on multi-fidelity surrogates, Structural and Multidisciplinary Optimization, 55 (3) (2017) 1029–1050.

    Article  MathSciNet  Google Scholar 

  3. L. Y. Zhu, W. W. Zhang, J. Q. Kou and Y. L. Yi, Machine learning methods for turbulence modeling in subsonic flows around airfoils, Physics of Fluids, 31 (1) (2019) 015105.

    Article  Google Scholar 

  4. F. G. Oztiryaki and T. Piskin, Airfoil performance analysis using shallow neural networks, AIAA Scitech 2021 Forum (2021) 0174.

  5. J. N. Kutz, Deep learning in fluid dynamics, Journal of Fluid Mechanics, 814 (2017) 1–4.

    Article  MATH  Google Scholar 

  6. J. Ling, A. Kurzawski and J. Templeton, Reynolds averaged turbulence modelling using deep neural networks with embedded invariance, Journal of Fluid Mechanics, 807 (2016) 155–166.

    Article  MathSciNet  MATH  Google Scholar 

  7. R. Zahn and C. Breitsamter, Airfoil buffet aerodynamics at plunge and pitch excitation based on long short-term memory neural network prediction, CEAS Aeronautical Journal (2021) 1–11.

  8. K. Balla, R. Sevilla, O. Hassan and K. Morgan, An application of neural networks to the prediction of aerodynamic coefficients of aerofoils and wings, Applied Mathematical Modelling, 96 (2021) 456–479.

    Article  MathSciNet  MATH  Google Scholar 

  9. L. Deng, Y. Q. Wang, Y. Liu, F. Wang, S. K. Li and J. Liu, A CNN-based vortex identification method, Journal of Visualization, 22 (1) (2019) 65–78.

    Article  Google Scholar 

  10. V. Sekar, Q. Jiang, C. Shu and B. C. Khoo, Fast flow field prediction over airfoils using deep learning approach, Physics of Fluids, 31 (5) (2019) 057103.

    Article  Google Scholar 

  11. W. L. Lyu, S. Y. Wang and A. M. Yang, Some improvements of hybrid trim method for a helicopter rotor in forward flight, Aerospace Science and Technology, 113 (2021) 106709.

    Article  Google Scholar 

  12. Y. J. Sun, G. Sun and S. Y. Wang, Neural net based wing shape prediction, Chinese Quarterly of Mechanics, 35 (3) (2014) 482–490.

    Google Scholar 

  13. X. Y. Wang, S. Y. Wang, J. Tao, G. Sun and J. Mao, A PCA-ANN-based inverse design model of stall lift robustness for high-lift device, Aerospace Science and Technology, 81 (2018) 272–283.

    Article  Google Scholar 

  14. A. Kharal and A. Saleem, Neural networks based airfoil generation for a given cp using bezier-parsec parameterization, Aerospace Science and Technology, 23 (1) (2012) 330–344.

    Article  Google Scholar 

  15. Y. F. Zhang, C. Y. Yan and H. X. Chen, An inverse design method for airfoils based on pressure gradient distribution, Energies, 13 (13) (2020) 3400.

    Article  Google Scholar 

  16. H. P. Wang, X. Jiang, Y. Chao, Q. Li, M. Z. Li, T. Chen and W. R. Ouyang, Numerical optimization of horizontal-axis wind turbine blades with surrogate model, Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, 235 (5) (2021) 1173–1186.

    Google Scholar 

  17. A. J. Al-Mahasneh, S. G. Anavatti and M. A. Garratt, Evolving general regression neural networks for learning from noisy datasets, 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China (2019) 1473–1478.

  18. F. R. Marzabadi, M. Masdari and M. R. Soltani, Application of artificial neural network in aerodynamic coefficient prediction of subducted airfoil, Journal of Research in Science and Engineering, 2 (1) (2020) 13–17.

    Google Scholar 

  19. J. E. Stolzman and S. Manoharan, Testing the efficacy of dimples on a naca airfoil at low Reynolds numbers: a numerical study, AIAA Aviation 2021 Forum (2021) 2584.

  20. Z. H. Han, Kriging surrogate model and its application to design optimization: a review of re-cent progress, Acta Aeronautica et Astronautica Sinica, 37 (11) (2016) 3197–3225.

    Google Scholar 

  21. X. C. Sun, Z. H. Han, F. Liu, K. Song and W. P. Song, Design and analysis of hypersonic vehicle airfoil/wing at wide-range mach numbers, Acta Aeronautica et Astronautica Sinica, 39 (6) (2018) 31–42.

    Google Scholar 

  22. R. F. Xu, W. P. Song and K. Zhang, Investigation of effect of transition on wind turbine airfoil optimization design, Acta Energiae Solaris Sinica, 32 (12) (2011) 1798–1803.

    Google Scholar 

  23. J. Chen, Q. Wang, S. L. Li, X. F. Guo and X. D. Wang, Study of optimization design method for wind turbine airfoil combining airfoil integrated theory and B-spine, Acta Energiae Solaris Sinica, 35 (10) (2014) 1930–1935.

    Google Scholar 

  24. J. Chen, Q. F. Lu, X. D. Wang and J. T. Cheng, Research on optimization of general airfoil profiles for wind turbines based on adaptive genetic algorithm, China Mechanical Engineering, 20 (20) (2009) 2448–2451+2469.

    Google Scholar 

  25. F. Q. Miao, H. S. Park, C. Kim and S. Ahn, Swarm intelligence based on modified PSO algorithm for the optimization of axial-flow pump impeller, Journal of Mechanical Science and Technology, 29 (11) (2015) 4867–4876.

    Article  Google Scholar 

  26. T. Deshamukhya, D. Bhanja, S. Nath and S. A. Hazarika, Prediction of optimum design variables for maximum heat transfer through a rectangular porous fin using particle swarm optimization, Journal of Mechanical Science and Technology, 32 (9) (2018) 4495–4502.

    Article  Google Scholar 

  27. Y. Shi and R. Eberhart, Empirical study of particle swarm optimization, Proceedings of the 1999 Congress on Evolutionary Computation, Washingdon, DC, USA (1999) 1945–1950.

  28. Z. H. Zhan and J. Zhang, Adaptive particle swarm optimization, IEEE Transactions on System, Man, and Cyber-netics-Part B, 39 (6) (2009) 1362–1381.

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by the Chongqing Foundation and Frontier Project (Grant No. cstc2016jcyjA0448), Chongqing Municipal Education Commission Scientific Research Project (Grant No. KJ1600628) and Manufacturing Equipment Mechanism Design and Control Chongqing Key Laboratory Open Fund (Grant No. 1556031).

Author information

Authors and Affiliations

  1. Chongqing Key Laboratory of Manufacturing Equipment Mechanism Design and Control, Chongqing Technology and Business University, Chongqing, 400067, China

    Xudong Wang, Hao Ju & Jiahong Lu

Authors
  1. Xudong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hao Ju
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jiahong Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xudong Wang.

Additional information

Xudong Wang is a Professor at Chongqing Technology and Business University. He received his Ph.D. degree in Mechanical Design and Theory from Chongqing University, Chongqing, in Jun. 2009. From Sep. 2007 to Sep. 2008, he was a Joint Training Ph.D student with the School of Mechanical Engineering, the Technical University of Denmark. His research interests include dynamics of Machinery, optimization design and intelligent Vehicles.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, X., Ju, H. & Lu, J. Wind turbine airfoils optimization design by generalized regression neural network under small sample. J Mech Sci Technol 37, 217–228 (2023). https://doi.org/10.1007/s12206-022-1223-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-022-1223-2

Keywords

Search

Navigation