Prediction of aerodynamic coefficients for twisting shapes of buildings and structures based on machine learning and CFD-modelling

Cover Page

Cite item

Full Text

Abstract

Introduction. Research was carried out on the application of machine learning to predict aerodynamic coefficients on buildings and structures with twisted form configurations. Data from aerodynamic simulations using numerical modelling in ANSYS CFX was used for training. The quality of predictions made by various machine learning models was evaluated in comparison to numerical simulations. Conclusions related to the use of machine learning models for determining wind loads on buildings and structures are drawn.Materials and methods. Python programming language and the following libraries, Pandas, NumPy, Scikit-learn, and Matplotlib were used to analyze the obtained results and to develop the machine learning model. The study considered four machine learning methods: linear regression, decision tree, k-nearest neighbours, and random forest. Aerodynamic simulations based on numerical modelling methods in ANSYS CFX were used to generate the training data. The accuracy of different machine learning models in predicting aerodynamic coefficients was evaluated using the statistical measure of R-squared.Results. As a result of the research, a database of 217 numerical solutions was compiled for various angles of twist of the building’s form. These results include the distribution of aerodynamic pressure coefficients over the building’s surface, as well as aerodynamic force and moment coefficients (Cx, Cy, CMz) as a function of height. The data was used to train four machine learning models. The best-performing machine learning model (random forest) was verified by comparing it to the results of numerical modelling.Conclusions. Various machine learning models for predicting aerodynamic coefficients on buildings and structures were investigated. Conclusions were drawn regarding the applicability of machine learning methods as an alternative approach to determining wind loads.

About the authors

S. G. Saiyan

Moscow State University of Civil Engineering (National Research University) (MGSU)

Email: Berformert@gmail.com
ORCID iD: 0000-0003-0694-4865

V. B. Shelepina

Moscow State University of Civil Engineering (National Research University) (MGSU)

Email: veronika.shel@mail.ru

References

  1. Mooneghi M.A., Kargarmoakhar R. Aerodynamic mitigation and shape optimization of buildings : review // Journal of Building Engineering. 2016. Vol. 6. Pp. 225–235. doi: 10.1016/j.jobe.2016.01.009
  2. Stathopoulos T., Alrawashdeh H. Wind loads on buildings: A code of practice perspective // Journal of Wind Engineering and Industrial Aerodynamics. 2020. Vol. 206. P. 104338. doi: 10.1016/j.jweia.2020.104338
  3. Сатанов А.А., Васин А.Д. Экспериментальное исследование распределения ветрового давления на высотное здание уникальной формы // Приволжский научный журнал. 2021. № 3 (59). С. 38–46. EDN AANDEZ.
  4. Егорычев О.О., Чурин П.С. Экспериментальное исследование ветровых нагрузок на высотные здания // Жилищное строительство. 2015. № 6. С. 20–22. EDN TZVIWT.
  5. Saiyan S., Andreev V., Paushkin A. Numerical simulation of accelerations of the upper floors of a high-rise building under wind influence // Lecture Notes in Civil Engineering. 2022. Pp. 269–279. doi: 10.1007/978-3-031-10853-2_25
  6. Belostotsky A., Afanasyeva I., Negrozova I., Goryachevsky O. Simulation of aerodynamic instability of building structures on the example of a bridge section. Part 2: Solution of the problem in a coupled aeroelastic formulation and comparison with engineering estimates // International Journal for Computational Civil and Structural Engineering. 2021. Vol. 17. Issue 3. Pp. 24–38. doi: 10.22337/2587-9618-2021-17-3-24-38
  7. Zheng X., Montazeri H., Blocken B. CFD simulations of wind flow and mean surface pressure for buildings with balconies: Comparison of RANS and LES // Building and Environment. 2020. Vol. 173. P. 106747. doi: 10.1016/j.buildenv.2020.106747
  8. Rezaeiha A., Montazeri H., Blocken B. On the accuracy of turbulence models for CFD simulations of vertical axis wind turbines // Energy. 2019. Vol. 180. Pp. 838–857. doi: 10.1016/j.energy.2019.05.053
  9. Дубинский С.И. Численное моделирование ветровых воздействий на высотные здания и комплексы : дис. … канд. тех. наук. М. : МГСУ, 2010. 198 с. EDN QEVMND.
  10. Белостоцкий А.М., Акимов П.А., Афанасьева И.Н. Вычислительная аэродинамика в задачах строительства : учебное пособие. М. : АСВ, 2017. 720 с.
  11. Zhang F.L., Xiong H.B., Shi W.X., Ou X. Structural Health Monitoring of shanghai tower during different stages using a Bayesian approach // Structural Control and Health Monitoring. 2016. Vol. 23. Issue 11. Pp. 1366–1384. doi: 10.1002/stc.1840
  12. Lapin V.A., Yerzhanov S.Y., Makish N.K. Monitoring the behavior of a high-rise building under wind loads // IOP Conference Series: Materials Science and Engineering. 2020. Vol. 953. Issue 1. P. 012087. doi: 10.1088/1757-899X/953/1/012087
  13. Колчин В.Н. Специфика применения технологии «искусственного интеллекта» в строительстве // Инновации и инвестиции. 2022. № 3. С. 250–253. EDN JJLECU.
  14. Málaga-Chuquitaype C. Machine learning in structural design : an opinionated review // Frontiers in Built Environment. 2022. Vol. 8. doi: 10.3389/fbuil.2022.815717
  15. Sun H., Burton H.V., Huang H. Machine learning applications for building structural design and performance assessment : state-of-the-art review // Journal of Building Engineering. 2021. Vol. 33. P. 101816. doi: 10.1016/j.jobe.2020.101816
  16. Nguyen P.T. Application machine learning in construction management // TEM Journal. 2021. Pp. 1385–1389. doi: 10.18421/tem103-48
  17. Lee J., Lee S. Construction site safety management: A computer vision and deep learning approach // Sensors. 2023. Vol. 23. Issue 2. P. 944. doi: 10.3390/s23020944
  18. Gomez-Cabrera A., Escamilla-Ambrosio P.J. Review of machine-learning techniques applied to structural health monitoring systems for building and bridge structures // Applied Sciences. 2022. Vol. 12. Issue 21. P. 10754. doi: 10.3390/app122110754
  19. Wu T., Snaiki R. Applications of machine learning to wind engineering // Frontiers in Built Environment. 2022. Vol. 8. doi: 10.3389/fbuil.2022.811460
  20. Li J., Du X., Martins J.R.R.A. Machine learning in aerodynamic shape optimization // Progress in Aerospace Sciences. 2022. Vol. 134. P. 100849. doi: 10.1016/j.paerosci.2022.100849
  21. Peng W., Zhang Y., Laurendeau E., Desmarais M.C. Learning aerodynamics with neural network // Scientific Reports. 2022. Vol. 12. Issue 1. doi: 10.1038/s41598-022-10737-4
  22. Ahmed S., Kamal K., Ratlamwala T.A., Mathavan S., Hussain G., Alkahtani M. et al. Aerodynamic analyses of airfoils using machine learning as an alternative to RANS simulation // Applied Sciences. 2022. Vol. 12. Issue 10. P. 5194. doi: 10.3390/app12105194
  23. Zan B.W., Han Z.H., Xu C.Z., Liu M.Q., Wang W.Z. High-dimensional aerodynamic data modeling using a machine learning method based on a convolutional neural network // Advances in Aerodynamics. 2022. Vol. 4. Issue 1. doi: 10.1186/s42774-022-00128-8
  24. Yang B. Wind engineering for high-rise buildings : a review // Wind and Structures. 2021. Vol. 32. Issue 3. Pp. 249–265. doi: 10.12989/was.2021.32.3.249
  25. Sarker I.H. Machine learning: algorithms, real-world applications and research directions // SN Computer Science. 2021. Vol. 2. Issue 3. doi: 10.1007/s42979-021-00592-x

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).