Wind and Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Machine learning-based prediction of wind forces on CAARC standard tall buildings

  • Yi Li (School of Civil Engineering, Changsha University of Science and Technology) ;
  • Jie-Ting Yin (School of Civil Engineering, Hunan University of Science and Technology) ;
  • Fu-Bin Chen (School of Civil Engineering, Changsha University of Science and Technology) ;
  • Qiu-Sheng Li (Department of Architecture and Civil Engineering, City University of Hong Kong)
  • Received : 2022.06.13
  • Accepted : 2022.12.19
  • Published : 2023.06.25
⟨ Previous Next ⟩

Abstract

Although machine learning (ML) techniques have been widely used in various fields of engineering practice, their applications in the field of wind engineering are still at the initial stage. In order to evaluate the feasibility of machine learning algorithms for prediction of wind loads on high-rise buildings, this study took the exposure category type, wind direction and the height of local wind force as the input features and adopted four different machine learning algorithms including k-nearest neighbor (KNN), support vector machine (SVM), gradient boosting regression tree (GBRT) and extreme gradient (XG) boosting to predict wind force coefficients of CAARC standard tall building model. All the hyper-parameters of four ML algorithms are optimized by tree-structured Parzen estimator (TPE). The result shows that mean drag force coefficients and RMS lift force coefficients can be well predicted by the GBRT algorithm model while the RMS drag force coefficients can be forecasted preferably by the XG boosting algorithm model. The proposed machine learning based algorithms for wind loads prediction can be an alternative of traditional wind tunnel tests and computational fluid dynamic simulations.

Keywords

Acknowledgement

The work presented in this paper was fully supported by the grants from National Natural Science Foundation of China (Project no: 51708207, 52278479 and 51878271), grants from Hunan Provincial Natural Science Foundation (Project no: 2020JJ5176 and 2023JJ30016), a grant from Civil Engineering Key Discipline of Changsha University of Science and Technology (23ZDXK11) and an open foundation of Key Laboratory of Safety and Control for Bridge Engineering of CSUST, Ministry of Education (13KB01).

References

  1. Chen, F.B., Liu,H.M., Chen, W., Shu, Z.R., Li, Y. and Li, Q.S. (2022), "Characterizing wind pressure on CAARC standard tall building with various facade appurtenances", J. Build. Eng., 59, 105015. https://doi.org/10.1016/j.jobe.2022.105015.
  2. Chen, F.B., Wang. X.L., Li, X., Shu. Z.R. and Zhou, K. (2022), "Prediction of wind pressures on tall buildings using wavelet neural network", J. Build. Eng., 46, 103674. https://doi.org/10.1016/j.jobe.2021.103674.
  3. Chen, T. and Guestrin, C. (2016), "XGBoost: A scalable tree boosting system", The 22nd ACM SIGKDD International, 16, 785-794. https://doi.org/10.1145/2939672.2939785.
  4. Cortes, C. and Vapnik, V. (1995), "Support-vector networks", Machine Learning, 20(3), 273-297. https://link.springer.com/article/10.1007/BF00994018.
  5. Dong, H., He, D. and Wang, F. (2020), "SMOTE-XGBoost using Tree Parzen Estimator optimization for copper flotation method classification", Powder Technol., 375, 174-181. https://doi.org/10.1016/j.powtec.2020.07.065.
  6. Durbin, M., Wonders, M., Flaska, M. and Lintereur, A.T. (2021), "K-Nearest Neighbors regression for the discrimination of gamma rays and neutrons in organic scintillators", Nuclear Inst. Meth. Phys. Res., 987, 164826. https://doi.org/10.1016/j.nima.2020.164826.
  7. GB 50009-2012 (2012), Load Code for the Design of Building Structures. China Architecture and Building Press, Beijing.
  8. Gu, M. and Quan, Y. (2004), "Across-wind loads of typical tall buildings", J. Wind Eng. Ind. Aerod., 92(13), 1147-1165. https://doi.org/10.1016/j.jweia.2004.06.004.
  9. Guo, Q., Zhuang, T., Li, Z. and He, S. (2021), "Prediction of reservoir saturation field in high water cut stage by bore-ground electromagnetic method based on machine learning", J. Petroleum Sci. Eng., 204, 108678. https://doi.org/10.1016/j.petrol.2021.108678.
  10. Hashemizadeh, A., Maaref, A., Shateri, M., Larestani, A. and Hemmati-Sarapardeh, A. (2021), "Experimental measurement and modeling of water-based drilling mud density using adaptive boosting decision tree, support vector machine, and K-nearest neighbors: A case study from the South Pars gas field", J. Petroleum Sci. Eng., 207, 109132. https://doi.org/10.1016/j.petrol.2021.109132.
  11. Hu, G. and Kwok K.C.S. (2020), "Predicting wind pressures around circular cylinders using machine learning techniques", J. Wind Eng. Ind. Aerod., 198, 104099. https://doi.org/10.1016/j.jweia.2020.104099.
  12. Hu, G., Liu, L., Tao, D., Song, J., Kse, K.T. and Kwok K.C.S. (2020), "Deep learning-based investigation of wind pressures on tall building under interference effects", J. Wind Eng. Ind. Aerod., 201, 104138. https://doi.org/10.1016/j.jweia.2020.104138.
  13. Jo, Y., Min, K., Jung, D., Sunwoo, M. and Han, M. (2019), "Comparative study of the artificial neural network with three hyper-parameter optimization methods for the precise LP-EGR estimation using in-cylinder pressure in a turbocharged GDI engine", Appl. Thermal Eng., 149, 1324-1334. https://doi.org/10.1016/j.applthermaleng.2018.12.139.
  14. Kareem, A. (1990), "Measurements of pressure and force fields on building models in simulated atmospheric flows", J. Wind Eng. Ind. Aerod., 36, 589-599. https://doi.org/10.1016/0167-6105(90)90341-9.
  15. Kokkinos, Y. and Margaritis, K.G. (2018), "Managing the computational cost of model selection and cross-validation in extreme learning machines via Cholesky, SVD, QR and eigen decompositions", Neurocomputing, 295, 29-45. https://doi.org/10.1016/j.neucom.2018.01.005.
  16. Kotsiantis, S.B. (2007), "Supervised machine learning: A review of classification techniques", Informatica, 31, 249-268.
  17. Li, X. and Li, Q.S. (2019), "Observations of typhoon effects on a high-rise building and verification of wind tunnel predictions", J. Wind Eng. Ind. Aerod., 184, 174-184. https://doi.org/10.1016/j.jweia.2018.11.026.
  18. Li, Y., Song, Q., Li, C., Huang, X. and Zhang, Y. (2022), "Reduction of wind loads on rectangular tall buildings with different taper ratios", J. Build. Eng., 46, 103588. https://doi.org/10.1016/j.jobe.2021.103588.
  19. Li, Y., Li, C., Li, Q.S., Li, Y.G. and Chen, F.B. (2021), "Refined mathematical models for across-wind loads of rectangular tall buildings with aerodynamic modifications", Int. J. Struct. Stab. Dyn., 21(9), 2150131. https://doi.org/10.1142/S0219455421501315.
  20. Li, Y., Li, C., Li, Q.S., Song, Q., Huang X. and Li, Y.G. (2020), "Aerodynamic performance of CAARC standard tall building model by various corner chamfers", J. Wind Eng. Ind. Aerod., 202, 104197. https://doi.org/10.1016/j.jweia.2020.104197.
  21. Li, Y. and Li, Q. S. (2016), "Across-wind dynamic loads on L-shaped tall buildings", Wind Struct., 23(5), 385-403. https://www.researchgate.net/publication/309670618. https://doi.org/10.12989/was.2016.23.5.385
  22. Li, Y., Li, Q.S. and Chen, F. (2017), "Wind tunnel study of wind-induced torques on L-shaped tall buildings", J. Wind Eng. Ind. Aerod., 167, 41-50. https://doi.org/10.1016/j.jweia.2017.04.013.
  23. Li, Y., Li, Y.G., Li, Q.S. and Tee, K.F. (2019), "Investigation of wind effect reduction on square high-rise buildings by corner modification", Adv. Struct. Eng., 22(6), 1488-1500. https://doi.org/10.1177/136943321881611.
  24. Li, Y., Tian, X., Tee, K. F., Li, Q.S. and Li, Y.G. (2018), "Aerodynamic treatments for reduction of wind loads on high-rise buildings", J. Wind Eng. Ind. Aerod., 172, 107-115. https://doi.org/10.1016/j.jweia.2017.11.006.
  25. Li, Y., Zhang, J.W. and Li, Q.S. (2014), "Experimental investigation of characteristics of torsional wind loads on rectangular tall buildings", Struct. Eng. Mech., 49(1), 129-145. https://doi.org/10.12989/sem.2014.49.1.129.
  26. Liang, S.G., Liu, S.C., Li, Q.S., Zhang, L.L and Gu, M. (2002), "Mathematic model of acrosswind dynamic loads on rectangular tall buildings", J. Wind Eng. Ind. Aerod., 90, 1757-1770. https://doi.org/10.1016/S0167-6105(02)00285-4.
  27. Lin, N., Letchford, C., Tamura, Y., Liang, B. and Nakamura, O. (2005), "Characteristics of wind forces acting on tall buildings", J. Wind Eng. Ind. Aerod., 93(3), 217-242. https://doi.org/10.1016/j.jweia.2004.12.001.
  28. Lin, P.F., Hu, G., Li, C., Li, L.X., Xiao, Y.Q., Tse. K.T. and Kwok, K.C.S. (2021), "Machine learning-based prediction of crosswind vibrations of rectangular cylinders", J. Wind Eng. Ind. Aerod., 211, 104549. https://doi.org/10.1016/j.jweia.2021.104549.
  29. Liu, J., Huang, Q., Ulishney, C. and Dumitrescu, C.E. (2021), "Machine learning assisted prediction of exhaust gas temperature of a heavy-duty natural gas spark ignition engine", Appl. Energy, 300, 117413. https://doi.org/10.1016/j.apenergy.2021.117413.
  30. Melbourne, W.H. (1980), "Comparison of measurements on the CAARC standard tall building model in simulated model wind flows", J. Wind Eng. Ind. Aerod., 6(1-2), 73-88. https://doi.org/10.1016/0167-6105(80)90023-9.
  31. Morariu, C., Morariu O., Raileanu, S. and Borangiu, T. (2020), "Machine learning for predictive scheduling and resource allocation in large scale manufacturing systems", Comput. Ind., 120, 103244. https://doi.org/10.1016/j.compind.2020.103244.
  32. Nguyen, H., Liu J. and Zio, E. (2020), "A long-term prediction approach based on long short-term memory neural networks with automatic parameter optimization by Tree-structured Parzen Estimator and applied to time-series data of NPP steam generators", Appl. Soft Comput. J., 89, 106116. https://doi.org/10.1016/j.asoc.2020.106116.
  33. Osarogiagbon, A.U., Khan F., Venkatesan, R. and Gillard, P. (2021), "Review and analysis of supervised machine learning algorithms for hazardous events in drilling operations", Process Safety Environ. Protect., 147, 367-384. https://doi.org/10.1016/j.psep.2020.09.038.
  34. Pan, Z., Wang, Y. and Pan, Y. (2020), "A new locally adaptive k-nearest neighbor algorithm based on discrimination class", Knowledge-Based Syst., 204, 106185. https://doi.org/10.1016/j.knosys.2020.106185.
  35. Ramadhan, R.A., Heatubun Y.R., Tan, S.F. and Lee, H. (2021), "Comparison of physical and machine learning models for estimating solar irradiance and photovoltaic power", Renew. Energy, 178, 1006-1019. https://doi.org/10.1016/j.renene.2021.06.079.
  36. Refaeilzadeh, P., Tang, L. and Huan, L. (2009), Cross-Validation, in: Encyclopedia of Database Systems. Springer US, Boston, 532-538.
  37. Rodriguez-Galiano, V., Sanchez-Castillo, M., Chica-OImo, M. and Chica-Rivas, M. (2015), "Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines", Ore Geology Rev., 71, 804-818. https://doi.org/10.1016/j.oregeorev.2015.01.001.
  38. Su, X., An, J., Zhang, Y., Zhu, P. and Zhu, B. (2020), "Prediction of ozone hourly concentrations by support vector machine and kernel extreme learning machine using wavelet transformation and partial least squares methods", Atmos. Pollut. Res., 11, 51-60. https://doi.org/10.1016/j.apr.2020.02.024.
  39. Tao, T., Liu, Y., Qiao, Y., Gao, L., Lu, J., Zhang, C. and Wang, Y. (2021), "Wind turbine blade icing diagnosis using hybrid features and Stacked-XGBoost algorithm", Renew. Energy, 180, 1004-1013. https://doi.org/10.1016/j.renene.2021.09.008.
  40. Tian, J., Gurley, K.R., Diaz, M.T., Fernandez-Caban, P.L., Masters, F.J. and Fang, R. (2020), "Low-rise gable roof buildings pressure prediction using deep neural networks", J. Wind Eng. Ind. Aerod., 196, 104026. https://doi.org/10.1016/j.jweia.2019.104026.
  41. Tian, Z., Xiao, J., Feng, H. and Wei, Y. (2020). "Credit risk assessment based on gradient boosting decision tree", Procedia Comput. Sci., 174, 150-160. https://doi.org/10.1016/j.procs.2020.06.070.
  42. Tixier, A.P., Hallowell, M.R., Rajagopalan, B. and Bowman, D. (2016), "Application of machine learning to construction injury prediction", Automat. Construct., 69, 102-114. https://doi.org/10.1016/j.autcon.2016.05.016.
  43. Trizoglou, P., Liu, X. and Lin, Z. (2021), "Fault detection by an ensemble framework of Extreme Gradient Boosting (XGBoost) in the operation of offshore wind turbines", Renew. Energy, 179, 945-962. https://doi.org/10.1016/j.renene.2021.07.085.
  44. Vakharia, V. and Gujar, R. (2019), "Prediction of compressive strength and portland cement composition using cross-validation and feature ranking techniques", Construct. Build. Mater., 225, 292-301. https://doi.org/10.1016/j.conbuildmat.2019.07.224.
  45. Vapnik, V., Golowich, S.E. and Smola, A. (1997), "Support vector method for function approximation, regression estimation, and signal processing", Adv. Neural Inform. Process. Syst., 281-287.
  46. Wang, J. and Hu, J. (2015), "A robust combination approach for short-term wind speed forecasting and analysis - Combination of the ARIMA (Autoregressive Integrated Moving Average), ELM (Extreme Learning Machine), SVM (Support Vector Machine) and LSSVM (Least Square SVM) forecasts using a GPR (Gaussian Process Regression) model", Energy, 93, 41-56. https://doi.org/10.1016/j.energy.2015.08.045.
  47. Wu, T. and Snaiki, R. (2022), "Applications of machine learning to wind engineering", Front. Built Environ., 8, 811460. https://doi.org/10.3389/fbuil.2022.811460.
  48. Yan, B.W., Ding, W.H., Zhou, X.H., Guo, K.P., Ren, H.Y., Li, X. and Yang, Q.S. (2023), "Experimental study on the aeroelastic response of a square supertall building considering twisted wind effect", Eng. Struct., 283, 115923. https://doi.org/10.1016/j.engstruct.2023.115923.
  49. Yan, Y., Lu, D. and Wang, K. (2021), "Accelerated discovery of single-phase refractory high entropy alloys assisted by machine learning", Comput, Mater. Sci., 199, 110723. https://doi.org/10.1016/j.commatsci.2021.110723.
  50. Yang, L. and Shami, A. (2020), "On hyperparameter optimization of machine learning algorithms: Theory and practice", Neurocomputing, 415, 295-316. https://doi.org/10.1016/j.neucom.2020.07.061.
  51. Yanamandra, K., Chen, GL., Xu, X., Mac, G. and Gupta, N. (2020), "Reverse engineering of additive manufactured composite part by tool path reconstruction using imaging and machine learning", Compos. Sci. Technol., 198, 108318. https://doi.org/10.1016/j.compscitech.2020.108318.
  52. Zhang, L., He, M. and Shao, S. (2020), "Machine learning for halide perovskite materials", Nano Energy, 78, 105380. https://doi.org/10.1016/j.nanoen.2020.105380.