Machine learning-based prediction of crosswind vibrations of rectangular cylinders

Abstract Due to the complexity of crosswind vibrations of rectangular cylinders, current research on crosswind vibrations of rectangular cylinders mainly relies on expensive wind tunnel tests and time-consuming numerical simulation techniques. In this study, in order to evaluate crosswind vibrations of rectangular cylinders, machine learning method was used to build an efficient and effective prediction model for supplementing the above two research tools. 5 machine learning models based on decision tree regression, k-nearest neighbor regression, random forest, gradient boosting regression tree (GBRT) and histogram gradient boosting regression tree algorithms were trained based on the existing high-quality and reliable wind tunnel test datasets of crosswind responses of rectangular cylinders. The hyper-parameters were optimized by using particle swarm optimization method. 4 types of crosswind vibration phenomena, including over-coupled, coupled, semi-coupled and decoupled, were predicted. It was found that the GBRT model is capable of predicting crosswind responses of rectangular cylinders at side ratios from 0.75 to 3 and Scruton numbers from 0 to 150 under wind flow with turbulence intensities from 0 to 16%. Evidently, GBRT model can be an effective and economical method to study crosswind vibrations of rectangular cylinders and hence supplement traditional wind tunnel tests and numerical simulation techniques.

[1]  E. de Langre,et al.  Coupling of Structure and Wake Oscillators in Vortex-Induced Vibrations , 2004 .

[2]  Hui Hu,et al.  Passive jet control of flow around a circular cylinder , 2015 .

[3]  M. Kubát.  An Introduction to Machine Learning , 2017, Springer International Publishing.

[4]  Wenli Chen,et al.  Investigation and control of vortex-induced vibration of twin box girders , 2013 .

[5]  Qiusheng Li,et al.  Prediction of wind-induced pressures on a large gymnasium roof using artificial neural networks , 2007 .

[6]  Enrico Zio,et al.  Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[7]  Mitchell A. Wawzonek.  Aeroelastic behavior of square section prisms in uniform flow , 1979 .

[8]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[9]  Xiao Yi-qing.  CFD NUMERICAL SIMULATION OF FLOW-INDUCED VIBRATION WITH DIFFERENT CROSS-SECTION CYLINDER , 2009 .

[10]  J. Concato,et al.  A simulation study of the number of events per variable in logistic regression analysis. , 1996, Journal of clinical epidemiology.

[11]  Tetsuro Tamura,et al.  The role of separated shear layers in unstable oscillations of a rectangular cylinder around a resonant velocity , 2002 .

[12]  John David Smith,et al.  An experimental study of the aeroelastic instability of rectangular cylinders , 1962 .

[13]  J. Y. Fu,et al.  Prediction of wind loads on a large flat roof using fuzzy neural networks , 2006 .

[14]  Billie F. Spencer,et al.  Automated modal identification using principal component and cluster analysis: Application to a long‐span cable‐stayed bridge , 2019, Structural Control and Health Monitoring.

[15]  Pascal Hémon,et al.  ON THE AEROELASTIC BEHAVIOUR OF RECTANGULAR CYLINDERS IN CROSS-FLOW , 2002 .

[16]  Yuequan Bao,et al.  Machine learning paradigm for structural health monitoring , 2020, Structural Health Monitoring.

[17]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[18]  Zhengqing Chen,et al.  Coupling investigation on Vortex-induced vibration and Galloping of rectangular cylinders , 2014 .

[19]  Hui Li,et al.  Data-driven modeling of vortex-induced vibration of a long-span suspension bridge using decision tree learning and support vector regression , 2018 .

[20]  J. D. Holmes,et al.  Wind Loading of Structures , 2001 .

[21]  Martin Krzywinski,et al.  Points of Significance: Classification and regression trees , 2017, Nature Methods.

[22]  Gianni Bartoli,et al.  Experimental investigation on VIV-galloping interaction of a rectangular 3:2 cylinder , 2015 .

[23]  J. Kutz,et al.  Compressive Sensing Based Machine Learning Strategy For Characterizing The Flow Around A Cylinder With Limited Pressure Measurements , 2013 .

[24]  Gianni Bartoli,et al.  Aeroelastic stability of two long-span arch structures: A collaborative experience in two wind tunnel facilities , 2016 .

[25]  Thomas V. Santosham.  Force measurements on bluff cylinders and aeroelastic galloping of a rectangular cylinder , 1966 .

[26]  Hui Li,et al.  A novel long short-term memory neural-network-based self-excited force model of limit cycle oscillations of nonlinear flutter for various aerodynamic configurations , 2020 .

[27]  Mahdi Hasanipanah,et al.  Prediction of air-overpressure caused by mine blasting using a new hybrid PSO–SVR model , 2016, Engineering with Computers.

[28]  Turgut Sarpkaya,et al.  A critical review of the intrinsic nature of vortex-induced vibrations , 2004 .

[29]  Abinet Tesfaye Eseye,et al.  Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information , 2018 .

[30]  Gianni Bartoli,et al.  VIV–galloping instability of rectangular cylinders: Review and new experiments , 2014 .

[31]  Yoram Reich,et al.  Evaluating machine learning models for engineering problems , 1999, Artif. Intell. Eng..

[32]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[33]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[34]  Hua-Ping Wan,et al.  A probabilistic approach for short-term prediction of wind gust speed using ensemble learning , 2020 .

[35]  Claudio Mannini,et al.  Interference of vortex-induced vibration and transverse galloping for a rectangular cylinder , 2016 .

[36]  Yukio Tamura,et al.  Wake-Oscillator Model of Vortex-Induced Oscillation of Circular Cylinder , 1981 .

[37]  Ahsan Kareem,et al.  Modeling hysteretic nonlinear behavior of bridge aerodynamics via cellular automata nested neural network , 2011 .

[38]  Mahdi Hasanipanah,et al.  Application of PSO to develop a powerful equation for prediction of flyrock due to blasting , 2017, Neural Computing and Applications.

[39]  P. Hémon.  LARGE GALLOPING OSCILLATIONS OF A SQUARE SECTION CYLINDER IN WIND TUNNEL , 2012 .

[40]  Zhu Xue,et al.  Prediction of wind loads on high-rise building using a BP neural network combined with POD , 2017 .

[41]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[42]  Jinling Liang,et al.  Multistability of complex-valued neural networks with distributed delays , 2016, Neural Computing and Applications.

[43]  C. Feng.  The measurement of vortex induced effects in flow past stationary and oscillating circular and D-section cylinders , 1968 .

[44]  Hui Hu,et al.  An experimental study on the unsteady vortices and turbulent flow structures around twin-box-girder bridge deck models with different gap ratios , 2014 .

[45]  Zhi-Hua Zhou,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[46]  Yasuharu Nakamura,et al.  The effects of turbulence on the mean flow past two-dimensional rectangular cylinders , 1984, Journal of Fluid Mechanics.

[47]  Gang Hu,et al.  Machine learning strategy for predicting flutter performance of streamlined box girders , 2021 .

[48]  M. Clerc,et al.  The swarm and the queen: towards a deterministic and adaptive particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[49]  Jinping Ou,et al.  Numerical study on the suppression of the vortex-induced vibration of an elastically mounted cylinder by a traveling wave wall , 2014 .

[50]  Robert H. Scanlan,et al.  AIR FOIL AND BRIDGE DECK FLUTTER DERIVATIVES , 1971 .

[51]  Niu Hua-wei.  RESEARCH ON COUPLING OF THE VORTEX-EXCITED RESONANCE AND GALLOPING OF THE BLUFF BODY WITH LARGE SLENDERNESS RATIO , 2012 .

[52]  Tommaso Massai.  On the Interaction between vortex-induced vibrations and galloping in rectangular cylinders of low side ratio , 2015 .

[53]  A. Laneville.  Effects of turbulence on wind induced vibrations of bluff cylinders , 1973 .

[54]  G. V. Parkinson,et al.  Experiments on flow-induced vibration of a square-section cylinder , 1987 .

[55]  Hui Li,et al.  Cluster Analysis of Winds and Wind-induced Vibrations on a Long-span Bridge based on Long-term Field Monitoring Data , 2017 .

[56]  C. Mannini.  Incorporation of turbulence in a nonlinear wake-oscillator model for the prediction of unsteady galloping response , 2020 .

[57]  M. A. Wawzonek,et al.  Some considerations of combined effects of galloping and vortex resonance , 1981 .

[58]  Gianni Bartoli,et al.  Interference of vortex-induced vibration and galloping: experiments and mathematical modelling , 2017 .

[59]  Hui Hu,et al.  An experimental investigation on vortex induced vibration of a flexible inclined cable under a shear flow , 2015 .

[60]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[61]  G. V. Parkinson,et al.  THE SQUARE PRISM AS AN AEROELASTIC NON-LINEAR OSCILLATOR , 1964 .

[62]  Wenli Chen,et al.  An ultrasonic transmission thickness measurement system for study of water rivulets characteristics of stay cables suffering from wind–rain-induced vibration , 2010 .

[63]  L. D. Zhu,et al.  Nonlinear mathematical model of unsteady galloping force on a rectangular 2:1 cylinder , 2017 .

[64]  Alireza Bokaian,et al.  Effects of Vortex‐Resonance on Nearby Galloping Instability , 1985 .

[65]  Dacheng Tao,et al.  Deep learning-based investigation of wind pressures on tall building under interference effects , 2020 .

[66]  G. V. Parkinson,et al.  On the Aeroelastic Instability of Bluff Cylinders , 1961 .

[67]  T. Miyata,et al.  PRESSURE DISTRIBUTION MEASUREMENTS FOR WIND INDUCED VIBRATIONS OF BOX GIRDER BRIDGES , 1984 .

[68]  Biswajeet Pradhan,et al.  Modification of landslide susceptibility mapping using optimized PSO-ANN technique , 2018, Engineering with Computers.

[69]  Robert M. Corless,et al.  A model of the combined effects of vortex-induced oscillation and galloping , 1988 .

[70]  Hui Li,et al.  Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder , 2018 .

[71]  J. Ou,et al.  Suppression of vortex-induced vibration of a circular cylinder using suction-based flow control , 2013 .

[72]  Adel M. Alimi,et al.  PSO-based analysis of Echo State Network parameters for time series forecasting , 2017, Appl. Soft Comput..

[73]  K. Washizu,et al.  Aeroelastic instability of rectangular cylinders in a heaving mode , 1978 .

[74]  Gang Hu,et al.  Predicting wind pressures around circular cylinders using machine learning techniques , 2019, ArXiv.

[75]  G. V. Parkinson,et al.  Phenomena and modelling of flow-induced vibrations of bluff bodies , 1989 .

[76]  A. Marra,et al.  Unsteady galloping of a rectangular cylinder in turbulent flow , 2018 .