Prediction of aeroelastic response of bridge decks using artificial neural networks

Abstract The assessment of wind-induced vibrations is considered vital for the design of long-span bridges. The aim of this research is to develop a methodological framework for robust and efficient prediction strategies for complex aerodynamic phenomena using hybrid models that employ numerical analyses as well as meta-models. Here, an approach to predict motion-induced aerodynamic forces is developed using artificial neural network (ANN). The ANN is implemented in the classical formulation and trained with a comprehensive dataset which is obtained from computational fluid dynamics forced vibration simulations. The input to the ANN is the response time histories of a bridge section, whereas the output is the motion-induced forces. The developed ANN has been tested for training and test data of different cross section geometries which provide promising predictions. The prediction is also performed for an ambient response input with multiple frequencies. Moreover, the trained ANN for aerodynamic forcing is coupled with the structural model to perform fully-coupled fluid–structure interaction analysis to determine the aeroelastic instability limit. The sensitivity of the ANN parameters to the model prediction quality and the efficiency has also been highlighted. The proposed methodology has wide application in the analysis and design of long-span bridges.

[1]  Khader M. Hamdia,et al.  Uncertainty quantification of the fracture properties of polymeric nanocomposites based on phase field modeling , 2015 .

[2]  Sungmoon Jung,et al.  Weighted error functions in artificial neural networks for improved wind energy potential estimation , 2013 .

[3]  Guido Morgenthal,et al.  An immersed interface method for the Vortex-In-Cell algorithm , 2007 .

[4]  Emil Simiu,et al.  Wind effects on structures : fundamentals and applications to design , 1996 .

[5]  Luca Caracoglia,et al.  Estimation of torsional-flutter probability in flexible bridges considering randomness in flutter derivatives , 2011 .

[6]  G. Morgenthal,et al.  A synergistic study of a CFD and semi-analytical models for aeroelastic analysis of bridges in turbulent wind conditions , 2018, Journal of Fluids and Structures.

[7]  P. Lancaster,et al.  Surfaces generated by moving least squares methods , 1981 .

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

[9]  Juan M. Gimenez,et al.  Prediction of wind pressure coefficients on building surfaces using artificial neural networks , 2018 .

[10]  You-Lin Xu,et al.  Prediction of typhoon design wind speed and profile over complex terrain , 2013 .

[11]  Daniel T. Valentine,et al.  Investigation of the Aerodynamic Analysis of Super Long–Span Bridges by Using ERA-Based Reduced-Order Models , 2014 .

[12]  Jamshid Ghaboussi,et al.  Estimation of Aeroelastic Parameters of Bridge Decks Using Neural Networks , 2004 .

[13]  Ahsan Kareem,et al.  Linear and nonlinear aeroelastic analysis frameworks for cable-supported bridges , 2013 .

[14]  Forrest J. Masters,et al.  Predicting Roof Pressures on a Low-Rise Structure From Freestream Turbulence Using Artificial Neural Networks , 2018, Front. Built Environ..

[15]  Timon Rabczuk,et al.  A software framework for probabilistic sensitivity analysis for computationally expensive models , 2016, Adv. Eng. Softw..

[16]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[17]  R. Clough,et al.  Dynamics Of Structures , 1975 .

[18]  Ahsan Kareem,et al.  Changing dynamic of bridge aerodynamics , 2015 .

[19]  M. Steiner,et al.  An adaptive sampling method for global sensitivity analysis based on least-squares support vector regression , 2019, Reliab. Eng. Syst. Saf..

[20]  Guido Morgenthal,et al.  A Comparative Assessment of Aerodynamic Models for Buffeting and Flutter of Long-Span Bridges , 2017 .

[21]  Ru-Cheng Xiao,et al.  Probabilistic free vibration and flutter analyses of suspension bridges , 2005 .

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

[23]  G. Morgenthal,et al.  Aeroelastic analyses of bridges using a Pseudo-3D vortex method and velocity-based synthetic turbulence generation , 2018, Engineering Structures.

[24]  G. Morgenthal,et al.  Vortex-Induced Vibrations on Cross Sections in Tandem Arrangement , 2014 .

[25]  G. Arfken.  Mathematical Methods for Physicists , 1967 .

[26]  Guido Morgenthal,et al.  Framework for sensitivity and uncertainty quantification in the flutter assessment of bridges , 2016 .

[27]  Allan Larsen,et al.  Discrete vortex simulation of flow around five generic bridge deck sections , 1998 .

[28]  Jong-Cheng Wu,et al.  Prediction of flutter derivatives by artificial neural networks , 2008 .

[29]  Pedro Martinez-Vazquez,et al.  Wind field reproduction using neural networks and conditional simulation , 2007 .

[30]  Khader M. Hamdia,et al.  Hybrid nonlinear surrogate models for fracture behavior of polymeric nanocomposites , 2017 .

[31]  David Surry,et al.  Prediction of pressure coefficients on roofs of low buildings using artificial neural networks , 2003 .

[32]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

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

[34]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.