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.

Data-driven Aerodynamic Analysis of Structures using Gaussian Processes

“…For comparison, other data-driven models (cf. e.g., Wu and Kareem (2011); Abbas et al (2020)) are based on the nondimensional vertical amplitude and/or dimensional frequency. This formulation makes an easier transition of the learned latent functions f L and f M between scales (e.g., wind tunnel and real structure).…”

“…There is not yet a consistent method to select the number of terms for bluff bodies. Abbas et al (2020) used up to 3 terms; however, their NFIR model included the velocity and acceleration as a lagged input. Li et al (2020) used equivalent lags up to τ = 20.…”

“…Moreover, such models can be trained not only on wind tunnel or CFD data but also on real monitoring data, leading to the potential to use them for real-time model updating (Castellon et al, 2021). Several data-driven models have been recently presented to predict nonlinear aerodynamic forces, including flutter, and have been mainly based on Artificial Neural Networks (ANN) (Wu and Kareem, 2011;Abbas et al, 2020;Li et al, 2020). These models included past terms of the deck displacements as input (typically in a dimensional form) and output the aerodynamic forces.…”

Random dynamic analysis of vertical train–bridge systems under small probability by surrogate model and subset simulation with splitting

“…Surrogate models such as Kriging, radial basis function, and support vector regression; and artificial neural network (ANN) have been applied in optimization, reliability analysis and wind engineering [17][18][19]. Although the surrogate models are used to predict time series [20], the current response of dynamic systems relates to historical responses and external excitation. Therefore, the nonlinear autoregressive with exogenous input (NARX) model is introduced to the surrogate model for a dynamic system.…”

Prediction of Bridge Fires Characteristics Using Machine Learning

“…Machine Learning (ML) is a subset of Artificial Intelligence (AI) that concentrates on algorithms and statistical models allowing computers to complete tasks without explicit instructions. It is a strong process of extracting a model from a huge database for making predictions [86]. Using input data and generating a special output, a machine learning algorithm accomplishs a goal without being explicitly written (i.e., hardcoded).…”