“…Snaiki and Wu (2019) 18 developed a knowledge‐enhanced deep‐learning algorithm for simulating tropical cyclone boundary‐layer winds, and Li et al (2018) 19 proposed a data‐driven approach using machine learning to model vortex‐induced vibrations on long‐span bridges. Kim et al (2020) 20 applied clustering algorithms to the study of wind pressures on buildings, and Diop et al (2022) 21 investigated the unsteady flow around high‐rise buildings using OpenFoam, incorporating a vortex method.…”
SummaryThis research investigates the influence of wind on four closely spaced parallel building models using computational fluid dynamics (CFD). The buildings are positioned either perpendicular to the wind direction or at various oblique angles. The aerodynamic results obtained for these buildings in an interfering condition are compared to those of an isolated tall building using the interference and obliquity effect (IOE) factor. Graphical comparisons are made among the different models and faces, considering various obliquity angles (OAs). The inner building models exhibit higher pressure and force coefficients at higher OAs. The variation of pressure coefficients along the horizontal peripheral direction is also analyzed, and the trade‐offs of higher and lower OAs are discussed for the different building models. Furthermore, an artificial neural network (ANN) is trained using surface pressure coefficients from approximately 6000 data points distributed over different facets of building models. Categorical encoding is employed using one‐hot encoding‐based dummy variables for different building models, while numerical variables such as OA and X, Y, and Z coordinates are included as input for the ANN. The ANN is trained using a total of 238,340 data points (considering different building models and different OA scenarios), and its parameters are monitored during training to minimize errors and achieve high predictability. Finally, a representative case is used to plot the pressure contour obtained from the trained ANN, which is shown to be highly comparable to the CFD‐based contour.
“…Snaiki and Wu (2019) 18 developed a knowledge‐enhanced deep‐learning algorithm for simulating tropical cyclone boundary‐layer winds, and Li et al (2018) 19 proposed a data‐driven approach using machine learning to model vortex‐induced vibrations on long‐span bridges. Kim et al (2020) 20 applied clustering algorithms to the study of wind pressures on buildings, and Diop et al (2022) 21 investigated the unsteady flow around high‐rise buildings using OpenFoam, incorporating a vortex method.…”
SummaryThis research investigates the influence of wind on four closely spaced parallel building models using computational fluid dynamics (CFD). The buildings are positioned either perpendicular to the wind direction or at various oblique angles. The aerodynamic results obtained for these buildings in an interfering condition are compared to those of an isolated tall building using the interference and obliquity effect (IOE) factor. Graphical comparisons are made among the different models and faces, considering various obliquity angles (OAs). The inner building models exhibit higher pressure and force coefficients at higher OAs. The variation of pressure coefficients along the horizontal peripheral direction is also analyzed, and the trade‐offs of higher and lower OAs are discussed for the different building models. Furthermore, an artificial neural network (ANN) is trained using surface pressure coefficients from approximately 6000 data points distributed over different facets of building models. Categorical encoding is employed using one‐hot encoding‐based dummy variables for different building models, while numerical variables such as OA and X, Y, and Z coordinates are included as input for the ANN. The ANN is trained using a total of 238,340 data points (considering different building models and different OA scenarios), and its parameters are monitored during training to minimize errors and achieve high predictability. Finally, a representative case is used to plot the pressure contour obtained from the trained ANN, which is shown to be highly comparable to the CFD‐based contour.
“…Clustering algorithms proved effective in recognizing intricate pressure and flow patterns, offering a promising machine‐learning technique for building analysis alongside conventional wind engineering methods. Diop et al 38 explored unsteady flow around high‐rise buildings using OpenFoam, devising a Vortex Method for generating realistic upstream fluctuations, validated against experimental data. The study explored flow reconstruction using limited velocity measurements within the wake, showcasing better results compared to wall pressure measurements, with linear regression outperforming Artificial Neural Network regression.…”
SummaryThis study investigates the impact of different positions of two limbs on the structural response of a rectangular building model to wind forces. The building's geometry assumes Z and + shapes based on specific limb configurations. Computational fluid dynamics (CFD) simulations are performed to quantify wind‐induced pressures, resulting in wind force coefficients. These coefficients are used to develop predictive machine learning models through Gene Expression Programming, Group Method of Data Handling‐combinatorial (GMDH‐Combi), Model Tree, and Artificial Neural Network (ANN) techniques. The ANN analysis explores various combinations of training algorithms, adaptation functions, activation functions, and performance functions to enhance model accuracy. Among these, the Levenberg–Marquardt (LM) with gradient descent with momentum (GDM) adaptation function and sigmoid activation function exhibit superior performance with high R‐squared values. These predictive models are then employed for a comprehensive comparative assessment of the maximum wind force coefficient (CF, max) concerning different limb positions and angles of attack (AOA). For CF, max vs Limb position, variations of limb position are examined for most critical cases of AOA. Similarly, the study of CF, max vs AOA involves an exhaustive investigation into the variation of AOA for the building with the worst limb position. The analysis reveals that changes in AOA have a more pronounced effect on CF, max compared to alterations in limb position. Interestingly, within the AOA range of 1.5 to 2.5, the CF, max consistently reaches a minimum across all models. However, the relationship between CF, max and the critical structural parameter ‘S' (representing limb position) remains less conclusive for the most significant AOAs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.