Figure 20 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Drag coefficients (a), the decreasing ratio of drag coefficients (b), lift coefficient (c), and decreasing ratio of lift coefficients (d) of the convex cross-section.
Source publication
This study aimed to estimate the drag and lift coefficients of the long-span bridge pylon using the finite volume method (FVM). The k-ω turbulence model was applied to analyze the behavior of wind flow around the pylon, yielding drag and lift coefficient values with an error of 0.98% compared to a previous tunnel experiment. Four recommended cross-...
Similar publications
A 3-dimensional incompressible laminar flow and heat-transfer in a plate-fin heat exchanger (PFHE) where investigated numerically in this article. The influence of mounting a longitudinal vortex generator (LVG) on the offset rectangular-triangular fin (ORT) in the PFHE, on thermal and hydro-dynamic fields are presented. The novelty of this study is...
Citations
... This model initially dissects image characteristics such as curves, edges, and lines in the early layers. Subsequent layers then organize and synthesize these features, while the final layers are responsible for reconstructing the image from scratch [72,73]. For example, Yuan et al. [14] investigated the application of CNN to predict the continuity of L-PBF tracks. ...
The utilization of metal Additive Manufacturing (AM) has led to substantial progress in the manufacturing process of metal components. Evaluating the influence of the wide variety of factors related to the material type, AM process, and the resultant microstructure and properties is not easy and accurate by traditional engineering strategies. Therefore, one of the most effective ways to improve AM performance is to employ artificial intelligence methods, such as Machine Learning (ML), to establish complex links and enhance control over systems and product quality. The integration of these powerful ML techniques presents an emerging opportunity to revolutionize manufacturing processes, tackle production challenges, and optimize resource consumption. Consequently, in this review, the role of machine learning in laser-based metal additive manufacturing is explored by highlighting its applications in process optimization and property prediction. Evaluation of the results reported in the literature indicates that it is possible to establish relationships between process, structure, and properties by considering inputs such as part geometry, material properties, microstructural characteristics, and AM process parameters and utilizing ML algorithms. Defect detection and in-situ monitoring are among the other applications of ML algorithms in AM procedures, enhancing the manufacturability and repeatability of metal components. For this purpose, various linkages and correlations for Directed Energy Deposition and Laser Powder Bed Fusion are outlined in this review. The advancement in hardware and software will boost the advantage of applying data-driven approaches to overcome the obstacles in metal AM.
