Yazar "Okbaz, Abdulkerim" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Flow control over a circular cylinder using vortex generators: Particle image velocimetry analysis and machine-learning-based prediction of flow characteristics
    (Elsevier, 2023) Okbaz, Abdulkerim; Aksoy, Muharrem Hilmi; Kurtulmuş, Nazım; Çolak, Andaç Batur
    Controlling the flow around circular cylinders is crucial to mitigate vortex-induced vibrations and prevent structural damage in a range of applications, such as marine and offshore engineering, tall buildings, long-span bridges, transport ships, and heat exchangers. In this study, we aimed to control the turbulent flow structure around a circular cylinder by placing vortex generators (VGs). We examined the flow structure using particle image velocimetry (PIV). This enabled quantitative data acquisition, intuitive flow visualization, and drag co efficient determination from PIV data. We developed artificial neural network (ANN) models that successfully predict both mean and instantaneous flow characteristics for different scenarios. Our findings show that using VGs elongated the wake and increased vortex formation lengths while reducing velocity fluctuations and the drag coefficient. A minimum drag coefficient of 0.718 was achieved with VGs oriented at ? = 60? & ? = 60?, reducing the drag by 35.3% compared to the bare cylinder. The drag coefficient exhibited a substantial inverse correlation with both wake and vortex formation lengths. This study is significant for controlling flow structures, providing detailed insights into the near-wake region, and highlighting the potential applications of machine learning in fluid dynamics.
  • Küçük Resim Yok
    Öğe
    Prediction of heat transfer characteristics in a microchannel with vortex generators by machine learning
    (Walter de Gruyter, 2022) Gönül, Alişan; Çolak, Andaç Batur; Kayaci, Nurullah; Okbaz, Abdulkerim; Dalkilic, Ahmet Selim
    Because of the prompt improvements in Micro-Electro-Mechanical Systems, thermal management necessities have altered paying attention to the compactness and high energy consumption of actual electronic devices in industry. In this study, 625 data sets obtained numerically according to the change of five different geometric parameters and Reynolds numbers for delta winglet type vortex generator pairs placed in a microchannel were utilized. Four dissimilar artificial neural network models were established to predict the heat transfer characteristics in a microchannel with innovatively oriented vortex generators in the literature. Friction factor, Nusselt number, and performance evaluation criteria were considered to explore the heat transfer characteristics. Different neuron numbers were determined in the hidden layer of each of the models in which the Levethenberg–Marquardt training algorithm was benefited as the training algorithm. The predicted values were checked against the target data and empirical correlations. The coefficient of determination values calculated for each machine learning model were found to be above 0.99. According to obtained results, the designed artificial neural networks can provide high prediction performance for each data set and have higher prediction accuracy compared to empirical correlations. All data predicted by machine learning models were collected within the range of ±3% deviation bands, whereas the majority of the estimated data by empirical correlations dispersed within ±20% ones. For that reason, a full evaluation of the estimation performance of artificial neural networks versus empirical correlations data is enabled to fill a gap in the literature as one of the uncommon works.