Yazar "Genc, Omer" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    From experimental data to predictions: Artificial intelligence supported new mathematical approaches for estimating thermal conductivity, viscosity and zeta potential in Fe3O4-water magnetic nanofluids
    (Elsevier, 2023) Sahin, Fevzi; Genc, Omer; Gokcek, Murat; Colak, Andas Batur
    Magnetic nanofluids (MNs) are considered advanced heat transfer fluids of the future due to their ability to function as intelligent fluids, with the applied external magnetic field effect being readily manageable. In this study, firstly, the stabilities of Fe3O4-water MNs prepared at 0.1, 0.25, 0.5, 0.75 and 1 mass ratios were determined by zeta potential measurement. The thermal conductivity and viscosities of MNs with appropriate stability were measured at 20–60 ?C for all mass ratios. Secondly, using experimental data, two different artificial neural network (ANN) models were developed: one for thermal conductivity and viscosity depending on the temperature (20–60 ?C) and mass ratio values and one for zeta potential depending on pH and mass ratio. Finally, using the obtained ANN data, two new mathematical correlations are proposed to predict thermal conductivity and viscosity. The study’s results revealed that the developed ANN model has MSE and R values of 4.51E-06 and 0.99968, respectively, for thermal conductivity and viscosity of Fe3O4-water MNs can be accurately predicted by novel mathematical correlations.
  • Küçük Resim
    Öğe
    Microstructural design of solid oxide fuel cell electrodes by micro-modeling coupled with artificial neural network
    (Elsevier, 2023) Timurkutluk, Bora; Ciflik, Yelda; Sonugur, Guray; Altan, Tolga; Genc, Omer; Colak, Andac Batur
    Artificial neural network (ANN) is used to model active three/triple phase boundaries (TPBs) in solid oxide fuel cell (SOFC) electrodes composed of phases with various particle sizes for the first time in the literature. Electrode mi crostructures comprising catalyst, electrolyte and pore phases with the same volume fraction, but various mean particle sizes are synthetically generated via Dream.3D software and the active TPB densities are measured by COMSOL software to obtain input data for training the ANN models as well as to validate the network results. In this regard, three learning methods of Bayesian regulation (BR), Levenberg-Marquardt (LM) and Scaled conjugate gradient (SCG) with various hidden layer and neuron numbers are examined. Among ANN models with three inputs and one output, the model with BR including one hidden layer and five neurons performs the best. This model revealing an average relative error of only 0.036 is then employed to simulate SOFC electrodes microstructures with new particle sizes not introduced in the learning process. The active TPB densities estimated by ANN are found to agree well with the computed ones. Therefore, ANN modeling is considered as a useful tool for the prediction of active TPB density in SOFC electrodes after a careful selection of backpropagation method and network structure.