Artificial Neural Network for Modeling Thermal Conductivity of Biodiesels with Different Metallic Nanoparticles for Heat Transfer Applications

Thermal conductivity of two types of nanobiodiesels (NBs) was investigated theoretically and experimentally. The first type of NBs (C4-Au) was composed of C4 biodiesel (purchased from Biofuels of Mexico) filled with Au nanoparticles (Au-NPs) and the second type (SB-Ag) was composed of soybean biodiesel (SB) filled with Ag nanoparticles (Ag-NPs). It has been demonstrated in the literature that the addition of Au-NPs or Ag-NPs to biodiesel can lead to a significant increase in thermal properties. The photothermal techniques were used to determine the thermal diffusivity (D), thermal effusivity (e), and thermal conductivity (k) of biodiesel filled with Au-NPs or Ag-NPs for different concentrations. For about two decades, researchers have made the effort to predict the enhancement of the thermal conductivity of nanofluids based on experiments and several theoretical models have been proposed. One of these analytical models, which have allowed researchers to calculate the thermal conductivity of the nanofluids, is the Hamilton–Crosser Model. This model is based on the classical theory of compounds and mixtures containing particles in the order of millimeters or micrometers and fails dramatically in predicting the thermal conductivity of nanofluids. In that sense, the Hamilton–Crosser model (H–C) cannot represent adequately the enhancement in k as a function of NP’s concentration. Then, the artificial neural network (ANN) modeling method was used to predict the thermal conductivity of the two NBs studied in this work.