semi-experimental model to predict thermal conductivity coefficient of nanofluids using artificial neural networks (ann)

Attempts were made in the present study to propose an artificial neural network (ann) model for the proper estimation of thermal conductivity of nanofluids. the ann model was designed based on using 800 existing experimental data containing spherical nanoparticles of al2o3, tio2, cuo, zno, zro2, ceo2, mgo, sio2, al, cu, fe, ag, sic, diamond fe2o3, and fe3o4 dispersed in various base fluids of water, ethylene glycol, radiator cooling, and oils. five effective parameters include the thermal conductivity of the main fluid and nanoparticles, volume fraction of the nanoparticles (0.4−0.4 %), temperature (10−80 ℃), and particle diameter (4−150 nm) were considered as input values, and the thermal conductivity of nanofluid was defined as the target variable. the levenberg-marquardt (l-m) back-propagation algorithm was used to design this model. according to results, the best r and lowest mse using 5-13-1 topology were founded to be about 0.9965 and 0.000238, respectively, indicating good fitting between predicted results and target points. also, the results of comparison between the ann model and experimental points indicated successful validation of the presented model for estimating the thermal conductivity of nanofluids.