The thermal conductivity of nanofluids depends on several factors such as temperature,
concentration and temperature. These parameters have the most significant effect on thermal
conductivity compared with other factors. In the present study, the accuracy of trained Perceptron
neural network with 10 neurons and three input variables including size of nanoparticles,
temperature and concentration is evaluated. The sum of squared errors and the correlation
coefficient of the trained neural network are equal to 0.99293 and 0.00031, respectively.
