In this study, an experimental study on the effect of temperature and particles concentration on the dynamic viscosity of MWCNT-OH and their composites with Ag, Au and Pd in water, ethylene glycol and ethylene glycol/water (60:40 vol%) is presented. The experiments were carried out in the solid weight fraction range of 0.0125–0.1 under the temperature range from 10 to 40 °C. The results show that the nanofluids behave as a Newtonian fluid for all solid mass fractions and temperatures considered. In addition, the dynamic viscosity increases with increasing the solid mass fraction and decreases with the temperature rising. Additionally, the performance of the artificial neural network (ANN) based on back propagation training with 20 neurons in hidden layer for predicting of behavior of above mention nanofluids was investigated. The AAD% of a collection of 192 data points for all nanofluids using the ANN at various temperatures, solid mass fractions, viscosity of based fluids, molar mass of based fluids and diameter of nanoparticles is 0.98%.