Thermal Resistance Modeling of Oscillating Heat Pipes for Nanofluids by Artificial Intelligence Approach

Abstract

In this study, thermal resistance of a closed-loop oscillating heat pipe (OHP) is investigated using experimental tests and artificial intelligence methods. For this target, γFe2O3 and Fe3O4 nanoparticles are mixed with the base fluid. Also, intelligent models are developed to predict the thermal resistance of the OHP. These models are developed based on the heat input into evaporator section, the thermal conductivity of working fluids, and the ratio of the inner diameter to length of OHP. The intelligent methods are multilayer feed-forward neural network (MLFFNN), adaptive neuro-fuzzy inference system (ANFIS) and group method of data handling (GMDH) type neural network. Thermal resistance of the heat pipe (as a measure of thermal performance) is considered as the target. The results showed that using the nanofluids as working fluid in the OHP decreased the thermal resistance, where this decrease for Fe3O4/water nanofluid was more than that of γFe2O3/water. The intelligent models also predicted successfully the thermal resistance of OHP with a correlation coefficient close to 1. The root-mean-square error (RMSE) for MLFFNN, ANFIS, and GMDH models was obtained as 0.0508, 0.0556, and 0.0569 (°C/W) (for the test data), respectively.