Recent advances in machine learning research for nanofluid heat transfer in renewable energy

Nanofluid has been pioneered as a novel generation heat transfer medium, which has advanced the heat transfer performance for the past two decades in renewable energy. Machine learning (ML) has drawn considerable attention in the last few years. ML techniques have proved suitable in nanofluid research regarding the thermophysical properties’ prediction and thermal performance in different heat transfer applications. This chapter presents an outline of ML, its techniques, and nanofluids’ thermophysical properties applied in heat transfer systems. Models pioneered by various ML approaches such as Multilayer perception artificial neural network (ANN), Adaptive neuro-fuzzy inference system, Radial basis function network, and Least Square support vector machine have been presented. The ANN approach is a promising approach for demonstrating numerically the heat transfer behavior of nanofluids, with the multilayer perceptron being the most studied type. The parameters such as thermal conductivity, viscosity, specific heat, exergy efficiency, pressure drop, and Nusselt number have been computed as outputs by learning algorithms. In the last section, challenges and future opportunities have been discussed.