Litcius/Paper detail

A Comprehensive Review of Predicting the Thermophysical Properties of Nanofluids Using Machine Learning Methods

Helin Wang, Xueye Chen

2022Industrial & Engineering Chemistry Research18 citationsDOI

Abstract

Nanofluids are often used as heat transfer fluids due to their good thermal and flow properties. Nanofluids are widely used in energy systems such as solar collectors, heat exchangers, and heat pipes. The thermophysical properties of nanofluids can significantly affect their performance in engineering systems. According to current research in this field, machine learning is a very attractive method to predict the thermophysical properties of nanofluids. We believe that, compared with experiments, machine learning methods are more efficient, rapid, accurate, and practical. The accuracy of the model is affected by factors such as the input variables, the data set selected during the modeling process, and the applied algorithm. This is a comprehensive review that describes the use of different machine learning methods to predict the thermophysical properties of nanofluids (conventional and hybrid nanofluids). This is very useful for researchers, scientists, and engineers in the field of nanofluids.

Topics & Concepts

NanofluidComputer scienceHeat transferHeat exchangerField (mathematics)Materials scienceProcess engineeringProcess (computing)ThermodynamicsMachine learningMechanical engineeringMathematicsEngineeringPhysicsOperating systemPure mathematicsNanofluid Flow and Heat TransferHeat Transfer MechanismsSolar Thermal and Photovoltaic Systems
A Comprehensive Review of Predicting the Thermophysical Properties of Nanofluids Using Machine Learning Methods | Litcius