Machine Learning Approach for Thermal Characteristics and Improvement of Heat Transfer of Nanofluids—A Review

Machine learning (ML) provides an array of methodologies for understanding many challenging obstacles in multiple domains, mostly the discipline of heat transfer and thermal systems. In nanofluid investigations about thermophysical attribute prediction and thermo-hydrodynamic performance testing, machine learning methods would be particularly helpful. The goal of the current review is to examine the advantages and uses of various machine learning algorithms applied in nanofluid-based vapour compression refrigeration systems and to highlight recent advancements in this field. The rapid development of nanofluids is being driven by a record amount of data from experiments, field observations, and extensive simulations at multiple space and time scales. There are many ways to collect data-related information from machine learning that can be used to comprehend the use of nanofluids. The importance of ML in assessing the thermophysical characteristics of nanofluid is in-depth highlighted. The forecasting of thermophysical characteristics and heat transfer rate using data-driven machine learning techniques will be helpful in finding the most important aspects in nanofluid research.