Nanofluids, colloidal suspensions of nanoparticles in base fluids, exhibit fascinating thermophysical properties that have garnered significant attention in various fields, particularly in thermal engineering and nanotechnology. Accurate prediction of these properties is crucial for their effective utilization in applications such as heat transfer enhancement, cooling systems and advanced manufacturing processes. Traditional methods for predicting nanofluids properties often face challenges due to the complex interactions between nanoparticles and base fluids. In recent years, artificial intelligence (AI) techniques have emerged as promising tools for predicting the thermophysical properties of nanofluids. This article provides a comprehensive review of the application of AI methods, including machine learning and deep learning, in predicting the thermophysical properties of nanofluids. The review explores various AI algorithms, data sources and modelling approaches employed in this domain, highlighting their advantages, limitations and future prospects.
HTML PDFShare this article
Physical Mathematics received 686 citations as per Google Scholar report
