A Neural Regression Model for Predicting Thermal Conductivity of CNT Nanofluids with Multiple Base Fluids

High thermal conductivity of carbon nanotube nanofluids (knf) has received great attention. However, the current researches are limited by experimental conditions and lack a comprehensive understanding of knf variation law. In view of proposition of data-driven methods in recent years, using experimental data to drive prediction is an effective way to obtain knf, which could clarify variation law of knf and thus greatly save experimental and time costs. This work proposed a neural regression model for predicting knf. It took into account four influencing factors, including carbon nanotube diameter, volume fraction, temperature and base fluid thermal conductivity (kf). Where, four conventional fluids with kf, including R113, water, ethylene glycol and ethylene glycol-water mixed liquid were considered as base fluid considers. By training this model, it can predict knf with different factors. Also, change law of four influencing factors considered on the knf enhancement has discussed and the correlation between different influencing factors and knf enhancement is presented. Finally, compared with nine common machine learning methods, the proposed neural regression model shown the highest accuracy among these.