Assessment of thermal conductivity and viscosity of alumina-based engine coolant nanofluids using random forest approach

Thermal conductivity and viscosity are crucial thermophysical properties of nanofluids. They play a pivotal role in industries involved with heat transfer applications. Alumina (Al2O3) nanoparticles known to be good additive for enhancement favorable results countless research. However, the measurement nanofluids through experimental is expensive. Therefore, random forest (RF), an advanced computational intelligence approach, proposed correctly predict thermal alumina-based engine coolant this Experimental data from previous literature utilized as input parameters development models. The prediction temperature concentration, whereas temperature, shear rate. Error metrics consisting R-squared (R2), Adjusted (A-R2), Mean Squared (MSE), Root (RMSE), Absolute (MAE) used analyze determine performance each model. Based on results, it observed that all models exhibit significantly high consistent predictive accuracy R2 0.9877 0.9974 prediction. can enhanced by training multiple datasets which include several diversified