Designing a committee of machines for modeling viscosity of water-based nanofluids

Viscosity is a crucial thermophysical feature of substance that must be accurately determined before designing system with nanofluid as the working fluid. In this study, modern technique committee machine intelligent (CMIS) used for establishing predictive model relative viscosity water-based nanofluids. The was developed by considering 1440 experimental data points different types nanofluids containing Al2O3, SiC, SiO2, TiO2, CuO, nanodiamond, and Fe3O4 nanoparticles. CMIS combines three models including multilayer perceptron (MLP) trained Levenberg-Marquardt (LM), an MLP Bayesian Regularization (BR) radial basis function (RBF) approach to estimate Statistical graphical error criteria revealed successfully estimates all over whole ranges operational conditions mean absolute approximately 1.25%. According their precision performance, established provides best followed BR-MLP, LM-MLP, RBF models. Moreover, performance estimation capability verified against 13 theoretical empirical