International Journal of Heat and Mass Transfer | 2021
Developing Convective Mass Transfer of Nanofluids in Fully Developed Flow Regimes in a Circular Tube: Modeling using Fuzzy Inference System and ANFIS
Abstract
Abstract In this study, actual nanofluids Sherwood numbers were compared by the Look-up Table-based Fuzzy Inference System (LUT-based FIS) and the Fuzzy C-means Adaptive Nero Fuzzy Inference System (FCM-ANFIS) predicted data in a circular tube under both laminar and turbulent flow regimes. Three influential parameters including material types, Reynolds numbers, and nanoparticles volume concentrations were used as the input attributes. Intelligent models had also one output presented by Sherwood numbers. The results revealed that nanoparticles size and type could play an important role in determining the mass transfer in nanofluids and the optimum nanoparticle concentration. The maximum increase in mass transfer for all nanofluids occurred in laminar flow, 36% in a 0.03% TiO2, 21% in a 0.0057% SiO2, and 16.8% in 0.01% Al2O3 nanofluids. Comparison of the experimental data with the predicted ones by FIS and ANFIS models showed that these models could predict convective mass transfer in nanofluids, while ANFIS models with only 5 rules and the shorter running time (19 s) had a simpler structure and precisely imitated the mass transfer. The best RMSE and R2 for the test data under laminar and turbulent flow were 0.044, 0.98, and 0.022, 0.99, respectively.