International Journal of Energy Research, Journal Year: 2022, Volume and Issue: 46(13), P. 19242 - 19257

Published: April 23, 2022

Hybrid nanofluids are gaining popularity owing to the synergistic effects of nanoparticles, which provide them with better heat transfer capabilities than base fluids and normal nanofluids. The thermophysical characteristics hybrid critical in shaping transmission properties. As a result, before using qualities industrial applications, an in-depth investigation properties is required. In this paper, metamodel framework constructed forecast effect nanofluid temperature concentration on numerous parameters Fe3O4-coated MWCNT Evolutionary gene expression programming (GEP) adaptive neural fuzzy inference system (ANFIS) were employed develop prediction models. model was trained 70% datasets, remaining 15% used for testing validation. A variety statistical measurements Taylor's diagrams assess proposed Pearson's correlation coefficient (R), determination (R2) regression index, error evaluated root mean squared (RMSE). model's comprehensive assessment additionally includes modern efficiency indices such as Kling-Gupta (KGE) Nash-Sutcliffe (NSCE). models demonstrated impressive capabilities. However, GEP (R > 0.9825, R2 0.9654, RMSE = 0.7929, KGE 0.9188, NSCE 0.9566) outperformed ANFIS 0.9601, 0.9218, 1.495, 0.8015, 0.8745) majority findings. generated robust enough replace repetitive expensive lab procedures required measure Highlights Predictions AI-based performed well GEP-based prognostic validated compared Taylor

Language: Английский