Accurate Prediction of Hybrid Nanofluids Viscosity: A Comparison of Soft Computational Approaches, Empirical, and Theoretical Models DOI

Hossein Ghadery‐Fahliyany,

Majid Mohammadi,

Mohammad Haji‐Savameri

и другие.

Advanced Theory and Simulations, Год журнала: 2025, Номер unknown

Опубликована: Май 30, 2025

Abstract Hybrid nanofluids exhibit enhanced thermal properties compared to conventional nanofluids. Viscosity, critical for assessing heat transfer efficiency, influences pressure drop and pumping power. This study models hybrid nanofluid viscosity using Radial Basis Function (RBF), Multilayer Perceptron (MLP), a Committee Machine Intelligent System (CMIS). A dataset of 584 data points is utilized. Particle Swarm Optimization (PSO) Farmland Fertility Algorithm (FFA) are employed train the RBF, while MLP utilized Scaled Conjugate Gradient (SCG), Bayesian Regularization (BR), Levenberg‐Marquardt (LM) algorithms. The CMIS created by integrating MLP‐BR, RBF‐FFA, RBF‐PSO networks. AAPRE values RBF‐PSO, MLP‐LM, MLP‐SCG, 1.7464, 1.6647, 2.6851, 2.1889, 2.1792, 1.519, respectively. R 2 0.9689, 0.9394, 0.4794, 0.9727, 0.9404, 0.9688, respectively, which indicates that model with lowest Average Absolute Percent Relative Error (AAPRE) highest Determination Coefficient (R ) value most accurate outperforms other in estimating viscosity, demonstrating greater accuracy than empirical theoretical models. Sensitivity analysis showed temperature has significant positive impact on nanoparticle size negative effect. reliable predicting exhibiting broad application range minimal outlier data.

Язык: Английский

Improving the Thermal Performance of Flat-Plate Solar Collectors for Building Applications Through Hybrid Nanofluids and Vortex-Inducing Geometries DOI Creative Commons
Rashid Khan,

Waqed H. Hassan,

As’ad Alizadeh

и другие.

Case Studies in Thermal Engineering, Год журнала: 2025, Номер unknown, С. 106377 - 106377

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Accurate Prediction of Hybrid Nanofluids Viscosity: A Comparison of Soft Computational Approaches, Empirical, and Theoretical Models DOI

Hossein Ghadery‐Fahliyany,

Majid Mohammadi,

Mohammad Haji‐Savameri

и другие.

Advanced Theory and Simulations, Год журнала: 2025, Номер unknown

Опубликована: Май 30, 2025

Abstract Hybrid nanofluids exhibit enhanced thermal properties compared to conventional nanofluids. Viscosity, critical for assessing heat transfer efficiency, influences pressure drop and pumping power. This study models hybrid nanofluid viscosity using Radial Basis Function (RBF), Multilayer Perceptron (MLP), a Committee Machine Intelligent System (CMIS). A dataset of 584 data points is utilized. Particle Swarm Optimization (PSO) Farmland Fertility Algorithm (FFA) are employed train the RBF, while MLP utilized Scaled Conjugate Gradient (SCG), Bayesian Regularization (BR), Levenberg‐Marquardt (LM) algorithms. The CMIS created by integrating MLP‐BR, RBF‐FFA, RBF‐PSO networks. AAPRE values RBF‐PSO, MLP‐LM, MLP‐SCG, 1.7464, 1.6647, 2.6851, 2.1889, 2.1792, 1.519, respectively. R 2 0.9689, 0.9394, 0.4794, 0.9727, 0.9404, 0.9688, respectively, which indicates that model with lowest Average Absolute Percent Relative Error (AAPRE) highest Determination Coefficient (R ) value most accurate outperforms other in estimating viscosity, demonstrating greater accuracy than empirical theoretical models. Sensitivity analysis showed temperature has significant positive impact on nanoparticle size negative effect. reliable predicting exhibiting broad application range minimal outlier data.

Язык: Английский

Процитировано

0