Utilizing artificial neural networks to predict the thermal performance of conical tubes with pulsating flow

Abdelghany, Mohamed T.; Elshamy, Samir M.; Sharafeldin, M.A.; Abdellatif, Osama E.

doi:10.1016/j.applthermaleng.2023.120087

Cited by 7 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ANN that has stepped into the world in the mid-20th, is a computational scheme utilized to develop algorithms for modeling complex patterns [ 31 ]. The other effective technique to optimize the parameters and specify the best operating condition in the engineering processes is RSM [ [32] , [33] , [34] ] This scheme allows assessing the impacts of multiple parameters and their interactions on the examined responses [ [35] , [36] , [37] ].…”

Section: Introductionmentioning

confidence: 99%

Thermo-hydraulic performance optimization of a disk-shaped microchannel heat sink applying computational fluid dynamics, artificial neural network, and response surface methodology

Vaferi,

Vajdi,

Nekahi

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Thermo-hydraulic performance optimization of a disk-shaped microchannel heat sink applying computational fluid dynamics, artificial neural network, and response surface methodology

Vaferi,

Vajdi,

Nekahi

et al. 2023

Heliyon

View full text Add to dashboard Cite

Rapid heat source layout optimization in three‐dimensional integrated circuits using artificial neural network reduced‐order model in combination with Bayesian optimization

Zhang,

Song,

Rao

et al. 2024

Heat Trans

View full text Add to dashboard Cite

In this study, an efficient optimization framework was developed to determine the parameters of through‐silicon vias and the layout of heat sources in three‐dimensional integrated circuits (3D ICs), employing an artificial neural network (ANN) reduced‐order model in conjunction with a Bayesian optimization (BO) algorithm. The proposed method effectively predicts the temperature distribution in 3D ICs and refines their thermal parameters, offering solutions to thermal management challenges. Latin hypercube sampling was utilized for data sampling, enhancing the previously established rapid thermal analysis method through parameterization of heat source locations. The temperature distribution data for varying hotspot locations in 3D ICs were fitted using an appropriately defined objective function, leading to the development of a reduced‐order ANN model that accelerates temperature prediction. The computational results demonstrate that the neural network model exhibits a deviation in predicted values of less than 2%, and the coefficient of determination R2 approximately 0.93, underscoring high predictive accuracy. Additionally, the optimization outcomes and the efficiency of the selected BO algorithm were thoroughly evaluated. Notably, the BO algorithm achieved the global optimum in just 4.07 s across 250 iterations, demonstrating an effective power distribution strategy for the 3D ICs model.

show abstract

Experimental investigation on the effect of pulsating flow on heat transfer and pressure drop in conical tubes

Abdelghany

Elshamy

Sharafeldin

et al. 2023

J Therm Anal Calorim

View full text Add to dashboard Cite

In order to boost the heat transfer rate in a conical coiled tube (CCT) using an active technique, a solenoid valve was placed ahead of the CCT and employed as a pulse generator in this research. Experimentally, the effect of pulsation on heat transfer and pressure drop in the CCT was investigated. Experiments were conducted for pulsating flow throughout a Womersley number (Wo) range of 30–48, which corresponds to a pulsating frequency of 4–10 Hz, a Dean number (De) of 1148–2983, and a coil torsion (λ) of 0.02–0.052. Results revealed that pulsating flow yields larger Nu values than steady flow. A rise in heat transfer characteristics is achieved by decreasing both the pulse frequency and the coil torsion. A pulsating flow at 4 Hz (Wo = 30) was shown to promote heat transfer by the most of all the examined frequencies. The average Nu increases as De increases, although the friction factor often decreases as De increases. When the coil torsion is reduced from 0.052 to 0.02 while maintaining the same De and Wo, the average Nu and ƒ increase by 23% and 30%, respectively. A correlation for the average Nusselt number and friction factor was presented, taking frequency and coil torsion into account.

show abstract

Utilizing artificial neural networks to predict the thermal performance of conical tubes with pulsating flow

Cited by 7 publications

References 42 publications

Thermo-hydraulic performance optimization of a disk-shaped microchannel heat sink applying computational fluid dynamics, artificial neural network, and response surface methodology

Thermo-hydraulic performance optimization of a disk-shaped microchannel heat sink applying computational fluid dynamics, artificial neural network, and response surface methodology

Rapid heat source layout optimization in three‐dimensional integrated circuits using artificial neural network reduced‐order model in combination with Bayesian optimization

Experimental investigation on the effect of pulsating flow on heat transfer and pressure drop in conical tubes

Contact Info

Product

Resources

About