Applying Artificial Neural Networks (ANNs) for prediction of the thermal characteristics of water/ethylene glycol-based mono, binary and ternary nanofluids containing MWCNTs, titania, and zinc oxide

Hybrid nanocomposites impact on heat transfer efficiency and pressure drop in turbulent flow systems: application of numerical and machine learning insights

This research explores the feasibility of using a nanocomposite from multi-walled carbon nanotubes (MWCNTs) and graphene nanoplatelets (GNPs) for thermal engineering applications. The hybrid nanocomposites were suspended in water at various volumetric concentrations. Their heat transfer and pressure drop characteristics were analyzed using computational fluid dynamics and artificial neural network models. The study examined flow regimes with Reynolds numbers between 5000 and 17,000, inlet fluid temperatures ranging from 293.15 to 333.15 K, and concentrations from 0.01 to 0.2% by volume. The numerical results were validated against empirical correlations for heat transfer coefficient and pressure drop, showing an acceptable average error. The findings revealed that the heat transfer coefficient and pressure drop increased significantly with higher inlet temperatures and concentrations, achieving approximately 45.22% and 452.90%, respectively. These results suggested that MWCNTs-GNPs nanocomposites hold promise for enhancing the performance of thermal systems, offering a potential pathway for developing and optimizing advanced thermal engineering solutions.

Modelling the effects of mixing ratio and temperature on the thermal conductivity of GNP-Alumina hybrid nanofluids: A comparison of ANN, RSM, and linear regression methods

This research aimed to evaluate and compare the efficacy of three distinct methods for forecasting the thermal conductivity of GNP-Alumina hybrid nanofluids. The methods under consideration were artificial neural network (ANN), response surface methodology (RSM), and linear regression (LR). The predictive performance of the ANN model was investigated in relation to the number of neurons in the hidden layer. The findings revealed that the optimal number of neurons was 7, which produced the best performance with an overall mean square error (MSE) of 1.08E-06. The correlation coefficient was also high at 0.99799. The RSM approach involved testing linear, quadratic, cubic, and quartic models, with the quadratic model showing the highest predicted R2 (0.9721) values, indicating that it provided the best fit to the data. Finally, the LR model was developed using a backward elimination approach, with temperature and volume fraction being the significant variables in the final model. Overall, the ANN model produced the most accurate predictions, followed by the RSM and LR models. These findings suggest that the ANN and RSM techniques can be effective tools for forecasting the thermal conductivity of nanofluids, and highlight the importance of selecting appropriate model parameters for optimal performance.

New Solutions of Fractional Jeffrey Fluid with Ternary Nanoparticles Approach

The existing work deals with the Jeffrey fluid having an unsteady flow, which is moving along a vertical plate. A fractional model with ternary, hybrid, and nanoparticles is obtained. Using suitable dimensionless parameters, the equations for energy, momentum, and Fourier's law were converted into non-dimensional equations. In order to obtain a fractional model, a fractional operator known as the Prabhakar operator is used. To find a generalized solution for temperature as well as a velocity field, the Laplace transform is used. With the help of graphs, the impact of various parameters on velocity as well as temperature distribution is obtained. As a result, it is noted that ternary nanoparticles approach can be used to increase the temperature than the results obtained in the recent existing literature. The obtained solutions are also useful in the sense of choosing base fluids (water, kerosene and engine oil) for nanoparticles to achieved the desired results. Further, by finding the specific value of fractional parameters, the thermal and boundary layers can be controlled for different times. Such a fractional approach is very helpful in handling the experimental data by using theoretical information. Moreover, the rate of heat transfer for ternary nanoparticles is greater in comparison to hybrid and mono nanoparticles. For large values of fractional parameters, the rate of heat transfer decreases while skin friction increases. Finally, the present results are the improvement of the results that have already been published recently in the existing literature. Fractional calculus enables us to control the boundary layers as well as rate of heat transfer and skin friction for finding suitable values of fractional parameters. This approach can be very helpful in electronic devices and industrial heat management system.