Response surface methodology (RSM) and artificial neural network (ANN) simulations for thermal flow hybrid nanofluid flow with Darcy-Forchheimer effects

Alhadri, Muapper; Raza, Jawad; Yashkun, Ubaidullah; Lund, Liaquat Ali; Maatki, Chemseddine; Khan, Sami Ullah; Kolsi, Lioua

doi:10.1016/j.jics.2022.100607

Cited by 54 publications

(10 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate ANN outcomes, error analysis must be performed. To give a mutual series for methods of measurement and training, the parameters should be normalized in the majority of cases when the input range is diverse (Alhadri, 2022). The prophetic capabilities of an ANN model will be determined by some suitable statistical error indices, including mean square error (MSE), performance, gradient and Mu.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Artificial neural network simulation and sensitivity analysis for optimal thermal transport of magnetic viscous fluid over shrinking wedge via RSM

Zeeshan

Khan

Ellahi

et al. 2023

HFF

View full text Add to dashboard Cite

Purpose This study aims to model the important flow response quantities over a shrinking wedge with the help of response surface methodology (RSM) and an artificial neural network (ANN). An ANN simulation for optimal thermal transport of incompressible viscous fluid under the impact of the magnetic effect (MHD) over a shrinking wedge with sensitivity analysis and optimization with RSM has yet not been investigated. This effort is devoted to filling the gap in existing literature. Design/methodology/approach A statistical experimental design is a setup with RSM using a central composite design (CCD). This setup involves the combination of values of input parameters such as porosity, shrinking and magnetic effect. The responses of skin friction coefficient and Nusselt number are required against each parameter combination of the experimental design, which is computed by solving the simplified form of the governing equations using bvp4c (a built-in technique in MATLAB). An empirical model for Cfx and Nux using RSM and ANN adopting the Levenberg–Marquardt algorithm based on trained neural networks (LMA-TNN) is attained. The empirical model for skin friction coefficient and Nusselt number using RSM has 99.96% and 99.99% coefficients of determination, respectively. Findings The values of these matrices show the goodness of fit for these quantities. The authors compared the results obtained from bvp4c, RSM and ANN and found them all to be in good agreement. A sensitivity analysis is performed, which shows that Cfx as well as Nux are most affected by porosity. However, they are least affected by magnetic parameters. Originality/value This study aims to simulate ANN and sensitivity analysis for optimal thermal transport of magnetic viscous fluid over shrinking wedge.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Artificial neural network simulation and sensitivity analysis for optimal thermal transport of magnetic viscous fluid over shrinking wedge via RSM

Zeeshan

Khan

Ellahi

et al. 2023

HFF

View full text Add to dashboard Cite

show abstract

“…Khashi'ie et al [57] deal with the RSM on the hybrid nanofluid flow subject to a vertical and permeable wedge. RSM and artificial neural network (ANN) simulations for thermal flow hybrid nanofluid flow with Darcy-Forchheimer effects have been conducted by Alhadri et al [58]. Myson and Mahanthesh [59] investigated the sensitivity analysis of nonlinear convective heat transport of a hybrid nano liquid sandwiched by micropolar liquid using RSM.…”

Section: Introductionmentioning

confidence: 99%

Mixed convection hybrid nanofluid flow over a stationary permeable vertical cone with thermal radiation and convective boundary condition

Yahaya,

Mustafa,

Arifin

et al. 2024

Z Angew Math Mech

View full text Add to dashboard Cite

Many real‐world devices, such as heat exchangers, geothermal reservoirs, and cooling systems, utilize the concept of boundary layer flow across a cone geometry. The current study presents and analyses the mathematical formulation for the mixed convection flow of a hybrid nanofluid over a permeable stationary cone. The heat transfer analysis considers the effects of thermal radiation and convective boundary condition. Numerical and statistical analyses of this flow problem yield new, physically significant results. The numerical analysis is carried out using the bvp4c solver in Matlab. Similarity transformations are performed to obtain a system of nonlinear ordinary differential equations from the governing partial differential equations and boundary conditions. In both assisting and opposing flows, spherical‐ and platelet‐shaped nanoparticles are observed to produce the lowest and highest local skin friction coefficient, respectively. The spherical‐ and blade‐shaped nanoparticles also offer the highest and lowest local Nusselt number, respectively, with a difference of 6.4% (assisting) and 6.03% (opposing). Meanwhile, the increase in the mixed convection parameter raised the velocity profile but diminished the temperature profile of the hybrid nanofluid. Then, the relationship of the Biot number , suction (S), and thermal radiation (R) parameters with the local Nusselt number is investigated through the response surface methodology (RSM). The local Nusselt number for the current flow problem is estimated to be maximized at 0.814323 (assisting) and 0.814629 (opposing) when these parameters are at the highest range of , , and . Several researchers had presented experimental studies conducted at different temperatures (15, 25, 35°C), mass flow rates (ranging from 0.00076 to 0.041 kg/s), and nanoparticle concentrations (0.387, 0.992, 3.12, 4.71 mass%).

show abstract

“…Notably, the influence of parameters related to suction, magnetism, and permeability on the solutions is found to be noteworthy. Moreover, for surfaces exhibiting reduction, an escalation in the volume fractions of copper nanoparticles leads to an enhancement in local skin friction, while causing a reduction in the local Nu [4]. This research investigates the utilization of an ANN coupled with the Back Propagated Levenberg Marquardt algorithm (BPLM) to analyze the entropy generation within a model of magnetohydrodynamic third-grade nanofluid flow (MHD-TGNFM) that incorporates chemical reactions and heat sink/source effects [35].The Ree-Eyring fluid model's nano-material flow is evaluated using a method called Levenberg Marquardt with backpropagated NNs in [41].…”

Section: Introductionmentioning

confidence: 99%

Neural network design for cubic autocatalysis chemical processes, the flow of a Darcy‐Forchheimer viscous fluid is optimized for entropy

Shah,

Raja,

Shoaib

et al. 2023

Z Angew Math Mech

View full text Add to dashboard Cite

In this article, neural network backpropagation (NNBP) is used to present two‐dimensional Darcy‐Forchheimer viscous fluid (DFVF) of viscous liquid against a stretching sheet under the influence of heat sink/source and viscous dissipation. Mathematical modelling and numerical simulation are also discussed. Thermal polymer processing, engineering processes, and industrial processes all benefit from the dynamic entropy generation phenomenon. Scientists are primarily interested in finding ways to decrease entropy formation to polish up the thermal performance of industrial systems. In this continuation, the optimal frame for the Darcy‐Forchheimer flow with a curved surface has been developed. Non‐linear partial systems are converted to dimensionless differential systems through the employment of the appropriate variables. Utilizing tools from the bvp4c method, the problem's highly nonlinear equations are numerically solved. These ODEs are solved by applying the bvp4c solution approach to produce the reference dataset for NNBP. Using this reference dataset in MATLAB, the graphs for the solution and error analysis for changing various parameters are analyzed. The performance of NNBP is validated using mean squared error data, regression analysis, and error histogram. The DFVF solution is examined using the testing, validation, and training procedures. Examined through influential variables the effects of fluid flow, thermal field, Bejan number, and concentration.

show abstract

Response surface methodology (RSM) and artificial neural network (ANN) simulations for thermal flow hybrid nanofluid flow with Darcy-Forchheimer effects

Cited by 54 publications

References 46 publications

Artificial neural network simulation and sensitivity analysis for optimal thermal transport of magnetic viscous fluid over shrinking wedge via RSM

Artificial neural network simulation and sensitivity analysis for optimal thermal transport of magnetic viscous fluid over shrinking wedge via RSM

Mixed convection hybrid nanofluid flow over a stationary permeable vertical cone with thermal radiation and convective boundary condition

Neural network design for cubic autocatalysis chemical processes, the flow of a Darcy‐Forchheimer viscous fluid is optimized for entropy

Contact Info

Product

Resources

About