Computational intelligence of Levenberg-Marquardt backpropagation neural networks to study the dynamics of expanding/contracting cylinder for Cross magneto-nanofluid flow model

Abstract: Exploration and exploitation of artificial intelligence (AI) techniques have growing interest for the research community investigating in engineering and technological fields to provide improved efficiencies and augmented human abilities in daily live operations, business strategies and society evolution. A novel application of AI based backpropagating networks (BPNs) was presented for bioconvection model in transverse transportation of rheological fluid involving Lorentz force interaction and gyrotactic microorganisms. The governing nonlinear PDEs for bioconvection rheological fluidic system (BRFS) was reduced to nonlinear system of ODEs by competency of similarity adjustments. A reference data of designed BPNs was constructed for variants of BRFS representing scenarios for thermophoresis parameter, Brownian motion, Prandtl numbers, magnetic variables, squeezing and Lewis numbers by applying the Adams numerical solver. The said data were segmented arbitrary in training, testing, and validation sets to execute BPNs to calculate the approximate solutions for variants of BRFS and comparison with standard solution to validate the consistent accuracy. The worthy performance of AI based BPNs was additionally certified by learning curve on MSE based fitness, histograms and regression metrics.

Abstract: The aim of this study is to present the numerical solutions of the higher order singular nonlinear differential equations using an advanced intelligent computational approach by manipulating the Morlet wavelet (MW) neural networks (NNs), global approach as genetic algorithm (GA) and quick local search approach as interior-point method (IPM), i.e., GA-IPM. MWNNs is applied to discretize the higher order singular nonlinear differential equations to express the activation function using the mean square error. The performance of the designed MWNNs using the GA-IPM is observed to solve three different variants based on the higher order singular nonlinear differential model to check the significance, efficacy and consistency of the designed MWNNs using the GA-IPM. Furthermore, statistical performances are provided to check the precision, accuracy and convergence of the present approach.

Abstract: The aim of study is to investigate the mass and heat transfer phenomena in hybrid hydro-nanofluidic system involving Al2O3–Cu–H2O over the rotating disk in porous medium with viscous dissolution and Joule heating through the stochastic solver by way of Levenberg-Marquardt backpropagation neural networks. The mathematical model in system of PDEs describes the physical phenomena of the hybrid hydro-nanofluid flow problem are converted into set of ODEs by means of scaling group transformations. The datasets are constructed by utilizing the power of explicit Runge-Kutta numerical method that help to the develop a continuous neural networks mapping. The validation, training and testing processes are utilized to learn the neural network mapping to estimate the solution of various scenarios with cases that are constructed by varying different values of physical constraints such as porosity factor, inertia coefficient, Prandtl number, Brinkman number, radiation parameter, mgnetic parameter, concentration of nanoparticles on the velocities and temperature profiles. Determination, convergence, verification and stability of Levenberg-Marquardt backpropogation neural network mappings are validated on the assessment of achieved accuracy through regression based statistical analysis, mean squared error and error histograms for hybrid hydro-nanofluidic model.

Abstract: This article examines entropy production (EP) of magneto-hydrodynamics viscous fluid flow model (MHD-VFFM) subject to a variable thickness surface with heat sink/source effect by utilizing the inte...

Abstract: Hybrid nanofluid gains attention of scientists due to its dynamic properties in various fields, and thus, hybrid nanofluids can be taken as an innovative form of nanofluids. Even though analysts ac...

Abstract: Heat transfer and fluid flow due to buoyancy forces in a partially heated enclosure using nanofluids is carried out using different types of nanoparticles. The flush mounted heater is located to the left vertical wall with a finite length. The temperature of the right vertical wall is lower than that of heater while other walls are insulated. The finite volume technique is used to solve the governing equations. Calculations were performed for Rayleigh number (103 ⩽ Ra ⩽ 5 × 105), height of heater (0.1 ⩽ h ⩽ 0.75), location of heater (0.25 ⩽ yp ⩽ 0.75), aspect ratio (0.5 ⩽ A ⩽ 2) and volume fraction of nanoparticles (0 ⩽ φ ⩽ 0.2). Different types of nanoparticles were tested. An increase in mean Nusselt number was found with the volume fraction of nanoparticles for the whole range of Rayleigh number. Heat transfer also increases with increasing of height of heater. It was found that the heater location affects the flow and temperature fields when using nanofluids. It was found that the heat transfer enhancement, using nanofluids, is more pronounced at low aspect ratio than at high aspect ratio.

Abstract: In this paper magnetohydrodynamics nanofluid hydrothermal treatment in a cubic cavity heated from below is presented. The mathematical model consists of continuity and the momentum equations, while a new model is proposed to see the effects Brownian motion on the effective viscosity and thermal conductivity of nanofluid. The Lattice Boltzmann method is utilized to simulate three dimensional problems. The Koo–Kleinstreuer–Li correlation is also taken into account. Numerical calculation is made for different values of Hartmann number, nanoparticle volume fraction and Rayleigh number. The results are presented graphically in terms of streamlines, isotherms and isokinetic energy as well as Nusselt number. It is observed that the applying magnetic field results in a force opposite to the flow direction that leads to drag the flow and then reduces the convection currents by reducing the velocities. Also it can be concluded that Nusselt number is an increasing function of Rayleigh number and nanofluid volume fraction while it is a decreasing function of Hartmann number.

Abstract: The present work explores the magnetohydrodynamic (MHD) flow of Carreau nanoliquid by exponentially convected stretchable surface. Formulation and computations are presented for Brownian motion and thermophoresis. Concentration by zero mass condition is reported. Consideration of thermal radiation characterizes the heat transfer process. Transformation procedure is utilized for reduction of PDEs into ODEs. Highly nonlinear complex problems are computed numerically through Runge–Kutta Fehlberg technique. Salient characteristics of local Weissenberg number, Hartman number, Biot number, thermophoresis parameter, Prandtl number, thermal radiation parameter and Schmidt number on the velocity, temperature, nanoparticles concentration, surface drag force and Nusselt number are reported through graphs and Tables. The results demonstrated here reveal that the velocity distribution for local Weissenberg number in case of shear thinning liquid reduces whereas it increments for shear thickening liquid. Temperature and thermal layer thickness are increasing functions of thermal radiation. Besides this the results of presented analysis are compared with the available works in particular situations and reasonable agreement is noted.

Abstract: Due to the variation in fluid flow behavior in various physical conditions, the presented study have been performed an investigation of cross-fluid flow containing gyrotactic microorganisms and nanoparticles on a horizontal and three-dimensional cylinder considering viscous dissipation and magnetic field. The governing equations of the problem have been solved by the Runge-Kutta fifth-order method. The aim of this study is to inspect the effects of cross fluid, microorganisms, and magnetic field, on velocity, temperature, and concentration profiles. Also, Heat flux and mass flux values for nanoparticles and microorganisms have been calculated in tabular form. In this research, the simultaneous utilization of nanoparticles with motile microorganisms in cross fluid, and three-dimensional assessment on the cylinder has been proposed as an innovation. The results show that, when the Brownian motion parameter varies from 0.1 to 0.4 and at η = 4 , the concentration of nanoparticle deduces about 80.43%. Furthermore, with the change of bioconvection Lewis number from 0.2 to 0.5, it was observed that the concentration of the microorganisms reduced about 78.38%.