Thermal analysis of a viscoelastic Maxwell hybrid nanofluid with graphene and polythiophene nanoparticles: Insights from an artificial neural network model

Alexandria Engineering Journal 94 (2024) 193–211 Available online 26 March 2024 1110-0168/© 2024 The Author(s). Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Thermal analysis of a viscoelastic Maxwell hybrid nanofluid with graphene and polythiophene nanoparticles: Insights from an artificial neural network model Muhammad Sheraz Junaid a , Muhammad Nauman Aslam a , * , Muhammad Asim Khan b , Salman Saleem c , Muhammad Bilal Riaz d , e , ** a Department of Mathematics and Statistics, The University of Lahore, Lahore, Pakistan b School of Chemistry and Chemical Engineering, Linyi University China, China c Department of Mathematics, College of Science, King Khalid University, Abha 61413, Saudi Arabia d IT4Innovations, VSB – Technical University of Ostrava, Ostrava, Czech Republic e Department of Computer Science and Mathematics, Lebanese American University, Byblos, Lebanon ARTICLE INFO Keywords: Thermal radiations Maxwell fluid Artificial neural networking EMHD Hybrid nanofluid ABSTRACT The utilization of solar radiation by converting them into thermal energy is discussed in this paper. Nanoparticles improve the ability of heat transfer therefore, it is beneficial in the use of solar thermal systems and energy storage devices. The novel mixture of nanoparticles Graphene and Polythiophene in base fluid, which has high thermodynamic properties for the improvement of thermal effect with electromagnetic effect by using Maxwell fluid model is discussed. Polyvinyl alcohol water is taken as base fluid flowing through a moveable flat plat. The governing partial differential equations are transformed into ordinary differential equations. The semi-analytical technique, homotopy analysis method is used to obtain the solution of the ordinary differential equations. The velocity is enhanced with magnetic and electric field strength. The increase of the Prandtl number, Eckert number and chemical reaction parameter, exceeds the thermal effect which produces more entropy generation and heat enhancement. The results show that the hybrid nanofluid with this Novel mixture is highly thermodynamic with higher entropy and rapid thermal augmentation which can be used in energy production and energy storage devices. A novel intelligent numerical computing technique multi-layer perceptron with feedforward back-propagation, an artificial neural networking method with the Levenberg-Marquard algorithm is used in this model. The data is gathered for the neural networking method training, validation, and testing. The efficiency of the model is obtained and mean square error is obtained by artificial neural networking. 1. Introduction Global warming or green-house effects are caused when carbon dioxide, toxic particles and air pollutants trap heat for decades in the earth’s atmosphere which causes earth to become warmer. That is why to avoid these effects, researchers are working on renewable energy. In last two decades significant research has been done for energy production and energy storage devices. The nanoparticles and material with different fluids are taken under analysis for more improved performance of energy production. Especially the artificial neural network structures are beneficial for the description and prediction of performance. To enhance performance of energy storage and production devices, nanoparticles have significant role with viscous non-Newtonian fluids. Maxwell fluid model is used for the description of viscous nonNewtonian fluids. Sudarmozhi et al. [1] investigate Maxwell fluid through a porous inclined vertical plate. Magnetic radiation effect with heat convective boundary layer is taken for the flow, which causes an increase of temperature of the fluid because of more electric field and velocity of the fluid goes down. Abbas et al. [2] scrutinized Maxwell fluid under the influence of Soret-Dufour and second-order slips flow with thermal slip. Transport phenomena of the fluid are under study. They analyze the fluid velocity enhancement with the increment of velocity slip condition, whereas thermal thickness declines. Maxwell fluid flow through a stretching plate has applications in energy production as solar thermal devices and parabolic solar * Corresponding author. ** Corresponding author at: IT4Innovations, VSB – Technical University of Ostrava, Ostrava, Czech Republic. E-mail addresses: [email protected] (M.N. Aslam), [email protected] (M.B. Riaz). Contents lists available at ScienceDirect Alexandria Engineering Journal journal homepage: www.elsevier.com/locate/aej https://doi.org/10.1016/j.aej.2024.03.029 Received 14 December 2023; Received in revised form 15 February 2024; Accepted 12 March 2024 Alexandria Engineering Journal 94 (2024) 193–211 194 collectors, energy storage devices as electrolyte flow in batteries, and polymer processing. Bhatti et al. [3] discussed Maxwell fluid flow through a stretchable surface with the effect of quadratic convection and non-Fourier heat flux. The spectral investigation is taken with the use of Lie symmetry transformations. The computational study produces a reduction in temperature and an enhancement of velocity. Sudarmozhi et al. [4] studied Maxwell fluid flow through a porous medium under the influence of magnetohydrodynamic with double diffusion. Thermal effects with radiation effect and chemical reaction is taken. Radiation effect enhances the temperature and concentration goes down due to chemical reaction. Riaz et al. [5] investigated Maxwell fluid flow with fractional derivatives and in the presence of nanoparticles. Fractional parameters are analyzed to be a better solution for experiments and theoretical facts. Nanoparticles enhance thermal effect and slow down the velocity of the fluid. Yasin et al. [6] analyzed Maxwell fluid with peristaltically induced flow with the influence of Darcy’s law and the Hall effect with slip conditions. Hartman number slows down the velocity, whereas Hall current enhances it. Thermal analysis is a way to enhance heat transfer rate, heat exchanger systems, thermal and hydrodynamic systems. It is essential for the working of automotive cooling, refrigeration and heat exchangers. That is why it is interesting to investigate innovative ideas about thermal analysis. A variety of methods suggested by scholars to enhance thermal ability, and still scholars and scientists are working on better ideas to save energy [7–11]. Jalili et al. [12] investigated thermal analysis of nanofluid flow with thermophoresis, Brownian motion, and under the effect of Hall current. Prandtl number and Brownian motion directly effects the temperature of the fluid, while concentration declines. Kumar et al. [13] scrutinized the thermal analysis of a moving plate, of non-Fourier heat flux model. Convection-conduction and radiation-conduction are gained with the reduction of thermal analysis. Bothe et al. [14] analyzed thermal analysis of electrical double layer capacitors with the use of thermal analysis cell. The investigation is taken under electrochemical properties and in-situ simulations. The analysis provide that the electro-double layer capacitors have better stability. Tan et al. [15] discussed thermal analysis numerically of nanofluid flowing through a porous medium with curved hot wall. The region of flow is taken through wavy shapes of the wall. The speed of the fluid is noticed to be slower down in the medium while the conductivity of the fluid is enhanced by 11.97%. Regordosa et al. [16] investigated thermal analysis of carbon and silicon to be able to contents of the cast of Nomenclature u,v Velocity components T Temperature Γ Angle of inclination k Thermal conductivity Cp Heat capacity Qe Heat source Uw Variable velocity B(t)Magnetic field impact E Electric field λ Fluid relaxation Pr Prandtl number hf Heat transfer cg Mass transfer Ec Eckert number NG Entropy generation Be Bejan number Nb Brownian diffusion parameter M Magnetic field Nt Thermophoresis diffusion parameter θ Temperature profile ϕ Concentration profile ϕ1 Volume fraction of Graphene Oxide ϕ2 Volume fraction of Polythiophene Le Lewis number A Unsteadiness parameter k Chemical reaction parameter Bi Biot number Br Brinkman number Cf Skin friction Nux Nusselt number Shx Sherwood number L Diffusion parameter Subscripts f Fluid hnf Hybrid nanofluid w At the surface ∞ Free stream Table 1 Thermophysical properties of hybrid nanofluid. Property hybrid nanofluid Thermal Conductivity khnf kf=(ϕ1ks1+ϕ2ks2 ϕhnf )+2kf+2(ϕ1ks1+ϕ2ks2)− 2ϕhnf kf (ϕ1ks1+ϕ2 ρ s2 ϕhnf )+2kf− (ϕ1ks1+ϕ2ks2)+ϕhnf kf Dynamic viscosity μ hnf = μ f (1−ϕhnf )2.5 Density ρ hnf = (1−ϕhnf ) ρ f+ϕ2 ρ s2+ϕ1 ρ s1 Heat Capacity ( ρ Cp)hnf = (1−ϕhnf )( ρ Cp)f+ ( ρ Cp)s1ϕ1+ ( ρ Cp)s2ϕ2 Electric conductivity σ hnf σ f= (ϕ1 ρ s1+ϕ2 ρ s2 ϕhnf )+2 σ f+2(ϕ1 ρ s1+ϕ2 ρ s2)− 2ϕhnf σ f (ϕ1 ρ s1+ϕ2 ρ s2 ϕhnf )+2 σ f− (ϕ1 ρ s1+ϕ2 ρ s2)+ϕhnf σ f Table 2 Thermophysical characteristics of base liquids [43] and nanoparticles. Property Water PVA Graphene Oxide Polythiophene Cp (J/kgK)4179 2000 765 2545 ρ (kg/m3)997.1 1020 3600 1060 k (W/mK)0.613 0.2 2000 4.4 σ (S/m)0.05 11.7×10 −6 4.57×10 −8 0.1 Table 2* Comparing values of θ ′ (0)with variant inPr, when A=0,Γ=0,φ=0,Nr =0, Ec =0and Bi =0. Pr Ref.[59] Ref. [60] Ref. [52] Present 0.72 0.80876181 0.80876181 0.80876181 0.80876181 1.0 1.00000000 1.00000000 1.00000000 1.00000000 3.0 1.92357420 1.92357420 1.92357420 1.92357420 7.0 3.07314651 3.07314651 3.07314651 3.07314651 10.0 3.72055429 3.72055429 3.72055429 3.72055429 M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 195 iron. Ming et al. [17] analyzed thermal analysis through ultra-thin heat pipes of heat dissipation system. The analysis presents that the heat dissipation capacity of the system improved and uniformly attained temperature. Energy is a requirement of these days with less coast and environment-friendly conditions. So, the involvement of the electric effect enhances the heat transfer rate of the fluid, which is helpful for the rapid production of energy. The enforcement of magnetic fields is also an enhancing agent in thermal and mass transfer flow. The magnetic field with the involvement of hybrid nanoparticles rapidly influences the fluid flow velocity, and the heat transfer rate is noticed to rise more bitterly compared to simple fluid flow through different geometries [18–23]. Electromagnetohydrodynamic (EMHD) flow of fluid has a rapid heat transfer rate with the production of electric and magnetic effects. Elboughdiri et al. [24] scrutinized EMHD nanofluid flow towards a horizontal electromagnetic actuator. The dissipative point flow model with take copper as nanoparticles and second-grade fluid flow. The enhancement of thermal radiative heat flux and joule heating is noticed in the process. G. Rasool et al. [25] analyzed EMHD non-Darcian nanofluid flowing through a convective Riga plate. Numerical investigation is done with the help of validated differential quadratic process. The porosity factor produces an important enhancement in viscous drag forces and electromagnetic forces produce reverse impact. Gandhi et al. [26] discussed EMHD nanofluid flow with blood as base fluid flowing in an irregular stenotic permeable artery. Computational analysis is taken with Casson fluid model. This study is helpful for the diagnosis of hemodynamic abnormalities. The nanofluids with two different types of nanoparticles mixed in them are known as hybrid nanofluids. Combined nanoparticles often exhibit synergistic properties that arise from the combination of different materials. By integrating multiple types of nanoparticles, each with unique properties, it is possible to produce nanocomposites with enhanced or novel characteristics compared to individual nanoparticles. The hybrid nanoparticles can tailor functionality, and improve the stability and compatibility of a fluid [27–31]. Therefore, hybrid nanofluids have applications in science, electronics, biomedicine, energy, and engineering. Mishra et al. [32] developed a machine-learning algorithm for the assessment of ternary hybrid nanofluid flowing through three different situations. The use of ANN for the prediction of data enables more precise predictions of the fluid flow. Mishra and Pathak [33] investigated a comparative behavior of ternary hybrid nanofluid and hybrid nanofluid behavior for thermal analysis of the fluid. Upreti and Mishra [34] analyze the performance of a hybrid nanofluid through a rotating disk with Cattaneo-Christov double diffusion and Yamad-Ota model for thermal analysis. Mishra and Kumar [35] investigated the nanofluid flow through a wedge, Boungiorno Model is used to investigate numerical results of viscous dissipation and heat generation/absorption. Mishra and Upreti [36] investigated computational analysis of fluid flow through an inclined cylinder with slip conditions. Sharma et al. [37] investigated EMHD nanofluid flowing through a plate. Entropy generation and thermal radiations analysis with Jeffery fluid model is analyzed numerically. The analysis shows that the heat transfer rate is better with EMHD effect and in the presence of nanoparticles. Jakeer et al. [38] scrutinized EMHD ternary hybrid nanofluid flow over a stretchable surface. Numerical analysis is taken of Darcy Forchheimer flow with thermal radiations, BVP4C solver in MATLAB is used to get the numerical solutions of the problem. Alfwzan et al. [39] discussed EMHD nanofluid flow with hybrid nanoparticles and activation energy phenomena. The results can be used for managing bleeding by manipulating the magnetic field in the drug infusion mechanism. Entropy generation is the change of entropy due to internal irreversibility of the system. The rate of growth of entropy has usage in Fig. 1. Velocity variations due to change in values of (a) β (b) E 1and (c) M. M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 196 Fig. 2. Temperature variations due to (a) E 1(b) M(c) Ec (d) Nr(e) Nb(f) Nt(g) Pr(h) Qe. M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 197 thermal engineering. In thermal engineering entropy irreversibility is used as indicator of final state’s reversibility. Optimizing performance, assessments can be made based on entropy generation. Farooq et al. [40] scrutinized entropy generation of hybrid nanofluid flowing through a stretching surface. The computational analysis is taken out with the use of Keller Box scheme. The velocity reduces with magnetic parameter, temperature and entropy of the fluid enhances with increasing the magnetic force. Mahmood et al. [41] investigated entropy generation significance with the involvement of nanoparticles of nanofluid flowing through a stretching sheet. The study explores that the involvement of nanoparticles raises the thermal conductivity of the fluid. Temperature and entropy generation of the fluid also have improved. Rafique et al. [42] analyzed entropy generation of magnetohydrodynamic fluid flow through a stretching surface with the influence of Joule heating. In this investigation they analyzed that Os-shaped nanoparticles have more thermal entropy than the brick, blade, cylinder and platelet-shaped nanoparticles. Sharma et al. [43] discuss entropy generation of the nanofluid with thermal radiation and viscous dissipation. The investigation is taken in parabolic trough solar collector, the results show that the influence of nanoparticles enhances the thermal effect and entropy generation which shows the enhancement in solar energy production. Khan et al. [44] investigate entropy generation of chemically reactive flow of Reiner-Rivlin liquid with nanoparticles and thermal radiations. The results reflect the enhancement of flow rate with an increase in thermal properties which enhances entropy generation. Akhter et al. [45] scrutinized the entropy generation of hydromagnetic hybrid nanofluid flow through a partially heated porous cavity with heat conductive obstacles. The heat transfer rate and entropy generation are enhanced due to the increment of Rayleigh number. The expansion in population and technological advancement enhance the usage of energy, energy production with the help of fossil fuels is exotic for living organisms due to climate change and global warming. Therefore, the production of energy with the help of non-toxic or environment-friendly materials like solar energy, hydrogen engines, biomass, and wind energy resources. Furthermore, after the production of energy, energy storage devices also need to improve if we convert a thing to solar energy then we must have good storage devices for a longterm storage of the energy. Sayed et al. [46] discuss energy storage systems with renewable energy sources. The feasibility of improving energy storage capacity is also discussed. The production of green hydrogen and fuel cells which are helpful production and storage of energy. LUO et al. [47] investigated energy storage and dissipation law with triaxial cyclic compression. Linear energy storage law produce elastic strain energy and dissipation strain energy under different pressure is noticed. Chen et al. [48] scrutinized energy storage device progress in electrical energy. Comparison is made among technologies in terms of technical properties, applications and developments. Kousksou et al. [49] investigated energy storage technologies and installation of many energy storage devices. This study includes the feasibility of storage device applications for future installations and for renewable energy systems. Amrouche et al. [50] analyzed renewable energy systems and storage devices. The application of photovoltaic and wind electric power systems is under study. Comparison is made for energy storage devices of different power systems. Bull [51] discusses renewable energy sources and future descriptions of energy resources. The technicalities, cost, and applications of renewable energy production and implications for enhancement of energy. This work discusses the flow of Maxwell electromagnetohydrodynamic (EMHD) hybrid nanofluid through a moveable flat plate. The novel mixture of nanoparticles Graphene and Polythiophene is considered, the study shows these nanoparticles are highly thermodynamic due to which the heat transfer process exceeds with the Fig. 3. Concentration variations due to (a) k(b) Le (c) Nb(d) Nt. M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 198 help of these nanoparticles. The entropy generation study describes the thermal enhancement of the hybrid nanofluid, this shows that the fluid with the mixing of these nanoparticles can generate energy with less cost and can be a more vigilant energy storage fluid. The optimization of the problem is taken by using artificial neural networking (ANN) which is obtained by providing data for training, testing, and validation. Mean square error and error histogram are obtained for the analysis of data. The following are research questions that are discussed in this research work. •What are thermodynamic characteristics of polythiophene? •What is effect of Polythiophene and Graphene Oxide nanoparticles in a viscoelastic fluid? •Entropy generation of this hybrid nanofluid. •Data analysis with artificial neural networking. 2. Problem formulation Consider a viscoelastic, unsteady, incompressible, laminar fluid flow through a moveable flat plate with variable velocity depending on time. Uw(x,t) = bx 1−ξt, where b is primarily expandable. Isolated surface temperature is taken as Tw(x,t) = T∞+b∗x 1−ξt. For sustainability, we consider x =0. Tw, b∗and T∞are respectively wall temperature, variation rate and ambient temperature. The plate is supposed to be slippery and surface is subjected to gradient of temperature the plate is slippy. Uniform Magneto impact B(t) = B0  1−ξt √employed perpendicular to the flow path. Fig. 4. Entropy generation and Bejan number variations due to (a)change in Entropy with Br(a ∗)change in Bejan number with Br(b)change in entropy with E1(b∗) change in Bejan number with E1(c)change in entropy due to Ec (c∗)variations in Bejan number with Ec(d)variations in entropy due to L (d∗)change in Bejan number with L(e)change in entropy with M(e∗)change in Bejan number with M(f)change in entropy with Nr(f∗)change in Bejan number with Nr. M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 199 Fig. 4. (continued). M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 200 Fig. 4*(a). Streamlines of the fluid flow with E 1=0.5,1.0and1.5. Fig. 4*(b). Streamlines of the fluid flow with β 1.0,3.0 and 5.0. Fig. 4*(c). Isotherms of the fluid flow with M 0.3d,0.5 and 0.7. M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 201 Fig. 4*(d). Isotherms of the fluid flow with Ec 0.2,0.5 and 0.7. Fig. 4*(e). Isotherms of the fluid flow with Nr 0.2,0.4 and 0.6. Table 3 Values of physical quantities Skin friction, Nusselt number and Sherwood number with Pr=5.6. β M E1 Pr Ec Nt Le k Nb Cfx Nux Shx 0.3 0.6 0.2 5.6 0.2 1.1 0.3 0.5 1.2 0.0435673 1.3039784 1.3181417 0.1 0.1055425 0.3 0.0435673 0.5 −0.0175147 0.2 −0.0532415 0.4 −0.0050902 0.6 0.0435673 0.2 0.0435673 0.4 0.1368172 0.6 0.3233171 5.5 1.2369233 6.5 1.9806622 7.5 2.8870414 0.0 1.4590469 0.2 1.3039784 0.4 1.1489098 1.0 1.3899100 1.4 1.4931873 1.8 1.5970849 0.0 1.1431069 0.3 1.2689466 0.6 1.3951076 0.2 1.2243670 0.4 1.2541473 0.6 1.2836855 1.0 1.4483427 1.4 1.2495223 1.8 1.1390664 M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 208 Eckert number Ec on the heat lines. The stream function’s intensity is consistent and orderly, with heat lines exhibiting a clockwise and symmetrical pattern. The recorded peak simulation values are reported as 1.28 (Ec =0.2), 1.30 (Ec =0.5), and 1.32 (Ec =0.7). The estimates of heat lines are enhanced as the Eckert number varies. Increasing the values of the Eckert number results in heightened energy transport within the fluid flow system. This leads to a conversion of kinetic energy into heat energy, causing an elevation in heat lines. Fig. 4*(e) presents heat lines corresponding to various estimates of the radiative parameter. The stream function is marked by robust, uniform, and clockwise circulation. Regarding heat lines, the highest values occur at 1.30 (Nr = 0.2), 1.32 (Nr =0.4), and 1.34 (Nr =0.6). Augmenting the magnetic field parameter enhances the physical resistance among fluid particles, resulting in collisions that produce increased heat. 8. Artificial neural networking model The Artificial neural network is like the working of an animal brain with interconnected neural cells, this technique is the multi-processing computer framework with the use of simple processing components, simple scaler messages, and a high level of interconnections and adaptive interactions between components. Multi-Layer Feed Forward (MLFF) is commonly used artificial neural network type. The network consists of an input, some hidden layers and an output layer. The knowledge is stored in connection Weights. Training is a process of changing the connection Weights by using an appropriate learning method. A database is maintained by the system for ANN to solve database and input values. This model in comparison of human brain is on per in terms of optimization, clustering, learning, classification, prediction and generalization [58]. The important benefits of ANN technique are described as follow, •ANN can be efficient on a minimal hardware platform. •The complex class distribution mapping is comparatively easy in ANN. Fig. 10. Display of Sherwood number. M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 209 •The input vector produces possible outcomes in training. •The repeated trainings produce Weights representing outcomes. The feed forward method is efficient because of backpropagation method which is used in MLFF. The backpropagation method can utilize the neuron by rearranging the weight with calculating the error of outcomes. This rearrangement is used for all neuron to reduce the error. The equation for the net input for the jth hidden neuron, yj(x) = ∑ l i=1 W1jixi+aj. The ithnode hidden layer is presented as xi, the jthnode hidden layer is denoted by aj, and the linking weights between xiandajis presented by W1ji. The output hidden layer is denoted as, zj(x) = 1 1+e−yj(x), The output layer of kthorder, ok(x) = ∑ m j=1 W2kjzj+bk. W2kjis the connecting weights between the kthnode of output layer and jthnode of hidden layer. bkis the biasing term at the kthnode of the output layer. The hidden layer’s node count is determined by trial and error, depending on the number of epochs needed to train the network, avoid input parameter over or under-setting, and ensure convergence of the learning process. Following such repeated processes, it was discovered that the convergence criteria employed were the introduction of one hidden layer with five neurons in order to reduce the disparity between the anticipated values of skin friction, Nusselt number and Sherwood number. Out of the total amount of data, 70% was utilized for training, 15%for validation, and the remaining 15% was used to test the model’s predictions. Table 3. describes the values of skin frictionCfx, Nusselt number Nuxand Sherwood number Shx with different parameters variation. Tables 4, 5 and 6 Shows the levels for different values of Skin friction, Nusselt number and Sherwood number. Table 7 produce the codded values of response for the physical quantities. 8.1. Skin friction The description of Skin friction with the use of ANN for validation and optimization is shown in Figs. (5 and 6) below. Fig. 5(a) shows the error optimization which is about 10−5and Fig. 5(b) presents the error histogram with validation, training and test. The data results are optimized and result validation is shown. Fig. 6 is the presentation of regression for skin friction with training, validation and test with 99 percent validity. Table 8 shows results of skin friction with analytical method and their comparison with artificial neural networking results, and error in percentage between these values. Table 3 shows that the increase in electric field and magnetic field results in increase of skin friction, while increase of Maxwell parameter βdecreases the Skin friction. 8.2. Nusselt number Display of Nusselt number for validation and optimization by using ANN method shown in Figs. 7 and 8. Fig. 7 shows the error produced in optimizing the values of Nusselt with the use of ANN, Fig. 7(a) is the representation of Mean square error which is 10−4optimization, Fig. 7 (b) shows the error histogram with training, validation and test. Zero error is obtained up to 10−4. Table 9 shows the presentation of comparison between the analytical method used and the ANN results, which shows the numerical method is approximate and up to 99 percent. Table 3 shows that Nusselt number augmented with the enhancement of Prandtl number Pr and thermophoresis diffusion parameter Nt, whereas Nusselt decreases with Eckert number Ec. Fig. 8 shows the regression for the validation, training and test which is 99 percent with the data used. 8.3. Sherwood number Presentation of Sherwood number with the use of ANN for the validation and optimization of data and numerical method used. Fig. 9(a) shows the error produced and optimized data validation up to 10−3. Fig. 9(b) shows the error histogram with validation, training, and test. Fig. 10 shows the regression for validation, test, and training with the use of ANN. Table 10 is the display of comparison of the analytical results produced and the ANN method results, percentage error is shown. Table 3 shows Sherwood number enhances with increase of the values of Lewis number Leand chemical reaction parameterk, Sherwood number goes down with the increase of Brownian diffusion parameter Nb. 9. Conclusion This study is the analysis of fluid flow through a moveable flat surface, Maxwell fluid with hybrid nanoparticles of Graphene and Polythiophene are taken in viscoelastic fluid to analyze the velocity, temperature and concentration of the flowing fluid. Entropy generation of the fluid with these nanoparticles also analyzed with Bejan number. Physical quantities are analyzed and optimized with the use of ANN. The major findings of this work are, •The velocity enhanced due to Maxwell parameter, and it goes down due to increase of electric and magnetic field. •Temperature increased with Prandtl number, Eckert number, magnetic and electric field effects. •Concentration enhanced due to thermophoresis diffusion parameter, and decreased with Lewis number and chemical reaction parameter. •Entropy generation enhanced with the increase of Eckert number, electric field, magnetic field, and radiation parameter, whereas entropy decreased due to Brinkman number. Table 10 Comparison of Numerical method and ANN. Codded values Shx Runs A B C HAM Method ANN Error 1 -1 -1 -1 1.3619 1.3576 -0.32% 2 0 -1 -1 1.4437 1.4431 -0.04% 3 1 -1 -1 1.5269 1.5246 -0.15% 4 -1 0 -1 1.3619 1.3651 0.23% 5 -1 1 -1 1.3619 1.3619 0.00% 6 -1 -1 0 1.6443 1.6443 0.00% 7 -1 -1 1 1.0545 1.0317 -2.21% 8 0 0 0 1.2759 1.2693 -0.52% 9 -1 0 0 1.1643 1.1643 0.00% 10 1 0 0 1.3883 1.3883 0.00% 11 0 -1 0 1.2462 1.2462 0.00% 12 0 1 0 1.3054 1.3008 -0.35% 13 0 0 -1 1.4735 1.4676 -0.40% 14 0 0 1 1.1661 1.1639 -0.19% 15 1 1 1 1.3364 1.3364 0.00% 16 0 1 1 1.1956 1.1946 -0.08% 17 -1 1 1 1.0545 1.0545 0.0% 18 1 0 1 1.2786 1.2786 0.00% 19 1 -1 1 1.2198 1.2198 0.00% 20 1 1 -1 1.6438 1.6442 0.02% 21 1 1 0 1.4462 1.4471 0.06% M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 210 •Bejan number also exceeded with Eckert number, electric and magnetic field, and radiation parameter increment, while Bejan number decreased with the increase of Brinkman number. •Skin friction decreased due to Maxwell parameter, and increased with magnetic and electric effects increase. •Nusselt number enhanced with Prandtl number and Thermophoresis diffusion parameter’s increment, and decreased due to Eckert number. •Sherwood number enhanced with Lewis number and chemical reaction parameter’s enhancement, and goes down with the Brownian diffusion parameter. In this study, we analyze the fluid flow through a moveable stretching surface, hybrid nanofluid with novel mixture is taken under investigation. The study shows highly thermodynamic properties and with ANN the data is optimized with the accuracy of data. So, experimental work can be made on this fluid flow problem. This mathematical model is used for thermal and solute analysis with isotherms and streamline graphs, this model with various geometries like wedge, cone and disk embedded with different physical properties can be analyzed. Declaration of Competing Interest The authors have no conflicts of interest to declare. All co-authors have seen and agree with the contents of the manuscript. Acknowledgements The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work through large group Research Project under grant number RGP2/194/44. References [1] K. Sudarmozhi, D. Iranian, I. Khan, A. S. Al-johani, S.M. Eldin, Magneto radiative and heat convective flow boundary layer in Maxwell fluid across a porous inclined vertical plate, Sci. Rep. 13 (1) (2023) 6253. [2] S.A. Shehzad, Z. Abbas, A. Rauf, Z. Abdelmalek, Dynamics of fluid flow through Soret-Dufour impacts subject to upward and downward motion of rotating disk, Int. Commun. Heat. Mass Transf. 120 (2021) 105025. [3] M.M. Bhatti, A. Shahid, I.E. Sarris, O. Anwar B´ eg, Spectral relaxation computation of Maxwell fluid flow from a stretching surface with quadratic convection and nonFourier heat flux using Lie symmetry transformations, Int. J. Mod. Phys. B 37 (09) (2023) 2350082. [4] K. Sudarmozhi, D. Iranian, I. Khan, J. Alzahrani, A.S. Al-johani, S.M. Eldin, Double diffusion in a porous medium of MHD Maxwell fluid with thermal radiation, heat generation and chemical reaction, Case Stud. Therm. Eng. 43 (2023) 102700. [5] A. Riaz, M.I. Asjad, M.Y. Almusawa, S.M. Eldin, N.M. Said, M.I. Khan, New solutions of fractional Maxwell fluid with ternary-hybrid nanoparticles, Case Stud. Therm. Eng. 47 (2023) 103091. [6] M. Yasin, S. Hina, R. Naz, A modern study on peristaltically induced flow of Maxwell fluid considering modified Darcy’s law and Hall effect with slip condition, Alex. Eng. J. 76 (2023) 835–850. [7] B. Jalili, A.M. Ganji, A. Shateri, P. Jalili, D.D. Ganji, Thermal analysis of nonNewtonian visco-inelastic fluid MHD flow between rotating disks, Case Stud. Therm. Eng. 49 (2023) 103333. [8] A. Shateri, M.M. Moghaddam, B. Jalili, Y. Khan, P. Jalili, D.D. Ganji, Heat transfer analysis of unsteady nanofluid flow between moving parallel plates with magnetic field: analytical approach, J. Cent. South Univ. 30 (7) (2023) 2313–2323. [9] Jalili, P., Azar, A.A., Jalili, B., & Ganji, D.D. (2023). The HAN method for a thermal analysis of forced non-Newtonian MHD Reiner-Rivlin viscoelastic fluid motion between two disks. Heliyon. [10] B. Jalili, A. Rezaeian, P. Jalili, F. Ommi, D.D. Ganji, Numerical modeling of magnetic field impact on the thermal behavior of a microchannel heat sink, Case Stud. Therm. Eng. 45 (2023) 102944. [11] P. Jalili, S.M. Sharif Mousavi, B. Jalili, P. Pasha, D.D. Ganji, Thermal evaluation of MHD Jeffrey fluid flow in the presence of a heat source and chemical reaction, Int. J. Mod. Phys. B (2023) 2450113. [12] P. Jalili, H. Narimisa, B. Jalili, A. Shateri, D.D. Ganji, A novel analytical approach to micro-polar nanofluid thermal analysis in the presence of thermophoresis, Brownian motion and Hall currents, Soft Comput. 27 (2) (2023) 677–689. [13] R.S. Varun Kumar, M.D. Alsulami, I.E. Sarris, B.C. Prasannakumara, S. Rana, Backpropagated neural network modeling for the non-fourier thermal analysis of a moving plate, Mathematics 11 (2) (2023) 438. [14] A. Bothe, S.E.M. Pourhosseini, P. Ratajczak, F. B´ eguin, A. Balducci, Analysis of thermal and electrochemical properties of electrical double-layer capacitors by using an in-situ simultaneous thermal analysis cell, Electrochim. Acta 444 (2023) 141974. [15] X. Tan, S.H. Altoum, H.A. Othman, M.I. Syam, M.A. Salman, A. Musa, Thermal analysis of nanofluid flow within porous enclosure with curved hot wall utilizing numerical approach, Case Stud. Therm. Eng. 45 (2023) 102923. [16] A. Regordosa, J. Lacaze, J. Sertucha, M.J. Castro-Roman, U. de La Torre, O. Dezellus, Is thermal analysis able to provide carbon and silicon contents of cast irons, Int. J. Met. 17 (2) (2023) 592–603. [17] T. Ming, X. Liao, T. Shi, K. Yin, Z. Wang, M.H. Ahmadi, Y. Wu, The thermal analysis of the heat dissipation system of the charging module integrated with ultra-thin heat pipes, Energy Built Environ. 4 (5) (2023) 506–515. [18] E.R. El-Zahar, A.M. Rashad, W. Saad, L.F. Seddek, Magneto-hybrid nanofluids flow via mixed convection past a radiative circular cylinder, Sci. Rep. 10 (1) (2020) 10494. [19] S. Jakeer, P.B. Reddy, A.M. Rashad, H.A. Nabwey, Impact of heated obstacle position on magneto-hybrid nanofluid flow in a lid-driven porous cavity with Cattaneo-Christov heat flux pattern, Alex. Eng. J. 60 (1) (2021) 821–835. [20] A. Mahdy, E.R. El-Zahar, A.M. Rashad, W. Saad, H.S. Al-Juaydi, The magnetonatural convection flow of a micropolar hybrid nanofluid over a vertical plate saturated in a porous medium, Fluids 6 (6) (2021) 202. [21] E.R. El-Zahar, A.E.N. Mahdy, A.M. Rashad, W. Saad, L.F. Seddek, Unsteady MHD mixed convection flow of Non-Newtonian Casson hybrid nanofluid in the stagnation zone of sphere spinning impulsively, Fluids 6 (6) (2021) 197. [22] A. Mourad, A. Aissa, F. Mebarek-Oudina, W. Jamshed, W. Ahmed, H.M. Ali, A. M. Rashad, Galerkin finite element analysis of thermal aspects of Fe3O4-MWCNT/ water hybrid nanofluid filled in wavy enclosure with uniform magnetic field effect, Int. Commun. Heat. Mass Transf. 126 (2021) 105461. [23] E.R. El-Zahar, A.M. Rashad, H.S. Al-Juaydi, Studying massive suction impact on magneto-flow of a hybridized Casson nanofluid on a porous continuous moving or fixed surface, Symmetry 14 (3) (2022) 627. [24] N. Elboughdiri, D. Ghernaout, T. Muhammad, A. Alshehri, R. Sadat, M.R. Ali, A. Wakif, Towards a novel EMHD dissipative stagnation point flow model for radiating copper-based ethylene glycol nanofluids: an unsteady two-dimensional homogeneous second-grade flow case study, Case Stud. Therm. Eng. 45 (2023) 102914. [25] G. Rasool, A. Wakif, X. Wang, A. Shafiq, A.J. Chamkha, Numerical passive control of alumina nanoparticles in purely aquatic medium featuring EMHD driven nonDarcian nanofluid flow over convective Riga surface, Alex. Eng. J. 68 (2023) 747–762. [26] R. Gandhi, B.K. Sharma, N.K. Mishra, Q.M. Al-Mdallal, Computer simulations of EMHD Casson nanofluid flow of blood through an irregular stenotic permeable artery: application of Koo-Kleinstreuer-Li correlations, Nanomaterials 13 (4) (2023) 652. [27] S.A.M. Mehryan, P. Goudarzi, S.M.H. Zadeh, M. Ghodrat, O. Younis, M. Ghalambaz, Thermal vibrational and gravitational analysis of a hybrid aqueous suspension comprising Ag–MgO hybrid nano-additives, Int. Commun. Heat. Mass Transf. 126 (2021) 105345. [28] S.A.M. Mehryan, M.A. Sheremet, M. Soltani, M. Izadi, Natural convection of magnetic hybrid nanofluid inside a double-porous medium using two-equation energy model, J. Mol. Liq. 277 (2019) 959–970. [29] R. Mohebbi, S.A.M. Mehryan, M. Izadi, O. Mahian, Natural convection of hybrid nanofluids inside a partitioned porous cavity for application in solar power plants, J. Therm. Anal. Calorim. 137 (2019) 1719–1733. [30] M. Izadi, H.F. Oztop, M.A. Sheremet, S.A.M. Mehryan, N. Abu-Hamdeh, Coupled FHD–MHD free convection of a hybrid nanoliquid in an inversed T-shaped enclosure occupied by partitioned porous media, Numer. Heat. Transf., Part A: Appl. 76 (6) (2019) 479–498. [31] M. Izadi, M.A. Sheremet, S.A.M. Mehryan, Natural convection of a hybrid nanofluid affected by an inclined periodic magnetic field within a porous medium, Chin. J. Phys. 65 (2020) 447–458. [32] A. Mishra, S.K. Rawat, M. Yaseen, M. Pant, Development of machine learning algorithm for assessment of heat transfer of ternary hybrid nanofluid flow towards three different geometries: Case of artificial neural network, Heliyon 9 (11) (2023). [33] A. Mishra, G. Pathak, A comparative analysis of MoS2-SiO2/H2O hybrid nanofluid and MoS2-SiO2-GO/H2O ternary hybrid nanofluid over an inclined cylinder with heat generation/absorption, Numer. Heat. Transf., Part A: Appl. (2023) 1–30. [34] H. Upreti, A. Mishra, The performance evolution of hybrid nanofluid flow over a rotating disk using Cattaneo–Christov double diffusion and Yamada–Ota model, Waves Random Complex Media (2022) 1–21. [35] A. Mishra, M. Kumar, Numerical analysis of MHD nanofluid flow over a wedge, including effects of viscous dissipation and heat generation/absorption, using Buongiorno model, Heat. Transf. 50 (8) (2021) 8453–8474. [36] A. Mishra, H. Upreti, Computational analysis of radiative nanofluid flow past an inclined cylinder with slip effects using the Yamada–Ota model, Numer. Heat. Transf., Part A: Appl. (2023) 1–19. [37] B.K. Sharma, A. Kumar, R. Gandhi, M.M. Bhatti, N.K. Mishra, Entropy generation and thermal radiation analysis of EMHD Jeffrey nanofluid flow: applications in solar energy, Nanomaterials 13 (3) (2023) 544. [38] S. Jakeer, S.R.R. Reddy, S.V. Easwaramoorthy, H.T. Basha, J. Cho, Exploring the influence of induced magnetic fields and double-diffusive convection on carreau nanofluid flow through diverse geometries: a comparative study using numerical and ANN approaches, Mathematics 11 (17) (2023) 3687. [39] W.F. Alfwzan, A. Imran, F.M. Allehiany, M.S. Aldhabani, A mathematical model for cilia actuated transport of Gold–Silver hybrid nanofluid EMHD flow with activation energy phenomena, Case Stud. Therm. Eng. 49 (2023) 103252. M.S. Junaid et al. Alexandria Engineering Journal 94 (2024) 193–211 211 [40] U. Farooq, H. Waqas, M.S. Aldhabani, N. Fatima, A. Alhushaybari, M.R. Ali, T. Muhammad, Modeling and computational framework of radiative hybrid nanofluid configured by a stretching surface subject to entropy generation: using Keller box scheme, Arab. J. Chem. 16 (4) (2023) 104628. [41] Z. Mahmood, M. Abd El-Rahman, U. Khan, A.M. Hassan, H.A.E.W. Khalifa, Entropy generation due to nanofluid flow in porous media over radiative permeable exponentially surface with nanoparticle aggregation effect, Tribol. Int. 188 (2023) 108852. [42] K. Rafique, Z. Mahmood, H. Alqahtani, S.M. Eldin, Various nanoparticle shapes and quadratic velocity impacts on entropy generation and MHD flow over a stretching sheet with joule heating, Alex. Eng. J. 71 (2023) 147–159. [43] B.K. Sharma, A. Kumar, R. Gandhi, M.M. Bhatti, N.K. Mishra, Entropy generation and thermal radiation analysis of EMHD Jeffrey nanofluid flow: applications in solar energy, Nanomaterials 13 (3) (2023) 544. [44] S.A. Khan, T. Hayat, A. Alsaedi, Entropy generation in chemically reactive flow of Reiner-Rivlin liquid conveying tiny particles considering thermal radiation, Alex. Eng. J. 66 (2023) 257–268. [45] R. Akhter, M.M. Ali, M.A. Alim, Entropy generation due to hydromagnetic buoyancy-driven hybrid-nanofluid flow in partially heated porous cavity containing heat conductive obstacle, Alex. Eng. J. 62 (2023) 17–45. [46] E.T. Sayed, A.G. Olabi, A.H. Alami, A. Radwan, A. Mdallal, A. Rezk, M. A. Abdelkareem, Renewable energy and energy storage systems, Energies 16 (3) (2023) 1415. [47] L.U.O. Song, F.Q. GONG, L.L. LI, P.E.N.G. Kang, Linear energy storage and dissipation laws and damage evolution characteristics of rock under triaxial cyclic compression with different confining pressures, Trans. Nonferrous Met. Soc. China 33 (7) (2023) 2168–2182. [48] Y. Chen, S. Li, S. Lin, M. Chen, C. Tang, X. Liu, Promising energy-storage applications by flotation of graphite ores: a review, Chem. Eng. J. 454 (2023) 139994. [49] T. Kousksou, P. Bruel, A. Jamil, T. El Rhafiki, Y. Zeraouli, Energy storage: applications and challenges, Sol. Energy Mater. Sol. Cells 120 (2014) 59–80. [50] S.O. Amrouche, D. Rekioua, T. Rekioua, S. Bacha, Overview of energy storage in renewable energy systems, Int. J. Hydrog. Energy 41 (45) (2016) 20914–20927. [51] S.R. Bull, Renewable energy today and tomorrow, Proc. IEEE 89 (8) (2001) 1216–1226. [52] S. Mukhopadhyay, Heat transfer analysis of the unsteady flow of a Maxwell fluid over a stretching surface in the presence of a heat source/sink, Chin. Phy. Soc. 29 (5) (2012) 054701–054703. [53] W. Jamshed, M.R. Eid, N.A.A.M. Nasir, K.S. Nisar, A. Aziz, F. Shahzad, A. Shukla, Thermal examination of renewable solar energy in parabolic trough solar collector utilizing Maxwell nanofluid: a noble case study, Case Stud. Therm. Eng. 27 (2021) 101258. [54] A.U. Yahya, N. Salamat, W.H. Huang, I. Siddique, S. Abdal, S. Hussain, Thermal charactristics for the flow of Williamson hybrid nanofluid (MoS2+ZnO) based with engine oil over a streched sheet, Case Stud. Therm. Eng. 26 (2021) 101196. [55] M.Q. Brewster, Thermal Radiative Transfer and Properties, John Wiley and Sons, 1992. [56] T. Hayat, M. Qasim, S. Mesloub, MHD flow and heat transfer over permeable stretching sheet with slip conditions, Int. J. Numer. Methods Fluid. 566 (2011) 963–975. [57] A. Kumar, R. Tripathi, R. Singh, V.K. Chaurasiya, Simultaneous effects of nonlinear thermal radiation and Joule heating on the flow of Williamson nanofluid with entropy generation, Phys. A: Stat. Mech. its Appl. 551 (2020) 123972. [58] P.B.A. Reddy, S. Jakeer, H.T. Basha, S.R.R. Reddy, T.M. Kumar, Multi-layer artificial neural network modeling of entropy generation on MHD stagnation point flow of cross-nanofluid, Waves Random Complex Media (2022) 1e28. [59] W. Jamshed, E.K. Akgül, K.S. Nisar, Keller box study for inclined magnetically driven Casson nanofluid over a stretching sheet: single phase model, Phys. Scr. 96 (2021) 065201. [60] W. Jamshed, S.U. Devi, K.S. Nisar, Single phase-based study of Ag-Cu/EO Williamson hybrid nanofluid flow over a stretching surface with shape factor, Phys. Scr. 96 (2021) 065202. [61] X. Wang, X. Xu, S.U.S. Choi, L. Zhou, Thermophysical properties of hybrid nanofluids: a review, Int. J. Heat. Mass Transf. 143 (2019) 118515, https://doi. org/10.1016/j.ijheatmasstransfer.2019.118515. [62] C.H. Chon, K.D. Kihm, Thermophysical properties of nanoparticle suspensions, Int. J. Heat. Mass Transf. 54 (17-18) (2011) 3726–3736, https://doi.org/10.1016/j. ijheatmasstransfer.2011.04.039. [63] D.P. Kulkarni, D.K. Das, A.G. Kumbhar, A review on the thermophysical properties of hybrid nanofluids, Renew. Sustain. Energy Rev. 59 (2016) 326–337, https://doi. org/10.1016/j.rser.2015.12.334. [64] S. Suresh, K.P. Venkitaraj, A review on the thermophysical properties of hybrid nanofluids for heat transfer applications, J. Appl. Phys. 120 (1) (2016) 011101, https://doi.org/10.1063/1.4955191. [65] D.P. Kulkarni, D.K. Das, A.G. Kumbhar, A review on the thermophysical properties of hybrid nanofluids and the mechanisms of enhancement in thermo-physical properties, J. Mol. Liq. 240 (2017) 420–436, https://doi.org/10.1016/j. molliq.2017.05.118. M.S. Junaid et al.