A COMPARATIVE STUDY OF MULTIPLE REGRESSION AND MACHINE LEARNING TECHNIQUES FOR PREDICTION OF NANOFLUID HEAT TRANSFER

2021 ◽  
pp. 1-22
Author(s):  
Eyup Kocak ◽  
Ulku Ece Ayli ◽  
Hasmet Turkoglu
Keyword(s):  
Heat Transfer ◽  
Nusselt Number ◽  
Multiple Regression ◽  
Volume Fraction ◽  
Particle Diameter ◽  
Machine Learning Techniques ◽  
Exponential Factor ◽  
Nano Fluid ◽  
Neuro Fuzzy ◽  
Interface System

Abstract The aim of this paper is to introduce and discuss prediction power of the multiple regression technique, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Interface System (ANFIS) methods for predicting the forced convection heat transfer characteristics of a turbulent nano fluid flow a pipe. Water and Al2O3 mixture is used as the nano fluid. Utilizing FLUENT software, numerical computations were performed with volume fraction ranging between 0.3% and 5%, particle diameter ranging between 20 and 140 nm and Reynolds number ranging between 7000 and 21000. Based on the computationally obtained results, a correlation is developed for Nusselt number using the multiple regression method. Also, based on the CFD results different ANN architectures with different number of neurons in the hidden layers and several training algorithms (Levenberg-Marquardt, Bayesian Regularization, Scaled Conjugate Gradient) are tested to find the best ANN architecture. In addition, Adaptive Neuro-fuzzy Interface System (ANFIS) is also used to predict the Nusselt number. In the ANFIS, number of clusters, exponential factor and Membership Function (MF) type are optimized. The results obtained from multiple regression correlation, ANN and ANFIS were compared. According to the obtained results, ANFIS is a powerful tool with a R2 of 0.9987 for predictions.

Modeling of mixed convection in an enclosure using multiple regression, artificial neural network, and adaptive neuro-fuzzy interface system models

2020 ◽  
Vol 234 (15) ◽  
pp. 3078-3093
Author(s):  
Ece Aylı
Keyword(s):  
Neural Network ◽  
Heat Transfer ◽  
Artificial Neural Network ◽  
Nusselt Number ◽  
Forced Convection ◽  
Number Distribution ◽  
Neuro Fuzzy ◽  
Interface System ◽  
Nusselt Number Distribution ◽  
Artificial Neural

In this study, the heat transfer characteristics of laminar combined forced convection through a horizontal duct are obtained with the help of the numerical methods. The effect of the geometrical parameters of the cavity and Reynolds number on the heat transfer is investigated. New heat transfer correlation for hydrodynamically fully developed, laminar combined forced convection through a horizontal duct is proposed with an average error of 6.98% and R2 of 0.8625. The obtained correlation results are compared with the artificial neural network and adaptive neuro-fuzzy interface system models. Due to the obtained results, good agreement is identified between the numerical results and predicted adaptive neuro-fuzzy interface system results. In conclusion, it is seen that adaptive neuro-fuzzy interface system can predict the Nusselt number distribution with a higher accuracy than the developed correlation and the artificial neural network model. The developed adaptive neuro-fuzzy interface system model predicts the Nusselt number with 1.07% mean average percentage error and 0.9983 R2 value. The effect of the different training algorithms and their ability to predict Nusselt number distribution are examined. According to the results, the Bayesian regulation algorithm gives the best approach with a 2.235% error. According to the examination that is performed in this study, the adaptive neuro-fuzzy interface system is a powerful, robust tool that can be used with confidence for predicting the thermal performance.

Natural Convection in a Nano-Fluid Filled Square Enclosure

2020 ◽  
Vol 847 ◽  
pp. 114-119
Author(s):  
Barbie Leena Barhoi ◽  
Ramesh Chandra Borah ◽  
Sandeep Singh
Keyword(s):  
Heat Transfer ◽  
Nusselt Number ◽  
Natural Convection ◽  
Rayleigh Number ◽  
Volume Fraction ◽  
Control Volume ◽  
Convection Heat Transfer ◽  
Ansys Fluent ◽  
Square Enclosure ◽  
Nano Fluid

The present study relates to numerical investigation of natural convection heat transfer in a nanofluid filled square enclosure. One side of the enclosure is maintained at high temperature and the other side at a low temperature; while the top and bottom sides are adiabatic. The commercial CFD software ANSYS-FLUENT© was used to solve this numerical problem with the governing differential equations discretized by a control volume approach. nanofluids of Cu-water, Al2O3-water and TiO2-water have been simulated for a range of Rayleigh numbers and volume fractions. The results were obtained in the form of streamlines and isotherms. Interpretations of the results are done based on heat transfer rates, volume fraction, Rayleigh number and Nusselt number. It is to be noted that addition of nanoparticles enhances the heat transfer rate. It is also observed that the Nusselt number is highly affected by volume fraction and Rayleigh number.

Effect of Nanofluid on Heat Transfer Enhancement for Mixed Convection Flow Over a Corrugated Surface

2020 ◽  
Vol 45 (4) ◽  
pp. 373-383
Author(s):  
Nepal Chandra Roy ◽  
Sadia Siddiqa
Keyword(s):  
Heat Transfer ◽  
Boundary Layer ◽  
Nusselt Number ◽  
Mixed Convection ◽  
Local Nusselt Number ◽  
Richardson Number ◽  
Thermal Boundary Layer ◽  
Volume Fraction ◽  
Convection Flow ◽  
Mixed Convection Flow

AbstractA mathematical model for mixed convection flow of a nanofluid along a vertical wavy surface has been studied. Numerical results reveal the effects of the volume fraction of nanoparticles, the axial distribution, the Richardson number, and the amplitude/wavelength ratio on the heat transfer of Al2O3-water nanofluid. By increasing the volume fraction of nanoparticles, the local Nusselt number and the thermal boundary layer increases significantly. In case of \mathrm{Ri}=1.0, the inclusion of 2 % and 5 % nanoparticles in the pure fluid augments the local Nusselt number, measured at the axial position 6.0, by 6.6 % and 16.3 % for a flat plate and by 5.9 % and 14.5 %, and 5.4 % and 13.3 % for the wavy surfaces with an amplitude/wavelength ratio of 0.1 and 0.2, respectively. However, when the Richardson number is increased, the local Nusselt number is found to increase but the thermal boundary layer decreases. For small values of the amplitude/wavelength ratio, the two harmonics pattern of the energy field cannot be detected by the local Nusselt number curve, however the isotherms clearly demonstrate this characteristic. The pressure leads to the first harmonic, and the buoyancy, diffusion, and inertia forces produce the second harmonic.

Study of the boundary layer heat transfer of nanofluids over a stretching sheet: Passive control of nanoparticles at the surface

2015 ◽  
Vol 93 (7) ◽  
pp. 725-733 ◽  
Author(s):  
M. Ghalambaz ◽  
E. Izadpanahi ◽  
A. Noghrehabadi ◽  
A. Chamkha
Keyword(s):  
Heat Transfer ◽  
Thermal Conductivity ◽  
Boundary Layer ◽  
Nusselt Number ◽  
Heat Transfer Enhancement ◽  
Base Fluid ◽  
Stretching Sheet ◽  
Volume Fraction ◽  
Enhancement Ratio ◽  
Transfer Enhancement

The boundary layer heat and mass transfer of nanofluids over an isothermal stretching sheet is analyzed using a drift-flux model. The relative slip velocity between the nanoparticles and the base fluid is taken into account. The nanoparticles’ volume fractions at the surface of the sheet are considered to be adjusted passively. The thermal conductivity and the dynamic viscosity of the nanofluid are considered as functions of the local volume fraction of the nanoparticles. A non-dimensional parameter, heat transfer enhancement ratio, is introduced, which shows the alteration of the thermal convective coefficient of the nanofluid compared to the base fluid. The governing partial differential equations are reduced into a set of nonlinear ordinary differential equations using appropriate similarity transformations and then solved numerically using the fourth-order Runge–Kutta and Newton–Raphson methods along with the shooting technique. The effects of six non-dimensional parameters, namely, the Prandtl number of the base fluid Prbf, Lewis number Le, Brownian motion parameter Nb, thermophoresis parameter Nt, variable thermal conductivity parameter Nc and the variable viscosity parameter Nv, on the velocity, temperature, and concentration profiles as well as the reduced Nusselt number and the enhancement ratio are investigated. Finally, case studies for Al2O3 and Cu nanoparticles dispersed in water are performed. It is found that increases in the ambient values of the nanoparticles volume fraction cause decreases in both the dimensionless shear stress f″(0) and the reduced Nusselt number Nur. Furthermore, an augmentation of the ambient value of the volume fraction of nanoparticles results in an increase the heat transfer enhancement ratio hnf/hbf. Therefore, using nanoparticles produces heat transfer enhancement from the sheet.

Enhancement of Heat Transfer of Rectangular Saw Tooth Shaped Micro Channel Heat Sink with Water Nano Fluid/Aluminium Oxide

2015 ◽  
Vol 813-814 ◽  
pp. 685-689
Author(s):  
M. Vijay Anand Marimuthu ◽  
B. Venkatraman ◽  
S. Kandhasamy
Keyword(s):  
Heat Transfer ◽  
Reynolds Number ◽  
Nusselt Number ◽  
Pressure Drop ◽  
Heat Sink ◽  
Micro Channel ◽  
Performance Curve ◽  
Theoretical Level ◽  
Enhancement Of Heat Transfer ◽  
Nano Fluid

This paper investigates the performance and characteristics of saw tooth shape micro channel in the theoretical level. If the conduct area of the nano fluid increases the heat transfer also increases. The performance curve has drawn Reynolds number against nusselt number, heat transfer co efficient. Pressure drop plays an important role in this device. If pressure drop is high the heat transfer increases. The result in this experiment shows clearly that the heat transfer is optimized.

scholarly journals Study of convection heat transfer enhancement inside lid driven cavity utilizing fins and nanofluid

2017 ◽  
Vol 21 (6 Part A) ◽  
pp. 2431-2442
Author(s):  
Arash Lavasani ◽  
Mousa Farhadi ◽  
Darzi Rabienataj
Keyword(s):  
Heat Transfer ◽  
Nusselt Number ◽  
Richardson Number ◽  
Volume Fraction ◽  
Convection Heat Transfer ◽  
Thermal Conductivity Ratio ◽  
Convection Flow ◽  
Driven Cavity ◽  
Ratio Change ◽  
Hot Surface

In the present study, the effect of suspension of nanoparticle on mixed convection flow is investigated numerically in lid driven cavity with fins on its hot surface. Study is carried out for Richardson numbers ranging from 0.1 to 10, fin(s) height ratio change from 0.05 to 0.15 and volume fraction of nanoparticles from 0 to 0.03, respectively. The thermal conductivity ratio (kfin/kf) is equal to 330 and Grashof number is assumed to be constant (104) so that the Richardson numbers changes with Reynolds number. Results show that the heat transfer enhances by using nanofluid for all studied Richardson numbers. Adding fins on hot wall has different effects on heat transfer depend to Richardson number and height of fins. Use of low height fin in flow with high Richardson number enhances the heat transfer rate while by increasing the height of fin the heat transfer reduces even lower than it for pure fluid. The overall enhancement in Nusselt number by adding 3% nanoparticles and 3 fins is 54% at Ri=10. They cause reduction of Nusselt Number by 25% at Ri=0.1. Higher fins decrease the heat transfer due to blocking fluid at corners of fins.

scholarly journals Heat transfer studies in compact heat exchanger using ZnO and TiO2 nanofluids in ethylene glycol/water

2018 ◽  
Vol 24 (4) ◽  
pp. 309-318
Author(s):  
Srinivasan Manikandan ◽  
Rajoo Baskar
Keyword(s):  
Heat Transfer ◽  
Nusselt Number ◽  
Ethylene Glycol ◽  
Volume Fraction ◽  
Inlet Temperature ◽  
Percentage Increase ◽  
Cold Side ◽  
Volume Fractions ◽  
Experimental Values ◽  
Tio2 Nanofluids

This paper reports an experimental study on the heat transfer characteristics of a nanofluid consisting of ZnO/water/ethylene glycol (EG) and TiO2/water/ /ethylene glycol. In this study, the base fluids of ethylene glycol (EG):water (W) with volume fractions of 30:70, 40:60, and 50:50 were prepared, and 0.2 to 1.0 volume fractions of ZnO and TiO2 nanofluids were used as a cold side fluid. The prime objective of this study is to identify the effects of nanofluid concentration and three different hot fluid inlet temperatures viz., 55, 65 and 75?C C on the heat transfer enhancement of cold side fluid. The results are compared with base fluids and the percentage increase of the Nusselt number because of nanoparticle addition is noted both experimentally and theoretically. The results showed that at the hot fluid inlet temperature of 75?C, the increase in the Nusselt number is maximum with volume concentrations of 0.6 and 0.8% for ZnO and TiO2 nanofluids, respectively. The corresponding maximum Nusselt number enhancements are about 11.5 and 21.4%, respectively, for the base fluid volume fraction of 30:70 (EG:W). There is good agreement between the results calculated from experimental values and the correlation.

scholarly journals Effects of a Rotating Cone on the Mixed Convection in a Double Lid-Driven 3D Porous Trapezoidal Nanofluid Filled Cavity under the Impact of Magnetic Field

Nanomaterials ◽  
2020 ◽  
Vol 10 (3) ◽  
pp. 449 ◽  
Author(s):  
Ali J. Chamkha ◽  
Fatih Selimefendigil ◽  
Hakan F. Oztop
Keyword(s):  
Magnetic Field ◽  
Heat Transfer ◽  
Nusselt Number ◽  
Aspect Ratio ◽  
Mixed Convection ◽  
Average Nusselt Number ◽  
Volume Fraction ◽  
Rotational Velocity ◽  
Rotating Cone ◽  
The Impact

Effects of a rotating cone in 3D mixed convection of CNT-water nanofluid in a double lid-driven porous trapezoidal cavity is numerically studied considering magnetic field effects. The numerical simulations are performed by using the finite element method. Impacts of Richardson number (between 0.05 and 50), angular rotational velocity of the cone (between −300 and 300), Hartmann number (between 0 and 50), Darcy number (between 10 − 4 and 5 × 10 − 2 ), aspect ratio of the cone (between 0.25 and 2.5), horizontal location of the cone (between 0.35 H and 0.65 H) and solid particle volume fraction (between 0 and 0.004) on the convective heat transfer performance was studied. It was observed that the average Nusselt number rises with higher Richardson numbers for stationary cone while the effect is reverse for when the cone is rotating in clockwise direction at the highest supped. Higher discrepancies between the average Nusselt number is obtained for 2D cylinder and 3D cylinder configuration which is 28.5% at the highest rotational speed. Even though there are very slight variations between the average Nu values for 3D cylinder and 3D cone case, there are significant variations in the local variation of the average Nusselt number. Higher enhancements in the average Nusselt number are achieved with CNT particles even though the magnetic field reduced the convection and the value is 84.3% at the highest strength of magnetic field. Increasing the permeability resulted in higher local and average heat transfer rates for the 3D porous cavity. In this study, the aspect ratio of the cone was found to be an excellent tool for heat transfer enhancement while 95% enhancements in the average Nusselt number were obtained. The horizontal location of the cone was found to have slight effects on the Nusselt number variations.

CFD Investigation of Al2O3 Nanoparticles Effect on Heat Transfer Enhancement of Newtonian and Non-Newtonian Fluids in a Helical Coil

2019 ◽  
Vol 14 (3) ◽  
Author(s):  
Javad Aminian Dehkordi ◽  
Arezou Jafari
Keyword(s):  
Heat Transfer ◽  
Aqueous Solution ◽  
Nusselt Number ◽  
Base Fluid ◽  
Volume Fraction ◽  
Reynolds Numbers ◽  
Helical Coil ◽  
Al2o3 Nanoparticles ◽  
Nanoparticles Volume Fraction ◽  
Computational Fluid Dynamics Cfd

Abstract The present study applied computational fluid dynamics (CFD) to investigate the heat transfer of Newtonian (water) and non-Newtonian (0.3 %wt. aqueous solution of carboxymethylcellulose (CMC)) fluids in the presence of Al2O3 nanoparticles. To analyze the heat transfer rate, investigations were performed in a vertical helical coil as essential heat transfer equipment, at different inlet Reynolds numbers. To verify the accuracy of the simulation model, experimental data reported in the literature were employed. Comparisons showed the validity of simulation results. From the results, compared to the aqueous solution of CMC, water had a higher Nusselt number. In addition, it was observed that adding nanoparticles to a base fluid presented different results in which water/Al2O3 nanofluid with nanoparticles’ volume fraction of 5 % was more effective than the same base fluid with a volume fraction of 10 %. In lower ranges of Reynolds number, adding nanoparticles was more effective. For CMC solution (10 %), increasing concentration of nanoparticles caused an increase in the apparent viscosity. Consequently, the Nusselt number was reduced. The findings reveal the important role of fluid type and nanoparticle concentration in the design and development of heat transfer equipment.

Sign in / Sign up

Export Citation Format

Share Document