Ehsan Rezaei

MODELING OF HEAT TRANSFER IN AN AIR COOLER EQUIPPED WITH CLASSIC TWISTED TAPE INSERTS USING ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM

This paper reports the application of an adaptive neuro-fuzzy inference system (ANFIS) to model the experimental results of heat transfer in an air-cooled heat exchanger equipped with classic twisted tape inserts. The aim is to consider the effects of the twist ratio of classic inserts and Reynolds number variation on average heat transfer in the air cooler. The training data for optimizing the ANFIS structure are based on available experimental data. A hybrid learning algorithm consisting of the gradient descends method and the least-squares method is used for ANFIS training. The proposed ANFIS was developed using MATLAB functions. For the best ANFIS structure obtained in this study, the maximum errors of the training and test data were found to be 0.111% and 2.378%, respectively. Also, the mean relative errors of the training and test data were found to be 0.011% and 1.316%, respectively. The obtained results showed that ANFIS can be used to predict experimental results precisely.

Neuro-Fuzzy Modeling of the Free Convection from Vertical Arrays of Isothermal Cylinders

D = cylinder diameter, m g = gravitational acceleration, m∕s L = length of the cylinder, m mf = membership function N = number of cylinders in the array, N 5 Ni = ordinal number of the ith cylinder in the array Nui = average Nusselt number of the ith cylinder in the array Nua = average Nusselt number for all the cylinders in each vertical array Ra = Rayleigh number based on the cylinder diameter gβ Tw − T∞ D∕va Sh = horizontal center-to-center separation distance, m Sv = vertical center-to-center separation distance, m T = temperature, K W = flow diverter width, m w = rule’s firing strength w = normalized firing strength α = thermal diffusivity of air, m∕s β = coefficient of volumetric thermal expansion of air, (1∕K) e = fringe shift N = refers to every fixed node in the second layer of the Takagi–Sugeno architecture Π = refers to every fixed node in the second layer of the Takagi–Sugeno architecture v = kinematic viscosity of air, m∕s φ = angle of flow diverter, 45 deg Subscripts

The Application of Imperialist Competitive Algorithm in Optimizing the Free Convection Heat Transfer in a Vertical Cavity with Flow Diverters

This paper discussed about the application of imperialist competitive algorithm (ICA) to optimize the free convection in a vertical cavity with adiabatic horizontal, isothermally vertical walls and adiabatic diverters. Experiments included diverter angle with respect to horizon ranging from 0° to 150°. Also, the Rayleigh number based on the cavity side length varied from 6×103 to 1.2×104. After data reduction, the regression equation of convective heat flux was obtained as a function of Rayleigh number and diverter angle. Then the cost function was optimized using ICA. One can be sure that the convective heat flux will be optimized due to the optimization of the cost function. Computational results indicate that the proposed optimization algorithm is quite effective and powerful in optimizing the cost function. According to the results, in order to obtain maximum heat transfer, the diverter angle must be at the highest level.

Fuzzy Logic to Model the Free Convection Heat Transfer from Horizontal Isothermal Cylinders Arranged in Vertical and Inclined Arrays

This paper highlights the application of fuzzy logic to predict the free convection heat transfer from horizontal isothermal cylinders arranged in vertical and inclined arrays. Experiments included cylinder spacing (center-to-center) varying from 2 to 5 times the cylinder diameter and horizontal spacing ranging from 0 to 2 times the cylinder diameter in inclined array. Also, Rayleigh number based on the cylinder diameter varied from 10 3 to 3×10 3 . It was observed that the increase of cylinder spacing in vertical and inclined array and horizontal spacing in inclined array results in heat transfer increase from the array. Moreover, it was shown that, fuzzy logic is a powerful technique used for predicting the heat transfer due to its low error rate. The average error of fuzzy technique as compared with experimental data was found to be 0.081 % for this study.

Modeling the Free Convection Heat Transfer in a Horizontal Cavity with Flow Diverters Using Adaptive Neuro-Fuzzy Inference System

This paper highlights the application of adaptive neuro-fuzzy inference system (ANFIS) to model the free convection heat transfer in a horizontal cavity with adiabatic vertical and isothermally horizontal walls and adiabatic diverters. The main focus of the present paper is to consider the effects of diverter angle and Rayleigh number variation on average free convection heat transfer in the horizontal cavity. The training data for optimizing the ANFIS structure is obtained experimentally by a Mach-Zehnder interferometer. A hybrid learning algorithm consists of gradient descend method and least-squares method is used for ANFIS training. The proposed ANFIS developed using MATLAB functions. For the best ANFIS structure obtained in this study, the maximum errors of the train and test data were found to be 0.148% and 6.651%, respectively. Also, the mean relative errors of the train and test data were found to be 0.049% and 2.54%, respectively. The predicted results show that ANFIS can predict the experimental results precisely.