Prediction of thermal conductivity of liquid and vapor refrigerants for pure and their binary, ternary mixtures using artificial neural network

Abstract

The determination of thermophysical properties of hydrofluorocarbons (HFC S) isvery important,especially the thermal conductivity. The present work, investigated the potential of an artificial neural network (ANN) model to correlate the thermal conductivity of (HFC S) at (169.87-533.02) K, (0.047-68.201) MPa and (0.0089-0.1984) W.m.-1 K-1 temperature, pressure and thermal conductivity ranges respectively, of 11systems from 3 different categories including five pure systems(R32, R125, R134a,R152a,R143a),four binary mixtures systems(R32+R125, R32+R134a, R125+ R134a,R125+R143a), and two ternary mixtures systems (R32+R125+ R134a, R125+ R134a+ R143a).Each one received 1817,794and 616 data points, respectively.The application of this model forthese3227 data points of liquid and vapor at several temperatures and pressures allowed to train, validate and test the model. This A c c e p t e d M a n u s c r i p t 2 study showed that ANN models represent a good alternative to estimate the thermal conductivity of different refrigerant systems with a good accuracy. The squared correlation coefficients of thermal conductivity predicted by ANN were R 2 = 0.998with an acceptable level of accuracy of RMSE = 0.0035 and AAD= 0.002 %.The results of applying the trained neural network model to the test data indicate that the method has a highly significant prediction capability.

Modelling Drying Time of Candesartan Cilexetil Powder Using Computational Intelligence Technique

“…This data set will be normalised between [−βγ, (1−β)γ] which leads to the stable convergence of network weights and biases by having all inputs with the same range of values and using premnmx/postmnmx function already programmed in MATLAB software expressed by the following equation: [18][19][20][21] ( ) ( ) ( ) in min max min…”

Artificial Neural Network Model for the Prediction of Thermal Conductivity of Saturated Liquid Refrigerants and n-Alkanes

“…The method proposed by Bridgman is based on the theoretical calculation considering molecular motion and interaction, but there is not both enough accuracy and simple expression. ,, Several methods use group contribution theory. ,− Moreover, some empirical and semiempirical methods such as corresponding-state principle and multiparameter correlation have also been used to predict the thermal conductivity. − …”

“…Recently, many researchers have employed artificial neural networks (ANN) to correlate the thermal properties, such as surface tension, − density, , and in particular thermal conductivity. ,,− Karabulut and Koyuncu exploited the feed-forward ANN model to develop thermal conductivity correlations of propane for the first time. Later, Eslamloueyan and Khademi developed an ANN model to reproduce and predict thermal conductivity at atmospheric pressure for various pure gases.…”

“…Subsequently, Pierantozzi and Petrucci, 28 Ghaderi et al, 30 Ghalem et al, 4 and Wang et al 27 developed ANN models to correlate and predict thermal conductivity for various refrigerants, respectively. However, in the case of the model in ref ( 28 ), the temperature range covered is not wide enough for some refrigerants.…”

Using artificial neural network for predicting heat transfer coefficient during flow boiling in an inclined channel

“…Artificial intelligence is a tool used for modeling the complex phenomenon of heat transfer, the artificial neural networks is one of the techniques of artificial intelligence that can provide useful tools for modeling and correlating practical heat transfer problems, artificial neural network technique has been used by Mohamedi et al [12] for prediction of the transport and thermodynamic properties on saturated vapor and saturated liquid of the water, which are used also for prediction of thermal conductivity of liquid and vapor refrigerants for pure and their binary, ternary mixtures [13], ANN has been used for the prediction of flow boiling of Al 2 O 3 and TiO 2 nanofluids in horizontal tube [14] prediction of pool boiling heat transfer coefficient for various nano-refrigerants [15], prediction of flow boiling curves [16], prediction of the normal boiling point temperature and relative liquid density of petroleum fractions and pure hydrocarbons [17].…”