Predicting Parameters of Heat Transfer in a Shell and Tube Heat Exchanger Using Aluminum Oxide Nanofluid with Artificial Neural Network (ANN) and Self-Organizing Map (SOM)

Abstract

This study is a model of artificial perceptron neural network including three inputs to predict the Nusselt number and energy consumption in the processing of tomato paste in a shell-and-tube heat exchanger with aluminum oxide nanofluid. The Reynolds number in the range of 150–350, temperature in the range of 70–90 K, and nanoparticle concentration in the range of 2–4% were selected as network input variables, while the corresponding Nusselt number and energy consumption were considered as the network target. The network has 3 inputs, 1 hidden layer with 22 neurons and an output layer. The SOM neural network was also used to determine the number of winner neurons. The advanced optimal artificial neural network model shows a reasonable agreement in predicting experimental data with mean square errors of 0.0023357 and 0.00011465 and correlation coefficients of 0.9994 and 0.9993 for the Nusselt number and energy consumption data set. The obtained values of eMAX for the Nusselt number and energy consumption are 0.1114, and 0.02, respectively. Desirable results obtained for the two factors of correlation coefficient and mean square error indicate the successful prediction by artificial neural network with a topology of 3-22-2.

Heat exchanger design considering variable overall heat transfer coefficient: An artificial neural network approach

“…The Reynolds number, temperature, and nanoparticle concentration were selected to train an ANN that considers 22 neurons in the hidden layer to predict the energy consumption and Nusselt number in shell and tube heat exchanger. 26 Along the same timeline, research on deep learning has increased dramatically in the last 2 years. 27 define Deep Neural Networks as ANNs obtained by means of the composition of simple functions, the mathematical function is fully connected where each neuron is connected to all neurons in adjacent layers.…”

“…6. In recent years, the radial basis transfer function was used to train ANN models, some examples are shown in Maddah et al 25 and Zolghadri et al 26 This article aims to introduce a new perspective, called the ANN, which allows us to calculate the heat transfer area considering the assumption of variable overall heat transfer coefficient.…”

“…Then Maddah, 25 used a different strategy, the authors uses an ANN model to predict the exergetic efficiency of a U‐shaped heat exchanger, the Levenberg–Marquardt method is used to optimize the adjustment parameters in the hidden layer considering seven neurons; for the evaluation, the use of convective coefficients was not reported, special emphasis was placed on the thermal‐physical properties of the hybrid Cu/CNTs water‐based nanofluids. The Reynolds number, temperature, and nanoparticle concentration were selected to train an ANN that considers 22 neurons in the hidden layer to predict the energy consumption and Nusselt number in shell and tube heat exchanger 26 …”

“…However, the impact of this prediction on the calculation of transfer area under conditions of variable U has not yet been considered. In recent years, the radial basis transfer function was used to train ANN models, some examples are shown in Maddah et al 25 and Zolghadri et al 26 …”

“…In recent years, the radial basis transfer function was used to train ANN models, some examples are shown in Maddah et al 25 and Zolghadri et al 26 …”