Modeling of Heat Transfer in Cisterns Using Artificial Neural Networks

Abstract

Nomenclature a = output of the transfer function a j k = Jth element of the artificial neural network's output related with input vector Pk a q = network's output for p q a 0 = input of the first layer B = y intercept of the regression line in the scatter plot b = bias e j k = Jth element of the error ways of Fk = summation of the error in the Kth frequency f = transfer function of the layer M = regression line slope in the scatter plot perf = neural network's performance function (sum of squared error) P i = input vector of the network R = correlation coefficient between the artificial neural network's output and observation S L = number of neurons in layer L T i = target vector for input P i t j k = Jth element of the target vector related with input vector Pk ! = weight matrix of each layer Subscript J = Jth element of the answer network Superscript L = number of network layers

Experimental and theoretical investigation of thermal performance of underground cold-water reservoirs

“…It was observed that a stable thermal stratification develops during the storage phase and preserved during the withdrawal cycle. In a recent study, Madoliat et al [6] investigated the thermal behavior of a longterm cold-water underground reservoir using the Artificial Neural Networks. Their results also show that a stable thermal stratification develops in the water inside the reservoir.…”

Performance Evaluation of a Modular Design of Wind Tower with Wetted Surfaces

“…For centuries, people living in the Middle East have used various passive cooling systems to provide pleasant cool air [1][2][3][4][5] and cold drinkable water [6][7][8][9][10][11][12][13][14][15] during the hot summer months. One of these systems is the wind tower, or wind catcher, which creates passive ventilation and provides thermal comfort for the building inhabitants.…”