Optimization of an absorption heat transformer with two-duplex components using inverse neural network and solved by genetic algorithm

Abstract

An artificial neural network (ANN) model was developed to predict the coefficient of performance (COP) of an absorption heat transformer with a new physical design consisting of compact components, and its inverse (ANNi) was used to optimize the system's performance, coupled for the water purification. This ANN model takes into account the input and output temperature (T) of each duplex component (generator-condenser and evaporator-absorber), as well as the concentration of solution LiBr–H2O (X), pressure (P) and mass flow (ṁ). The best fitting training data was acquired with 16–7–1 considering a hyperbolic tangent sigmoid transfer-function in the hidden layer and a linear transfer-function in the output. Comparing the predicted and experimental data it was observed a satisfactory agreement (R2 > 0.9969 and MPE ∼ 3%). Furthermore, from this ANN model, a strategy was developed for optimization of a generator and an evaporator input temperatures using inverse artificial neural networks (ANNi) and solved by the method of genetic algorithms (GAs). The good prediction of the ANN model, as well as the optimized data using ANNi-GAs, makes it possible to control on-line the operation of the system, increasing the value of COP.