COP prediction for the integration of a water purification process in a heat transformer: with and without energy recycling

Abstract

A predictive model for a water purification process integrated in an absorption heat transformer, using an artificial neural network, is proposed in order to obtain on-line predictions of the coefficient of performance (COP). This model takes into account the input and output temperatures for each one of the four components (absorber, generator, evaporator, and condenser), as well as two pressure parameters of the absorption heat transformer and LiBr+H 2O concentrations. Two separate feedforward networks with one hidden layer were used to predict the COP values which increased with energy recycling, and the COP values without energy recycling, respectively. For the networks, the Levenberg-Marquardt learning algorithm, the hyperbolic tangent sigmoid transfer-function and the linear transfer-function were used. The best fitting training data set was obtained with three neurons in the hidden layer, which made it possible to predict COP with accuracy at least as good as that of the experimental error over the whole experimental range. On the validation data set, simulations and experimental data test were in good agreement ( R 2 >0.99). The developed models can be used for a reliable on-line state estimation and control of a water purification process integrated in an absorption heat transformer.