An overall exergy analysis of glass-tedlar photovoltaic thermal air collector incorporating thermoelectric cooler: A comparative study using artificial neural networks

Abstract

In this research, a three-layer feed-forward artificial neural network (ANN) model has been developed for glass-tedlar photovoltaic thermal (PVT) air collector incorporating thermoelectric cooler (TEC). The ANN model is used for estimating the fluctuating outputs of the glass-tedlar PVT-TEC air collector, i.e. thermal energy gain, electrical energy gain, overall thermal energy gain and overall exergy gain, as a result of intermittent and varying weather conditions. The traditional modelling techniques, used for predicting the output performances of a PVT system, rely on analysis of complex relationships between different components of PVT collector, solution of differential equations and several design parameters. ANN model, however, aids in approximating the outputs by learning through training examples and hence, does not involve complex analysis and calculations. The developed ANN model is based on global solar radiation, diffuse solar radiation and ambient temperature, as inputs. Further, the outputs of glass-tedlar PVT-TEC air collector [Case I] are compared against glass-glass PVT-TEC air collector [Case II], using ANN model. The monthly and annual outputs of glass-tedlar PVT-TEC air collector [Case I] have been estimated for New Delhi, India. Also, a comparison between the annual results of Case I and Case II, obtained using ANN model, has been presented.