Temperature prediction of Soil-Pipe-Air Heat Exchanger using neural networks

In this paper, we use the concept of neural networks to propose an intelligent tool that can we help to evaluate any aspect of earth-to-air heat exchanger. The present study focuses mostly on those aspects related to the passive heating or cooling performance of the building. Two models have been developed for this purpose, namely theoretical and intelligent. The theoretical model is developed by analyzing the energy balance equation in ground whereas the intelligent model is a development of data driven artificial neural networks model. Seven variables influencing the thermal performance of the soil-pipe-air heat exchanger (SPAHE) which are taken into account. Both models are validated against other published model.