Artificial neural networks for predicting the performance of heat pumps with horizontal ground heat exchangers

Autor: Yu Zhou, Guillermo Narsilio, Nikolas Makasis, Kenichi Soga, Peng Chen, Lu Aye
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: Frontiers in Energy Research, Vol 12 (2024)
Druh dokumentu: article
ISSN: 2296-598X
DOI: 10.3389/fenrg.2024.1423695
Popis: A Ground Coupled Heat Pump (GCHP) is a highly energy efficient heating, ventilation, and air conditioning (HVAC) system that utilises the ground as the heat source when heating and as the heat sink when cooling. This paper investigates GCHP systems with horizontal Ground Heat Exchangers (GHEs) in the rural industry, exemplifying the technology for poultry (chicken) sheds in Australia. This investigation aims to provide an Artificial Neural Network (ANN) model that can be used for GCHP design at various locations with different climates. To this extent, a Transient System Simulation Tool (TRNSYS) model for a typical horizontal GHE applied in a rural farm was first verified. Using this model, over 700,000 hourly performance data items were obtained, covering over 80 different yearly loading patterns under three different climate conditions. The simulated performance data was then used to train the ANN. As a result, the trained ANN can predict the performance of GCHP systems with identical (multiple) GHEs even under climatic conditions (and locations) that have not been specifically trained for. Unlike other works, the newly introduced ANN model is accurate even with limited types of input data, with high accuracy (less than 5% error in most cases tested). This ANN model is 100 times computationally faster than TRNSYS simulations and 10,000 times faster than finite element models.
Databáze: Directory of Open Access Journals