Experimental investigation of influence of phase change materials in energy consumption of air-conditioning units and prediction performance evaluation of modified deep neural network model

Abstract

In this study, the influence of hybrid phase change materials on the energy consumption of air-conditioning units installed to maintain a comfortable temperature inside the testing room was experimentally studied and numerically analyzed. The Paraffin, Halloysite and Ethylene glycol microcapsules were combined to form PHEg filler materials. These PHEg phase change materials were further mixed into a normal Portland cement mortar to prepare 5 different phase change material mortars. Based on the prepared motors, a pair of 1.22 m × 1.22 m × 0.2 m size test specimens were prepared to experiment. After testing the specimens with various outside temperatures, the energy consumed by an air-conditioning unit was reported. There was a 20–22% reduction in energy consumption recorded while testing with phase change material mortar specimens than normal cement mortar. Also, the results proved that the energy consumption of the air-conditioning unit could be reduced further by 10% when the outdoor temperature dropped to below 24 °C. In addition, the performances of prepared samples were predicted using a modified deep neural network model. The developed model accumulated 99.867% accuracy and a maximum of 0.1607 mean absolute error and 0.0172 root mean square error, better than several existing neural network models.