The purpose of this study was to develop a data-driven predictive model that can predict the supply air temperature (SAT) in an air-handling unit (AHU) by using a neural network. A case study was selected, and AHU operational data from December 2015 to November 2016 was collected. A data-driven predictive model was generated through an evolving process that consisted of an initial model, an optimal model, and an adaptive model. In order to develop the optimal model, input variables, the number of neurons and hidden layers, and the period of the training data set were considered. Since AHU data changes over time, an adaptive model, which has the ability to actively cope with constantly changing data, was developed. This adaptive model determined the model with the lowest mean square error (MSE) of the 91 models, which had two hidden layers and sets up a 12-hour test set at every prediction. The adaptive model used recently collected data as training data and utilized the sliding window technique rather than the accumulative data method. Furthermore, additional testing was performed to validate the adaptive model using AHU data from another building. The final adaptive model predicts SAT to a root mean square error (RMSE) of less than 0.6 °C.
The aim of the present study was to investigate the thermal performance of window systems using full-scale measurements and simulation tools. A chamber was installed on the balcony of an apartment to control the temperatures which can create condensation on the interior surfaces of window systems. The condensation process on the window was carefully scrutinized when outdoor and indoor temperature and indoor relative humidity ranged from −15 °C to −20 °C, 23 °C to 24 °C, and 50% to 65%, respectively. The results of these investigations were analyzed to determine how the moisture is influenced by changing temperatures. It appears that the glass-edge was highly susceptible to the temperature variations and the lowest temperature on the glass edge was caused by the heat transfer through the spacer, between the two glass panels of the window. The results from the simulation used in this study confirm that the thermal performance of window systems can be improved the use of super insulated or thermally broken spacers. If the values of the indoor humidity and temperature are given, then the outdoor temperature when condensation forms can be obtained by using Temperature Difference Ratio (TDR). This methodology can be employed to predict the possible occurrence of condensation.