Development of an artificial neural network model based thermal control logic for double skin envelopes in winter

This study proposes an Artificial Neural Network (ANN)-based thermal control method for double skin envelope buildings in winter. A thermal control logic for controlling heating systems and openings on the internal and external envelopes of a double skin building was developed using the ANN-based predictive and adaptive control model. Employing the predicted values for the future indoor air temperature (i.e., the air temperature rise or drop by the next control cycle), the control logic predetermines the operation of the heating system and the opening conditions of internal and external envelopes of a double skin building. After the parametrical optimization of the initial ANN model, the performance of the optimized ANN model was tested for prediction accuracy and adaptability using the data measured from an actual double-skinned envelope building. The analysis results revealed that the ANN model proved its prediction accuracy and adaptability for the different climate conditions and envelope orientations. The developed control logic and model in this study are effectively applied for thermal control of double skinned envelope buildings.