Development of the digital-twin for building facilities (Part 1): Verification of predictive accuracy of ANN models for heat source system based on operation data

We evaluated the building method of ANN models targeting the heat source system operated. As the result, the finding and issue are as follows. 1. It was suggested that building facilities models with high predictive accuracy is available to realize by ANN models based on operation data. 2. There is trade-off between predictive accuracy and calculation time, the ANN model with well-balance has hidden layers of 50-50, and mini-batch size of 64. 3. Predictive accuracy of gas and power consumption are lower than others, it is considered that more complex ANN models are needed to improve the predictive accuracy. © 2020 Architectural Institute of Japan. All rights reserved.