In situ virtual sensors in building digital twins: framework and methodology

A novel sensing system is essential for intelligent building operations and digitalization of the building life cycle. Therefore, this study introduces the concept and framework of in situ virtual sensing in building operations, proposes modeling methodologies for in situ virtual sensors, and shows the applications of representative virtual sensors in a real operational system. The concept of in situ virtual sensing involves virtual sensors that are built, operated, verified/validated, and calibrated in operational buildings and the digital twins. Considering the virtual sensor purposes and available modeling resources, modeling methodologies are proposed to achieve the virtual sensing under limited modeling environments in the target building operation. Case studies showed an RMSE of approximately 0.5 degrees C during the winter season in the real buildings without experimental modeling environments (such as laboratory and manufacturing facilities). According to the findings and results, this study can contribute by providing in-depth insight into virtual sensing-driven building operations, digitalization, and intelligence.