Simultaneous in-situ calibration for physical and virtual sensors towards digital twin-enabled building operations

Digital twin-enabled building operations heavily rely on a building sensor network to collect operational data. Virtual sensing, in combination with physical sensors, has great potential in establishing a reliable and informative sensing environment. However, physical sensors can experience hardware errors or systematic errors due to the working environment within building systems. Virtual sensors are also subject to their model uncertainties arising from input physical sensor errors and changes in system operations. These virtual sensor errors have a negative effect on the in-situ calibration accuracy of corresponding physical sensors. To address these issues, this study proposes a simultaneous in-situ calibration (SIC) method designed to calibrate multiple physical and virtual sensors with varying errors in the context of digital twins. The SIC problem is mathematically formulated, including two types of distance functions (direct and indirect) and defining correction functions to calibrate various types of virtual sensors (such as backup, validation, replacement/virtualization, and observation sensors). Importantly, the proposed method tackles the challenges posed by the unknown calibration environment in operational systems. A field application study was conducted for two physical sensors and three different virtual sensors operating in a district heating substation serving real residential buildings in Korea. The case study shows how the different calibration accuracies for each sensor depend on the calibration approaches, such as physicaltargeted (existing Case 1), virtual-targeted (existing Case 2), and simultaneous calibration (novel Case 3). Under the simultaneous errors, only Case 3 satisfied the reference accuracy for all sensors. Specifically, the average MAEs in Case 3 were improved by approximately 79.3%, 75.3%, 63.9%, and 87.5% for the target physical sensor, backup virtual sensor, virtualized sensor, and validation virtual sensor, respectively, compared to the accuracies before calibration. These results demonstrate the importance and effectiveness of simultaneous in-situ calibration of physical and virtual sensors in digital twin-enabled building operations. The proposed calibration can contribute to the synchronization of physical and virtual building systems, thus achieving reliable and informative virtual sensing-driven digital twins.