Virtual measurement of the air properties in air-handling units (AHUs) or virtual re-calibration of sensors

Abstract

Heating ventilation, and air-conditioning (HVAC) systems in North America are major users of energy in commercial and institutional buildings. Although modern monitoring strategies allow for energy waste reduction and building performance optimization, the poor quality or absence of measurements may compromise those strategies. Virtual sensors can provide measurements where physical sensors are not installed (virtual measurement) or can replace the faulty sensors (virtual re-calibration). The paper presents three different methods with different goals. Method A that is based on a physically-based model is applied to virtually re-calibrate one faulty temperature sensor of outdoor air temperature. Methods B and C, which are based on data-driven models, require additional short-term measurements with portable calibrated sensors. Method B is used for the virtual measurement of two physical variables (temperature and relative humidity). Method C is used for the re-calibration of one faulty sensor. The three methods use measurements from the building automation systems (BAS) of a university building. Methods A and B effectively correct the faulty measurements of the outdoor air properties as the mean absolute error (MAE) does not exceed the correspondent uncertainty. The virtual re-calibration capability of Method C varies between the training and validation periods as a consequence of the variation of weather conditions.