Estimating\nAir Change Rate in Mechanically Ventilated\nClassrooms Using a Single CO<sub>2</sub> Sensor and Automated Data\nSegmentation

With\na growing emphasis on indoor air quality (IAQ) in educational\nenvironments, CO<sub>2</sub> monitoring in classrooms has become commonplace.\nCO<sub>2</sub> data can be used to estimate outdoor air change rate\n(ACH) based on the mass balance principle, which can be further linked\nto human health, performance, and building energy consumption. This\nstudy used a novel machine learning method to automatically segment\nCO<sub>2</sub> concentration time series data into build-up, equilibrium,\nand decay periods, and then estimated classroom ACH using the corresponding\nCO<sub>2</sub> mass balance equations. This method, applied to 40\nclassrooms in two mechanically ventilated K-6 schools, generated up\nto ten ACH estimates per day per classroom. A comparison with ACH\ncalculated using the mechanical ventilation rates with 100% outdoor\nair reported by the building automation system during the study period\nreveals a slight underestimation by the decay and build-up methods,\nwhile the equilibrium method produced closer estimates. These differences\nmay be attributed to uncertainties in occupancy, activity, CO<sub>2</sub> emission rates, and air mixing. This research underscores\nthe potential of leveraging CO<sub>2</sub> data for more comprehensive\nIAQ assessments and highlights the challenges associated with accurately\nestimating ACH in real-world settings.