Lumped Model Versus Data-Driven Model for Prediction of Particulate Matter for Two School Buildings

This paper presents a prediction approach for indoor particulate matter (PM2.5, PM10) of two school gyms using a lumped model and an artificial neural network model. The aforementioned two models were developed based on the measurement data including indoor/outdoor PM2.5 & PM10 sensors, on/off status of energy recovery ventilators, and CCTV images of occupants. As a result, the artificial neural network and the lumped model had an accuracy within MBE 13.6% and −0.1% and CVRMSE 29.9%, 18%, respectively. It was found that indoor particulate matter was influenced by the outdoor particulate matter, indoor relative humidity, the number of occupants, and the degree of indoor activity. It is suggested that the model predictive control of the ventilators should be performed for better IAQ.