A Smart CO2-Based Ventilation Control Framework to Minimize the Infection Risk of COVID-19 In Public Buildings
Document Type
Conference Proceeding
Publication Date
1-1-2022
Abstract
This study aims to present a smart ventilation control framework to reduce the infection risk of COVID-19 in indoor spaces of public buildings. To achieve this goal, an artificial neural network (ANN) was trained based on the results from a parametric computational fluid dynamics (CFD) simulation to predict the COVID-19 infection risk according to the zone carbon dioxide (CO2) concentration and other information (e.g., zone dimension). Four sample cases were analyzed to reveal how the CO2 concentration setpoint was varied for a given risk level under different scenarios. A framework of smart ventilation control was briefly discussed based on the ANN model. This framework could automatically adjust the system outdoor airflow rate and variable air volume (VAV) terminal box supply airflow rate to meet the needs of reducing infection risk and achieving a good energy performance.
Publication Source (Journal or Book title)
Building Simulation Conference Proceedings
First Page
3473
Last Page
3482
Recommended Citation
Pang, Z., Hu, P., Lu, X., Wang, Q., & O'Neill, Z. (2022). A Smart CO2-Based Ventilation Control Framework to Minimize the Infection Risk of COVID-19 In Public Buildings. Building Simulation Conference Proceedings, 3473-3482. https://doi.org/10.26868/25222708.2021.30299