Skip to main content

Research Repository

Advanced Search

Deep learning and computer vision based occupancy CO2 level prediction for demand-controlled ventilation (DCV)

Wei, Shuangyu; Tien, Paige Wenbin; Chow, Tin Wai; Wu, Yupeng; Calautit, John Kaiser

Authors

Shuangyu Wei

Paige Wenbin Tien

Tin Wai Chow

YUPENG WU yupeng.wu@nottingham.ac.uk
Professor of Building Physics



Abstract

The present study investigated the potential of the application of a live occupancy detection approach to assist the operations of demand-controlled ventilation (DCV) systems to ensure that sufficient interior thermal conditions and air quality were attained while reducing unnecessary building energy loads to improve building energy performance. Faster region-based convolutional neural network (RCNN) models were trained to detect the number of people and occupancy activities respectively, and deployed to an artificial intelligence (AI)-powered camera. Experimental tests were carried out within a case study room to assess the performance of this approach. Due to the less complexity of people counting model, it achieved an average intersection over union (IoU) detection accuracy of about 98.9%, which was higher than activity detection model of about 88.5%. During the detection, the count-based occupancy profiles were produced according to the real-time information about the number of people and their activities. To estimate the effect of this approach on indoor air quality and energy demand, scenario-based modelling of the case study building under four ventilation scenarios was carried out via building energy simulation (BES). Results showed that the proposed approach could provide demand-driven ventilation controls data on the dynamic changes of occupancy to improve the indoor air quality (IAQ) and address the problem of under- or over-estimation of the ventilation demand when using the static or fixed profiles.

Citation

Wei, S., Tien, P. W., Chow, T. W., Wu, Y., & Calautit, J. K. (2022). Deep learning and computer vision based occupancy CO2 level prediction for demand-controlled ventilation (DCV). Journal of Building Engineering, 56, Article 104715. https://doi.org/10.1016/j.jobe.2022.104715

Journal Article Type Article
Acceptance Date May 28, 2022
Online Publication Date May 31, 2022
Publication Date Sep 15, 2022
Deposit Date Jun 23, 2022
Publicly Available Date Jun 23, 2022
Journal Journal of Building Engineering
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 56
Article Number 104715
DOI https://doi.org/10.1016/j.jobe.2022.104715
Keywords Mechanics of Materials; Safety, Risk, Reliability and Quality; Building and Construction; Architecture; Civil and Structural Engineering
Public URL https://nottingham-repository.worktribe.com/output/8633356
Publisher URL https://www.sciencedirect.com/science/article/pii/S2352710222007288
Additional Information This article is maintained by: Elsevier; Article Title: Deep learning and computer vision based occupancy CO2 level prediction for demand-controlled ventilation (DCV); Journal Title: Journal of Building Engineering; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.jobe.2022.104715; Content Type: article; Copyright: © 2022 The Authors. Published by Elsevier Ltd.

Files







You might also like



Downloadable Citations