A long short-term memory physics-informed neural network model for CO2-based natural ventilation rate estimation

The occupant-released CO2 tracer gas approach has been widely used for ventilation rate estimation. This approach is non-invasive, low-cost, and does not interfere with the occupants’ activities. However, the CO2 measurement noise and CO2 generation uncertainties can significantly affect the accurac...

ver descrição completa

Detalhes bibliográficos
Autores: Miao, Sen|||0000-0003-0266-9405, Gangolells Solanellas, Marta|||0000-0001-7921-595X, Tejedor Herrán, Blanca|||0000-0002-2064-0617
Tipo de documento: artigo
Data de publicação:2025
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/446502
Acesso em linha:https://hdl.handle.net/2117/446502
https://dx.doi.org/10.1016/j.jobe.2025.114094
Access Level:Acceso aberto
Palavra-chave:Natural ventilation rate
CO2 tracer gas
Kalman filter
Long short-term memory
Physics-informed neural network
Àrees temàtiques de la UPC::Edificació::Instal·lacions i acondicionament d'edificis::Instal·lacions de ventilació
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Descrição
Resumo:The occupant-released CO2 tracer gas approach has been widely used for ventilation rate estimation. This approach is non-invasive, low-cost, and does not interfere with the occupants’ activities. However, the CO2 measurement noise and CO2 generation uncertainties can significantly affect the accuracy of the estimated ventilation rates, while the dynamics of the natural ventilation rates could challenge the stability of the estimators. As commonly applied techniques, the moving average filter and the extended Kalman filter have their own advantages and limitations in addressing these issues. To further address the challenges in the natural ventilation rate estimation, this paper proposes a novel model named “NVR-PINN”, based on the long short-term memory-physics-informed neural network and validates it with a case study. The proposed model combines the strengths of the moving average filter and the extended Kalman filter, demonstrating better practical values. It is capable of handling both CO2 measurement noise and CO2 generation uncertainty, effectively capturing the temporal dynamics of the natural ventilation rate, while processing the entire time series observation with a defined sequence window to yield more stable and consistent estimates. The analysis of the case study also revealed useful evidence for relevant research with regard to the applicability of existing ventilation rate estimation techniques.