Uncertainties in neural network model based on carbon dioxide concentration for occupancy estimation

다국어 초록 (Multilingual Abstract)

Demand control ventilation is employed to save energy by adjusting airflow rate according to the ventilation load of a building. This paper investigates a method for occupancy estimation by using a dynamic neural network model based on carbon dioxide concentration in an occupied zone. The method can be applied to most commercial and residential buildings where human effluents to be ventilated. An indoor simulation program CONTAMW is used to generate indoor CO 2 data corresponding to various occupancy schedules and airflow patterns to train neural network models. Coefficients of variation are obtained depending on the complexities of the physical parameters as well as the system parameters of neural networks, such as the numbers of hidden neurons and tapped delay lines. We intend to identify the uncertainties caused by the model parameters themselves, by excluding uncertainties in input data inherent in measurement. Our results show estimation accuracy is highly influenced by the frequency of occupancy variation but not significantly influenced by fluctuation in the airflow rate. Furthermore, we discuss the applicability and validity of the present method based on passive environmental conditions for estimating occupancy in a room from the viewpoint of demand control ventilation applications.

참고문헌 (Reference)

1 ASHRAE, "Ventilation for acceptable indoor air quality"

2 N. Nassif, "Ventilation control strategy using the supply CO2 concentration setpoint" 11 (11): 239-262, 2005

3 Y. P. Ke, "Using carbon dioxide measurements to determine occupancy for ventilation controls"

4 A. Persily, "Simulations of indoor air quality and ventilation impacts of demand controlled ventilation in commercial and institutional buildings" NISTIR 1-36, 2003

5 H. Han, "Occupancy estimation based on CO2 concentration using dynamic network model" 2013

6 K. P. Lam, "Occupancy detection through an extensive environmental sensor network in an open-plan office building" 1452-1459, 2009

7 G. P. Zhang, "Neural network forecasting for seasonal and trend time series" 160 (160): 501-514, 2005

8 D. Johansson, "Measurements of occupancy levels in multi-family dwellings-application to demand controlled ventilation" 43 (43): 2449-2455, 2011

9 KEITI, "Indoor environment management technology trends of building based on eco-energy" KEITI 77-, 2012

10 A. Ebadat, "Estimation of building occupancy level through environment signals deconvolution" 13 : 1-8, 2013

11 S. Ogasawara, "Effect of energy conservation by controlled ventilation : case study in a department store" 2 (2): 3-8, 1979

12 T. Kusuda, "Control of ventilation to conserve energy while maintaining acceptable indoor air quality" 82 : 1169-1181, 1976

13 W. S. Dols, "CONTAMW 1.0 user manual : multizone airflow and contaminant transport analysis software" NISTIR 2000

14 S. T. Taylor, "CO2-based DCV using 62. 1-2004" 48 : 67-75, 2006

15 M. O. Ng, "CO2-Based demand controlled ventilation under new ASHRAE Standard 62.1-2010: A case study for a gymnasium of an elementary school at west Lafayette" 43 (43): 3216-3225, 2011

16 W. J. Fisk, "CO2 monitoring for demand controlled ventilation in commercial buildings" LBNL 42-43, 2010

17 S. A. Kalogirou, "Applications of artificial neural-networks for energy systems" 67 (67): 17-35, 2000

18 B. Dong, "An information technology enabled sustainability test-bed(ITEST)for occupancy detection through an environmental sensing network" 42 (42): 1038-1046, 2010

19 X. Xu, "An adaptive demand-controlled ventilation strategy with zone temperature reset for multi-zone airconditioning systems" 16 (16): 426-437, 2007

20 Z. Yang, "A multisensor based occupancy estimation model for supporting demand driven HVAC operations" 2 : 98-105, 2012