An intelligent climate monitoring system for hygrothermal virtual measurement in closed buildings using Internet-of-things and artificial hydrocarbon networks.

Studies analyzing indoor thermal environments comprising temperature and humidity may be insufficient when obtaining data from sensors, which may be susceptible to inaccurate or failed information from internal and external factors. Therefore, this study proposes an intelligent climate monitoring using a supervised learning method for virtual hygrothermal measurement in enclosed buildings used to predict temperature and relative humidity when a sensor failure is detected. The methodology comprises the data collection from a wireless sensor network, the building of the learning model for predicting the dynamics of environmental variables, and the implementation of a sensor failure detection model. We use an artificial hydrocarbon network as the learning model for their simplicity and effectiveness under uncertain and noisy data. The experiments use data acquired in two settings: (1) a laboratory office and (2) a museum storage room. The first scenario has multiple workstations, and the staff turns on or off the air conditioning depending on the feeling of comfort, generating an uncontrolled environment for the variables of interest. The second scenario has controlled temperature and humidity to ensure the conservation conditions of the museum pieces. Both scenarios used 12 sensors that acquired data for one month, providing an average of 58,300 values for each variable. Results of the proposed methodology provide 95% of accuracy in terms of sensor failure detection and identification, and less than 0.22% of tolerance variability in temperature and humidity after sensor accommodation in both scenarios.