Work

Soft sensor development for local temperature prediction in a dual-diffuser shared room under heating conditions

Year: 2026
Type: article
Abstract: Recently, increasing attention has been paid to occupant-centric HVAC control in shared spaces, which are typically equipped with multiple diffusers. Such control requires local thermal information that a single return-air measurement cannot provide. To obtain the temperature around occupants, a gray-box soft-sensor model has been developed in this study by adapting a single-diffuser model. A dual-diffuser room, the most basic multi-supply configuration, was investigated. Water-based experiments were conducted using two supply nozzles to reproduce indoor thermo-hydrodynamics in the heating mode, including thermally stratified conditions, at a constant total flow rate. Seven combinations of supply temperatures and flow rates were tested to evaluate model accuracy. The results show that predictive accuracy is sensitive to supply-temperature combinations, whereas the flow-rate allocation under a fixed total flow rate has only a minor influence. The model demonstrates physical interpretability and training efficiency while its generalization capability requires the training conditions to span the supply-temperature combinations of interest. The proposed soft-sensor model facilitates the development of occupant-centric HVAC control strategies and supports energy-efficient HVAC operation in shared spaces.
Language: English
Open Access status: hybrid
Estimated APC paid: $3,000
OpenAlex ID: W7225987251
FWCI:
Cites: 29
Cited by:
Related to: 10