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

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.

Authors

Institutions

Publication Details

Journal
Thermal Science and Engineering Progress
Published
2026-11-13
DOI
https://doi.org/10.1016/j.tsep.2026.105007
Primary Topic
Building Energy and Comfort Optimization
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Daisuke Satou, Ruizi Zhang, Yasuki Kansha, Jinxin Wang et al.
Thermal Science and Engineering Progress
Building Energy and Comfort Optimization
article

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

Daisuke Satou, Ruizi Zhang, Yasuki Kansha, Jinxin Wang, Hiroaki Kanayama, Hisashi Takahashi, Yuka Sakai
article en

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.

Thermal Science and Engineering ProgressVol. 80
Daikin (Japan) (JP), The University of Tokyo (JP)
New Energy and Industrial Technology Development Organization
Building Energy and Comfort Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon