Machine learning-based personal thermal comfort model for electric vehicles with local infrared radiant warmers
Thermal comfort of occupants in conventional vehicles driven by an internal combustion engine is controlled by heating, ventilation, and air conditioning (HVAC) system. However, the operation of a conventional HVAC system decreases the mileage of electric vehicle (EV) in the heating mode by nearly 5...
Saved in:
Published in | Journal of mechanical science and technology Vol. 35; no. 7; pp. 3239 - 3247 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Seoul
Korean Society of Mechanical Engineers
01.07.2021
Springer Nature B.V 대한기계학회 |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Thermal comfort of occupants in conventional vehicles driven by an internal combustion engine is controlled by heating, ventilation, and air conditioning (HVAC) system. However, the operation of a conventional HVAC system decreases the mileage of electric vehicle (EV) in the heating mode by nearly 50 %. Thus, local radiant heating was proposed as a heating strategy to reduce electric energy consumption while providing reasonable thermal comfort. In this work, we developed a personalized overall thermal sensation (OS) model using machine learning to evaluate the thermopsychological effect of local radiant heating and simulate the OS of occupants in EVs. Data were obtained from a real EV that went through a cold environmental chamber and were evaluated using random forest algorithm. By considering individual thermal preferences of occupants, we predicted the OS for each subject with higher accuracy by a factor of 2.6 compared with the prediction performed using the weighted average method. Total energy consumption was reduced by approximately 10 % in the EV equipped with local infrared radiant warmers while providing OS that was comparable with that of the HVAC system. |
---|---|
ISSN: | 1738-494X 1976-3824 |
DOI: | 10.1007/s12206-021-0644-7 |