This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
A New Method Using Neural Networks to Evaluate the Transitional Thermal Sensation of an Automobile Occupant
Annotation ability available
Sector:
Language:
English
Abstract
The objects of this work is to develop a method of evaluating the thermal sensation of an automobile occupant and predicting its transition for the development of a new control system for automobile air-conditioners. An automobile air-conditioner is designed only to control the air-temperature of a passenger compartment. However, The most important factor in controlling automobile air-conditioner is the thermal amenity for occupants when an air-conditioner is controlled. For the control of the thermal amenity, it is necessary to quantitatively evaluate the thermal sensation of occupants.
This paper presents a new method using neural networks, which was developed to evaluate the thermal sensation of an automobile occupant and to predict its transition from the occupant's skin temperature and temperature of the passenger compartment. Experiments were performed in an environmental chamber. Subjects with supplied clothes and thermocouples on their faces took automobile seats and voted their thermal sensation. The results showed an accuracy within 0.5 of the voting scales used. This accuracy is high enough to control an air-conditioner.
Recommended Content
Authors
Citation
Ueda, M., Ohno, Y., Taniguchi, Y., and Aoki, H., "A New Method Using Neural Networks to Evaluate the Transitional Thermal Sensation of an Automobile Occupant," SAE Technical Paper 920217, 1992, https://doi.org/10.4271/920217.Also In
References
- Moderate Thermal Environments-Determination of the PMV and PPD indices and Specification of the Conditions for Thermal Comfort International Standard Organization Geneva 1984
- Hensel, h. Thermoreception and Temperature Regulation Academic Press London 1981
- Sejnowski, T.j. Rosenberg, C.R Parallel Networks that Learn to Pronounce English Text Complex System 1 1987 145 168
- Rumelhart, D.H. Hinton, G.E. Williams, R.J. Learning representation by back-propagation errors Nature 322 1986 533 536