Mobility has become a substantial part in our society. Since we spend a lot of our available time on the road, we expect the automotive environment to provide similar comfort levels than residential buildings. Within this context, this research thesis especially focuses on automotive thermal comfort control. The automotive cabin is a very special environment, which is characterized by extreme inhomogeneity and overall transient behavior. Thermal comfort is a very vague and a very subjective term, which depends on physiological and psychological variables. Theories for thermal comfort in transient environments have not been fully established yet and researchers are still busy with its investigation. At present, automotive industry relies on extensive thermal comfort models, manikins and powerful simulation tools to assess and control thermal comfort. This thesis studies the application of artificial intelligence and proposes a blackbox approach which aims for extracting thermal comfort knowledge directly from human's interaction with the HVAC controls. This methodology avoids the use of human physiological and psychological thermal comfort models and does not require any a-priori knowledge. A novel comfort acquisition tool has been developed and has been integrated into a research vehicle in order to gather the required data for system learning. Data has been collected during spring, autumn and summer conditions in Southern Africa. Methods of data mining have been applied and an intelligent implementation using artificial neural networks has been proposed. The achieved results are promising and allow for about 87 perecent correct classification. It is concluded that methods of artificial intelligence perform well and are far superior compared to conventional approaches. These methods can be used as a powerful tool for the development process of vehicle air-conditioning controls and have great potential for time and cost reduction.
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:nmmu/vital:9645 |
| Date | January 2011 |
| Creators | Kranz, Jürgen |
| Publisher | Nelson Mandela Metropolitan University, Faculty of Engineering, the Built Environment and Information Technology |
| Source Sets | South African National ETD Portal |
| Language | English |
| Detected Language | English |
| Type | Thesis, Doctoral, PhD |
| Format | xiii, 196 leaves, pdf |
| Rights | Nelson Mandela Metropolitan University |
Page generated in 0.0024 seconds