Abstract
The main purpose of tunnel ventilation system is to maintain CO pollutant concentration and VI (visibility index) under an adequate level to provide drivers with comfortable and safe driving environment. Moreover, it is necessary to minimize power consumption used to operate ventilation system. To achieve these purposes, FLC (fuzzy logic controller) has been usually utilized because complex and nonlinear system like tunnel ventilation is difficult to control with conventional quantitative methods. Membership functions of FLC consist of inputs such as pollutant level inside tunnel, pollutant emission rates from vehicles, and outputs, the number of running jet-fans. The conventional fuzzy control methods have been designed just by relying on simple experiences and using trial and error method. In this paper, FLC is optimally redesigned using GA (genetic algorithm) which is a stochastic global search method. In the process of constructing objective function of GA, maintaining pollutant concentration level under allowable limit and decreasing energy consumption are included. Finally, the simulation results performed with real data collected from the target tunnel ventilation system are shown. It is confirmed that the GA-based FLC shows more efficient performance than the conventional FLC.
Original language | English |
---|---|
Publication status | Published - 2005 |
Event | 22nd International Symposium on Automation and Robotics in Construction, ISARC 2005 - Ferrara, Italy Duration: 2005 Sept 11 → 2005 Sept 14 |
Other
Other | 22nd International Symposium on Automation and Robotics in Construction, ISARC 2005 |
---|---|
Country/Territory | Italy |
City | Ferrara |
Period | 05/9/11 → 05/9/14 |
Keywords
- FLC (fuzzy logic controller)
- Real-valued GA (genetic algorithm)
- Tunnel ventilation control
ASJC Scopus subject areas
- Artificial Intelligence
- Human-Computer Interaction
- Building and Construction